{ "families": [ { "alphafold_models": 19000, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family is unknown.", "domain_architectures": 25, "interpro_id": "IPR007278", "known_evidence_count": null, "matches": 40691, "name": "Domain of unknown function (DUF397)", "partial_evidence_count": null, "pfam_id": "PF04149", "proteins": 37657, "proteomes": 1831, "short_name": "DUF397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04149", "structures": 0, "taxa": 2162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19007, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a putative ligand binding domain found in bacterial transcription regulators that have an N-terminal HTH domain [pfam:PF13560].", "domain_architectures": 42, "interpro_id": "IPR043917", "known_evidence_count": null, "matches": 37543, "name": "Domain of unknown function (DUF5753)", "partial_evidence_count": null, "pfam_id": "PF19054", "proteins": 37511, "proteomes": 1857, "short_name": "DUF5753", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19054", "structures": 0, "taxa": 2194, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19995, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of prokaryotic proteins have no known function. [swissprot:P71138] a protein of unknown function in the family has been misannotated as alpha-dextrin 6-glucanohydrolase.", "domain_architectures": 45, "interpro_id": "IPR002881", "known_evidence_count": null, "matches": 31548, "name": "Protein of unknown function DUF58", "partial_evidence_count": null, "pfam_id": "PF01882", "proteins": 31251, "proteomes": 13552, "short_name": "DUF58", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01882", "structures": 0, "taxa": 18964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15881, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain contains several highly conserved charged amino acids, suggesting this may be an enzymatic domain (Bateman A pers. obs). The entry includes SanA [swissprot:P33017] and Sfix ([swissprot:O33790]) from Salmonella typhimurium which are involved in Vancomycin resistance [[cite:PUB00019464]]. These proteins may be involved in murein synthesis [[cite:PUB00019465]]. This domain is found in Escherichia coli YdcF, which has been shown to bind S-adenosyl-L-methionine (AdoMet), but whose biochemical function has not been identified [[cite:PUB00050945]].", "domain_architectures": 92, "interpro_id": "IPR003848", "known_evidence_count": null, "matches": 25685, "name": "DUF218 domain", "partial_evidence_count": null, "pfam_id": "PF02698", "proteins": 25685, "proteomes": 14217, "short_name": "DUF218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02698", "structures": 1, "taxa": 20830, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 16566, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C terminus of the YchF GTP-binding protein ([swissprot:O13998]) and is possibly related to the ubiquitin-like and MoaD/ThiS superfamilies.", "domain_architectures": 137, "interpro_id": "IPR013029", "known_evidence_count": null, "matches": 23716, "name": "Protein of unknown function (DUF933)", "partial_evidence_count": null, "pfam_id": "PF06071", "proteins": 23701, "proteomes": 20956, "short_name": "YchF-GTPase_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06071", "structures": 12, "taxa": 34445, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in plants, and is approximately 100 amino acids in length. Considering the very diverse range of other domains it is associated with it is possible that this domain is a binding/guiding region. There are two highly conserved tryptophan residues.", "domain_architectures": 1056, "interpro_id": "IPR025558", "known_evidence_count": null, "matches": 23565, "name": "Domain of unknown function (DUF4283)", "partial_evidence_count": null, "pfam_id": "PF14111", "proteins": 23437, "proteomes": 339, "short_name": "DUF4283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14111", "structures": 0, "taxa": 984, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15479, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This entry (ex DUF4371) represents a RNase-like domain in Zinc finger MYM-type protein 1 (ZMYM1), FAM200 and similar proteins mainly found in animals. FAM200 is characterised by its involvement in cellular regulatory processes, its precise function remains to be elucidated.", "domain_architectures": 951, "interpro_id": "IPR025398", "known_evidence_count": null, "matches": 22713, "name": "ZMYM1/FAM200, RNase-like domain", "partial_evidence_count": null, "pfam_id": "PF14291", "proteins": 21818, "proteomes": 1267, "short_name": "DUF4371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14291", "structures": 0, "taxa": 4275, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 17072, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The function of the plant proteins constituting this family is unknown.", "domain_architectures": 302, "interpro_id": "IPR004158", "known_evidence_count": null, "matches": 23865, "name": "Plant protein of unknown function", "partial_evidence_count": null, "pfam_id": "PF03140", "proteins": 21663, "proteomes": 386, "short_name": "DUF247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03140", "structures": 0, "taxa": 1061, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function. Most of the members are gag-polyproteins.", "domain_architectures": 1118, "interpro_id": "IPR005312", "known_evidence_count": null, "matches": 21116, "name": "Protein of unknown function (DUF1759)", "partial_evidence_count": null, "pfam_id": "PF03564", "proteins": 20944, "proteomes": 467, "short_name": "DUF1759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03564", "structures": 0, "taxa": 1789, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13058, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from bacteria, archaea and eukaryotes, including NTF2-Like SgcJ protein from Streptomyces carzinostaticus, which plays a role in the biosynthesis of the 9-membered enediyne antitumor antibiotic C-1027. It shows a cone-like alpha+beta barrel structure with a long N-terminal alpha- helix, a curved six-stranded antiparallel beta-sheet and two additional shorter alpha-helices. Its specific function is still unkown [[cite:PUB00100883]].", "domain_architectures": 127, "interpro_id": "IPR027843", "known_evidence_count": null, "matches": 21018, "name": "Domain of unknown function (DUF4440)", "partial_evidence_count": null, "pfam_id": "PF14534", "proteins": 20901, "proteomes": 9416, "short_name": "DUF4440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14534", "structures": 14, "taxa": 13277, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11735, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in a range of retrotransposon polyproteins.", "domain_architectures": 1120, "interpro_id": "IPR040676", "known_evidence_count": null, "matches": 20760, "name": "Family of unknown function (DUF5641)", "partial_evidence_count": null, "pfam_id": "PF18701", "proteins": 20636, "proteomes": 472, "short_name": "DUF5641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18701", "structures": 0, "taxa": 1848, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13291, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 18 } }, "demotion_reasons": [], "description": "This family consists of hypothetical proteins some of which are putative membrane proteins. No functional information or experimental verification of function is known. This domain is around 100 amino acids long.", "domain_architectures": 173, "interpro_id": "IPR003807", "known_evidence_count": null, "matches": 18687, "name": "Domain of unknown function (DUF202)", "partial_evidence_count": null, "pfam_id": "PF02656", "proteins": 18669, "proteomes": 7356, "short_name": "DUF202", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02656", "structures": 3, "taxa": 11815, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11006, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 113, "interpro_id": "IPR025161", "known_evidence_count": null, "matches": 18631, "name": "Putative transposase of IS4/5 family (DUF4096)", "partial_evidence_count": null, "pfam_id": "PF13340", "proteins": 18629, "proteomes": 5344, "short_name": "DUF4096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13340", "structures": 0, "taxa": 8051, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 12676, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family includes the DUF34/metal-binding protein/NIF3 proteins, which are widely distributed across superkingdoms. They were previously annotated as GTP cyclohydrolase 1 type 2 [[cite:PUB00070175]] and, recently, through a comprehensive literature review and integrative bioinformatics analyses it was revealed that annotations for these members were misleading as they were based on a single set of in vitro results examining the NIF3 homolog of Helicobacter pylori [[cite:PUB00070175]]. Actually, they have varied phenotypes with the unifying functional role as metal-binding proteins [[cite:PUB00100327]]. This entry contains several NIF3 (NGG1p interacting factor 3) protein homologues. NIF3 interacts with the yeast transcriptional coactivator NGG1p which is part of the ADA complex, the exact function of this interaction is unknown [[cite:PUB00002954],[cite:PUB00019927]].", "domain_architectures": 53, "interpro_id": "IPR002678", "known_evidence_count": null, "matches": 18654, "name": "Duf34/NIF3 (NGG1p interacting factor 3)", "partial_evidence_count": null, "pfam_id": "PF01784", "proteins": 18574, "proteomes": 16807, "short_name": "DUF34_NIF3", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01784", "structures": 16, "taxa": 26806, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 11207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is often found associated to the N-terminus of the HNH endonuclease domain [pfam:PF01844]. The function of this domain is uncertain. This family has been called the 13E12 repeat family [[cite:PUB00057273]].", "domain_architectures": 37, "interpro_id": "IPR003870", "known_evidence_count": null, "matches": 19420, "name": "Domain of unknown function (DUF222)", "partial_evidence_count": null, "pfam_id": "PF02720", "proteins": 18467, "proteomes": 2216, "short_name": "DUF222", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02720", "structures": 0, "taxa": 2801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in the Intracellular iron chaperone frataxin YdhG [[cite:PUB00098100]] and the uncharacterised protein YdeI from Bacillus subtilis.", "domain_architectures": 33, "interpro_id": "IPR014922", "known_evidence_count": null, "matches": 18242, "name": "Domain of unknown function (DU1801)", "partial_evidence_count": null, "pfam_id": "PF08818", "proteins": 18172, "proteomes": 8371, "short_name": "DUF1801", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08818", "structures": 4, "taxa": 11668, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11560, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This presumed domain is found at the N-terminus of many proteins found in transposons.", "domain_architectures": 78, "interpro_id": "IPR008490", "known_evidence_count": null, "matches": 17574, "name": "Transposase domain (DUF772)", "partial_evidence_count": null, "pfam_id": "PF05598", "proteins": 17572, "proteomes": 6555, "short_name": "DUF772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05598", "structures": 0, "taxa": 10733, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 14906, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a large family of fungal integral membrane proteins.", "domain_architectures": 216, "interpro_id": "IPR045339", "known_evidence_count": null, "matches": 17391, "name": "Family of unknown function (DUF6534)", "partial_evidence_count": null, "pfam_id": "PF20152", "proteins": 17299, "proteomes": 298, "short_name": "DUF6534", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20152", "structures": 0, "taxa": 744, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9780, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is found at the C-terminus of bacterial RNA polymerase ECF sigma factor proteins.", "domain_architectures": 42, "interpro_id": "IPR046531", "known_evidence_count": null, "matches": 16823, "name": "Family of unknown function (DUF6596)", "partial_evidence_count": null, "pfam_id": "PF20239", "proteins": 16812, "proteomes": 6132, "short_name": "DUF6596", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20239", "structures": 0, "taxa": 8083, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10934, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Members of this family have so far been found in bacteria and mouse SwissProt or TrEMBL entries. However possible family members have also been identified in translated rat (Genbank:AW144450) and human (Genbank:AI478629) ESTs. A mouse family member has been named SIMPL (signalling molecule that associates with mouse pelle-like kinase). SIMPL appears to facilitate and/or regulate complex formation between IRAK/mPLK (IL-1 receptor-associated kinase) and IKK (inhibitor of kappa-B kinase) containing complexes, and thus regulate NF-kappa-B activity [[cite:PUB00010115]]. Separate experiments demonstrate that a mouse family member (named LaXp180) binds the Listeria monocytogenes surface protein ActA, which is a virulence factor that induces actin polymerisation. It may also bind stathmin, a protein involved in signal transduction and in the regulation of microtubule dynamics [[cite:PUB00009982]]. In bacteria its function is unknown, but it is thought to be located in the periplasm or outer membrane.", "domain_architectures": 17, "interpro_id": "IPR007497", "known_evidence_count": null, "matches": 16828, "name": "Protein of unknown function (DUF541)", "partial_evidence_count": null, "pfam_id": "PF04402", "proteins": 16767, "proteomes": 13193, "short_name": "SIMPL", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04402", "structures": 3, "taxa": 20114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10032, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This an all-beta structure with a twenty-residue repeat with a highly conserved repeating GD, gly-asp, motif that has been described as Toastrack DUF4097, whose function is unknown. It has been suggested to form part of a bacterial adhesin. Toastrack has been transferred from bacteria to certain eukaryotes, such as FAM185A from human and its orthologues in animals and other eukaryotes.", "domain_architectures": 69, "interpro_id": "IPR025164", "known_evidence_count": null, "matches": 16667, "name": "Toastrack DUF4097", "partial_evidence_count": null, "pfam_id": "PF13349", "proteins": 16423, "proteomes": 8115, "short_name": "DUF4097", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13349", "structures": 0, "taxa": 13326, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9783, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins several of which are putative membrane proteins.", "domain_architectures": 64, "interpro_id": "IPR010281", "known_evidence_count": null, "matches": 16325, "name": "Bacterial protein of unknown function (DUF885)", "partial_evidence_count": null, "pfam_id": "PF05960", "proteins": 16004, "proteomes": 7410, "short_name": "DUF885", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05960", "structures": 3, "taxa": 10525, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10419, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 9, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 11, "interpro_id": "IPR019264", "known_evidence_count": null, "matches": 15886, "name": "Uncharacterized protein conserved in bacteria (DUF2179)", "partial_evidence_count": null, "pfam_id": "PF10035", "proteins": 15886, "proteomes": 5206, "short_name": "DUF2179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10035", "structures": 1, "taxa": 8097, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 8872, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It shares significanrt similarity with known SH3 domains and it is predicted to adopt similar structure.", "domain_architectures": 760, "interpro_id": "IPR061864", "known_evidence_count": null, "matches": 15881, "name": "Domain of unknown function (DUF8803)", "partial_evidence_count": null, "pfam_id": "PF31073", "proteins": 15860, "proteomes": 861, "short_name": "DUF8803", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31073", "structures": 0, "taxa": 3149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9380, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Domain found in small family of bacterial secreted proteins with no known function. Also found in Paramecium bursaria chlorella virus 1. This domain is short and found in one or two copies. The domain has a conserved HH motif that may be functionally important. This domain belongs to the ferritin superfamily. It contains two sequence similar repeats each of which is composed of two alpha helices.", "domain_architectures": 40, "interpro_id": "IPR005183", "known_evidence_count": null, "matches": 16107, "name": "Domain of unknown function (DUF305)", "partial_evidence_count": null, "pfam_id": "PF03713", "proteins": 15758, "proteomes": 7077, "short_name": "DUF305", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03713", "structures": 11, "taxa": 9875, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10211, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain, whose function is unknown, is found within a group of putative lipases. Proteins containing this domain include YOR059C (Lpl1) from budding yeasts. Lpl1 has been identified as a phospholipase B [[cite:PUB00073522]]. They contain an alpha/beta hydrolase fold.", "domain_architectures": 547, "interpro_id": "IPR007751", "known_evidence_count": null, "matches": 16829, "name": "Putative serine esterase (DUF676)", "partial_evidence_count": null, "pfam_id": "PF05057", "proteins": 15503, "proteomes": 4005, "short_name": "DUF676", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05057", "structures": 0, "taxa": 10132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11045, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a number of hypothetical bacterial proteins of unknown function approximately 400 residues long.", "domain_architectures": 99, "interpro_id": "IPR010869", "known_evidence_count": null, "matches": 15402, "name": "Protein of unknown function (DUF1501)", "partial_evidence_count": null, "pfam_id": "PF07394", "proteins": 15357, "proteomes": 4880, "short_name": "DUF1501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07394", "structures": 0, "taxa": 7183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9814, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain of unknown function appears towards the C-terminus of proteins of the NAD dependent epimerase/dehydratase family ([pfam:PF01370]) in bacteria, eukaryotes and archaea. Many of the proteins in which it is found are involved in cell-division inhibition.", "domain_architectures": 54, "interpro_id": "IPR013549", "known_evidence_count": null, "matches": 15270, "name": "Domain of unknown function (DUF1731)", "partial_evidence_count": null, "pfam_id": "PF08338", "proteins": 15266, "proteomes": 12014, "short_name": "DUF1731", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08338", "structures": 2, "taxa": 19138, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3731, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 131 and 151 amino acids in length. The family is found in association with [pfam:PF00225], [pfam:PF00498]. There is a single completely conserved residue W that may be functionally important.", "domain_architectures": 232, "interpro_id": "IPR022164", "known_evidence_count": null, "matches": 17500, "name": "Kinesin protein", "partial_evidence_count": null, "pfam_id": "PF12473", "proteins": 15238, "proteomes": 2568, "short_name": "DUF3694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12473", "structures": 0, "taxa": 6851, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 7687, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Streptomyces proteins as well as one from Mycobacterium tuberculosis. The function of these proteins is unknown.", "domain_architectures": 15, "interpro_id": "IPR007995", "known_evidence_count": null, "matches": 15056, "name": "Protein of unknown function (DUF742)", "partial_evidence_count": null, "pfam_id": "PF05331", "proteins": 15048, "proteomes": 2263, "short_name": "DUF742", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05331", "structures": 0, "taxa": 2627, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9886, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry represents a group of bacterial proteins, including AlgH from Pseudomonas aeruginosa, which is involved in the transcriptional regulation of alginate biosynthesis [[cite:PUB00104069]].", "domain_architectures": 101, "interpro_id": "IPR003774", "known_evidence_count": null, "matches": 14759, "name": "AlgH-like", "partial_evidence_count": null, "pfam_id": "PF02622", "proteins": 14657, "proteomes": 12317, "short_name": "DUF179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02622", "structures": 8, "taxa": 17355, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 8861, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "The function of this family is unknown.", "domain_architectures": 30, "interpro_id": "IPR002763", "known_evidence_count": null, "matches": 14657, "name": "Protein of unknown function DUF72", "partial_evidence_count": null, "pfam_id": "PF01904", "proteins": 14646, "proteomes": 9981, "short_name": "DUF72", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01904", "structures": 3, "taxa": 13949, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12310, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a short conserved region found in a large family of fungal integral membrane proteins.", "domain_architectures": 170, "interpro_id": "IPR045340", "known_evidence_count": null, "matches": 14285, "name": "Family of unknown function (DUF6533)", "partial_evidence_count": null, "pfam_id": "PF20151", "proteins": 14207, "proteomes": 242, "short_name": "DUF6533", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20151", "structures": 0, "taxa": 628, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8907, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of the YetF protein, which contains three N-terminal transmembrane helices.", "domain_architectures": 17, "interpro_id": "IPR007353", "known_evidence_count": null, "matches": 14140, "name": "YetF C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF04239", "proteins": 14102, "proteomes": 7086, "short_name": "DUF421", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04239", "structures": 1, "taxa": 10446, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 8845, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 200 residues in length. The function of this family is unknown although most members have 6 TM regions, and may be putative permeases.", "domain_architectures": 68, "interpro_id": "IPR010699", "known_evidence_count": null, "matches": 13423, "name": "Protein of unknown function (DUF1275)", "partial_evidence_count": null, "pfam_id": "PF06912", "proteins": 13380, "proteomes": 8655, "short_name": "DUF1275", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06912", "structures": 0, "taxa": 12724, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10797, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several plant proteins of unknown function. Three of the sequences (from Gossypium hirsutum) in this family are described as cotton fibre expressed proteins [[cite:PUB00011314]]. The remaining sequences, found in Arabidopsis thaliana, are uncharacterised.", "domain_architectures": 110, "interpro_id": "IPR008480", "known_evidence_count": null, "matches": 13264, "name": "Cotton fibre expressed protein", "partial_evidence_count": null, "pfam_id": "PF05553", "proteins": 13240, "proteomes": 375, "short_name": "DUF761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05553", "structures": 0, "taxa": 1045, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9735, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain in Centrosome-associated protein 350 (Cep350), Protein TRM32 and Protein LONGIFOLIA 1/2 found in eukaryotes. This domain contains a helical fold. LNG2 in association with LNG1, regulates leaf morphology by promoting longitudinal polar cell elongation independently of ROT3. It associates with microtubules and recruits TON1A and TON1B to the cytoskeleton through its C-terminal [[cite:PUB00078481],[cite:PUB00095561]].", "domain_architectures": 136, "interpro_id": "IPR025486", "known_evidence_count": null, "matches": 12713, "name": "LONGIFOLIA 1/2-like C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF14309", "proteins": 12694, "proteomes": 676, "short_name": "DUF4378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14309", "structures": 0, "taxa": 2203, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 7682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "", "domain_architectures": 192, "interpro_id": "IPR007569", "known_evidence_count": null, "matches": 12670, "name": "Protein of unknown function (DUF559)", "partial_evidence_count": null, "pfam_id": "PF04480", "proteins": 12664, "proteomes": 6339, "short_name": "DUF559", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04480", "structures": 2, "taxa": 9510, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9535, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins from C. elegans and A. thaliana.", "domain_architectures": 210, "interpro_id": "IPR006869", "known_evidence_count": null, "matches": 12762, "name": "Protein of unknown function, DUF547", "partial_evidence_count": null, "pfam_id": "PF04784", "proteins": 12661, "proteomes": 3039, "short_name": "DUF547", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04784", "structures": 0, "taxa": 6613, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7035, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in a variety of Actinomycetales proteins. All of the proteins containing this domain are uncharacterised and probably membrane bound or associated. It is unclear to the function of this domain.", "domain_architectures": 38, "interpro_id": "IPR012551", "known_evidence_count": null, "matches": 12531, "name": "DUF1707 SHOCT-like domain", "partial_evidence_count": null, "pfam_id": "PF08044", "proteins": 12418, "proteomes": 2787, "short_name": "DUF1707", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08044", "structures": 0, "taxa": 3401, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 10110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several plant proteins of unknown function.", "domain_architectures": 166, "interpro_id": "IPR007493", "known_evidence_count": null, "matches": 12288, "name": "Protein of unknown function, DUF538", "partial_evidence_count": null, "pfam_id": "PF04398", "proteins": 12176, "proteomes": 384, "short_name": "DUF538", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04398", "structures": 1, "taxa": 1122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8332, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found at the C-terminus of isoleucyl tRNA ligase enzymes.", "domain_architectures": 77, "interpro_id": "", "known_evidence_count": null, "matches": 12171, "name": "Domain of unknown function (DUF5915)", "partial_evidence_count": null, "pfam_id": "PF19302", "proteins": 12169, "proteomes": 10940, "short_name": "DUF5915", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19302", "structures": 7, "taxa": 18730, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10516, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 12, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 38 } }, "demotion_reasons": [], "description": "This set of domains is found in various eukaryotic proteins. Function is unknown.", "domain_architectures": 235, "interpro_id": "IPR015048", "known_evidence_count": null, "matches": 13193, "name": "Domain of unknown function (DUF1899)", "partial_evidence_count": null, "pfam_id": "PF08953", "proteins": 12107, "proteomes": 2919, "short_name": "DUF1899", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08953", "structures": 11, "taxa": 7698, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8692, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "", "domain_architectures": 73, "interpro_id": "IPR004879", "known_evidence_count": null, "matches": 12146, "name": "Protein of unknown function, DUF255", "partial_evidence_count": null, "pfam_id": "PF03190", "proteins": 12093, "proteomes": 9928, "short_name": "Thioredox_DsbH", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03190", "structures": 2, "taxa": 18007, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6896, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in a wide variety of bacterial signalling proteins. It is likely to be a transmembrane domain involved in ligand sensing.", "domain_architectures": 541, "interpro_id": "IPR025201", "known_evidence_count": null, "matches": 12032, "name": "Domain of unknown function (DUF4118)", "partial_evidence_count": null, "pfam_id": "PF13493", "proteins": 12032, "proteomes": 8148, "short_name": "DUF4118", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13493", "structures": 1, "taxa": 11245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8659, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It shares similarity to members of the Plant mobile domain superfamily.", "domain_architectures": 416, "interpro_id": "IPR061633", "known_evidence_count": null, "matches": 12320, "name": "Domain of unknown function (DUF8566)", "partial_evidence_count": null, "pfam_id": "PF29561", "proteins": 11980, "proteomes": 310, "short_name": "DUF8566", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29561", "structures": 0, "taxa": 872, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7735, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This family represents a conserved region of approximately 60 residues within a number of hypothetical bacterial and archaeal proteins of unknown function.", "domain_architectures": 56, "interpro_id": "IPR010652", "known_evidence_count": null, "matches": 11798, "name": "Protein of unknown function (DUF1232)", "partial_evidence_count": null, "pfam_id": "PF06803", "proteins": 11798, "proteomes": 9060, "short_name": "DUF1232", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06803", "structures": 0, "taxa": 15395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8600, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "The apaG domain is a ~125 amino acids domain present in bacterial apaG proteins and in eukaryotic F-box proteins. The domain is named after the bacterial apaG protein, of which it forms the core. The domain also occurs in the C-terminal part of eukaryotic proteins with an N-terminal F-box domain. The Salmonella typhimurium apaG domain protein corD is involved in Co(2+) resistance and Mg(2+) efflux. Tertiary structures from different apaG proteins show a fold of several beta-sheets. The apaG domain may be involved in protein-protein interactions which could be implicated in substrate-specificity [[cite:PUB00009972],[cite:PUB00016988],[cite:PUB00018539],[cite:PUB00016989]].", "domain_architectures": 67, "interpro_id": "IPR007474", "known_evidence_count": null, "matches": 11776, "name": "ApaG domain", "partial_evidence_count": null, "pfam_id": "PF04379", "proteins": 11744, "proteomes": 9065, "short_name": "DUF525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04379", "structures": 9, "taxa": 15356, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 7574, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain contains a beta-tent fold [[cite:PUB00078711]].", "domain_architectures": 59, "interpro_id": "IPR007361", "known_evidence_count": null, "matches": 13879, "name": "Domain of unknown function (DUF427)", "partial_evidence_count": null, "pfam_id": "PF04248", "proteins": 11655, "proteomes": 7242, "short_name": "NTP_transf_9", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04248", "structures": 1, "taxa": 10968, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7890, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function is a possible integral membrane protein from Caenorhabditis elegans. This family of proteins has GO references indicating the protein is involved in nematode larval development and is a positive regulator of growth rate.", "domain_architectures": 52, "interpro_id": "IPR006696", "known_evidence_count": null, "matches": 11493, "name": "Protein of unknown function (DUF423)", "partial_evidence_count": null, "pfam_id": "PF04241", "proteins": 11481, "proteomes": 10266, "short_name": "DUF423", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04241", "structures": 0, "taxa": 17329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7658, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This entry represents the central domain found in archaeal proteins such as DNA double-strand break repair helicase HerA ([ec:3.6.4.12]). HerA is a helicase which is able to utilise either 3' or 5' single-stranded DNA extensions for loading and subsequent DNA duplex unwinding [[cite:PUB00076694]]. It forms a complex with NurA nuclease, this complex has the 5'-3' DNA end resection activity and is essential for cell viability in the crenarchaeon Sulfolobus islandicus [[cite:PUB00076695]]. This domain includes the the central RecA-like catalytic core and a flanking four-helix bundle [[cite:PUB00078094]]. The function of this prokaryotic domain is unknown. It contains several conserved aspartates and histidines that could be metal ligands.", "domain_architectures": 87, "interpro_id": "IPR002789", "known_evidence_count": null, "matches": 11481, "name": "Helicase HerA, central domain", "partial_evidence_count": null, "pfam_id": "PF01935", "proteins": 11479, "proteomes": 6966, "short_name": "DUF87", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01935", "structures": 38, "taxa": 11524, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 6894, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is found at the N-terminus of bacterial transcription factor proteins, suggesting that this may be a regulatory domain that binds to some as yet unknown ligand.", "domain_architectures": 12, "interpro_id": "IPR046532", "known_evidence_count": null, "matches": 11477, "name": "Domain of unknown function (DUF6597)", "partial_evidence_count": null, "pfam_id": "PF20240", "proteins": 11475, "proteomes": 5733, "short_name": "DUF6597", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20240", "structures": 0, "taxa": 7815, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6940, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This presumed domain is found at the C-terminus of proteins that contain a transglutaminase core domain. The function of this domain is unknown. The domain has a conserved TXXE motif.", "domain_architectures": 18, "interpro_id": "IPR025403", "known_evidence_count": null, "matches": 11292, "name": "Domain of unknown function (DUF4129)", "partial_evidence_count": null, "pfam_id": "PF13559", "proteins": 11292, "proteomes": 7443, "short_name": "DUF4129", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13559", "structures": 0, "taxa": 10458, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8560, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains a number of bacterial and eukaryotic proteins of unknown function that are approximately 300 residues long.", "domain_architectures": 153, "interpro_id": "IPR010721", "known_evidence_count": null, "matches": 11547, "name": "Protein of unknown function (DUF1295)", "partial_evidence_count": null, "pfam_id": "PF06966", "proteins": 11275, "proteomes": 5887, "short_name": "DUF1295", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06966", "structures": 0, "taxa": 11764, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9492, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A large family of paralogous proteins apparently unique to planctomycetes.", "domain_architectures": 65, "interpro_id": "IPR011453", "known_evidence_count": null, "matches": 11484, "name": "Protein of unknown function (DUF1559)", "partial_evidence_count": null, "pfam_id": "PF07596", "proteins": 11251, "proteomes": 173, "short_name": "SBP_bac_10", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07596", "structures": 0, "taxa": 429, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6020, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain can be found on the N-terminal of uncharacterized proteins from various Rhodopseudomonas and Pseudomonas species, often, but not always followed by the ron siderophore sensor protein family (FecR, PF04773). The function of this domain is unknown.", "domain_architectures": 15, "interpro_id": "IPR032623", "known_evidence_count": null, "matches": 11207, "name": "Domain of unknown function (DUF4880)", "partial_evidence_count": null, "pfam_id": "PF16220", "proteins": 11207, "proteomes": 2574, "short_name": "DUF4880", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16220", "structures": 2, "taxa": 3666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5867, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is composed of 6 transmembrane alpha helices and is found at the N-terminus of a large family of bacterial signalling proteins. It is structurally related to the N-terminus of the DesK protein. That region is believed to be involved in sensing membrane fluidity.", "domain_architectures": 31, "interpro_id": "IPR055558", "known_evidence_count": null, "matches": 11267, "name": "Domain of unknown function (DUF7134)", "partial_evidence_count": null, "pfam_id": "PF23539", "proteins": 11170, "proteomes": 3100, "short_name": "DUF7134", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23539", "structures": 0, "taxa": 3729, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8297, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Transposase-like protein with no known function.", "domain_architectures": 499, "interpro_id": "IPR007021", "known_evidence_count": null, "matches": 11190, "name": "Domain of unknown function (DUF659)", "partial_evidence_count": null, "pfam_id": "PF04937", "proteins": 11104, "proteomes": 714, "short_name": "DUF659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04937", "structures": 0, "taxa": 2440, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7031, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Family of short repeats that occurs in a limited number of membrane proteins. It may divide further in short repeats of around 7-10 residues of the pattern G-#-X(2)-#(2)-X (#=hydrophobic).", "domain_architectures": 21, "interpro_id": "IPR005325", "known_evidence_count": null, "matches": 16655, "name": "Short repeat of unknown function (DUF308)", "partial_evidence_count": null, "pfam_id": "PF03729", "proteins": 11024, "proteomes": 7680, "short_name": "DUF308", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03729", "structures": 0, "taxa": 11139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7045, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins shows structural similarity to other pectin lyase families. Although structures from this family align with acetyl-transferases, there is no conservation of catalytic residues found. It is likely that the function is one of cell-adhesion. In PDB:3jx8, it is interesting to note that the sequence of contains several well defined sequence repeats, centred around GSG motifs defining the tight beta turn between the two sheets of the super-helix; there are 8 such repeats in the C-terminal half of the protein, which could be grouped into 4 repeats of two. It seems likely that this family belongs to the superfamily of trimeric auto-transporter adhesins (TAAs), which are important virulence factors in Gram-negative pathogens [[cite:PUB00029784]] [[cite:PUB00051306]]. In the case of Parabacteroides distasonis, which is a component of the normal distal human gut microbiota, TAA-like complexes probably modulate adherence to the host (information derived from TOPSAN).", "domain_architectures": 34, "interpro_id": "IPR021255", "known_evidence_count": null, "matches": 11258, "name": "Putative auto-transporter adhesin, head GIN domain", "partial_evidence_count": null, "pfam_id": "PF10988", "proteins": 10865, "proteomes": 3662, "short_name": "DUF2807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10988", "structures": 14, "taxa": 5354, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 7835, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 122, "interpro_id": "IPR018535", "known_evidence_count": null, "matches": 10943, "name": "Domain of unknown function (DUF1996)", "partial_evidence_count": null, "pfam_id": "PF09362", "proteins": 10819, "proteomes": 2593, "short_name": "DUF1996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09362", "structures": 0, "taxa": 4264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6905, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain of unknown function occurs in Epoxyqueuosine reductase QueG, an iron-sulfur cluster-binding protein, together with the 4Fe-4S binding domain ([pfam:PF00037]). QueG catalyses the conversion of epoxyqueuosine (oQ) to queuosine (Q), which is a hypermodified base found in the wobble positions of tRNA(Asp), tRNA(Asn), tRNA(His) and tRNA(Tyr) [[cite:PUB00058202]].", "domain_architectures": 17, "interpro_id": "IPR013542", "known_evidence_count": null, "matches": 10771, "name": "Epoxyqueuosine reductase QueG, DUF1730", "partial_evidence_count": null, "pfam_id": "PF08331", "proteins": 10770, "proteomes": 10737, "short_name": "QueG_DUF1730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08331", "structures": 5, "taxa": 15247, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7176, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "These proteins are related to the [pfam:PF00462] family. This entry includes several viral glutaredoxins and many related bacterial and eukaryotic proteins of unknown function. The best characterised member is G4L ([swissprot:P68460]) from Vaccinia virus (strain Western Reserve/WR) (VACV), which is necessary for virion morphogenesis and replication [[cite:PUB00020627]]. This is a cytoplasmic protein which functions as a shuttle in a redox pathway between membrane-associated E10R and L1R or F9L [[cite:PUB00020628]].", "domain_architectures": 53, "interpro_id": "IPR008554", "known_evidence_count": null, "matches": 10669, "name": "Glutaredoxin-like domain (DUF836)", "partial_evidence_count": null, "pfam_id": "PF05768", "proteins": 10668, "proteomes": 10193, "short_name": "Glrx-like", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05768", "structures": 6, "taxa": 16954, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7658, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised prokaryotic proteins. In most of these proteins this domain is flanked by a P-loop ATPase-like domain from the N-termini and by Restriction endonuclease-like domain at the C-termini. The domain represented by this entry has significant to known winged helix domains.", "domain_architectures": 13, "interpro_id": "IPR061673", "known_evidence_count": null, "matches": 10626, "name": "Domain of unknown function (DUF8612)", "partial_evidence_count": null, "pfam_id": "PF30184", "proteins": 10626, "proteomes": 4109, "short_name": "DUF8612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30184", "structures": 0, "taxa": 7338, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6735, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain is frequently found to the N-terminus of the Competence domain, [pfam:PF03772].", "domain_architectures": 18, "interpro_id": "IPR025405", "known_evidence_count": null, "matches": 10540, "name": "Domain of unknown function (DUF4131)", "partial_evidence_count": null, "pfam_id": "PF13567", "proteins": 10525, "proteomes": 10484, "short_name": "DUF4131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13567", "structures": 7, "taxa": 15321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8371, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This is a C-terminal region of plant IQ-containing putative calmodulin-binding proteins.", "domain_architectures": 121, "interpro_id": "IPR025064", "known_evidence_count": null, "matches": 10450, "name": "Protein of unknown function (DUF4005)", "partial_evidence_count": null, "pfam_id": "PF13178", "proteins": 10434, "proteomes": 382, "short_name": "DUF4005", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13178", "structures": 0, "taxa": 1063, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 510, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in eukaryotes on neurobeachin and BEACH domain-containing proteins (BDCPs) [[cite:PUB00075927],[cite:PUB00098184]]. Mutations in this proteins are associated with Lipopolysaccharide-responsive and beige-like anchor (LRBA) deficiency [[cite:PUB00098184]]. According to structure prediction is adopts an alpha-helical solenoid structure.", "domain_architectures": 349, "interpro_id": "IPR031570", "known_evidence_count": null, "matches": 11316, "name": "Neurobeachin/BDCP, DUF4704 alpha solenoid region", "partial_evidence_count": null, "pfam_id": "PF15787", "proteins": 10161, "proteomes": 1996, "short_name": "DUF4704", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15787", "structures": 0, "taxa": 6072, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6370, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 90 residues in length. The function of this family is unknown.", "domain_architectures": 28, "interpro_id": "IPR010753", "known_evidence_count": null, "matches": 10206, "name": "Domain of unknown function (DUF1330)", "partial_evidence_count": null, "pfam_id": "PF07045", "proteins": 10160, "proteomes": 5925, "short_name": "DUF1330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07045", "structures": 4, "taxa": 8347, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5941, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Probable integral membrane protein.", "domain_architectures": 17, "interpro_id": "IPR007349", "known_evidence_count": null, "matches": 10175, "name": "Protein of unknown function (DUF418)", "partial_evidence_count": null, "pfam_id": "PF04235", "proteins": 10136, "proteomes": 5940, "short_name": "DUF418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04235", "structures": 0, "taxa": 8178, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6899, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "These family members are 7TM putative membrane transporter proteins. The family is similar to the SBF family of bile-acid symporters, [pfam:PF01758].", "domain_architectures": 56, "interpro_id": "IPR016833", "known_evidence_count": null, "matches": 10186, "name": "SBF-like CPA transporter family (DUF4137)", "partial_evidence_count": null, "pfam_id": "PF13593", "proteins": 10043, "proteomes": 7930, "short_name": "SBF_like", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13593", "structures": 0, "taxa": 13544, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5886, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is of unknown function. It is sometimes found adjacent to [pfam:PF07690] and [pfam:PF03176] which are both transporter domains.", "domain_architectures": 15, "interpro_id": "IPR023845", "known_evidence_count": null, "matches": 10021, "name": "Domain of unknown function (DUF3817)", "partial_evidence_count": null, "pfam_id": "PF12823", "proteins": 10016, "proteomes": 6530, "short_name": "DUF3817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12823", "structures": 0, "taxa": 8275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6095, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function.", "domain_architectures": 71, "interpro_id": "IPR008523", "known_evidence_count": null, "matches": 10077, "name": "Protein of unknown function (DUF805)", "partial_evidence_count": null, "pfam_id": "PF05656", "proteins": 9999, "proteomes": 6449, "short_name": "DUF805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05656", "structures": 0, "taxa": 9370, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8139, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in plants and is often associated with DUF294, [pfam:PF04578].", "domain_architectures": 181, "interpro_id": "IPR025315", "known_evidence_count": null, "matches": 10494, "name": "Domain of unknown function (DUF4220)", "partial_evidence_count": null, "pfam_id": "PF13968", "proteins": 9939, "proteomes": 354, "short_name": "DUF4220", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13968", "structures": 0, "taxa": 964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6409, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 52, "interpro_id": "IPR018959", "known_evidence_count": null, "matches": 10019, "name": "Domain of unknown function (DUF1989)", "partial_evidence_count": null, "pfam_id": "PF09347", "proteins": 9857, "proteomes": 5418, "short_name": "DUF1989", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09347", "structures": 3, "taxa": 8536, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6583, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Family members are found in small bacterial proteins, and also in the heavy chains of fungal proteins that contain the domain kinesin, in which this region is located C-terminal of the motor domain ([pfam:PF00225]). It adopts a coiled-coil-like conformation [[cite:PUB00038888]].", "domain_architectures": 6, "interpro_id": "IPR007420", "known_evidence_count": null, "matches": 9854, "name": "Protein of unknown function (DUF465)", "partial_evidence_count": null, "pfam_id": "PF04325", "proteins": 9854, "proteomes": 5604, "short_name": "DUF465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04325", "structures": 1, "taxa": 7749, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5162, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 65 residues found in ABC transporter ATP-binding proteins. The domain is located C-terminal to ABC_tran ([pfam:PF00005]) and AAA_21 ([pfam:PF13304]) domains. Many of these proteins are annotated as multidrug ABC transporters or ABC-2 type transport systems, including some daunorubicin/doxorubicin resistance proteins. This family is found almost exclusively in Actinomycetota, particularly Streptomyces. The function of this domain remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061807", "known_evidence_count": null, "matches": 9691, "name": "Domain of unknown function (DUF8746)", "partial_evidence_count": null, "pfam_id": "PF30808", "proteins": 9690, "proteomes": 3254, "short_name": "DUF8746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30808", "structures": 0, "taxa": 3867, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "", "domain_architectures": 353, "interpro_id": "IPR003871", "known_evidence_count": null, "matches": 9749, "name": "Domain of unknown function DUF223", "partial_evidence_count": null, "pfam_id": "PF02721", "proteins": 9531, "proteomes": 506, "short_name": "DUF223", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02721", "structures": 0, "taxa": 1779, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is likely to be a carbohydrate-binding domain of some description as it is found immediately C-terminal to the glycosyl-hydrolase family Glyco_hydro_31, [pfam:PF01055].", "domain_architectures": 246, "interpro_id": "IPR033403", "known_evidence_count": null, "matches": 9482, "name": "Domain of unknown function (DUF5110)", "partial_evidence_count": null, "pfam_id": "PF17137", "proteins": 9478, "proteomes": 6011, "short_name": "DUF5110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17137", "structures": 30, "taxa": 10913, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5910, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "The YlxR family has been demonstrated to regulate metabolic gene expression [[cite:PUB00101021]].", "domain_architectures": 6, "interpro_id": "IPR007393", "known_evidence_count": null, "matches": 9419, "name": "Protein of unknown function (DUF448)", "partial_evidence_count": null, "pfam_id": "PF04296", "proteins": 9419, "proteomes": 9397, "short_name": "YlxR", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04296", "structures": 1, "taxa": 13449, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8097, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It has detectable similarity to plant mobile domains and it is predicted to adopt similar structure.", "domain_architectures": 109, "interpro_id": "IPR056647", "known_evidence_count": null, "matches": 10094, "name": "Domain of unknown function (DUF7745)", "partial_evidence_count": null, "pfam_id": "PF24924", "proteins": 9216, "proteomes": 108, "short_name": "DUF7745", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24924", "structures": 0, "taxa": 290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7460, "candidate_reasons": [ "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains the 17.2 kD subunit of complex I (NDUFA12) and its homologues. The family also contains a second related eukaryotic protein of unknown function, e.g. [swissprot:Q9BV02].", "domain_architectures": 92, "interpro_id": "IPR007763", "known_evidence_count": null, "matches": 9228, "name": "NADH ubiquinone oxidoreductase subunit NDUFA12", "partial_evidence_count": null, "pfam_id": "PF05071", "proteins": 9214, "proteomes": 5704, "short_name": "NDUFA12", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05071", "structures": 291, "taxa": 11992, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6926, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in eukaryotes. This presumed domain is about 50 amino acids in length. This domain is found associated with [pfam:PF00069], [pfam:PF08276], [pfam:PF00954], [pfam:PF01453].", "domain_architectures": 403, "interpro_id": "IPR021820", "known_evidence_count": null, "matches": 9317, "name": "Domain of unknown function (DUF3403)", "partial_evidence_count": null, "pfam_id": "PF11883", "proteins": 9192, "proteomes": 359, "short_name": "DUF3403", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11883", "structures": 0, "taxa": 979, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5344, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family represents a putative component of ActP-like carboxylate transporters. Several members are cofit with adjacent ActP-like permeases, and the family appears to represent a membrane protein. It has been suggested to be involved in pyruvate utilisation [[cite:PUB00093610]].", "domain_architectures": 5, "interpro_id": "IPR007436", "known_evidence_count": null, "matches": 9097, "name": "Protein of unknown function, DUF485", "partial_evidence_count": null, "pfam_id": "PF04341", "proteins": 9096, "proteomes": 6300, "short_name": "DUF485", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04341", "structures": 0, "taxa": 8285, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5897, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family includes prokaryotic proteins of unknown function, as well as a protein annotated as the pit accessory protein from Sinorhizobium meliloti [swissprot:O30498]. However, the function of this protein is also unknown (Pit stands for Phosphate transport). It is probably distantly related to [pfam:PF01895] (personal obs:Yeats C).", "domain_architectures": 10, "interpro_id": "IPR018445", "known_evidence_count": null, "matches": 9082, "name": "Protein of unknown function DUF47", "partial_evidence_count": null, "pfam_id": "PF01865", "proteins": 9082, "proteomes": 8245, "short_name": "PhoU_div", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01865", "structures": 3, "taxa": 11416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6670, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Predicted to be an integral membrane protein.", "domain_architectures": 38, "interpro_id": "IPR007462", "known_evidence_count": null, "matches": 9091, "name": "Protein of unknown function (DUF502)", "partial_evidence_count": null, "pfam_id": "PF04367", "proteins": 9071, "proteomes": 6263, "short_name": "DUF502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04367", "structures": 0, "taxa": 10061, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5636, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "Members of this family pertain to a set of functionally uncharacterised hypothetical bacterial proteins. They adopt a ferredoxin-like fold, with a beta-alpha-beta-beta-alpha-beta arrangement [[cite:PUB00032088]].", "domain_architectures": 8, "interpro_id": "IPR015269", "known_evidence_count": null, "matches": 9056, "name": "Domain of unknown function (DUF1949)", "partial_evidence_count": null, "pfam_id": "PF09186", "proteins": 9056, "proteomes": 9028, "short_name": "DUF1949", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09186", "structures": 2, "taxa": 12454, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5315, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of unknown function.", "domain_architectures": 16, "interpro_id": "IPR025419", "known_evidence_count": null, "matches": 9244, "name": "Domain of unknown function (DUF4142)", "partial_evidence_count": null, "pfam_id": "PF13628", "proteins": 9035, "proteomes": 4726, "short_name": "DUF4142", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13628", "structures": 0, "taxa": 6260, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7471, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain found in RMND1 from mammals, Sif2/Sif3 from fission yeasts and Rmd1/Rmd8/YDR282C (Mrx10) from budding yeasts. RMND1 and its yeast homologue, Mrx10, are mitochondrial proteins required for mitochondrial translation [[cite:PUB00076329],[cite:PUB00076330]]. Rmd1 and Rmd8 are cytoplasmic proteins required for sporulation [[cite:PUB00075393]].", "domain_architectures": 131, "interpro_id": "IPR003734", "known_evidence_count": null, "matches": 9108, "name": "RMND1/Sif2-Sif3/Mrx10, DUF155", "partial_evidence_count": null, "pfam_id": "PF02582", "proteins": 9028, "proteomes": 4343, "short_name": "DUF155", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02582", "structures": 0, "taxa": 10538, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5589, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the C-terminal region of several hypothetical proteins of unknown function. Family members are mostly bacterial, but a few are also found in eukaryotes and archaea.", "domain_architectures": 42, "interpro_id": "IPR010621", "known_evidence_count": null, "matches": 9261, "name": "Protein of unknown function (DUF1214)", "partial_evidence_count": null, "pfam_id": "PF06742", "proteins": 8964, "proteomes": 3968, "short_name": "DUF1214", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06742", "structures": 4, "taxa": 6144, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7348, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 165, "interpro_id": "IPR007658", "known_evidence_count": null, "matches": 9018, "name": "Protein of unknown function, DUF594", "partial_evidence_count": null, "pfam_id": "PF04578", "proteins": 8927, "proteomes": 351, "short_name": "DUF594", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04578", "structures": 0, "taxa": 955, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5317, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of a series of hypothetical bacterial proteins. One of the family members [swissprot:Q45543] from Bacillus subtilis is thought to be involved in cell division and sporulation [[cite:PUB00011928]].", "domain_architectures": 6, "interpro_id": "IPR010273", "known_evidence_count": null, "matches": 8826, "name": "Bacterial protein of unknown function (DUF881)", "partial_evidence_count": null, "pfam_id": "PF05949", "proteins": 8824, "proteomes": 3335, "short_name": "DUF881", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05949", "structures": 1, "taxa": 4412, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5434, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function. It has similarity to [pfam:PF01292] suggesting it is a haem-binding cytochrome.", "domain_architectures": 58, "interpro_id": "IPR019251", "known_evidence_count": null, "matches": 8775, "name": "Predicted membrane protein (DUF2231)", "partial_evidence_count": null, "pfam_id": "PF09990", "proteins": 8774, "proteomes": 5572, "short_name": "DUF2231", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09990", "structures": 0, "taxa": 8314, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of a number of hypothetical bacterial proteins. The aligned region spans around 56 residues and contains 4 highly conserved cysteine residues towards the N-terminus. The function of this family is unknown. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 19, "interpro_id": "IPR010710", "known_evidence_count": null, "matches": 8714, "name": "Protein of unknown function (DUF1289)", "partial_evidence_count": null, "pfam_id": "PF06945", "proteins": 8714, "proteomes": 5326, "short_name": "DUF1289", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06945", "structures": 0, "taxa": 7181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7320, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 121 and 170 amino acids in length. It is usually found in association with [pfam:PF00595] (PDZ) and [pfam:PF00412] (LIM), and often contains the conserved Zasp-like motif (IPR006643).", "domain_architectures": 96, "interpro_id": "IPR031847", "known_evidence_count": null, "matches": 8771, "name": "Domain of unknown function (DUF4749)", "partial_evidence_count": null, "pfam_id": "PF15936", "proteins": 8665, "proteomes": 1150, "short_name": "DUF4749", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15936", "structures": 0, "taxa": 3816, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is typically between 120 to 143 amino acids in length.", "domain_architectures": 154, "interpro_id": "IPR021833", "known_evidence_count": null, "matches": 8639, "name": "Domain of unknown function (DUF3425)", "partial_evidence_count": null, "pfam_id": "PF11905", "proteins": 8625, "proteomes": 1153, "short_name": "DUF3425", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11905", "structures": 0, "taxa": 2399, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5431, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of hypothetical bacterial proteins of unknown function as well as phage Gp49 proteins.", "domain_architectures": 7, "interpro_id": "IPR009241", "known_evidence_count": null, "matches": 8618, "name": "Phage derived protein Gp49-like (DUF891)", "partial_evidence_count": null, "pfam_id": "PF05973", "proteins": 8618, "proteomes": 5161, "short_name": "Gp49", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05973", "structures": 4, "taxa": 8458, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in a variety of bacterial proteins. It is found associated at the N-terminus associated with other domains such as the SLT domain and glutaredoxin domains in some proteins. The function of this domain is unknown, but it may have an Ig-like fold.", "domain_architectures": 53, "interpro_id": "IPR025392", "known_evidence_count": null, "matches": 8587, "name": "Domain of unknown function (DUF4124)", "partial_evidence_count": null, "pfam_id": "PF13511", "proteins": 8584, "proteomes": 2921, "short_name": "DUF4124", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13511", "structures": 0, "taxa": 4127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6673, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This is a large family of uncharacterised proteins found in all domains of life. The structure shows a novel fold with three beta sheets. A dimeric form is found in the crystal structure. It was suggested that the cleft in between the two monomers might bing nucleic acid [[cite:PUB00019473]].", "domain_architectures": 80, "interpro_id": "IPR007523", "known_evidence_count": null, "matches": 8559, "name": "Protein of unknown function (DUF498/DUF598)", "partial_evidence_count": null, "pfam_id": "PF04430", "proteins": 8557, "proteomes": 7131, "short_name": "DUF498", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04430", "structures": 9, "taxa": 14086, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6836, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found frequently at the N-terminus of family DUF3741, [pfam:PF12552].", "domain_architectures": 95, "interpro_id": "IPR032795", "known_evidence_count": null, "matches": 8546, "name": "DUF761-associated sequence motif", "partial_evidence_count": null, "pfam_id": "PF14383", "proteins": 8540, "proteomes": 377, "short_name": "VARLMGL", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14383", "structures": 0, "taxa": 1031, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5048, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "Family member FomD is a protein encoded in the fosfomycin biosynthesis gene cluster [[cite:PUB00009885],[cite:PUB00100530]], which hydrolyses (S)-HPP-CMP to give (S)-HPP and CMP in the presence of Mn2 or Co2 [[cite:PUB00100530]]. FomD also hydrolyses cytidylyl 2-hydroxyethylphosphonate (HEP-CMP), which is a biosynthetic intermediate before C-methylation. FomD structure revealed that it has a beta-barrel fold consisting of a large twisted antiparallel beta-sheet, a key feature of DUF402-containing proteins. The function of this domain is unknown. It has a Tyr residue which activates a water molecule to promote nucleophilic attack on the phosphorus atom of the phosphonate moiety [[cite:PUB00100530]]. This domain has also been found in Ntdp (nucleoside tri- and diphosphatase, also known as Sa1684) from Staphylococcus aureus [[cite:PUB00100531]].", "domain_architectures": 23, "interpro_id": "IPR007295", "known_evidence_count": null, "matches": 8523, "name": "Protein of unknown function (DUF402)", "partial_evidence_count": null, "pfam_id": "PF04167", "proteins": 8509, "proteomes": 5477, "short_name": "DUF402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04167", "structures": 12, "taxa": 7221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6902, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This plant protein may be a leucine zipper, but there is no experimental evidence for this.", "domain_architectures": 124, "interpro_id": "IPR006867", "known_evidence_count": null, "matches": 8800, "name": "Protein of unknown function (DUF632)", "partial_evidence_count": null, "pfam_id": "PF04782", "proteins": 8489, "proteomes": 380, "short_name": "DUF632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04782", "structures": 0, "taxa": 1091, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4957, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family represents a putative integral membrane protein that is likely to be the membrane component of an ABC transport system.", "domain_architectures": 14, "interpro_id": "IPR038750", "known_evidence_count": null, "matches": 8412, "name": "Family of unknown function (DUF6198)", "partial_evidence_count": null, "pfam_id": "PF19700", "proteins": 8403, "proteomes": 5840, "short_name": "DUF6198", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19700", "structures": 0, "taxa": 8014, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6773, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in putative Harbinger-related nucleases, mostly found in plants. It adopts a cyclin-like fold, forming a small helical bundle. This domain is usually found adjacent to [pfam:PF13359].", "domain_architectures": 238, "interpro_id": "IPR058353", "known_evidence_count": null, "matches": 8390, "name": "Domain of unknown function (DUF8040)", "partial_evidence_count": null, "pfam_id": "PF26138", "proteins": 8386, "proteomes": 865, "short_name": "DUF8040", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26138", "structures": 0, "taxa": 2918, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5385, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Members of this family contain a four-stranded beta sheet and three alpha helices flanked by an additional beta strand. They are predominantly found in the bacterial GTP-binding protein Obg, and are still functionally uncharacterised [[cite:PUB00022779]].", "domain_architectures": 29, "interpro_id": "IPR015349", "known_evidence_count": null, "matches": 8360, "name": "Domain of unknown function (DUF1967)", "partial_evidence_count": null, "pfam_id": "PF09269", "proteins": 8357, "proteomes": 8086, "short_name": "DUF1967", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09269", "structures": 1, "taxa": 11853, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5088, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Predicted to be a membrane protein.", "domain_architectures": 15, "interpro_id": "IPR007383", "known_evidence_count": null, "matches": 8633, "name": "Protein of unknown function (DUF445)", "partial_evidence_count": null, "pfam_id": "PF04286", "proteins": 8323, "proteomes": 7616, "short_name": "DUF445", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04286", "structures": 0, "taxa": 10811, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5910, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Domain is found in an undescribed set of proteins [[cite:PUB00016669]]. Normally occurs uniquely within a sequence, but is found as a tandem repeat ([swissprot:Q9X8B8]). Shows interesting phylogenetic distribution with majority of examples in bacteria and archaea, but it is also found in some fungal proteins. The hypothetical protein TT1751 from Thermus thermophilus has a beta-alpha-beta(4)-alpha structural fold [[cite:PUB00028717]].", "domain_architectures": 28, "interpro_id": "IPR005180", "known_evidence_count": null, "matches": 8521, "name": "Domain of unknown function DUF302", "partial_evidence_count": null, "pfam_id": "PF03625", "proteins": 8300, "proteomes": 5609, "short_name": "DUF302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03625", "structures": 3, "taxa": 9120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6506, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents an SH3 barrel like domain found in a large family of AAA proteins. The function of these proteins is uncertain.", "domain_architectures": 154, "interpro_id": "IPR054289", "known_evidence_count": null, "matches": 8282, "name": "Domain of unknown function (DUF7025)", "partial_evidence_count": null, "pfam_id": "PF22942", "proteins": 8265, "proteomes": 1103, "short_name": "DUF7025", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22942", "structures": 0, "taxa": 2325, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised bacterial proteins that share similarity to members of the DoxD-like superfamily.", "domain_architectures": 11, "interpro_id": "IPR061630", "known_evidence_count": null, "matches": 8245, "name": "Domain of unknown function (DUF8561)", "partial_evidence_count": null, "pfam_id": "PF29531", "proteins": 8243, "proteomes": 5655, "short_name": "DUF8561", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29531", "structures": 0, "taxa": 7750, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 681, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is typically between 582 to 594 amino acids in length. This domain is found associated with [pfam:PF07717], [pfam:PF00271], [pfam:PF04408].", "domain_architectures": 55, "interpro_id": "IPR024590", "known_evidence_count": null, "matches": 8434, "name": "Domain of unknown function (DUF3418)", "partial_evidence_count": null, "pfam_id": "PF11898", "proteins": 8235, "proteomes": 8101, "short_name": "DUF3418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11898", "structures": 8, "taxa": 10483, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4999, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 139 and 165 amino acids in length. There is a conserved PYF sequence motif. There is a single completely conserved residue N that may be functionally important.", "domain_architectures": 14, "interpro_id": "IPR027961", "known_evidence_count": null, "matches": 8206, "name": "Domain of unknown function (DUF4442)", "partial_evidence_count": null, "pfam_id": "PF14539", "proteins": 8206, "proteomes": 6151, "short_name": "DUF4442", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14539", "structures": 2, "taxa": 8366, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5508, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Two structures have been solved for members of this large (>500 members) family of bacterial proteins present mostly in environmental bacteria and metagenomes (distant homologues are also present in several Plasmodium species). TOPSAN analysis for pdb:3pjy shows that there is much similarity with the other solved structure, pdb:3m7a, solved for UniProt:Q2GA55 (Saro_0823), a homologue of Thermotoga maritima TM1668, UniProt:Q9X1Z6., The homologue in Caulobacter crescentus (CC1388), UniProt:Q9A8G6, is associated with CspD, a cold shock protein (CC1387), UniProt:Q9A8G7. However, the genomic context of UniProt:Q2GA55 is most conserved with a putative xylose isomerase, suggesting a possible role in extracellular sugar processing. Saro_0821, UniProt:Q2GA57, is annotated as an AMP-dependent synthetase and ligase. PDB:3m7a structure corresponds to the C-terminal (27-165) fragment of the YP_496102 (Saro_0823) protein and it is structurally unique, as the best hits from Dali have a Z-score of 3.8 (1nt0, 2j1t, 3kq4) and it is thus a likely candidate for a new fold. Interestingly, many of the top Dali hits are involved in sugar metabolism. There are no obvious active site-like cavities on the protein surface of 3m7a (http://www.topsan.org/Proteins/JCSG/).", "domain_architectures": 19, "interpro_id": "IPR003795", "known_evidence_count": null, "matches": 8203, "name": "Uncharacterized ACR, COG1430", "partial_evidence_count": null, "pfam_id": "PF02643", "proteins": 8199, "proteomes": 7198, "short_name": "DUF192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02643", "structures": 2, "taxa": 10914, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 994, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This putative domain is found in a range of RHS proteins.", "domain_architectures": 3104, "interpro_id": "IPR045351", "known_evidence_count": null, "matches": 8191, "name": "Domain of unknown function (DUF6531)", "partial_evidence_count": null, "pfam_id": "PF20148", "proteins": 8183, "proteomes": 4011, "short_name": "DUF6531", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20148", "structures": 12, "taxa": 6046, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1504, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical/structural eukaryotic proteins.", "domain_architectures": 66, "interpro_id": "IPR015022", "known_evidence_count": null, "matches": 8401, "name": "Domain of unknown function (DUF1908)", "partial_evidence_count": null, "pfam_id": "PF08926", "proteins": 8174, "proteomes": 1250, "short_name": "DUF1908", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08926", "structures": 2, "taxa": 4043, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of putative lipoproteins. The structure for [swissprot:Q64U78], PDB:3fzx, the first structural template for this large family including several homologues in the human gut microbiome and in metagenomic datasets, folds into a beta barrel that topologically looks like a small-scale porin (such as FepA). [swissprot:Q64U78] is a putative exported protein, and this fold is of the YmcC-like type, with a predicted signal peptide SpI cleavage site AGAMA|QNQDC, and a Phobius server prediction of non-cytoplasmic localisation for amino acids 21-236. The possibility of it being a membrane protein can be ruled out by the hydrophilic nature of the solvent exposed surface outside the barrels. Analysis of sequence conservation suggests that an area near Glu172/Trp206 is potentially interesting. These two residues are also conserved in Dali hit PDB:2in5, a hypothetical lipoprotein classified as a new YmcC-like fold in SCOP (SCOP:159271, with a 12-stranded meander beta-sheet folded into a deformed beta-barrel) despite large structural differences between the two structures, suggesting similarity in function.", "domain_architectures": 10, "interpro_id": "IPR021457", "known_evidence_count": null, "matches": 8049, "name": "Protein of unknown function (DUF3108)", "partial_evidence_count": null, "pfam_id": "PF11306", "proteins": 8047, "proteomes": 6575, "short_name": "DUF3108", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11306", "structures": 0, "taxa": 9208, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6813, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised eukaryotic proteins.", "domain_architectures": 125, "interpro_id": "IPR008547", "known_evidence_count": null, "matches": 8537, "name": "Eukaryotic protein of unknown function (DUF829)", "partial_evidence_count": null, "pfam_id": "PF05705", "proteins": 8043, "proteomes": 2796, "short_name": "DUF829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05705", "structures": 0, "taxa": 7614, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5051, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found associated with [pfam:PF00571]. This region is uncharacterised, however it seems to be similar to [pfam:PF01909], conserving the DXD motif. This strongly suggests that members of this family are also nucleotidyltransferases (Bateman A pers. obs.).", "domain_architectures": 253, "interpro_id": "IPR005105", "known_evidence_count": null, "matches": 8056, "name": "Putative nucleotidyltransferase DUF294", "partial_evidence_count": null, "pfam_id": "PF03445", "proteins": 8040, "proteomes": 5549, "short_name": "DUF294", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03445", "structures": 0, "taxa": 8028, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5272, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "", "domain_architectures": 12, "interpro_id": "IPR003791", "known_evidence_count": null, "matches": 8034, "name": "Uncharacterized BCR, YaiI/YqxD family COG1671", "partial_evidence_count": null, "pfam_id": "PF02639", "proteins": 8028, "proteomes": 7791, "short_name": "DUF188", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02639", "structures": 0, "taxa": 11060, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 386, "interpro_id": "IPR025452", "known_evidence_count": null, "matches": 7996, "name": "Domain of unknown function (DUF4218)", "partial_evidence_count": null, "pfam_id": "PF13960", "proteins": 7949, "proteomes": 330, "short_name": "DUF4218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13960", "structures": 0, "taxa": 1234, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 10, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is typically between 156 to 173 amino acids in length.", "domain_architectures": 222, "interpro_id": "IPR021893", "known_evidence_count": null, "matches": 7999, "name": "Domain of unknown function (DUF3504)", "partial_evidence_count": null, "pfam_id": "PF12012", "proteins": 7930, "proteomes": 1139, "short_name": "DUF3504", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12012", "structures": 2, "taxa": 3772, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4726, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of conserved bacterial and archaeal proteins.", "domain_architectures": 18, "interpro_id": "IPR009339", "known_evidence_count": null, "matches": 7932, "name": "Protein of unknown function (DUF998)", "partial_evidence_count": null, "pfam_id": "PF06197", "proteins": 7895, "proteomes": 4360, "short_name": "DUF998", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06197", "structures": 0, "taxa": 6290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5387, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Family of uncharacterised proteins found in bacteria and eukaryotes that belongs to the Cupin superfamily.", "domain_architectures": 53, "interpro_id": "IPR009327", "known_evidence_count": null, "matches": 7933, "name": "Cupin superfamily (DUF985)", "partial_evidence_count": null, "pfam_id": "PF06172", "proteins": 7881, "proteomes": 7039, "short_name": "Cupin_5", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06172", "structures": 7, "taxa": 11447, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5177, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 9, "interpro_id": "IPR019223", "known_evidence_count": null, "matches": 7872, "name": "Uncharacterized protein conserved in bacteria (DUF2147)", "partial_evidence_count": null, "pfam_id": "PF09917", "proteins": 7871, "proteomes": 5290, "short_name": "DUF2147", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09917", "structures": 1, "taxa": 7178, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 6581, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an integral membrane region of a large family of fungal proteins. This region likely contains three transmembrane helices. Some proteins contain two copies of this region. The function of these proteins is unknown.", "domain_architectures": 160, "interpro_id": "IPR045338", "known_evidence_count": null, "matches": 7928, "name": "Family of unknown function (DUF6535)", "partial_evidence_count": null, "pfam_id": "PF20153", "proteins": 7754, "proteomes": 207, "short_name": "DUF6535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20153", "structures": 0, "taxa": 575, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4678, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in bacterial lipoproteins. The function is not known.", "domain_architectures": 8, "interpro_id": "IPR025411", "known_evidence_count": null, "matches": 7665, "name": "Domain of unknown function (DUF4136)", "partial_evidence_count": null, "pfam_id": "PF13590", "proteins": 7650, "proteomes": 4433, "short_name": "DUF4136", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13590", "structures": 2, "taxa": 5774, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5075, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This domain is found in a group of putative heme-iron utilisation proteins, such as HugZ. It can also be found in C-terminal of the glutamyl-tRNA reductase-binding (GluTRBP) protein from Arabidopsis [[cite:PUB00075508]]. GluTRBP is involved in the regulation of glutamyl-tRNA reductase (GluTR) which is important for the synthesis and distribution of 5-aminolevulinate, a precursor in heme and chlorophyll biosynthesis [[cite:PUB00075509]]. GluTRBP is necessary for efficient photosynthetic electron transport in chloroplasts [[cite:PUB00075510]].", "domain_architectures": 76, "interpro_id": "IPR019595", "known_evidence_count": null, "matches": 7613, "name": "Domain of unknown function (DUF2470)", "partial_evidence_count": null, "pfam_id": "PF10615", "proteins": 7608, "proteomes": 5685, "short_name": "DUF2470", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10615", "structures": 16, "taxa": 9310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4402, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This integral membrane domain is functionally uncharacterised. One of the membrane helices contains two GXXG motifs that are usually associated with dimerisation.", "domain_architectures": 46, "interpro_id": "IPR025241", "known_evidence_count": null, "matches": 7546, "name": "Domain of unknown function (DUF4190)", "partial_evidence_count": null, "pfam_id": "PF13828", "proteins": 7546, "proteomes": 3785, "short_name": "DUF4190", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13828", "structures": 0, "taxa": 4865, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5837, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of paralogues in the planctomyces.", "domain_architectures": 106, "interpro_id": "IPR011444", "known_evidence_count": null, "matches": 7538, "name": "Protein of unknown function (DUF1549)", "partial_evidence_count": null, "pfam_id": "PF07583", "proteins": 7523, "proteomes": 829, "short_name": "PSCyt2", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07583", "structures": 0, "taxa": 1459, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4980, "candidate_reasons": [ "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, archaea and eukaryotes.", "domain_architectures": 59, "interpro_id": "IPR024601", "known_evidence_count": null, "matches": 7549, "name": "Domain of unknown function (DUF3458_C) ARM repeats", "partial_evidence_count": null, "pfam_id": "PF17432", "proteins": 7508, "proteomes": 6773, "short_name": "DUF3458_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17432", "structures": 117, "taxa": 10111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4667, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found towards the C terminus of Beta-glucuronidase from Formosa agariphila (P17_GH2) and similar proteins mainly from bacteria and fungi. P17_GH2 is involved in the degradation of the polysaccharide ulvan. The function of this domain, which shows an all-beta structure, is unknown [[cite:PUB00093668]].", "domain_architectures": 279, "interpro_id": "IPR032311", "known_evidence_count": null, "matches": 7520, "name": "Domain of unknown function (DUF4982)", "partial_evidence_count": null, "pfam_id": "PF16355", "proteins": 7504, "proteomes": 3206, "short_name": "DUF4982", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16355", "structures": 40, "taxa": 5073, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5804, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of proteins found in Rhodopirellula baltica.", "domain_architectures": 102, "interpro_id": "IPR022655", "known_evidence_count": null, "matches": 7604, "name": "Protein of unknown function (DUF1553)", "partial_evidence_count": null, "pfam_id": "PF07587", "proteins": 7484, "proteomes": 807, "short_name": "PSD1", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07587", "structures": 0, "taxa": 1409, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5346, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 17 } }, "demotion_reasons": [], "description": "This domain is highly charged and may represent a small helical extension of the Smr domain ([pfam:PF01713]), known as N-ext, whose function is not yet clear [[cite:PUB00098095]].", "domain_architectures": 237, "interpro_id": "IPR013899", "known_evidence_count": null, "matches": 7427, "name": "Domain of unknown function (DUF1771)", "partial_evidence_count": null, "pfam_id": "PF08590", "proteins": 7421, "proteomes": 2861, "short_name": "DUF1771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08590", "structures": 0, "taxa": 7508, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6024, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This region is sometimes found at the N-terminus of putative plant bZIP proteins. Its function is not known. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 88, "interpro_id": "IPR006868", "known_evidence_count": null, "matches": 7424, "name": "Protein of unknown function (DUF630)", "partial_evidence_count": null, "pfam_id": "PF04783", "proteins": 7419, "proteomes": 379, "short_name": "DUF630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04783", "structures": 0, "taxa": 1076, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is almost always found C-terminal to an ATPase core family.", "domain_architectures": 13, "interpro_id": "IPR025420", "known_evidence_count": null, "matches": 7379, "name": "Domain of unknown function (DUF4143)", "partial_evidence_count": null, "pfam_id": "PF13635", "proteins": 7379, "proteomes": 3423, "short_name": "DUF4143", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13635", "structures": 0, "taxa": 6215, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4873, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, archaea and eukaryotes. The domain has an Ig-like fold. This domain is found associated with [pfam:PF01433].", "domain_architectures": 50, "interpro_id": "IPR035414", "known_evidence_count": null, "matches": 7380, "name": "Domain of unknown function (DUF3458) Ig-like fold", "partial_evidence_count": null, "pfam_id": "PF11940", "proteins": 7370, "proteomes": 6720, "short_name": "DUF3458", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11940", "structures": 117, "taxa": 10033, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4518, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region about 130 residues long within hypothetical proteins of unknown function. Family members include eukaryotic, bacterial and archaeal proteins.", "domain_architectures": 44, "interpro_id": "IPR010679", "known_evidence_count": null, "matches": 7351, "name": "Protein of unknown function (DUF1254)", "partial_evidence_count": null, "pfam_id": "PF06863", "proteins": 7338, "proteomes": 3330, "short_name": "DUF1254", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06863", "structures": 3, "taxa": 5359, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5987, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family contains hypothetical plant proteins of unknown function. Family members contain a number of conserved cysteine residues.", "domain_architectures": 80, "interpro_id": "IPR009606", "known_evidence_count": null, "matches": 7413, "name": "Protein of unknown function (DUF1218)", "partial_evidence_count": null, "pfam_id": "PF06749", "proteins": 7332, "proteomes": 383, "short_name": "DUF1218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06749", "structures": 0, "taxa": 1100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 432, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain is found in chromatin remodelling factors (CHDs) from subfamily II [[cite:PUB00098174]] including CHD3/4/5 from animals and PICKLE. from Arabidopsis. The exact function is, as yet, unknown.", "domain_architectures": 196, "interpro_id": "IPR009463", "known_evidence_count": null, "matches": 7329, "name": "CHD subfamily II, DUF1087", "partial_evidence_count": null, "pfam_id": "PF06465", "proteins": 7326, "proteomes": 1594, "short_name": "DUF1087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06465", "structures": 2, "taxa": 5059, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4874, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 50 residues in length. The function of this family is unknown.", "domain_architectures": 5, "interpro_id": "IPR009760", "known_evidence_count": null, "matches": 7316, "name": "Protein of unknown function (DUF1328)", "partial_evidence_count": null, "pfam_id": "PF07043", "proteins": 7314, "proteomes": 5296, "short_name": "DUF1328", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07043", "structures": 0, "taxa": 7604, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5666, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of functionally uncharacterised domains are found in a set of Arabidopsis thaliana hypothetical proteins.", "domain_architectures": 248, "interpro_id": "IPR015410", "known_evidence_count": null, "matches": 7322, "name": "Domain of unknown function (DUF1985)", "partial_evidence_count": null, "pfam_id": "PF09331", "proteins": 7235, "proteomes": 123, "short_name": "DUF1985", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09331", "structures": 2, "taxa": 359, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4705, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This protein family is found in bacteria, including Protein YciF from Escherichia coli. This protein is produced by bacteria in response to stress conditions. It adopts a dimeric configuration in which each monomer shows five alpha-helices. Its function is still unknown [[cite:PUB00041161]].", "domain_architectures": 15, "interpro_id": "IPR010287", "known_evidence_count": null, "matches": 7244, "name": "Domain of unknown function (DUF892)", "partial_evidence_count": null, "pfam_id": "PF05974", "proteins": 7232, "proteomes": 3560, "short_name": "DUF892", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05974", "structures": 6, "taxa": 5175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4374, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 11, "interpro_id": "IPR010406", "known_evidence_count": null, "matches": 7241, "name": "Protein of unknown function (DUF1003)", "partial_evidence_count": null, "pfam_id": "PF06210", "proteins": 7199, "proteomes": 6325, "short_name": "DUF1003", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06210", "structures": 0, "taxa": 8500, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4450, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found C-terminal to a Rossmann-like domain suggesting that these proteins are oxidoreductases.", "domain_architectures": 15, "interpro_id": "IPR018931", "known_evidence_count": null, "matches": 7207, "name": "Domain of unknown function (DUF2520)", "partial_evidence_count": null, "pfam_id": "PF10728", "proteins": 7198, "proteomes": 7076, "short_name": "DUF2520", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10728", "structures": 2, "taxa": 9443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4748, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Family of hypothetical bacterial proteins with an undetermined function.", "domain_architectures": 25, "interpro_id": "IPR005240", "known_evidence_count": null, "matches": 7185, "name": "Domain of unknown function (DUF389)", "partial_evidence_count": null, "pfam_id": "PF04087", "proteins": 7177, "proteomes": 5575, "short_name": "DUF389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04087", "structures": 0, "taxa": 9165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4039, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 28, "interpro_id": "IPR018721", "known_evidence_count": null, "matches": 7232, "name": "Uncharacterized protein conserved in bacteria (DUF2252)", "partial_evidence_count": null, "pfam_id": "PF10009", "proteins": 7123, "proteomes": 4473, "short_name": "DUF2252", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10009", "structures": 0, "taxa": 6204, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a family of bacterial proteins that form an integral membrane protein complex. These complexes form an alpha/alpha(8) structure. These proteins are composed of repeats of a two TM helix motif. The function of these proteins is currently unknown.", "domain_architectures": 7, "interpro_id": "IPR007140", "known_evidence_count": null, "matches": 7639, "name": "Domain of Unknown Function (DUF350)", "partial_evidence_count": null, "pfam_id": "PF03994", "proteins": 7119, "proteomes": 5751, "short_name": "DUF350", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03994", "structures": 0, "taxa": 7882, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This bacterial family of proteins have no known function.", "domain_architectures": 21, "interpro_id": "IPR021295", "known_evidence_count": null, "matches": 7086, "name": "Protein of unknown function (DUF2867)", "partial_evidence_count": null, "pfam_id": "PF11066", "proteins": 7081, "proteomes": 5951, "short_name": "DUF2867", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11066", "structures": 0, "taxa": 8150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4670, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are widely (though sparsely) distributed bacterial proteins, about 230 residues in length. All members have a motif RxxRDxRFxxx[DN]KxxY. The function of this protein family is unknown.", "domain_architectures": 20, "interpro_id": "IPR012808", "known_evidence_count": null, "matches": 7150, "name": "Conserved hypothetical protein (DUF2461)", "partial_evidence_count": null, "pfam_id": "PF09365", "proteins": 7048, "proteomes": 6081, "short_name": "DUF2461", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09365", "structures": 0, "taxa": 9261, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5765, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains a highly conserved EXR sequence motif.", "domain_architectures": 135, "interpro_id": "IPR056632", "known_evidence_count": null, "matches": 7149, "name": "Domain of unknown function (DUF7730)", "partial_evidence_count": null, "pfam_id": "PF24864", "proteins": 7034, "proteomes": 850, "short_name": "DUF7730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24864", "structures": 0, "taxa": 1663, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3329, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 23, "interpro_id": "IPR021235", "known_evidence_count": null, "matches": 7007, "name": "Protein of unknown function (DUF2637)", "partial_evidence_count": null, "pfam_id": "PF10935", "proteins": 7007, "proteomes": 2235, "short_name": "DUF2637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10935", "structures": 0, "taxa": 2921, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5534, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in Arabidopsis thaliana and contains several uncharacterised proteins.", "domain_architectures": 128, "interpro_id": "IPR007750", "known_evidence_count": null, "matches": 8898, "name": "Protein of unknown function (DUF674)", "partial_evidence_count": null, "pfam_id": "PF05056", "proteins": 6997, "proteomes": 371, "short_name": "DUF674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05056", "structures": 0, "taxa": 1037, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found singly or as up to five tandem repeats in a small set of bacterial proteins. There are two or three alpha-helices, and possibly a beta-strand.", "domain_architectures": 11, "interpro_id": "IPR007139", "known_evidence_count": null, "matches": 23114, "name": "Domain of Unknown Function (DUF349)", "partial_evidence_count": null, "pfam_id": "PF03993", "proteins": 6957, "proteomes": 6539, "short_name": "DUF349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03993", "structures": 0, "taxa": 8240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6079, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 9, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in O-mannosyl -transferases TMTC1-4, and constitutes a loop between TM7 and TM8 located in the ER lumen that contains a small hydrophobic, but not membrane-embedded helix. This loop is critical for catalysis and binding of ligands, especially the lipid-linked sugar moiety [[cite:PUB00098068]]. TMTCs transfers mannosyl residues to the hydroxyl group of serine or threonine residues. The 4 members of the TMTC family are O-mannosyl-transferases acting primarily on the cadherin superfamily; each member has distinct roles in decorating the cadherin domains with O-linked mannose glycans at specific regions. These proteins also act as O-mannosyl-transferase on other proteins such as PDIA3 [[cite:PUB00098069]].", "domain_architectures": 1307, "interpro_id": "IPR013618", "known_evidence_count": null, "matches": 6939, "name": "Protein O-mannosyl-transferase TMTC, DUF1736", "partial_evidence_count": null, "pfam_id": "PF08409", "proteins": 6936, "proteomes": 1367, "short_name": "TMTC_DUF1736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08409", "structures": 0, "taxa": 4389, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4685, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 110 amino acids in length. The family is found in association with [pfam:PF00578]. LPAM signal peptide sequence is found in some family members.", "domain_architectures": 31, "interpro_id": "IPR025380", "known_evidence_count": null, "matches": 6941, "name": "Domain of unknown function (DUF4369)", "partial_evidence_count": null, "pfam_id": "PF14289", "proteins": 6924, "proteomes": 1881, "short_name": "DUF4369", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14289", "structures": 0, "taxa": 2509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3977, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a presumed domain of unknown function that is found in a wide range of proteins that includes eukaryotic transposon protein.", "domain_architectures": 332, "interpro_id": "IPR046700", "known_evidence_count": null, "matches": 6955, "name": "Domain of unknown function (DUF6570)", "partial_evidence_count": null, "pfam_id": "PF20209", "proteins": 6915, "proteomes": 686, "short_name": "DUF6570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20209", "structures": 0, "taxa": 2302, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4684, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This DUF is sometimes found at the C-terminal end of proteins carrying a Transposase_21 domain, [pfam:PF02992].", "domain_architectures": 339, "interpro_id": "IPR025312", "known_evidence_count": null, "matches": 6912, "name": "Domain of unknown function (DUF4216)", "partial_evidence_count": null, "pfam_id": "PF13952", "proteins": 6901, "proteomes": 261, "short_name": "DUF4216", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13952", "structures": 0, "taxa": 822, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5873, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is equally distributed in both metazoa and plants. Annotation associated with [swissprot:Q9SLW7] suggest that it may be involved in response to viral attack in plants. However, no clear function has been assigned to this family.", "domain_architectures": 74, "interpro_id": "IPR006904", "known_evidence_count": null, "matches": 6932, "name": "Family of unknown function (DUF716)", "partial_evidence_count": null, "pfam_id": "PF04819", "proteins": 6890, "proteomes": 1331, "short_name": "DUF716", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04819", "structures": 1, "taxa": 4107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3957, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 50 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR022062", "known_evidence_count": null, "matches": 6885, "name": "Protein of unknown function (DUF3618)", "partial_evidence_count": null, "pfam_id": "PF12277", "proteins": 6885, "proteomes": 4250, "short_name": "DUF3618", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12277", "structures": 0, "taxa": 5380, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4539, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of putative prokaryotic signal transducing proteins of Pii-type.", "domain_architectures": 22, "interpro_id": "IPR018551", "known_evidence_count": null, "matches": 6871, "name": "Putative prokaryotic signal transducing protein", "partial_evidence_count": null, "pfam_id": "PF09413", "proteins": 6871, "proteomes": 6128, "short_name": "DUF2007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09413", "structures": 1, "taxa": 8736, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a number of uncharacterised bacterial proteins. It is predicted to form a a six-bladed beta-propeller with significant similarity to glucose/sorbosone dehydrogenases.", "domain_architectures": 317, "interpro_id": "IPR055557", "known_evidence_count": null, "matches": 7254, "name": "Domain of unknown function (DUF7133)", "partial_evidence_count": null, "pfam_id": "PF23500", "proteins": 6867, "proteomes": 1349, "short_name": "DUF7133", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23500", "structures": 0, "taxa": 2191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3381, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in uncharacterised bacterial proteins. Many members of this entry are thought to be lipoproteins. This domain may adopt a Ig-like fold.", "domain_architectures": 16, "interpro_id": "IPR025326", "known_evidence_count": null, "matches": 6853, "name": "Domain of unknown function (DUF4232)", "partial_evidence_count": null, "pfam_id": "PF14016", "proteins": 6841, "proteomes": 2440, "short_name": "DUF4232", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14016", "structures": 0, "taxa": 3022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4660, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic proteins, has no known function.", "domain_architectures": 12, "interpro_id": "IPR018639", "known_evidence_count": null, "matches": 6840, "name": "Uncharacterized protein conserved in bacteria (DUF2062)", "partial_evidence_count": null, "pfam_id": "PF09835", "proteins": 6840, "proteomes": 6079, "short_name": "DUF2062", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09835", "structures": 0, "taxa": 9353, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4569, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial and plant proteins of around 250 residues in length. The function of this family is unknown.", "domain_architectures": 48, "interpro_id": "IPR010775", "known_evidence_count": null, "matches": 7117, "name": "Protein of unknown function (DUF1365)", "partial_evidence_count": null, "pfam_id": "PF07103", "proteins": 6838, "proteomes": 6438, "short_name": "DUF1365", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07103", "structures": 0, "taxa": 10470, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of large bacterial proteins of unknown function.", "domain_architectures": 135, "interpro_id": "IPR014917", "known_evidence_count": null, "matches": 6998, "name": "Protein of unknown function (DUF1800)", "partial_evidence_count": null, "pfam_id": "PF08811", "proteins": 6783, "proteomes": 4528, "short_name": "DUF1800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08811", "structures": 0, "taxa": 6599, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4537, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function. Structurally, this family resembles TPR-like repeats.", "domain_architectures": 72, "interpro_id": "IPR010323", "known_evidence_count": null, "matches": 6784, "name": "Bacterial protein of unknown function (DUF924)", "partial_evidence_count": null, "pfam_id": "PF06041", "proteins": 6777, "proteomes": 6004, "short_name": "DUF924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06041", "structures": 1, "taxa": 9328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4099, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 20 } }, "demotion_reasons": [], "description": "This domain is found in the catalytic core RABEX-5 present in Homo sapiens. RABEX, also known as Rab GTPase exchange factors, regulate endocytic trafficking through activation of the Rab families RAB5, RAB21 and RAB22. The domain is helical in nature [[cite:PUB00042275]].", "domain_architectures": 99, "interpro_id": "IPR041545", "known_evidence_count": null, "matches": 6758, "name": "Domain of unknown function (DUF5601)", "partial_evidence_count": null, "pfam_id": "PF18151", "proteins": 6756, "proteomes": 3165, "short_name": "DUF5601", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18151", "structures": 9, "taxa": 8367, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3973, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised bacterial proteins of unknown function.", "domain_architectures": 25, "interpro_id": "IPR010296", "known_evidence_count": null, "matches": 6748, "name": "Bacterial protein of unknown function (DUF899)", "partial_evidence_count": null, "pfam_id": "PF05988", "proteins": 6714, "proteomes": 3846, "short_name": "DUF899", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05988", "structures": 0, "taxa": 5389, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4002, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of bacterial proteins have no known function. These proteins are likely to be integral membrane proteins. The proteins contain a highly conserved glutamic acid close to their C-terminus.", "domain_architectures": 5, "interpro_id": "IPR021354", "known_evidence_count": null, "matches": 6711, "name": "Protein of unknown function (DUF2975)", "partial_evidence_count": null, "pfam_id": "PF11188", "proteins": 6710, "proteomes": 5416, "short_name": "DUF2975", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11188", "structures": 0, "taxa": 7618, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4578, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is likely to act in a regulatory capacity like [pfam:PF01842] domains. This domain has a remarkable property in that the C-terminal residue of every protein in the family lies up in the alignment. This suggests that the C-terminal residue plays some important functional role (Bateman A pers obs).", "domain_architectures": 13, "interpro_id": "IPR007454", "known_evidence_count": null, "matches": 6695, "name": "Protein of unknown function (DUF493)", "partial_evidence_count": null, "pfam_id": "PF04359", "proteins": 6695, "proteomes": 6234, "short_name": "DUF493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04359", "structures": 3, "taxa": 9203, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from Arabidopsis thaliana.", "domain_architectures": 152, "interpro_id": "IPR007877", "known_evidence_count": null, "matches": 7161, "name": "Protein of unknown function (DUF707)", "partial_evidence_count": null, "pfam_id": "PF05212", "proteins": 6684, "proteomes": 528, "short_name": "DUF707", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05212", "structures": 0, "taxa": 1499, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4354, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 24, "interpro_id": "IPR007367", "known_evidence_count": null, "matches": 6683, "name": "Protein of unknown function (DUF433)", "partial_evidence_count": null, "pfam_id": "PF04255", "proteins": 6680, "proteomes": 2536, "short_name": "DUF433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04255", "structures": 2, "taxa": 4744, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3943, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains many hypothetical bacterial proteins.", "domain_architectures": 8, "interpro_id": "IPR012545", "known_evidence_count": null, "matches": 6690, "name": "Protein of unknown function (DUF1697)", "partial_evidence_count": null, "pfam_id": "PF08002", "proteins": 6677, "proteomes": 6145, "short_name": "DUF1697", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08002", "structures": 1, "taxa": 8287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5329, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised eukaryotic proteins.", "domain_architectures": 124, "interpro_id": "IPR007941", "known_evidence_count": null, "matches": 7124, "name": "Protein of unknown function (DUF726)", "partial_evidence_count": null, "pfam_id": "PF05277", "proteins": 6642, "proteomes": 3362, "short_name": "DUF726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05277", "structures": 0, "taxa": 8425, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4300, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 35, "interpro_id": "IPR018750", "known_evidence_count": null, "matches": 6638, "name": "Predicted membrane protein (DUF2306)", "partial_evidence_count": null, "pfam_id": "PF10067", "proteins": 6637, "proteomes": 4578, "short_name": "DUF2306", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10067", "structures": 0, "taxa": 7088, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This family of bacterial protein C-terminal regions is highly conserved but the function is not known. Several members are annotated as being endo-1,4-beta-xylanase-like, but this could not be confirmed, and the structure can be defined as a heat-shock cognate 70kd protein 44kd ATPase.", "domain_architectures": 60, "interpro_id": "IPR021729", "known_evidence_count": null, "matches": 6649, "name": "Protein of unknown function (DUF3298)", "partial_evidence_count": null, "pfam_id": "PF11738", "proteins": 6617, "proteomes": 4704, "short_name": "DUF3298", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11738", "structures": 5, "taxa": 6583, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5353, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a conserved region found in several uncharacterised plant proteins.", "domain_architectures": 98, "interpro_id": "IPR006740", "known_evidence_count": null, "matches": 6824, "name": "Protein of unknown function, DUF604", "partial_evidence_count": null, "pfam_id": "PF04646", "proteins": 6609, "proteomes": 993, "short_name": "DUF604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04646", "structures": 1, "taxa": 2280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5575, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents an integral membrane domain found in eukaryotic proteins. [swissprot:Q12239], a Saccharomyces cerervisiae protein, has been shown to localise COP II vesicles [[cite:PUB00016470]]. This protein has a predicted structure which shows similiarity to the rhomboid proteases.", "domain_architectures": 89, "interpro_id": "IPR061914", "known_evidence_count": null, "matches": 6654, "name": "Eukaryotic integral membrane protein (DUF1751)", "partial_evidence_count": null, "pfam_id": "PF08551", "proteins": 6596, "proteomes": 3657, "short_name": "DUF1751", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08551", "structures": 0, "taxa": 9370, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4799, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This domain is frequently found at the N-terminus of proteins carrying the glycerate kinase-like domain MOFRL, [pfam:PF05161].", "domain_architectures": 37, "interpro_id": "IPR025286", "known_evidence_count": null, "matches": 6602, "name": "Domain of unknown function (DUF4147)", "partial_evidence_count": null, "pfam_id": "PF13660", "proteins": 6574, "proteomes": 5579, "short_name": "DUF4147", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13660", "structures": 2, "taxa": 10758, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4886, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes several uncharacterised proteins.", "domain_architectures": 53, "interpro_id": "IPR006747", "known_evidence_count": null, "matches": 6716, "name": "Protein of unknown function, DUF599", "partial_evidence_count": null, "pfam_id": "PF04654", "proteins": 6557, "proteomes": 2916, "short_name": "DUF599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04654", "structures": 0, "taxa": 4652, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial and plant proteins of unknown function.", "domain_architectures": 71, "interpro_id": "IPR009297", "known_evidence_count": null, "matches": 6558, "name": "Protein of unknown function (DUF952)", "partial_evidence_count": null, "pfam_id": "PF06108", "proteins": 6552, "proteomes": 6285, "short_name": "DUF952", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06108", "structures": 3, "taxa": 10038, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4045, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function.", "domain_architectures": 5, "interpro_id": "IPR008526", "known_evidence_count": null, "matches": 6555, "name": "Protein of unknown function (DUF808)", "partial_evidence_count": null, "pfam_id": "PF05661", "proteins": 6542, "proteomes": 6449, "short_name": "DUF808", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05661", "structures": 0, "taxa": 8449, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4092, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Predicted membrane protein.", "domain_architectures": 13, "interpro_id": "IPR007401", "known_evidence_count": null, "matches": 6528, "name": "Protein of unknown function (DUF454)", "partial_evidence_count": null, "pfam_id": "PF04304", "proteins": 6528, "proteomes": 5786, "short_name": "DUF454", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04304", "structures": 0, "taxa": 8430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3921, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins.", "domain_architectures": 29, "interpro_id": "IPR015018", "known_evidence_count": null, "matches": 6414, "name": "Domain of unknown function (DUF1905)", "partial_evidence_count": null, "pfam_id": "PF08922", "proteins": 6414, "proteomes": 4133, "short_name": "DUF1905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08922", "structures": 1, "taxa": 5813, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4254, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 50 amino acids in length. This domain is found associated with [pfam:PF00037]. This domain has a single completely conserved residue N that may be functionally important.", "domain_architectures": 12, "interpro_id": "IPR022569", "known_evidence_count": null, "matches": 6412, "name": "Domain of unknown function (DUF3470)", "partial_evidence_count": null, "pfam_id": "PF11953", "proteins": 6412, "proteomes": 5697, "short_name": "DUF3470", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11953", "structures": 32, "taxa": 7784, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function.", "domain_architectures": 6, "interpro_id": "IPR009325", "known_evidence_count": null, "matches": 6391, "name": "Protein of unknown function (DUF983)", "partial_evidence_count": null, "pfam_id": "PF06170", "proteins": 6391, "proteomes": 3818, "short_name": "DUF983", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06170", "structures": 0, "taxa": 5207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5500, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Members of this family of functionally uncharacterised domains are predominantly found in dnaj-like proteins.", "domain_architectures": 87, "interpro_id": "IPR015399", "known_evidence_count": null, "matches": 6386, "name": "Domain of unknown function (DUF1977)", "partial_evidence_count": null, "pfam_id": "PF09320", "proteins": 6377, "proteomes": 3222, "short_name": "DUF1977", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09320", "structures": 0, "taxa": 8603, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "These hypothetical proteins, from bacteria such as Rhodopirellula baltica, Bacteroides thetaiotaomicron, and Porphyromonas gingivalis, share a region of conserved sequence towards their N-termini.", "domain_architectures": 105, "interpro_id": "IPR011467", "known_evidence_count": null, "matches": 6764, "name": "Protein of unknown function (DUF1573)", "partial_evidence_count": null, "pfam_id": "PF07610", "proteins": 6342, "proteomes": 2416, "short_name": "DUF1573", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07610", "structures": 0, "taxa": 3555, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5514, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 11, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family of proteins, found from plants to humans, is PRAT4 (A and B), a Protein Associated with Toll-like receptor 4. The Toll family of receptors - TLRs - plays an essential role in innate recognition of microbial products, the first line of defence against bacterial infection [[cite:PUB00109675]]. PRAT4A influences the subcellular distribution and the strength of TLR responses and alters the relative activity of each TLR. PRAT4B regulates TLR4 trafficking to the cell surface and the extent of its expression there [[cite:PUB00109676]][[cite:PUB00109677]]. TLR4 recognizes lipopolysaccharide (LPS), one of the most immuno-stimulatory glycolipids constituting the outer membrane of the Gram-negative bacteria. This family has also been described as a SAP-like MIR-interacting protein family.", "domain_architectures": 121, "interpro_id": "IPR021852", "known_evidence_count": null, "matches": 7021, "name": "TLR4 regulator and MIR-interacting MSAP", "partial_evidence_count": null, "pfam_id": "PF11938", "proteins": 6340, "proteomes": 1740, "short_name": "DUF3456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11938", "structures": 1, "taxa": 5435, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3901, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function found in viruses. This family is a P-loop member whose proteins are thought to be SF3 helicases, which are involved in replication initiation.", "domain_architectures": 120, "interpro_id": "IPR045455", "known_evidence_count": null, "matches": 6258, "name": "Family of unknown function (DUF5906)", "partial_evidence_count": null, "pfam_id": "PF19263", "proteins": 6257, "proteomes": 4308, "short_name": "DUF5906", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19263", "structures": 5, "taxa": 8166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5405, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain can be found in EH-domain-containing ATPase 2 (EHD2) present in Mus musculus. The domain is helical in nature and has extensive contacts with the G-domain [[cite:PUB00049104]].", "domain_architectures": 117, "interpro_id": "IPR040990", "known_evidence_count": null, "matches": 6295, "name": "Domain of unknown function (DUF5600)", "partial_evidence_count": null, "pfam_id": "PF18150", "proteins": 6255, "proteomes": 1994, "short_name": "DUF5600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18150", "structures": 5, "taxa": 6071, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5002, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised transmembrane domains from plants.", "domain_architectures": 71, "interpro_id": "IPR061627", "known_evidence_count": null, "matches": 6393, "name": "Domain of unknown function (DUF8558)", "partial_evidence_count": null, "pfam_id": "PF29520", "proteins": 6229, "proteomes": 397, "short_name": "DUF8558", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29520", "structures": 0, "taxa": 1117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is found frequently C-terminal to Het [pfam:PF06985] and it is predicted to fold into a beta-barrel structure similar to Het-6 beta-barrel domain.", "domain_architectures": 321, "interpro_id": "IPR058525", "known_evidence_count": null, "matches": 6224, "name": "Domain of unknown function (DUF8212)", "partial_evidence_count": null, "pfam_id": "PF26640", "proteins": 6202, "proteomes": 709, "short_name": "DUF8212", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26640", "structures": 0, "taxa": 1462, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3939, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several highly conserved hypothetical proteins of around 150 residues in length. The function of this family is unknown.", "domain_architectures": 27, "interpro_id": "IPR009783", "known_evidence_count": null, "matches": 6200, "name": "Protein of unknown function (DUF1348)", "partial_evidence_count": null, "pfam_id": "PF07080", "proteins": 6169, "proteomes": 5618, "short_name": "DUF1348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07080", "structures": 1, "taxa": 8657, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4924, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "Members of this family have several predicted transmembrane helices. One member of the family has been characterised as protein PGR (AtPGR). PGR is suggested to be a potential glucose-responsive regulator in carbohydrate metabolism in plants. This entry also includes protein VTE6, which is a Pphytyl-phosphate kinase catalysing the conversion of phytyl-monophosphate to phytyl-diphosphate [[cite:PUB00092523]].", "domain_architectures": 97, "interpro_id": "IPR002794", "known_evidence_count": null, "matches": 6228, "name": "Integral membrane protein DUF92", "partial_evidence_count": null, "pfam_id": "PF01940", "proteins": 6136, "proteomes": 4750, "short_name": "DUF92", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01940", "structures": 0, "taxa": 11004, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3739, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a presumed domain that is found associated with a variety of enzyme domains. The function of this domain is unknown.", "domain_architectures": 20, "interpro_id": "IPR046667", "known_evidence_count": null, "matches": 6088, "name": "Family of unknown function (DUF6537)", "partial_evidence_count": null, "pfam_id": "PF20169", "proteins": 6083, "proteomes": 3786, "short_name": "DUF6537", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20169", "structures": 0, "taxa": 5252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains sequences derived from proteins of unknown function expressed by Drosophila melanogaster and Anopheles gambiae.", "domain_architectures": 42, "interpro_id": "IPR012464", "known_evidence_count": null, "matches": 6218, "name": "Protein of unknown function (DUF1676)", "partial_evidence_count": null, "pfam_id": "PF07898", "proteins": 6071, "proteomes": 256, "short_name": "DUF1676", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07898", "structures": 0, "taxa": 1046, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3419, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as membrane proteins however this cannot be confirmed.", "domain_architectures": 6, "interpro_id": "IPR021401", "known_evidence_count": null, "matches": 6066, "name": "Protein of unknown function (DUF3040)", "partial_evidence_count": null, "pfam_id": "PF11239", "proteins": 6066, "proteomes": 3759, "short_name": "DUF3040", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11239", "structures": 0, "taxa": 4493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4077, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 137 and 165 amino acids in length. Proteins in this family are related to the thiosulfate transporter, but appear to be about half the length. Suggesting this family may operate as a dimer to make a functional transporter.", "domain_architectures": 25, "interpro_id": "IPR046513", "known_evidence_count": null, "matches": 6090, "name": "Family of unknown function (DUF6691)", "partial_evidence_count": null, "pfam_id": "PF20398", "proteins": 6051, "proteomes": 5423, "short_name": "DUF6691", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20398", "structures": 0, "taxa": 8400, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3658, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in bacteria. Many members are annotated as being putative membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR021215", "known_evidence_count": null, "matches": 6047, "name": "Protein of unknown function (DUF2752)", "partial_evidence_count": null, "pfam_id": "PF10825", "proteins": 6047, "proteomes": 4859, "short_name": "DUF2752", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10825", "structures": 0, "taxa": 6622, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4672, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "AntibioticMech": 1, "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "The members of this family are sequences derived from hypothetical eukaryotic and bacterial proteins. The region in question is approximately 60 residues long.", "domain_architectures": 64, "interpro_id": "IPR012875", "known_evidence_count": null, "matches": 6047, "name": "Protein of unknown function (DUF1674)", "partial_evidence_count": null, "pfam_id": "PF07896", "proteins": 6044, "proteomes": 5637, "short_name": "DUF1674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07896", "structures": 3, "taxa": 11709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3776, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is based on the first domain of the PDB structure PDB:3KD4(residues 1-228). It is structurally similar to domains in other hydrolases, eg. M1 family aminopeptidase (3ebi, Z=10, rmsd 3.6A for 152 CA, seq id 12%), despite lack of any significant sequence similarity.", "domain_architectures": 130, "interpro_id": "IPR024618", "known_evidence_count": null, "matches": 6053, "name": "Domain of Unknown Function with PDB structure (DUF3857)", "partial_evidence_count": null, "pfam_id": "PF12969", "proteins": 6025, "proteomes": 2859, "short_name": "DUF3857", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12969", "structures": 1, "taxa": 4180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are uncharacterised. They are 500-1200 amino acids in length and share a long region conservation that probably corresponds to several domains. The Go annotation for the protein indicates that it is involved in nematode larval development and has a positive regulation on growth rate.", "domain_architectures": 151, "interpro_id": "IPR004245", "known_evidence_count": null, "matches": 6613, "name": "Protein of unknown function (DUF229)", "partial_evidence_count": null, "pfam_id": "PF02995", "proteins": 6003, "proteomes": 653, "short_name": "DUF229", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02995", "structures": 0, "taxa": 2252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3592, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The sequences featured in this family are found in hypothetical archaeal and bacterial proteins of unknown function. The region in question is approximately 200 amino acids long.", "domain_architectures": 15, "interpro_id": "IPR012467", "known_evidence_count": null, "matches": 5999, "name": "Protein of unknown function (DUF1684)", "partial_evidence_count": null, "pfam_id": "PF07920", "proteins": 5991, "proteomes": 4487, "short_name": "DUF1684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07920", "structures": 4, "taxa": 5862, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3466, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of transmembrane proteins is related to ABC2 membrane transporter proteins.", "domain_architectures": 6, "interpro_id": "IPR024295", "known_evidence_count": null, "matches": 5982, "name": "Protein of unknown function (DUF2705)", "partial_evidence_count": null, "pfam_id": "PF10920", "proteins": 5982, "proteomes": 3982, "short_name": "DUF2705", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10920", "structures": 0, "taxa": 5345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3699, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 282 and 353 amino acids in length. There is a single completely conserved residue D that may be functionally important. The N-terminus contains a lipoprotein signal peptide sequence.", "domain_architectures": 10, "interpro_id": "IPR025645", "known_evidence_count": null, "matches": 5982, "name": "Domain of unknown function (DUF4349)", "partial_evidence_count": null, "pfam_id": "PF14257", "proteins": 5982, "proteomes": 5426, "short_name": "DUF4349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14257", "structures": 0, "taxa": 7753, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3600, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain that is found N-terminal to [pfam:PF13376]. The function of these proteins is unknown. These proteins contain a conserved motif ALCXGWID in the central part of the sequence. This domain is found in both bacterial and fungal proteins.", "domain_architectures": 25, "interpro_id": "IPR059456", "known_evidence_count": null, "matches": 5878, "name": "Domain of unknown function (DUF8412)", "partial_evidence_count": null, "pfam_id": "PF28474", "proteins": 5877, "proteomes": 5237, "short_name": "DUF8412", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28474", "structures": 0, "taxa": 7681, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4727, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 56, "interpro_id": "IPR025423", "known_evidence_count": null, "matches": 5873, "name": "Domain of unknown function (DUF4149)", "partial_evidence_count": null, "pfam_id": "PF13664", "proteins": 5870, "proteomes": 4152, "short_name": "DUF4149", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13664", "structures": 0, "taxa": 9406, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4950, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins from fungi. These proteins may be associated with the membrane.", "domain_architectures": 91, "interpro_id": "IPR061631", "known_evidence_count": null, "matches": 9065, "name": "Family of unknown function (DUF8562)", "partial_evidence_count": null, "pfam_id": "PF29556", "proteins": 5863, "proteomes": 879, "short_name": "DUF8562", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29556", "structures": 0, "taxa": 1815, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4479, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised eukaryotic proteins.", "domain_architectures": 208, "interpro_id": "IPR061763", "known_evidence_count": null, "matches": 6307, "name": "Domain of unknown function (DUF8702)", "partial_evidence_count": null, "pfam_id": "PF30719", "proteins": 5834, "proteomes": 217, "short_name": "DUF8702", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30719", "structures": 0, "taxa": 1010, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4782, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins that contain a set of C-terminal transmembrane helices. The family may be related to [pfam:PF10267].", "domain_architectures": 89, "interpro_id": "IPR046529", "known_evidence_count": null, "matches": 5903, "name": "Family of unknown function (DUF6594)", "partial_evidence_count": null, "pfam_id": "PF20237", "proteins": 5827, "proteomes": 856, "short_name": "DUF6594", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20237", "structures": 0, "taxa": 1703, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4957, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 9, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This short presumed domain is found close to the C-terminus of FHIP proteins, FAM160B proteins and UPF0518 family proteins.", "domain_architectures": 73, "interpro_id": "IPR045669", "known_evidence_count": null, "matches": 5825, "name": "Family of unknown function (DUF5917)", "partial_evidence_count": null, "pfam_id": "PF19314", "proteins": 5822, "proteomes": 2033, "short_name": "DUF5917", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19314", "structures": 1, "taxa": 5875, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3595, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a subclade of DUF488 domains lacking the catalytic residues common to the rhodanese-phosphatase superfamily. The C-terminal core strand is degenerate in this subclade [[cite:PUB00153826]].", "domain_architectures": 19, "interpro_id": "IPR052552", "known_evidence_count": null, "matches": 5813, "name": "Inactive DUF488-N3 subclade", "partial_evidence_count": null, "pfam_id": "PF22752", "proteins": 5812, "proteomes": 5534, "short_name": "DUF488-N3i", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22752", "structures": 0, "taxa": 8134, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4085, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family is usually found at the C-terminus of proteins.", "domain_architectures": 45, "interpro_id": "IPR037291", "known_evidence_count": null, "matches": 5835, "name": "Domain of unknown function (DUF4139)", "partial_evidence_count": null, "pfam_id": "PF13598", "proteins": 5804, "proteomes": 4060, "short_name": "DUF4139", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13598", "structures": 0, "taxa": 7178, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4987, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a fungal protein family of unknown function.", "domain_architectures": 65, "interpro_id": "IPR046496", "known_evidence_count": null, "matches": 6113, "name": "Family of unknown function (DUF6589)", "partial_evidence_count": null, "pfam_id": "PF20231", "proteins": 5801, "proteomes": 355, "short_name": "DUF6589", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20231", "structures": 0, "taxa": 1169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2436, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 145 and 166 amino acids in length. The family is found in association with [pfam:PF00412]. There are two completely conserved residues (W and L) that may be functionally important.", "domain_architectures": 55, "interpro_id": "IPR031865", "known_evidence_count": null, "matches": 8042, "name": "Domain of unknown function (DUF4757)", "partial_evidence_count": null, "pfam_id": "PF15949", "proteins": 5783, "proteomes": 999, "short_name": "DUF4757", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15949", "structures": 0, "taxa": 3296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3470, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small extracellular three helical bundle domain found at the N-terminus of proteins that contain a C-terminal [pfam:PF01944] integral membrane domain. This suggests these proteins are involved in sporulation. This domain is found in Pseudomonadati and Bacillati.", "domain_architectures": 4, "interpro_id": "IPR059457", "known_evidence_count": null, "matches": 5774, "name": "Domain of unknown function (DUF8413)", "partial_evidence_count": null, "pfam_id": "PF28475", "proteins": 5774, "proteomes": 5722, "short_name": "DUF8413", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28475", "structures": 0, "taxa": 7670, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3532, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 22, "interpro_id": "IPR021527", "known_evidence_count": null, "matches": 5829, "name": "Protein of unknown function (DUF2795)", "partial_evidence_count": null, "pfam_id": "PF11387", "proteins": 5759, "proteomes": 4180, "short_name": "DUF2795", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11387", "structures": 0, "taxa": 5661, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3822, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function.", "domain_architectures": 12, "interpro_id": "IPR008533", "known_evidence_count": null, "matches": 5774, "name": "Protein of unknown function (DUF815)", "partial_evidence_count": null, "pfam_id": "PF05673", "proteins": 5758, "proteomes": 5624, "short_name": "DUF815", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05673", "structures": 0, "taxa": 8474, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3586, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes a number of hypothetical bacterial and archaeal proteins of unknown function.", "domain_architectures": 18, "interpro_id": "IPR010718", "known_evidence_count": null, "matches": 5739, "name": "Protein of unknown function (DUF1294)", "partial_evidence_count": null, "pfam_id": "PF06961", "proteins": 5738, "proteomes": 5562, "short_name": "DUF1294", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06961", "structures": 0, "taxa": 8261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This putative domain is found in one or more copies in several plant proteins. The function of the domain is unknown.", "domain_architectures": 128, "interpro_id": "IPR046533", "known_evidence_count": null, "matches": 6189, "name": "Domain of unknown function (DUF6598)", "partial_evidence_count": null, "pfam_id": "PF20241", "proteins": 5730, "proteomes": 148, "short_name": "DUF6598", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20241", "structures": 0, "taxa": 497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4651, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from Arabidopsis thaliana and Oryza sativa. The function of this family is unknown.", "domain_architectures": 84, "interpro_id": "IPR008586", "known_evidence_count": null, "matches": 5796, "name": "Plant protein of unknown function (DUF868)", "partial_evidence_count": null, "pfam_id": "PF05910", "proteins": 5726, "proteomes": 372, "short_name": "DUF868", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05910", "structures": 0, "taxa": 1026, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3498, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria, archaea, and is approximately 170 to 200 amino acids in length. This domain is part of the glutaminase superfamily, suggesting it may have an enzymatic function. The domain is founded between two transmembrane helix domains giving it a membrane localisation.", "domain_architectures": 42, "interpro_id": "IPR025646", "known_evidence_count": null, "matches": 5708, "name": "Domain of unknown function (DUF4350)", "partial_evidence_count": null, "pfam_id": "PF14258", "proteins": 5702, "proteomes": 5273, "short_name": "DUF4350", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14258", "structures": 0, "taxa": 7409, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3793, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, archaea and eukaryotes. This domain is typically between 98 to 114 amino acids in length. This domain is found associated with [pfam:PF00144].", "domain_architectures": 83, "interpro_id": "IPR021860", "known_evidence_count": null, "matches": 5744, "name": "Domain of unknown function (DUF3471)", "partial_evidence_count": null, "pfam_id": "PF11954", "proteins": 5699, "proteomes": 3801, "short_name": "DUF3471", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11954", "structures": 1, "taxa": 5874, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4098, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins has no known function", "domain_architectures": 64, "interpro_id": "", "known_evidence_count": null, "matches": 5724, "name": "Protein of unknown function (DUF3237)", "partial_evidence_count": null, "pfam_id": "PF11578", "proteins": 5667, "proteomes": 2897, "short_name": "DUF3237", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11578", "structures": 7, "taxa": 5009, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4540, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 210 amino acids in length. This domain is found associated with [pfam:PF00226]. This domain has two conserved sequence motifs: FSH and FSH.", "domain_architectures": 159, "interpro_id": "IPR024593", "known_evidence_count": null, "matches": 7632, "name": "Domain of unknown function (DUF3444)", "partial_evidence_count": null, "pfam_id": "PF11926", "proteins": 5641, "proteomes": 380, "short_name": "DUF3444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11926", "structures": 0, "taxa": 1043, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3623, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family has structural similarity to proteins in the nucleotide-diphospho-sugar transferases superfamily. The similarity suggests that it is an enzyme with a sugar substrate.", "domain_architectures": 29, "interpro_id": "IPR018641", "known_evidence_count": null, "matches": 5625, "name": "Uncharacterized protein conserved in bacteria (DUF2064)", "partial_evidence_count": null, "pfam_id": "PF09837", "proteins": 5624, "proteomes": 4988, "short_name": "DUF2064", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09837", "structures": 1, "taxa": 7957, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3777, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function. This family appears related to [pfam:PF10755].", "domain_architectures": 18, "interpro_id": "IPR014509", "known_evidence_count": null, "matches": 5618, "name": "Predicted membrane protein (DUF2238)", "partial_evidence_count": null, "pfam_id": "PF09997", "proteins": 5616, "proteomes": 4424, "short_name": "DUF2238", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09997", "structures": 0, "taxa": 6831, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3630, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 31, "interpro_id": "IPR021314", "known_evidence_count": null, "matches": 5616, "name": "Protein of unknown function (DUF2911)", "partial_evidence_count": null, "pfam_id": "PF11138", "proteins": 5610, "proteomes": 1896, "short_name": "DUF2911", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11138", "structures": 0, "taxa": 2519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 70 residues found in BPTF (Bromodomain PHD finger transcription factor) proteins and related DDT domain-containing proteins in eukaryotes. This domain is located downstream of the WSD domain ([pfam:PF15613]). BPTF is a subunit of the NURF chromatin remodelling complex that catalyses ATP-dependent nucleosome sliding [[cite:PUB00101089]]. In plant RLT (RINGLET) proteins, this domain is also present downstream of the WSD domain. The function of this domain remains to be determined.", "domain_architectures": 200, "interpro_id": "IPR061860", "known_evidence_count": null, "matches": 5604, "name": "Domain of unknown function (DUF8799)", "partial_evidence_count": null, "pfam_id": "PF31066", "proteins": 5603, "proteomes": 1563, "short_name": "DUF8799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31066", "structures": 0, "taxa": 4976, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4122, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is related to the [pfam:PF01569] family (personal obs: C Yeats).", "domain_architectures": 73, "interpro_id": "IPR003832", "known_evidence_count": null, "matches": 5657, "name": "Divergent PAP2 family", "partial_evidence_count": null, "pfam_id": "PF02681", "proteins": 5597, "proteomes": 2648, "short_name": "DUF212", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02681", "structures": 0, "taxa": 4958, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3377, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in uncharacterised sequences from fungi. It may be a winged helix domain according to structure predictions.", "domain_architectures": 1332, "interpro_id": "IPR056681", "known_evidence_count": null, "matches": 5588, "name": "Domain of unknown function (DUF7779)", "partial_evidence_count": null, "pfam_id": "PF25000", "proteins": 5587, "proteomes": 1884, "short_name": "DUF7779", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25000", "structures": 0, "taxa": 3284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is a putative membrane protein that contains glycine zipper motifs [[cite:PUB00055608]].", "domain_architectures": 2, "interpro_id": "IPR007403", "known_evidence_count": null, "matches": 5579, "name": "Protein of unknown function (DUF456)", "partial_evidence_count": null, "pfam_id": "PF04306", "proteins": 5579, "proteomes": 5526, "short_name": "DUF456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04306", "structures": 0, "taxa": 7686, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3538, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes several proteins of uncharacterised function.", "domain_architectures": 16, "interpro_id": "IPR007433", "known_evidence_count": null, "matches": 5595, "name": "Protein of unknown function, DUF481", "partial_evidence_count": null, "pfam_id": "PF04338", "proteins": 5577, "proteomes": 4434, "short_name": "DUF481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04338", "structures": 0, "taxa": 6421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 177 to 195 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR024520", "known_evidence_count": null, "matches": 5630, "name": "Protein of unknown function (DUF3558)", "partial_evidence_count": null, "pfam_id": "PF12079", "proteins": 5575, "proteomes": 1395, "short_name": "DUF3558", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12079", "structures": 0, "taxa": 1706, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3699, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of functionally uncharacterised proteins. The family is found in eukaryotes, and represents the conserved central region of the member proteins.", "domain_architectures": 104, "interpro_id": "IPR021840", "known_evidence_count": null, "matches": 9334, "name": "Protein of unknown function (DUF3433)", "partial_evidence_count": null, "pfam_id": "PF11915", "proteins": 5555, "proteomes": 1036, "short_name": "DUF3433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11915", "structures": 0, "taxa": 2121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3617, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Bacterial protein of unknown function. One family member ([swissprot:Q97LI1]) is predicted to contain a von Willebrand factor (vWF) type A domain (Smart:VWA). Another family member YeaH is predicted to be part of a conserved signalling pathway with the kinase YeaG and the SpoVR protein YcgB. The pathway may be involved in nitrogen metabolism (see Supplementary note 5 in [[cite:PUB00093610]].)", "domain_architectures": 7, "interpro_id": "IPR006698", "known_evidence_count": null, "matches": 7057, "name": "Protein of unknown function (DUF444)", "partial_evidence_count": null, "pfam_id": "PF04285", "proteins": 5552, "proteomes": 5312, "short_name": "DUF444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04285", "structures": 0, "taxa": 7469, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised eukaryotic proteins. It has a detectable sequence similarity to protein kinase domains and it is predicted to adopt similar structure.", "domain_architectures": 82, "interpro_id": "IPR056002", "known_evidence_count": null, "matches": 5561, "name": "Domain of unknown function (DUF7580)", "partial_evidence_count": null, "pfam_id": "PF24476", "proteins": 5539, "proteomes": 808, "short_name": "DUF7580", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24476", "structures": 0, "taxa": 1618, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4810, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family is composed of sequences derived from a number of hypothetical eukaryotic proteins of unknown function.", "domain_architectures": 85, "interpro_id": "IPR012466", "known_evidence_count": null, "matches": 5584, "name": "Protein of unknown function (DUF1681)", "partial_evidence_count": null, "pfam_id": "PF07933", "proteins": 5538, "proteomes": 2935, "short_name": "DUF1681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07933", "structures": 5, "taxa": 8207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3709, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR025421", "known_evidence_count": null, "matches": 6113, "name": "Domain of unknown function (DUF4148)", "partial_evidence_count": null, "pfam_id": "PF13663", "proteins": 5538, "proteomes": 664, "short_name": "DUF4148", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13663", "structures": 0, "taxa": 876, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3729, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised fungal proteins. It shares detectable similarity to the N-terminal domain of NACHT proteins and it is predicted to adopt similar structure.", "domain_architectures": 601, "interpro_id": "IPR056125", "known_evidence_count": null, "matches": 5544, "name": "Domain of unknown function (DUF7708)", "partial_evidence_count": null, "pfam_id": "PF24809", "proteins": 5537, "proteomes": 844, "short_name": "DUF7708", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24809", "structures": 0, "taxa": 1715, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4439, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several plant proteins of unknown function.", "domain_architectures": 76, "interpro_id": "IPR008507", "known_evidence_count": null, "matches": 5951, "name": "Protein of unknown function (DUF789)", "partial_evidence_count": null, "pfam_id": "PF05623", "proteins": 5534, "proteomes": 465, "short_name": "DUF789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05623", "structures": 0, "taxa": 1279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3627, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 90 residues in length. The function of this family is unknown.", "domain_architectures": 6, "interpro_id": "IPR009711", "known_evidence_count": null, "matches": 5586, "name": "Protein of unknown function (DUF1292)", "partial_evidence_count": null, "pfam_id": "PF06949", "proteins": 5532, "proteomes": 3518, "short_name": "DUF1292", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06949", "structures": 0, "taxa": 5568, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4740, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This family consists of several of unknown function from a variety of eukaryotic organisms.", "domain_architectures": 81, "interpro_id": "IPR008564", "known_evidence_count": null, "matches": 5591, "name": "Eukaryotic protein of unknown function (DUF846)", "partial_evidence_count": null, "pfam_id": "PF05832", "proteins": 5530, "proteomes": 3237, "short_name": "DUF846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05832", "structures": 0, "taxa": 8650, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3326, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function.", "domain_architectures": 6, "interpro_id": "IPR008497", "known_evidence_count": null, "matches": 5507, "name": "Domain of unknown function (DUF779)", "partial_evidence_count": null, "pfam_id": "PF05610", "proteins": 5498, "proteomes": 5293, "short_name": "DUF779", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05610", "structures": 0, "taxa": 6875, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3088, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Domain found in bacteria with undetermined function. Its structure has been determined and is an immunoglobulin-like fold.", "domain_architectures": 15, "interpro_id": "IPR012533", "known_evidence_count": null, "matches": 5571, "name": "Domain of unknown function (DUF1775)", "partial_evidence_count": null, "pfam_id": "PF07987", "proteins": 5495, "proteomes": 4313, "short_name": "DUF1775", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07987", "structures": 4, "taxa": 5552, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3607, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins but contains one sequence ([swissprot:P40893]) from Saccharomyces cerevisiae. Members of this family are typically around 200 residues in length. The function of this family is unknown.", "domain_architectures": 104, "interpro_id": "IPR009784", "known_evidence_count": null, "matches": 5534, "name": "Protein of unknown function (DUF1349)", "partial_evidence_count": null, "pfam_id": "PF07081", "proteins": 5486, "proteomes": 4331, "short_name": "DUF1349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07081", "structures": 2, "taxa": 7131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3371, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 120 residues in length. The function of this family is unknown.", "domain_architectures": 9, "interpro_id": "IPR009732", "known_evidence_count": null, "matches": 5474, "name": "Protein of unknown function (DUF1304)", "partial_evidence_count": null, "pfam_id": "PF06993", "proteins": 5474, "proteomes": 5171, "short_name": "DUF1304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06993", "structures": 0, "taxa": 7137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2919, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is family of proteins conserved in Actinobacteria. Many members are annotated as putative membrane proteins but this could not be confirmed.", "domain_architectures": 99, "interpro_id": "IPR018929", "known_evidence_count": null, "matches": 5519, "name": "Protein of unknown function (DUF2510)", "partial_evidence_count": null, "pfam_id": "PF10708", "proteins": 5472, "proteomes": 2670, "short_name": "DUF2510", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10708", "structures": 0, "taxa": 3272, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 124, "interpro_id": "IPR021514", "known_evidence_count": null, "matches": 5449, "name": "Protein of unknown function (DUF3176)", "partial_evidence_count": null, "pfam_id": "PF11374", "proteins": 5441, "proteomes": 808, "short_name": "DUF3176", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11374", "structures": 0, "taxa": 1609, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4386, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of PSI proteins from Arabidopsis. This domain is found associated with [pfam:PF11961]. PSI1 was identified as a gene that is co-expressed with the phytosulfokine (PSK) receptor genes PSKR1 and PSKR2 in Arabidopsis thaliana. PSI proteins are plant-specific and promote growth [[cite:PUB00093967]].", "domain_architectures": 66, "interpro_id": "IPR007700", "known_evidence_count": null, "matches": 5441, "name": "Protein of unknown function (DUF668)", "partial_evidence_count": null, "pfam_id": "PF05003", "proteins": 5432, "proteomes": 380, "short_name": "DUF668", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05003", "structures": 0, "taxa": 1049, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4418, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is found in bacteria and eukaryotes. This presumed domain is typically between 143 to 227 amino acids in length.", "domain_architectures": 78, "interpro_id": "IPR021771", "known_evidence_count": null, "matches": 5418, "name": "Domain of unknown function (DUF3336)", "partial_evidence_count": null, "pfam_id": "PF11815", "proteins": 5403, "proteomes": 2403, "short_name": "DUF3336", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11815", "structures": 0, "taxa": 5273, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4056, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is predicted to fold into a alpha/beta structure that shares similarity with domains members of the Ribonuclease H-like superfamily.", "domain_architectures": 238, "interpro_id": "IPR061762", "known_evidence_count": null, "matches": 5518, "name": "Domain of unknown function (DUF8701)", "partial_evidence_count": null, "pfam_id": "PF30715", "proteins": 5398, "proteomes": 335, "short_name": "DUF8701", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30715", "structures": 0, "taxa": 1497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3449, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of proteins with unknown function found in archaea and bacteria.", "domain_architectures": 14, "interpro_id": "IPR008323", "known_evidence_count": null, "matches": 5449, "name": "Protein of unknown function (DUF1015)", "partial_evidence_count": null, "pfam_id": "PF06245", "proteins": 5367, "proteomes": 5159, "short_name": "DUF1015", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06245", "structures": 0, "taxa": 7869, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3579, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 279 and 365 amino acids in length and contain an lipoprotein attachment site at their N-terminus.", "domain_architectures": 4, "interpro_id": "IPR025345", "known_evidence_count": null, "matches": 5361, "name": "Domain of unknown function (DUF4249)", "partial_evidence_count": null, "pfam_id": "PF14054", "proteins": 5360, "proteomes": 1904, "short_name": "DUF4249", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14054", "structures": 0, "taxa": 2549, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This region appears distantly related to leucine rich repeats.", "domain_architectures": 964, "interpro_id": "IPR005046", "known_evidence_count": null, "matches": 10751, "name": "Mycoplasma protein of unknown function, DUF285", "partial_evidence_count": null, "pfam_id": "PF03382", "proteins": 5356, "proteomes": 1258, "short_name": "DUF285", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03382", "structures": 0, "taxa": 2519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3424, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Family of bacterial hypothetical proteins that is sometimes associated with GTPase domains.", "domain_architectures": 12, "interpro_id": "IPR021147", "known_evidence_count": null, "matches": 5355, "name": "Domain of unknown function (DUF697)", "partial_evidence_count": null, "pfam_id": "PF05128", "proteins": 5355, "proteomes": 4215, "short_name": "DUF697", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05128", "structures": 0, "taxa": 6642, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of PSI proteins from Arabidopsis. This domain is found associated with [pfam:PF05003]. PSI1 was identified as a gene that is co-expressed with the phytosulfokine (PSK) receptor genes PSKR1 and PSKR2 in Arabidopsis thaliana. PSI proteins are plant-specific and promote growth [[cite:PUB00093967]].", "domain_architectures": 61, "interpro_id": "IPR021864", "known_evidence_count": null, "matches": 5357, "name": "Domain of unknown function (DUF3475)", "partial_evidence_count": null, "pfam_id": "PF11961", "proteins": 5352, "proteomes": 380, "short_name": "DUF3475", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11961", "structures": 0, "taxa": 1040, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 297, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This is an uncharacterised domain that is found on the CCR4-Not complex component Not1. Not1 is a global regulator of transcription that affects genes positively and negatively and is thought to regulate transcription factor TFIID [[cite:PUB00010586]].", "domain_architectures": 202, "interpro_id": "IPR024557", "known_evidence_count": null, "matches": 5351, "name": "CCR4-Not complex, Not1 subunit, domain of unknown function DUF3819", "partial_evidence_count": null, "pfam_id": "PF12842", "proteins": 5334, "proteomes": 3046, "short_name": "DUF3819", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12842", "structures": 7, "taxa": 8104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4340, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "DUF2358 is a family of conserved proteins found from plants to humans. The function is unknown.", "domain_architectures": 96, "interpro_id": "IPR018790", "known_evidence_count": null, "matches": 5347, "name": "Uncharacterized conserved protein (DUF2358)", "partial_evidence_count": null, "pfam_id": "PF10184", "proteins": 5328, "proteomes": 1630, "short_name": "DUF2358", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10184", "structures": 0, "taxa": 5288, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4758, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 12 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in eukaryotes. This presumed domain is typically between 125 to 142 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR021802", "known_evidence_count": null, "matches": 5354, "name": "Domain of unknown function (DUF3371)", "partial_evidence_count": null, "pfam_id": "PF11851", "proteins": 5325, "proteomes": 756, "short_name": "DUF3371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11851", "structures": 3, "taxa": 2383, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3820, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 53, "interpro_id": "IPR007402", "known_evidence_count": null, "matches": 5360, "name": "Protein of unknown function (DUF455)", "partial_evidence_count": null, "pfam_id": "PF04305", "proteins": 5286, "proteomes": 4384, "short_name": "DUF455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04305", "structures": 0, "taxa": 7669, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function mainly found at the C-terminal of sequences from ticks, spiders and similar sequences from arthropods. This domain may adopt an alpha-helical bundle fold similar to Ty3 transposon capsid-like proteins.", "domain_architectures": 303, "interpro_id": "IPR061825", "known_evidence_count": null, "matches": 5297, "name": "Domain of unknown function (DUF8764)", "partial_evidence_count": null, "pfam_id": "PF30931", "proteins": 5286, "proteomes": 272, "short_name": "DUF8764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30931", "structures": 0, "taxa": 1133, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3392, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is based on the third domain of the PDB structure 3KD4(residues 410-525). It is structurally similar to part of neuropilin-2 (Z=4.6, rmsd 3.6A for 83 CA, 7% seq id). This domain and the second domain appears to be part of peptide-n-glycanase (1x3w, 2g9f).", "domain_architectures": 51, "interpro_id": "IPR024544", "known_evidence_count": null, "matches": 5270, "name": "Domain of Unknown Function with PDB structure (DUF3858)", "partial_evidence_count": null, "pfam_id": "PF12970", "proteins": 5265, "proteomes": 1921, "short_name": "DUF3858", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12970", "structures": 1, "taxa": 2789, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3329, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This small domain is found at the N-terminus of a set of likely FAD-binding proteins. It forms an alpha-beta plait fold.", "domain_architectures": 38, "interpro_id": "IPR059480", "known_evidence_count": null, "matches": 5259, "name": "Domain of unknown function (DUF8436)", "partial_evidence_count": null, "pfam_id": "PF28550", "proteins": 5259, "proteomes": 5243, "short_name": "DUF8436", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28550", "structures": 1, "taxa": 7628, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3287, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of bacterial proteins comprises various hypothetical and putative membrane proteins. Their exact function, has not, as yet, been defined.", "domain_architectures": 11, "interpro_id": "IPR018723", "known_evidence_count": null, "matches": 5242, "name": "Predicted membrane protein (DUF2254)", "partial_evidence_count": null, "pfam_id": "PF10011", "proteins": 5235, "proteomes": 4446, "short_name": "DUF2254", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10011", "structures": 0, "taxa": 6796, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3460, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family may include an HTH domain.", "domain_architectures": 26, "interpro_id": "IPR041527", "known_evidence_count": null, "matches": 5446, "name": "DUF1016 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF17761", "proteins": 5224, "proteomes": 3056, "short_name": "DUF1016_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17761", "structures": 0, "taxa": 5233, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4445, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised fungal proteins", "domain_architectures": 85, "interpro_id": "IPR046522", "known_evidence_count": null, "matches": 5230, "name": "Family of unknown function (DUF6699)", "partial_evidence_count": null, "pfam_id": "PF20415", "proteins": 5213, "proteomes": 1288, "short_name": "DUF6699", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20415", "structures": 0, "taxa": 2889, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3243, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is found at the C-terminus of tail specific proteases. Its function is unknown. This family is found in bacteria and eukaryotes. This presumed domain is typically between 88 to 187 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR020992", "known_evidence_count": null, "matches": 5206, "name": "C-terminal domain of tail specific protease (DUF3340)", "partial_evidence_count": null, "pfam_id": "PF11818", "proteins": 5206, "proteomes": 4982, "short_name": "DUF3340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11818", "structures": 6, "taxa": 6747, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 344, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Members of this family are found in various ubiquitin protein ligases.", "domain_architectures": 219, "interpro_id": "IPR010314", "known_evidence_count": null, "matches": 5279, "name": "Domain of Unknown Function (DUF913)", "partial_evidence_count": null, "pfam_id": "PF06025", "proteins": 5188, "proteomes": 2798, "short_name": "DUF913", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06025", "structures": 13, "taxa": 7364, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2794, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria, archaea and eukaryotes, and is approximately 140 amino acids in length. The family is found in association with [pfam:PF00271], [pfam:PF00176]. Most of the proteins in this family are annotated as SNF2 helicases but there is little accompanying literature to confirm this.", "domain_architectures": 21, "interpro_id": "IPR022138", "known_evidence_count": null, "matches": 5190, "name": "SNF2 Helicase protein", "partial_evidence_count": null, "pfam_id": "PF12419", "proteins": 5188, "proteomes": 3825, "short_name": "DUF3670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12419", "structures": 0, "taxa": 5631, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3297, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family corresponds to the C-terminal presumed transmembrane helix found in DUF883 proteins. The helix contains a glycine zipper motif suggestive of dimerisation.", "domain_architectures": 8, "interpro_id": "IPR043605", "known_evidence_count": null, "matches": 5187, "name": "DUF883 C-terminal glycine zipper region", "partial_evidence_count": null, "pfam_id": "PF19029", "proteins": 5187, "proteomes": 2832, "short_name": "DUF883_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19029", "structures": 0, "taxa": 3894, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4088, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in a putative tumour suppressor gene [[cite:PUB00057318]] and in a ligand for the the urokinase-type plasminogen activator receptor, which plays a role in cellular migration and adhesion [[cite:PUB00057319],[cite:PUB00057320]].", "domain_architectures": 38, "interpro_id": "IPR025232", "known_evidence_count": null, "matches": 7353, "name": "Domain of unknown function (DUF4174)", "partial_evidence_count": null, "pfam_id": "PF13778", "proteins": 5184, "proteomes": 2744, "short_name": "DUF4174", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13778", "structures": 0, "taxa": 5180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3251, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteobacterial metallo-peptidases.", "domain_architectures": 21, "interpro_id": "IPR015995", "known_evidence_count": null, "matches": 5181, "name": "Metallopeptidase family M81", "partial_evidence_count": null, "pfam_id": "PF07364", "proteins": 5172, "proteomes": 3251, "short_name": "DUF1485", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07364", "structures": 2, "taxa": 5037, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 4181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "These sequences are derived from a number of hypothetical plant proteins. The region in question is approximately 270 amino acids long. Some members of this family are annotated as yeast pheromone receptor proteins AR781 but no literature was found to support this.", "domain_architectures": 62, "interpro_id": "IPR012442", "known_evidence_count": null, "matches": 5202, "name": "Protein of unknown function (DUF1645)", "partial_evidence_count": null, "pfam_id": "PF07816", "proteins": 5158, "proteomes": 370, "short_name": "DUF1645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07816", "structures": 0, "taxa": 1014, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This approximately 50 residue region is found in a number of sequences derived from hypothetical plant proteins. This region features a highly basic 5 amino-acid stretch towards its centre.", "domain_architectures": 57, "interpro_id": "IPR012438", "known_evidence_count": null, "matches": 5176, "name": "Protein of unknown function (DUF1639)", "partial_evidence_count": null, "pfam_id": "PF07797", "proteins": 5155, "proteomes": 380, "short_name": "DUF1639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07797", "structures": 0, "taxa": 1086, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3487, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 33, "interpro_id": "IPR018531", "known_evidence_count": null, "matches": 5155, "name": "Domain of unknown function (DUF1993)", "partial_evidence_count": null, "pfam_id": "PF09351", "proteins": 5147, "proteomes": 3501, "short_name": "DUF1993", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09351", "structures": 2, "taxa": 5284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3078, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of bacterial sequences several of which are thought to be general stress proteins.", "domain_architectures": 2, "interpro_id": "IPR009293", "known_evidence_count": null, "matches": 5145, "name": "Bacterial protein of unknown function (DUF948)", "partial_evidence_count": null, "pfam_id": "PF06103", "proteins": 5145, "proteomes": 4467, "short_name": "DUF948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06103", "structures": 0, "taxa": 5722, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1665, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain is found in eukaryotes and is typically between 445 to 462 amino acids in length. Most members are annotated as being transcription initiation factor TFIID subunit 1, and this region is the conserved central portion of these proteins.", "domain_architectures": 140, "interpro_id": "IPR022591", "known_evidence_count": null, "matches": 5429, "name": "Protein of unknown function (DUF3591)", "partial_evidence_count": null, "pfam_id": "PF12157", "proteins": 5144, "proteomes": 3243, "short_name": "DUF3591", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12157", "structures": 30, "taxa": 8558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3290, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of the members of this bacterial protein family is unknown. Some members may be involved in conferring cation resistance.", "domain_architectures": 13, "interpro_id": "IPR007332", "known_evidence_count": null, "matches": 5119, "name": "Protein of unknown function, DUF411", "partial_evidence_count": null, "pfam_id": "PF04214", "proteins": 5118, "proteomes": 3661, "short_name": "DUF411", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04214", "structures": 2, "taxa": 5368, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4435, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 35 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is typically between 124 to 150 amino acids in length. This domain is found associated with [pfam:PF01858], [pfam:PF01857]. This domain has a single completely conserved residue W that may be functionally important.", "domain_architectures": 53, "interpro_id": "IPR024599", "known_evidence_count": null, "matches": 5123, "name": "Domain of unknown function (DUF3452)", "partial_evidence_count": null, "pfam_id": "PF11934", "proteins": 5112, "proteomes": 1687, "short_name": "DUF3452", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11934", "structures": 2, "taxa": 5318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3310, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family represents a series of bacterial domains of unknown function of around 50 residues in length. Members of this family are often found as tandem repeats and in some cases represent the whole protein. All member proteins are described as being hypothetical.", "domain_architectures": 29, "interpro_id": "IPR010879", "known_evidence_count": null, "matches": 7944, "name": "Domain of unknown function (DUF1508)", "partial_evidence_count": null, "pfam_id": "PF07411", "proteins": 5109, "proteomes": 4114, "short_name": "DUF1508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07411", "structures": 5, "taxa": 6061, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3267, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several proteins of uncharacterised function.", "domain_architectures": 6, "interpro_id": "IPR007435", "known_evidence_count": null, "matches": 5092, "name": "Protein of unknown function, DUF484", "partial_evidence_count": null, "pfam_id": "PF04340", "proteins": 5088, "proteomes": 4716, "short_name": "DUF484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04340", "structures": 1, "taxa": 6409, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4046, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 9, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 11 } }, "demotion_reasons": [], "description": "This domain is found in plant proteins that often carry a galactosyltransferase domain, [pfam:PF01762], at their C-terminus.", "domain_architectures": 75, "interpro_id": "IPR025298", "known_evidence_count": null, "matches": 5097, "name": "Domain of unknown function (DUF4094)", "partial_evidence_count": null, "pfam_id": "PF13334", "proteins": 5074, "proteomes": 381, "short_name": "DUF4094", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13334", "structures": 0, "taxa": 1069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4648, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family are mainly hypothetical proteins expressed by grasses.", "domain_architectures": 108, "interpro_id": "IPR011676", "known_evidence_count": null, "matches": 5266, "name": "Protein of unknown function (DUF1618)", "partial_evidence_count": null, "pfam_id": "PF07762", "proteins": 5068, "proteomes": 41, "short_name": "DUF1618", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07762", "structures": 0, "taxa": 148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family represents a conserved region in a number of uncharacterised plant proteins.", "domain_architectures": 54, "interpro_id": "IPR006460", "known_evidence_count": null, "matches": 5103, "name": "Protein of unknown function, DUF617", "partial_evidence_count": null, "pfam_id": "PF04759", "proteins": 5066, "proteomes": 377, "short_name": "DUF617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04759", "structures": 0, "taxa": 1047, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3512, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial and plant proteins of around 125 residues in length. The function of this family is unknown.", "domain_architectures": 34, "interpro_id": "IPR010865", "known_evidence_count": null, "matches": 5069, "name": "Protein of unknown function (DUF1499)", "partial_evidence_count": null, "pfam_id": "PF07386", "proteins": 5062, "proteomes": 3993, "short_name": "DUF1499", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07386", "structures": 0, "taxa": 6913, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2920, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 21, "interpro_id": "IPR018727", "known_evidence_count": null, "matches": 5157, "name": "Uncharacterized conserved protein (DUF2267)", "partial_evidence_count": null, "pfam_id": "PF10025", "proteins": 5059, "proteomes": 2550, "short_name": "DUF2267", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10025", "structures": 1, "taxa": 3953, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3179, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in found in uncharacterised proteins predominantly from bacteria. The uncharacterised [swissprot:Q9I1U6] from Pseudomonas aeruginosa shows a ferritin-like topology with a four-helix-bundle fold that lacks metal-ion-binding site typical of the ferritin family ([pfam:PF00210]) but has a potential metal-binding site [[cite:PUB00065044]]. The function is unknown.", "domain_architectures": 12, "interpro_id": "IPR019052", "known_evidence_count": null, "matches": 5046, "name": "Domain of unknown function (DUF2383)", "partial_evidence_count": null, "pfam_id": "PF09537", "proteins": 5046, "proteomes": 3489, "short_name": "DUF2383", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09537", "structures": 1, "taxa": 5006, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3039, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Although the function is not known this domain occurs almost invariably at the very C-terminus of the IMS family DNA-polymerase repair proteins, IMS, [pfam:PF00817].", "domain_architectures": 17, "interpro_id": "IPR025188", "known_evidence_count": null, "matches": 5032, "name": "Domain of unknown function (DUF4113)", "partial_evidence_count": null, "pfam_id": "PF13438", "proteins": 5032, "proteomes": 3460, "short_name": "DUF4113", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13438", "structures": 0, "taxa": 5234, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3228, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in eubacterial and archaebacterial proteins of unknown function. The proteins contain a motif HXXXEXX(W/Y) where X can be any amino acid. This motif is likely to be functionally important and may be involved in metal binding.", "domain_architectures": 16, "interpro_id": "IPR005500", "known_evidence_count": null, "matches": 4988, "name": "Domain of unknown function (DUF309)", "partial_evidence_count": null, "pfam_id": "PF03745", "proteins": 4982, "proteomes": 4259, "short_name": "DUF309", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03745", "structures": 3, "taxa": 6670, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3760, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is predicted to adopt a globular structure composed of a curved beta-sheet and helices packed on it. It contains conserved histidine and aspartate residues some of which cluster in space. This domain shares similarity with domains members of the Ribonuclease H-like superfamily.", "domain_architectures": 153, "interpro_id": "IPR057191", "known_evidence_count": null, "matches": 5023, "name": "Domain of unknown function (DUF7869)", "partial_evidence_count": null, "pfam_id": "PF25273", "proteins": 4972, "proteomes": 309, "short_name": "DUF7869", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25273", "structures": 0, "taxa": 1359, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 517, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain is found in the neurobeachins (NBEAs) and BEACH domain containing proteins (BDCPs). NBEAS are localised near Golgi apparatus and is involved in vesicular trafficking, intracellular transport, membrane dynamics, endosomal recycling, and receptor signalling. BDCPs are associated with lysosome size, apoptosis, autophagy, granule size, or synapse formation. Mutations in this domain have been related to autosomal recessively inherited lipopolysaccharide-responsive beige-like anchor (LRBA) protein deficiency, responsible for common variable immunodeficiency (CVID) and autoimmune lymphoproliferative syndrome (ALPS) [[cite:PUB00098183]]. NBEAs deficiency may induce spine loss with defects in synaptic efficacy and plasticity, being associated with autism spectrum disorder (ASD) and ASD-related syndromes [[cite:PUB00098182]].", "domain_architectures": 84, "interpro_id": "IPR010508", "known_evidence_count": null, "matches": 4996, "name": "Neurobeachin-like, DUF1088", "partial_evidence_count": null, "pfam_id": "PF06469", "proteins": 4966, "proteomes": 1181, "short_name": "DUF1088", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06469", "structures": 0, "taxa": 3860, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 313, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "", "domain_architectures": 172, "interpro_id": "IPR010309", "known_evidence_count": null, "matches": 5962, "name": "Domain of Unknown Function (DUF908)", "partial_evidence_count": null, "pfam_id": "PF06012", "proteins": 4940, "proteomes": 2701, "short_name": "DUF908", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06012", "structures": 13, "taxa": 7092, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3055, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8, "TraitMech": 1 } }, "demotion_reasons": [], "description": "This domain normally occurs as tandem repeats; however it is found as a single copy in the S. cerevisiae DNA-binding nuclear protein YCR593 ([swissprot:P25357]). This protein is involved in sporulation part of the SET3C complex, which is required to repress early/middle sporulation genes during meiosis ([[cite:PUB00019472]]). The bacterial proteins are likely to be involved in a cell wall function as they are found in conjunction with the [pfam:PF07501] domain, which is involved in various cell surface processes. This domain is also present in the resuscitation-promoting factors RpfB from Mycobacterium tuberculosis and Rpf2 from Corynebacterium glutamicum. These are factors that stimulate resuscitation of dormant cells [[cite:PUB00075582]]. This domain has a beta grasp fold. Structural description of this domain revealed a structural conservation between these domains and ubiquitin, hence it is termed UBL-G5 [[cite:PUB00137668]].", "domain_architectures": 44, "interpro_id": "IPR007137", "known_evidence_count": null, "matches": 12547, "name": "G5-linked-Ubiquitin-like domain", "partial_evidence_count": null, "pfam_id": "PF03990", "proteins": 4937, "proteomes": 4394, "short_name": "DUF348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03990", "structures": 1, "taxa": 5839, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2805, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 7, "interpro_id": "IPR021333", "known_evidence_count": null, "matches": 4945, "name": "Protein of unknown function (DUF2946)", "partial_evidence_count": null, "pfam_id": "PF11162", "proteins": 4937, "proteomes": 2912, "short_name": "DUF2946", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11162", "structures": 0, "taxa": 4021, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 243, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 340 amino acids in length. This domain is found associated with [pfam:PF00443].", "domain_architectures": 59, "interpro_id": "IPR021905", "known_evidence_count": null, "matches": 4996, "name": "Domain of unknown function (DUF3517)", "partial_evidence_count": null, "pfam_id": "PF12030", "proteins": 4934, "proteomes": 2006, "short_name": "DUF3517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12030", "structures": 2, "taxa": 5540, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3068, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "The exact function of this domain is not clear, but it frequently occurs as an N-terminal region of transposase 3 or IS3 family of insertion elements.", "domain_architectures": 24, "interpro_id": "IPR025296", "known_evidence_count": null, "matches": 4915, "name": "Domain of unknown function (DUF4158)", "partial_evidence_count": null, "pfam_id": "PF13700", "proteins": 4914, "proteomes": 2509, "short_name": "DUF4158", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13700", "structures": 4, "taxa": 4315, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3097, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in proteins expressed by bacterial or archaeal species. Some of these are annotated as being transmembrane proteins, and in fact many of these sequences contain a high proportion of hydrophobic residues. One protein containing this domain is immunity protein SdpI (swiss:O32241) from Bacillus subtilis, which provides protection for the cell against the toxic effects of its own SdpC killing factor, and also functions as a receptor/signal transduction protein [[cite:PUB00055038]].", "domain_architectures": 19, "interpro_id": "IPR012867", "known_evidence_count": null, "matches": 4912, "name": "Domain of unknown function (DUF1648)", "partial_evidence_count": null, "pfam_id": "PF07853", "proteins": 4912, "proteomes": 4034, "short_name": "DUF1648", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07853", "structures": 0, "taxa": 6352, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3904, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in insects, but also some other eukaryotes. Proteins in this family are typically between 109 and 322 amino acids in length. This domain may be involved in DNA-binding.", "domain_architectures": 293, "interpro_id": "IPR032135", "known_evidence_count": null, "matches": 4926, "name": "Helix-turn-helix domain (DUF4817)", "partial_evidence_count": null, "pfam_id": "PF16087", "proteins": 4912, "proteomes": 289, "short_name": "DUF4817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16087", "structures": 0, "taxa": 1256, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2804, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as membrane proteins however this cannot be confirmed. Currently this family of proteins has no known function.", "domain_architectures": 6, "interpro_id": "IPR016566", "known_evidence_count": null, "matches": 4997, "name": "Protein of unknown function (DUF3159)", "partial_evidence_count": null, "pfam_id": "PF11361", "proteins": 4904, "proteomes": 3672, "short_name": "DUF3159", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11361", "structures": 0, "taxa": 4367, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1490, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins.", "domain_architectures": 1345, "interpro_id": "IPR061754", "known_evidence_count": null, "matches": 5396, "name": "Domain of unknown function (DUF8693)", "partial_evidence_count": null, "pfam_id": "PF30702", "proteins": 4898, "proteomes": 1044, "short_name": "DUF8693", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30702", "structures": 4, "taxa": 1497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3081, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins that carry the highly characteristic met-zincin motif HExxHxxGxxH, the extended zinc-binding domain of metallopeptidases.", "domain_architectures": 34, "interpro_id": "IPR032534", "known_evidence_count": null, "matches": 4883, "name": "Met-zincin", "partial_evidence_count": null, "pfam_id": "PF16313", "proteins": 4879, "proteomes": 2789, "short_name": "DUF4953", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16313", "structures": 0, "taxa": 4302, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2819, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This region consists of two a pair of transmembrane helices and occurs three times in each of the family member proteins.", "domain_architectures": 8, "interpro_id": "IPR009597", "known_evidence_count": null, "matches": 14084, "name": "Domain of Unknown Function (DUF1206)", "partial_evidence_count": null, "pfam_id": "PF06724", "proteins": 4875, "proteomes": 4165, "short_name": "DUF1206", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06724", "structures": 0, "taxa": 5617, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a large family of uncharacterised fungal proteins.", "domain_architectures": 74, "interpro_id": "IPR045341", "known_evidence_count": null, "matches": 4895, "name": "Domain of unknown function (DUF6532)", "partial_evidence_count": null, "pfam_id": "PF20149", "proteins": 4845, "proteomes": 218, "short_name": "DUF6532", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20149", "structures": 0, "taxa": 617, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4083, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family is a family of eukaryotic membrane proteins. It was previously annotated as including a putative receptor for human cytomegalovirus gH [[cite:PUB00019476]] but this has has since been disputed [[cite:PUB00044752]]. Analysis of the mouse Tapt1 protein (transmembrane anterior posterior transformation 1) has shown it to be involved in patterning of the vertebrate axial skeleton.", "domain_architectures": 84, "interpro_id": "IPR008010", "known_evidence_count": null, "matches": 4980, "name": "Eukaryotic membrane protein family", "partial_evidence_count": null, "pfam_id": "PF05346", "proteins": 4804, "proteomes": 3258, "short_name": "DUF747", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05346", "structures": 0, "taxa": 8637, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3573, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family has several highly conserved GD sequence-motifs of unknown function. The family is found in bacteria, archaea and fungi.", "domain_architectures": 39, "interpro_id": "IPR025187", "known_evidence_count": null, "matches": 4806, "name": "Domain of unknown function (DUF4112)", "partial_evidence_count": null, "pfam_id": "PF13430", "proteins": 4803, "proteomes": 4032, "short_name": "DUF4112", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13430", "structures": 0, "taxa": 7043, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2982, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 203 and 228 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025324", "known_evidence_count": null, "matches": 4804, "name": "Protein of unknown function (DUF4230)", "partial_evidence_count": null, "pfam_id": "PF14014", "proteins": 4803, "proteomes": 4074, "short_name": "DUF4230", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14014", "structures": 0, "taxa": 5655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3479, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from both prokaryotes and eukaryotes. The function of this family is unknown.", "domain_architectures": 34, "interpro_id": "IPR010342", "known_evidence_count": null, "matches": 4974, "name": "Protein of unknown function (DUF938)", "partial_evidence_count": null, "pfam_id": "PF06080", "proteins": 4790, "proteomes": 4036, "short_name": "DUF938", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06080", "structures": 0, "taxa": 8134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3085, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, archaea and eukaryotes, and is approximately 120 amino acids in length.", "domain_architectures": 47, "interpro_id": "IPR025510", "known_evidence_count": null, "matches": 5884, "name": "Domain of unknown function (DUF4397)", "partial_evidence_count": null, "pfam_id": "PF14344", "proteins": 4753, "proteomes": 3223, "short_name": "DUF4397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14344", "structures": 0, "taxa": 4566, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3833, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 13 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria and eukaryotes. This domain is typically between 126 to 140 amino acids in length. This domain is found associated with [pfam:PF00487].", "domain_architectures": 54, "interpro_id": "IPR021863", "known_evidence_count": null, "matches": 4749, "name": "Domain of unknown function (DUF3474)", "partial_evidence_count": null, "pfam_id": "PF11960", "proteins": 4727, "proteomes": 1106, "short_name": "DUF3474", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11960", "structures": 0, "taxa": 3036, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3772, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This entry describes a domain of unknown function, which could adopt a similar fold to the SWEET-like (TM helices) domain. It was found in Transmembrane E3 ubiquitin-proteins and members of the DSC E3 ubiquitin ligase complex. It is predominant in fungi and plants, including the FLY1/2 proteins from Arabidopsis thaliana, the DSC complex protein from Schizosaccharomyces pombe, and TUL1 from Saccharomyces cerevisiae. This domain hasn't been functionally characterised yet but it is formed by seven alpha-helices [[cite:PUB00150892]].", "domain_architectures": 106, "interpro_id": "IPR021319", "known_evidence_count": null, "matches": 5532, "name": "Transmembrane E3 ligase/DUF2921 transmembrane domain", "partial_evidence_count": null, "pfam_id": "PF11145", "proteins": 4715, "proteomes": 1974, "short_name": "DUF2921", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11145", "structures": 0, "taxa": 4518, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3016, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain that probably has an Ig-like fold is found in three copies in BatD proteins that are involved in tolerance to oxygen in in Bacteroides spp.", "domain_architectures": 47, "interpro_id": "IPR025738", "known_evidence_count": null, "matches": 7215, "name": "BatD DUF11 like domain", "partial_evidence_count": null, "pfam_id": "PF13584", "proteins": 4713, "proteomes": 4203, "short_name": "BatD", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13584", "structures": 0, "taxa": 6064, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3004, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This domain has no known function. The domain contains three conserved cysteines at its C terminus.", "domain_architectures": 45, "interpro_id": "IPR022765", "known_evidence_count": null, "matches": 4700, "name": "Domain of unknown function DUF83", "partial_evidence_count": null, "pfam_id": "PF01930", "proteins": 4690, "proteomes": 3965, "short_name": "Cas_Cas4", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01930", "structures": 10, "taxa": 8240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family was previously missannotated in Pfam as NikM.", "domain_architectures": 14, "interpro_id": "IPR019613", "known_evidence_count": null, "matches": 4683, "name": "Domain of unknown function (DUF4198)", "partial_evidence_count": null, "pfam_id": "PF10670", "proteins": 4681, "proteomes": 3553, "short_name": "DUF4198", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10670", "structures": 8, "taxa": 5514, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2859, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes several uncharacterised bacterial proteins.", "domain_architectures": 3, "interpro_id": "IPR006938", "known_evidence_count": null, "matches": 4662, "name": "Protein of unknown function, DUF624", "partial_evidence_count": null, "pfam_id": "PF04854", "proteins": 4662, "proteomes": 2289, "short_name": "DUF624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04854", "structures": 0, "taxa": 3274, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2967, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic proteins, has no known function.", "domain_architectures": 9, "interpro_id": "IPR018637", "known_evidence_count": null, "matches": 4664, "name": "Uncharacterized protein conserved in bacteria (DUF2059)", "partial_evidence_count": null, "pfam_id": "PF09832", "proteins": 4656, "proteomes": 3913, "short_name": "DUF2059", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09832", "structures": 3, "taxa": 5564, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1957, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, archaea and eukaryotes. This domain shows structural similarity to TIR domains. This domain is found within the TEP1 (Telomerase protein component 1) protein.", "domain_architectures": 764, "interpro_id": "IPR025139", "known_evidence_count": null, "matches": 4656, "name": "Domain of unknown function (DUF4062)", "partial_evidence_count": null, "pfam_id": "PF13271", "proteins": 4653, "proteomes": 2809, "short_name": "DUF4062", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13271", "structures": 4, "taxa": 6452, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Mycobacterium tuberculosis and leprae proteins of unknown function.", "domain_architectures": 12, "interpro_id": "IPR007969", "known_evidence_count": null, "matches": 4648, "name": "Protein of unknown function (DUF732)", "partial_evidence_count": null, "pfam_id": "PF05305", "proteins": 4640, "proteomes": 1067, "short_name": "DUF732", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05305", "structures": 0, "taxa": 1726, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3915, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in eukaryotes. This presumed domain is typically between 350 to 473 amino acids in length. This domain is found associated with [pfam:PF07923].", "domain_architectures": 77, "interpro_id": "IPR021819", "known_evidence_count": null, "matches": 5835, "name": "Domain of unknown function (DUF3402)", "partial_evidence_count": null, "pfam_id": "PF11882", "proteins": 4638, "proteomes": 2743, "short_name": "DUF3402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11882", "structures": 1, "taxa": 7250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2903, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry has been described to include subclades of DUF488 domains (namely DUF488-s, for DUF488-short subclade, DUF488-l for long subclade and DUF488-u for DUF488-standalone subclade) which all which contain the ancestral core of the domain. DUF488-s commonly pairs with the DUF488-l subclade on the genome. In the case of DUF488-l and DUF488-u, the core domain is followed by a single beta-strand that stacks at the C-terminus of the core beta-sheet and a multi-helical 'cap' [[cite:PUB00153826]]. Unlike the DUF488-s and DUF488-l subclades, DUF488-u is not found adjacent to other DUF488 subclades on the genome [[cite:PUB00153826]].", "domain_architectures": 25, "interpro_id": "IPR007438", "known_evidence_count": null, "matches": 4652, "name": "Domain of unknown function DUF488", "partial_evidence_count": null, "pfam_id": "PF04343", "proteins": 4633, "proteomes": 4007, "short_name": "DUF488", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04343", "structures": 0, "taxa": 6608, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2874, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 13, "interpro_id": "IPR025196", "known_evidence_count": null, "matches": 4636, "name": "Domain of unknown function (DUF4126)", "partial_evidence_count": null, "pfam_id": "PF13548", "proteins": 4632, "proteomes": 4297, "short_name": "DUF4126", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13548", "structures": 0, "taxa": 6129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4396, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed HTH domain found in a group of uncharacterised archaeal sequences.", "domain_architectures": 17, "interpro_id": "IPR055768", "known_evidence_count": null, "matches": 4834, "name": "Domain of unknown function (DUF7344)", "partial_evidence_count": null, "pfam_id": "PF24035", "proteins": 4630, "proteomes": 319, "short_name": "DUF7344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24035", "structures": 0, "taxa": 507, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2909, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Family of hypothetical bacterial proteins.", "domain_architectures": 5, "interpro_id": "IPR007546", "known_evidence_count": null, "matches": 4622, "name": "Protein of unknown function (DUF503)", "partial_evidence_count": null, "pfam_id": "PF04456", "proteins": 4622, "proteomes": 4588, "short_name": "DUF503", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04456", "structures": 1, "taxa": 6558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2759, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This entry describes an uncharacterized domain, sometimes found in association with a PRC-barrel domain [pfam:PF05239] which is also found in rRNA processing protein RimM and in a photosynthetic reaction centre complex protein). This domain is found in proteins from Bacillus subtilis, Deinococcus radiodurans, Nostoc sp. PCC 7120, Myxococcus xanthus, and several other species. The function is not known.", "domain_architectures": 19, "interpro_id": "IPR019060", "known_evidence_count": null, "matches": 4687, "name": "Domain of unknown function (DUF2382)", "partial_evidence_count": null, "pfam_id": "PF09557", "proteins": 4597, "proteomes": 2584, "short_name": "DUF2382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09557", "structures": 0, "taxa": 3862, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3776, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a beta-sandwich structure.", "domain_architectures": 72, "interpro_id": "IPR057678", "known_evidence_count": null, "matches": 4770, "name": "Domain of unknown function (DUF7918)", "partial_evidence_count": null, "pfam_id": "PF25534", "proteins": 4594, "proteomes": 1159, "short_name": "DUF7918", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25534", "structures": 0, "taxa": 2479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3757, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family includes members such as plant proteins AtDMPs 1-10 (Arabidopsis thaliana DUF679 domain membrane proteins 1 -10) [[cite:PUB00136742]]. The AtDMP proteins are predicted to have four transmembrane spans, with cytosolic amino- and carboxy-termini. DMP1 is a membrane protein that may be involved in membrane fission during breakdown of the ER and the tonoplast during leaf senescence and in membrane fusion during vacuole biogenesis in roots [[cite:PUB00086645]]. Several DMP proteins are expressed in senescing organs (DMP1, -3, -4) or tissues that will stall later in development (DMP1, -2, -4, -7). These expression patterns strongly suggest involvement of several DMPs in various programmed cell death processes, e.g. senescence, dehiscence and abscission [[cite:PUB00136742]]. AtDMP8 and AtDMP9 however, have been shown to facilitate gamete fusion during double fertilisation in flowering plants [[cite:PUB00093467]].", "domain_architectures": 52, "interpro_id": "IPR007770", "known_evidence_count": null, "matches": 4715, "name": "Protein of unknown function (DUF679)", "partial_evidence_count": null, "pfam_id": "PF05078", "proteins": 4584, "proteomes": 395, "short_name": "DUF679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05078", "structures": 0, "taxa": 1097, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2749, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function contains four conserved cysteines and a conserved histidine, including a CXXXXH motif.", "domain_architectures": 1, "interpro_id": "IPR025242", "known_evidence_count": null, "matches": 4583, "name": "Domain of unknown function (DUF4193)", "partial_evidence_count": null, "pfam_id": "PF13834", "proteins": 4583, "proteomes": 3864, "short_name": "DUF4193", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13834", "structures": 0, "taxa": 4570, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2944, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain may fall upstream of a met-zincin domain.", "domain_architectures": 22, "interpro_id": "IPR033413", "known_evidence_count": null, "matches": 4584, "name": "Domain of unknown function (DUF5117)", "partial_evidence_count": null, "pfam_id": "PF17148", "proteins": 4582, "proteomes": 2621, "short_name": "DUF5117", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17148", "structures": 0, "taxa": 3935, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3055, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are hypothetical proteins.", "domain_architectures": 12, "interpro_id": "IPR025297", "known_evidence_count": null, "matches": 4725, "name": "Domain of unknown function (DUF4159)", "partial_evidence_count": null, "pfam_id": "PF13709", "proteins": 4575, "proteomes": 3958, "short_name": "DUF4159", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13709", "structures": 1, "taxa": 5786, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3696, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "Family of uncharacterised plant proteins.", "domain_architectures": 76, "interpro_id": "IPR045265", "known_evidence_count": null, "matches": 4627, "name": "Protein of unknown function (DUF568)", "partial_evidence_count": null, "pfam_id": "PF04526", "proteins": 4572, "proteomes": 377, "short_name": "DUF568", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04526", "structures": 0, "taxa": 1048, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3219, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family is often found at the N-terminus of its member proteins, with DUF4139, [pfam:PF13598], at the C-terminus.", "domain_architectures": 31, "interpro_id": "IPR025554", "known_evidence_count": null, "matches": 4584, "name": "N-terminal domain of unknown function (DUF4140)", "partial_evidence_count": null, "pfam_id": "PF13600", "proteins": 4568, "proteomes": 3188, "short_name": "DUF4140", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13600", "structures": 0, "taxa": 5590, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3516, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 15 } }, "demotion_reasons": [], "description": "This family represents a duplicated conserved region found in a number of uncharacterised plant proteins, potentially in the stem. There is a conserved CGP sequence motif.", "domain_architectures": 197, "interpro_id": "IPR006946", "known_evidence_count": null, "matches": 8102, "name": "Protein of unknown function (DUF642)", "partial_evidence_count": null, "pfam_id": "PF04862", "proteins": 4558, "proteomes": 970, "short_name": "DUF642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04862", "structures": 0, "taxa": 2286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2490, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 3, "interpro_id": "IPR021449", "known_evidence_count": null, "matches": 4557, "name": "Protein of unknown function (DUF3099)", "partial_evidence_count": null, "pfam_id": "PF11298", "proteins": 4557, "proteomes": 3560, "short_name": "DUF3099", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11298", "structures": 0, "taxa": 4160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 662, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This conserved domain is found in Thyroid adenoma-associated proteins (THADA) and the yeast homologue, TRM732. Trm732 forms a complex with the methyltransferase Trm7 to 2'- O-methylate tRNA residue 32 (Nm32), being required for Trm7 methylation activity. In humans, mutations of the Trm7 homologue FTSJ1, which interacts with THADA, impair Nm32 modifications, associated with non-syndromic X-linked intellectual disability [[cite:PUB00098320],[cite:PUB00098321],[cite:PUB00098322]]. It has been suggested that these proteins may play a role in additional biological processes not related to translation. This domain contains a RRSAGLP conserved motif that is required for tRNA modification activity (Funk HM et.al., Preprint from bioRxiv, 03 Jun 2021 DOI: 10.1101/2021.06.03.446962) [[cite:PUB00098320],[cite:PUB00098321],[cite:PUB00098322]].", "domain_architectures": 87, "interpro_id": "IPR019442", "known_evidence_count": null, "matches": 4613, "name": "THADA/TRM732, DUF2428", "partial_evidence_count": null, "pfam_id": "PF10350", "proteins": 4556, "proteomes": 3000, "short_name": "DUF2428", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10350", "structures": 1, "taxa": 7989, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2951, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function, however members have been suggested to be an accessory protein for sulfite reduction. This is based on the observation that they strongly cofit with various genes in the sulfate assimilation pathway in various Pseudomonas as well as in Marinobacter adhaerens HP15 and C. basilensis 4G11 (see Supplementary note 5 in [[cite:PUB00093610]].)", "domain_architectures": 6, "interpro_id": "IPR008318", "known_evidence_count": null, "matches": 4552, "name": "Bacterial protein of unknown function (DUF934)", "partial_evidence_count": null, "pfam_id": "PF06073", "proteins": 4552, "proteomes": 4216, "short_name": "DUF934", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06073", "structures": 0, "taxa": 5533, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3662, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 120 amino acids in length. The family is found in association with [pfam:PF00097]. There are two completely conserved residues (R and L) that may be functionally important.", "domain_architectures": 66, "interpro_id": "IPR022143", "known_evidence_count": null, "matches": 4563, "name": "Protein of unknown function (DUF3675)", "partial_evidence_count": null, "pfam_id": "PF12428", "proteins": 4528, "proteomes": 376, "short_name": "DUF3675", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12428", "structures": 0, "taxa": 1048, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3631, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant proteins with the AAA domain ([pfam:PF00004]). This domain is predicted to adopt an all alpha configuration.", "domain_architectures": 61, "interpro_id": "IPR056653", "known_evidence_count": null, "matches": 4529, "name": "Domain of unknown function (DUF7751)", "partial_evidence_count": null, "pfam_id": "PF24933", "proteins": 4524, "proteomes": 380, "short_name": "DUF7751", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24933", "structures": 0, "taxa": 1065, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2825, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This conserved protein (similar to YgjF), found in various prokaryotes, has no known function.", "domain_architectures": 4, "interpro_id": "IPR018644", "known_evidence_count": null, "matches": 4531, "name": "Uncharacterized conserved protein (COG2071)", "partial_evidence_count": null, "pfam_id": "PF09844", "proteins": 4522, "proteomes": 3809, "short_name": "DUF2071", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09844", "structures": 0, "taxa": 5197, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3608, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found one to three times in a group of uncharacterised plant proteins. Many members of this family are annotated as transposases.", "domain_architectures": 312, "interpro_id": "IPR058352", "known_evidence_count": null, "matches": 4606, "name": "Domain of unknown function (DUF8039)", "partial_evidence_count": null, "pfam_id": "PF26133", "proteins": 4497, "proteomes": 165, "short_name": "DUF8039", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26133", "structures": 0, "taxa": 556, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3616, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 50 amino acids in length.", "domain_architectures": 53, "interpro_id": "IPR022212", "known_evidence_count": null, "matches": 4482, "name": "Protein of unknown function (DUF3741)", "partial_evidence_count": null, "pfam_id": "PF12552", "proteins": 4480, "proteomes": 376, "short_name": "DUF3741", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12552", "structures": 0, "taxa": 1033, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2969, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of bacterial and archaeal proteins with unknown function. Some members are associated with a C-terminal peptidoglycan binding domain. So perhaps this could be an enzyme involved in peptidoglycan metabolism.", "domain_architectures": 18, "interpro_id": "IPR010430", "known_evidence_count": null, "matches": 4487, "name": "Family of unknown function (DUF1028)", "partial_evidence_count": null, "pfam_id": "PF06267", "proteins": 4479, "proteomes": 3724, "short_name": "DUF1028", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06267", "structures": 1, "taxa": 5630, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 14, "interpro_id": "IPR008023", "known_evidence_count": null, "matches": 6200, "name": "Domain of Unknown Function (DUF748)", "partial_evidence_count": null, "pfam_id": "PF05359", "proteins": 4475, "proteomes": 3512, "short_name": "DUF748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05359", "structures": 0, "taxa": 5048, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3868, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in eukaryotes. Proteins in this family are typically between 220 to 787 amino acids in length. This family belongs to the CREST superfamily [[cite:PUB00085069]], which are distant members of the GPCR superfamily.", "domain_architectures": 51, "interpro_id": "IPR021910", "known_evidence_count": null, "matches": 4599, "name": "Protein of unknown function (DUF3522)", "partial_evidence_count": null, "pfam_id": "PF12036", "proteins": 4473, "proteomes": 1621, "short_name": "DUF3522", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12036", "structures": 5, "taxa": 5007, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2528, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "PathwayMech": 1, "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 110 amino acids in length. This domain is found associated with [pfam:PF00128], [pfam:PF02922].", "domain_architectures": 17, "interpro_id": "IPR022567", "known_evidence_count": null, "matches": 4466, "name": "Domain of unknown function (DUF3459)", "partial_evidence_count": null, "pfam_id": "PF11941", "proteins": 4466, "proteomes": 3912, "short_name": "DUF3459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11941", "structures": 11, "taxa": 5139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2898, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the second domain of DUF5686 family protein.", "domain_architectures": 16, "interpro_id": "IPR043741", "known_evidence_count": null, "matches": 4451, "name": "Family of unknown function (DUF5686)", "partial_evidence_count": null, "pfam_id": "PF18939", "proteins": 4450, "proteomes": 2044, "short_name": "DUF5686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18939", "structures": 0, "taxa": 2729, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3023, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes several putative integral membrane proteins which have been predicted as the putative subunit of transporters for D-alanine or lactate (See Supplementary note 5 in [[cite:PUB00093610]]).", "domain_architectures": 6, "interpro_id": "IPR019886", "known_evidence_count": null, "matches": 4442, "name": "Domain of unknown function (DUF4212)", "partial_evidence_count": null, "pfam_id": "PF13937", "proteins": 4437, "proteomes": 4252, "short_name": "DUF4212", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13937", "structures": 0, "taxa": 6384, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2810, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 11, "interpro_id": "IPR025404", "known_evidence_count": null, "matches": 4454, "name": "Domain of unknown function (DUF4130", "partial_evidence_count": null, "pfam_id": "PF13566", "proteins": 4432, "proteomes": 4352, "short_name": "DUF4130", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13566", "structures": 0, "taxa": 6270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3860, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of fungal proteins.", "domain_architectures": 59, "interpro_id": "IPR046521", "known_evidence_count": null, "matches": 4563, "name": "Family of unknown function (DUF6698)", "partial_evidence_count": null, "pfam_id": "PF20414", "proteins": 4431, "proteomes": 191, "short_name": "DUF6698", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20414", "structures": 0, "taxa": 498, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 147 to 245 amino acids in length.", "domain_architectures": 20, "interpro_id": "IPR021836", "known_evidence_count": null, "matches": 4397, "name": "Protein of unknown function (DUF3429)", "partial_evidence_count": null, "pfam_id": "PF11911", "proteins": 4396, "proteomes": 4057, "short_name": "DUF3429", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11911", "structures": 0, "taxa": 8211, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2774, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised metazoan proteins. It is predicted to adopt a non-compact structure composed mainly of alpha-helices. This domain is sometimes found in combination with [pfam:PF00078] and [pfam:PF26215].", "domain_architectures": 378, "interpro_id": "IPR059466", "known_evidence_count": null, "matches": 4452, "name": "Domain of unknown function (DUF8422)", "partial_evidence_count": null, "pfam_id": "PF28514", "proteins": 4394, "proteomes": 322, "short_name": "DUF8422", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28514", "structures": 0, "taxa": 1497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2854, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in bacteria. This domain has an incomplete membrane beta barrel fold.", "domain_architectures": 15, "interpro_id": "IPR063082", "known_evidence_count": null, "matches": 4490, "name": "Family of unknown function (DUF5686) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF31095", "proteins": 4392, "proteomes": 2027, "short_name": "DUF5686_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31095", "structures": 0, "taxa": 2709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3475, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several uncharacterised plant proteins.", "domain_architectures": 66, "interpro_id": "IPR008479", "known_evidence_count": null, "matches": 6307, "name": "Protein of unknown function (DUF760)", "partial_evidence_count": null, "pfam_id": "PF05542", "proteins": 4391, "proteomes": 762, "short_name": "DUF760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05542", "structures": 0, "taxa": 2071, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3517, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 81 and 97 amino acids in length. The proteins in the family are often annotated as wound-induced proteins however there is little accompanying literature to confirm this.", "domain_architectures": 49, "interpro_id": "IPR022251", "known_evidence_count": null, "matches": 4574, "name": "Wound-induced protein", "partial_evidence_count": null, "pfam_id": "PF12609", "proteins": 4377, "proteomes": 360, "short_name": "DUF3774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12609", "structures": 0, "taxa": 989, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2665, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised bacterial proteins.", "domain_architectures": 8, "interpro_id": "IPR007511", "known_evidence_count": null, "matches": 4406, "name": "Protein of unknown function (DUF501)", "partial_evidence_count": null, "pfam_id": "PF04417", "proteins": 4375, "proteomes": 4323, "short_name": "DUF501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04417", "structures": 0, "taxa": 5481, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2642, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are annotated as putative inner membrane proteins.", "domain_architectures": 7, "interpro_id": "IPR025291", "known_evidence_count": null, "matches": 4368, "name": "Domain of unknown function (DUF4153)", "partial_evidence_count": null, "pfam_id": "PF13687", "proteins": 4354, "proteomes": 4039, "short_name": "DUF4153", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13687", "structures": 0, "taxa": 5794, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3544, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised, found in bacteria and fungi. Proteins in this family are typically between 392 and 644 amino acids in length. According to structure predictions, this domain may have a cupin-like fold.", "domain_architectures": 123, "interpro_id": "IPR049192", "known_evidence_count": null, "matches": 4696, "name": "Protein of unknown function (DUF4246)", "partial_evidence_count": null, "pfam_id": "PF14033", "proteins": 4354, "proteomes": 1303, "short_name": "DUF4246", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14033", "structures": 0, "taxa": 2721, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain is specific to the human splicing factor 3b subunit 2 and it's orthologues. Splicing factor 3b subunit 2 or SAP145 is a suppressor of U2 snRNA mutations. Pre-mRNA splicing is catalysed by a large ribonucleoprotein complex called the spliceosome. Spliceosomes are multi-component enzymes that catalyse pre-mRNA splicing and form step-wise by the ordered interaction of UsnRNPs and non-snRNP proteins with short conserved regions of the pre-mRNA at the 5' and 3' splice sites and branch site [[cite:PUB00013034]].", "domain_architectures": 60, "interpro_id": "IPR007180", "known_evidence_count": null, "matches": 4397, "name": "Domain of unknown function (DUF382)", "partial_evidence_count": null, "pfam_id": "PF04037", "proteins": 4347, "proteomes": 3033, "short_name": "DUF382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04037", "structures": 57, "taxa": 8016, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2789, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins. They appear to belong to the outer membrane beta barrel superfamily.", "domain_architectures": 4, "interpro_id": "IPR019619", "known_evidence_count": null, "matches": 4333, "name": "Protein of unknown function (DUF2490)", "partial_evidence_count": null, "pfam_id": "PF10677", "proteins": 4332, "proteomes": 2223, "short_name": "DUF2490", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10677", "structures": 0, "taxa": 3122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3561, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins.", "domain_architectures": 45, "interpro_id": "IPR006873", "known_evidence_count": null, "matches": 4480, "name": "Protein of unknown function (DUF620)", "partial_evidence_count": null, "pfam_id": "PF04788", "proteins": 4330, "proteomes": 373, "short_name": "DUF620", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04788", "structures": 0, "taxa": 1030, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2639, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and archaea. Proteins in this family are typically between 145 to 860 amino acids in length. This protein is found associated with [pfam:PF00343]. This protein has a conserved AYF sequence motif.", "domain_architectures": 19, "interpro_id": "IPR024517", "known_evidence_count": null, "matches": 4311, "name": "Protein of unknown function (DUF3417)", "partial_evidence_count": null, "pfam_id": "PF11897", "proteins": 4311, "proteomes": 4077, "short_name": "DUF3417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11897", "structures": 8, "taxa": 6141, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2946, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Predicted membrane protein with four transmembrane helices.", "domain_architectures": 3, "interpro_id": "IPR007352", "known_evidence_count": null, "matches": 4306, "name": "Protein of unknown function (DUF420)", "partial_evidence_count": null, "pfam_id": "PF04238", "proteins": 4306, "proteomes": 3704, "short_name": "DUF420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04238", "structures": 0, "taxa": 5115, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3873, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in eukaryotes. This presumed domain is about 70 amino acids in length.", "domain_architectures": 42, "interpro_id": "IPR021805", "known_evidence_count": null, "matches": 4298, "name": "Domain of unknown function (DUF3377)", "partial_evidence_count": null, "pfam_id": "PF11857", "proteins": 4298, "proteomes": 743, "short_name": "DUF3377", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11857", "structures": 1, "taxa": 2271, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2780, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 11, "interpro_id": "IPR048389", "known_evidence_count": null, "matches": 4677, "name": "Predicted membrane protein (DUF2207) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20990", "proteins": 4298, "proteomes": 3582, "short_name": "DUF2207_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20990", "structures": 0, "taxa": 5478, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2728, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria and archaea. This presumed domain is typically between 117 to 158 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR024560", "known_evidence_count": null, "matches": 4293, "name": "Domain of unknown function (DUF3362)", "partial_evidence_count": null, "pfam_id": "PF11842", "proteins": 4293, "proteomes": 4226, "short_name": "DUF3362", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11842", "structures": 0, "taxa": 6414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2616, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 14, "interpro_id": "IPR019286", "known_evidence_count": null, "matches": 5069, "name": "Predicted membrane protein (DUF2339)", "partial_evidence_count": null, "pfam_id": "PF10101", "proteins": 4289, "proteomes": 4191, "short_name": "DUF2339", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10101", "structures": 0, "taxa": 6159, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2600, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of various hypothetical proteins from cyanobacteria, none of which are functionally described. The aligned region is approximately 120-140 amino acids long corresponding to almost the entire length of the proteins in the family. [swissprot:Q2RPE2], PDB:3fcn, is a small protein that has a novel all-alpha fold. The N-terminal helical hairpin is likely to function as a dimerisation module. This protein is a member of PFam family PF01724. The function of this protein is unknown. One protein sequence contains a fusion of this protein and a DnaB domain, suggesting a possible role in DNA helicase activity (hypothetical). Dali hits have low Z and high rmsd, suggesting probably only topological similarities (not functional relevance) (details derived from TOPSAN). The family has several highly conserved sequence motifs, including YD/ExD, DxxNVxEEIE, and CPY/F/W, as well as conserved tryptophans.", "domain_architectures": 11, "interpro_id": "IPR002636", "known_evidence_count": null, "matches": 4280, "name": "Domain of unknown function DUF29", "partial_evidence_count": null, "pfam_id": "PF01724", "proteins": 4280, "proteomes": 791, "short_name": "DUF29", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01724", "structures": 1, "taxa": 1622, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2687, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a putative component of efflux pumps that comprise MFP and FUSC proteins. Several members are in an operon with and have similar mutants phenotypes as an RND efflux pump and a fusaric acid resistance-like protein [[cite:PUB00093610]]. This system is involved in transporting diverse substrates including 4-hydroxybenzoate and octanoate [[cite:PUB00106931]].", "domain_architectures": 1, "interpro_id": "IPR012451", "known_evidence_count": null, "matches": 4265, "name": "Protein of unknown function (DUF1656)", "partial_evidence_count": null, "pfam_id": "PF07869", "proteins": 4265, "proteomes": 2613, "short_name": "DUF1656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07869", "structures": 0, "taxa": 3566, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1716, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 60 amino acids in length. The family is found in association with [pfam:PF05057].", "domain_architectures": 29, "interpro_id": "IPR022122", "known_evidence_count": null, "matches": 4259, "name": "Protein FAM135", "partial_evidence_count": null, "pfam_id": "PF12394", "proteins": 4258, "proteomes": 1471, "short_name": "DUF3657", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12394", "structures": 0, "taxa": 4685, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 18, "interpro_id": "IPR024498", "known_evidence_count": null, "matches": 4238, "name": "Protein of unknown function (DUF2786)", "partial_evidence_count": null, "pfam_id": "PF10979", "proteins": 4238, "proteomes": 3588, "short_name": "DUF2786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10979", "structures": 0, "taxa": 5482, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2882, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains proteins of unknown function from archaeal, bacterial and plant species.", "domain_architectures": 46, "interpro_id": "IPR008537", "known_evidence_count": null, "matches": 4418, "name": "Protein of unknown function (DUF819)", "partial_evidence_count": null, "pfam_id": "PF05684", "proteins": 4232, "proteomes": 2948, "short_name": "DUF819", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05684", "structures": 0, "taxa": 5131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 80 amino acids in length.", "domain_architectures": 133, "interpro_id": "IPR032071", "known_evidence_count": null, "matches": 4330, "name": "Domain of unknown function (DUF4806)", "partial_evidence_count": null, "pfam_id": "PF16064", "proteins": 4220, "proteomes": 365, "short_name": "DUF4806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16064", "structures": 0, "taxa": 1433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3582, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family is found at the very C-terminus of proteins that carry a G-patch domain, [pfam:PF01585]. The domain is short and cysteine-rich.", "domain_architectures": 58, "interpro_id": "IPR025239", "known_evidence_count": null, "matches": 4205, "name": "Domain of unknown function (DUF4187)", "partial_evidence_count": null, "pfam_id": "PF13821", "proteins": 4203, "proteomes": 2874, "short_name": "DUF4187", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13821", "structures": 0, "taxa": 7658, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2760, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 167 and 182 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR025250", "known_evidence_count": null, "matches": 4202, "name": "Protein of unknown function (DUF4199)", "partial_evidence_count": null, "pfam_id": "PF13858", "proteins": 4202, "proteomes": 2266, "short_name": "DUF4199", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13858", "structures": 0, "taxa": 3106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2050, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "", "domain_architectures": 49, "interpro_id": "IPR025451", "known_evidence_count": null, "matches": 4200, "name": "Domain of unknown function (DUF4211)", "partial_evidence_count": null, "pfam_id": "PF13926", "proteins": 4193, "proteomes": 2154, "short_name": "DUF4211", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13926", "structures": 0, "taxa": 6023, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2485, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "Members of these family are putative lipoproteins that fall into the Antigen MPT63/MPB63 (immunoprotective extracellular protein) superfamily.", "domain_architectures": 41, "interpro_id": "IPR029051", "known_evidence_count": null, "matches": 4227, "name": "Domain of unknown function (DUF4352)", "partial_evidence_count": null, "pfam_id": "PF11611", "proteins": 4179, "proteomes": 2845, "short_name": "DUF4352", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11611", "structures": 2, "taxa": 4337, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2501, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Members of this family are found in a set of prokaryotic hypothetical proteins. Their exact function, has not, as yet, been defined. This entry represents the C-terminal domain.", "domain_architectures": 9, "interpro_id": "IPR048447", "known_evidence_count": null, "matches": 4164, "name": "DUF1980 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF21537", "proteins": 4163, "proteomes": 3427, "short_name": "DUF1980_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21537", "structures": 0, "taxa": 4998, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2900, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 26, "interpro_id": "IPR018720", "known_evidence_count": null, "matches": 4764, "name": "Uncharacterized conserved protein (DUF2249)", "partial_evidence_count": null, "pfam_id": "PF10006", "proteins": 4156, "proteomes": 2464, "short_name": "DUF2249", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10006", "structures": 0, "taxa": 3942, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3801, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins. Based on its distant similarity to [pfam:PF02221] and conserved pattern of cysteine residues it is possible that these domains are also lipid binding.", "domain_architectures": 49, "interpro_id": "IPR010512", "known_evidence_count": null, "matches": 4459, "name": "Protein of unknown function (DUF1091)", "partial_evidence_count": null, "pfam_id": "PF06477", "proteins": 4153, "proteomes": 158, "short_name": "DUF1091", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06477", "structures": 0, "taxa": 632, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2580, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of short bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR021741", "known_evidence_count": null, "matches": 4149, "name": "Protein of unknown function (DUF3311)", "partial_evidence_count": null, "pfam_id": "PF11755", "proteins": 4149, "proteomes": 3058, "short_name": "DUF3311", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11755", "structures": 0, "taxa": 4086, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2290, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 5, "interpro_id": "IPR025447", "known_evidence_count": null, "matches": 4564, "name": "Domain of unknown function (DUF4192)", "partial_evidence_count": null, "pfam_id": "PF13830", "proteins": 4146, "proteomes": 3389, "short_name": "DUF4192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13830", "structures": 0, "taxa": 3943, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3433, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The sequences found in this family are all derived from hypothetical plant proteins of unknown function. The region features a number of highly conserved cysteine residues.", "domain_architectures": 43, "interpro_id": "IPR012876", "known_evidence_count": null, "matches": 4163, "name": "Protein of unknown function (DUF1677)", "partial_evidence_count": null, "pfam_id": "PF07911", "proteins": 4145, "proteomes": 378, "short_name": "DUF1677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07911", "structures": 0, "taxa": 1073, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2691, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain found in biotin carboxyl carrier protein of acetyl-CoA carboxylase proteins. Structure prediction suggests this domain may mediate homodimerisation.", "domain_architectures": 4, "interpro_id": "IPR061745", "known_evidence_count": null, "matches": 4142, "name": "Domain of unknown function (DUF8684)", "partial_evidence_count": null, "pfam_id": "PF30639", "proteins": 4142, "proteomes": 4103, "short_name": "DUF8684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30639", "structures": 1, "taxa": 5514, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2563, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 475 residues in length. The majority of family members are from Pseudomonas species but the family also contains sequences from Shewanella oneidensis and Thauera aromatica.", "domain_architectures": 16, "interpro_id": "IPR010752", "known_evidence_count": null, "matches": 4143, "name": "Protein of unknown function (DUF1329)", "partial_evidence_count": null, "pfam_id": "PF07044", "proteins": 4141, "proteomes": 1465, "short_name": "DUF1329", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07044", "structures": 0, "taxa": 2071, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2317, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 110 residues found in uncharacterised proteins in bacteria, predominantly in Actinomycetes (Streptomyces, Micromonospora) and some Bacilli. This domain adopts an immunoglobulin-like fold and is a member of clan CL0159. Many proteins contain two tandem copies of this domain. The function of this domain remains to be determined.", "domain_architectures": 18, "interpro_id": "IPR061893", "known_evidence_count": null, "matches": 7783, "name": "Domain of unknown function (DUF8832)", "partial_evidence_count": null, "pfam_id": "PF31173", "proteins": 4135, "proteomes": 2747, "short_name": "DUF8832", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31173", "structures": 0, "taxa": 3766, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2710, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found at the N-terminal of a group of poorly characterised bacterial sequences. The function of this domain is unknown.", "domain_architectures": 24, "interpro_id": "IPR055396", "known_evidence_count": null, "matches": 4189, "name": "Domain of unknown function (DUF7088)", "partial_evidence_count": null, "pfam_id": "PF23357", "proteins": 4112, "proteomes": 3777, "short_name": "DUF7088", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23357", "structures": 0, "taxa": 6165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3320, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of sequences found in a number of hypothetical plant proteins of unknown function. The region of interest contains nine highly conserved cysteine residues and is approximately 160 amino acids in length, and is probably a zinc-binding domain.", "domain_architectures": 70, "interpro_id": "IPR012866", "known_evidence_count": null, "matches": 4397, "name": "Protein of unknown function (DUF1644)", "partial_evidence_count": null, "pfam_id": "PF07800", "proteins": 4111, "proteomes": 382, "short_name": "DUF1644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07800", "structures": 0, "taxa": 1118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is typically between 439 to 459 amino acids in length. This domain is found associated with [pfam:PF00271], [pfam:PF02985], [pfam:PF00176]. This domain has two completely conserved residues (P and K) that may be functionally important.", "domain_architectures": 117, "interpro_id": "IPR022707", "known_evidence_count": null, "matches": 4195, "name": "Domain of unknown function (DUF3535)", "partial_evidence_count": null, "pfam_id": "PF12054", "proteins": 4104, "proteomes": 3104, "short_name": "DUF3535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12054", "structures": 5, "taxa": 8240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2663, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of unknown function mostly found in Rhizobium species. Members of this family have an alpha/beta hydrolase fold.", "domain_architectures": 52, "interpro_id": "IPR010297", "known_evidence_count": null, "matches": 4147, "name": "Alpha/beta hydrolase of unknown function (DUF900)", "partial_evidence_count": null, "pfam_id": "PF05990", "proteins": 4099, "proteomes": 2650, "short_name": "DUF900", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05990", "structures": 0, "taxa": 4529, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3507, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 8, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family is found in eukaryotes. It is a coiled-coil domain of unknwon function.", "domain_architectures": 60, "interpro_id": "IPR025252", "known_evidence_count": null, "matches": 4110, "name": "Domain of unknown function (DUF4200)", "partial_evidence_count": null, "pfam_id": "PF13863", "proteins": 4099, "proteomes": 1324, "short_name": "DUF4200", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13863", "structures": 5, "taxa": 4259, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2969, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 200 and 228 amino acids in length. There is a conserved GCP sequence motif near the N-terminus.", "domain_architectures": 28, "interpro_id": "IPR025649", "known_evidence_count": null, "matches": 4112, "name": "Domain of unknown function (DUF4360)", "partial_evidence_count": null, "pfam_id": "PF14273", "proteins": 4097, "proteomes": 1337, "short_name": "DUF4360", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14273", "structures": 0, "taxa": 2248, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2462, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. They are presicted to adopt a structure with similarity to members of the Bet v 1-like superfamily.", "domain_architectures": 43, "interpro_id": "IPR018960", "known_evidence_count": null, "matches": 4498, "name": "Domain of unknown function (DUF1990)", "partial_evidence_count": null, "pfam_id": "PF09348", "proteins": 4093, "proteomes": 3184, "short_name": "DUF1990", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09348", "structures": 0, "taxa": 4631, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2672, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 11, "interpro_id": "IPR018702", "known_evidence_count": null, "matches": 4100, "name": "Predicted membrane protein (DUF2207) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF09972", "proteins": 4093, "proteomes": 3457, "short_name": "DUF2207", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09972", "structures": 0, "taxa": 5387, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2576, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of predicted outer membrane beta barrel proteins. These proteins remain uncharacterised. They are approximately 600 residues long. These proteins are likely part of an exporter system that includes an MMPL exporter, a DUF1329 protein [pfam:PF07044] family protein that likely acts as a LolA-like chaperone.", "domain_architectures": 4, "interpro_id": "IPR010727", "known_evidence_count": null, "matches": 4085, "name": "Protein of unknown function (DUF1302)", "partial_evidence_count": null, "pfam_id": "PF06980", "proteins": 4085, "proteomes": 1779, "short_name": "DUF1302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06980", "structures": 0, "taxa": 2737, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2585, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 17, "interpro_id": "IPR018673", "known_evidence_count": null, "matches": 4079, "name": "Uncharacterized protein conserved in bacteria (DUF2141)", "partial_evidence_count": null, "pfam_id": "PF09912", "proteins": 4079, "proteomes": 2713, "short_name": "DUF2141", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09912", "structures": 0, "taxa": 4304, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2317, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 4, "interpro_id": "IPR021678", "known_evidence_count": null, "matches": 4072, "name": "Protein of unknown function (DUF3263)", "partial_evidence_count": null, "pfam_id": "PF11662", "proteins": 4072, "proteomes": 3695, "short_name": "DUF3263", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11662", "structures": 2, "taxa": 4443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3407, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in eukaryotes. Proteins in this family are typically between 291 to 390 amino acids in length. This protein has a conserved NLRC sequence motif.", "domain_architectures": 107, "interpro_id": "IPR021838", "known_evidence_count": null, "matches": 4146, "name": "Protein of unknown function (DUF3431)", "partial_evidence_count": null, "pfam_id": "PF11913", "proteins": 4066, "proteomes": 930, "short_name": "DUF3431", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11913", "structures": 0, "taxa": 2010, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2588, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria, archaea and eukaryotes, and is approximately 120 amino acids in length. The family is found in association with [pfam:PF01136].", "domain_architectures": 14, "interpro_id": "IPR020988", "known_evidence_count": null, "matches": 4068, "name": "Collagenase", "partial_evidence_count": null, "pfam_id": "PF12392", "proteins": 4066, "proteomes": 3922, "short_name": "DUF3656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12392", "structures": 0, "taxa": 6281, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2090, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. However, they fold into a compact domain that is structurally related to the Phospholipase D protein family ([pfam:PF13091]). This suggests they may have an enzymatic activity.", "domain_architectures": 7, "interpro_id": "IPR049244", "known_evidence_count": null, "matches": 4068, "name": "Domain of unknown function (DUF6879)", "partial_evidence_count": null, "pfam_id": "PF21806", "proteins": 4066, "proteomes": 1340, "short_name": "DUF6879", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21806", "structures": 0, "taxa": 1609, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain consisting of a novel repeat fold which containing five repeats, each of them comprising three antiparallel beta-strands and a short alpha-helix, according to structure predictions (e.g SwissProt:S8CFV9). This domain is found in Casein kinase 1-like protein HD16 from rice, a protein involved in the regulation of flowering time through gibberellin (GA) signaling and independently of photoperiod [[cite:PUB00155615]].", "domain_architectures": 97, "interpro_id": "IPR055900", "known_evidence_count": null, "matches": 4215, "name": "Domain of unknown function (DUF7477)", "partial_evidence_count": null, "pfam_id": "PF24289", "proteins": 4059, "proteomes": 496, "short_name": "DUF7477", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24289", "structures": 0, "taxa": 1395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3040, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Domain that is sometimes present in iron-sulphur proteins.", "domain_architectures": 27, "interpro_id": "IPR007160", "known_evidence_count": null, "matches": 4077, "name": "Domain of unknown function (DUF362)", "partial_evidence_count": null, "pfam_id": "PF04015", "proteins": 4054, "proteomes": 1971, "short_name": "DUF362", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04015", "structures": 0, "taxa": 4185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3090, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 82, "interpro_id": "IPR033433", "known_evidence_count": null, "matches": 4169, "name": "Domain of unknown function (DUF5127)", "partial_evidence_count": null, "pfam_id": "PF17168", "proteins": 4053, "proteomes": 1843, "short_name": "DUF5127", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17168", "structures": 0, "taxa": 3557, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2257, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are found in various bacterial hypothetical proteins, as well as Rhs element Vgr proteins.", "domain_architectures": 42, "interpro_id": "IPR018769", "known_evidence_count": null, "matches": 4053, "name": "Uncharacterized protein conserved in bacteria (DUF2345)", "partial_evidence_count": null, "pfam_id": "PF10106", "proteins": 4050, "proteomes": 1178, "short_name": "DUF2345", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10106", "structures": 3, "taxa": 1787, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3017, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 174 to 251 amino acids in length.", "domain_architectures": 32, "interpro_id": "IPR021851", "known_evidence_count": null, "matches": 4104, "name": "Protein of unknown function (DUF3455)", "partial_evidence_count": null, "pfam_id": "PF11937", "proteins": 4050, "proteomes": 2397, "short_name": "DUF3455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11937", "structures": 0, "taxa": 4182, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2326, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 23 } }, "demotion_reasons": [], "description": "This entry represents a long alpha helical region found in dynactin-like proteins from eukaryotes. This region may mediate oligomerisation forming a coiled-coil.", "domain_architectures": 49, "interpro_id": "IPR059265", "known_evidence_count": null, "matches": 4049, "name": "Domain of unknown function (DUF8221)", "partial_evidence_count": null, "pfam_id": "PF26666", "proteins": 4048, "proteomes": 1798, "short_name": "DUF8221", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26666", "structures": 19, "taxa": 4724, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2210, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 70 and 180 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR025629", "known_evidence_count": null, "matches": 4048, "name": "Domain of unknown function (DUF4287)", "partial_evidence_count": null, "pfam_id": "PF14117", "proteins": 4047, "proteomes": 3313, "short_name": "DUF4287", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14117", "structures": 0, "taxa": 4435, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3246, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several uncharacterised proteins found in Arabidopsis thaliana.", "domain_architectures": 57, "interpro_id": "IPR007789", "known_evidence_count": null, "matches": 4271, "name": "Protein of unknown function (DUF688)", "partial_evidence_count": null, "pfam_id": "PF05097", "proteins": 4039, "proteomes": 378, "short_name": "DUF688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05097", "structures": 0, "taxa": 1040, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 10, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "Members of this family are found in various putative zinc finger proteins.", "domain_architectures": 53, "interpro_id": "", "known_evidence_count": null, "matches": 4180, "name": "Domain of unknown function (DUF702)", "partial_evidence_count": null, "pfam_id": "PF05142", "proteins": 4031, "proteomes": 691, "short_name": "DUF702", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05142", "structures": 0, "taxa": 2200, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found at the C-terminal of the epsilon catalytic subunit of DNA polymerase. It is found C terminal to [pfam:PF03104] and [pfam:PF00136].", "domain_architectures": 127, "interpro_id": "IPR013697", "known_evidence_count": null, "matches": 4174, "name": "Domain of unknown function (DUF1744)", "partial_evidence_count": null, "pfam_id": "PF08490", "proteins": 4030, "proteomes": 3173, "short_name": "DUF1744", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08490", "structures": 22, "taxa": 8413, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 28, "interpro_id": "IPR021454", "known_evidence_count": null, "matches": 4029, "name": "Protein of unknown function (DUF3105)", "partial_evidence_count": null, "pfam_id": "PF11303", "proteins": 4026, "proteomes": 3090, "short_name": "DUF3105", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11303", "structures": 0, "taxa": 5244, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 399, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 33 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in eukaryotes. This presumed domain is typically between 422 to 486 amino acids in length. This domain is found associated with [pfam:PF02145].", "domain_architectures": 48, "interpro_id": "IPR024584", "known_evidence_count": null, "matches": 4140, "name": "Domain of unknown function (DUF3384)", "partial_evidence_count": null, "pfam_id": "PF11864", "proteins": 4026, "proteomes": 2365, "short_name": "DUF3384", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11864", "structures": 3, "taxa": 6322, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2557, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 215 and 302 amino acids in length. There is a DE motif at the N-terminus and a QXXD motif at the C-terminus that may be functionally important.", "domain_architectures": 7, "interpro_id": "IPR024524", "known_evidence_count": null, "matches": 4014, "name": "Protein of unknown function (DUF3800)", "partial_evidence_count": null, "pfam_id": "PF12686", "proteins": 4014, "proteomes": 3397, "short_name": "DUF3800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12686", "structures": 0, "taxa": 6139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1869, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain might be involved in the biosynthesis of the molybdopterin cofactor in E.coli.", "domain_architectures": 38, "interpro_id": "IPR025406", "known_evidence_count": null, "matches": 4004, "name": "Domain of unknown function (DUF4132)", "partial_evidence_count": null, "pfam_id": "PF13569", "proteins": 3995, "proteomes": 2133, "short_name": "DUF4132", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13569", "structures": 0, "taxa": 3194, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2476, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain represents a ribosome-associating protein predicted to mediate translation inhibition alongside repair of DNA damage or restriction in conflict contexts. A subset of this family contains a conserved histidine residue, raising the possibility that it directly acts as a RNase or in RNA end-processing [[cite:PUB00097693]].", "domain_architectures": 15, "interpro_id": "IPR018691", "known_evidence_count": null, "matches": 3990, "name": "Uncharacterized protein conserved in bacteria (DUF2188)", "partial_evidence_count": null, "pfam_id": "PF09954", "proteins": 3987, "proteomes": 3119, "short_name": "DUF2188", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09954", "structures": 0, "taxa": 5021, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2998, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "NTPase_I-T is a family of NTPases with supreme activity against ITP and XTP. Active site analysis and structure comparison of YjjX strongly suggested that it is an NTP binding protein with nucleoside triphosphatase activity. YjjX exhibits a mixed alpha-beta fold [[cite:PUB00038960],[cite:PUB00037841]].", "domain_architectures": 24, "interpro_id": "IPR026533", "known_evidence_count": null, "matches": 4030, "name": "Protein of unknown function DUF84", "partial_evidence_count": null, "pfam_id": "PF01931", "proteins": 3984, "proteomes": 3631, "short_name": "NTPase_I-T", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01931", "structures": 4, "taxa": 7463, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This short domain is found in fungi, plants and animals, and the proteins appear to be necessary for chromosome segregation during meiosis.", "domain_architectures": 39, "interpro_id": "IPR025261", "known_evidence_count": null, "matches": 3979, "name": "Domain of unknown function (DUF4210)", "partial_evidence_count": null, "pfam_id": "PF13915", "proteins": 3976, "proteomes": 2444, "short_name": "DUF4210", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13915", "structures": 0, "taxa": 6680, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR021400", "known_evidence_count": null, "matches": 3958, "name": "Protein of unknown function (DUF3039)", "partial_evidence_count": null, "pfam_id": "PF11238", "proteins": 3958, "proteomes": 3865, "short_name": "DUF3039", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11238", "structures": 0, "taxa": 4615, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2386, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 5, "interpro_id": "IPR021246", "known_evidence_count": null, "matches": 3955, "name": "Protein of unknown function (DUF2797)", "partial_evidence_count": null, "pfam_id": "PF10977", "proteins": 3954, "proteomes": 3913, "short_name": "DUF2797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10977", "structures": 0, "taxa": 5107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR021426", "known_evidence_count": null, "matches": 3951, "name": "Protein of unknown function (DUF3073)", "partial_evidence_count": null, "pfam_id": "PF11273", "proteins": 3951, "proteomes": 3792, "short_name": "DUF3073", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11273", "structures": 0, "taxa": 4492, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2730, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of around 250 residues in length which are found in both plants and bacteria. The function of this family is unknown. Structurally it lies in the Thioredoxin-like superfamily.", "domain_architectures": 22, "interpro_id": "IPR010634", "known_evidence_count": null, "matches": 3963, "name": "Protein of unknown function (DUF1223)", "partial_evidence_count": null, "pfam_id": "PF06764", "proteins": 3945, "proteomes": 3312, "short_name": "DUF1223", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06764", "structures": 1, "taxa": 5423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is typically between 460 to 473 amino acids in length. This domain is found associated with [pfam:PF00270], [pfam:PF00271].", "domain_architectures": 9, "interpro_id": "IPR021904", "known_evidence_count": null, "matches": 3996, "name": "Domain of unknown function (DUF3516)", "partial_evidence_count": null, "pfam_id": "PF12029", "proteins": 3945, "proteomes": 3900, "short_name": "DUF3516", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12029", "structures": 0, "taxa": 4779, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2673, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised bacterial proteins of unknown function.", "domain_architectures": 7, "interpro_id": "IPR007948", "known_evidence_count": null, "matches": 4095, "name": "Protein of unknown function (DUF736)", "partial_evidence_count": null, "pfam_id": "PF05284", "proteins": 3942, "proteomes": 1509, "short_name": "DUF736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05284", "structures": 0, "taxa": 2328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2496, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 13, "interpro_id": "IPR009282", "known_evidence_count": null, "matches": 4372, "name": "Bacterial protein of unknown function (DUF937)", "partial_evidence_count": null, "pfam_id": "PF06078", "proteins": 3932, "proteomes": 3374, "short_name": "DUF937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06078", "structures": 0, "taxa": 4881, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 136 to 304 amino acids in length. This region represents a transmembrane region found at the C-terminus of the proteins.", "domain_architectures": 9, "interpro_id": "IPR021949", "known_evidence_count": null, "matches": 3946, "name": "Transmembrane domain of unknown function (DUF3566)", "partial_evidence_count": null, "pfam_id": "PF12089", "proteins": 3929, "proteomes": 3853, "short_name": "DUF3566", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12089", "structures": 0, "taxa": 4699, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2426, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "A family of uncharacterised proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]].", "domain_architectures": 78, "interpro_id": "IPR025048", "known_evidence_count": null, "matches": 4095, "name": "Protein of unknown function (DUF3987)", "partial_evidence_count": null, "pfam_id": "PF13148", "proteins": 3922, "proteomes": 2813, "short_name": "DUF3987", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13148", "structures": 0, "taxa": 5270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2457, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family has four conserved cysteines, which is suggestive of a metal binding function.", "domain_architectures": 2, "interpro_id": "IPR011437", "known_evidence_count": null, "matches": 5619, "name": "Domain of Unknown Function (DUF1540)", "partial_evidence_count": null, "pfam_id": "PF07561", "proteins": 3921, "proteomes": 2828, "short_name": "DUF1540", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07561", "structures": 0, "taxa": 4055, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2525, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found at the C-terminal of patatin-like proteins from bacteria. There is a conserved tyrosine residue and a conserved FxxxPP sequence motif.", "domain_architectures": 8, "interpro_id": "IPR045943", "known_evidence_count": null, "matches": 3908, "name": "Domain of unknown function (DUF6363)", "partial_evidence_count": null, "pfam_id": "PF19890", "proteins": 3908, "proteomes": 3172, "short_name": "DUF6363", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19890", "structures": 0, "taxa": 4643, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 170 amino acids in length. There is a conserved ALE sequence motif.", "domain_architectures": 77, "interpro_id": "IPR022085", "known_evidence_count": null, "matches": 3919, "name": "Protein of unknown function (DUF3632)", "partial_evidence_count": null, "pfam_id": "PF12311", "proteins": 3906, "proteomes": 893, "short_name": "DUF3632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12311", "structures": 0, "taxa": 1840, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3396, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "CellStructureMech": 1, "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family of short eukaryotic proteins has no known function. Most of the members of this family are only 80 amino acid residues long. However the Arabidopsis homologue is over 300 residues long. The presumed domain contains a conserved amino terminal cysteine and a conserved motif GXGXGXG in the carboxy terminal half that may be functionally important.", "domain_architectures": 41, "interpro_id": "IPR007512", "known_evidence_count": null, "matches": 3910, "name": "Domain of unknown function (DUF543)", "partial_evidence_count": null, "pfam_id": "PF04418", "proteins": 3901, "proteomes": 2958, "short_name": "DUF543", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04418", "structures": 0, "taxa": 7989, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2708, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial and fungal proteins has several members annotated as being putative molybdopterin-guanine dinucleotide biosynthesis protein A; however this could not be verified. Hence the function is not known. This family also includes the DUF3532 that was found to be related and was merged into this family. Members of this family also fall into the NE0471 N-terminal domain-like superfamily, a family of proteins with a unique fold in SCOP:143880.", "domain_architectures": 25, "interpro_id": "IPR018841", "known_evidence_count": null, "matches": 3902, "name": "Protein of unknown function (DUF2442)", "partial_evidence_count": null, "pfam_id": "PF10387", "proteins": 3900, "proteomes": 2496, "short_name": "DUF2442", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10387", "structures": 3, "taxa": 4598, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2427, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function. The N-terminal domain found in this entry is related to [pfam:PF05532].", "domain_architectures": 3, "interpro_id": "IPR043604", "known_evidence_count": null, "matches": 3896, "name": "DUF883 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF05957", "proteins": 3896, "proteomes": 2175, "short_name": "DUF883", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05957", "structures": 0, "taxa": 2882, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2286, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins and transcriptional activators, has no known function. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 35, "interpro_id": "IPR018656", "known_evidence_count": null, "matches": 3891, "name": "Uncharacterized protein conserved in bacteria (DUF2087)", "partial_evidence_count": null, "pfam_id": "PF09860", "proteins": 3891, "proteomes": 3355, "short_name": "DUF2087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09860", "structures": 0, "taxa": 4859, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3292, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised and it is found in the central region of fungal SPB1 and mammalian homologue FTSJ3. This domain is found associated with [pfam:PF07780], [pfam:PF01728]. SPB1 is an adoMet-dependent rRNA methyltransferase required for proper assembly of pre-ribosomal particles during the biogenesis of the 60S ribosomal subunit [[cite:PUB00016377]]. FTSJ3, SPB1 homologue in humans, is associated with NIP7 (involved in the biogenesis of 40S subunit) and functions in pre-rRNA processing [[cite:PUB00068805]].", "domain_architectures": 77, "interpro_id": "IPR024576", "known_evidence_count": null, "matches": 3912, "name": "Ribosomal RNA methyltransferase Spb1, DUF3381", "partial_evidence_count": null, "pfam_id": "PF11861", "proteins": 3891, "proteomes": 3174, "short_name": "DUF3381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11861", "structures": 35, "taxa": 8437, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2291, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 2, "interpro_id": "IPR025445", "known_evidence_count": null, "matches": 3882, "name": "Domain of unknown function (DUF4191)", "partial_evidence_count": null, "pfam_id": "PF13829", "proteins": 3882, "proteomes": 3863, "short_name": "DUF4191", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13829", "structures": 0, "taxa": 4577, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as membrane proteins. This cannot be confirmed.", "domain_architectures": 3, "interpro_id": "IPR021403", "known_evidence_count": null, "matches": 3879, "name": "Protein of unknown function (DUF3043)", "partial_evidence_count": null, "pfam_id": "PF11241", "proteins": 3879, "proteomes": 3858, "short_name": "DUF3043", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11241", "structures": 0, "taxa": 4588, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 237 and 284 amino acids in length. There are two conserved sequence motifs: DLG and DGPRW.", "domain_architectures": 8, "interpro_id": "IPR022183", "known_evidence_count": null, "matches": 3877, "name": "Protein of unknown function (DUF3710)", "partial_evidence_count": null, "pfam_id": "PF12502", "proteins": 3873, "proteomes": 3798, "short_name": "DUF3710", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12502", "structures": 0, "taxa": 4470, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2004, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in bacteria.", "domain_architectures": 5, "interpro_id": "IPR043737", "known_evidence_count": null, "matches": 4116, "name": "Family of unknown function (DUF5682)", "partial_evidence_count": null, "pfam_id": "PF18934", "proteins": 3862, "proteomes": 2882, "short_name": "DUF5682", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18934", "structures": 0, "taxa": 4069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3331, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 23 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 144 and 173 amino acids in length. The family is found in association with [pfam:PF00884].", "domain_architectures": 20, "interpro_id": "IPR024609", "known_evidence_count": null, "matches": 4724, "name": "Sulfatase protein", "partial_evidence_count": null, "pfam_id": "PF12548", "proteins": 3855, "proteomes": 1064, "short_name": "DUF3740", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12548", "structures": 0, "taxa": 3500, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2037, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in large multi-domain proteins. The domain is typically located between N-terminal domains, such as lamin tail domains ([pfam:PF00932]) or cadherin-like domains, and C-terminal regions containing endonuclease/exonuclease ([pfam:PF03372], [pfam:PF19580]) or calcium-binding repeat domains ([pfam:PF00353]). The function of this domain remains to be determined.", "domain_architectures": 459, "interpro_id": "IPR061578", "known_evidence_count": null, "matches": 3863, "name": "Domain of unknown function (DUF8508)", "partial_evidence_count": null, "pfam_id": "PF29190", "proteins": 3848, "proteomes": 3545, "short_name": "DUF8508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29190", "structures": 0, "taxa": 5602, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently there is no known function.", "domain_architectures": 11, "interpro_id": "IPR022603", "known_evidence_count": null, "matches": 3848, "name": "Protein of unknown function (DUF3152)", "partial_evidence_count": null, "pfam_id": "PF11350", "proteins": 3845, "proteomes": 2716, "short_name": "DUF3152", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11350", "structures": 0, "taxa": 3234, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently there is no known function.", "domain_architectures": 2, "interpro_id": "IPR021517", "known_evidence_count": null, "matches": 3835, "name": "Protein of unknown function (DUF3180)", "partial_evidence_count": null, "pfam_id": "PF11377", "proteins": 3835, "proteomes": 3826, "short_name": "DUF3180", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11377", "structures": 0, "taxa": 4500, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes bacterial proteins of unknown function.", "domain_architectures": 35, "interpro_id": "IPR029475", "known_evidence_count": null, "matches": 3841, "name": "Family of unknown function (DUF6807)", "partial_evidence_count": null, "pfam_id": "PF14100", "proteins": 3835, "proteomes": 2201, "short_name": "DUF6807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14100", "structures": 0, "taxa": 3006, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2060, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 605, "interpro_id": "IPR013431", "known_evidence_count": null, "matches": 16666, "name": "Domain of unknown function (DUF5122) beta-propeller", "partial_evidence_count": null, "pfam_id": "PF17164", "proteins": 3833, "proteomes": 2090, "short_name": "DUF5122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17164", "structures": 0, "taxa": 3316, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2291, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Member proteins often found in Actinomycetes clustered with signal peptidase and/or RNAse-HII.", "domain_architectures": 5, "interpro_id": "IPR019592", "known_evidence_count": null, "matches": 3831, "name": "Protein of unknown function (DUF2469)", "partial_evidence_count": null, "pfam_id": "PF10611", "proteins": 3831, "proteomes": 3820, "short_name": "DUF2469", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10611", "structures": 0, "taxa": 4534, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This functionally uncharacterised, N-terminal domain is found in a number of bacterial proteins, including Cyclic di-GMP phosphodiesterase PA4108 ([swissprot:Q9HWS0]). It is often found associated with the HD domain [pfam:PF13328].", "domain_architectures": 10, "interpro_id": "IPR021812", "known_evidence_count": null, "matches": 3829, "name": "Domain of unknown function (DUF3391)", "partial_evidence_count": null, "pfam_id": "PF11871", "proteins": 3829, "proteomes": 2061, "short_name": "DUF3391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11871", "structures": 0, "taxa": 2946, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2681, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "Although this family has overlaps with SLBB, the majority of its sequences are unique. Several family members, eg UniProtKB:A0RGA8, that do not overlap have an LPXTG-cell wall anchor at their C-terminus, a SSF_Family 10_polysaccharide_lyase or Glycosyltransferase structure associated with them in the middle region, as shown by InterPro, as well as this domain at the N-terminus.", "domain_architectures": 237, "interpro_id": "IPR027954", "known_evidence_count": null, "matches": 4032, "name": "Domain of unknown function (DUF4430)", "partial_evidence_count": null, "pfam_id": "PF14478", "proteins": 3827, "proteomes": 2349, "short_name": "DUF4430", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14478", "structures": 9, "taxa": 5024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2379, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 50 amino acids in length. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR022134", "known_evidence_count": null, "matches": 3822, "name": "Protein of unknown function (DUF3667)", "partial_evidence_count": null, "pfam_id": "PF12412", "proteins": 3822, "proteomes": 2506, "short_name": "DUF3667", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12412", "structures": 0, "taxa": 3387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family is conserved from fungi to Metazoa and includes plants. The function is not known, but several members have zinc-finger domain, zf-MYND, [pfam:PF01753], at their very C-terminus. Others are also associated with DUF1279, [pfam:PF06916].", "domain_architectures": 124, "interpro_id": "IPR027974", "known_evidence_count": null, "matches": 3844, "name": "Domain of unknown function (DUF4470)", "partial_evidence_count": null, "pfam_id": "PF14737", "proteins": 3822, "proteomes": 1799, "short_name": "DUF4470", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14737", "structures": 0, "taxa": 5066, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2231, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is an alpha-helical domain found in gene neighborhoods that contain genes encoding ubiquitin, cysteine synthases and JAB peptidases [[cite:PUB00034476]].", "domain_architectures": 4, "interpro_id": "IPR018561", "known_evidence_count": null, "matches": 3823, "name": "Domain of unknown function (DUF2017)", "partial_evidence_count": null, "pfam_id": "PF09438", "proteins": 3819, "proteomes": 3718, "short_name": "DUF2017", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09438", "structures": 0, "taxa": 4448, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2275, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as ATP-binding proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR021456", "known_evidence_count": null, "matches": 3806, "name": "Protein of unknown function (DUF3107)", "partial_evidence_count": null, "pfam_id": "PF11305", "proteins": 3806, "proteomes": 3798, "short_name": "DUF3107", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11305", "structures": 2, "taxa": 4473, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2435, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family consists of bacterial proteins. YjgK (TabA) influences biofilm formation by toxin-antitoxin systems [[cite:PUB00078078]]. Another member of this family, YhcH, is a possible sugar isomerase of sialic acid catabolism [[cite:PUB00054289]].", "domain_architectures": 8, "interpro_id": "IPR004375", "known_evidence_count": null, "matches": 3805, "name": "YhcH/YjgK/YiaL", "partial_evidence_count": null, "pfam_id": "PF04074", "proteins": 3803, "proteomes": 2623, "short_name": "DUF386", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04074", "structures": 4, "taxa": 4146, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2217, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as DNA-binding proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 2, "interpro_id": "IPR021421", "known_evidence_count": null, "matches": 3803, "name": "Protein of unknown function (DUF3071)", "partial_evidence_count": null, "pfam_id": "PF11268", "proteins": 3803, "proteomes": 3786, "short_name": "DUF3071", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11268", "structures": 0, "taxa": 4495, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2243, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR021408", "known_evidence_count": null, "matches": 3801, "name": "Protein of unknown function (DUF3046)", "partial_evidence_count": null, "pfam_id": "PF11248", "proteins": 3801, "proteomes": 3786, "short_name": "DUF3046", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11248", "structures": 0, "taxa": 4468, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 66 and 95 amino acids in length. There is a conserved EYA sequence motif.", "domain_architectures": 13, "interpro_id": "IPR025338", "known_evidence_count": null, "matches": 3798, "name": "Protein of unknown function (DUF4244)", "partial_evidence_count": null, "pfam_id": "PF14029", "proteins": 3798, "proteomes": 3734, "short_name": "DUF4244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14029", "structures": 0, "taxa": 4420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 5, "interpro_id": "IPR021391", "known_evidence_count": null, "matches": 3850, "name": "Protein of unknown function (DUF3027)", "partial_evidence_count": null, "pfam_id": "PF11228", "proteins": 3790, "proteomes": 3749, "short_name": "DUF3027", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11228", "structures": 0, "taxa": 4482, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of integral membrane proteins has no known function. The family includes members with two or four transmembrane helices.", "domain_architectures": 6, "interpro_id": "IPR021529", "known_evidence_count": null, "matches": 4699, "name": "Domain of unknown function (DUF2798)", "partial_evidence_count": null, "pfam_id": "PF11391", "proteins": 3790, "proteomes": 3235, "short_name": "DUF2798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11391", "structures": 0, "taxa": 4798, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 137 and 164 amino acids in length. These proteins are integral membrane proteins with four transmembrane helices. The contain several conserved histidines and AlphaFold 3 predicts a confident zinc binding site. Structure prediction also suggests that these proteins might form a homotetrameric complex UniProt:A0A3B9LPY9 iPTM=0.9. The four subunits are alternating in different orientations in the presumed membrane. The structure prediction also suggests a central pore between the subunits.", "domain_architectures": 5, "interpro_id": "", "known_evidence_count": null, "matches": 3778, "name": "Domain of unknown function (DUF4383)", "partial_evidence_count": null, "pfam_id": "PF14325", "proteins": 3778, "proteomes": 2396, "short_name": "DUF4383", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14325", "structures": 0, "taxa": 3221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of prokaryotic proteins with unknown function. Contains a number of highly conserved polar residues that could suggest an enzymatic activity.", "domain_architectures": 5, "interpro_id": "IPR026325", "known_evidence_count": null, "matches": 3803, "name": "Domain of unknown function (DUF932)", "partial_evidence_count": null, "pfam_id": "PF06067", "proteins": 3775, "proteomes": 2622, "short_name": "DUF932", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06067", "structures": 0, "taxa": 4473, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3038, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family are hypothetical eukaryotic proteins of unknown function. The region in question is approximately 100 amino acid residues long.", "domain_architectures": 59, "interpro_id": "IPR012881", "known_evidence_count": null, "matches": 3772, "name": "Protein of unknown function (DUF1685)", "partial_evidence_count": null, "pfam_id": "PF07939", "proteins": 3768, "proteomes": 374, "short_name": "DUF1685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07939", "structures": 0, "taxa": 1024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2576, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of conserved fungal and bacterial membrane proteins with unknown function.", "domain_architectures": 10, "interpro_id": "IPR013879", "known_evidence_count": null, "matches": 3769, "name": "Protein of unknown function (DUF1761)", "partial_evidence_count": null, "pfam_id": "PF08570", "proteins": 3768, "proteomes": 3415, "short_name": "DUF1761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08570", "structures": 0, "taxa": 5717, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2433, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a beta barrel domain found in primarily in bacteria, but also in archaea and in kinetoplastids. Proteins in this family are typically between 150 and 242 amino acids in length. The domain is often found in integral membrane proteins. This family contains the Tsi4 immunity protein from P. aeruginosa which acts as an immunity protein to the Tse4 toxin [[cite:PUB00155609]]. AlphaFold multimer modelling shows that these two protein are likely to interact directly.", "domain_architectures": 22, "interpro_id": "IPR021994", "known_evidence_count": null, "matches": 3919, "name": "Domain of unknown function (DUF3592)", "partial_evidence_count": null, "pfam_id": "PF12158", "proteins": 3762, "proteomes": 2802, "short_name": "DUF3592", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12158", "structures": 0, "taxa": 4789, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 3, "interpro_id": "IPR021555", "known_evidence_count": null, "matches": 3765, "name": "Protein of unknown function (DUF3000)", "partial_evidence_count": null, "pfam_id": "PF11452", "proteins": 3761, "proteomes": 3750, "short_name": "DUF3000", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11452", "structures": 0, "taxa": 4421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021398", "known_evidence_count": null, "matches": 3759, "name": "Protein of unknown function (DUF3037)", "partial_evidence_count": null, "pfam_id": "PF11236", "proteins": 3759, "proteomes": 3636, "short_name": "DUF3037", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11236", "structures": 0, "taxa": 4955, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from fungi. It is predicted to contain seven transmembrane helices.", "domain_architectures": 59, "interpro_id": "IPR056120", "known_evidence_count": null, "matches": 3830, "name": "Domain of unknown function (DUF7703)", "partial_evidence_count": null, "pfam_id": "PF24802", "proteins": 3749, "proteomes": 728, "short_name": "DUF7703", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24802", "structures": 0, "taxa": 1419, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2215, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR021412", "known_evidence_count": null, "matches": 3748, "name": "Protein of unknown function (DUF3052)", "partial_evidence_count": null, "pfam_id": "PF11253", "proteins": 3748, "proteomes": 3650, "short_name": "DUF3052", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11253", "structures": 0, "taxa": 4487, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3, "TraitMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 116, "interpro_id": "", "known_evidence_count": null, "matches": 3817, "name": "Protein of unknown function (DUF3223)", "partial_evidence_count": null, "pfam_id": "PF11523", "proteins": 3748, "proteomes": 741, "short_name": "DUF3223", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11523", "structures": 19, "taxa": 2035, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2333, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins and Radical Sam domain proteins, has no known function. This domain is distantly related to tRNA pseudouridine synthases, suggesting this family may carry out a function related to RNA modification. But this family appears to lack the catalytic aspartate found in pseudouridine synthases.", "domain_architectures": 11, "interpro_id": "IPR018768", "known_evidence_count": null, "matches": 3743, "name": "Uncharacterized protein conserved in bacteria (DUF2344)", "partial_evidence_count": null, "pfam_id": "PF10105", "proteins": 3741, "proteomes": 3719, "short_name": "DUF2344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10105", "structures": 0, "taxa": 5969, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2940, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised fungal proteins that also contain the domain [pfam:PF24883] at its N-terminal end. This domain is predicted to have a mainly alpha helical configuration.", "domain_architectures": 157, "interpro_id": "IPR056693", "known_evidence_count": null, "matches": 3745, "name": "Domain of unknown function (DUF7791)", "partial_evidence_count": null, "pfam_id": "PF25053", "proteins": 3739, "proteomes": 671, "short_name": "DUF7791", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25053", "structures": 0, "taxa": 1348, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2673, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 126 and 142 amino acids in length.", "domain_architectures": 61, "interpro_id": "IPR025363", "known_evidence_count": null, "matches": 3738, "name": "Domain of unknown function (DUF4267)", "partial_evidence_count": null, "pfam_id": "PF14087", "proteins": 3737, "proteomes": 2193, "short_name": "DUF4267", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14087", "structures": 0, "taxa": 3495, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2097, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised actinobacterial zinc binding domains. The proteins contain a characteristic CXHH motif. Only the second of those two histidines acts as the zinc ligand according to structure prediction (ipTM = 0.94).", "domain_architectures": 2, "interpro_id": "IPR055878", "known_evidence_count": null, "matches": 3726, "name": "Domain of unknown function (DUF7455)", "partial_evidence_count": null, "pfam_id": "PF24254", "proteins": 3726, "proteomes": 3498, "short_name": "DUF7455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24254", "structures": 0, "taxa": 4187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 993, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 17 } }, "demotion_reasons": [], "description": "This domain, found in Synaptojanin, has no known function.", "domain_architectures": 24, "interpro_id": "IPR015047", "known_evidence_count": null, "matches": 3740, "name": "Domain of unknown function (DUF1866)", "partial_evidence_count": null, "pfam_id": "PF08952", "proteins": 3724, "proteomes": 1173, "short_name": "DUF1866", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08952", "structures": 2, "taxa": 3875, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in eukaryotes. Proteins in this family are typically between 435 to 791 amino acids in length. This family is related to [pfam:PF00589] suggesting it may be an integrase enzyme.", "domain_architectures": 95, "interpro_id": "IPR021842", "known_evidence_count": null, "matches": 3997, "name": "Protein of unknown function (DUF3435)", "partial_evidence_count": null, "pfam_id": "PF11917", "proteins": 3722, "proteomes": 736, "short_name": "DUF3435", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11917", "structures": 0, "taxa": 1583, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2364, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of several hypothetical bacterial proteins, including SPO0140 from Ruegeria pomeroyi ([swissprot:Q5LWU5]). It folds into a a beta-meander-alpha-helix- beta-meander core bound to a twisted mixed six-stranded beta-sheet. Its specific function is unknown [[cite:PUB00062529]].", "domain_architectures": 5, "interpro_id": "IPR048341", "known_evidence_count": null, "matches": 3716, "name": "Domain of unknown function (DUF1285), N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF06938", "proteins": 3716, "proteomes": 3706, "short_name": "DUF1285_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06938", "structures": 2, "taxa": 4895, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3001, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of AT14A like proteins from Arabidopsis thaliana. At14a has a small domain that has sequence similarities to integrins from fungi, insects and humans. Transcripts of At14a are found in all Arabidopsis tissues and localises partly to the plasma membrane [[cite:PUB00010152]].", "domain_architectures": 66, "interpro_id": "IPR007749", "known_evidence_count": null, "matches": 3822, "name": "Protein of unknown function (DUF677)", "partial_evidence_count": null, "pfam_id": "PF05055", "proteins": 3710, "proteomes": 378, "short_name": "DUF677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05055", "structures": 0, "taxa": 1035, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2986, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 86, "interpro_id": "IPR018962", "known_evidence_count": null, "matches": 3744, "name": "Domain of unknown function (DUF1995)", "partial_evidence_count": null, "pfam_id": "PF09353", "proteins": 3709, "proteomes": 723, "short_name": "DUF1995", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09353", "structures": 0, "taxa": 2009, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3083, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 60, "interpro_id": "IPR021369", "known_evidence_count": null, "matches": 3717, "name": "Protein of unknown function (DUF2985)", "partial_evidence_count": null, "pfam_id": "PF11204", "proteins": 3707, "proteomes": 1605, "short_name": "DUF2985", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11204", "structures": 0, "taxa": 3583, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function predominantly found at the N-terminal of sequences from ticks, spiders and similar sequences from arthropods. According to structure predictions this domain may adopt a alpha-helical bundle fold similar to Ty3 transposon capsid-like proteins.", "domain_architectures": 194, "interpro_id": "IPR055469", "known_evidence_count": null, "matches": 3709, "name": "Domain of unknown function (DUF7041)", "partial_evidence_count": null, "pfam_id": "PF23055", "proteins": 3700, "proteomes": 271, "short_name": "DUF7041", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23055", "structures": 0, "taxa": 1117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2110, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 6, "interpro_id": "IPR018735", "known_evidence_count": null, "matches": 3685, "name": "Uncharacterized conserved protein (DUF2277)", "partial_evidence_count": null, "pfam_id": "PF10041", "proteins": 3685, "proteomes": 3615, "short_name": "DUF2277", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10041", "structures": 0, "taxa": 4454, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2630, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised and is found in eukaryotic proteins, such as TBC1 domain family members 1 and 4. This presumed domain is typically between 50 to 64 amino acids in length. TBC domain proteins may act as GTPase-activating proteins for RAB2A, RAB8A, RAB10 and RAB14 [[cite:PUB00079096]].", "domain_architectures": 37, "interpro_id": "IPR021785", "known_evidence_count": null, "matches": 3675, "name": "Domain of unknown function (DUF3350)", "partial_evidence_count": null, "pfam_id": "PF11830", "proteins": 3672, "proteomes": 1039, "short_name": "DUF3350", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11830", "structures": 0, "taxa": 3476, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a protein domain found in phage proteins that usually contain an N-terminal [pfam:PF10979]. The function of these protein is unknown.", "domain_architectures": 16, "interpro_id": "IPR055592", "known_evidence_count": null, "matches": 3674, "name": "Domain of unknown function (DUF7168)", "partial_evidence_count": null, "pfam_id": "PF23771", "proteins": 3672, "proteomes": 3251, "short_name": "DUF7168", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23771", "structures": 0, "taxa": 5073, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3295, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The hypothetical proteins found in this family are expressed by Oryza sativa and are of unknown function.", "domain_architectures": 86, "interpro_id": "IPR012871", "known_evidence_count": null, "matches": 4008, "name": "Protein of unknown function (DUF1668)", "partial_evidence_count": null, "pfam_id": "PF07893", "proteins": 3671, "proteomes": 106, "short_name": "DUF1668", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07893", "structures": 0, "taxa": 366, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2088, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 166 to 214 amino acids in length. This protein has a conserved RCG sequence motif.", "domain_architectures": 2, "interpro_id": "IPR021903", "known_evidence_count": null, "matches": 3814, "name": "Protein of unknown function (DUF3515)", "partial_evidence_count": null, "pfam_id": "PF12028", "proteins": 3671, "proteomes": 3528, "short_name": "DUF3515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12028", "structures": 0, "taxa": 4113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2099, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an C-terminal Toprim-like domain found in DUF3097 proteins. This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR021447", "known_evidence_count": null, "matches": 3669, "name": "DUF3097, C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF11296", "proteins": 3669, "proteomes": 3659, "short_name": "DUF3097_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11296", "structures": 0, "taxa": 4315, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 125 to 163 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR021888", "known_evidence_count": null, "matches": 3666, "name": "Protein of unknown function (DUF3499)", "partial_evidence_count": null, "pfam_id": "PF12005", "proteins": 3663, "proteomes": 3652, "short_name": "DUF3499", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12005", "structures": 0, "taxa": 4306, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2091, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal Tudor-like domain found in DUF3097 proteins. This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 4, "interpro_id": "IPR053883", "known_evidence_count": null, "matches": 3658, "name": "DUF3097, N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF22845", "proteins": 3658, "proteomes": 3650, "short_name": "DUF3097_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22845", "structures": 0, "taxa": 4300, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2935, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and eukaryotes, and is approximately 150 amino acids in length. The family is found in association with [pfam:PF00293].", "domain_architectures": 58, "interpro_id": "IPR031804", "known_evidence_count": null, "matches": 3664, "name": "Domain of unknown function (DUF4743)", "partial_evidence_count": null, "pfam_id": "PF15916", "proteins": 3656, "proteomes": 2944, "short_name": "DUF4743", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15916", "structures": 1, "taxa": 7026, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 142 and 168 amino acids in length. There are two completely conserved C residues that may be functionally important.", "domain_architectures": 20, "interpro_id": "IPR025508", "known_evidence_count": null, "matches": 3647, "name": "Domain of unknown function (DUF4395)", "partial_evidence_count": null, "pfam_id": "PF14340", "proteins": 3645, "proteomes": 3397, "short_name": "DUF4395", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14340", "structures": 0, "taxa": 4668, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2090, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 122 and 147 amino acids in length. Proteins in this family are integral membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR025327", "known_evidence_count": null, "matches": 3632, "name": "Protein of unknown function (DUF4233)", "partial_evidence_count": null, "pfam_id": "PF14017", "proteins": 3632, "proteomes": 3621, "short_name": "DUF4233", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14017", "structures": 0, "taxa": 4209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3057, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 78 and 89 amino acids in length.", "domain_architectures": 27, "interpro_id": "IPR022024", "known_evidence_count": null, "matches": 4049, "name": "Protein of unknown function (DUF3602)", "partial_evidence_count": null, "pfam_id": "PF12223", "proteins": 3628, "proteomes": 1304, "short_name": "DUF3602", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12223", "structures": 0, "taxa": 2718, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of a number of eukaryotic proteins of around 72 residues in length. The function of this family is unknown.", "domain_architectures": 53, "interpro_id": "IPR009653", "known_evidence_count": null, "matches": 3627, "name": "Protein of unknown function (DUF1242)", "partial_evidence_count": null, "pfam_id": "PF06842", "proteins": 3626, "proteomes": 2457, "short_name": "DUF1242", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06842", "structures": 0, "taxa": 7184, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3012, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a large family of Uncharacterized fungal proteins.", "domain_architectures": 51, "interpro_id": "IPR046528", "known_evidence_count": null, "matches": 3630, "name": "Family of unknown function (DUF6593)", "partial_evidence_count": null, "pfam_id": "PF20236", "proteins": 3617, "proteomes": 286, "short_name": "DUF6593", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20236", "structures": 0, "taxa": 780, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2375, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are found in various hypothetical prokaryotic proteins, as well as putative cytochrome c oxidases. Their exact function has not, as yet, been established.", "domain_architectures": 4, "interpro_id": "IPR018692", "known_evidence_count": null, "matches": 3620, "name": "Predicted integral membrane protein (DUF2189)", "partial_evidence_count": null, "pfam_id": "PF09955", "proteins": 3613, "proteomes": 2448, "short_name": "DUF2189", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09955", "structures": 0, "taxa": 3491, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2365, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in potential toxin-antitoxin system component [[cite:PUB00091006]].", "domain_architectures": 12, "interpro_id": "IPR041049", "known_evidence_count": null, "matches": 3607, "name": "Domain of unknown function (DUF5615)", "partial_evidence_count": null, "pfam_id": "PF18480", "proteins": 3607, "proteomes": 1599, "short_name": "DUF5615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18480", "structures": 0, "taxa": 3328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2047, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. It is about 120 amino acids in length and contains several conserved motifs that may be functionally important. This domain is sometimes associated with the FHA domain.", "domain_architectures": 14, "interpro_id": "IPR025391", "known_evidence_count": null, "matches": 3603, "name": "Domain of unknown function (DUF4123)", "partial_evidence_count": null, "pfam_id": "PF13503", "proteins": 3599, "proteomes": 1502, "short_name": "DUF4123", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13503", "structures": 1, "taxa": 2205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2891, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised fungal proteins. It is often found associated with [pfam:PF26082].", "domain_architectures": 94, "interpro_id": "IPR058348", "known_evidence_count": null, "matches": 3617, "name": "Family of unknown function (DUF8035)", "partial_evidence_count": null, "pfam_id": "PF26118", "proteins": 3599, "proteomes": 870, "short_name": "DUF8035", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26118", "structures": 0, "taxa": 1701, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2329, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in bacteria. The function is not known.", "domain_architectures": 5, "interpro_id": "IPR021279", "known_evidence_count": null, "matches": 3600, "name": "Protein of unknown function (DUF2721)", "partial_evidence_count": null, "pfam_id": "PF11026", "proteins": 3598, "proteomes": 3177, "short_name": "DUF2721", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11026", "structures": 0, "taxa": 4759, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2300, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of several hypothetical bacterial proteins. The structure revealed a superficial similarity of this domain to pleckstrin homology-like folds [[cite:PUB00062529]].", "domain_architectures": 4, "interpro_id": "IPR048342", "known_evidence_count": null, "matches": 3594, "name": "Protein of unknown function (DUF1285), C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF21028", "proteins": 3594, "proteomes": 3586, "short_name": "DUF1285_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21028", "structures": 1, "taxa": 4708, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2432, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR019201", "known_evidence_count": null, "matches": 3586, "name": "Uncharacterized protein conserved in bacteria (DUF2065)", "partial_evidence_count": null, "pfam_id": "PF09838", "proteins": 3586, "proteomes": 3580, "short_name": "DUF2065", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09838", "structures": 0, "taxa": 5186, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 228 and 249 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR025245", "known_evidence_count": null, "matches": 3596, "name": "Protein of unknown function (DUF4197)", "partial_evidence_count": null, "pfam_id": "PF13852", "proteins": 3580, "proteomes": 3190, "short_name": "DUF4197", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13852", "structures": 0, "taxa": 4420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2734, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family of transmembrane proteins is functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 393 to 772 amino acids in length.", "domain_architectures": 41, "interpro_id": "IPR022703", "known_evidence_count": null, "matches": 3668, "name": "Protein of unknown function (DUF3533)", "partial_evidence_count": null, "pfam_id": "PF12051", "proteins": 3579, "proteomes": 1899, "short_name": "DUF3533", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12051", "structures": 0, "taxa": 3403, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2664, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a vWA-like domain found at the C-terminal of uncharacterised proteins containing the [pfam:PF11443] domain at the N-terminal [[cite:PUB00152793]].", "domain_architectures": 79, "interpro_id": "IPR056690", "known_evidence_count": null, "matches": 3665, "name": "Domain of unknown function (DUF7788)", "partial_evidence_count": null, "pfam_id": "PF25043", "proteins": 3573, "proteomes": 1373, "short_name": "DUF7788", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25043", "structures": 0, "taxa": 3488, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3000, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain is found at the N-terminal of several eukaryotic RNA processing proteins, including Arabidopsis TGH, which is involved in microRNA (miRNA) and small interfering RNA (siRNA) biogenesis [[cite:PUB00077126]].", "domain_architectures": 88, "interpro_id": "IPR011666", "known_evidence_count": null, "matches": 3576, "name": "G patch domain-containing protein, N-terminal", "partial_evidence_count": null, "pfam_id": "PF07713", "proteins": 3570, "proteomes": 2990, "short_name": "DUF1604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07713", "structures": 4, "taxa": 8113, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2059, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR021491", "known_evidence_count": null, "matches": 3565, "name": "Protein of unknown function (DUF3145)", "partial_evidence_count": null, "pfam_id": "PF11343", "proteins": 3565, "proteomes": 3546, "short_name": "DUF3145", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11343", "structures": 0, "taxa": 4150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2599, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 18, "interpro_id": "IPR018714", "known_evidence_count": null, "matches": 3565, "name": "Uncharacterized protein conserved in bacteria (DUF2237)", "partial_evidence_count": null, "pfam_id": "PF09996", "proteins": 3562, "proteomes": 3324, "short_name": "DUF2237", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09996", "structures": 3, "taxa": 5795, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2033, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR021465", "known_evidence_count": null, "matches": 3562, "name": "Protein of unknown function (DUF3117)", "partial_evidence_count": null, "pfam_id": "PF11314", "proteins": 3561, "proteomes": 3543, "short_name": "DUF3117", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11314", "structures": 0, "taxa": 4176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3062, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical eukaryotic proteins of unknown function.", "domain_architectures": 39, "interpro_id": "IPR009548", "known_evidence_count": null, "matches": 3569, "name": "Protein of unknown function (DUF1168)", "partial_evidence_count": null, "pfam_id": "PF06658", "proteins": 3557, "proteomes": 3082, "short_name": "DUF1168", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06658", "structures": 7, "taxa": 8297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2822, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 9, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 160 amino acids in length. This domain is found associated with [pfam:PF00225]. This domain is found associated with [pfam:PF00225]. This domain has two conserved sequence motifs: EVE and ESA.", "domain_architectures": 61, "interpro_id": "IPR021881", "known_evidence_count": null, "matches": 3595, "name": "Domain of unknown function (DUF3490)", "partial_evidence_count": null, "pfam_id": "PF11995", "proteins": 3556, "proteomes": 408, "short_name": "DUF3490", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11995", "structures": 0, "taxa": 1132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2876, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Plant protein of unknown function.", "domain_architectures": 57, "interpro_id": "IPR006943", "known_evidence_count": null, "matches": 3547, "name": "Plant protein of unknown function (DUF641)", "partial_evidence_count": null, "pfam_id": "PF04859", "proteins": 3537, "proteomes": 369, "short_name": "DUF641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04859", "structures": 0, "taxa": 998, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2000, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 143 and 204 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045596", "known_evidence_count": null, "matches": 3540, "name": "Family of unknown function (DUF6459)", "partial_evidence_count": null, "pfam_id": "PF20060", "proteins": 3537, "proteomes": 3484, "short_name": "DUF6459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20060", "structures": 0, "taxa": 4103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of uncharacterised prokaryotic proteins. Multiple predicted transmembrane regions suggest that the region is membrane associated.", "domain_architectures": 2, "interpro_id": "IPR007563", "known_evidence_count": null, "matches": 3543, "name": "Protein of unknown function (DUF554)", "partial_evidence_count": null, "pfam_id": "PF04474", "proteins": 3534, "proteomes": 3168, "short_name": "DUF554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04474", "structures": 0, "taxa": 5319, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2022, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 132 and 153 amino acids in length. There is a single completely conserved residue C that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR025443", "known_evidence_count": null, "matches": 3526, "name": "Domain of unknown function (DUF4307)", "partial_evidence_count": null, "pfam_id": "PF14155", "proteins": 3526, "proteomes": 3490, "short_name": "DUF4307", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14155", "structures": 0, "taxa": 4045, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2006, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins. Its exact function has not, as yet, been described.", "domain_architectures": 37, "interpro_id": "IPR015315", "known_evidence_count": null, "matches": 3608, "name": "Domain of unknown function (DUF1963)", "partial_evidence_count": null, "pfam_id": "PF09234", "proteins": 3520, "proteomes": 2481, "short_name": "DUF1963", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09234", "structures": 1, "taxa": 4134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2349, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of bacterial proteins are multi-pass membrane proteins with up to 10 (2 x 4/5) transmembrane regions. The exact function of this potential pore molecule is not known, but in many instances it is associated with ABC-transporter-like domains, implying that it is part of a secretion system that uses energy.", "domain_architectures": 7, "interpro_id": "IPR018710", "known_evidence_count": null, "matches": 3490, "name": "Predicted membrane protein (DUF2232)", "partial_evidence_count": null, "pfam_id": "PF09991", "proteins": 3490, "proteomes": 3333, "short_name": "DUF2232", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09991", "structures": 0, "taxa": 5896, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2612, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a uncharacterised domain found in eukaryotes and viruses. According to structure predictions and comparison, this domain may have a alpha-helical fold closely related to the TROVE domain suggesting possible involvement in RNA binding [[cite:PUB00152793]].", "domain_architectures": 83, "interpro_id": "IPR058580", "known_evidence_count": null, "matches": 4233, "name": "Domain of unknown function (DUF2828)", "partial_evidence_count": null, "pfam_id": "PF11443", "proteins": 3487, "proteomes": 1366, "short_name": "DUF2828", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11443", "structures": 0, "taxa": 3464, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2302, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a functionally uncharacterised domain found in bacterial proteins.", "domain_architectures": 41, "interpro_id": "IPR021782", "known_evidence_count": null, "matches": 3489, "name": "Protein of unknown function (DUF3347)", "partial_evidence_count": null, "pfam_id": "PF11827", "proteins": 3483, "proteomes": 1550, "short_name": "DUF3347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11827", "structures": 0, "taxa": 2183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 33, "interpro_id": "IPR021327", "known_evidence_count": null, "matches": 3518, "name": "Protein of unknown function (DUF2934)", "partial_evidence_count": null, "pfam_id": "PF11154", "proteins": 3474, "proteomes": 1883, "short_name": "DUF2934", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11154", "structures": 0, "taxa": 2777, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2088, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 150 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009921", "known_evidence_count": null, "matches": 5999, "name": "Protein of unknown function (DUF1456)", "partial_evidence_count": null, "pfam_id": "PF07308", "proteins": 3460, "proteomes": 3410, "short_name": "DUF1456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07308", "structures": 0, "taxa": 4557, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1951, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021617", "known_evidence_count": null, "matches": 5475, "name": "Protein of unknown function (DUF3231)", "partial_evidence_count": null, "pfam_id": "PF11553", "proteins": 3451, "proteomes": 911, "short_name": "DUF3231", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11553", "structures": 1, "taxa": 1269, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2961, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This is a conserved domain found in tectonic proteins (TCTN1/2/3) which contains conserved cysteine residues predicted to form disulfide bond. This domain is found in two tandem copies. It is predicted to fold into an alpha/beta structure with unique topology composed of a central mixed beta-sheet and alpha-helix packed on it. Although function of this domain is currently unknown, studies on TCTN2 suggest that it is indispensable for its functions [[cite:PUB00097826],[cite:PUB00097827]]. TCTN1, TCTN2, and TCTN3 are members of the tectonic protein family that play crucial roles in ciliogenesis and ciliary function. While they share some common functions, each protein also has specific roles in the process of cilia formation and maintenance. These proteins interact with several other ciliopathy proteins, forming a complex known as the Tectonic ciliopathy complex. This complex is required for hedgehog signalling transduction and regulation of ciliary membrane composition [[cite:PUB00069722],[cite:PUB00160606]].", "domain_architectures": 51, "interpro_id": "IPR011677", "known_evidence_count": null, "matches": 6251, "name": "Tectonic domain of DUF1619", "partial_evidence_count": null, "pfam_id": "PF07773", "proteins": 3441, "proteomes": 1145, "short_name": "TCTN_DUF1619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07773", "structures": 0, "taxa": 3864, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1856, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found on a variety of different proteins including transferases, and allergen V5/Tpx-1 related proteins.", "domain_architectures": 855, "interpro_id": "IPR025282", "known_evidence_count": null, "matches": 4503, "name": "Domain of unknown function (DUF4214)", "partial_evidence_count": null, "pfam_id": "PF13946", "proteins": 3439, "proteomes": 940, "short_name": "DUF4214", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13946", "structures": 0, "taxa": 1878, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2815, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 120 amino acids in length. There are two conserved sequence motifs: YGL and LRDR. This family is related to GATase enzyme domains.", "domain_architectures": 66, "interpro_id": "IPR024286", "known_evidence_count": null, "matches": 3520, "name": "Aluminium induced protein", "partial_evidence_count": null, "pfam_id": "PF12481", "proteins": 3430, "proteomes": 418, "short_name": "DUF3700", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12481", "structures": 0, "taxa": 1197, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1966, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 95 and 122 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025323", "known_evidence_count": null, "matches": 3424, "name": "Protein of unknown function (DUF4229)", "partial_evidence_count": null, "pfam_id": "PF14012", "proteins": 3424, "proteomes": 3384, "short_name": "DUF4229", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14012", "structures": 0, "taxa": 3988, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2782, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 50 amino acids in length. This domain has two completely conserved residues (Y and K) that may be functionally important.", "domain_architectures": 47, "interpro_id": "IPR021899", "known_evidence_count": null, "matches": 3421, "name": "Domain of unknown function (DUF3511)", "partial_evidence_count": null, "pfam_id": "PF12023", "proteins": 3421, "proteomes": 375, "short_name": "DUF3511", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12023", "structures": 0, "taxa": 1034, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2183, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family contains many hypothetical proteins. It also includes two putative methyltransferase proteins, [swissprot:Q8EEE6] and [swissprot:Q88MX8].", "domain_architectures": 10, "interpro_id": "IPR027555", "known_evidence_count": null, "matches": 3420, "name": "Protein of unknown function (DUF1698)", "partial_evidence_count": null, "pfam_id": "PF08003", "proteins": 3413, "proteomes": 3257, "short_name": "Methyltransf_9", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08003", "structures": 7, "taxa": 4980, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2330, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 335 to 438 amino acids in length. This protein has a conserved GHH sequence motif. This protein has two completely conserved G residues that may be functionally important.", "domain_architectures": 45, "interpro_id": "IPR021889", "known_evidence_count": null, "matches": 3422, "name": "Protein of unknown function (DUF3500)", "partial_evidence_count": null, "pfam_id": "PF12006", "proteins": 3406, "proteomes": 2385, "short_name": "DUF3500", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12006", "structures": 1, "taxa": 4021, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2018, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This repeat is found as four tandem repeats in a family of bacterial membrane proteins. Each repeat contains two transmembrane regions and a conserved tryptophan.", "domain_architectures": 8, "interpro_id": "IPR007136", "known_evidence_count": null, "matches": 12903, "name": "Repeat of Unknown Function (DUF347)", "partial_evidence_count": null, "pfam_id": "PF03988", "proteins": 3401, "proteomes": 2200, "short_name": "DUF347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03988", "structures": 0, "taxa": 3429, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1728, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised but contains a C-terminal DNA-binding HTH domain. This family is distantly related to [pfam:PF02624] suggesting it is likely to be a ligand binding domain. This family of proteins is found in actinobacteria and firmicutes. Proteins in this family are typically between 326 and 366 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR045981", "known_evidence_count": null, "matches": 3445, "name": "Family of unknown function (DUF5937)", "partial_evidence_count": null, "pfam_id": "PF19361", "proteins": 3388, "proteomes": 1670, "short_name": "DUF5937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19361", "structures": 0, "taxa": 2061, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2035, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 223 and 526 amino acids in length. There is a conserved FPY sequence motif.", "domain_architectures": 18, "interpro_id": "IPR025566", "known_evidence_count": null, "matches": 4170, "name": "Domain of unknown function (DUF4331)", "partial_evidence_count": null, "pfam_id": "PF14224", "proteins": 3387, "proteomes": 2376, "short_name": "DUF4331", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14224", "structures": 0, "taxa": 3517, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1961, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR014487", "known_evidence_count": null, "matches": 3380, "name": "Protein of unknown function (DUF3151)", "partial_evidence_count": null, "pfam_id": "PF11349", "proteins": 3380, "proteomes": 3371, "short_name": "DUF3151", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11349", "structures": 0, "taxa": 3974, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2883, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 140 and 163 amino acids in length.", "domain_architectures": 50, "interpro_id": "IPR022226", "known_evidence_count": null, "matches": 3404, "name": "Protein of unknown function (DUF3752)", "partial_evidence_count": null, "pfam_id": "PF12572", "proteins": 3380, "proteomes": 2909, "short_name": "DUF3752", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12572", "structures": 0, "taxa": 7825, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2250, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 13, "interpro_id": "IPR003793", "known_evidence_count": null, "matches": 3851, "name": "Uncharacterized ACR, COG1993", "partial_evidence_count": null, "pfam_id": "PF02641", "proteins": 3378, "proteomes": 2906, "short_name": "DUF190", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02641", "structures": 2, "taxa": 4805, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 220 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 10, "interpro_id": "IPR032531", "known_evidence_count": null, "matches": 3372, "name": "Domain of unknown function (DUF4956)", "partial_evidence_count": null, "pfam_id": "PF16316", "proteins": 3371, "proteomes": 2805, "short_name": "DUF4956", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16316", "structures": 0, "taxa": 4434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3078, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in plants, and is typically between 86 and 97 amino acids in length. The domain contains several conserved cysteine and histidine residues that may form a zinc binding site.", "domain_architectures": 63, "interpro_id": "IPR022059", "known_evidence_count": null, "matches": 3521, "name": "Protein of unknown function (DUF3615)", "partial_evidence_count": null, "pfam_id": "PF12274", "proteins": 3367, "proteomes": 66, "short_name": "DUF3615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12274", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2281, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical prokaryotic proteins. Its exact function has not, as yet, been described.", "domain_architectures": 35, "interpro_id": "IPR015814", "known_evidence_count": null, "matches": 3360, "name": "Domain of unknown function (DUF1932)", "partial_evidence_count": null, "pfam_id": "PF09130", "proteins": 3360, "proteomes": 2856, "short_name": "DUF1932", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09130", "structures": 3, "taxa": 4890, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2083, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 214 and 245 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR025495", "known_evidence_count": null, "matches": 3410, "name": "Domain of unknown function (DUF4386)", "partial_evidence_count": null, "pfam_id": "PF14329", "proteins": 3359, "proteomes": 2367, "short_name": "DUF4386", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14329", "structures": 0, "taxa": 3799, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2821, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "", "domain_architectures": 50, "interpro_id": "IPR007205", "known_evidence_count": null, "matches": 3367, "name": "Domain of unknown function (DUF383)", "partial_evidence_count": null, "pfam_id": "PF04063", "proteins": 3354, "proteomes": 2899, "short_name": "DUF383", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04063", "structures": 3, "taxa": 7768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2471, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 59, "interpro_id": "IPR025638", "known_evidence_count": null, "matches": 3932, "name": "Domain of unknown function (DUF4336)", "partial_evidence_count": null, "pfam_id": "PF14234", "proteins": 3348, "proteomes": 2559, "short_name": "DUF4336", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14234", "structures": 0, "taxa": 5463, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3002, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical eukaryotic proteins of unknown function.", "domain_architectures": 28, "interpro_id": "IPR009533", "known_evidence_count": null, "matches": 3359, "name": "Protein of unknown function (DUF1151)", "partial_evidence_count": null, "pfam_id": "PF06625", "proteins": 3345, "proteomes": 1091, "short_name": "DUF1151", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06625", "structures": 0, "taxa": 3635, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2035, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 140 amino acids in length. This domain is found associated with [pfam:PF01547].", "domain_architectures": 6, "interpro_id": "IPR022627", "known_evidence_count": null, "matches": 3344, "name": "Domain of unknown function (DUF3502)", "partial_evidence_count": null, "pfam_id": "PF12010", "proteins": 3344, "proteomes": 831, "short_name": "DUF3502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12010", "structures": 4, "taxa": 1232, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1836, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in a group of uncharacterised bacterial proteins. These proteins are probably distantly related to Aeronamide N-methyltransferases AerE. They share two similar domains that are predicted in the same arrangement. This domain is found N-terminal to the methyltransferase domain and has a weak sequence similarity to various HTH domains.", "domain_architectures": 10, "interpro_id": "IPR055487", "known_evidence_count": null, "matches": 3347, "name": "Domain of unknown function (DUF7059)", "partial_evidence_count": null, "pfam_id": "PF23186", "proteins": 3343, "proteomes": 3319, "short_name": "DUF7059", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23186", "structures": 0, "taxa": 3913, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It has significant sequence similarity to the alpha+beta domain found in DNA primases and it is predicted to adopt similar structure.", "domain_architectures": 41, "interpro_id": "IPR055570", "known_evidence_count": null, "matches": 3343, "name": "Domain of unknown function (DUF7146)", "partial_evidence_count": null, "pfam_id": "PF23639", "proteins": 3343, "proteomes": 1962, "short_name": "DUF7146", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23639", "structures": 0, "taxa": 3101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in bacteria and archaea and is homologous to the hypothetical protein ybgA from E. coli.", "domain_architectures": 5, "interpro_id": "IPR013560", "known_evidence_count": null, "matches": 3342, "name": "Protein of unknown function (DUF1722)", "partial_evidence_count": null, "pfam_id": "PF08349", "proteins": 3342, "proteomes": 3166, "short_name": "DUF1722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08349", "structures": 0, "taxa": 4798, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2249, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several proteins of uncharacterised function. The family is represented in the Transport classification database as 2.A.7.34, though the exact nature of what is transported is not known.", "domain_architectures": 3, "interpro_id": "IPR007437", "known_evidence_count": null, "matches": 3338, "name": "Putative member of DMT superfamily (DUF486)", "partial_evidence_count": null, "pfam_id": "PF04342", "proteins": 3338, "proteomes": 3295, "short_name": "DMT_6", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04342", "structures": 0, "taxa": 5169, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1944, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of bacterial hypothetical integral membrane proteins have no known function.", "domain_architectures": 5, "interpro_id": "IPR018729", "known_evidence_count": null, "matches": 3336, "name": "Predicted integral membrane protein (DUF2269)", "partial_evidence_count": null, "pfam_id": "PF10027", "proteins": 3335, "proteomes": 2795, "short_name": "DUF2269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10027", "structures": 0, "taxa": 4097, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2086, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial small basic proteins of around 100 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009709", "known_evidence_count": null, "matches": 3329, "name": "Protein of unknown function (DUF1290)", "partial_evidence_count": null, "pfam_id": "PF06947", "proteins": 3329, "proteomes": 3308, "short_name": "DUF1290", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06947", "structures": 0, "taxa": 4347, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1621, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an integral membrane protein of unknown function. Proteins in this family are found in a range of bacterial species.", "domain_architectures": 11, "interpro_id": "IPR046675", "known_evidence_count": null, "matches": 3331, "name": "Family of unknown function (DUF6545)", "partial_evidence_count": null, "pfam_id": "PF20182", "proteins": 3327, "proteomes": 1405, "short_name": "DUF6545", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20182", "structures": 0, "taxa": 1699, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2815, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "", "domain_architectures": 40, "interpro_id": "IPR007206", "known_evidence_count": null, "matches": 3320, "name": "Domain of unknown function (DUF384)", "partial_evidence_count": null, "pfam_id": "PF04064", "proteins": 3319, "proteomes": 2917, "short_name": "DUF384", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04064", "structures": 3, "taxa": 7801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2027, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of hypothetical bacterial proteins of unknown function.", "domain_architectures": 32, "interpro_id": "IPR023387", "known_evidence_count": null, "matches": 3317, "name": "Protein of unknown function (DUF1653)", "partial_evidence_count": null, "pfam_id": "PF07866", "proteins": 3317, "proteomes": 3259, "short_name": "DUF1653", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07866", "structures": 1, "taxa": 4729, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small protein domain found in alpha proteobacteria. Its structure is composed of a four stranded sheet packed on one side by an alpha helix. The function of these proteins is unknown.", "domain_architectures": 2, "interpro_id": "IPR054189", "known_evidence_count": null, "matches": 3310, "name": "Domain of unknown function (DUF6894)", "partial_evidence_count": null, "pfam_id": "PF21834", "proteins": 3310, "proteomes": 690, "short_name": "DUF6894", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21834", "structures": 0, "taxa": 905, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1876, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria. Some members are annotated as alanine rich membrane proteins however this cannot be confirmed.", "domain_architectures": 2, "interpro_id": "IPR021443", "known_evidence_count": null, "matches": 3305, "name": "Protein of unknown function (DUF3093)", "partial_evidence_count": null, "pfam_id": "PF11292", "proteins": 3305, "proteomes": 3194, "short_name": "DUF3093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11292", "structures": 0, "taxa": 3699, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2703, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is found in eukaryotes. Proteins in this family are about 70 amino acids in length.", "domain_architectures": 29, "interpro_id": "IPR021775", "known_evidence_count": null, "matches": 3420, "name": "Protein of unknown function (DUF3339)", "partial_evidence_count": null, "pfam_id": "PF11820", "proteins": 3304, "proteomes": 357, "short_name": "DUF3339", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11820", "structures": 0, "taxa": 1004, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2089, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 8, "interpro_id": "IPR019285", "known_evidence_count": null, "matches": 3336, "name": "Uncharacterised protein conserved in bacteria (DUF2336)", "partial_evidence_count": null, "pfam_id": "PF10098", "proteins": 3293, "proteomes": 1261, "short_name": "DUF2336", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10098", "structures": 0, "taxa": 1764, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1843, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 188 and 235 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025339", "known_evidence_count": null, "matches": 3287, "name": "Protein of unknown function (DUF4245)", "partial_evidence_count": null, "pfam_id": "PF14030", "proteins": 3286, "proteomes": 3273, "short_name": "DUF4245", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14030", "structures": 0, "taxa": 3769, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1995, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 8, "interpro_id": "IPR011200", "known_evidence_count": null, "matches": 3364, "name": "Uncharacterized protein conserved in bacteria (DUF2332)", "partial_evidence_count": null, "pfam_id": "PF10094", "proteins": 3285, "proteomes": 2882, "short_name": "DUF2332", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10094", "structures": 0, "taxa": 3876, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2827, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a domain found predominantly in eukaryotes and associated with [pfam:PF00628] [pfam:PF01753] [pfam:PF00439] [pfam:PF00855]. Family members include protein kinase C-binding protein 1 (also known as ZMYND8) which acts as a transcriptional corepressor of the H3K4 demethylase JARID1D [[cite:PUB00085454]]. ZMYND8 (zinc finger and MYND [myeloid, Nervy, and DEAF-1] domain containing 8) binds acetylated damaged chromatin, including actively transcribed regions, as a means of recruiting the nucleosome remodeling and histone deacetylation (NuRD) chromatin remodeling complex for transcriptional repression and DNA double-strand break (DSB) repair by homologous recombination (HR) [[cite:PUB00103635]].", "domain_architectures": 30, "interpro_id": "IPR021931", "known_evidence_count": null, "matches": 3369, "name": "Protein kinase C-binding protein 1", "partial_evidence_count": null, "pfam_id": "PF12064", "proteins": 3284, "proteomes": 702, "short_name": "DUF3544", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12064", "structures": 0, "taxa": 2145, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2059, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a long region of similarity found to the C-terminus of a CBM9 domain. According to BOCTOPUS prediction this region has a membrane barrel topology suggesting this entry may represent a novel carbohydrate channel.", "domain_architectures": 6, "interpro_id": "IPR045670", "known_evidence_count": null, "matches": 3651, "name": "Domain of unknown function (DUF5916)", "partial_evidence_count": null, "pfam_id": "PF19313", "proteins": 3279, "proteomes": 1897, "short_name": "DUF5916", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19313", "structures": 0, "taxa": 2747, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1863, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function. The structure of one of the proteins in this family has been shown to adopt an alpha beta fold.", "domain_architectures": 4, "interpro_id": "IPR018988", "known_evidence_count": null, "matches": 3267, "name": "Protein of unknown function (DUF2000)", "partial_evidence_count": null, "pfam_id": "PF09391", "proteins": 3265, "proteomes": 2843, "short_name": "DUF2000", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09391", "structures": 1, "taxa": 4027, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2047, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Some family members may be secreted or integral membrane proteins.", "domain_architectures": 7, "interpro_id": "IPR007486", "known_evidence_count": null, "matches": 3265, "name": "Protein of unknown function (DUF533)", "partial_evidence_count": null, "pfam_id": "PF04391", "proteins": 3264, "proteomes": 2860, "short_name": "DUF533", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04391", "structures": 0, "taxa": 4077, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021428", "known_evidence_count": null, "matches": 3254, "name": "Protein of unknown function (DUF3078)", "partial_evidence_count": null, "pfam_id": "PF11276", "proteins": 3254, "proteomes": 2066, "short_name": "DUF3078", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11276", "structures": 0, "taxa": 2820, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2808, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry contains a large diverse family of fungal proteins of unknown function. They are predicted to adopt a globular structure that resembles the conserved core of the PPPDE superfamily (after Permuted Papain fold Peptidases of DsRNA viruses and Eukaryotes) consisting of thiol peptidases with a circularly permuted papain-like fold.", "domain_architectures": 57, "interpro_id": "IPR046670", "known_evidence_count": null, "matches": 3248, "name": "Family of unknown function (DUF6540)", "partial_evidence_count": null, "pfam_id": "PF20174", "proteins": 3248, "proteomes": 842, "short_name": "DUF6540", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20174", "structures": 0, "taxa": 1815, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1732, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000219) is described by MIBiG as an example of the following biosynthetic classes, polyketide and saccharide, in particular the elloramycin biosynthetic gene cluster from Streptomyces olivaceus [[cite:PUB00099394]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 5, "interpro_id": "IPR046291", "known_evidence_count": null, "matches": 3275, "name": "Family of unknown function (DUF6328)", "partial_evidence_count": null, "pfam_id": "PF19853", "proteins": 3243, "proteomes": 2748, "short_name": "DUF6328", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19853", "structures": 0, "taxa": 3369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2825, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a highly conserved 100 residue coiled-coil region which is found in short coiled-coil protein (SCOC) in human and UNC-69 in Caenorhabditis elegans. In human, SCOC is required for autophagosome formation during amino acid starvation. It forms a starvation-sensitive trimeric complex with UVRAG (UV radiation resistance associated gene) and FEZ1 and may regulate ULK1 and Beclin 1 complex activities [[cite:PUB00086016]]. In C. elegans, this small, evolutionarily conserved coiled-coil domain-containing protein, UNC-69, acts as a binding partner of UNC-76. Together they participate in a common genetic pathway necessary for axon extension and cooperate to regulate the size and position of synaptic vesicles in axons. Moreover, both proteins colocalize as puncta in neuronal processes and mutations in UNC-69 preferentially disrupt membrane traffic within axons [[cite:PUB00109243]].", "domain_architectures": 25, "interpro_id": "IPR019357", "known_evidence_count": null, "matches": 3243, "name": "Short coiled-coil protein", "partial_evidence_count": null, "pfam_id": "PF10224", "proteins": 3242, "proteomes": 2499, "short_name": "DUF2205", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10224", "structures": 1, "taxa": 6762, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2001, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 50 amino acids in length. There is a single completely conserved residue W that may be functionally important. These proteins contain two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR043727", "known_evidence_count": null, "matches": 3242, "name": "Family of unknown function (DUF5670)", "partial_evidence_count": null, "pfam_id": "PF18919", "proteins": 3242, "proteomes": 2519, "short_name": "DUF5670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18919", "structures": 0, "taxa": 3735, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "In B. subtilis, one small SOS response operon under the control of LexA, the yneA operon, is comprised of three genes: yneA, yneB, and ynzC [[cite:PUB00053936]]. This family consists of several short, hypothetical bacterial proteins of unknown function. These proteins are mainly found in gram-positive firmicutes. Structures show that the N-terminus is composed of two alpha helices forming a helix-loop-helix motif. The structure of ynzC from B. subtilis forms a trimeric complex [[cite:PUB00047592]]. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]]. This family is also known as UPF0291.", "domain_architectures": 9, "interpro_id": "IPR009242", "known_evidence_count": null, "matches": 3234, "name": "Bacterial protein of unknown function (DUF896)", "partial_evidence_count": null, "pfam_id": "PF05979", "proteins": 3234, "proteomes": 2870, "short_name": "DUF896", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05979", "structures": 3, "taxa": 4172, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2052, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 9, "interpro_id": "IPR014580", "known_evidence_count": null, "matches": 3232, "name": "Uncharacterized protein conserved in bacteria (DUF2200)", "partial_evidence_count": null, "pfam_id": "PF09966", "proteins": 3232, "proteomes": 3156, "short_name": "DUF2200", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09966", "structures": 1, "taxa": 4822, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1865, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from Rhizobium meliloti, Rhizobium loti and Agrobacterium tumefaciens. The function of this family is unknown. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 6, "interpro_id": "IPR010385", "known_evidence_count": null, "matches": 3230, "name": "Protein of unknown function (DUF982)", "partial_evidence_count": null, "pfam_id": "PF06169", "proteins": 3223, "proteomes": 514, "short_name": "DUF982", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06169", "structures": 1, "taxa": 702, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2055, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of bacterial domains are predominantly found in transglutaminase and transglutaminase-like proteins. Their exact function is, as yet, unknown, but they are likely to act as amidoligase enzymes [[cite:PUB00053382]] Protein in this family are found in conserved gene neighborhoods encoding a glutamine amidotransferase-like thiol peptidase (in proteobacteria) or an Aig2 family cyclotransferase protein (in firmicutes) [[cite:PUB00053382]].", "domain_architectures": 11, "interpro_id": "IPR018667", "known_evidence_count": null, "matches": 3483, "name": "Putative amidoligase enzyme (DUF2126)", "partial_evidence_count": null, "pfam_id": "PF09899", "proteins": 3222, "proteomes": 3132, "short_name": "DUF2126", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09899", "structures": 0, "taxa": 4574, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short bacterial proteins of around 100 residues in length. The function of this family is unknown.", "domain_architectures": 13, "interpro_id": "IPR023163", "known_evidence_count": null, "matches": 3245, "name": "Protein of unknown function (DUF1244)", "partial_evidence_count": null, "pfam_id": "PF06844", "proteins": 3218, "proteomes": 3203, "short_name": "DUF1244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06844", "structures": 2, "taxa": 4395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2179, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 150 residues in length. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR009562", "known_evidence_count": null, "matches": 3220, "name": "Protein of unknown function (DUF1178)", "partial_evidence_count": null, "pfam_id": "PF06676", "proteins": 3214, "proteomes": 3148, "short_name": "DUF1178", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06676", "structures": 0, "taxa": 4261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2569, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found at the N-terminus of member of the DUF761 family [pfam:PF05553]. Many members are plant proteins.", "domain_architectures": 27, "interpro_id": "IPR025520", "known_evidence_count": null, "matches": 3216, "name": "Domain of unknown function (DUF4408)", "partial_evidence_count": null, "pfam_id": "PF14364", "proteins": 3211, "proteomes": 369, "short_name": "DUF4408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14364", "structures": 0, "taxa": 1015, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1646, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a four-helical up-and-down bundle and it is likely transmembrane.", "domain_architectures": 3, "interpro_id": "IPR055568", "known_evidence_count": null, "matches": 3209, "name": "Domain of unknown function (DUF7144)", "partial_evidence_count": null, "pfam_id": "PF23636", "proteins": 3209, "proteomes": 1714, "short_name": "DUF7144", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23636", "structures": 0, "taxa": 2084, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2366, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This helix-turn-helix (HTH) domain is found twice in a group of uncharacterised proteins from plants. It is often found associated with [pfam:PF04827] and has a highly conserved motif DYF.", "domain_architectures": 179, "interpro_id": "IPR059462", "known_evidence_count": null, "matches": 3213, "name": "Domain of unknown function (DUF8418)", "partial_evidence_count": null, "pfam_id": "PF28509", "proteins": 3209, "proteomes": 192, "short_name": "DUF8418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28509", "structures": 0, "taxa": 655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2425, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains a number of bacterial and eukaryotic proteins of unknown function that are approximately 200 residues long. Some family members are annotated as putative lipoproteins.", "domain_architectures": 60, "interpro_id": "IPR010686", "known_evidence_count": null, "matches": 3269, "name": "Protein of unknown function (DUF1264)", "partial_evidence_count": null, "pfam_id": "PF06884", "proteins": 3207, "proteomes": 2088, "short_name": "DUF1264", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06884", "structures": 0, "taxa": 4434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2281, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of PIN domains that cleaves single-stranded RNA in a sequence- or structure-dependent manner. The PIN domain has a Rossmanoid fold with a central parallel beta-sheet surrounded by alpha-helices.", "domain_architectures": 5, "interpro_id": "IPR021799", "known_evidence_count": null, "matches": 3208, "name": "PIN domain", "partial_evidence_count": null, "pfam_id": "PF11848", "proteins": 3206, "proteomes": 1816, "short_name": "DUF3368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11848", "structures": 0, "taxa": 3821, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 310 amino acids in length. The family is found in association with [pfam:PF02138], [pfam:PF00400]. There is a conserved RDN sequence motif.", "domain_architectures": 128, "interpro_id": "", "known_evidence_count": null, "matches": 3255, "name": "Domain of unknown function (DUF4800)", "partial_evidence_count": null, "pfam_id": "PF16057", "proteins": 3200, "proteomes": 1155, "short_name": "DUF4800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16057", "structures": 0, "taxa": 3780, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1840, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Corynebacterineae. The function is not known though most members are annotated as either secreted, or membrane, proteins.", "domain_architectures": 1, "interpro_id": "IPR019675", "known_evidence_count": null, "matches": 3198, "name": "Protein of unknown function (DUF2550)", "partial_evidence_count": null, "pfam_id": "PF10739", "proteins": 3198, "proteomes": 3188, "short_name": "DUF2550", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10739", "structures": 0, "taxa": 3763, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1901, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as YerB. However currently no function is known. This entry represents the C-terminal domain.", "domain_architectures": 9, "interpro_id": "IPR035328", "known_evidence_count": null, "matches": 3197, "name": "Protein of unknown function (DUF3048) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF17479", "proteins": 3197, "proteomes": 2972, "short_name": "DUF3048_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17479", "structures": 1, "taxa": 4032, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1894, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as YerB. However currently no function is known. This entry represents the N-terminal domain.", "domain_architectures": 11, "interpro_id": "IPR021416", "known_evidence_count": null, "matches": 3193, "name": "Protein of unknown function (DUF3048) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF11258", "proteins": 3193, "proteomes": 2977, "short_name": "DUF3048", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11258", "structures": 1, "taxa": 4034, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2634, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It has detectable similarity to known PIN domains, in particular to NYN domain, and it is predicted to adopt a similar structure.", "domain_architectures": 78, "interpro_id": "IPR057683", "known_evidence_count": null, "matches": 3298, "name": "Domain of unknown function (DUF7923)", "partial_evidence_count": null, "pfam_id": "PF25540", "proteins": 3188, "proteomes": 1117, "short_name": "DUF7923", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25540", "structures": 0, "taxa": 2309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2139, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several short hypothetical bacterial proteins of unknown function. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 3, "interpro_id": "IPR009296", "known_evidence_count": null, "matches": 3187, "name": "Bacterial protein of unknown function (DUF951)", "partial_evidence_count": null, "pfam_id": "PF06107", "proteins": 3187, "proteomes": 3174, "short_name": "DUF951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06107", "structures": 0, "taxa": 4756, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1960, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 9, "interpro_id": "IPR018677", "known_evidence_count": null, "matches": 3184, "name": "Predicted membrane protein (DUF2157)", "partial_evidence_count": null, "pfam_id": "PF09925", "proteins": 3183, "proteomes": 3089, "short_name": "DUF2157", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09925", "structures": 0, "taxa": 4807, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2567, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised fungal proteins. It has a remote similarity to members of the PD-(D/E)XK nuclease superfamily and it is likely to adopt similar structure with a conserved active site architecture.", "domain_architectures": 57, "interpro_id": "IPR057684", "known_evidence_count": null, "matches": 3245, "name": "Domain of unknown function (DUF7924)", "partial_evidence_count": null, "pfam_id": "PF25545", "proteins": 3173, "proteomes": 638, "short_name": "DUF7924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25545", "structures": 0, "taxa": 1373, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1817, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Actinobacteria. The function is not known.", "domain_architectures": 2, "interpro_id": "IPR019662", "known_evidence_count": null, "matches": 3162, "name": "Protein of unknown function (DUF2516)", "partial_evidence_count": null, "pfam_id": "PF10724", "proteins": 3162, "proteomes": 3154, "short_name": "DUF2516", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10724", "structures": 0, "taxa": 3691, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2408, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised metazoan sequences. This domain shares similarity with the LAP2alpha C-terminal dimerization domain.", "domain_architectures": 137, "interpro_id": "IPR061808", "known_evidence_count": null, "matches": 3197, "name": "Domain of unknown function (DUF8747)", "partial_evidence_count": null, "pfam_id": "PF30815", "proteins": 3161, "proteomes": 169, "short_name": "DUF8747", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30815", "structures": 0, "taxa": 757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1742, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal helical domain of approximately 60 residues found in bacterial SAM-dependent methyltransferases. This domain is always located N-terminal to a methyltransferase domain ([pfam:PF09445], [pfam:PF13649]) and is frequently followed by a THUMP-like domain ([pfam:PF18096]). The family is found almost exclusively in Actinomycetota, particularly in Streptomyces species and related genera. The specific function of this N-terminal domain remains to be determined.", "domain_architectures": 16, "interpro_id": "IPR061749", "known_evidence_count": null, "matches": 3160, "name": "Domain of unknown function (DUF8688)", "partial_evidence_count": null, "pfam_id": "PF30650", "proteins": 3160, "proteomes": 3148, "short_name": "DUF8688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30650", "structures": 0, "taxa": 3756, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1833, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Predicted to be an integral membrane protein with multiple membrane spans.", "domain_architectures": 4, "interpro_id": "IPR007427", "known_evidence_count": null, "matches": 3165, "name": "Protein of unknown function (DUF475)", "partial_evidence_count": null, "pfam_id": "PF04332", "proteins": 3157, "proteomes": 2744, "short_name": "DUF475", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04332", "structures": 0, "taxa": 3655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2753, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is typically between 231 to 249 amino acids in length. This domain is found associated with [pfam:PF00439].", "domain_architectures": 32, "interpro_id": "IPR021900", "known_evidence_count": null, "matches": 3226, "name": "Domain of unknown function (DUF3512)", "partial_evidence_count": null, "pfam_id": "PF12024", "proteins": 3150, "proteomes": 1320, "short_name": "DUF3512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12024", "structures": 2, "taxa": 4267, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2575, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised plant proteins of unknown function.", "domain_architectures": 40, "interpro_id": "IPR008004", "known_evidence_count": null, "matches": 4176, "name": "Protein of unknown function (DUF740)", "partial_evidence_count": null, "pfam_id": "PF05340", "proteins": 3149, "proteomes": 369, "short_name": "DUF740", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05340", "structures": 0, "taxa": 1012, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2617, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is the N-terminal region of a family of proteins conserved in fungi. Several members are annotated as being Ftp1 but this could not be confirmed. The function is not known.", "domain_architectures": 38, "interpro_id": "IPR018825", "known_evidence_count": null, "matches": 3156, "name": "Domain of unknown function (DUF2427)", "partial_evidence_count": null, "pfam_id": "PF10348", "proteins": 3148, "proteomes": 1424, "short_name": "DUF2427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10348", "structures": 0, "taxa": 2957, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2724, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "FAM98A and B proteins are found from worms to humans but their function is unknown. This entry is of a family of proteins that is rich in glycines.", "domain_architectures": 39, "interpro_id": "IPR018797", "known_evidence_count": null, "matches": 3301, "name": "Protein of unknown function (DUF2465)", "partial_evidence_count": null, "pfam_id": "PF10239", "proteins": 3143, "proteomes": 1334, "short_name": "DUF2465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10239", "structures": 1, "taxa": 4363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2053, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 25, "interpro_id": "IPR007362", "known_evidence_count": null, "matches": 3146, "name": "Protein of unknown function (DUF429)", "partial_evidence_count": null, "pfam_id": "PF04250", "proteins": 3140, "proteomes": 2956, "short_name": "DUF429", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04250", "structures": 0, "taxa": 4823, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1855, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 12, "interpro_id": "IPR017136", "known_evidence_count": null, "matches": 3135, "name": "Uncharacterized protein conserved in bacteria (DUF2256)", "partial_evidence_count": null, "pfam_id": "PF10013", "proteins": 3135, "proteomes": 3070, "short_name": "DUF2256", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10013", "structures": 0, "taxa": 5078, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1979, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial and one archaeal sequence of around 120 residues in length. The function of this family is unknown. The structure of this family shows it to be part of the Dimeric-alpha-beta-barrel superfamily. Many members are annotated as being RNA signal recognition particle 4.5S RNA, but this could not be verified.", "domain_architectures": 8, "interpro_id": "IPR009874", "known_evidence_count": null, "matches": 3392, "name": "Protein of unknown function (DUF1428)", "partial_evidence_count": null, "pfam_id": "PF07237", "proteins": 3131, "proteomes": 2854, "short_name": "DUF1428", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07237", "structures": 1, "taxa": 4136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1805, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 88 and 119 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025329", "known_evidence_count": null, "matches": 3122, "name": "Protein of unknown function (DUF4235)", "partial_evidence_count": null, "pfam_id": "PF14019", "proteins": 3122, "proteomes": 2670, "short_name": "DUF4235", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14019", "structures": 0, "taxa": 3326, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2515, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in the uncharacterized protein At4g22758 from Arabidopsis thaliana and related proteins. It shares significant sequence similarity with CRIM domain and it is predicted to adopt a similar structure with ubiquitin-like topology.", "domain_architectures": 35, "interpro_id": "IPR055482", "known_evidence_count": null, "matches": 3129, "name": "Domain of unknown function (DUF7054)", "partial_evidence_count": null, "pfam_id": "PF23156", "proteins": 3117, "proteomes": 374, "short_name": "DUF7054", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23156", "structures": 0, "taxa": 1024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2736, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 70 residues found almost exclusively in spiders (Araneae), particularly in the families Araneidae and Nephilidae. The domain is found in one to three copies per protein. Some family members occur in proteins that also contain a GEMIN2/SIP1 domain ([pfam:PF04938]). The function of this domain remains to be determined.", "domain_architectures": 112, "interpro_id": "IPR061836", "known_evidence_count": null, "matches": 3124, "name": "Domain of unknown function (DUF8775)", "partial_evidence_count": null, "pfam_id": "PF31019", "proteins": 3113, "proteomes": 166, "short_name": "DUF8775", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31019", "structures": 0, "taxa": 813, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1547, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in plants, and is approximately 120 amino acids in length. It is found in hypothetical UvrD-like Helicases and related sequences, all containing a P-loop motif that is characteristic of the AAA superfamily. This domain is located towards the N-terminal, adjacent the AAA domain ([pfam:PF13086]). There are two conserved motifs, GD and RIW. There is also a highly conserved D residue.", "domain_architectures": 147, "interpro_id": "IPR045529", "known_evidence_count": null, "matches": 3291, "name": "Domain of unknown function (DUF6469)", "partial_evidence_count": null, "pfam_id": "PF20073", "proteins": 3111, "proteomes": 374, "short_name": "DUF6469", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20073", "structures": 0, "taxa": 1059, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1906, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several proteins of uncharacterised function.", "domain_architectures": 9, "interpro_id": "IPR007432", "known_evidence_count": null, "matches": 3108, "name": "Protein of unknown function, DUF480", "partial_evidence_count": null, "pfam_id": "PF04337", "proteins": 3108, "proteomes": 3014, "short_name": "DUF480", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04337", "structures": 3, "taxa": 4167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1775, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 21, "interpro_id": "IPR025436", "known_evidence_count": null, "matches": 3104, "name": "Domain of unknown function (DUF4179)", "partial_evidence_count": null, "pfam_id": "PF13786", "proteins": 3104, "proteomes": 1191, "short_name": "DUF4179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13786", "structures": 1, "taxa": 1711, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2636, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This is domain is found N-terminal in tectonic proteins (TCTN1/2/3) It contains a number of conserved cysteine residues predicted to form disulfide bonds. Although function of this domain is currently unknown, studies on TCTN2 suggest that it is indispensable for its functions [[cite:PUB00097826],[cite:PUB00097827]]. TCTN1, TCTN2, and TCTN3 are members of the tectonic protein family that play crucial roles in ciliogenesis and ciliary function. While they share some common functions, each protein also has specific roles in the process of cilia formation and maintenance. These proteins interact with several other ciliopathy proteins, forming a complex known as the Tectonic ciliopathy complex. This complex is required for hedgehog signalling transduction and regulation of ciliary membrane composition [[cite:PUB00069722],[cite:PUB00160606]].", "domain_architectures": 41, "interpro_id": "IPR057724", "known_evidence_count": null, "matches": 3095, "name": "N-terminal domain of DUF1619", "partial_evidence_count": null, "pfam_id": "PF25752", "proteins": 3088, "proteomes": 1178, "short_name": "DUF1619_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25752", "structures": 0, "taxa": 3947, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 221, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in archaea and bacteria. Many members are annotated as being putative DNA helicase-related proteins.", "domain_architectures": 73, "interpro_id": "IPR025103", "known_evidence_count": null, "matches": 3084, "name": "Protein of unknown function (DUF4011)", "partial_evidence_count": null, "pfam_id": "PF13195", "proteins": 3083, "proteomes": 2829, "short_name": "DUF4011", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13195", "structures": 0, "taxa": 4776, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1735, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is often found N-terminal to the GNAT acetyltransferase domain, [pfam:PF00583] and FR47, [pfam:PF08445].", "domain_architectures": 5, "interpro_id": "IPR025289", "known_evidence_count": null, "matches": 3075, "name": "Domain of unknown function (DUF4081)", "partial_evidence_count": null, "pfam_id": "PF13312", "proteins": 3074, "proteomes": 3065, "short_name": "DUF4081", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13312", "structures": 0, "taxa": 3606, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1960, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins including a bacterial stress protein YcjX. The crystal structure of YcjX from Shewanella oneidensis has now been solved, and shows it to be a Ras-like GTP-binding protein. However, YcjX utilizes a non-canonical switch 2' motif not found in any other G protein [[cite:PUB00098451]].", "domain_architectures": 2, "interpro_id": "IPR007413", "known_evidence_count": null, "matches": 3080, "name": "YcjX-like family, DUF463", "partial_evidence_count": null, "pfam_id": "PF04317", "proteins": 3073, "proteomes": 3042, "short_name": "DUF463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04317", "structures": 3, "taxa": 4173, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2574, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins mainly from fungi. It has a detectable similarity to domains members of Lipid-translocating exporter superfamily and are predicted to adopt similar structure.", "domain_architectures": 48, "interpro_id": "IPR056119", "known_evidence_count": null, "matches": 3200, "name": "Domain of unknown function (DUF7702)", "partial_evidence_count": null, "pfam_id": "PF24800", "proteins": 3070, "proteomes": 1041, "short_name": "DUF7702", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24800", "structures": 0, "taxa": 2173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2168, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a three-bladed beta-alpha propeller domain with unknown function. It is often associated with enzymatic domains in bacterial cell surface proteins. Individual blade consist of a three-stranded antiparallel beta-sheet and an alpha-helix packed on it. In some members this helix may have transitioned to a random coil.", "domain_architectures": 408, "interpro_id": "IPR043708", "known_evidence_count": null, "matches": 3257, "name": "Domain of unknown function (DUF5648)", "partial_evidence_count": null, "pfam_id": "PF18885", "proteins": 3054, "proteomes": 938, "short_name": "DUF5648", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18885", "structures": 0, "taxa": 2019, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1931, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are all Actinobacteria. The function is not known.", "domain_architectures": 5, "interpro_id": "IPR019639", "known_evidence_count": null, "matches": 3052, "name": "Protein of unknown function (DUF2505)", "partial_evidence_count": null, "pfam_id": "PF10698", "proteins": 3050, "proteomes": 2217, "short_name": "DUF2505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10698", "structures": 0, "taxa": 2929, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1964, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 154 and 182 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR025348", "known_evidence_count": null, "matches": 3044, "name": "Domain of unknown function (DUF4252)", "partial_evidence_count": null, "pfam_id": "PF14060", "proteins": 3044, "proteomes": 1532, "short_name": "DUF4252", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14060", "structures": 0, "taxa": 2081, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2090, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria, archaea and viruses. Proteins in this family are typically between 101 to 118 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR021857", "known_evidence_count": null, "matches": 3098, "name": "Protein of unknown function (DUF3467)", "partial_evidence_count": null, "pfam_id": "PF11950", "proteins": 3040, "proteomes": 2911, "short_name": "DUF3467", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11950", "structures": 0, "taxa": 4436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1999, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are found in a set of hypothetical bacterial proteins. Their precise function has not, as yet, been defined.", "domain_architectures": 1, "interpro_id": "IPR015231", "known_evidence_count": null, "matches": 3039, "name": "Domain of unknown function (DUF1934)", "partial_evidence_count": null, "pfam_id": "PF09148", "proteins": 3039, "proteomes": 3026, "short_name": "DUF1934", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09148", "structures": 1, "taxa": 4351, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2172, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 27, "interpro_id": "IPR019240", "known_evidence_count": null, "matches": 3041, "name": "Uncharacterized conserved protein (DUF2196)", "partial_evidence_count": null, "pfam_id": "PF09962", "proteins": 3036, "proteomes": 2952, "short_name": "DUF2196", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09962", "structures": 0, "taxa": 4854, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 815, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins.", "domain_architectures": 1475, "interpro_id": "IPR061757", "known_evidence_count": null, "matches": 6555, "name": "Domain of unknown function (DUF8696)", "partial_evidence_count": null, "pfam_id": "PF30705", "proteins": 3034, "proteomes": 1513, "short_name": "DUF8696", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30705", "structures": 4, "taxa": 2370, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1773, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as yjgA however currently no function for the protein is known.", "domain_architectures": 12, "interpro_id": "IPR021257", "known_evidence_count": null, "matches": 3026, "name": "Protein of unknown function (DUF2809)", "partial_evidence_count": null, "pfam_id": "PF10990", "proteins": 3026, "proteomes": 2908, "short_name": "DUF2809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10990", "structures": 0, "taxa": 4130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1406, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family is unknown.", "domain_architectures": 358, "interpro_id": "IPR011936", "known_evidence_count": null, "matches": 9600, "name": "Domain of unknown function (DUF4215)", "partial_evidence_count": null, "pfam_id": "PF13948", "proteins": 3021, "proteomes": 458, "short_name": "DUF4215", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13948", "structures": 0, "taxa": 1560, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1771, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR021441", "known_evidence_count": null, "matches": 3013, "name": "Protein of unknown function (DUF3090)", "partial_evidence_count": null, "pfam_id": "PF11290", "proteins": 3013, "proteomes": 2997, "short_name": "DUF3090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11290", "structures": 0, "taxa": 3655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1687, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 127 and 269 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR025511", "known_evidence_count": null, "matches": 3011, "name": "Domain of unknown function (DUF4398)", "partial_evidence_count": null, "pfam_id": "PF14346", "proteins": 3009, "proteomes": 1253, "short_name": "DUF4398", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14346", "structures": 1, "taxa": 1823, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1695, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 6, "interpro_id": "IPR009334", "known_evidence_count": null, "matches": 3021, "name": "Protein of unknown function (DUF993)", "partial_evidence_count": null, "pfam_id": "PF06187", "proteins": 3006, "proteomes": 2849, "short_name": "DUF993", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06187", "structures": 1, "taxa": 3633, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain has no known function. It is found in various hypothetical bacterial proteins.", "domain_architectures": 31, "interpro_id": "IPR015077", "known_evidence_count": null, "matches": 3002, "name": "Domain of unknown function (DUF1858)", "partial_evidence_count": null, "pfam_id": "PF08984", "proteins": 3001, "proteomes": 2106, "short_name": "DUF1858", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08984", "structures": 3, "taxa": 3742, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1571, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 169 and 263 amino acids in length. This domain is often associated with the WGR domain [pfam:PF05406].", "domain_architectures": 18, "interpro_id": "IPR025334", "known_evidence_count": null, "matches": 3001, "name": "Protein of unknown function (DUF4240)", "partial_evidence_count": null, "pfam_id": "PF14024", "proteins": 3000, "proteomes": 2162, "short_name": "DUF4240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14024", "structures": 0, "taxa": 2993, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1731, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterized proteins.Their predicted structure shows some similarity to ADP-rybosylating toxins.", "domain_architectures": 3, "interpro_id": "IPR054206", "known_evidence_count": null, "matches": 3002, "name": "Family of unknown function (DUF6912)", "partial_evidence_count": null, "pfam_id": "PF21853", "proteins": 2999, "proteomes": 2981, "short_name": "DUF6912", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21853", "structures": 0, "taxa": 3540, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1839, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacteria, and is approximately 60 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR025587", "known_evidence_count": null, "matches": 3009, "name": "Domain of unknown function (DUF4351)", "partial_evidence_count": null, "pfam_id": "PF14261", "proteins": 2992, "proteomes": 627, "short_name": "DUF4351", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14261", "structures": 0, "taxa": 1509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1861, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 167 and 310 amino acids in length.", "domain_architectures": 22, "interpro_id": "IPR025509", "known_evidence_count": null, "matches": 2993, "name": "Domain of unknown function (DUF4396)", "partial_evidence_count": null, "pfam_id": "PF14342", "proteins": 2992, "proteomes": 2638, "short_name": "DUF4396", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14342", "structures": 0, "taxa": 4269, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1551, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000202) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family contains a protein found in the azicemicin B biosynthetic gene cluster from Kibdelosporangium sp. MJ126-NF4 [[cite:PUB00099399]]. The function of this protein is unknown.", "domain_architectures": 5, "interpro_id": "IPR046036", "known_evidence_count": null, "matches": 2984, "name": "Family of unknown function (DUF5994)", "partial_evidence_count": null, "pfam_id": "PF19457", "proteins": 2979, "proteomes": 1343, "short_name": "DUF5994", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19457", "structures": 0, "taxa": 1586, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1883, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins. The structure of one of the members in this family has been solved and it adopts a mainly alpha helical structure.", "domain_architectures": 31, "interpro_id": "IPR014937", "known_evidence_count": null, "matches": 2985, "name": "Protein of unknown function (DUF1810)", "partial_evidence_count": null, "pfam_id": "PF08837", "proteins": 2978, "proteomes": 2691, "short_name": "DUF1810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08837", "structures": 1, "taxa": 3975, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1913, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 85 residues in length. The function of this family is unknown.", "domain_architectures": 7, "interpro_id": "IPR009962", "known_evidence_count": null, "matches": 2978, "name": "Protein of unknown function (DUF1488)", "partial_evidence_count": null, "pfam_id": "PF07369", "proteins": 2977, "proteomes": 1716, "short_name": "DUF1488", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07369", "structures": 1, "taxa": 2276, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1825, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various prokaryotes, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018643", "known_evidence_count": null, "matches": 2976, "name": "Predicted membrane protein (DUF2069)", "partial_evidence_count": null, "pfam_id": "PF09842", "proteins": 2976, "proteomes": 2968, "short_name": "DUF2069", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09842", "structures": 0, "taxa": 3790, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2320, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 120 amino acids in length. This domain has a conserved CDCGGWD sequence motif.", "domain_architectures": 40, "interpro_id": "IPR021916", "known_evidence_count": null, "matches": 4113, "name": "Domain of unknown function (DUF3527)", "partial_evidence_count": null, "pfam_id": "PF12043", "proteins": 2976, "proteomes": 371, "short_name": "DUF3527", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12043", "structures": 0, "taxa": 1008, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1880, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as DNA binding proteins. No function is currently known.", "domain_architectures": 21, "interpro_id": "IPR021487", "known_evidence_count": null, "matches": 2985, "name": "Protein of unknown function (DUF3140)", "partial_evidence_count": null, "pfam_id": "PF11338", "proteins": 2973, "proteomes": 2514, "short_name": "DUF3140", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11338", "structures": 0, "taxa": 3898, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1617, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 91 and 130 amino acids in length. There is a conserved HYD sequence motif.", "domain_architectures": 13, "interpro_id": "IPR025109", "known_evidence_count": null, "matches": 2973, "name": "Protein of unknown function (DUF4031)", "partial_evidence_count": null, "pfam_id": "PF13223", "proteins": 2973, "proteomes": 2901, "short_name": "DUF4031", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13223", "structures": 0, "taxa": 3694, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 328, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 230 amino acids in length. There are two conserved sequence motifs: LLE and NMG.", "domain_architectures": 121, "interpro_id": "IPR022099", "known_evidence_count": null, "matches": 3033, "name": "Protein of unknown function (DUF3638)", "partial_evidence_count": null, "pfam_id": "PF12340", "proteins": 2966, "proteomes": 1128, "short_name": "DUF3638", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12340", "structures": 0, "taxa": 2537, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1838, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. It is found in bacteria and archaea and is typically between 243 to 275 amino acids in length. This domain is found associated with [pfam:PF04851], [pfam:PF00271]. It has a detectable similarity to known PUA domains and it is predicted to adopt similar structure.", "domain_architectures": 41, "interpro_id": "IPR021835", "known_evidence_count": null, "matches": 2960, "name": "Domain of unknown function (DUF3427)", "partial_evidence_count": null, "pfam_id": "PF11907", "proteins": 2960, "proteomes": 2860, "short_name": "DUF3427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11907", "structures": 1, "taxa": 4671, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1936, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This domain is always found in conjunction with the HHE domain ([pfam:PF03794]) at the N-terminus.", "domain_architectures": 13, "interpro_id": "IPR019903", "known_evidence_count": null, "matches": 2957, "name": "Domain of Unknown function (DUF542)", "partial_evidence_count": null, "pfam_id": "PF04405", "proteins": 2957, "proteomes": 2674, "short_name": "ScdA_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04405", "structures": 11, "taxa": 4323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2382, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found N-terminal of [pfam:PF14033]) which may consist of four helices.", "domain_architectures": 70, "interpro_id": "IPR049207", "known_evidence_count": null, "matches": 2956, "name": "Domain of unknown function DUF4246, N-terminal", "partial_evidence_count": null, "pfam_id": "PF21666", "proteins": 2952, "proteomes": 1124, "short_name": "DUF4246_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21666", "structures": 0, "taxa": 2304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2065, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This region is found in a number of hypothetical bacterial and archaeal proteins. According to structure it has a P-loop structure.", "domain_architectures": 6, "interpro_id": "IPR035086", "known_evidence_count": null, "matches": 2945, "name": "Domain of unknown function (DUF1611_C) P-loop domain", "partial_evidence_count": null, "pfam_id": "PF07755", "proteins": 2944, "proteomes": 2533, "short_name": "DUF1611", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07755", "structures": 3, "taxa": 4365, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1879, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "Protein of unknown function, cotranscribed with purB in Escherichia coli, but with function unrelated to purine biosynthesis [[cite:PUB00009959]].", "domain_architectures": 3, "interpro_id": "IPR007451", "known_evidence_count": null, "matches": 2947, "name": "Protein of unknown function (DUF489)", "partial_evidence_count": null, "pfam_id": "PF04356", "proteins": 2941, "proteomes": 2855, "short_name": "DUF489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04356", "structures": 2, "taxa": 3952, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2421, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Fungi. It shares significant sequence similarity with domains members of the Bet v1-like superfamily and it is predicted to adopt similar structure.", "domain_architectures": 44, "interpro_id": "IPR055481", "known_evidence_count": null, "matches": 2952, "name": "Domain of unknown function (DUF7053)", "partial_evidence_count": null, "pfam_id": "PF23155", "proteins": 2938, "proteomes": 926, "short_name": "DUF7053", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23155", "structures": 0, "taxa": 1878, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1086, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, eukaryotes and viruses. Proteins in this family are typically between 85 and 119 amino acids in length.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 2936, "name": "Family of unknown function (DUF6124)", "partial_evidence_count": null, "pfam_id": "PF19619", "proteins": 2936, "proteomes": 278, "short_name": "DUF6124", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19619", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2628, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain is found in eukaryotes at the C-terminus of neuropilins. It represents the transmembrane region of these transmembrane glycoproteins, that are predominantly co-receptors for another class of proteins known as semaphorins. The domain is found associated with [pfam:PF00754], [pfam:PF00431], [pfam:PF00629].", "domain_architectures": 28, "interpro_id": "IPR022579", "known_evidence_count": null, "matches": 2935, "name": "C-terminal domain of neuropilin glycoprotein", "partial_evidence_count": null, "pfam_id": "PF11980", "proteins": 2935, "proteomes": 697, "short_name": "DUF3481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11980", "structures": 0, "taxa": 2141, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1889, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of archaeal and bacterial sequences, including HVO_0229 ([swissprot:D4GZH4]). This domain may consist of several transmembrane helices.", "domain_architectures": 8, "interpro_id": "IPR057169", "known_evidence_count": null, "matches": 2935, "name": "Domain of unknown function (DUF7847)", "partial_evidence_count": null, "pfam_id": "PF25231", "proteins": 2935, "proteomes": 2410, "short_name": "DUF7847", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25231", "structures": 0, "taxa": 3558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1797, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of bacterial proteins of unknown function.", "domain_architectures": 10, "interpro_id": "IPR021727", "known_evidence_count": null, "matches": 2931, "name": "Protein of unknown function (DUF3299)", "partial_evidence_count": null, "pfam_id": "PF11736", "proteins": 2927, "proteomes": 2009, "short_name": "DUF3299", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11736", "structures": 1, "taxa": 2929, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1568, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 18, "interpro_id": "IPR015035", "known_evidence_count": null, "matches": 2919, "name": "Domain of unknown function (DUF1918)", "partial_evidence_count": null, "pfam_id": "PF08940", "proteins": 2918, "proteomes": 2067, "short_name": "DUF1918", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08940", "structures": 1, "taxa": 2471, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1787, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021737", "known_evidence_count": null, "matches": 2911, "name": "Protein of unknown function (DUF3307)", "partial_evidence_count": null, "pfam_id": "PF11750", "proteins": 2910, "proteomes": 2809, "short_name": "DUF3307", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11750", "structures": 0, "taxa": 4456, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1952, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic proteins, has no known function.", "domain_architectures": 7, "interpro_id": "IPR018638", "known_evidence_count": null, "matches": 3489, "name": "Predicted membrane protein (DUF2061)", "partial_evidence_count": null, "pfam_id": "PF09834", "proteins": 2908, "proteomes": 2733, "short_name": "DUF2061", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09834", "structures": 0, "taxa": 4182, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1610, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in Actinobacteria. Proteins in this family are typically between 695 and 823 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046112", "known_evidence_count": null, "matches": 3159, "name": "Family of unknown function (DUF6049)", "partial_evidence_count": null, "pfam_id": "PF19516", "proteins": 2904, "proteomes": 2830, "short_name": "DUF6049", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19516", "structures": 0, "taxa": 3413, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1908, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised bacterial proteins. It is usually found associated with methyltransferase domains such as [pfam:PF13489] and [pfam:PF13649] and is predicted to adopt an alpha-beta configuration. It has a conserved motif F/YWDG.", "domain_architectures": 3, "interpro_id": "IPR057206", "known_evidence_count": null, "matches": 2903, "name": "Domain of unknown function (DUF7884)", "partial_evidence_count": null, "pfam_id": "PF25371", "proteins": 2903, "proteomes": 2721, "short_name": "DUF7884", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25371", "structures": 2, "taxa": 4152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 636 to 810 amino acids in length.", "domain_architectures": 36, "interpro_id": "IPR021822", "known_evidence_count": null, "matches": 3039, "name": "Protein of unknown function (DUF3405)", "partial_evidence_count": null, "pfam_id": "PF11885", "proteins": 2888, "proteomes": 937, "short_name": "DUF3405", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11885", "structures": 0, "taxa": 1901, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1897, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This domain lies at the C-terminus of primase proteins carrying the TOPRIM, [pfam:PF01751], domain. The exact function of the domain is not known.", "domain_architectures": 10, "interpro_id": "IPR025156", "known_evidence_count": null, "matches": 2887, "name": "Domain of unknown function (DUF4093)", "partial_evidence_count": null, "pfam_id": "PF13331", "proteins": 2887, "proteomes": 2873, "short_name": "DUF4093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13331", "structures": 2, "taxa": 4158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, eukaryotes and viruses. Proteins in this family are typically between 348 and 454 amino acids in length.", "domain_architectures": 62, "interpro_id": "IPR025533", "known_evidence_count": null, "matches": 3032, "name": "Domain of unknown function (DUF4419)", "partial_evidence_count": null, "pfam_id": "PF14388", "proteins": 2886, "proteomes": 1010, "short_name": "DUF4419", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14388", "structures": 0, "taxa": 2427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2400, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function that has a beta trefoil fold. Some family members contain a two or three copies of the domain.", "domain_architectures": 81, "interpro_id": "IPR007679", "known_evidence_count": null, "matches": 3765, "name": "Beta-trefoil domain of unknown function (DUF569)", "partial_evidence_count": null, "pfam_id": "PF04601", "proteins": 2884, "proteomes": 380, "short_name": "DUF569", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04601", "structures": 0, "taxa": 1055, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1603, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 218 and 342 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR025565", "known_evidence_count": null, "matches": 2891, "name": "Domain of unknown function (DUF4328)", "partial_evidence_count": null, "pfam_id": "PF14219", "proteins": 2882, "proteomes": 2258, "short_name": "DUF4328", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14219", "structures": 0, "taxa": 3091, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2048, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in fungi, and is approximately 130 amino acids in length. This domain showed a distant similarity to LEA-2 domains [[cite:PUB00100166]].", "domain_architectures": 55, "interpro_id": "IPR022185", "known_evidence_count": null, "matches": 4862, "name": "Protein of unknown function (DUF3712)", "partial_evidence_count": null, "pfam_id": "PF12505", "proteins": 2881, "proteomes": 1187, "short_name": "DUF3712", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12505", "structures": 0, "taxa": 2520, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2023, "candidate_reasons": [ "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 5, "interpro_id": "IPR035402", "known_evidence_count": null, "matches": 2880, "name": "Domain of unknown function (DUF1611_N) Rossmann-like domain", "partial_evidence_count": null, "pfam_id": "PF17396", "proteins": 2880, "proteomes": 2488, "short_name": "DUF1611_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17396", "structures": 3, "taxa": 4276, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1725, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in a variety of restriction endonuclease enzymes. The exact function of this domain is uncertain.", "domain_architectures": 52, "interpro_id": "IPR025285", "known_evidence_count": null, "matches": 2876, "name": "Domain of unknown function (DUF4145)", "partial_evidence_count": null, "pfam_id": "PF13643", "proteins": 2875, "proteomes": 2630, "short_name": "DUF4145", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13643", "structures": 1, "taxa": 4852, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1690, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 2, "interpro_id": "IPR014995", "known_evidence_count": null, "matches": 2872, "name": "Domain of unknown function (DUF1844)", "partial_evidence_count": null, "pfam_id": "PF08899", "proteins": 2872, "proteomes": 2866, "short_name": "DUF1844", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08899", "structures": 0, "taxa": 3747, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1629, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes members mostly found in Actinobacteria. Some family members are thought to be dihydroorotate dehydrogenases, however there is no evidence to support the relationship to [pfam:PF01180].", "domain_architectures": 2, "interpro_id": "IPR043758", "known_evidence_count": null, "matches": 2868, "name": "Family of unknown function (DUF5703)", "partial_evidence_count": null, "pfam_id": "PF18963", "proteins": 2868, "proteomes": 2862, "short_name": "DUF5703", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18963", "structures": 0, "taxa": 3318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 923, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family include various bacterial hypothetical proteins, as well as CoA enzyme activases. The exact function of this domain has not, as yet, been defined.", "domain_architectures": 8, "interpro_id": "IPR018709", "known_evidence_count": null, "matches": 2884, "name": "CoA enzyme activase uncharacterised domain (DUF2229)", "partial_evidence_count": null, "pfam_id": "PF09989", "proteins": 2867, "proteomes": 2007, "short_name": "DUF2229", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09989", "structures": 0, "taxa": 3700, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family, around 80 residues, consists of uncharacterized and nuclear receptor coactivator 2 proteins and is mainly found in mammalia species. The specific function of this family is still unknown.", "domain_architectures": 69, "interpro_id": "IPR032565", "known_evidence_count": null, "matches": 2865, "name": "Domain of unknown function (DUF4927)", "partial_evidence_count": null, "pfam_id": "PF16279", "proteins": 2865, "proteomes": 735, "short_name": "DUF4927", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16279", "structures": 2, "taxa": 2239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1985, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of bacterial proteins conserved of unknown function.", "domain_architectures": 2, "interpro_id": "IPR021320", "known_evidence_count": null, "matches": 2863, "name": "Protein of unknown function (DUF2905)", "partial_evidence_count": null, "pfam_id": "PF11146", "proteins": 2863, "proteomes": 2763, "short_name": "DUF2905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11146", "structures": 0, "taxa": 4592, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2426, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins.", "domain_architectures": 41, "interpro_id": "IPR061829", "known_evidence_count": null, "matches": 2877, "name": "Domain of unknown function (DUF8768)", "partial_evidence_count": null, "pfam_id": "PF30970", "proteins": 2858, "proteomes": 929, "short_name": "DUF8768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30970", "structures": 0, "taxa": 1857, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 475, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 12 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 170 amino acids in length.", "domain_architectures": 52, "interpro_id": "IPR022188", "known_evidence_count": null, "matches": 3451, "name": "Protein of unknown function (DUF3715)", "partial_evidence_count": null, "pfam_id": "PF12509", "proteins": 2847, "proteomes": 838, "short_name": "DUF3715", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12509", "structures": 1, "taxa": 2672, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1622, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the third domain found in DUF1631 family proteins. The members of this family are sequences derived from a group of hypothetical proteins expressed by certain bacterial species.", "domain_architectures": 23, "interpro_id": "IPR059982", "known_evidence_count": null, "matches": 2843, "name": "Protein of unknown function (DUF1631) third domain", "partial_evidence_count": null, "pfam_id": "PF26672", "proteins": 2843, "proteomes": 1504, "short_name": "DUF1631_3rd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26672", "structures": 0, "taxa": 1984, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2299, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "These sequences are derived from hypothetical plant proteins of unknown function. The region in question is approximately 250 residues long.", "domain_architectures": 51, "interpro_id": "IPR012870", "known_evidence_count": null, "matches": 2924, "name": "Protein of unknown function (DUF1666)", "partial_evidence_count": null, "pfam_id": "PF07891", "proteins": 2840, "proteomes": 365, "short_name": "DUF1666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07891", "structures": 0, "taxa": 975, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 398 to 802 amino acids in length.", "domain_architectures": 51, "interpro_id": "IPR021829", "known_evidence_count": null, "matches": 2893, "name": "Protein of unknown function (DUF3419)", "partial_evidence_count": null, "pfam_id": "PF11899", "proteins": 2840, "proteomes": 2607, "short_name": "DUF3419", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11899", "structures": 0, "taxa": 5100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1786, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 33, "interpro_id": "IPR025442", "known_evidence_count": null, "matches": 2877, "name": "Domain of unknown function (DUF4185)", "partial_evidence_count": null, "pfam_id": "PF13810", "proteins": 2834, "proteomes": 1527, "short_name": "DUF4185", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13810", "structures": 3, "taxa": 2369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 858, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 160 amino acids in length. There are two completely conserved residues (C and G) that may be functionally important.", "domain_architectures": 1212, "interpro_id": "IPR025592", "known_evidence_count": null, "matches": 2877, "name": "Domain of unknown function (DUF4347)", "partial_evidence_count": null, "pfam_id": "PF14252", "proteins": 2830, "proteomes": 1643, "short_name": "DUF4347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14252", "structures": 0, "taxa": 3780, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1818, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain falls upstream of a met-zincin domain.", "domain_architectures": 6, "interpro_id": "IPR033428", "known_evidence_count": null, "matches": 2829, "name": "Domain of unknown function (DUF5118)", "partial_evidence_count": null, "pfam_id": "PF17162", "proteins": 2829, "proteomes": 1597, "short_name": "DUF5118", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17162", "structures": 0, "taxa": 2362, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1852, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various bacterial hypothetical and putative membrane proteins, has no known function.", "domain_architectures": 4, "interpro_id": "IPR019253", "known_evidence_count": null, "matches": 2827, "name": "Integral membrane protein (DUF2244)", "partial_evidence_count": null, "pfam_id": "PF10003", "proteins": 2827, "proteomes": 2773, "short_name": "DUF2244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10003", "structures": 0, "taxa": 3854, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2359, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised eukaryotic proteins. It has a detectable similarity to Tumor protein p53-inducible protein 11 (TP53I11) and it is predicted to adopt similar structure.", "domain_architectures": 37, "interpro_id": "IPR056121", "known_evidence_count": null, "matches": 2824, "name": "Domain of unknown function (DUF7704)", "partial_evidence_count": null, "pfam_id": "PF24803", "proteins": 2820, "proteomes": 1087, "short_name": "DUF7704", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24803", "structures": 0, "taxa": 2247, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1980, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of putative membrane proteins found in archaea and bacteria. It is sometimes found C terminal to [pfam:PF02308].", "domain_architectures": 6, "interpro_id": "IPR025105", "known_evidence_count": null, "matches": 2823, "name": "Domain of unknown function (DUF4010)", "partial_evidence_count": null, "pfam_id": "PF13194", "proteins": 2819, "proteomes": 2605, "short_name": "DUF4010", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13194", "structures": 0, "taxa": 4250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1690, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 14 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 100 amino acids in length. This domain is found associated with [pfam:PF02653].", "domain_architectures": 4, "interpro_id": "IPR021807", "known_evidence_count": null, "matches": 2818, "name": "Domain of unknown function (DUF3382)", "partial_evidence_count": null, "pfam_id": "PF11862", "proteins": 2818, "proteomes": 2308, "short_name": "DUF3382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11862", "structures": 0, "taxa": 3067, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 298, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 40 amino acids in length. There is a conserved HPD sequence motif.", "domain_architectures": 121, "interpro_id": "IPR022105", "known_evidence_count": null, "matches": 2819, "name": "Protein of unknown function (DUF3645)", "partial_evidence_count": null, "pfam_id": "PF12359", "proteins": 2817, "proteomes": 1102, "short_name": "DUF3645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12359", "structures": 0, "taxa": 2491, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1585, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain has a ferritin-like fold.", "domain_architectures": 2, "interpro_id": "IPR029447", "known_evidence_count": null, "matches": 2817, "name": "Domain of unknown function (DUF4439)", "partial_evidence_count": null, "pfam_id": "PF14530", "proteins": 2817, "proteomes": 2806, "short_name": "DUF4439", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14530", "structures": 1, "taxa": 3266, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1726, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 158 and 180 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR025489", "known_evidence_count": null, "matches": 2841, "name": "Domain of unknown function (DUF4381)", "partial_evidence_count": null, "pfam_id": "PF14316", "proteins": 2816, "proteomes": 2417, "short_name": "DUF4381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14316", "structures": 0, "taxa": 3438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1760, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins conserved in Proteobacteria of unknown function.", "domain_architectures": 1, "interpro_id": "IPR021313", "known_evidence_count": null, "matches": 2812, "name": "Protein of unknown function (DUF2909)", "partial_evidence_count": null, "pfam_id": "PF11137", "proteins": 2812, "proteomes": 2721, "short_name": "DUF2909", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11137", "structures": 0, "taxa": 3493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1950, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 16, "interpro_id": "IPR021414", "known_evidence_count": null, "matches": 2820, "name": "Protein of unknown function (DUF3054)", "partial_evidence_count": null, "pfam_id": "PF11255", "proteins": 2810, "proteomes": 2613, "short_name": "DUF3054", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11255", "structures": 0, "taxa": 4060, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1561, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of a group of uncharacterised bacterial proteins. It is predicted to show an alpha-beta configuration. It has highly conserved W and R residues as well as GW and GF motifs.", "domain_architectures": 5, "interpro_id": "IPR058498", "known_evidence_count": null, "matches": 2816, "name": "Domain of unknown function (DUF8185)", "partial_evidence_count": null, "pfam_id": "PF26572", "proteins": 2808, "proteomes": 2793, "short_name": "DUF8185", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26572", "structures": 0, "taxa": 3220, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1450, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. Proteins in this family are primarily found in Bacteroidetes. Proteins in this family are typically between 241 and 255 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR045749", "known_evidence_count": null, "matches": 2802, "name": "Family of unknown function (DUF6090)", "partial_evidence_count": null, "pfam_id": "PF19578", "proteins": 2802, "proteomes": 505, "short_name": "DUF6090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19578", "structures": 0, "taxa": 833, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2506, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins conserved from nematodes to humans. The function is not known.", "domain_architectures": 27, "interpro_id": "IPR018787", "known_evidence_count": null, "matches": 2865, "name": "Uncharacterised conserved protein (DUF2371)", "partial_evidence_count": null, "pfam_id": "PF10177", "proteins": 2800, "proteomes": 1056, "short_name": "DUF2371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10177", "structures": 0, "taxa": 3341, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1591, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the second domain found in DUF1631 family proteins. The members of this family are sequences derived from a group of hypothetical proteins expressed by certain bacterial species.", "domain_architectures": 24, "interpro_id": "IPR059907", "known_evidence_count": null, "matches": 2790, "name": "Protein of unknown function (DUF1631) 2nd domain", "partial_evidence_count": null, "pfam_id": "PF26671", "proteins": 2790, "proteomes": 1515, "short_name": "DUF1631_2nd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26671", "structures": 0, "taxa": 1996, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2063, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "The proteins in this family are functionally uncharacterised. The proteins are around 450 amino acids long and includes Streptococcus pneumoniae Sp0239 which is structurally similar to ribonucleotide reductase (RNR) and pyruvate formate lyase (PFL). It is likely that this family represents a group of glycerol-3-phosphate dehydrogenases.", "domain_architectures": 7, "interpro_id": "IPR007841", "known_evidence_count": null, "matches": 2799, "name": "Uncharacterised ACR (DUF711)", "partial_evidence_count": null, "pfam_id": "PF05167", "proteins": 2789, "proteomes": 2660, "short_name": "DUF711", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05167", "structures": 1, "taxa": 4756, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2162, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "A family of uncharacterised proteins.", "domain_architectures": 26, "interpro_id": "IPR012469", "known_evidence_count": null, "matches": 2847, "name": "Protein of unknown function (DUF1688)", "partial_evidence_count": null, "pfam_id": "PF07958", "proteins": 2786, "proteomes": 2098, "short_name": "DUF1688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07958", "structures": 0, "taxa": 4100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This conserved domain of unknown function is usually found tandemly repeated in the nuclear receptor coactivator family (NCOA1/2/3, also known as the SRC/p160 nuclear receptor coactivator family, which are ligand-dependent transcription factors [[cite:PUB00097822],[cite:PUB00069373]].", "domain_architectures": 62, "interpro_id": "IPR010011", "known_evidence_count": null, "matches": 3753, "name": "Nuclear receptor coactivator, DUF1518", "partial_evidence_count": null, "pfam_id": "PF07469", "proteins": 2780, "proteomes": 701, "short_name": "DUF1518", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07469", "structures": 0, "taxa": 2146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1729, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and includes YfiR from E. coli. YfiR has been shown to regulate YfiN, a diguanylate cyclase and a bifunctional protein that produces c-di-GMP in response to reductive stress and then dynamically relocates to the division site to arrest cell division in response to envelope stress in Escherichia coli. YfiR may serve as a periplasmic redox sensor that regulates YfiN activity in response to reducing conditions [[cite:PUB00088310],[cite:PUB00088309]]. HmsC in Yersinia Pestis is the orthologue of YfiR from E. coli [[cite:PUB00091013]]. HmsC is a periplasmic protein that interacts directly with the periplasmic domain (PD) of HmsD and causes proteolytic degradation of HmsD, which in turn negatively regulates Y. pestis biofilm formation [[cite:PUB00091014]].", "domain_architectures": 17, "interpro_id": "IPR025293", "known_evidence_count": null, "matches": 2788, "name": "YfiR/HmsC-like", "partial_evidence_count": null, "pfam_id": "PF13689", "proteins": 2780, "proteomes": 1988, "short_name": "DUF4154", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13689", "structures": 12, "taxa": 3030, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1820, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of bacterial and phage proteins of unknown function. There are three highly conserved cysteine residues in the disposition, Cx6Cxxc, amongst many highly conserved residues.", "domain_architectures": 13, "interpro_id": "IPR011101", "known_evidence_count": null, "matches": 2802, "name": "Protein of unknown function (DUF5131)", "partial_evidence_count": null, "pfam_id": "PF07505", "proteins": 2778, "proteomes": 2316, "short_name": "DUF5131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07505", "structures": 0, "taxa": 4489, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1808, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of 14 highly conserved sequences, from hypothetical proteins expressed by both bacterial and archaeal species.", "domain_architectures": 2, "interpro_id": "IPR012427", "known_evidence_count": null, "matches": 2778, "name": "Protein of unknown function (DUF1622)", "partial_evidence_count": null, "pfam_id": "PF07784", "proteins": 2777, "proteomes": 2580, "short_name": "DUF1622", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07784", "structures": 0, "taxa": 4271, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a putative domain found at the N-terminus of a wide range of fungal proteins of unknown function.", "domain_architectures": 75, "interpro_id": "IPR046539", "known_evidence_count": null, "matches": 2856, "name": "Family of unknown function (DUF6604)", "partial_evidence_count": null, "pfam_id": "PF20253", "proteins": 2776, "proteomes": 809, "short_name": "DUF6604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20253", "structures": 0, "taxa": 1681, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1574, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function. However, it is clearly related to the VWA domain.", "domain_architectures": 7, "interpro_id": "IPR018698", "known_evidence_count": null, "matches": 2775, "name": "VWA-like domain (DUF2201)", "partial_evidence_count": null, "pfam_id": "PF09967", "proteins": 2775, "proteomes": 2454, "short_name": "DUF2201", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09967", "structures": 0, "taxa": 4194, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1727, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a HTH domain found in a group of uncharacterised sequences from bacteria and archaea, including the Uncharacterized HTH-type transcriptional regulator MJ0774 from Methanocaldococcus jannaschii.", "domain_architectures": 16, "interpro_id": "IPR061532", "known_evidence_count": null, "matches": 2789, "name": "Domain of unknown function (DUF8462)", "partial_evidence_count": null, "pfam_id": "PF28795", "proteins": 2775, "proteomes": 2249, "short_name": "DUF8462", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28795", "structures": 0, "taxa": 3342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is highly conserved, but its function is unknown. It can be isolated from HeLa cell nucleoli and is found to be homologous with Leydig cell tumour protein whose function is unknown [1, supplementary Table I].", "domain_architectures": 42, "interpro_id": "IPR019034", "known_evidence_count": null, "matches": 2783, "name": "Protein of unknown function (DUF2462)", "partial_evidence_count": null, "pfam_id": "PF09495", "proteins": 2773, "proteomes": 2494, "short_name": "DUF2462", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09495", "structures": 7, "taxa": 6695, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of transmembrane proteins are functionally uncharacterised. This protein is found in eukaryotes. Proteins in this family are typically between 427 to 453 amino acids in length.", "domain_architectures": 63, "interpro_id": "IPR021924", "known_evidence_count": null, "matches": 2967, "name": "Protein of unknown function (DUF3537)", "partial_evidence_count": null, "pfam_id": "PF12056", "proteins": 2773, "proteomes": 384, "short_name": "DUF3537", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12056", "structures": 0, "taxa": 1055, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1720, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 43, "interpro_id": "IPR021352", "known_evidence_count": null, "matches": 2770, "name": "Protein of unknown function (DUF2971)", "partial_evidence_count": null, "pfam_id": "PF11185", "proteins": 2770, "proteomes": 2334, "short_name": "DUF2971", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11185", "structures": 0, "taxa": 4172, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2273, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved region found in fungal proteins. It is predicted as a transmembrane and composed of alpha-helices.", "domain_architectures": 76, "interpro_id": "IPR059463", "known_evidence_count": null, "matches": 3072, "name": "Domain of unknown function (DUF8419)", "partial_evidence_count": null, "pfam_id": "PF28510", "proteins": 2770, "proteomes": 720, "short_name": "DUF8419", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28510", "structures": 0, "taxa": 1425, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1695, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins and misannotated lysozyme proteins, it has no known function. This domain contains a [S/T]GA[S/T] conserved motif and serves as a flavinylation substrate for ApbE, and is likely to be involved in extracytosolic redox activities [[cite:PUB00098250]].", "domain_architectures": 4, "interpro_id": "IPR014469", "known_evidence_count": null, "matches": 2764, "name": "Predicted periplasmic protein (DUF2271)", "partial_evidence_count": null, "pfam_id": "PF10029", "proteins": 2764, "proteomes": 2590, "short_name": "DUF2271", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10029", "structures": 0, "taxa": 3726, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1526, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of a group of uncharacterised bacterial proteins. It is predicted to show an alpha-beta configuration. It has highly conserved W, R and L residues.", "domain_architectures": 4, "interpro_id": "IPR058323", "known_evidence_count": null, "matches": 2758, "name": "Domain of unknown function (DUF8010)", "partial_evidence_count": null, "pfam_id": "PF26035", "proteins": 2757, "proteomes": 2749, "short_name": "DUF8010", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26035", "structures": 0, "taxa": 3160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1737, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 80 residues in length. Members of this family contain four highly conserved cysteine residues. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009910", "known_evidence_count": null, "matches": 2748, "name": "Protein of unknown function (DUF1450)", "partial_evidence_count": null, "pfam_id": "PF07293", "proteins": 2748, "proteomes": 1437, "short_name": "DUF1450", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07293", "structures": 0, "taxa": 1909, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2403, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in eukaryotes. This presumed domain is about 100 amino acids in length. This domain is found associated with [pfam:PF02214], [pfam:PF00520].", "domain_architectures": 23, "interpro_id": "IPR024587", "known_evidence_count": null, "matches": 2745, "name": "Domain of unknown function (DUF3399)", "partial_evidence_count": null, "pfam_id": "PF11879", "proteins": 2742, "proteomes": 1070, "short_name": "DUF3399", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11879", "structures": 17, "taxa": 3604, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1912, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 9, "interpro_id": "IPR025427", "known_evidence_count": null, "matches": 2735, "name": "Domain of unknown function (DUF4160)", "partial_evidence_count": null, "pfam_id": "PF13711", "proteins": 2735, "proteomes": 1927, "short_name": "DUF4160", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13711", "structures": 0, "taxa": 3813, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Plant protein of unknown function.", "domain_architectures": 36, "interpro_id": "IPR006927", "known_evidence_count": null, "matches": 2812, "name": "Plant protein of unknown function (DUF639)", "partial_evidence_count": null, "pfam_id": "PF04842", "proteins": 2733, "proteomes": 387, "short_name": "DUF639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04842", "structures": 0, "taxa": 1084, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1936, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 17, "interpro_id": "IPR018744", "known_evidence_count": null, "matches": 2733, "name": "Uncharacterized conserved protein (DUF2293)", "partial_evidence_count": null, "pfam_id": "PF10056", "proteins": 2733, "proteomes": 2176, "short_name": "DUF2293", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10056", "structures": 0, "taxa": 3539, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2265, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents Uncharacterized protein KIAA0930 homolog found in animals. KIAA0930 is localised in the cytosol and not secreted from cells. Expression of KIAA0930 (C22orf9) is significantly higher in pancreatic, colorectal, gastric, and tongue cancer tissues than in normal tissues [[cite:PUB00163385]].", "domain_architectures": 52, "interpro_id": "", "known_evidence_count": null, "matches": 2841, "name": "Uncharacterized conserved protein (DUF2045)", "partial_evidence_count": null, "pfam_id": "PF09741", "proteins": 2724, "proteomes": 1472, "short_name": "DUF2045", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09741", "structures": 0, "taxa": 4691, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1779, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021321", "known_evidence_count": null, "matches": 2724, "name": "Protein of unknown function (DUF2922)", "partial_evidence_count": null, "pfam_id": "PF11148", "proteins": 2724, "proteomes": 1878, "short_name": "DUF2922", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11148", "structures": 0, "taxa": 2845, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2346, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family is found from fungi to humans, but its exact function is not known.", "domain_architectures": 47, "interpro_id": "", "known_evidence_count": null, "matches": 2725, "name": "Domain of unknown function (DUF4078)", "partial_evidence_count": null, "pfam_id": "PF13300", "proteins": 2722, "proteomes": 2448, "short_name": "DUF4078", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13300", "structures": 0, "taxa": 6555, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1544, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal helical domain of DUF1631 protein family proteins. The members of this family are sequences derived from a group of hypothetical proteins expressed by certain bacterial species.", "domain_architectures": 26, "interpro_id": "IPR012434", "known_evidence_count": null, "matches": 2722, "name": "Protein of unknown function (DUF1631) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF07793", "proteins": 2721, "proteomes": 1510, "short_name": "DUF1631", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07793", "structures": 0, "taxa": 2014, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1653, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR018636", "known_evidence_count": null, "matches": 2718, "name": "Uncharacterized protein conserved in bacteria (DUF2058)", "partial_evidence_count": null, "pfam_id": "PF09831", "proteins": 2715, "proteomes": 2460, "short_name": "DUF2058", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09831", "structures": 0, "taxa": 3341, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1700, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR025235", "known_evidence_count": null, "matches": 3295, "name": "Domain of unknown function (DUF4178)", "partial_evidence_count": null, "pfam_id": "PF13785", "proteins": 2715, "proteomes": 2530, "short_name": "DUF4178", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13785", "structures": 0, "taxa": 3683, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1674, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 190 and 214 amino acids in length. There are two conserved sequence motifs: VYQAY and RMTW.", "domain_architectures": 28, "interpro_id": "IPR025633", "known_evidence_count": null, "matches": 2732, "name": "Domain of unknown function (DUF4291)", "partial_evidence_count": null, "pfam_id": "PF14124", "proteins": 2713, "proteomes": 2361, "short_name": "DUF4291", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14124", "structures": 0, "taxa": 4128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1749, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 180 residues in length. The function of this family is unknown.", "domain_architectures": 32, "interpro_id": "IPR009858", "known_evidence_count": null, "matches": 2722, "name": "Protein of unknown function (DUF1415)", "partial_evidence_count": null, "pfam_id": "PF07209", "proteins": 2712, "proteomes": 2492, "short_name": "DUF1415", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07209", "structures": 0, "taxa": 3434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1561, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins with unknown function appear to be restricted to Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR021385", "known_evidence_count": null, "matches": 2698, "name": "Protein of unknown function (DUF3017)", "partial_evidence_count": null, "pfam_id": "PF11222", "proteins": 2698, "proteomes": 2674, "short_name": "DUF3017", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11222", "structures": 0, "taxa": 3186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1812, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Rhizobiales specific proteins of around 270 residues in length. The function of this family is unknown.", "domain_architectures": 25, "interpro_id": "IPR010607", "known_evidence_count": null, "matches": 2706, "name": "Protein of unknown function (DUF1194)", "partial_evidence_count": null, "pfam_id": "PF06707", "proteins": 2696, "proteomes": 1341, "short_name": "DUF1194", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06707", "structures": 0, "taxa": 2089, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria, archaea and eukaryotes, and is typically between 135 and 166 amino acids in length. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 35, "interpro_id": "IPR022227", "known_evidence_count": null, "matches": 2711, "name": "Protein of unknown function (DUF3754)", "partial_evidence_count": null, "pfam_id": "PF12576", "proteins": 2696, "proteomes": 1027, "short_name": "DUF3754", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12576", "structures": 0, "taxa": 2922, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1692, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 23, "interpro_id": "IPR014543", "known_evidence_count": null, "matches": 2690, "name": "Uncharacterized protein conserved in bacteria (DUF2218)", "partial_evidence_count": null, "pfam_id": "PF09981", "proteins": 2690, "proteomes": 2280, "short_name": "DUF2218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09981", "structures": 1, "taxa": 3264, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2075, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 41, "interpro_id": "IPR018971", "known_evidence_count": null, "matches": 2734, "name": "Protein of unknown function (DUF1997)", "partial_evidence_count": null, "pfam_id": "PF09366", "proteins": 2687, "proteomes": 728, "short_name": "DUF1997", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09366", "structures": 0, "taxa": 2024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1802, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical archaeal proteins have no known function.", "domain_architectures": 4, "interpro_id": "IPR019277", "known_evidence_count": null, "matches": 2678, "name": "Uncharacterized conserved protein (DUF2304)", "partial_evidence_count": null, "pfam_id": "PF10066", "proteins": 2678, "proteomes": 2509, "short_name": "DUF2304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10066", "structures": 0, "taxa": 3785, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1753, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 426 to 444 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR021830", "known_evidence_count": null, "matches": 2688, "name": "Protein of unknown function (DUF3422)", "partial_evidence_count": null, "pfam_id": "PF11902", "proteins": 2677, "proteomes": 2520, "short_name": "DUF3422", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11902", "structures": 0, "taxa": 3650, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1730, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 125 and 141 amino acids in length. There is a single completely conserved residue E that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR025597", "known_evidence_count": null, "matches": 2670, "name": "Domain of unknown function (DUF4345)", "partial_evidence_count": null, "pfam_id": "PF14248", "proteins": 2670, "proteomes": 2303, "short_name": "DUF4345", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14248", "structures": 0, "taxa": 3531, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1677, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial and archaeal proteins of around 200 residues in length. The function of this family is unknown. The family carries a repeated glycine-zipper sequence- motif, GxxxGxxxG, where the x following the G is frequently found to be an alanine. As glycine-zippers occur in membrane proteins, this family is likely to be found spanning a membrane.", "domain_architectures": 8, "interpro_id": "IPR009200", "known_evidence_count": null, "matches": 2668, "name": "Protein of unknown function (DUF1269)", "partial_evidence_count": null, "pfam_id": "PF06897", "proteins": 2668, "proteomes": 2012, "short_name": "DUF1269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06897", "structures": 0, "taxa": 3219, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1645, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in Proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR024409", "known_evidence_count": null, "matches": 2661, "name": "Protein of unknown function (DUF3833)", "partial_evidence_count": null, "pfam_id": "PF12915", "proteins": 2661, "proteomes": 2497, "short_name": "DUF3833", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12915", "structures": 0, "taxa": 3609, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1673, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short presumed domain is found at the N-terminus of a variety of phage integrase proteins.", "domain_architectures": 21, "interpro_id": "IPR046668", "known_evidence_count": null, "matches": 2658, "name": "Domain of unknown function (DUF6538)", "partial_evidence_count": null, "pfam_id": "PF20172", "proteins": 2658, "proteomes": 1858, "short_name": "DUF6538", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20172", "structures": 0, "taxa": 2995, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1654, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR025234", "known_evidence_count": null, "matches": 2656, "name": "Domain of unknown function (DUF4177)", "partial_evidence_count": null, "pfam_id": "PF13783", "proteins": 2656, "proteomes": 2342, "short_name": "DUF4177", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13783", "structures": 0, "taxa": 3820, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1692, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 17, "interpro_id": "IPR024402", "known_evidence_count": null, "matches": 2654, "name": "Protein of unknown function (DUF2726)", "partial_evidence_count": null, "pfam_id": "PF10881", "proteins": 2654, "proteomes": 2261, "short_name": "DUF2726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10881", "structures": 0, "taxa": 3959, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2509, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, predominantly in Platyhelminthes, and is approximately 40 amino acids in length. It contains the conserved sequences QLxNIWNSK and KxRIFN. Many sequences containing this domain also contain a reverse transcriptase domain ([pfam:PF00078]).", "domain_architectures": 141, "interpro_id": "IPR045609", "known_evidence_count": null, "matches": 2694, "name": "Domain of unknown function (DUF6451)", "partial_evidence_count": null, "pfam_id": "PF20049", "proteins": 2654, "proteomes": 93, "short_name": "DUF6451", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20049", "structures": 0, "taxa": 536, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, archaea and eukaryotes. This domain is typically between 259 to 282 amino acids in length. This domain is found associated with [pfam:PF00534]. This domain has two conserved sequence motifs: GGVS and EHGIY.", "domain_architectures": 20, "interpro_id": "IPR022622", "known_evidence_count": null, "matches": 2821, "name": "Domain of unknown function (DUF3492)", "partial_evidence_count": null, "pfam_id": "PF11997", "proteins": 2650, "proteomes": 2116, "short_name": "DUF3492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11997", "structures": 0, "taxa": 3236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2223, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 180 amino acids in length.", "domain_architectures": 50, "interpro_id": "IPR025283", "known_evidence_count": null, "matches": 2677, "name": "Domain of unknown function (DUF4042)", "partial_evidence_count": null, "pfam_id": "PF13251", "proteins": 2648, "proteomes": 1668, "short_name": "DUF4042", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13251", "structures": 0, "taxa": 5264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1607, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 21, "interpro_id": "IPR018763", "known_evidence_count": null, "matches": 2631, "name": "Uncharacterized protein conserved in bacteria (DUF2334)", "partial_evidence_count": null, "pfam_id": "PF10096", "proteins": 2631, "proteomes": 2300, "short_name": "DUF2334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10096", "structures": 0, "taxa": 3558, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1621, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "These proteins, from several diverse bacteria, share a short conserved sequence towards their N termini.", "domain_architectures": 5, "interpro_id": "IPR011466", "known_evidence_count": null, "matches": 2626, "name": "Protein of unknown function (DUF1572)", "partial_evidence_count": null, "pfam_id": "PF07609", "proteins": 2625, "proteomes": 1879, "short_name": "DUF1572", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07609", "structures": 0, "taxa": 2488, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1594, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This is an N-terminal domain found in pyrimidine/purine nucleotide 5'-monophosphate nucleosidases (PpnN) in bacteria. PpnN catalyzes the hydrolysis of the N-glycosidic bond of diverse pyrimidine and purine nucleotide 5'-monophosphates, to form ribose 5-phosphate and the corresponding free base. It can use AMP, GMP, IMP, CMP, dTMP and UMP as substrates [[cite:PUB00084997]]. It is found in association with [pfam:PF03641] and [pfam:PF11892].", "domain_architectures": 5, "interpro_id": "IPR027820", "known_evidence_count": null, "matches": 2624, "name": "Pyrimidine/purine nucleotide 5'-monophosphate nucleosidases", "partial_evidence_count": null, "pfam_id": "PF14793", "proteins": 2624, "proteomes": 2618, "short_name": "DUF4478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14793", "structures": 9, "taxa": 3448, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1690, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain appears to be restricted to the Bacillales.", "domain_architectures": 3, "interpro_id": "IPR012452", "known_evidence_count": null, "matches": 2614, "name": "Protein of unknown function (DUF1657)", "partial_evidence_count": null, "pfam_id": "PF07870", "proteins": 2614, "proteomes": 910, "short_name": "DUF1657", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07870", "structures": 0, "taxa": 1310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in a group of uncharacterised proteins mainly from plants. This domain is predicted to adopt a globular structure that folds into a four helical bundle and has a significant sequence and structural similarity to MLKL executioner domain ([pfam:PF22215]).", "domain_architectures": 52, "interpro_id": "IPR054296", "known_evidence_count": null, "matches": 2617, "name": "Domain of unknown function (DUF7032)", "partial_evidence_count": null, "pfam_id": "PF23005", "proteins": 2612, "proteomes": 375, "short_name": "DUF7032", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23005", "structures": 0, "taxa": 1022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1820, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 274 and 374 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR025332", "known_evidence_count": null, "matches": 2651, "name": "Protein of unknown function (DUF4238)", "partial_evidence_count": null, "pfam_id": "PF14022", "proteins": 2610, "proteomes": 2089, "short_name": "DUF4238", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14022", "structures": 0, "taxa": 4121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1562, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 10, "interpro_id": "IPR010352", "known_evidence_count": null, "matches": 2630, "name": "Bacterial protein of unknown function (DUF945)", "partial_evidence_count": null, "pfam_id": "PF06097", "proteins": 2593, "proteomes": 2319, "short_name": "DUF945", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06097", "structures": 0, "taxa": 3254, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1907, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 19, "interpro_id": "IPR004256", "known_evidence_count": null, "matches": 2584, "name": "Archaea bacterial proteins of unknown function", "partial_evidence_count": null, "pfam_id": "PF03008", "proteins": 2584, "proteomes": 1684, "short_name": "DUF234", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03008", "structures": 0, "taxa": 3107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a plant and fungal family of unknown function. This family contains many hypothetical proteins.", "domain_architectures": 53, "interpro_id": "IPR013744", "known_evidence_count": null, "matches": 2631, "name": "Protein of unknown function (DUF1749)", "partial_evidence_count": null, "pfam_id": "PF08538", "proteins": 2584, "proteomes": 1716, "short_name": "DUF1749", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08538", "structures": 2, "taxa": 3969, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1482, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to mycobacteria.", "domain_architectures": 2, "interpro_id": "IPR019681", "known_evidence_count": null, "matches": 2584, "name": "Protein of unknown function (DUF2530)", "partial_evidence_count": null, "pfam_id": "PF10745", "proteins": 2584, "proteomes": 2576, "short_name": "DUF2530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10745", "structures": 0, "taxa": 3047, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1641, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in bacteria but its function is not known.", "domain_architectures": 2, "interpro_id": "IPR021738", "known_evidence_count": null, "matches": 2584, "name": "Protein of unknown function (DUF3309)", "partial_evidence_count": null, "pfam_id": "PF11752", "proteins": 2584, "proteomes": 2118, "short_name": "DUF3309", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11752", "structures": 0, "taxa": 3007, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this family are found in Fungi. This region is predicted as a transmembrane.", "domain_architectures": 76, "interpro_id": "IPR046623", "known_evidence_count": null, "matches": 2587, "name": "Family of unknown function (DUF6536)", "partial_evidence_count": null, "pfam_id": "PF20163", "proteins": 2579, "proteomes": 716, "short_name": "DUF6536", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20163", "structures": 0, "taxa": 1433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1462, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 7, "interpro_id": "IPR021708", "known_evidence_count": null, "matches": 2575, "name": "Domain of unknown function (DUF3291)", "partial_evidence_count": null, "pfam_id": "PF11695", "proteins": 2574, "proteomes": 2206, "short_name": "DUF3291", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11695", "structures": 0, "taxa": 3311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes and viruses. Proteins in this family are typically between 161 and 256 amino acids in length.", "domain_architectures": 37, "interpro_id": "IPR022036", "known_evidence_count": null, "matches": 2782, "name": "Protein of unknown function (DUF3605)", "partial_evidence_count": null, "pfam_id": "PF12239", "proteins": 2570, "proteomes": 1491, "short_name": "DUF3605", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12239", "structures": 1, "taxa": 3249, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1737, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical bacterial proteins of unknown function.", "domain_architectures": 7, "interpro_id": "IPR009534", "known_evidence_count": null, "matches": 2569, "name": "Protein of unknown function (DUF1153)", "partial_evidence_count": null, "pfam_id": "PF06627", "proteins": 2569, "proteomes": 2350, "short_name": "DUF1153", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06627", "structures": 2, "taxa": 3290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1215, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from plants. It is predicted to adopt a globular structure that has significant sequence and structural similarity to MBD domains.", "domain_architectures": 126, "interpro_id": "IPR054292", "known_evidence_count": null, "matches": 3423, "name": "Domain of unknown function (DUF7028)", "partial_evidence_count": null, "pfam_id": "PF22970", "proteins": 2569, "proteomes": 369, "short_name": "DUF7028", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22970", "structures": 0, "taxa": 1005, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2072, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 60 amino acids in length.", "domain_architectures": 52, "interpro_id": "IPR022190", "known_evidence_count": null, "matches": 2613, "name": "Protein of unknown function (DUF3716)", "partial_evidence_count": null, "pfam_id": "PF12511", "proteins": 2566, "proteomes": 685, "short_name": "DUF3716", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12511", "structures": 0, "taxa": 1339, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1332, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001774) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the MS-271 biosynthetic gene cluster from Streptomyces sp [[cite:PUB00099453]]. This family appears to be predominantly found in Actinobacteria. Some members of this family have been identified as putative cholesterol esterases.", "domain_architectures": 3, "interpro_id": "IPR046198", "known_evidence_count": null, "matches": 2566, "name": "Family of unknown function (DUF6230)", "partial_evidence_count": null, "pfam_id": "PF19741", "proteins": 2566, "proteomes": 1589, "short_name": "DUF6230", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19741", "structures": 0, "taxa": 1916, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1905, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of proteins identified in Rhodopirellula baltica.", "domain_architectures": 8, "interpro_id": "IPR011447", "known_evidence_count": null, "matches": 2566, "name": "Protein of unknown function (DUF1552)", "partial_evidence_count": null, "pfam_id": "PF07586", "proteins": 2565, "proteomes": 491, "short_name": "HXXSHH", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07586", "structures": 0, "taxa": 970, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1761, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is only found in bacteria. This presumed domain is typically between 116 to 159 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR024573", "known_evidence_count": null, "matches": 2668, "name": "Domain of unknown function (DUF3333)", "partial_evidence_count": null, "pfam_id": "PF11812", "proteins": 2565, "proteomes": 2532, "short_name": "DUF3333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11812", "structures": 0, "taxa": 3759, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2221, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 7, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 33 } }, "demotion_reasons": [], "description": "Proteins containing this domain include early growth response protein 1/2/3 (EGR1/2/3). EGR1 is a transcriptional regulator that binds specifically to 9-bp target sequences containing two CpG sites that can potentially be methylated at four cytosine bases [[cite:PUB00086408]]. EGR2, also known as Krox20, is an E3 ligase that sumoylates its Nab coregulators [[cite:PUB00086407]]. This domain has a single completely conserved residue P that may be functionally important. Furthermore, it is found associated with [pfam:PF00096].", "domain_architectures": 14, "interpro_id": "IPR021849", "known_evidence_count": null, "matches": 2576, "name": "Early growth response N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF11928", "proteins": 2563, "proteomes": 717, "short_name": "DUF3446", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11928", "structures": 2, "taxa": 2470, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2092, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 40 amino acids in length. There is a single completely conserved residue N that may be functionally important.", "domain_architectures": 27, "interpro_id": "IPR022228", "known_evidence_count": null, "matches": 2563, "name": "Protein of unknown function (DUF3755)", "partial_evidence_count": null, "pfam_id": "PF12579", "proteins": 2562, "proteomes": 410, "short_name": "DUF3755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12579", "structures": 0, "taxa": 1131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1533, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 5, "interpro_id": "IPR027839", "known_evidence_count": null, "matches": 2755, "name": "Domain of unknown function (DUF4432)", "partial_evidence_count": null, "pfam_id": "PF14486", "proteins": 2555, "proteomes": 2198, "short_name": "DUF4432", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14486", "structures": 1, "taxa": 3504, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1509, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 170 amino acids in length. The family is found in association with [pfam:PF06293].", "domain_architectures": 9, "interpro_id": "IPR025111", "known_evidence_count": null, "matches": 2555, "name": "Domain of unknown function (DUF4032)", "partial_evidence_count": null, "pfam_id": "PF13224", "proteins": 2552, "proteomes": 2527, "short_name": "DUF4032", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13224", "structures": 0, "taxa": 3209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found on the C-terminal of C7orf25 protein UPF0415. The C-terminal domain is homologous to the known PIN-like domains. The PIN-like domain is widespread among eukaryotes, including animals, plants, and fungi, but also present in some cyanobacteria, Deinococcus, and dsDNA viruses from the Mimiviridae family. The domain retains up to four potential catalytic residues, thus, depending on the protein is predicted to be an active or inactive nuclease and in a majority of the family members, the PIN-like domain is N-terminally fused with a potentially active PD-(D/E)XK-like domain [pfam:PF18474] [[cite:PUB00091006]].", "domain_architectures": 49, "interpro_id": "IPR010733", "known_evidence_count": null, "matches": 2576, "name": "Protein of unknown function (DUF1308)", "partial_evidence_count": null, "pfam_id": "PF07000", "proteins": 2550, "proteomes": 2155, "short_name": "DUF1308", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07000", "structures": 0, "taxa": 6269, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2479, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins that are found in Trichomonas.", "domain_architectures": 7, "interpro_id": "IPR024365", "known_evidence_count": null, "matches": 2556, "name": "Protein of unknown function (DUF3839)", "partial_evidence_count": null, "pfam_id": "PF12943", "proteins": 2550, "proteomes": 6, "short_name": "DUF3839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12943", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1819, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A region of similarity shared by several Rhodopirellula baltica cytochrome-like proteins that are predicted to be secreted. These proteins also match [pfam:PF07626] and [pfam:PF07624].", "domain_architectures": 136, "interpro_id": "IPR013039", "known_evidence_count": null, "matches": 2547, "name": "Protein of unknown function (DUF1588)", "partial_evidence_count": null, "pfam_id": "PF07627", "proteins": 2547, "proteomes": 493, "short_name": "PSCyt3", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07627", "structures": 0, "taxa": 968, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1724, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family corresponds to the C-terminal domain of proteins that are thought to belong to the rhomboid family. It is approximately 40 amino acids in length and it is found mainly in Bacteroidetes. It contains the conserved sequences DxILDKI, GYxxL and EKxxL.", "domain_architectures": 6, "interpro_id": "IPR046483", "known_evidence_count": null, "matches": 2544, "name": "Family of unknown function (DUF6576)", "partial_evidence_count": null, "pfam_id": "PF20216", "proteins": 2544, "proteomes": 2355, "short_name": "DUF6576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20216", "structures": 0, "taxa": 3320, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of membrane bound beta barrel proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes bacteria. Proteins in this family are typically between 227 and 265 amino acids in length.", "domain_architectures": 14, "interpro_id": "IPR045743", "known_evidence_count": null, "matches": 2627, "name": "Domain of unknown function (DUF6089)", "partial_evidence_count": null, "pfam_id": "PF19573", "proteins": 2543, "proteomes": 1896, "short_name": "DUF6089", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19573", "structures": 0, "taxa": 2478, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1646, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents an uncharacterised domain found in bacterial proteins from the Bacteroidota phylum, particularly in members of Flavobacteriaceae and Sphingobacteriaceae. The domain typically spans approximately 90-100 residues and is positioned between the TMEM260-like domain ([pfam:PF11028]) and the TMEM260_2 domain ([pfam:PF28495]) in the protein architecture. These proteins appear to be glycosyltransferases or related membrane proteins. The function of this domain remains to be determined.", "domain_architectures": 9, "interpro_id": "IPR059460", "known_evidence_count": null, "matches": 2539, "name": "Family of unknown function (DUF8416)", "partial_evidence_count": null, "pfam_id": "PF28497", "proteins": 2539, "proteomes": 2033, "short_name": "DUF8416", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28497", "structures": 0, "taxa": 2685, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1314, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR043763", "known_evidence_count": null, "matches": 2538, "name": "Family of unknown function (DUF5709)", "partial_evidence_count": null, "pfam_id": "PF18970", "proteins": 2538, "proteomes": 1908, "short_name": "DUF5709", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18970", "structures": 0, "taxa": 2248, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2099, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 37, "interpro_id": "IPR021261", "known_evidence_count": null, "matches": 2583, "name": "Protein of unknown function (DUF2838)", "partial_evidence_count": null, "pfam_id": "PF10998", "proteins": 2537, "proteomes": 1956, "short_name": "DUF2838", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10998", "structures": 0, "taxa": 4648, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1643, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Predicted transmembrane domain of unknown function. The majority of the family have two predicted transmembrane regions.", "domain_architectures": 1, "interpro_id": "IPR007211", "known_evidence_count": null, "matches": 2535, "name": "Domain of unknown function (DUF378)", "partial_evidence_count": null, "pfam_id": "PF04070", "proteins": 2535, "proteomes": 2189, "short_name": "DUF378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04070", "structures": 0, "taxa": 3504, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1679, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this uncharacterised protein family are found sporadically, so far only among spirochetes, epsilon and delta proteobacteria, and Bacteroides. The function is unknown and its gene neighbourhoods show little conservation.", "domain_architectures": 3, "interpro_id": "IPR014127", "known_evidence_count": null, "matches": 2566, "name": "Protein of unknown function (DUF2400)", "partial_evidence_count": null, "pfam_id": "PF09674", "proteins": 2533, "proteomes": 2480, "short_name": "DUF2400", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09674", "structures": 0, "taxa": 3560, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1682, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 3, "interpro_id": "IPR016772", "known_evidence_count": null, "matches": 2532, "name": "Uncharacterized protein conserved in bacteria (DUF2325)", "partial_evidence_count": null, "pfam_id": "PF10087", "proteins": 2532, "proteomes": 2173, "short_name": "DUF2325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10087", "structures": 0, "taxa": 3547, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1567, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria. The function is not known.", "domain_architectures": 6, "interpro_id": "IPR021284", "known_evidence_count": null, "matches": 2556, "name": "Protein of unknown function (DUF2750)", "partial_evidence_count": null, "pfam_id": "PF11042", "proteins": 2526, "proteomes": 1721, "short_name": "DUF2750", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11042", "structures": 0, "taxa": 2597, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, eukaryotes and viruses. Proteins in this family are typically between 182 and 530 amino acids in length. There is a single completely conserved residue D that may be functionally important.", "domain_architectures": 67, "interpro_id": "IPR025375", "known_evidence_count": null, "matches": 2517, "name": "Domain of unknown function (DUF4365)", "partial_evidence_count": null, "pfam_id": "PF14280", "proteins": 2517, "proteomes": 2128, "short_name": "DUF4365", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14280", "structures": 9, "taxa": 3573, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1346, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the domain of unknown function at the N-terminal domain in putative histidine kinases mostly found in bacteria. This domain (VBS) belongs to proteins with a conserved four or five- helix up-and-down bundle structure. This structure is typical of focal adhesion targeting (FAT) domains and is responsible for dimerisation. These proteins are also present in transcriptional regulators where the bundle structure is important for their dynamic conformational equilibrium to control target specificity. The conserved helical bundle architecture enables these proteins to function in protein-protein interactions and regulatory processes [[cite:PUB00075415],[cite:PUB00004911],[cite:PUB00161916]]. This domain is usually find associated with [pfam:PF07730].", "domain_architectures": 6, "interpro_id": "IPR059362", "known_evidence_count": null, "matches": 2519, "name": "Domain of unknown function (DUF8318)", "partial_evidence_count": null, "pfam_id": "PF26992", "proteins": 2517, "proteomes": 1779, "short_name": "DUF8318", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26992", "structures": 0, "taxa": 2159, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1771, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins.", "domain_architectures": 123, "interpro_id": "IPR061760", "known_evidence_count": null, "matches": 2511, "name": "Domain of unknown function (DUF8699)", "partial_evidence_count": null, "pfam_id": "PF30713", "proteins": 2506, "proteomes": 228, "short_name": "DUF8699", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30713", "structures": 0, "taxa": 1088, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2230, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several eukaryotic proteins of unknown function.", "domain_architectures": 24, "interpro_id": "IPR007998", "known_evidence_count": null, "matches": 2540, "name": "Protein of unknown function (DUF719)", "partial_evidence_count": null, "pfam_id": "PF05334", "proteins": 2504, "proteomes": 1178, "short_name": "DUF719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05334", "structures": 0, "taxa": 3885, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1794, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A region of similarity shared by several Rhodopirellula baltica cytochrome-like proteins that are predicted to be secreted. These proteins also match [pfam:PF07627], [pfam:PF07626], and [pfam:PF07624].", "domain_architectures": 142, "interpro_id": "IPR013042", "known_evidence_count": null, "matches": 2515, "name": "Protein of unknown function (DUF1592)", "partial_evidence_count": null, "pfam_id": "PF07631", "proteins": 2504, "proteomes": 490, "short_name": "PSD4", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07631", "structures": 0, "taxa": 965, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2003, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised eukaryotic proteins. It has detectable similarity to domains members of the MLKL N-terminal domain superfamily and is predicted to adopt similar structure.", "domain_architectures": 69, "interpro_id": "IPR056694", "known_evidence_count": null, "matches": 2512, "name": "Domain of unknown function (DUF7792)", "partial_evidence_count": null, "pfam_id": "PF25055", "proteins": 2502, "proteomes": 376, "short_name": "DUF7792", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25055", "structures": 0, "taxa": 1028, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1487, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function.", "domain_architectures": 8, "interpro_id": "IPR008535", "known_evidence_count": null, "matches": 2499, "name": "Protein of unknown function (DUF817)", "partial_evidence_count": null, "pfam_id": "PF05675", "proteins": 2498, "proteomes": 2468, "short_name": "DUF817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05675", "structures": 0, "taxa": 3479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1501, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 262 to 463 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR021834", "known_evidence_count": null, "matches": 2494, "name": "Protein of unknown function (DUF3426)", "partial_evidence_count": null, "pfam_id": "PF11906", "proteins": 2494, "proteomes": 2486, "short_name": "DUF3426", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11906", "structures": 0, "taxa": 3391, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1572, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry contains a number of hypothetical bacterial proteins of unknown function. Some family members contain more than one copy of this domain. This domain may adopt a barrel-like fold.", "domain_architectures": 13, "interpro_id": "IPR009642", "known_evidence_count": null, "matches": 2630, "name": "Domain of unknown function (DUF1236)", "partial_evidence_count": null, "pfam_id": "PF06823", "proteins": 2493, "proteomes": 879, "short_name": "DUF1236", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06823", "structures": 0, "taxa": 1179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1581, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 366 and 597 amino acids in length. There is a single completely conserved residue R that may be functionally important.", "domain_architectures": 14, "interpro_id": "IPR025519", "known_evidence_count": null, "matches": 2527, "name": "Domain of unknown function (DUF4407)", "partial_evidence_count": null, "pfam_id": "PF14362", "proteins": 2491, "proteomes": 2160, "short_name": "DUF4407", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14362", "structures": 0, "taxa": 2938, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1356, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in bacteria. According to structure predictions, members of this entry may consist of a novel repeat fold containing four repeat units, each of them containing eight antiparallel beta-strands.", "domain_architectures": 13, "interpro_id": "IPR043777", "known_evidence_count": null, "matches": 2499, "name": "Family of unknown function (DUF5719)", "partial_evidence_count": null, "pfam_id": "PF18986", "proteins": 2491, "proteomes": 2474, "short_name": "DUF5719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18986", "structures": 0, "taxa": 2971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1306, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised domains found in lipoproteins Actinomycete bacteria.", "domain_architectures": 4, "interpro_id": "IPR058407", "known_evidence_count": null, "matches": 2495, "name": "Domain of unknown function (DUF8094)", "partial_evidence_count": null, "pfam_id": "PF26366", "proteins": 2485, "proteomes": 1978, "short_name": "DUF8094", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26366", "structures": 0, "taxa": 2305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1489, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria and archaea. This domain is about 140 amino acids in length. This domain is found associated with [pfam:PF04055]. This domain has two conserved sequence motifs: CTPWG and PCYL, plus a highly conserved CxxCxxHC motif.", "domain_architectures": 6, "interpro_id": "IPR022563", "known_evidence_count": null, "matches": 2478, "name": "Domain of unknown function (DUF3463)", "partial_evidence_count": null, "pfam_id": "PF11946", "proteins": 2478, "proteomes": 2397, "short_name": "DUF3463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11946", "structures": 0, "taxa": 3540, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1595, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of conserved bacterial proteins with unknown function.", "domain_architectures": 6, "interpro_id": "IPR010412", "known_evidence_count": null, "matches": 2478, "name": "Protein of unknown function (DUF1007)", "partial_evidence_count": null, "pfam_id": "PF06226", "proteins": 2477, "proteomes": 2327, "short_name": "DUF1007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06226", "structures": 0, "taxa": 3372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 384 and 400 amino acids in length.", "domain_architectures": 38, "interpro_id": "IPR032757", "known_evidence_count": null, "matches": 2768, "name": "Domain of unknown function (DUF4683)", "partial_evidence_count": null, "pfam_id": "PF15735", "proteins": 2475, "proteomes": 744, "short_name": "DUF4683", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15735", "structures": 0, "taxa": 2245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1587, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 200 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032612", "known_evidence_count": null, "matches": 2511, "name": "Domain of unknown function (DUF4890)", "partial_evidence_count": null, "pfam_id": "PF16231", "proteins": 2475, "proteomes": 1642, "short_name": "DUF4890", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16231", "structures": 0, "taxa": 2306, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1982, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Arabidopsis thaliana proteins of around 225 residues in length. The function of this family is unknown.", "domain_architectures": 36, "interpro_id": "IPR009902", "known_evidence_count": null, "matches": 2528, "name": "Protein of unknown function (DUF1442)", "partial_evidence_count": null, "pfam_id": "PF07279", "proteins": 2473, "proteomes": 363, "short_name": "DUF1442", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07279", "structures": 0, "taxa": 992, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2014, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins predominantly from fungi. It has a detectable similarity to ADP ribosyltransferase domains and it is predicted to adopt a similar structure.", "domain_architectures": 50, "interpro_id": "IPR056009", "known_evidence_count": null, "matches": 2483, "name": "Domain of unknown function (DUF7587)", "partial_evidence_count": null, "pfam_id": "PF24494", "proteins": 2473, "proteomes": 995, "short_name": "DUF7587", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24494", "structures": 0, "taxa": 2157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1450, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001769) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the family saquayamycin A biosynthetic gene cluster from Streptomyces sp. and appears to be predominantly found in Actinobacteria [[cite:PUB00098947]].", "domain_architectures": 6, "interpro_id": "IPR045713", "known_evidence_count": null, "matches": 2469, "name": "Family of unknown function (DUF6069)", "partial_evidence_count": null, "pfam_id": "PF19545", "proteins": 2469, "proteomes": 1521, "short_name": "DUF6069", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19545", "structures": 0, "taxa": 2059, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1287, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 181 and 228 amino acids in length. There is a conserved GV motif.", "domain_architectures": 2, "interpro_id": "IPR046253", "known_evidence_count": null, "matches": 2467, "name": "Family of unknown function (DUF6286)", "partial_evidence_count": null, "pfam_id": "PF19803", "proteins": 2467, "proteomes": 1920, "short_name": "DUF6286", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19803", "structures": 0, "taxa": 2291, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1415, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 100 residues in length. Members of this family appear to be Actinomycete specific. The function of this family is unknown.", "domain_architectures": 18, "interpro_id": "IPR010814", "known_evidence_count": null, "matches": 2465, "name": "Protein of unknown function (DUF1416)", "partial_evidence_count": null, "pfam_id": "PF07210", "proteins": 2465, "proteomes": 2435, "short_name": "DUF1416", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07210", "structures": 0, "taxa": 2871, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1489, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 170 amino acids in length. The domain appears to be related to the GAF domain.", "domain_architectures": 35, "interpro_id": "IPR021800", "known_evidence_count": null, "matches": 2463, "name": "Domain of unknown function (DUF3369)", "partial_evidence_count": null, "pfam_id": "PF11849", "proteins": 2463, "proteomes": 1405, "short_name": "DUF3369", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11849", "structures": 0, "taxa": 2158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1646, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 120 amino acids in length. The family is found in association with [pfam:PF00004]. The proteins in this family are frequently annotated as the gamma and tau subunits of DNA polymerase III, however there is little accompanying literature to back this up.", "domain_architectures": 6, "interpro_id": "IPR022107", "known_evidence_count": null, "matches": 2463, "name": "DNA polymerase III gamma and tau subunits C terminal", "partial_evidence_count": null, "pfam_id": "PF12362", "proteins": 2463, "proteomes": 2459, "short_name": "DUF3646", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12362", "structures": 0, "taxa": 3456, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1537, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 150 residues in length. The function of this family is unknown.", "domain_architectures": 5, "interpro_id": "IPR009659", "known_evidence_count": null, "matches": 2462, "name": "Protein of unknown function (DUF1249)", "partial_evidence_count": null, "pfam_id": "PF06853", "proteins": 2461, "proteomes": 2456, "short_name": "DUF1249", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06853", "structures": 0, "taxa": 3280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1954, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains hypothetical plant proteins of unknown function.", "domain_architectures": 29, "interpro_id": "IPR010605", "known_evidence_count": null, "matches": 2479, "name": "Protein of unknown function (DUF1191)", "partial_evidence_count": null, "pfam_id": "PF06697", "proteins": 2456, "proteomes": 377, "short_name": "DUF1191", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06697", "structures": 0, "taxa": 1036, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1553, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised bacterial proteins which seem to be specific to the orders Clostridia and Bacillales. Family members are typically around 180 residues in length. The function of this family is unknown. These proteins are related to peptidase family M63 and so may be peptidases.", "domain_architectures": 3, "interpro_id": "IPR009665", "known_evidence_count": null, "matches": 2456, "name": "Protein of unknown function (DUF1256)", "partial_evidence_count": null, "pfam_id": "PF06866", "proteins": 2456, "proteomes": 1705, "short_name": "DUF1256", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06866", "structures": 0, "taxa": 2461, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1627, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 3, "interpro_id": "IPR025430", "known_evidence_count": null, "matches": 2455, "name": "Domain of unknown function (DUF4167)", "partial_evidence_count": null, "pfam_id": "PF13763", "proteins": 2455, "proteomes": 2376, "short_name": "DUF4167", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13763", "structures": 0, "taxa": 3279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1365, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is primarily found in actinobacteria. Proteins in this family are typically between 74 and 95 amino acids in length. This domain is related to [pfam:PF18969].", "domain_architectures": 1, "interpro_id": "IPR045597", "known_evidence_count": null, "matches": 2455, "name": "Domain of unknown function (DUF6458)", "partial_evidence_count": null, "pfam_id": "PF20059", "proteins": 2455, "proteomes": 1903, "short_name": "DUF6458", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20059", "structures": 0, "taxa": 2256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1661, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Members of this family of uncharacterised proteins are often named Smg.", "domain_architectures": 1, "interpro_id": "IPR007456", "known_evidence_count": null, "matches": 2454, "name": "Protein of unknown function (DUF494)", "partial_evidence_count": null, "pfam_id": "PF04361", "proteins": 2454, "proteomes": 2385, "short_name": "DUF494", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04361", "structures": 0, "taxa": 3503, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1577, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It shares significant similarity to Ig-like domains, in particular domains members of [pfam:PF12975] (DUF3859) and [pfam:PF22091] (DUF6941).", "domain_architectures": 10, "interpro_id": "IPR059472", "known_evidence_count": null, "matches": 2457, "name": "Domain of unknown function (DUF8428)", "partial_evidence_count": null, "pfam_id": "PF28532", "proteins": 2453, "proteomes": 1798, "short_name": "DUF8428", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28532", "structures": 0, "taxa": 2392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1692, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is typically between 143 and 173 amino acids in length. The family is found in association with [pfam:PF00528]. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 7, "interpro_id": "IPR022182", "known_evidence_count": null, "matches": 2452, "name": "Phosphate ATP-binding cassette transporter", "partial_evidence_count": null, "pfam_id": "PF12501", "proteins": 2451, "proteomes": 2423, "short_name": "DUF3708", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12501", "structures": 0, "taxa": 3490, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1805, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminus of DUF2264 family proteins. This domain adopts a beta sandwich domain that is structurally related to [pfam:PF07940], suggesting that DUF2264 proteins are oligosaccharide degrading enzymes.", "domain_architectures": 21, "interpro_id": "IPR049237", "known_evidence_count": null, "matches": 2471, "name": "DUF2264 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20938", "proteins": 2450, "proteomes": 1675, "short_name": "DUF2264_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20938", "structures": 0, "taxa": 3090, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1590, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins, widespread in gram-negative bacteria. Members contain three well-conserved motifs, HYC, CC (which may appear twice), and PP.", "domain_architectures": 2, "interpro_id": "IPR058512", "known_evidence_count": null, "matches": 2447, "name": "Family of unknown function (DUF8199)", "partial_evidence_count": null, "pfam_id": "PF26622", "proteins": 2443, "proteomes": 1613, "short_name": "DUF8199", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26622", "structures": 0, "taxa": 2119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1447, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of fungal uncharacterised sequences of unknown function. Some members are annotated as related to antimicrobial resistance. There are two highly conserved motifs FYxxLGF and GxPR.", "domain_architectures": 14, "interpro_id": "IPR061878", "known_evidence_count": null, "matches": 2457, "name": "Family of unknown function (DUF8817)", "partial_evidence_count": null, "pfam_id": "PF31120", "proteins": 2442, "proteomes": 2136, "short_name": "DUF8817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31120", "structures": 11, "taxa": 3226, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1680, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in bacteria and archaea, and is typically between 142 and 161 amino acids in length.", "domain_architectures": 21, "interpro_id": "IPR025491", "known_evidence_count": null, "matches": 2461, "name": "Domain of unknown function (DUF4382)", "partial_evidence_count": null, "pfam_id": "PF14321", "proteins": 2441, "proteomes": 1959, "short_name": "DUF4382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14321", "structures": 0, "taxa": 3072, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1891, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It shares similarity to known I/LWEQ domains.", "domain_architectures": 32, "interpro_id": "IPR061782", "known_evidence_count": null, "matches": 2537, "name": "Domain of unknown function (DUF8721)", "partial_evidence_count": null, "pfam_id": "PF30748", "proteins": 2440, "proteomes": 13, "short_name": "DUF8721", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30748", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short family is conserved in Proteobacteria. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR021344", "known_evidence_count": null, "matches": 2439, "name": "Protein of unknown function (DUF2970)", "partial_evidence_count": null, "pfam_id": "PF11174", "proteins": 2439, "proteomes": 2191, "short_name": "DUF2970", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11174", "structures": 0, "taxa": 2770, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1418, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes LftS, a soluble globular cytoplasmic protein of unknown function. It is suggested that LftS acts in aurantimycin A sensing or in removal of LftR from its operator sites.", "domain_architectures": 3, "interpro_id": "IPR008316", "known_evidence_count": null, "matches": 2433, "name": "Protein of unknown function (DUF1048)", "partial_evidence_count": null, "pfam_id": "PF06304", "proteins": 2432, "proteomes": 1535, "short_name": "DUF1048", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06304", "structures": 3, "taxa": 2136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1664, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 138 and 177 amino acids in length.", "domain_architectures": 44, "interpro_id": "IPR045632", "known_evidence_count": null, "matches": 2571, "name": "Family of unknown function (DUF6314)", "partial_evidence_count": null, "pfam_id": "PF19834", "proteins": 2428, "proteomes": 2262, "short_name": "DUF6314", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19834", "structures": 0, "taxa": 3878, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1364, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a presumed domain that is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 294 and 327 amino acids in length. Many proteins in this family are annotated at Topoisomerase II, but the source of this annotation is unclear.", "domain_architectures": 4, "interpro_id": "IPR045970", "known_evidence_count": null, "matches": 2433, "name": "Family of unknown function (DUF5926)", "partial_evidence_count": null, "pfam_id": "PF19348", "proteins": 2423, "proteomes": 2409, "short_name": "DUF5926", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19348", "structures": 0, "taxa": 2856, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in eukaryotes. Proteins in this family are typically between 185 to 298 amino acids in length. This protein is found associated with [pfam:PF00046].", "domain_architectures": 21, "interpro_id": "IPR021918", "known_evidence_count": null, "matches": 2514, "name": "Protein of unknown function (DUF3528)", "partial_evidence_count": null, "pfam_id": "PF12045", "proteins": 2413, "proteomes": 746, "short_name": "DUF3528", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12045", "structures": 0, "taxa": 2346, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1609, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function. Family members are found in Bacteria and Eukaryotes. In algae, this family is found on the N-terminal of diphthamide synthase family [pfam:PF01902] and is predicted to be a membrane transporter belonging to The ATP-binding Cassette (ABC) family [[cite:PUB00091274]]. In nematoda, it is found on the N-terminal side of ribosomal protein family L14 [pfam:PF00238]. It is also found on the N-terminal of Cob(I)alamin adenosyltransferase [pfam:PF01923] in other eukaryotes. Family members found in homo sapiens such as [swissprot:Q5VUE5], have been shown to be highly expressed in 15 high-grade neuroendocrine tumor cell lines and YAP1-positive small-cell lung cancer cell lines [[cite:PUB00091275]] as well as being up-regulated in two human Multiple Myloma cell lines in response to selective nuclear export inhibitor KPT-276 [[cite:PUB00091276]]. The HMM profile of this family reveals 4 highly conserved cysteines.", "domain_architectures": 40, "interpro_id": "IPR040807", "known_evidence_count": null, "matches": 2412, "name": "Family of unknown function (DUF5522)", "partial_evidence_count": null, "pfam_id": "PF17653", "proteins": 2412, "proteomes": 2151, "short_name": "DUF5522", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17653", "structures": 0, "taxa": 4314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1628, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 115 residues in length. Members of this family seem to be found exclusively in the Class Alphaproteobacteria. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR009964", "known_evidence_count": null, "matches": 2410, "name": "Protein of unknown function (DUF1491)", "partial_evidence_count": null, "pfam_id": "PF07372", "proteins": 2410, "proteomes": 2405, "short_name": "DUF1491", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07372", "structures": 3, "taxa": 3267, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2040, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function, which is found in eukaryotes. Proteins in this family are typically between 141 and 174 amino acids in length and contain a conserved LSF sequence motif.", "domain_architectures": 28, "interpro_id": "IPR027911", "known_evidence_count": null, "matches": 2410, "name": "Domain of unknown function (DUF4604)", "partial_evidence_count": null, "pfam_id": "PF15377", "proteins": 2408, "proteomes": 2162, "short_name": "DUF4604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15377", "structures": 0, "taxa": 5846, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. It is predicted to fold into a small alpha/beta structure composed of beta-hairpin and array of helices packed on it. This domain is usually found associated with a pair of P-loop domains with the typical for helicases arrangement.", "domain_architectures": 167, "interpro_id": "IPR059481", "known_evidence_count": null, "matches": 2405, "name": "Domain of unknown function (DUF8437)", "partial_evidence_count": null, "pfam_id": "PF28554", "proteins": 2405, "proteomes": 1679, "short_name": "DUF8437", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28554", "structures": 0, "taxa": 2928, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1918, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of plant proteins with undetermined function.", "domain_architectures": 30, "interpro_id": "IPR010410", "known_evidence_count": null, "matches": 2569, "name": "Protein of unknown function (DUF1005)", "partial_evidence_count": null, "pfam_id": "PF06219", "proteins": 2401, "proteomes": 378, "short_name": "DUF1005", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06219", "structures": 0, "taxa": 1043, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1587, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. However, it does show distant similarity to [pfam:PF00436], with proteins such as [swissprot:D1W984] being similar to both families. This suggests that this family may have a DNA-binding function.", "domain_architectures": 2, "interpro_id": "IPR021474", "known_evidence_count": null, "matches": 2398, "name": "Domain of unknown function (DUF3127)", "partial_evidence_count": null, "pfam_id": "PF11325", "proteins": 2398, "proteomes": 2260, "short_name": "DUF3127", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11325", "structures": 0, "taxa": 3154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1568, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found mostly in bacteria.", "domain_architectures": 11, "interpro_id": "IPR043738", "known_evidence_count": null, "matches": 2416, "name": "Family of unknown function (DUF5683)", "partial_evidence_count": null, "pfam_id": "PF18935", "proteins": 2397, "proteomes": 2262, "short_name": "DUF5683", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18935", "structures": 0, "taxa": 3174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 402, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found at the N-terminus of a variety of proteins that contain [pfam:PF12340].", "domain_architectures": 50, "interpro_id": "IPR046541", "known_evidence_count": null, "matches": 2438, "name": "Family of unknown function (DUF6606)", "partial_evidence_count": null, "pfam_id": "PF20255", "proteins": 2397, "proteomes": 901, "short_name": "DUF6606", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20255", "structures": 0, "taxa": 1967, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1364, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 188 and 316 amino acids in length.", "domain_architectures": 16, "interpro_id": "IPR046732", "known_evidence_count": null, "matches": 2408, "name": "Family of unknown function (DUF6624)", "partial_evidence_count": null, "pfam_id": "PF20329", "proteins": 2397, "proteomes": 1752, "short_name": "DUF6624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20329", "structures": 0, "taxa": 2578, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1200, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000696) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the gentamicin biosynthetic gene cluster from Micromonospora echinospora and appears to be predominantly found in actinobacteria and firmicutes [[cite:PUB00099418],[cite:PUB00098957]].", "domain_architectures": 4, "interpro_id": "IPR046096", "known_evidence_count": null, "matches": 2394, "name": "Family of unknown function (DUF6114)", "partial_evidence_count": null, "pfam_id": "PF19609", "proteins": 2394, "proteomes": 1549, "short_name": "DUF6114", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19609", "structures": 0, "taxa": 1901, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This family of proteins is found in bacteria. This domain is found C-terminal to an MobA-like guanyltransferase domain.", "domain_architectures": 5, "interpro_id": "IPR045598", "known_evidence_count": null, "matches": 2395, "name": "Domain of unknown function (DUF6457)", "partial_evidence_count": null, "pfam_id": "PF20058", "proteins": 2394, "proteomes": 2282, "short_name": "DUF6457", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20058", "structures": 0, "taxa": 2711, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1896, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a number of hypothetical proteins from Arabidopsis thaliana and Oryza sativa. The function of this family is unknown.", "domain_architectures": 57, "interpro_id": "IPR008581", "known_evidence_count": null, "matches": 3273, "name": "Plant protein of unknown function (DUF863)", "partial_evidence_count": null, "pfam_id": "PF05904", "proteins": 2387, "proteomes": 368, "short_name": "DUF863", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05904", "structures": 0, "taxa": 1001, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1882, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an 8-stranded flattened beta barrel domain which shows structural similarity to the lipocalin fold. The domain shows is found in three copies towards the N-terminus of DUF2921 family proteins.", "domain_architectures": 76, "interpro_id": "IPR057425", "known_evidence_count": null, "matches": 6449, "name": "DUF2921 lipocalin-like domain", "partial_evidence_count": null, "pfam_id": "PF25333", "proteins": 2385, "proteomes": 371, "short_name": "DUF2921_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25333", "structures": 0, "taxa": 1021, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1639, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short hypothetical archaeal proteins of unknown function.", "domain_architectures": 5, "interpro_id": "IPR009409", "known_evidence_count": null, "matches": 2404, "name": "Protein of unknown function (DUF1059)", "partial_evidence_count": null, "pfam_id": "PF06348", "proteins": 2384, "proteomes": 2004, "short_name": "DUF1059", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06348", "structures": 0, "taxa": 2876, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1622, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains a number of hypothetical bacterial proteins of unknown function approximately 300 residues in length. Some family members are predicted to be metal-dependent.", "domain_architectures": 6, "interpro_id": "IPR010787", "known_evidence_count": null, "matches": 2384, "name": "Protein of unknown function (DUF1385)", "partial_evidence_count": null, "pfam_id": "PF07136", "proteins": 2381, "proteomes": 2254, "short_name": "DUF1385", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07136", "structures": 0, "taxa": 3776, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1955, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into an alpha/beta structure with topological similarity to AraD-like domains.", "domain_architectures": 18, "interpro_id": "IPR057688", "known_evidence_count": null, "matches": 2397, "name": "Domain of unknown function (DUF7928)", "partial_evidence_count": null, "pfam_id": "PF25550", "proteins": 2379, "proteomes": 946, "short_name": "DUF7928", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25550", "structures": 0, "taxa": 2053, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1432, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 15, "interpro_id": "IPR015003", "known_evidence_count": null, "matches": 2391, "name": "Domain of unknown function (DUF1853)", "partial_evidence_count": null, "pfam_id": "PF08907", "proteins": 2376, "proteomes": 2328, "short_name": "DUF1853", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08907", "structures": 0, "taxa": 3134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2077, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 70 amino acids in length. There is a conserved HLR sequence motif. There are two completely conserved residues (W and H) that may be functionally important.", "domain_architectures": 15, "interpro_id": "IPR022194", "known_evidence_count": null, "matches": 2378, "name": "Protein of unknown function (DUF3719)", "partial_evidence_count": null, "pfam_id": "PF12516", "proteins": 2376, "proteomes": 957, "short_name": "DUF3719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12516", "structures": 0, "taxa": 3148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1373, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 14, "interpro_id": "IPR021607", "known_evidence_count": null, "matches": 2367, "name": "Protein of unknown function (DUF3224)", "partial_evidence_count": null, "pfam_id": "PF11528", "proteins": 2366, "proteomes": 2019, "short_name": "DUF3224", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11528", "structures": 2, "taxa": 2966, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1423, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 80 residues in length. This family contains a number of conserved cysteine residues and its function is unknown.", "domain_architectures": 7, "interpro_id": "IPR010696", "known_evidence_count": null, "matches": 2364, "name": "Protein of unknown function (DUF1272)", "partial_evidence_count": null, "pfam_id": "PF06906", "proteins": 2364, "proteomes": 2314, "short_name": "DUF1272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06906", "structures": 0, "taxa": 3389, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1503, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 110 amino acids in length. The family is found in association with [pfam:PF01734]. There are two completely conserved residues (F and G) that may be functionally important. The proteins in this family are frequently annotated as patatin family phospholipases however there is little accompanying literature to confirm this.", "domain_architectures": 7, "interpro_id": "IPR021095", "known_evidence_count": null, "matches": 2362, "name": "Patatin phospholipase", "partial_evidence_count": null, "pfam_id": "PF12536", "proteins": 2362, "proteomes": 1599, "short_name": "DUF3734", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12536", "structures": 0, "taxa": 2157, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1490, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 140 and 255 amino acids in length. There are two completely conserved C residues that may be functionally important.", "domain_architectures": 9, "interpro_id": "IPR025637", "known_evidence_count": null, "matches": 2649, "name": "Domain of unknown function (DUF4333)", "partial_evidence_count": null, "pfam_id": "PF14230", "proteins": 2361, "proteomes": 1354, "short_name": "DUF4333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14230", "structures": 0, "taxa": 1774, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1484, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 195 and 207 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR025350", "known_evidence_count": null, "matches": 2360, "name": "Protein of unknown function (DUF4254)", "partial_evidence_count": null, "pfam_id": "PF14063", "proteins": 2360, "proteomes": 1902, "short_name": "DUF4254", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14063", "structures": 0, "taxa": 2607, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1568, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. Some members of this family appear to be misannotated as RocC an amino acid transporter from B. subtilis.", "domain_architectures": 6, "interpro_id": "IPR015001", "known_evidence_count": null, "matches": 2360, "name": "Domain of unknown function (DUF1850)", "partial_evidence_count": null, "pfam_id": "PF08905", "proteins": 2359, "proteomes": 2163, "short_name": "DUF1850", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08905", "structures": 0, "taxa": 3378, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1465, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in bacteria. Some family members can be found at the N-terminal region of [pfam:PF00717].", "domain_architectures": 14, "interpro_id": "IPR043739", "known_evidence_count": null, "matches": 2357, "name": "Family of unknown function (DUF5684)", "partial_evidence_count": null, "pfam_id": "PF18936", "proteins": 2355, "proteomes": 1996, "short_name": "DUF5684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18936", "structures": 0, "taxa": 2880, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1879, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family include sequences that are parts of hypothetical proteins expressed by plant species. The region in question is about 170 amino acids long.", "domain_architectures": 37, "interpro_id": "IPR012862", "known_evidence_count": null, "matches": 2445, "name": "Protein of unknown function (DUF1635)", "partial_evidence_count": null, "pfam_id": "PF07795", "proteins": 2354, "proteomes": 378, "short_name": "DUF1635", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07795", "structures": 0, "taxa": 1043, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1573, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 150 residues in length. Members of this family seem to be founds exclusively in the Class Alphaproteobacteria. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR008320", "known_evidence_count": null, "matches": 2352, "name": "Protein of unknown function (DUF1489)", "partial_evidence_count": null, "pfam_id": "PF07370", "proteins": 2352, "proteomes": 2349, "short_name": "DUF1489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07370", "structures": 0, "taxa": 3148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2057, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family is found at the C-terminal of Homeobox proteins in Metazoa.", "domain_architectures": 14, "interpro_id": "IPR025281", "known_evidence_count": null, "matches": 2349, "name": "Domain of unknown function (DUF4074)", "partial_evidence_count": null, "pfam_id": "PF13293", "proteins": 2349, "proteomes": 748, "short_name": "DUF4074", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13293", "structures": 0, "taxa": 2291, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1480, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of proteins. Some members of the family are annotated as Peptidase E, but the does not appear to be any evidence to support that assertion.", "domain_architectures": 3, "interpro_id": "IPR046525", "known_evidence_count": null, "matches": 2347, "name": "Domain of unknown function (DUF6702)", "partial_evidence_count": null, "pfam_id": "PF20420", "proteins": 2346, "proteomes": 2108, "short_name": "DUF6702", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20420", "structures": 0, "taxa": 2849, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1966, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised fungal proteins. They are probably distantly related to domains members of the PD-(D/E)XK nuclease superfamily.", "domain_architectures": 53, "interpro_id": "IPR061632", "known_evidence_count": null, "matches": 2454, "name": "Domain of unknown function (DUF8563)", "partial_evidence_count": null, "pfam_id": "PF29557", "proteins": 2344, "proteomes": 1044, "short_name": "DUF8563", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29557", "structures": 0, "taxa": 2248, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1521, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The family is often found in association with [pfam:PF02661].", "domain_architectures": 11, "interpro_id": "IPR025230", "known_evidence_count": null, "matches": 2343, "name": "Domain of unknown function (DUF4172)", "partial_evidence_count": null, "pfam_id": "PF13776", "proteins": 2342, "proteomes": 2084, "short_name": "DUF4172", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13776", "structures": 1, "taxa": 3508, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the C-terminal of a group of uncharacterised sequences from Nocardia sp. According to structure predictions, this domain may adopt a winged helix fold with an insertion consisting of a long beta-hairpin and a short beta-strand.", "domain_architectures": 7, "interpro_id": "IPR056684", "known_evidence_count": null, "matches": 2338, "name": "Domain of unknown function (DUF7782)", "partial_evidence_count": null, "pfam_id": "PF25004", "proteins": 2338, "proteomes": 2322, "short_name": "DUF7782", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25004", "structures": 0, "taxa": 2740, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1960, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family is found in eukaryotes, and is approximately 90 amino acids in length.", "domain_architectures": 33, "interpro_id": "IPR027831", "known_evidence_count": null, "matches": 2407, "name": "Domain of unknown function (DUF4485)", "partial_evidence_count": null, "pfam_id": "PF14846", "proteins": 2336, "proteomes": 956, "short_name": "DUF4485", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14846", "structures": 0, "taxa": 3205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1545, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR012454", "known_evidence_count": null, "matches": 2333, "name": "Protein of unknown function (DUF1659)", "partial_evidence_count": null, "pfam_id": "PF07872", "proteins": 2333, "proteomes": 1709, "short_name": "DUF1659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07872", "structures": 0, "taxa": 2607, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1589, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 5, "interpro_id": "IPR018666", "known_evidence_count": null, "matches": 2356, "name": "Uncharacterized protein conserved in bacteria (DUF2125)", "partial_evidence_count": null, "pfam_id": "PF09898", "proteins": 2333, "proteomes": 1880, "short_name": "DUF2125", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09898", "structures": 0, "taxa": 2633, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1687, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A conserved sequence region at the C terminus of several cytochrome-like proteins in Rhodopirellula baltica.", "domain_architectures": 86, "interpro_id": "IPR011478", "known_evidence_count": null, "matches": 2330, "name": "Protein of unknown function (DUF1585)", "partial_evidence_count": null, "pfam_id": "PF07624", "proteins": 2330, "proteomes": 433, "short_name": "PSD2", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07624", "structures": 0, "taxa": 863, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 90 amino acids in length. This domain is found associated with [pfam:PF02826], [pfam:PF00389]. This domain has a conserved RRE sequence motif.", "domain_architectures": 7, "interpro_id": "IPR024531", "known_evidence_count": null, "matches": 2325, "name": "Domain of unknown function (DUF3410)", "partial_evidence_count": null, "pfam_id": "PF11890", "proteins": 2325, "proteomes": 2252, "short_name": "DUF3410", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11890", "structures": 3, "taxa": 3158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1423, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has a conserved HEXXH motif, suggesting they are putative peptidases of zincin fold [[cite:PUB00075429]].", "domain_architectures": 7, "interpro_id": "IPR010321", "known_evidence_count": null, "matches": 2332, "name": "Bacterial protein of unknown function (DUF922)", "partial_evidence_count": null, "pfam_id": "PF06037", "proteins": 2324, "proteomes": 1709, "short_name": "DUF922", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06037", "structures": 0, "taxa": 2478, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1748, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain is found on proteins carrying a PX domain. Its function is unknown.", "domain_architectures": 46, "interpro_id": "IPR024554", "known_evidence_count": null, "matches": 2741, "name": "Domain of unknown function in PX-proteins (DUF3818)", "partial_evidence_count": null, "pfam_id": "PF12825", "proteins": 2324, "proteomes": 1416, "short_name": "DUF3818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12825", "structures": 0, "taxa": 3022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1930, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family found in fungi. The function of this region is unknown. It appears to contain a pair of C-terminal transmembrane helices.", "domain_architectures": 87, "interpro_id": "IPR046536", "known_evidence_count": null, "matches": 2379, "name": "Family of unknown function (DUF6601)", "partial_evidence_count": null, "pfam_id": "PF20246", "proteins": 2321, "proteomes": 747, "short_name": "DUF6601", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20246", "structures": 0, "taxa": 1521, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several eukaryotic proteins of unknown function.", "domain_architectures": 12, "interpro_id": "IPR009432", "known_evidence_count": null, "matches": 2332, "name": "Protein of unknown function (DUF1075)", "partial_evidence_count": null, "pfam_id": "PF06388", "proteins": 2320, "proteomes": 1124, "short_name": "DUF1075", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06388", "structures": 0, "taxa": 3691, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1302, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is often found at the C-terminus of proteins containing [pfam:PF03435].", "domain_architectures": 21, "interpro_id": "IPR025311", "known_evidence_count": null, "matches": 2331, "name": "Domain of unknown function (DUF4166)", "partial_evidence_count": null, "pfam_id": "PF13761", "proteins": 2320, "proteomes": 2087, "short_name": "DUF4166", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13761", "structures": 0, "taxa": 3085, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1907, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 50 amino acids in length. This domain is found associated with [pfam:PF00023].", "domain_architectures": 57, "interpro_id": "IPR024228", "known_evidence_count": null, "matches": 2319, "name": "Domain of unknown function (DUF3420)", "partial_evidence_count": null, "pfam_id": "PF11900", "proteins": 2317, "proteomes": 364, "short_name": "DUF3420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11900", "structures": 4, "taxa": 1057, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1424, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018680", "known_evidence_count": null, "matches": 2316, "name": "Uncharacterized conserved protein (DUF2164)", "partial_evidence_count": null, "pfam_id": "PF09932", "proteins": 2316, "proteomes": 2279, "short_name": "DUF2164", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09932", "structures": 0, "taxa": 3192, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1590, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 55 residues found in Bacillota and Thermodesulfobacteriota. This domain is located N-terminal to the MoCF_biosynth domain ([pfam:PF00994]), which is involved in molybdenum cofactor biosynthesis. The function of this domain remains to be determined.", "domain_architectures": 11, "interpro_id": "IPR061867", "known_evidence_count": null, "matches": 2312, "name": "Domain of unknown function (DUF8806)", "partial_evidence_count": null, "pfam_id": "PF31083", "proteins": 2312, "proteomes": 2071, "short_name": "DUF8806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31083", "structures": 0, "taxa": 3430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 506, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in Focadhesin from animals and RST1 (RESURRECTION 1) from plants. Focadhesin (FOCAD) is a focal adhesion protein with potential tumour suppressor function in gliomas [[cite:PUB00075175]]. RST1 was originally identified in a genetic screen for factors involved in the biosynthesis of epicuticular waxes [[cite:PUB00098180]]. Later, RST1 and RST1 INTERACTING PROTEIN (RIPR) have been shown to act as cofactors of the cytoplasmic exosome and the Ski complex in plants [[cite:PUB00098179]]. It is involved in the suppression of siRNA-mediated silencing of transgenes and certain endogenous transcripts [[cite:PUB00098181]]. Structure predictions suggest that this is an alpha-helical domain with and armadillo-like fold.", "domain_architectures": 38, "interpro_id": "IPR022542", "known_evidence_count": null, "matches": 2822, "name": "Focadhesin/RST1, DUF3730", "partial_evidence_count": null, "pfam_id": "PF12530", "proteins": 2311, "proteomes": 1335, "short_name": "DUF3730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12530", "structures": 0, "taxa": 4349, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1465, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised bacterial proteins.", "domain_architectures": 7, "interpro_id": "IPR064877", "known_evidence_count": null, "matches": 2312, "name": "Protein of unknown function (DUF975)", "partial_evidence_count": null, "pfam_id": "PF06161", "proteins": 2310, "proteomes": 1680, "short_name": "DUF975", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06161", "structures": 0, "taxa": 2667, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1287, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 235 residues in length. Members of this family seem to be found exclusively in the Enterobacteria Salmonella typhimurium and Escherichia coli. The function of this family is unknown.", "domain_architectures": 23, "interpro_id": "IPR009677", "known_evidence_count": null, "matches": 2471, "name": "Protein of unknown function (DUF1266)", "partial_evidence_count": null, "pfam_id": "PF06889", "proteins": 2309, "proteomes": 1819, "short_name": "DUF1266", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06889", "structures": 0, "taxa": 2682, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1332, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain found in DUF1631 family proteins. This domain structurally resembles a tudor domain. The members of this family are sequences derived from a group of hypothetical proteins expressed by certain bacterial species.", "domain_architectures": 21, "interpro_id": "IPR060056", "known_evidence_count": null, "matches": 2332, "name": "Protein of unknown function (DUF1631) C-terminal tudor domain", "partial_evidence_count": null, "pfam_id": "PF26670", "proteins": 2309, "proteomes": 1381, "short_name": "DUF1631_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26670", "structures": 0, "taxa": 1826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1551, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 3, "interpro_id": "IPR025226", "known_evidence_count": null, "matches": 2358, "name": "Domain of unknown function (DUF4170)", "partial_evidence_count": null, "pfam_id": "PF13773", "proteins": 2304, "proteomes": 2131, "short_name": "DUF4170", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13773", "structures": 1, "taxa": 2888, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1849, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It has detectable similarity to methyltransferases and it is predicted to adopt similar structure. It contains two highly conserved cysteines and a histidine.", "domain_architectures": 50, "interpro_id": "IPR057192", "known_evidence_count": null, "matches": 3215, "name": "Domain of unknown function (DUF7870)", "partial_evidence_count": null, "pfam_id": "PF25276", "proteins": 2300, "proteomes": 378, "short_name": "DUF7870", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25276", "structures": 0, "taxa": 1082, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1844, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family are hypothetical plant proteins of unknown function. The region featured in this family is approximately 100 amino acids long.", "domain_architectures": 55, "interpro_id": "IPR012458", "known_evidence_count": null, "matches": 2306, "name": "Protein of unknown function (DUF1664)", "partial_evidence_count": null, "pfam_id": "PF07889", "proteins": 2287, "proteomes": 438, "short_name": "DUF1664", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07889", "structures": 0, "taxa": 1252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000354) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This includes a protein from the friulimicin A biosynthetic gene cluster from Actinoplanes friuliensis [[cite:PUB00099393]].", "domain_architectures": 10, "interpro_id": "IPR046037", "known_evidence_count": null, "matches": 2297, "name": "Family of unknown function (DUF5995)", "partial_evidence_count": null, "pfam_id": "PF19458", "proteins": 2287, "proteomes": 2049, "short_name": "DUF5995", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19458", "structures": 0, "taxa": 2734, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1432, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as yigF however currently no function is known.", "domain_architectures": 33, "interpro_id": "IPR024399", "known_evidence_count": null, "matches": 2283, "name": "Protein of unknown function (DUF2628)", "partial_evidence_count": null, "pfam_id": "PF10947", "proteins": 2283, "proteomes": 2088, "short_name": "DUF2628", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10947", "structures": 0, "taxa": 3270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1427, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 122 and 304 amino acids in length.", "domain_architectures": 25, "interpro_id": "IPR043714", "known_evidence_count": null, "matches": 2281, "name": "Domain of unknown function (DUF5655)", "partial_evidence_count": null, "pfam_id": "PF18899", "proteins": 2281, "proteomes": 2030, "short_name": "DUF5655", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18899", "structures": 0, "taxa": 3662, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1944, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain with a ubiquitin like fold that is often associated with [pfam:PF04601]. The function of this domain is not known.", "domain_architectures": 54, "interpro_id": "IPR054726", "known_evidence_count": null, "matches": 2311, "name": "DUF569 associated ubiquitin-like domain", "partial_evidence_count": null, "pfam_id": "PF22932", "proteins": 2277, "proteomes": 376, "short_name": "Ubiq_DUF_assoc", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22932", "structures": 0, "taxa": 1030, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1518, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function, which lies to the N-terminus of the protein. This domain family is found in eukaryotes, and is typically between 114 and 130 amino acids in length. There are two completely conserved residues (L and A) that may be functionally important. In humans, the gene that encodes this protein lies in the position, chromosome 2 open reading frame 55.", "domain_architectures": 24, "interpro_id": "IPR028030", "known_evidence_count": null, "matches": 2295, "name": "Domain of unknown function (DUF4592)", "partial_evidence_count": null, "pfam_id": "PF15262", "proteins": 2269, "proteomes": 532, "short_name": "DUF4592", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15262", "structures": 0, "taxa": 1903, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1224, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an integral membrane domain composed of four predicted transmembrane helices. The function of this region is unknown.", "domain_architectures": 1, "interpro_id": "IPR046672", "known_evidence_count": null, "matches": 2266, "name": "Domain of unknown function (DUF6542)", "partial_evidence_count": null, "pfam_id": "PF20177", "proteins": 2266, "proteomes": 2120, "short_name": "DUF6542", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20177", "structures": 0, "taxa": 2438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 13, "interpro_id": "IPR014973", "known_evidence_count": null, "matches": 2266, "name": "Domain of unknown function (DUF1835)", "partial_evidence_count": null, "pfam_id": "PF08874", "proteins": 2265, "proteomes": 2028, "short_name": "DUF1835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08874", "structures": 0, "taxa": 3040, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of TIM barrel proteins that are most closely related to [pfam:PF03328]. This strongly suggests that these proteins are enzyme with a possibly related function.", "domain_architectures": 7, "interpro_id": "IPR054255", "known_evidence_count": null, "matches": 2274, "name": "Domain of unknown function (DUF6986)", "partial_evidence_count": null, "pfam_id": "PF22484", "proteins": 2264, "proteomes": 2229, "short_name": "DUF6986", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22484", "structures": 0, "taxa": 2704, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1504, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 100 and 112 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR025563", "known_evidence_count": null, "matches": 2263, "name": "Domain of unknown function (DUF4286)", "partial_evidence_count": null, "pfam_id": "PF14114", "proteins": 2263, "proteomes": 2239, "short_name": "DUF4286", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14114", "structures": 0, "taxa": 3235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1543, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in bacteria. Proteins in this family are typically between 197 and 228 amino acids in length. This family appears to be distantly related to [pfam:PF13338] suggesting proteins in this family may be an antitoxin component of a toxin/antitoxin system.", "domain_architectures": 5, "interpro_id": "IPR045738", "known_evidence_count": null, "matches": 2262, "name": "Family of unknown function (DUF6088)", "partial_evidence_count": null, "pfam_id": "PF19570", "proteins": 2262, "proteomes": 1855, "short_name": "DUF6088", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19570", "structures": 0, "taxa": 3422, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1457, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 100 residues in length and is often known as YdbL. The function of this family is unknown.", "domain_architectures": 9, "interpro_id": "IPR008309", "known_evidence_count": null, "matches": 2258, "name": "Protein of unknown function (DUF1318)", "partial_evidence_count": null, "pfam_id": "PF07027", "proteins": 2258, "proteomes": 2228, "short_name": "DUF1318", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07027", "structures": 1, "taxa": 3311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1988, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is the conserved N-terminal 350 residues of a family of proteins of unknown function possibly containing a coiled-coil domain.", "domain_architectures": 34, "interpro_id": "IPR019152", "known_evidence_count": null, "matches": 2348, "name": "Uncharacterized conserved protein H4 (DUF2046)", "partial_evidence_count": null, "pfam_id": "PF09755", "proteins": 2257, "proteomes": 1648, "short_name": "DUF2046", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09755", "structures": 2, "taxa": 5194, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1440, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family of hypothetical prokaryotic proteins have no known function. It is thought that they are transmembrane proteins, but their function has not been inferred yet.", "domain_architectures": 2, "interpro_id": "IPR018678", "known_evidence_count": null, "matches": 2256, "name": "Predicted small integral membrane protein (DUF2160)", "partial_evidence_count": null, "pfam_id": "PF09928", "proteins": 2256, "proteomes": 2112, "short_name": "DUF2160", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09928", "structures": 0, "taxa": 2889, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1916, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry (ex DUF3759) represents virulence factors and related proteins in fungi including Concanamycin-induced protein C. Virulence factor cipC is involved in host Brassica napus (canola) leaf infection [[cite:PUB00163274]].", "domain_architectures": 33, "interpro_id": "IPR022234", "known_evidence_count": null, "matches": 2272, "name": "Virulence factor CipC-like", "partial_evidence_count": null, "pfam_id": "PF12585", "proteins": 2255, "proteomes": 1236, "short_name": "DUF3759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12585", "structures": 0, "taxa": 2613, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1483, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 4, "interpro_id": "IPR012683", "known_evidence_count": null, "matches": 2351, "name": "Domain of unknown function (DUF4175)", "partial_evidence_count": null, "pfam_id": "PF13779", "proteins": 2254, "proteomes": 2187, "short_name": "DUF4175", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13779", "structures": 0, "taxa": 3177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 155 and 179 amino acids in length. There is a single completely conserved residue C that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR022061", "known_evidence_count": null, "matches": 2253, "name": "Protein of unknown function (DUF3617)", "partial_evidence_count": null, "pfam_id": "PF12276", "proteins": 2253, "proteomes": 1802, "short_name": "DUF3617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12276", "structures": 0, "taxa": 2528, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 151 and 387 amino acids in length.", "domain_architectures": 24, "interpro_id": "IPR025364", "known_evidence_count": null, "matches": 2258, "name": "Domain of unknown function (DUF4268)", "partial_evidence_count": null, "pfam_id": "PF14088", "proteins": 2251, "proteomes": 2142, "short_name": "DUF4268", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14088", "structures": 0, "taxa": 3515, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1924, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of a number of conserved eukaryotic proteins of unknown function. The sequences carry three sets of CxxxC motifs, which might suggest a type of zinc-finger formation.", "domain_architectures": 31, "interpro_id": "IPR008560", "known_evidence_count": null, "matches": 2282, "name": "Eukaryotic protein of unknown function (DUF842)", "partial_evidence_count": null, "pfam_id": "PF05811", "proteins": 2249, "proteomes": 1539, "short_name": "DUF842", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05811", "structures": 0, "taxa": 4899, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1524, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR019225", "known_evidence_count": null, "matches": 2258, "name": "Uncharacterized protein conserved in bacteria (DUF2155)", "partial_evidence_count": null, "pfam_id": "PF09923", "proteins": 2245, "proteomes": 2243, "short_name": "DUF2155", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09923", "structures": 0, "taxa": 3207, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1324, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR018719", "known_evidence_count": null, "matches": 2243, "name": "Predicted membrane protein (DUF2243)", "partial_evidence_count": null, "pfam_id": "PF10002", "proteins": 2243, "proteomes": 2148, "short_name": "DUF2243", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10002", "structures": 0, "taxa": 3192, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1385, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 9, "interpro_id": "IPR021365", "known_evidence_count": null, "matches": 2270, "name": "Protein of unknown function (DUF2891)", "partial_evidence_count": null, "pfam_id": "PF11199", "proteins": 2243, "proteomes": 2202, "short_name": "DUF2891", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11199", "structures": 2, "taxa": 3237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1645, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several conserved glycines and phenylalanines.", "domain_architectures": 6, "interpro_id": "IPR011435", "known_evidence_count": null, "matches": 3044, "name": "Protein of unknown function (DUF1538)", "partial_evidence_count": null, "pfam_id": "PF07556", "proteins": 2236, "proteomes": 1455, "short_name": "DUF1538", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07556", "structures": 0, "taxa": 2665, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is expressed in Proteobacteria and Actinobacteria. The function is not known.", "domain_architectures": 2, "interpro_id": "IPR021724", "known_evidence_count": null, "matches": 2236, "name": "Protein of unknown function (DUF3297)", "partial_evidence_count": null, "pfam_id": "PF11730", "proteins": 2236, "proteomes": 2222, "short_name": "DUF3297", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11730", "structures": 0, "taxa": 2824, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1357, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several small bacterial proteins including the uncharacterized lipoproteins YgdI and YgdR. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR047807", "known_evidence_count": null, "matches": 2228, "name": "Domain of unknown function (DUF903)", "partial_evidence_count": null, "pfam_id": "PF06004", "proteins": 2228, "proteomes": 1020, "short_name": "DUF903", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06004", "structures": 8, "taxa": 1336, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1502, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 90 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009935", "known_evidence_count": null, "matches": 2228, "name": "Protein of unknown function (DUF1467)", "partial_evidence_count": null, "pfam_id": "PF07330", "proteins": 2228, "proteomes": 2227, "short_name": "DUF1467", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07330", "structures": 0, "taxa": 2990, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1318, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several putative bacterial membrane proteins. The function of this family is unclear.", "domain_architectures": 4, "interpro_id": "IPR009323", "known_evidence_count": null, "matches": 2242, "name": "Protein of unknown function (DUF979)", "partial_evidence_count": null, "pfam_id": "PF06166", "proteins": 2225, "proteomes": 2161, "short_name": "DUF979", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06166", "structures": 0, "taxa": 3099, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1330, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised bacterial membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR010374", "known_evidence_count": null, "matches": 2218, "name": "Protein of unknown function (DUF969)", "partial_evidence_count": null, "pfam_id": "PF06149", "proteins": 2217, "proteomes": 2159, "short_name": "DUF969", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06149", "structures": 0, "taxa": 3095, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of hypothetical proteins identified in Rhodopirellula baltica.", "domain_architectures": 9, "interpro_id": "IPR011463", "known_evidence_count": null, "matches": 2215, "name": "Protein of unknown function (DUF1569)", "partial_evidence_count": null, "pfam_id": "PF07606", "proteins": 2214, "proteomes": 1625, "short_name": "DUF1569", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07606", "structures": 0, "taxa": 2322, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1479, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_4780, a putative uncharacterized protein. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011],[cite:PUB00056012]]. This entry represents the C-terminal domain which may have a Ig-like fold.", "domain_architectures": 5, "interpro_id": "IPR022298", "known_evidence_count": null, "matches": 2214, "name": "Domain of unknown function (DUF4138)", "partial_evidence_count": null, "pfam_id": "PF13595", "proteins": 2214, "proteomes": 1098, "short_name": "DUF4138", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13595", "structures": 0, "taxa": 1464, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1309, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 104 and 223 amino acids in length. There is a single completely conserved residue R that may be functionally important.", "domain_architectures": 8, "interpro_id": "IPR025498", "known_evidence_count": null, "matches": 3332, "name": "Domain of unknown function (DUF4389)", "partial_evidence_count": null, "pfam_id": "PF14333", "proteins": 2214, "proteomes": 2048, "short_name": "DUF4389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14333", "structures": 0, "taxa": 2904, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1097, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 7, "interpro_id": "IPR046041", "known_evidence_count": null, "matches": 2213, "name": "Family of unknown function (DUF5999)", "partial_evidence_count": null, "pfam_id": "PF19462", "proteins": 2213, "proteomes": 1381, "short_name": "DUF5999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19462", "structures": 0, "taxa": 1563, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1929, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "The structure of this domain displays an alpha-beta-beta-alpha four layer topology, with an HxHxxxxxxxxxH motif that coordinates a zinc ion, and an acetate anion at a site that likely supports the enzymatic activity of an ester hydrolase [[cite:PUB00035389]].", "domain_architectures": 46, "interpro_id": "IPR015021", "known_evidence_count": null, "matches": 2361, "name": "Domain of Unknown Function (DUF1907)", "partial_evidence_count": null, "pfam_id": "PF08925", "proteins": 2209, "proteomes": 1513, "short_name": "DUF1907", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08925", "structures": 1, "taxa": 4543, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1674, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is ubiquitously found in uncharacterised bacterial and eukaryotic proteins. It contains several highly conserved cysteine residues some of which may be involved in metal coordination.", "domain_architectures": 35, "interpro_id": "IPR061791", "known_evidence_count": null, "matches": 2217, "name": "Domain of unknown function (DUF8730)", "partial_evidence_count": null, "pfam_id": "PF30774", "proteins": 2209, "proteomes": 1729, "short_name": "DUF8730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30774", "structures": 0, "taxa": 3698, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1496, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Predicted to be an integral membrane protein.", "domain_architectures": 3, "interpro_id": "IPR007382", "known_evidence_count": null, "matches": 2207, "name": "Protein of unknown function (DUF441)", "partial_evidence_count": null, "pfam_id": "PF04284", "proteins": 2207, "proteomes": 1960, "short_name": "DUF441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04284", "structures": 0, "taxa": 2964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1454, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 27, "interpro_id": "IPR021251", "known_evidence_count": null, "matches": 2212, "name": "Protein of unknown function (DUF2793)", "partial_evidence_count": null, "pfam_id": "PF10983", "proteins": 2207, "proteomes": 1785, "short_name": "DUF2793", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10983", "structures": 1, "taxa": 2704, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1361, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It shares significant similarity with the Thermococcus gammatolerans McrB N-terminal domain and related YTH domain-like domains. It adopts a typical PUA-like fold.", "domain_architectures": 77, "interpro_id": "IPR059470", "known_evidence_count": null, "matches": 2209, "name": "Domain of unknown function (DUF8426)", "partial_evidence_count": null, "pfam_id": "PF28530", "proteins": 2205, "proteomes": 2043, "short_name": "DUF8426", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28530", "structures": 0, "taxa": 3918, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1506, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family is functionally uncharacterised. This family family is found in bacteria and archaea, and is approximately 60 amino acids in length and contains two probable transmembrane helices. This entry is found in association with [pfam:PF10035]. The C-terminal transmembrane helix contains a GXXXGXXXG motif that is characteristic of transmembrane helices that dimerise.", "domain_architectures": 2, "interpro_id": "IPR044035", "known_evidence_count": null, "matches": 2198, "name": "Domain of unknown function (DUF5698)", "partial_evidence_count": null, "pfam_id": "PF18955", "proteins": 2198, "proteomes": 1934, "short_name": "DUF5698", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18955", "structures": 0, "taxa": 3195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1365, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 129 and 456 amino acids in length. There is a single completely conserved residue C that may be functionally important.", "domain_architectures": 71, "interpro_id": "IPR025460", "known_evidence_count": null, "matches": 2198, "name": "Domain of unknown function (DUF4280)", "partial_evidence_count": null, "pfam_id": "PF14107", "proteins": 2197, "proteomes": 1201, "short_name": "DUF4280", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14107", "structures": 2, "taxa": 1922, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function contains several highly conserved histidines.", "domain_architectures": 8, "interpro_id": "IPR025238", "known_evidence_count": null, "matches": 2199, "name": "Domain of unknown function (DUF4184)", "partial_evidence_count": null, "pfam_id": "PF13803", "proteins": 2194, "proteomes": 2002, "short_name": "DUF4184", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13803", "structures": 0, "taxa": 2675, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1580, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Bacterial domain of unknown function.", "domain_architectures": 8, "interpro_id": "IPR007172", "known_evidence_count": null, "matches": 2193, "name": "Domain of unknown function (DUF374)", "partial_evidence_count": null, "pfam_id": "PF04028", "proteins": 2192, "proteomes": 2036, "short_name": "DUF374", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04028", "structures": 0, "taxa": 3557, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1699, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It shares similarity with the HHM N-terminal domain.", "domain_architectures": 36, "interpro_id": "IPR061784", "known_evidence_count": null, "matches": 2267, "name": "Domain of unknown function (DUF8723)", "partial_evidence_count": null, "pfam_id": "PF30750", "proteins": 2192, "proteomes": 11, "short_name": "DUF8723", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30750", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1627, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Metazoa lineage. It is predicted to fold into an alpha-helical bundle.", "domain_architectures": 208, "interpro_id": "IPR061765", "known_evidence_count": null, "matches": 2200, "name": "Domain of unknown function (DUF8704)", "partial_evidence_count": null, "pfam_id": "PF30722", "proteins": 2191, "proteomes": 110, "short_name": "DUF8704", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30722", "structures": 0, "taxa": 628, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1366, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 90 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009749", "known_evidence_count": null, "matches": 2189, "name": "Protein of unknown function (DUF1315)", "partial_evidence_count": null, "pfam_id": "PF07023", "proteins": 2189, "proteomes": 2181, "short_name": "DUF1315", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07023", "structures": 0, "taxa": 2818, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1284, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family is found in range of different bacterial species. In many proteins it lies N-terminal to a TPR-repeat region at the C-terminus.", "domain_architectures": 239, "interpro_id": "IPR033396", "known_evidence_count": null, "matches": 2200, "name": "Domain of unknown function (DUF5107)", "partial_evidence_count": null, "pfam_id": "PF17128", "proteins": 2188, "proteomes": 1921, "short_name": "DUF5107", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17128", "structures": 1, "taxa": 2863, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1427, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021272", "known_evidence_count": null, "matches": 2190, "name": "Protein of unknown function (DUF2851)", "partial_evidence_count": null, "pfam_id": "PF11013", "proteins": 2178, "proteomes": 2159, "short_name": "DUF2851", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11013", "structures": 0, "taxa": 3068, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1293, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes protein CcdC from Bacillus subtilis. The function of Ccdc is not known.", "domain_architectures": 1, "interpro_id": "IPR058247", "known_evidence_count": null, "matches": 2174, "name": "CcdC protein", "partial_evidence_count": null, "pfam_id": "PF07301", "proteins": 2174, "proteomes": 1736, "short_name": "DUF1453", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07301", "structures": 0, "taxa": 2312, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1763, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical plant proteins from Arabidopsis thaliana and Oryza sativa. The function of this family is unknown.", "domain_architectures": 54, "interpro_id": "IPR010471", "known_evidence_count": null, "matches": 2227, "name": "Protein of unknown function (DUF1068)", "partial_evidence_count": null, "pfam_id": "PF06364", "proteins": 2173, "proteomes": 376, "short_name": "DUF1068", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06364", "structures": 0, "taxa": 1044, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1423, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is frequently found N-terminal to domains members of the Endonuclease/Exonuclease/phosphatase family [pfam:PF03372]. It is predicted to fold into a three-helical bundle.", "domain_architectures": 3, "interpro_id": "IPR059475", "known_evidence_count": null, "matches": 2171, "name": "Domain of unknown function (DUF8431)", "partial_evidence_count": null, "pfam_id": "PF28535", "proteins": 2171, "proteomes": 1912, "short_name": "DUF8431", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28535", "structures": 0, "taxa": 2503, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1495, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacteria, and is typically between 183 and 196 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR025641", "known_evidence_count": null, "matches": 2575, "name": "Domain of unknown function (DUF4340)", "partial_evidence_count": null, "pfam_id": "PF14238", "proteins": 2170, "proteomes": 1897, "short_name": "DUF4340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14238", "structures": 0, "taxa": 3752, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in actinobacteria, and is approximately 170 amino acids in length. This domain is found at the N-terminus of 2 component signalling proteins which also contain [pfam:PF07730], and [pfam:PF02518]. This domain presumably binds an as yet unknown ligand.", "domain_architectures": 6, "interpro_id": "IPR045975", "known_evidence_count": null, "matches": 2168, "name": "Family of unknown function (DUF5931)", "partial_evidence_count": null, "pfam_id": "PF19354", "proteins": 2168, "proteomes": 2155, "short_name": "DUF5931", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19354", "structures": 0, "taxa": 2483, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1347, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Members of this family are small proteins, about 70 residues in length, with a basic triplet near the N-terminus and a probable metal-binding motif CPXCX(18)CXXC. Members are found in various proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR012658", "known_evidence_count": null, "matches": 2163, "name": "Probable metal-binding protein (DUF2387)", "partial_evidence_count": null, "pfam_id": "PF09526", "proteins": 2163, "proteomes": 2157, "short_name": "DUF2387", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09526", "structures": 0, "taxa": 2748, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1298, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family is suggested to be the catalytic domain of tRNA pseudouridine synthase C by association. The structure has been solved for one member, as PDB:2HGK, which by inference is designated in this way.", "domain_architectures": 3, "interpro_id": "IPR023376", "known_evidence_count": null, "matches": 2160, "name": "tRNA pseudouridine synthase C", "partial_evidence_count": null, "pfam_id": "PF04287", "proteins": 2160, "proteomes": 2155, "short_name": "DUF446", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04287", "structures": 1, "taxa": 2839, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1343, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 70 amino acids in length. The family is found in association with [pfam:PF00239] and [pfam:PF07508]. There is a single completely conserved residue G that may be functionally important.", "domain_architectures": 21, "interpro_id": "IPR025378", "known_evidence_count": null, "matches": 2159, "name": "Domain of unknown function (DUF4368)", "partial_evidence_count": null, "pfam_id": "PF14287", "proteins": 2159, "proteomes": 628, "short_name": "DUF4368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14287", "structures": 0, "taxa": 1153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1540, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of proteins in Rhodopirellula baltica, associated with [pfam:PF07635], [pfam:PF07626], [pfam:PF07631], [pfam:PF07627], and [pfam:PF07624].", "domain_architectures": 102, "interpro_id": "IPR013043", "known_evidence_count": null, "matches": 2158, "name": "Protein of unknown function (DUF1595)", "partial_evidence_count": null, "pfam_id": "PF07637", "proteins": 2158, "proteomes": 456, "short_name": "PSD5", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07637", "structures": 0, "taxa": 898, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This a bacterial family of proteins which are annotated as putative lipoproteins.", "domain_architectures": 3, "interpro_id": "IPR021747", "known_evidence_count": null, "matches": 2155, "name": "Protein of unknown function (DUF3313)", "partial_evidence_count": null, "pfam_id": "PF11769", "proteins": 2155, "proteomes": 1661, "short_name": "DUF3313", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11769", "structures": 0, "taxa": 2420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1420, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 243 and 287 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR025634", "known_evidence_count": null, "matches": 2162, "name": "Domain of unknown function (DUF4292)", "partial_evidence_count": null, "pfam_id": "PF14125", "proteins": 2155, "proteomes": 2141, "short_name": "DUF4292", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14125", "structures": 1, "taxa": 2933, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1802, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins. Some of these contain an N-terminal F-box domain [pfam:PF00646].", "domain_architectures": 60, "interpro_id": "IPR046676", "known_evidence_count": null, "matches": 2182, "name": "Family of unknown function (DUF6546)", "partial_evidence_count": null, "pfam_id": "PF20183", "proteins": 2155, "proteomes": 490, "short_name": "DUF6546", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20183", "structures": 0, "taxa": 946, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1398, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein family appears to be primarily involved in transcriptional regulation and cellular processes. Members of this family, such as the one represented by [swissprot:Q8E4L3] (gene gbs1388), exhibit high levels of transcriptional activity and may be regulated by factors like the rex gene, indicating a role in significant cellular processes [[cite:PUB00156067]]. Another member, [swissprot:A6M310], gene name cbei_4884), is implicated in strain degeneration and regulatory functions linked to sporulation and solvent formation in Clostridium beijerinckii, suggesting conservation among clostridial species [[cite:PUB00156068]]. The sgo_1308 gene encodes a protein [swissprot:A8AXS9] containing the DUF1836 domain which belongs to the helix-turn-helix (HTH) clan, hinting at its role in transcriptional regulation, specifically influencing bacterial hemolysin III [[cite:PUB00156066]].", "domain_architectures": 3, "interpro_id": "IPR014975", "known_evidence_count": null, "matches": 2156, "name": "Domain of unknown function (DUF1836)", "partial_evidence_count": null, "pfam_id": "PF08876", "proteins": 2153, "proteomes": 1785, "short_name": "DUF1836", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08876", "structures": 0, "taxa": 2610, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1730, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to adopt a globular structure that has some similarity to SRA domain ([pfam:PF18491]). The function of this domain is unknown.", "domain_architectures": 66, "interpro_id": "IPR054293", "known_evidence_count": null, "matches": 2153, "name": "Domain of unknown function (DUF7029)", "partial_evidence_count": null, "pfam_id": "PF22974", "proteins": 2153, "proteomes": 787, "short_name": "DUF7029", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22974", "structures": 0, "taxa": 1596, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1228, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, as well as predicted zinc dependent proteases, has no known function.", "domain_architectures": 7, "interpro_id": "IPR018728", "known_evidence_count": null, "matches": 2152, "name": "Predicted Zn-dependent protease (DUF2268)", "partial_evidence_count": null, "pfam_id": "PF10026", "proteins": 2149, "proteomes": 1790, "short_name": "DUF2268", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10026", "structures": 0, "taxa": 2748, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR021252", "known_evidence_count": null, "matches": 2149, "name": "Protein of unknown function (DUF2794)", "partial_evidence_count": null, "pfam_id": "PF10984", "proteins": 2149, "proteomes": 2144, "short_name": "DUF2794", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10984", "structures": 0, "taxa": 2867, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1382, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is only found in bacteria. Proteins in this family are typically between 187 to 236 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR021958", "known_evidence_count": null, "matches": 2147, "name": "Protein of unknown function (DUF3575)", "partial_evidence_count": null, "pfam_id": "PF12099", "proteins": 2147, "proteomes": 1100, "short_name": "DUF3575", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12099", "structures": 0, "taxa": 1513, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain with unknown function. This domain has been described as structurally similar to Pfam: PF07143 (PDB:2ich, residues:24 to 220) [[cite:PUB00152793],[cite:PUB00055863]].", "domain_architectures": 7, "interpro_id": "IPR021243", "known_evidence_count": null, "matches": 2171, "name": "Domain of unknown function (DUF2804)", "partial_evidence_count": null, "pfam_id": "PF10974", "proteins": 2145, "proteomes": 1888, "short_name": "DUF2804", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10974", "structures": 0, "taxa": 2935, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1389, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 23, "interpro_id": "IPR021660", "known_evidence_count": null, "matches": 2146, "name": "Protein of unknown function (DUF3253)", "partial_evidence_count": null, "pfam_id": "PF11625", "proteins": 2145, "proteomes": 2055, "short_name": "DUF3253", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11625", "structures": 1, "taxa": 3404, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins from Bacteroidetes, is found with a PKD domain at the N-terminus. Several members are annotated as putative quinonprotein alcohol dehydrogenase-like proteins but this could not be confirmed. This entry represents a beta propeller like domain.", "domain_architectures": 40, "interpro_id": "IPR031815", "known_evidence_count": null, "matches": 2145, "name": "Domain of unknown function (DUF5074)", "partial_evidence_count": null, "pfam_id": "PF16819", "proteins": 2145, "proteomes": 1504, "short_name": "DUF5074", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16819", "structures": 17, "taxa": 2299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry consists of several bacterial proteins of unknown function. Some of the family members are described as inner membrane proteins. These proteins have a beta/alpha/alpha/beta/alpha hairpin structure that is repeated.", "domain_architectures": 14, "interpro_id": "IPR010295", "known_evidence_count": null, "matches": 2295, "name": "Bacterial protein of unknown function (DUF898)", "partial_evidence_count": null, "pfam_id": "PF05987", "proteins": 2143, "proteomes": 2073, "short_name": "DUF898", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05987", "structures": 0, "taxa": 3332, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 155 residues in length. Family members are present in Rhizobium, Agrobacterium and Streptomyces species.", "domain_architectures": 7, "interpro_id": "IPR009593", "known_evidence_count": null, "matches": 2140, "name": "Protein of unknown function (DUF1203)", "partial_evidence_count": null, "pfam_id": "PF06718", "proteins": 2138, "proteomes": 2106, "short_name": "DUF1203", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06718", "structures": 0, "taxa": 2956, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1455, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has been suggested to be an electron source for sulfite reductase. This family is usually found upstream of cysI, the beta subunit of this enzyme. This family was also found fused to cysI in Pseudomonas putida GB-1 (See Supplementary note 5 in [[cite:PUB00093610]]).", "domain_architectures": 4, "interpro_id": "IPR021270", "known_evidence_count": null, "matches": 2137, "name": "Protein of unknown function (DUF2849)", "partial_evidence_count": null, "pfam_id": "PF11011", "proteins": 2136, "proteomes": 2120, "short_name": "DUF2849", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11011", "structures": 0, "taxa": 2894, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1400, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]].", "domain_architectures": 7, "interpro_id": "IPR025288", "known_evidence_count": null, "matches": 2144, "name": "Protein of unknown function (DUF4080)", "partial_evidence_count": null, "pfam_id": "PF13311", "proteins": 2136, "proteomes": 2116, "short_name": "DUF4080", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13311", "structures": 0, "taxa": 3308, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of a group of uncharacterised bacterial proteins that also contain [pfam:PF09423]. This domain is predicted to show an immunoglobulin-like fold.", "domain_architectures": 12, "interpro_id": "IPR056702", "known_evidence_count": null, "matches": 2142, "name": "Domain of unknown function (DUF7800)", "partial_evidence_count": null, "pfam_id": "PF25077", "proteins": 2132, "proteomes": 2079, "short_name": "DUF7800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25077", "structures": 0, "taxa": 2761, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1380, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "An alpha helical domain with conserved polar residues suggestive of enzymatic function. The domain is associated with the 5-hydroxymethyl uridine synthase and is predicted to play a role in modified base biosynthesis pathways [[cite:PUB00091053]].", "domain_architectures": 5, "interpro_id": "IPR011630", "known_evidence_count": null, "matches": 4125, "name": "Nucleotide modification associated domain 1", "partial_evidence_count": null, "pfam_id": "PF07659", "proteins": 2127, "proteomes": 2105, "short_name": "DUF1599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07659", "structures": 0, "taxa": 2955, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1734, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function but appears to be part of the START superfamily.", "domain_architectures": 24, "interpro_id": "IPR024500", "known_evidence_count": null, "matches": 2134, "name": "Protein of unknown function (DUF3074)", "partial_evidence_count": null, "pfam_id": "PF11274", "proteins": 2126, "proteomes": 1284, "short_name": "DUF3074", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11274", "structures": 0, "taxa": 2656, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1516, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 187 and 205 amino acids in length. There are two conserved sequence motifs: LED and KMS. The function of these proteins is unknown, although many are incorrectly annotated as glutamyl tRNA synthetases.", "domain_architectures": 17, "interpro_id": "IPR025255", "known_evidence_count": null, "matches": 2128, "name": "Domain of unknown function (DUF4202)", "partial_evidence_count": null, "pfam_id": "PF13875", "proteins": 2122, "proteomes": 2080, "short_name": "DUF4202", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13875", "structures": 0, "taxa": 3479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1365, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Family of bacterial proteins with undetermined function.", "domain_architectures": 2, "interpro_id": "IPR006340", "known_evidence_count": null, "matches": 2118, "name": "Protein of unknown function (DUF436)", "partial_evidence_count": null, "pfam_id": "PF04260", "proteins": 2118, "proteomes": 2058, "short_name": "DUF436", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04260", "structures": 2, "taxa": 2940, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1835, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is only found in fly proteins. It is found associated with YLP motifs [pfam:PF02757] in some proteins.", "domain_architectures": 17, "interpro_id": "IPR004145", "known_evidence_count": null, "matches": 2167, "name": "Domain of unknown function (DUF243)", "partial_evidence_count": null, "pfam_id": "PF03103", "proteins": 2116, "proteomes": 249, "short_name": "DUF243", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03103", "structures": 0, "taxa": 942, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1390, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 136 and 154 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025635", "known_evidence_count": null, "matches": 2110, "name": "Domain of unknown function (DUF4293)", "partial_evidence_count": null, "pfam_id": "PF14126", "proteins": 2108, "proteomes": 2103, "short_name": "DUF4293", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14126", "structures": 0, "taxa": 2801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1410, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 3, "interpro_id": "IPR025227", "known_evidence_count": null, "matches": 2106, "name": "Domain of unknown function (DUF4169)", "partial_evidence_count": null, "pfam_id": "PF13770", "proteins": 2106, "proteomes": 2105, "short_name": "DUF4169", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13770", "structures": 0, "taxa": 2872, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 752, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is predominantly found in Bacteroidetes, and is about 100 amino acids in length. This domain contains a highly conserved YDxxGR motif which suggests that it is related the RHS repeats, that appear to be involved in ligand binding. RHS repeats share structural similarity with the eukaryotic tyrosine-aspartate (YD) repeat [[cite:PUB00070343]].", "domain_architectures": 258, "interpro_id": "IPR045619", "known_evidence_count": null, "matches": 2128, "name": "Domain of unknown function (DUF6443)", "partial_evidence_count": null, "pfam_id": "PF20041", "proteins": 2105, "proteomes": 812, "short_name": "DUF6443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20041", "structures": 0, "taxa": 1303, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001814) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This family includes a protein from the ulleungmycin biosynthetic gene cluster from Streptomyces sp. KCB13F003 [[cite:PUB00099461]].", "domain_architectures": 1, "interpro_id": "IPR046039", "known_evidence_count": null, "matches": 2104, "name": "Family of unknown function (DUF5997)", "partial_evidence_count": null, "pfam_id": "PF19460", "proteins": 2104, "proteomes": 2088, "short_name": "DUF5997", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19460", "structures": 0, "taxa": 2396, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1536, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an helical domain found at the C-terminal of fungal sequences, whose function is unknown.", "domain_architectures": 53, "interpro_id": "IPR056024", "known_evidence_count": null, "matches": 2109, "name": "Domain of unknown function (DUF7605)", "partial_evidence_count": null, "pfam_id": "PF24564", "proteins": 2103, "proteomes": 989, "short_name": "DUF7605", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24564", "structures": 0, "taxa": 2387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1415, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved domain found at the C-terminus of S41 family carboxyl-terminal processing peptidases in members of the phylum Bacteroidota. The domain is approximately 85-90 amino acids in length and is located immediately downstream of the Peptidase_S41 catalytic domain ([pfam:PF03572]). S41 family peptidases are serine proteases involved in C-terminal processing of proteins, including the removal of C-terminal extensions from penicillin-binding proteins and other substrates. This C-terminal domain is found exclusively in Bacteroidota, particularly in the classes Bacteroidia, Flavobacteriia, Cytophagia and Sphingobacteriia, suggesting it may confer phylum-specific functionality or substrate specificity. The domain architecture of these proteins typically consists of an N-terminal CtpB_N-like domain ([pfam:PF22694]), one or more PDZ domains ([pfam:PF00595], [pfam:PF13180], [pfam:PF17820]), the catalytic Peptidase_S41 domain, and this C-terminal domain. The function of this domain remains to be determined.", "domain_architectures": 11, "interpro_id": "IPR061513", "known_evidence_count": null, "matches": 2104, "name": "Family of unknown function (DUF8443)", "partial_evidence_count": null, "pfam_id": "PF28608", "proteins": 2103, "proteomes": 1778, "short_name": "DUF8443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28608", "structures": 0, "taxa": 2473, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1489, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A region of similarity shared by several Rhodopirellula baltica cytochrome-like proteins that are predicted to be secreted. These proteins also match [pfam:PF07624].", "domain_architectures": 110, "interpro_id": "IPR013036", "known_evidence_count": null, "matches": 2109, "name": "Protein of unknown function (DUF1587)", "partial_evidence_count": null, "pfam_id": "PF07626", "proteins": 2101, "proteomes": 461, "short_name": "PSD3", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07626", "structures": 0, "taxa": 897, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1348, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found at the N-terminus of bacterial and viral hypothetical proteins.", "domain_architectures": 7, "interpro_id": "IPR013619", "known_evidence_count": null, "matches": 2101, "name": "Domain of unknown function (DUF1737)", "partial_evidence_count": null, "pfam_id": "PF08410", "proteins": 2101, "proteomes": 2040, "short_name": "DUF1737", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08410", "structures": 0, "taxa": 2969, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1255, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic carbohydrate kinases, has no known function.", "domain_architectures": 5, "interpro_id": "IPR018659", "known_evidence_count": null, "matches": 2100, "name": "Uncharacterized protein conserved in bacteria (DUF2090)", "partial_evidence_count": null, "pfam_id": "PF09863", "proteins": 2096, "proteomes": 1986, "short_name": "DUF2090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09863", "structures": 0, "taxa": 2931, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1423, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR021265", "known_evidence_count": null, "matches": 2096, "name": "Protein of unknown function (DUF2842)", "partial_evidence_count": null, "pfam_id": "PF11003", "proteins": 2096, "proteomes": 2095, "short_name": "DUF2842", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11003", "structures": 0, "taxa": 2769, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1755, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised metazoan proteins. It is predicted to adopt a globular structure with lipocalin fold. It also contains several highly conserved cysteine residues that are likely involved in the formation of intra-domain disulfide bridges.", "domain_architectures": 96, "interpro_id": "IPR055470", "known_evidence_count": null, "matches": 2748, "name": "Domain of unknown function (DUF7042)", "partial_evidence_count": null, "pfam_id": "PF23069", "proteins": 2095, "proteomes": 479, "short_name": "DUF7042", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23069", "structures": 0, "taxa": 1700, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1409, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family are all sequences found within hypothetical proteins expressed by various bacterial species. The region concerned is approximately 150 residues long.", "domain_architectures": 9, "interpro_id": "IPR012441", "known_evidence_count": null, "matches": 2092, "name": "Protein of unknown function (DUF1643)", "partial_evidence_count": null, "pfam_id": "PF07799", "proteins": 2092, "proteomes": 1884, "short_name": "DUF1643", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07799", "structures": 0, "taxa": 3512, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is typically between 95 and 113 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR043725", "known_evidence_count": null, "matches": 2092, "name": "Domain of unknown function (DUF5667)", "partial_evidence_count": null, "pfam_id": "PF18915", "proteins": 2090, "proteomes": 2010, "short_name": "DUF5667", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18915", "structures": 0, "taxa": 2569, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1320, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 479 to 499 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR021804", "known_evidence_count": null, "matches": 2102, "name": "Protein of unknown function (DUF3375)", "partial_evidence_count": null, "pfam_id": "PF11855", "proteins": 2088, "proteomes": 1897, "short_name": "DUF3375", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11855", "structures": 12, "taxa": 2982, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1366, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from Agrobacterium, Rhizobium and Brucella species. The function of this family is unknown.", "domain_architectures": 9, "interpro_id": "IPR009389", "known_evidence_count": null, "matches": 2087, "name": "Protein of unknown function (DUF1045)", "partial_evidence_count": null, "pfam_id": "PF06299", "proteins": 2087, "proteomes": 1857, "short_name": "DUF1045", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06299", "structures": 0, "taxa": 2689, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1547, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 152 and 183 amino acids in length. The family is found in association with [pfam:PF00566]. There is a conserved NHLL sequence motif.", "domain_architectures": 16, "interpro_id": "IPR032738", "known_evidence_count": null, "matches": 2089, "name": "Domain of unknown function (DUF4682)", "partial_evidence_count": null, "pfam_id": "PF15733", "proteins": 2085, "proteomes": 1030, "short_name": "DUF4682", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15733", "structures": 0, "taxa": 3414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR006628", "known_evidence_count": null, "matches": 2085, "name": "Protein of unknown function (DUF3276)", "partial_evidence_count": null, "pfam_id": "PF11680", "proteins": 2084, "proteomes": 2030, "short_name": "DUF3276", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11680", "structures": 2, "taxa": 2709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1753, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function. The protein family is found in eukaryotes, and is typically between 170 and 183 amino acids in length.In humans, the gene encoding this protein lies in the position, chromosome 15 open reading frame 52.", "domain_architectures": 16, "interpro_id": "IPR029336", "known_evidence_count": null, "matches": 2098, "name": "Domain of unknown function (DUF4594)", "partial_evidence_count": null, "pfam_id": "PF15266", "proteins": 2084, "proteomes": 850, "short_name": "DUF4594", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15266", "structures": 0, "taxa": 2792, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents bacterial proteins that are predicted to be the outer membrane component of an efeUOB-like ferrous iron, uptake system [[cite:PUB00093610],[cite:PUB00070775]].", "domain_architectures": 5, "interpro_id": "IPR008311", "known_evidence_count": null, "matches": 2083, "name": "Protein of unknown function (DUF1513)", "partial_evidence_count": null, "pfam_id": "PF07433", "proteins": 2083, "proteomes": 2050, "short_name": "DUF1513", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07433", "structures": 0, "taxa": 2808, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1276, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 47, "interpro_id": "IPR018683", "known_evidence_count": null, "matches": 2162, "name": "Uncharacterized protein conserved in bacteria (DUF2169)", "partial_evidence_count": null, "pfam_id": "PF09937", "proteins": 2083, "proteomes": 1060, "short_name": "DUF2169", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09937", "structures": 1, "taxa": 1768, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1248, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function. It is mostly found in bacteria and can be present in multiple copies.", "domain_architectures": 131, "interpro_id": "IPR043744", "known_evidence_count": null, "matches": 2258, "name": "Family of unknown function (DUF5689)", "partial_evidence_count": null, "pfam_id": "PF18942", "proteins": 2083, "proteomes": 1679, "short_name": "DUF5689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18942", "structures": 0, "taxa": 2274, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1097, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function. Some family members overlap with [pfam:PF13646].", "domain_architectures": 10, "interpro_id": "IPR043746", "known_evidence_count": null, "matches": 2132, "name": "Family of unknown function (DUF5691)", "partial_evidence_count": null, "pfam_id": "PF18944", "proteins": 2083, "proteomes": 2042, "short_name": "DUF5691", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18944", "structures": 0, "taxa": 2813, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1362, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram-negative bacteria. It shares significant similarity to domains members of the DNA primase C-terminal domain superfamily such as [pfam:PF08278] and [pfam:PF00772].", "domain_architectures": 8, "interpro_id": "IPR059474", "known_evidence_count": null, "matches": 2089, "name": "Domain of unknown function (DUF8430)", "partial_evidence_count": null, "pfam_id": "PF28534", "proteins": 2082, "proteomes": 2081, "short_name": "DUF8430", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28534", "structures": 0, "taxa": 2792, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1418, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This model represents a family of conserved hypothetical proteins. It is usually (but not always) found in apparent phage-derived regions of bacterial chromosomes.", "domain_architectures": 14, "interpro_id": "IPR011740", "known_evidence_count": null, "matches": 2085, "name": "Conserved hypothetical protein 2217 (DUF2460)", "partial_evidence_count": null, "pfam_id": "PF09343", "proteins": 2080, "proteomes": 1723, "short_name": "DUF2460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09343", "structures": 4, "taxa": 2713, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1374, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 200 and 221 amino acids in length. There are two conserved sequence motifs: EYGR and KLWD.", "domain_architectures": 1, "interpro_id": "IPR025632", "known_evidence_count": null, "matches": 2080, "name": "Domain of unknown function (DUF4290)", "partial_evidence_count": null, "pfam_id": "PF14123", "proteins": 2080, "proteomes": 2077, "short_name": "DUF4290", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14123", "structures": 0, "taxa": 2748, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacterial uncharacterised proteins that probably belong to the penicillin-binding protein-type class of thioesterases. This domain is predicted to fold into a meander beta-barrel consisting of eight antiparallel beta-strands. It contains a semi-conserved GxWxW sequence motif near the N terminus.", "domain_architectures": 3, "interpro_id": "IPR056008", "known_evidence_count": null, "matches": 2078, "name": "Domain of unknown function (DUF7586)", "partial_evidence_count": null, "pfam_id": "PF24491", "proteins": 2078, "proteomes": 1725, "short_name": "DUF7586", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24491", "structures": 0, "taxa": 2012, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1230, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 8, "interpro_id": "IPR018650", "known_evidence_count": null, "matches": 2143, "name": "Predicted membrane protein (DUF2079)", "partial_evidence_count": null, "pfam_id": "PF09852", "proteins": 2068, "proteomes": 1551, "short_name": "DUF2079", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09852", "structures": 0, "taxa": 2584, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1486, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is a 6-bladed beta-propeller structure of unknown function. There is a highly conserved FDxxG motif which might be important.", "domain_architectures": 328, "interpro_id": "", "known_evidence_count": null, "matches": 2196, "name": "6-bladed beta-propeller", "partial_evidence_count": null, "pfam_id": "PF17170", "proteins": 2066, "proteomes": 948, "short_name": "DUF5128", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17170", "structures": 1, "taxa": 2522, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1656, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 54, "interpro_id": "IPR028011", "known_evidence_count": null, "matches": 2159, "name": "Domain of unknown function (DUF4476)", "partial_evidence_count": null, "pfam_id": "PF14771", "proteins": 2065, "proteomes": 1503, "short_name": "DUF4476", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14771", "structures": 0, "taxa": 3727, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1685, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. This domain has similarity to BAH domains.", "domain_architectures": 25, "interpro_id": "IPR061651", "known_evidence_count": null, "matches": 2081, "name": "Domain of unknown function (DUF8590)", "partial_evidence_count": null, "pfam_id": "PF29850", "proteins": 2060, "proteomes": 208, "short_name": "DUF8590", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29850", "structures": 0, "taxa": 572, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021448", "known_evidence_count": null, "matches": 2057, "name": "Protein of unknown function (DUF3098)", "partial_evidence_count": null, "pfam_id": "PF11297", "proteins": 2057, "proteomes": 2028, "short_name": "DUF3098", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11297", "structures": 0, "taxa": 2678, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1067, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of small hypothetical proteins, about 100 amino acids in length. The family includes five members (three in tandem) in Pseudomonas aeruginosa PAO1 and in Pseudomonas putida (strain KT2440), four in Pseudomonas syringae DC3000, and single members in several other Proteobacteria. The function is unknown.", "domain_architectures": 2, "interpro_id": "IPR012661", "known_evidence_count": null, "matches": 2054, "name": "Protein of unknown function (DUF2388)", "partial_evidence_count": null, "pfam_id": "PF09498", "proteins": 2053, "proteomes": 576, "short_name": "DUF2388", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09498", "structures": 0, "taxa": 671, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1198, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021250", "known_evidence_count": null, "matches": 2050, "name": "Protein of unknown function (DUF2789)", "partial_evidence_count": null, "pfam_id": "PF10982", "proteins": 2050, "proteomes": 1728, "short_name": "DUF2789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10982", "structures": 1, "taxa": 2259, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1336, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. However, structural-similarity searches indicate the family takes on an actin-like ATPase fold.", "domain_architectures": 2, "interpro_id": "IPR024213", "known_evidence_count": null, "matches": 2051, "name": "Protein of unknown function (DUF3822)", "partial_evidence_count": null, "pfam_id": "PF12864", "proteins": 2049, "proteomes": 2039, "short_name": "DUF3822", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12864", "structures": 1, "taxa": 2672, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1688, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function at the C-terminal in uncharacterised fungal proteins.", "domain_architectures": 34, "interpro_id": "IPR059798", "known_evidence_count": null, "matches": 2049, "name": "Domain of unknown function (DUF8568)", "partial_evidence_count": null, "pfam_id": "PF27034", "proteins": 2047, "proteomes": 764, "short_name": "DUF8568", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27034", "structures": 0, "taxa": 1544, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1331, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 90 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025381", "known_evidence_count": null, "matches": 2046, "name": "Domain of unknown function (DUF4296)", "partial_evidence_count": null, "pfam_id": "PF14129", "proteins": 2046, "proteomes": 2043, "short_name": "DUF4296", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14129", "structures": 0, "taxa": 2693, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1318, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function. Members of this family have an alpha/beta hydrolase fold.", "domain_architectures": 23, "interpro_id": "IPR010315", "known_evidence_count": null, "matches": 2132, "name": "Alpha/beta hydrolase of unknown function (DUF915)", "partial_evidence_count": null, "pfam_id": "PF06028", "proteins": 2045, "proteomes": 894, "short_name": "DUF915", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06028", "structures": 3, "taxa": 1503, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1343, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of BVU_3817 from Phocaeicola vulgatus ([swissprot:A6L6W4]) and similar proteins mostly found in Bacteroidetes. This domain shows an alpha/beta structure and is normally found associated with [pfam:PF18347]. Its function is unknown.", "domain_architectures": 3, "interpro_id": "IPR049280", "known_evidence_count": null, "matches": 2043, "name": "Domain of unknown function (DUF6852)", "partial_evidence_count": null, "pfam_id": "PF21186", "proteins": 2043, "proteomes": 2041, "short_name": "DUF6852", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21186", "structures": 1, "taxa": 2676, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1337, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is related to other known glycosyl hydrolases suggesting this domain is also involved in carbohydrate break down.", "domain_architectures": 30, "interpro_id": "IPR025275", "known_evidence_count": null, "matches": 2048, "name": "Putative glycosyl hydrolase domain", "partial_evidence_count": null, "pfam_id": "PF13200", "proteins": 2042, "proteomes": 1830, "short_name": "DUF4015", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13200", "structures": 1, "taxa": 2863, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 11, "interpro_id": "IPR025438", "known_evidence_count": null, "matches": 2042, "name": "Domain of unknown function (DUF4180)", "partial_evidence_count": null, "pfam_id": "PF13788", "proteins": 2042, "proteomes": 1992, "short_name": "DUF4180", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13788", "structures": 0, "taxa": 2899, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1340, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found at the N-terminal region of bacterial proteins.", "domain_architectures": 3, "interpro_id": "IPR041218", "known_evidence_count": null, "matches": 2039, "name": "Domain of unknown function (DUF5606)", "partial_evidence_count": null, "pfam_id": "PF18347", "proteins": 2039, "proteomes": 2038, "short_name": "DUF5606", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18347", "structures": 1, "taxa": 2673, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in bacteria.", "domain_architectures": 6, "interpro_id": "IPR043740", "known_evidence_count": null, "matches": 2056, "name": "Family of unknown function (DUF5685)", "partial_evidence_count": null, "pfam_id": "PF18937", "proteins": 2039, "proteomes": 1918, "short_name": "DUF5685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18937", "structures": 0, "taxa": 2663, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain of unknown function contains six well-conserved cysteine residues.", "domain_architectures": 22, "interpro_id": "IPR025240", "known_evidence_count": null, "matches": 2152, "name": "Domain of unknown function (DUF4189)", "partial_evidence_count": null, "pfam_id": "PF13827", "proteins": 2037, "proteomes": 1117, "short_name": "DUF4189", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13827", "structures": 1, "taxa": 1768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1325, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]]. According to structure predictions, members of this entry are distantly related to SNaCT domains (CLan:CL0806).", "domain_architectures": 1, "interpro_id": "IPR016979", "known_evidence_count": null, "matches": 2036, "name": "Uncharacterized protein conserved in bacteria (DUF2129)", "partial_evidence_count": null, "pfam_id": "PF09902", "proteins": 2036, "proteomes": 1985, "short_name": "DUF2129", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09902", "structures": 0, "taxa": 2666, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised protein. The function is not known however it is conserved in Bacteria.", "domain_architectures": 5, "interpro_id": "IPR021218", "known_evidence_count": null, "matches": 2035, "name": "Protein of Unknown function (DUF2784)", "partial_evidence_count": null, "pfam_id": "PF10861", "proteins": 2035, "proteomes": 1966, "short_name": "DUF2784", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10861", "structures": 0, "taxa": 2826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in bacteriodetes and pseudomonadota bacteria. it is found both on its own and in larger multidomain proteins.", "domain_architectures": 50, "interpro_id": "IPR061521", "known_evidence_count": null, "matches": 2032, "name": "Domain of unknown function (DUF8451)", "partial_evidence_count": null, "pfam_id": "PF28727", "proteins": 2032, "proteomes": 1687, "short_name": "DUF8451", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28727", "structures": 0, "taxa": 3425, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1688, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains a set of highly conserved cysteine residues that are predicted to form disulfide bonds. It is likely that proteins containing this domain are secreted.", "domain_architectures": 20, "interpro_id": "IPR056124", "known_evidence_count": null, "matches": 2042, "name": "Domain of unknown function (DUF7707)", "partial_evidence_count": null, "pfam_id": "PF24808", "proteins": 2031, "proteomes": 989, "short_name": "DUF7707", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24808", "structures": 0, "taxa": 2009, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of bacterial and archaeal proteins, the structure for one of whose members has been characterised. PDB:3kop from [swissprot:A0JVT3] probably adopts a new hexameric form compared to previous structures. The putative active is near the domain interface. 3kop is most closely related, structurally to PDB:1zx8, where the potential active site is located near residues E51 and Y53 (conserved in 1zx8). Beyond the two residues above, the other residues are not conserved. Also the shape of the active site differs from that of 1zx8. PDB:1zx8 belongs to family DUF369. [pfam:PF04126], which is part of the cyclophilin-like clan.", "domain_architectures": 2, "interpro_id": "IPR024532", "known_evidence_count": null, "matches": 2028, "name": "Protein of unknown function (DUF3830)", "partial_evidence_count": null, "pfam_id": "PF12903", "proteins": 2028, "proteomes": 1945, "short_name": "DUF3830", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12903", "structures": 1, "taxa": 2830, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1014, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 70 residues found in secreted alpha/beta hydrolases in Actinomycetes, particularly Streptomycetaceae, Microbacteriaceae, and Micrococcaceae. This domain is found N-terminal to various hydrolase domains including Abhydrolase_1 ([pfam:PF00561]) and Peptidase_S9 ([pfam:PF00326]). The function of this domain remains to be determined.", "domain_architectures": 10, "interpro_id": "IPR061866", "known_evidence_count": null, "matches": 2025, "name": "Domain of unknown function (DUF8805)", "partial_evidence_count": null, "pfam_id": "PF31080", "proteins": 2025, "proteomes": 1868, "short_name": "DUF8805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31080", "structures": 0, "taxa": 2125, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1317, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It probably folds into a small beta-sandwich. it is usually found associated with a transmembrane domain.", "domain_architectures": 2, "interpro_id": "IPR059477", "known_evidence_count": null, "matches": 2022, "name": "Domain of unknown function (DUF8433)", "partial_evidence_count": null, "pfam_id": "PF28541", "proteins": 2022, "proteomes": 2017, "short_name": "DUF8433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28541", "structures": 0, "taxa": 2640, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1248, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 155 and 220 amino acids in length. There are two conserved sequence motif, DCGG and QLW, and conserved cysteine residues at the C-terminal.", "domain_architectures": 5, "interpro_id": "IPR045534", "known_evidence_count": null, "matches": 2021, "name": "Family of unknown function (DUF6428)", "partial_evidence_count": null, "pfam_id": "PF20001", "proteins": 2020, "proteomes": 1734, "short_name": "DUF6428", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20001", "structures": 0, "taxa": 2296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1693, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is predicted to adopt a globular structure composed of alpha-helices.", "domain_architectures": 27, "interpro_id": "IPR055936", "known_evidence_count": null, "matches": 2033, "name": "Domain of unknown function (DUF7514)", "partial_evidence_count": null, "pfam_id": "PF24355", "proteins": 2019, "proteomes": 928, "short_name": "DUF7514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24355", "structures": 0, "taxa": 1859, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 58 and 85 amino acids in length. There is a single completely conserved residue G that may be functionally important.", "domain_architectures": 9, "interpro_id": "IPR022037", "known_evidence_count": null, "matches": 2060, "name": "Protein of unknown function (DUF3606)", "partial_evidence_count": null, "pfam_id": "PF12244", "proteins": 2018, "proteomes": 1146, "short_name": "DUF3606", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12244", "structures": 0, "taxa": 1608, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 932, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, archaea and viruses, and is approximately 90 amino acids in length. This domain is often found in two tandem copies.", "domain_architectures": 18, "interpro_id": "IPR027860", "known_evidence_count": null, "matches": 3839, "name": "Domain of unknown function (DUF4429)", "partial_evidence_count": null, "pfam_id": "PF14472", "proteins": 2018, "proteomes": 1137, "short_name": "DUF4429", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14472", "structures": 0, "taxa": 1504, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1223, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function. The domain, however, is found in various periplasmic ligand-binding sensor proteins.", "domain_architectures": 7, "interpro_id": "IPR018648", "known_evidence_count": null, "matches": 2035, "name": "Uncharacterized protein conserved in bacteria (DUF2076)", "partial_evidence_count": null, "pfam_id": "PF09849", "proteins": 2016, "proteomes": 1917, "short_name": "DUF2076", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09849", "structures": 0, "taxa": 2868, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1582, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 260 and 408 amino acids in length. This entry corresponds to a region of about 200 amino acids in length with multiple conserved motifs. There are two conserved sequence motifs: GAP and NGG. In some proteins this domain is found associated with various glycosyl transferase enzyme domains, suggesting this domain has a related role in glycan biosynthesis.", "domain_architectures": 34, "interpro_id": "IPR043729", "known_evidence_count": null, "matches": 2010, "name": "Protein of unknown function (DUF5672)", "partial_evidence_count": null, "pfam_id": "PF18922", "proteins": 2009, "proteomes": 956, "short_name": "DUF5672", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18922", "structures": 0, "taxa": 1843, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 220 amino acids in length.", "domain_architectures": 67, "interpro_id": "IPR046616", "known_evidence_count": null, "matches": 2094, "name": "Domain of unknown function (DUF6729)", "partial_evidence_count": null, "pfam_id": "PF20499", "proteins": 2009, "proteomes": 263, "short_name": "DUF6729", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20499", "structures": 0, "taxa": 1007, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1587, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 9, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family contains several uncharacterised proteins found in Arabidopsis thaliana and other plants. This region is often found associated with Agenet domains and may contain coiled-coil.", "domain_architectures": 61, "interpro_id": "IPR007930", "known_evidence_count": null, "matches": 2029, "name": "Protein of unknown function (DUF724)", "partial_evidence_count": null, "pfam_id": "PF05266", "proteins": 2006, "proteomes": 302, "short_name": "DUF724", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05266", "structures": 0, "taxa": 826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1344, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has a conserved HEXXH motif, suggesting the members are putative peptidases of zincin fold [[cite:PUB00075429]].", "domain_architectures": 5, "interpro_id": "IPR021683", "known_evidence_count": null, "matches": 2006, "name": "Putative zincin peptidase", "partial_evidence_count": null, "pfam_id": "PF11667", "proteins": 2006, "proteomes": 1584, "short_name": "DUF3267", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11667", "structures": 0, "taxa": 2645, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1477, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an uncharacterised family of proteins.", "domain_architectures": 25, "interpro_id": "IPR025067", "known_evidence_count": null, "matches": 2010, "name": "Protein of unknown function (DUF4079)", "partial_evidence_count": null, "pfam_id": "PF13301", "proteins": 2006, "proteomes": 751, "short_name": "DUF4079", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13301", "structures": 0, "taxa": 2147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 69 and 402 amino acids in length.", "domain_architectures": 46, "interpro_id": "IPR025330", "known_evidence_count": null, "matches": 2006, "name": "Protein of unknown function (DUF4236)", "partial_evidence_count": null, "pfam_id": "PF14020", "proteins": 2006, "proteomes": 1846, "short_name": "DUF4236", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14020", "structures": 0, "taxa": 3001, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are often found in the gene neighbourhood, or fused to, non-ribosomal peptide synthetases.", "domain_architectures": 4, "interpro_id": "IPR032369", "known_evidence_count": null, "matches": 2006, "name": "Domain of unknown function (DUF4872)", "partial_evidence_count": null, "pfam_id": "PF16169", "proteins": 2006, "proteomes": 1784, "short_name": "DUF4872", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16169", "structures": 0, "taxa": 2695, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1312, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The sequences featured in this family are derived from a number of hypothetical prokaryotic proteins. The region in question is approximately 130 amino acids long.", "domain_architectures": 3, "interpro_id": "IPR012863", "known_evidence_count": null, "matches": 2002, "name": "Protein of unknown function (DUF1636)", "partial_evidence_count": null, "pfam_id": "PF07845", "proteins": 2002, "proteomes": 1595, "short_name": "DUF1636", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07845", "structures": 1, "taxa": 2486, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1061, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 198 and 278 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR045592", "known_evidence_count": null, "matches": 2049, "name": "Family of unknown function (DUF6461)", "partial_evidence_count": null, "pfam_id": "PF20062", "proteins": 2002, "proteomes": 955, "short_name": "DUF6461", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20062", "structures": 0, "taxa": 1195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR021955", "known_evidence_count": null, "matches": 2001, "name": "Protein of unknown function (DUF3572)", "partial_evidence_count": null, "pfam_id": "PF12096", "proteins": 2001, "proteomes": 1960, "short_name": "DUF3572", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12096", "structures": 0, "taxa": 2584, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 221 and 326 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025367", "known_evidence_count": null, "matches": 2001, "name": "Domain of unknown function (DUF4271)", "partial_evidence_count": null, "pfam_id": "PF14093", "proteins": 2001, "proteomes": 1997, "short_name": "DUF4271", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14093", "structures": 0, "taxa": 2621, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 14 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in Lysine-specific demethylase 3B (KDM3B, also known as JmjC domain-containing histone demethylation protein 2B or JHDM2B) and related proteins. KDM3B is a histone demethylase that specifically demethylates lysine at position 9 of histone H3 [[cite:PUB00153916]]. This enzyme plays a central role in histone code. This domain is predicted to adopt an open beta-barrel with an SH3-like topology.", "domain_architectures": 15, "interpro_id": "IPR054294", "known_evidence_count": null, "matches": 1996, "name": "Domain of unknown function (DUF7030)", "partial_evidence_count": null, "pfam_id": "PF22989", "proteins": 1996, "proteomes": 685, "short_name": "DUF7030", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22989", "structures": 0, "taxa": 2415, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1743, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found towards the C-terminal end of human Calcium homeostasis endoplasmic reticulum protein (CHERP), which is involved in calcium homeostasis, growth and proliferation. This domain is usually found associated with [pfam:PF01585]. Its specific function is unknown. It shows highly conserved GWE and GLYE/DxY/F motifs.", "domain_architectures": 37, "interpro_id": "IPR056721", "known_evidence_count": null, "matches": 1997, "name": "Domain of unknown function (DUF7819)", "partial_evidence_count": null, "pfam_id": "PF25127", "proteins": 1994, "proteomes": 1224, "short_name": "DUF7819", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25127", "structures": 0, "taxa": 3986, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1323, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 140 amino acids in length. The family is found in association with [pfam:PF04055]. This family consists of proteins which are commonly annotated as Radical SAM domains but there is little annotation to back this up.", "domain_architectures": 15, "interpro_id": "IPR024521", "known_evidence_count": null, "matches": 2000, "name": "Protein of unknown function (DUF3641)", "partial_evidence_count": null, "pfam_id": "PF12345", "proteins": 1993, "proteomes": 1891, "short_name": "DUF3641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12345", "structures": 0, "taxa": 3689, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is approximately 380 amino acids in length. The family is found in association with [pfam:PF05147]. This domain may be involved in synthesis of a lantibiotic compound.", "domain_architectures": 15, "interpro_id": "IPR025410", "known_evidence_count": null, "matches": 2039, "name": "Domain of unknown function (DUF4135)", "partial_evidence_count": null, "pfam_id": "PF13575", "proteins": 1992, "proteomes": 1385, "short_name": "DUF4135", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13575", "structures": 2, "taxa": 2401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is the N-terminal domain of a putative glycoside hydrolase, DUF4038. It is found in a number of different bacterial orders.", "domain_architectures": 149, "interpro_id": "IPR032260", "known_evidence_count": null, "matches": 1992, "name": "Domain of unknown function (DUF5060)", "partial_evidence_count": null, "pfam_id": "PF16586", "proteins": 1992, "proteomes": 1250, "short_name": "DUF5060", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16586", "structures": 10, "taxa": 2224, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 709, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. It is found repeated several times in the vertebrate KIAA0556 proteins.", "domain_architectures": 32, "interpro_id": "IPR027859", "known_evidence_count": null, "matches": 4917, "name": "Domain of unknown function (DUF4457)", "partial_evidence_count": null, "pfam_id": "PF14652", "proteins": 1986, "proteomes": 1148, "short_name": "DUF4457", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14652", "structures": 0, "taxa": 3719, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000434) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This family includes a protein from the SW-163C biosynthetic gene cluster from Streptomyces sp. SNA15896 [[cite:PUB00083668]].", "domain_architectures": 4, "interpro_id": "IPR046038", "known_evidence_count": null, "matches": 1986, "name": "Family of unknown function (DUF5996)", "partial_evidence_count": null, "pfam_id": "PF19459", "proteins": 1984, "proteomes": 1867, "short_name": "DUF5996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19459", "structures": 0, "taxa": 2846, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1304, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 323 to 658 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR021795", "known_evidence_count": null, "matches": 2381, "name": "Protein of unknown function (DUF3363)", "partial_evidence_count": null, "pfam_id": "PF11843", "proteins": 1982, "proteomes": 1142, "short_name": "DUF3363", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11843", "structures": 0, "taxa": 1889, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1051, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001522) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the auroramycin biosynthetic gene cluster from Streptomyces filamentosus [[cite:PUB00099445]]. Some members of this family have been identified as putative phosphodiesterases.", "domain_architectures": 1, "interpro_id": "IPR046040", "known_evidence_count": null, "matches": 1979, "name": "Family of unknown function (DUF5998)", "partial_evidence_count": null, "pfam_id": "PF19461", "proteins": 1979, "proteomes": 1974, "short_name": "DUF5998", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19461", "structures": 0, "taxa": 2308, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1314, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins mainly from gram-negative bacteria. It is predicted to form a single transmembrane helix which sometime is found in combination with MlaD-like domain ([pfam:PF02470]).", "domain_architectures": 3, "interpro_id": "IPR059478", "known_evidence_count": null, "matches": 1978, "name": "Domain of unknown function (DUF8434)", "partial_evidence_count": null, "pfam_id": "PF28542", "proteins": 1978, "proteomes": 1977, "short_name": "DUF8434", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28542", "structures": 0, "taxa": 2594, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins, however some members of this family are annotated as membrane proteins.", "domain_architectures": 5, "interpro_id": "IPR021359", "known_evidence_count": null, "matches": 2084, "name": "Protein of unknown function (DUF2812)", "partial_evidence_count": null, "pfam_id": "PF11193", "proteins": 1977, "proteomes": 1295, "short_name": "DUF2812", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11193", "structures": 0, "taxa": 1983, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 895, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 16, "interpro_id": "IPR021224", "known_evidence_count": null, "matches": 1976, "name": "Protein of unknown function (DUF2690)", "partial_evidence_count": null, "pfam_id": "PF10901", "proteins": 1976, "proteomes": 1096, "short_name": "DUF2690", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10901", "structures": 0, "taxa": 1393, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1243, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR019882", "known_evidence_count": null, "matches": 1976, "name": "Protein of unknown function (DUF2805)", "partial_evidence_count": null, "pfam_id": "PF10985", "proteins": 1976, "proteomes": 1766, "short_name": "DUF2805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10985", "structures": 0, "taxa": 2707, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1279, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in bacterial proteins of unknown function. The crystal structure has been solved for a protein containing this domain SWISS:Q0WXP6 [[cite:PUB00085154]].", "domain_architectures": 36, "interpro_id": "IPR009270", "known_evidence_count": null, "matches": 1976, "name": "Domain of unknown function (DUF927)", "partial_evidence_count": null, "pfam_id": "PF06048", "proteins": 1975, "proteomes": 1538, "short_name": "DUF927", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06048", "structures": 2, "taxa": 2869, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1644, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a family that is found predominantly at the C-terminus of Kelch-containing proteins. However, the exact function of this region is not known.", "domain_architectures": 46, "interpro_id": "IPR025183", "known_evidence_count": null, "matches": 1978, "name": "Domain of unknown function (DUF4110)", "partial_evidence_count": null, "pfam_id": "PF13422", "proteins": 1975, "proteomes": 1792, "short_name": "DUF4110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13422", "structures": 0, "taxa": 4083, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 668, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is related to secretion system C-terminal sorting domains.", "domain_architectures": 448, "interpro_id": "IPR061755", "known_evidence_count": null, "matches": 1973, "name": "Domain of unknown function (DUF8694)", "partial_evidence_count": null, "pfam_id": "PF30703", "proteins": 1973, "proteomes": 611, "short_name": "DUF8694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30703", "structures": 4, "taxa": 778, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1244, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 190 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025352", "known_evidence_count": null, "matches": 1973, "name": "Protein of unknown function (DUF4256)", "partial_evidence_count": null, "pfam_id": "PF14066", "proteins": 1972, "proteomes": 1946, "short_name": "DUF4256", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14066", "structures": 0, "taxa": 2837, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of uncharacterised integral membrane proteins appears to be restricted to proteobacteria. These proteins are related to the DoxX family [pfam:PF07681]. Members of this family form a confident homodimeric structure, for example UniProtKB:A0A4R5FQM0 iPTM=0.94.", "domain_architectures": 5, "interpro_id": "IPR007339", "known_evidence_count": null, "matches": 2090, "name": "Protein of unknown function, DUF417", "partial_evidence_count": null, "pfam_id": "PF04224", "proteins": 1971, "proteomes": 1536, "short_name": "DUF417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04224", "structures": 0, "taxa": 2351, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1845, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "The region featured in this family is found in a number of C. elegans proteins, in one case ([swissprot:Q19034]) as a repeat. In many of the family members, this region is associated with the CHK region described by SMART as being found in ZnF_C4 and HLH domain-containing kinases. In fact, one member of this family ([swissprot:Q9GUC1]) is annotated as being a member of the nuclear hormone receptor family, and contains regions typical of such proteins (Interpro:IPR000536, Interpro:IPR008946, and Interpro:IPR001628).", "domain_architectures": 59, "interpro_id": "IPR012877", "known_evidence_count": null, "matches": 2154, "name": "Uncharacterized oxidoreductase dhs-27", "partial_evidence_count": null, "pfam_id": "PF07914", "proteins": 1968, "proteomes": 182, "short_name": "DUF1679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07914", "structures": 0, "taxa": 632, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1219, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Members of this family are found in a set of prokaryotic hypothetical proteins. Their exact function, has not, as yet, been defined. This entry represents the N-terminal 3-transmembrane helical domain.", "domain_architectures": 5, "interpro_id": "IPR048493", "known_evidence_count": null, "matches": 1979, "name": "DUF1980 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF09323", "proteins": 1967, "proteomes": 1678, "short_name": "DUF1980", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09323", "structures": 0, "taxa": 2503, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_0095, a putative uncharacterized protein As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), It appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011]][[cite:PUB00056012]].", "domain_architectures": 2, "interpro_id": "IPR025408", "known_evidence_count": null, "matches": 1969, "name": "Domain of unknown function (DUF4134)", "partial_evidence_count": null, "pfam_id": "PF13572", "proteins": 1966, "proteomes": 870, "short_name": "DUF4134", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13572", "structures": 0, "taxa": 1159, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 442, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain rich in cysteines often found several times in a group of uncharacterised eukaryotic proteins. Many members of this family are annotated as tyrosine-protein kinases.", "domain_architectures": 25, "interpro_id": "IPR058316", "known_evidence_count": null, "matches": 1967, "name": "Domain of unknown function (DUF8003)", "partial_evidence_count": null, "pfam_id": "PF26010", "proteins": 1964, "proteomes": 432, "short_name": "DUF8003", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26010", "structures": 0, "taxa": 1191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 50 amino acids in length. There are two completely conserved residues (K and Y) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025379", "known_evidence_count": null, "matches": 1963, "name": "Domain of unknown function (DUF4295)", "partial_evidence_count": null, "pfam_id": "PF14128", "proteins": 1963, "proteomes": 1960, "short_name": "DUF4295", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14128", "structures": 7, "taxa": 2600, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1578, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to adopt beta-Trefoil fold. It is closely related to members of Fascin [pfam:PF06268].", "domain_architectures": 84, "interpro_id": "IPR057232", "known_evidence_count": null, "matches": 2154, "name": "Domain of unknown function (DUF7910)", "partial_evidence_count": null, "pfam_id": "PF25490", "proteins": 1961, "proteomes": 445, "short_name": "DUF7910", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25490", "structures": 0, "taxa": 1294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1482, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical glycine rich plant and bacterial proteins of around 300 residues in length. The function of this family is unknown.", "domain_architectures": 21, "interpro_id": "IPR010903", "known_evidence_count": null, "matches": 2040, "name": "Protein of unknown function (DUF1517)", "partial_evidence_count": null, "pfam_id": "PF07466", "proteins": 1960, "proteomes": 803, "short_name": "DUF1517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07466", "structures": 0, "taxa": 2113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1642, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This entry is of the conserved N-terminal 150 residues of proteins conserved from plants to humans. The function is unknown although some annotation suggests it to be a transmembrane protein.", "domain_architectures": 40, "interpro_id": "IPR019164", "known_evidence_count": null, "matches": 1987, "name": "Predicted membrane protein (DUF2053)", "partial_evidence_count": null, "pfam_id": "PF09767", "proteins": 1959, "proteomes": 1351, "short_name": "DUF2053", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09767", "structures": 5, "taxa": 4461, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1605, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised fungal proteins, including Choriogenin Hminor from Beauveria bassiana (Swiss: J4W9A9) [[cite:PUB00161221]]. Its function is unknown. It is predicted to adopt an all-alpha configuration.", "domain_architectures": 12, "interpro_id": "IPR058317", "known_evidence_count": null, "matches": 1958, "name": "Domain of unknown function (DUF8004)", "partial_evidence_count": null, "pfam_id": "PF26013", "proteins": 1958, "proteomes": 872, "short_name": "DUF8004", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26013", "structures": 0, "taxa": 1707, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 114 and 126 amino acids in length. There is a conserved GLK sequence motif.", "domain_architectures": 5, "interpro_id": "IPR025356", "known_evidence_count": null, "matches": 1954, "name": "Domain of unknown function (DUF4260)", "partial_evidence_count": null, "pfam_id": "PF14079", "proteins": 1953, "proteomes": 1894, "short_name": "DUF4260", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14079", "structures": 0, "taxa": 2909, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1488, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant proteins. These proteins are probably distantly related to the plant-specific actin-binding protein SCAB1 and are predicted to contain a fusion domain composed of Ig and PH-like domains in a similar arrangement as in SCAB1 (([pfam:PF16709]) and ([pfam:PF17684])) [[cite:PUB00076164]]. The domain represented by this entry corresponds to an atypical PH-like domain.", "domain_architectures": 50, "interpro_id": "IPR055474", "known_evidence_count": null, "matches": 2197, "name": "Domain of unknown function (DUF7046)", "partial_evidence_count": null, "pfam_id": "PF23080", "proteins": 1952, "proteomes": 350, "short_name": "DUF7046", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23080", "structures": 0, "taxa": 983, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1610, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt beta-Trefoil fold. It is probably distantly related to domains members of [pfam:PF22799].", "domain_architectures": 32, "interpro_id": "IPR057229", "known_evidence_count": null, "matches": 1958, "name": "Domain of unknown function (DUF7907)", "partial_evidence_count": null, "pfam_id": "PF25484", "proteins": 1950, "proteomes": 879, "short_name": "DUF7907", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25484", "structures": 0, "taxa": 1785, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins of around 300 residues in length and is mainly found in bacteria from the Cytophaga-Flavobacteria-Bacteroides (CFB) group, both environmental and from human microbiome. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032274", "known_evidence_count": null, "matches": 1942, "name": "Domain of unknown function (DUF4835)", "partial_evidence_count": null, "pfam_id": "PF16119", "proteins": 1942, "proteomes": 1937, "short_name": "DUF4835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16119", "structures": 0, "taxa": 2580, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1244, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009526", "known_evidence_count": null, "matches": 1941, "name": "Protein of unknown function (DUF1146)", "partial_evidence_count": null, "pfam_id": "PF06612", "proteins": 1941, "proteomes": 1938, "short_name": "DUF1146", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06612", "structures": 0, "taxa": 2574, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small helical domain of unknown function found in proteins from Flavobacteriia. The domain is typically around 70-90 residues in length and is located towards the C-terminus of these proteins, following a short N-terminal region. The proteins are found almost exclusively in the Flavobacteriaceae family within the Bacteroidota phylum. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061527", "known_evidence_count": null, "matches": 1940, "name": "Domain of unknown function (DUF8457)", "partial_evidence_count": null, "pfam_id": "PF28774", "proteins": 1940, "proteomes": 1939, "short_name": "DUF8457", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28774", "structures": 0, "taxa": 2567, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised bacterial sequences. This domain is found at the N-terminal of [pfam:PF09839] and may have a fold consisting of three anti-parallel beta-strands followed by alpha-helices of which one is longer than the other two.", "domain_architectures": 4, "interpro_id": "IPR061666", "known_evidence_count": null, "matches": 1941, "name": "Domain of unknown function (DUF8605)", "partial_evidence_count": null, "pfam_id": "PF29988", "proteins": 1940, "proteomes": 1934, "short_name": "DUF8605", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29988", "structures": 0, "taxa": 2597, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1590, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved cysteine-rich region found in uncharacterised metazoan proteins. The conserved cysteine residues are predicted to form disulfide bonds.", "domain_architectures": 88, "interpro_id": "IPR059445", "known_evidence_count": null, "matches": 2256, "name": "Family of unknown function (DUF8401)", "partial_evidence_count": null, "pfam_id": "PF28443", "proteins": 1938, "proteomes": 179, "short_name": "DUF8401", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28443", "structures": 0, "taxa": 845, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1038, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins that are about 100 amino acids in length. These proteins are predicted to form homopentameric complexes. These proteins are found in actinomycete as well as a few phage genomes.", "domain_architectures": 8, "interpro_id": "IPR057204", "known_evidence_count": null, "matches": 1935, "name": "Domain of unknown function (DUF7882)", "partial_evidence_count": null, "pfam_id": "PF25355", "proteins": 1935, "proteomes": 389, "short_name": "DUF7882", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25355", "structures": 0, "taxa": 464, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 262 and 476 amino acids in length.", "domain_architectures": 69, "interpro_id": "IPR025507", "known_evidence_count": null, "matches": 2570, "name": "Domain of unknown function (DUF4394)", "partial_evidence_count": null, "pfam_id": "PF14339", "proteins": 1933, "proteomes": 1590, "short_name": "DUF4394", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14339", "structures": 0, "taxa": 2504, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes. The structure of this protein has been solved and each domain is composed of four alpha helices. A metal cluster composed of iron and magnesium lies between the two domains.", "domain_architectures": 4, "interpro_id": "IPR021328", "known_evidence_count": null, "matches": 3388, "name": "Domain of unknown function (DUF2935)", "partial_evidence_count": null, "pfam_id": "PF11155", "proteins": 1932, "proteomes": 1153, "short_name": "DUF2935", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11155", "structures": 2, "taxa": 1707, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1677, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family includes the uncharacterised protein C7orf73 that is found in eukaryotes. Members are generally less than 100 residues in length. Although the precise function of the domain is still unknown, members have a predicted N-terminal signal peptide sequence which suggests they are short secreted peptides.", "domain_architectures": 42, "interpro_id": "IPR027854", "known_evidence_count": null, "matches": 1932, "name": "Domain of unknown function (DUF4535)", "partial_evidence_count": null, "pfam_id": "PF15054", "proteins": 1931, "proteomes": 885, "short_name": "DUF4535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15054", "structures": 0, "taxa": 3025, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021312", "known_evidence_count": null, "matches": 1930, "name": "Protein of unknown function (DUF2889)", "partial_evidence_count": null, "pfam_id": "PF11136", "proteins": 1930, "proteomes": 1543, "short_name": "DUF2889", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11136", "structures": 0, "taxa": 2265, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 710, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, archaea and eukaryotes. This domain is about 160 amino acids in length. This domain is found associated with [pfam:PF02514].", "domain_architectures": 23, "interpro_id": "IPR022571", "known_evidence_count": null, "matches": 1931, "name": "Domain of unknown function (DUF3479)", "partial_evidence_count": null, "pfam_id": "PF11965", "proteins": 1930, "proteomes": 1330, "short_name": "DUF3479", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11965", "structures": 5, "taxa": 3066, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1492, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of archaeal proteins has no known function. A study suggests that some members may be G-quadruplex binding proteins [[cite:PUB00098045]].", "domain_architectures": 4, "interpro_id": "IPR002852", "known_evidence_count": null, "matches": 1928, "name": "Protein of unknown function DUF134", "partial_evidence_count": null, "pfam_id": "PF02001", "proteins": 1928, "proteomes": 1555, "short_name": "DUF134", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02001", "structures": 0, "taxa": 3102, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1324, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009531", "known_evidence_count": null, "matches": 1928, "name": "Protein of unknown function (DUF1150)", "partial_evidence_count": null, "pfam_id": "PF06620", "proteins": 1928, "proteomes": 1913, "short_name": "DUF1150", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06620", "structures": 1, "taxa": 2650, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This conserved hypothetical protein of unknown function is found in several Proteobacteria. Its function is unknown and its genome context is not well-conserved. It is found amid urease genes in at least one species.", "domain_architectures": 4, "interpro_id": "IPR011727", "known_evidence_count": null, "matches": 1926, "name": "Protein of unknown function (DUF2459)", "partial_evidence_count": null, "pfam_id": "PF09601", "proteins": 1925, "proteomes": 1865, "short_name": "DUF2459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09601", "structures": 0, "taxa": 2821, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1225, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "All the members of this family are uncharacterised proteins, but the environment in which they are found on the bacterial genome suggests a function as a glucose-6-phosphate isomerase (EC 5.3.1.9). This could not, however, be confirmed.", "domain_architectures": 1, "interpro_id": "IPR018914", "known_evidence_count": null, "matches": 1925, "name": "Protein of unknown function (DUF2480)", "partial_evidence_count": null, "pfam_id": "PF10652", "proteins": 1925, "proteomes": 1792, "short_name": "DUF2480", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10652", "structures": 0, "taxa": 2310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1545, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is very short and is found at the N-terminal of many Gag-pol polyprotein and related proteins. There is a highly conserved YxxWxxxM sequence motif.", "domain_architectures": 255, "interpro_id": "IPR025314", "known_evidence_count": null, "matches": 1933, "name": "Domain of unknown function (DUF4219)", "partial_evidence_count": null, "pfam_id": "PF13961", "proteins": 1921, "proteomes": 439, "short_name": "DUF4219", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13961", "structures": 0, "taxa": 1546, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 400 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown. However, in many instances the domain lies upstream of a glycosyl hydrolase family, usually family 88, so it might be involved in carbohydrate binding.", "domain_architectures": 15, "interpro_id": "IPR032342", "known_evidence_count": null, "matches": 1922, "name": "Domain of unknown function (DUF4861)", "partial_evidence_count": null, "pfam_id": "PF16153", "proteins": 1918, "proteomes": 1255, "short_name": "DUF4861", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16153", "structures": 0, "taxa": 1860, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This region is found in Apolipophorin proteins.", "domain_architectures": 185, "interpro_id": "IPR009454", "known_evidence_count": null, "matches": 1920, "name": "Domain of Unknown Function (DUF1081)", "partial_evidence_count": null, "pfam_id": "PF06448", "proteins": 1912, "proteomes": 839, "short_name": "DUF1081", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06448", "structures": 8, "taxa": 3006, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 60 amino acids in length. The family is found in association with [pfam:PF00924].", "domain_architectures": 8, "interpro_id": "IPR022249", "known_evidence_count": null, "matches": 1907, "name": "Protein of unknown function (DUF3772)", "partial_evidence_count": null, "pfam_id": "PF12607", "proteins": 1907, "proteomes": 1883, "short_name": "DUF3772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12607", "structures": 0, "taxa": 2550, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1518, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a globular alpha/beta structure with similarity to papain-like cysteine proteinases fold.", "domain_architectures": 40, "interpro_id": "IPR061560", "known_evidence_count": null, "matches": 1967, "name": "Domain of unknown function (DUF8490)", "partial_evidence_count": null, "pfam_id": "PF28979", "proteins": 1900, "proteomes": 385, "short_name": "DUF8490", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28979", "structures": 0, "taxa": 1064, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1248, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Firmicutes. Several members are annotated as being the protein YaaL. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019644", "known_evidence_count": null, "matches": 1898, "name": "Protein of unknown function (DUF2508)", "partial_evidence_count": null, "pfam_id": "PF10704", "proteins": 1898, "proteomes": 1869, "short_name": "DUF2508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10704", "structures": 0, "taxa": 2721, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1223, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram-negative bacteria. Ir shares a significant similarity to the N-terminal domain of DNAA and it is predicted to adopt similar structure.", "domain_architectures": 10, "interpro_id": "IPR059483", "known_evidence_count": null, "matches": 1898, "name": "Domain of unknown function (DUF8439)", "partial_evidence_count": null, "pfam_id": "PF28557", "proteins": 1898, "proteomes": 1896, "short_name": "DUF8439", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28557", "structures": 0, "taxa": 2464, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1157, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR018635", "known_evidence_count": null, "matches": 1907, "name": "Uncharacterized protein conserved in bacteria (DUF2057)", "partial_evidence_count": null, "pfam_id": "PF09829", "proteins": 1895, "proteomes": 1258, "short_name": "DUF2057", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09829", "structures": 0, "taxa": 1771, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1695, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 103 and 119 amino acids in length. There is a conserved HPD sequence motif. There are two completely conserved residues (N and F) that may be functionally important.", "domain_architectures": 34, "interpro_id": "IPR028031", "known_evidence_count": null, "matches": 1895, "name": "Domain of unknown function (DUF4460)", "partial_evidence_count": null, "pfam_id": "PF14687", "proteins": 1894, "proteomes": 1336, "short_name": "DUF4460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14687", "structures": 5, "taxa": 4279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria, but the function is not known.", "domain_architectures": 2, "interpro_id": "IPR021732", "known_evidence_count": null, "matches": 1889, "name": "Protein of unknown function (DUF3301)", "partial_evidence_count": null, "pfam_id": "PF11743", "proteins": 1889, "proteomes": 1887, "short_name": "DUF3301", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11743", "structures": 0, "taxa": 2509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 100 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009872", "known_evidence_count": null, "matches": 1888, "name": "Protein of unknown function (DUF1427)", "partial_evidence_count": null, "pfam_id": "PF07235", "proteins": 1888, "proteomes": 1454, "short_name": "DUF1427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07235", "structures": 0, "taxa": 2089, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "The proteins in this family are around 140-170 residues in length. The proteins contain many conserved residues. with the most conserved motifs found in the central and C-terminal region. The function of these proteins is unknown.", "domain_architectures": 4, "interpro_id": "IPR005585", "known_evidence_count": null, "matches": 1889, "name": "Protein of unknown function (DUF327)", "partial_evidence_count": null, "pfam_id": "PF03885", "proteins": 1887, "proteomes": 1868, "short_name": "DUF327", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03885", "structures": 5, "taxa": 2782, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are about 260 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR016866", "known_evidence_count": null, "matches": 1896, "name": "Protein of unknown function (DUF3450)", "partial_evidence_count": null, "pfam_id": "PF11932", "proteins": 1886, "proteomes": 1315, "short_name": "DUF3450", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11932", "structures": 0, "taxa": 2082, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1175, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of nematode proteins of unknown function. However, it seems likely that these proteins act as aspartic peptidases.", "domain_architectures": 165, "interpro_id": "IPR008737", "known_evidence_count": null, "matches": 1890, "name": "Putative peptidase (DUF1758)", "partial_evidence_count": null, "pfam_id": "PF05585", "proteins": 1883, "proteomes": 193, "short_name": "DUF1758", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05585", "structures": 0, "taxa": 768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1296, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 10, "interpro_id": "IPR019270", "known_evidence_count": null, "matches": 1885, "name": "Protein of unknown function (DUF2283)", "partial_evidence_count": null, "pfam_id": "PF10049", "proteins": 1883, "proteomes": 1293, "short_name": "DUF2283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10049", "structures": 0, "taxa": 2844, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1217, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 333 and 377 amino acids in length. There is a conserved HEXXH sequence motif that is characteristic of metallopeptidases. This family may therefore belong to an as yet uncharacterised family of peptidase enzymes.", "domain_architectures": 4, "interpro_id": "IPR024294", "known_evidence_count": null, "matches": 1883, "name": "Protein of unknown function (DUF3810)", "partial_evidence_count": null, "pfam_id": "PF12725", "proteins": 1882, "proteomes": 1866, "short_name": "DUF3810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12725", "structures": 0, "taxa": 2633, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1018, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 4, "interpro_id": "IPR032025", "known_evidence_count": null, "matches": 1881, "name": "Domain of unknown function (DUF5063)", "partial_evidence_count": null, "pfam_id": "PF16702", "proteins": 1881, "proteomes": 1858, "short_name": "DUF5063", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16702", "structures": 1, "taxa": 2494, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1504, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain found in Fungi is functionally uncharacterised.", "domain_architectures": 44, "interpro_id": "IPR046497", "known_evidence_count": null, "matches": 1930, "name": "Family of unknown function (DUF6590)", "partial_evidence_count": null, "pfam_id": "PF20233", "proteins": 1879, "proteomes": 712, "short_name": "DUF6590", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20233", "structures": 0, "taxa": 1418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Enterobacterial proteins of around 212 residues in length and is known as YjfM in Escherichia coli. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009576", "known_evidence_count": null, "matches": 1888, "name": "Protein of unknown function (DUF1190)", "partial_evidence_count": null, "pfam_id": "PF06693", "proteins": 1878, "proteomes": 1720, "short_name": "DUF1190", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06693", "structures": 0, "taxa": 2548, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1186, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 3, "interpro_id": "IPR016936", "known_evidence_count": null, "matches": 2285, "name": "Uncharacterized protein conserved in bacteria (DUF2333)", "partial_evidence_count": null, "pfam_id": "PF10095", "proteins": 1877, "proteomes": 1835, "short_name": "DUF2333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10095", "structures": 0, "taxa": 2574, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 120 residues in length and is mainly found in various Pseudomonas species. Distant homology analysis suggests that proteins from this family are related to pilin type IV proteins from the Bundlin (PF05307) family, this prediction is however not confirmed by any experimental evidence", "domain_architectures": 3, "interpro_id": "IPR032314", "known_evidence_count": null, "matches": 1874, "name": "Domain of unknown function (DUF4845)", "partial_evidence_count": null, "pfam_id": "PF16137", "proteins": 1874, "proteomes": 1869, "short_name": "DUF4845", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16137", "structures": 0, "taxa": 2627, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 135 and 160 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR022207", "known_evidence_count": null, "matches": 1882, "name": "Protein of unknown function (DUF3736)", "partial_evidence_count": null, "pfam_id": "PF12540", "proteins": 1872, "proteomes": 789, "short_name": "DUF3736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12540", "structures": 0, "taxa": 2658, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 975, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from Actinomycete bacteria. Proteins in this family are around 280-300 residues in length.", "domain_architectures": 3, "interpro_id": "IPR058396", "known_evidence_count": null, "matches": 1883, "name": "Domain of unknown function (DUF8083)", "partial_evidence_count": null, "pfam_id": "PF26312", "proteins": 1872, "proteomes": 1862, "short_name": "DUF8083", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26312", "structures": 0, "taxa": 2132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small conserved sequence region found in a variety of largely mycobacterial phage proteins as well as bacterial proteins. It is often found N-terminal to [pfam:PF07498].", "domain_architectures": 9, "interpro_id": "IPR055642", "known_evidence_count": null, "matches": 1871, "name": "Family of unknown function (DUF7218)", "partial_evidence_count": null, "pfam_id": "PF23855", "proteins": 1871, "proteomes": 1833, "short_name": "DUF7218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23855", "structures": 0, "taxa": 2570, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family belong to the Alphaproteobacteria. The function of the family is not known.", "domain_architectures": 4, "interpro_id": "IPR019632", "known_evidence_count": null, "matches": 1868, "name": "Protein of unknown function (DUF2497)", "partial_evidence_count": null, "pfam_id": "PF10691", "proteins": 1868, "proteomes": 1860, "short_name": "DUF2497", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10691", "structures": 0, "taxa": 2663, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is approximately 80 amino acids in length.", "domain_architectures": 53, "interpro_id": "IPR025493", "known_evidence_count": null, "matches": 1875, "name": "Domain of unknown function (DUF4384)", "partial_evidence_count": null, "pfam_id": "PF14326", "proteins": 1868, "proteomes": 1066, "short_name": "DUF4384", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14326", "structures": 0, "taxa": 2135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 973, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046086", "known_evidence_count": null, "matches": 1867, "name": "Family of unknown function (DUF6104)", "partial_evidence_count": null, "pfam_id": "PF19599", "proteins": 1867, "proteomes": 1851, "short_name": "DUF6104", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19599", "structures": 0, "taxa": 2170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 135 and 1079 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR025512", "known_evidence_count": null, "matches": 1971, "name": "Domain of unknown function (DUF4399)", "partial_evidence_count": null, "pfam_id": "PF14347", "proteins": 1866, "proteomes": 1494, "short_name": "DUF4399", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14347", "structures": 0, "taxa": 2223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1077, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this entry are encoded within a conserved gene four-gene neighbourhood found sporadically in a phylogenetically broad range of bacteria including: Nocardia farcinica, Symbiobacterium thermophilum, and Streptomyces avermitilis (Actinobacteria), Geobacillus kaustophilus (Firmicutes), Azoarcus sp. EbN1 and Ralstonia solanacearum (Betaproteobacteria).", "domain_architectures": 5, "interpro_id": "IPR013493", "known_evidence_count": null, "matches": 1887, "name": "Protein of unknown function (DUF2397)", "partial_evidence_count": null, "pfam_id": "PF09660", "proteins": 1865, "proteomes": 1529, "short_name": "DUF2397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09660", "structures": 2, "taxa": 2311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1221, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of unknown function found in proteins from Bacteroidota. The domain is around 75-95 residues in length and adopts a helical structure. The domain is found primarily in Flavobacteriaceae, Bacteroidales and Cytophagales within the Bacteroidota phylum. The function of this domain remains to be determined.", "domain_architectures": 7, "interpro_id": "IPR061528", "known_evidence_count": null, "matches": 1868, "name": "Domain of unknown function (DUF8458)", "partial_evidence_count": null, "pfam_id": "PF28775", "proteins": 1864, "proteomes": 1862, "short_name": "DUF8458", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28775", "structures": 0, "taxa": 2465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1508, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to adopt a globular alpha/beta structure.", "domain_architectures": 36, "interpro_id": "IPR057228", "known_evidence_count": null, "matches": 1883, "name": "Domain of unknown function (DUF7906)", "partial_evidence_count": null, "pfam_id": "PF25483", "proteins": 1861, "proteomes": 414, "short_name": "DUF7906", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25483", "structures": 0, "taxa": 1196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1762, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes. There are highly conserved motifs: DxxxGR/KG, HxGN and GRFL; and three highly conserved residues: W, K and R at the C-terminal.", "domain_architectures": 67, "interpro_id": "IPR049227", "known_evidence_count": null, "matches": 1980, "name": "Domain of unknown function (DUF6824)", "partial_evidence_count": null, "pfam_id": "PF20710", "proteins": 1855, "proteomes": 22, "short_name": "DUF6824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20710", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 834, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a region of several plant proteins of unknown function. A C2H2 zinc finger is predicted in this region in some family members, but the spacing between the cysteine residues is not conserved throughout the family.", "domain_architectures": 78, "interpro_id": "IPR006865", "known_evidence_count": null, "matches": 2007, "name": "Protein of unknown function (DUF629)", "partial_evidence_count": null, "pfam_id": "PF04780", "proteins": 1843, "proteomes": 390, "short_name": "DUF629", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04780", "structures": 0, "taxa": 1126, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1096, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic and archaeal proteins, has no known function.", "domain_architectures": 4, "interpro_id": "IPR021125", "known_evidence_count": null, "matches": 1839, "name": "Predicted membrane protein (DUF2127)", "partial_evidence_count": null, "pfam_id": "PF09900", "proteins": 1839, "proteomes": 1737, "short_name": "DUF2127", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09900", "structures": 0, "taxa": 2601, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of paralogous hypothetical proteins identified in Rhodopirellula baltica that also has members in Gloeobacter violaceus, Sinorhizobium meliloti and Agrobacterium tumefaciens.", "domain_architectures": 10, "interpro_id": "IPR011473", "known_evidence_count": null, "matches": 1839, "name": "Protein of unknown function (DUF1579)", "partial_evidence_count": null, "pfam_id": "PF07617", "proteins": 1836, "proteomes": 1562, "short_name": "DUF1579", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07617", "structures": 0, "taxa": 2418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1035, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family consists of uncharacterized proteins around 175 residues in length and is mainly found in various Streptomyces species. The function of this family is unknown. This family is related to the NUDIX hydrolases.", "domain_architectures": 1, "interpro_id": "IPR032582", "known_evidence_count": null, "matches": 1836, "name": "Domain of unknown function (DUF4916)", "partial_evidence_count": null, "pfam_id": "PF16262", "proteins": 1836, "proteomes": 1807, "short_name": "DUF4916", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16262", "structures": 1, "taxa": 2149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein family has no known function. Its members are about 300 amino acids in length. It has so far been detected in Firmicute bacteria and some archaebacteria.", "domain_architectures": 8, "interpro_id": "IPR009343", "known_evidence_count": null, "matches": 1835, "name": "Protein of unknown function (DUF1002)", "partial_evidence_count": null, "pfam_id": "PF06207", "proteins": 1835, "proteomes": 1767, "short_name": "DUF1002", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06207", "structures": 0, "taxa": 2499, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1241, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 190 amino acids in length. This domain is found associated with [pfam:PF06808].", "domain_architectures": 5, "interpro_id": "IPR021814", "known_evidence_count": null, "matches": 1834, "name": "Domain of unknown function (DUF3394)", "partial_evidence_count": null, "pfam_id": "PF11874", "proteins": 1834, "proteomes": 1724, "short_name": "DUF3394", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11874", "structures": 0, "taxa": 2808, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 972, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an NTF2 superfamily domain found in a family of uncharacterised proteins from the Actinomycetota phylum, specifically within the Actinomycetes class. The family is predominantly found in Streptomycetaceae and Nocardiaceae families, with a notable presence in Streptomyces species. Proteins in this family are typically around 250-300 amino acids in length. Many members contain predicted transmembrane helices, suggesting they may be integral membrane proteins.", "domain_architectures": 2, "interpro_id": "IPR058488", "known_evidence_count": null, "matches": 1834, "name": "Domain of unknown function (DUF8175)", "partial_evidence_count": null, "pfam_id": "PF26526", "proteins": 1832, "proteomes": 1257, "short_name": "DUF8175", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26526", "structures": 0, "taxa": 1587, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is typically between 149 to 170 amino acids in length. This domain has a single completely conserved residue P that may be functionally important.", "domain_architectures": 10, "interpro_id": "IPR021913", "known_evidence_count": null, "matches": 1830, "name": "Domain of unknown function (DUF3526)", "partial_evidence_count": null, "pfam_id": "PF12040", "proteins": 1829, "proteomes": 841, "short_name": "DUF3526", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12040", "structures": 0, "taxa": 1336, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in metazoa. Proteins in this family are typically between 285 and 978 amino acids in length.", "domain_architectures": 25, "interpro_id": "IPR032013", "known_evidence_count": null, "matches": 1840, "name": "Domain of unknown function (DUF4795)", "partial_evidence_count": null, "pfam_id": "PF16043", "proteins": 1829, "proteomes": 891, "short_name": "DUF4795", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16043", "structures": 0, "taxa": 3036, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial and related archaeal protein of around 180 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009845", "known_evidence_count": null, "matches": 1826, "name": "Protein of unknown function (DUF1405)", "partial_evidence_count": null, "pfam_id": "PF07187", "proteins": 1825, "proteomes": 1608, "short_name": "DUF1405", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07187", "structures": 0, "taxa": 2166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1187, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small SH3-like beta-barrel domain found N-terminal to the Smr domain ([pfam:PF01713]) in DNA mismatch repair proteins from Bacteroidota. The domain is approximately 50 residues in length and is found predominantly in Flavobacteriaceae, Sphingobacteriaceae and Cytophagales families. The Smr domain itself is involved in DNA mismatch repair processes. The specific function of this N-terminal domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061535", "known_evidence_count": null, "matches": 1822, "name": "Domain of unknown function (DUF8465)", "partial_evidence_count": null, "pfam_id": "PF28803", "proteins": 1822, "proteomes": 1820, "short_name": "DUF8465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28803", "structures": 0, "taxa": 2357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 5, "interpro_id": "IPR018733", "known_evidence_count": null, "matches": 1820, "name": "Protein of unknown function (DUF2274)", "partial_evidence_count": null, "pfam_id": "PF10038", "proteins": 1820, "proteomes": 1110, "short_name": "DUF2274", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10038", "structures": 0, "taxa": 1769, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1193, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in bacteria.", "domain_architectures": 19, "interpro_id": "IPR043781", "known_evidence_count": null, "matches": 1821, "name": "Family of unknown function (DUF5723)", "partial_evidence_count": null, "pfam_id": "PF18990", "proteins": 1820, "proteomes": 1357, "short_name": "DUF5723", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18990", "structures": 0, "taxa": 1934, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 200 residues in length. The function of this family is unknown although some members are annotated as being putative integral membrane proteins.", "domain_architectures": 2, "interpro_id": "IPR009793", "known_evidence_count": null, "matches": 1820, "name": "Protein of unknown function (DUF1361)", "partial_evidence_count": null, "pfam_id": "PF07099", "proteins": 1816, "proteomes": 1715, "short_name": "DUF1361", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07099", "structures": 0, "taxa": 2719, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 922, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Proteins in this family are uncharacterised, but have been identified as members of a gene cluster for the synthesis of the tetramic-acid antibiotic streptolydigin, which inhibits bacterial RNA polymerase (RNAP) [[cite:PUB00039075]].", "domain_architectures": 5, "interpro_id": "IPR033458", "known_evidence_count": null, "matches": 1819, "name": "Domain of unknown function (DUF5134)", "partial_evidence_count": null, "pfam_id": "PF17197", "proteins": 1816, "proteomes": 1452, "short_name": "DUF5134", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17197", "structures": 0, "taxa": 1733, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a small alpha helical domain from a family of uncharacterised proteins in halobacteria. The domain is found in proteins from various archaea, particularly within the Halobacteriales order. The proteins containing this domain are typically around 70 to 80 amino acids in length. The domain shows a high degree of conservation across different species within the Halobacteriales, suggesting a potentially important but yet unidentified role.", "domain_architectures": 4, "interpro_id": "IPR058442", "known_evidence_count": null, "matches": 1816, "name": "Domain of unknown function (DUF8129)", "partial_evidence_count": null, "pfam_id": "PF26450", "proteins": 1816, "proteomes": 1440, "short_name": "DUF8129", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26450", "structures": 0, "taxa": 1838, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1047, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this entry are encoded within a conserved gene four-gene neighbourhood found sporadically in a phylogenetically broad range of bacteria including: Nocardia farcinica, Symbiobacterium thermophilum, and Streptomyces avermitilis (Actinobacteria), Geobacillus kaustophilus (Firmicutes), Azoarcus sp. EbN1 and Ralstonia solanacearum (Betaproteobacteria).", "domain_architectures": 4, "interpro_id": "IPR013494", "known_evidence_count": null, "matches": 1842, "name": "Protein of unknown function (DUF2398)", "partial_evidence_count": null, "pfam_id": "PF09661", "proteins": 1814, "proteomes": 1504, "short_name": "DUF2398", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09661", "structures": 2, "taxa": 2275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in a group of uncharacterised proteins mainly from plants and prokaryotes. According to structure predictions it adopts a sensor-like fold, consisting of 7 beta-strands arranged in a beta-barrel like fold, surrounded by a small alpha-helix.", "domain_architectures": 18, "interpro_id": "IPR057710", "known_evidence_count": null, "matches": 1834, "name": "Domain of unknown function (DUF7950)", "partial_evidence_count": null, "pfam_id": "PF25821", "proteins": 1814, "proteomes": 367, "short_name": "DUF7950", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25821", "structures": 0, "taxa": 1006, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1071, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of short proteins are functionally uncharacterized. This family is restricted to Alpha-, Beta- and Gamma-proteobacteria.", "domain_architectures": 4, "interpro_id": "IPR021762", "known_evidence_count": null, "matches": 1813, "name": "Protein of unknown function (DUF3325)", "partial_evidence_count": null, "pfam_id": "PF11804", "proteins": 1813, "proteomes": 1404, "short_name": "DUF3325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11804", "structures": 0, "taxa": 1957, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1415, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from both cyanobacteria and plants. Members of this family are typically around 250 residues in length. The function of this family is unknown but the species distribution indicates that the family may be involved in photosynthesis.", "domain_architectures": 31, "interpro_id": "IPR010765", "known_evidence_count": null, "matches": 2122, "name": "Protein of unknown function (DUF1350)", "partial_evidence_count": null, "pfam_id": "PF07082", "proteins": 1809, "proteomes": 724, "short_name": "DUF1350", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07082", "structures": 0, "taxa": 2020, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1074, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and eukaryotes, and is approximately 100 amino acids in length. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 25, "interpro_id": "IPR025117", "known_evidence_count": null, "matches": 1802, "name": "Domain of unknown function (DUF4037)", "partial_evidence_count": null, "pfam_id": "PF13228", "proteins": 1802, "proteomes": 1616, "short_name": "DUF4037", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13228", "structures": 0, "taxa": 2594, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 240, "interpro_id": "IPR025197", "known_evidence_count": null, "matches": 6590, "name": "Domain of unknown function (DUF4116)", "partial_evidence_count": null, "pfam_id": "PF13475", "proteins": 1802, "proteomes": 200, "short_name": "DUF4116", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13475", "structures": 0, "taxa": 595, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 206, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 1072 and 1090 amino acids in length.", "domain_architectures": 53, "interpro_id": "IPR022155", "known_evidence_count": null, "matches": 2075, "name": "Protein of unknown function (DUF3684)", "partial_evidence_count": null, "pfam_id": "PF12449", "proteins": 1798, "proteomes": 1341, "short_name": "DUF3684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12449", "structures": 0, "taxa": 2927, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1005, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 138 and 149 amino acids in length. There are two completely conserved residues (W and P) that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR025058", "known_evidence_count": null, "matches": 1798, "name": "Protein of unknown function (DUF3995)", "partial_evidence_count": null, "pfam_id": "PF13160", "proteins": 1798, "proteomes": 1620, "short_name": "DUF3995", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13160", "structures": 0, "taxa": 2350, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1529, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry is a region of approximately 100 residues containing three pairs of cysteine residues. The region is conserved from plants to humans but its function is unknown.", "domain_architectures": 28, "interpro_id": "IPR019351", "known_evidence_count": null, "matches": 1807, "name": "Uncharacterized conserved protein (DUF2039)", "partial_evidence_count": null, "pfam_id": "PF10217", "proteins": 1797, "proteomes": 1399, "short_name": "DUF2039", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10217", "structures": 0, "taxa": 4558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 873, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Pseudomonadaceae.", "domain_architectures": 1, "interpro_id": "IPR021245", "known_evidence_count": null, "matches": 1796, "name": "Protein of unknown function (DUF2790)", "partial_evidence_count": null, "pfam_id": "PF10976", "proteins": 1796, "proteomes": 395, "short_name": "DUF2790", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10976", "structures": 1, "taxa": 456, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and archaea, and is approximately 100 amino acids in length. Shows sequence similarity to the RAMA domain [pfam:PF18755] which suggests this may be a DNA-binding domain.", "domain_architectures": 40, "interpro_id": "IPR025579", "known_evidence_count": null, "matches": 1806, "name": "Domain of unknown function (DUF4357)", "partial_evidence_count": null, "pfam_id": "PF14267", "proteins": 1796, "proteomes": 1689, "short_name": "DUF4357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14267", "structures": 0, "taxa": 3238, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1538, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This is a 100 residue conserved region of a family of proteins found from fungi to humans. This region contains three conserved Cysteines and a motif of {CP}{y/l}{HG}.", "domain_architectures": 25, "interpro_id": "IPR049431", "known_evidence_count": null, "matches": 1797, "name": "Uncharacterized conserved protein (DUF2043)", "partial_evidence_count": null, "pfam_id": "PF09740", "proteins": 1795, "proteomes": 1342, "short_name": "DUF2043", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09740", "structures": 11, "taxa": 4255, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1447, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain represents a conserved region that has a UBA like fold. It is found in a number of plant proteins of unknown function.", "domain_architectures": 20, "interpro_id": "IPR010820", "known_evidence_count": null, "matches": 1795, "name": "UBA-like domain (DUF1421)", "partial_evidence_count": null, "pfam_id": "PF07223", "proteins": 1794, "proteomes": 422, "short_name": "DUF1421", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07223", "structures": 0, "taxa": 1171, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length. These proteins are integral membrane proteins.", "domain_architectures": 1, "interpro_id": "IPR023804", "known_evidence_count": null, "matches": 1794, "name": "Protein of unknown function (DUF3792)", "partial_evidence_count": null, "pfam_id": "PF12670", "proteins": 1794, "proteomes": 1758, "short_name": "DUF3792", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12670", "structures": 0, "taxa": 2574, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1455, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. This domain has similarity to BAH domains.", "domain_architectures": 19, "interpro_id": "IPR061652", "known_evidence_count": null, "matches": 1796, "name": "Domain of unknown function (DUF8591)", "partial_evidence_count": null, "pfam_id": "PF29852", "proteins": 1794, "proteomes": 191, "short_name": "DUF8591", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29852", "structures": 0, "taxa": 505, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is approximately 60 amino acids in length. This domain is likely to adopt an OB-fold based on similarity to other families.", "domain_architectures": 47, "interpro_id": "IPR043724", "known_evidence_count": null, "matches": 3764, "name": "Domain of unknown function (DUF5666)", "partial_evidence_count": null, "pfam_id": "PF18914", "proteins": 1791, "proteomes": 1456, "short_name": "DUF5666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18914", "structures": 0, "taxa": 2460, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of SpoIID-like amidase enhancer proteins. It follows the SpoIID/LytB domain ([pfam:PF08486]) which is involved in peptidoglycan degradation. In Synechocystis sp. PCC 6803, the protein Slr0191 is annotated as a cell wall hydrolase and has been localised to the thylakoid membrane and periplasm. In Fibrobacter succinogenes, the homologue Fisuc_2398 shows increased expression in the presence of cellulose. The family is found in Cyanobacteriota, Bacillota and Bacteroidota. The specific function of this C-terminal domain remains to be determined.", "domain_architectures": 48, "interpro_id": "IPR061679", "known_evidence_count": null, "matches": 1795, "name": "Domain of unknown function (DUF8618)", "partial_evidence_count": null, "pfam_id": "PF30488", "proteins": 1790, "proteomes": 1447, "short_name": "DUF8618", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30488", "structures": 0, "taxa": 2886, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1041, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are bacterial hypothetical proteins, about 160 amino acids in length, found in various proteobacteria, including members of the genera Pseudomonas and Vibrio. The C-terminal region is poorly conserved and is not included in the model.", "domain_architectures": 6, "interpro_id": "IPR012659", "known_evidence_count": null, "matches": 1784, "name": "Protein of unknown function (DUF2390)", "partial_evidence_count": null, "pfam_id": "PF09523", "proteins": 1784, "proteomes": 1770, "short_name": "DUF2390", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09523", "structures": 0, "taxa": 2427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 526, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 110 amino acids in length.", "domain_architectures": 83, "interpro_id": "IPR021885", "known_evidence_count": null, "matches": 1811, "name": "Domain of unknown function (DUF3496)", "partial_evidence_count": null, "pfam_id": "PF12001", "proteins": 1781, "proteomes": 515, "short_name": "DUF3496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12001", "structures": 0, "taxa": 1772, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the second domain found in bacterial DNA primases, positioned between the N-terminal zinc ribbon domain ([pfam:PF01807]) and the C-terminal Toprim domain ([pfam:PF13155]). This domain is approximately 65-70 amino acids in length and is found predominantly in DNA primases from Bacteroidota species, particularly members of the Bacteroidales order. DNA primase (DnaG) synthesises RNA primers that are utilised by DNA polymerase during bacterial chromosomal DNA replication. The specific function of this middle domain remains to be determined, but its conservation suggests it plays an important structural or functional role in primase activity within these bacteria.", "domain_architectures": 11, "interpro_id": "IPR061534", "known_evidence_count": null, "matches": 1783, "name": "Domain of unknown function (DUF8464)", "partial_evidence_count": null, "pfam_id": "PF28801", "proteins": 1781, "proteomes": 828, "short_name": "DUF8464", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28801", "structures": 0, "taxa": 1200, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1376, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is ubiquitously found in one or multiple tandem copies. It has a detectable similarity to known NTF2-like domains and it is predicted to fold into a similar structure. When found in tandem, two copies pack on each other forming a barrel like structure.", "domain_architectures": 23, "interpro_id": "IPR058334", "known_evidence_count": null, "matches": 1842, "name": "Domain of unknown function (DUF8021)", "partial_evidence_count": null, "pfam_id": "PF26061", "proteins": 1780, "proteomes": 676, "short_name": "DUF8021", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26061", "structures": 0, "taxa": 1183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 975, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical, putative lipoproteins of around 80 residues in length. Members of this family seem to be specific to the Class Gammaproteobacteria. The function of this family is unknown.", "domain_architectures": 6, "interpro_id": "IPR010780", "known_evidence_count": null, "matches": 1779, "name": "Protein of unknown function (DUF1375)", "partial_evidence_count": null, "pfam_id": "PF07119", "proteins": 1779, "proteomes": 1106, "short_name": "DUF1375", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07119", "structures": 0, "taxa": 1557, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1046, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins have no known function.", "domain_architectures": 5, "interpro_id": "IPR020311", "known_evidence_count": null, "matches": 1778, "name": "Protein of unknown function (DUF2630)", "partial_evidence_count": null, "pfam_id": "PF10944", "proteins": 1778, "proteomes": 1693, "short_name": "DUF2630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10944", "structures": 0, "taxa": 2117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1556, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a group of animal membrane proteins, including human Membrane protein FAM174B, which is essential for Golgi structural integrity [[cite:PUB00151893]].", "domain_architectures": 11, "interpro_id": "", "known_evidence_count": null, "matches": 1781, "name": "Membrane protein FAM174-like", "partial_evidence_count": null, "pfam_id": "PF06679", "proteins": 1774, "proteomes": 910, "short_name": "DUF1180", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06679", "structures": 0, "taxa": 3108, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1047, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 147 and 227 amino acids in length. [swissprot:Q50763] is incorrectly annotated as the KatG protein.", "domain_architectures": 7, "interpro_id": "IPR025358", "known_evidence_count": null, "matches": 1773, "name": "Domain of unknown function (DUF4262)", "partial_evidence_count": null, "pfam_id": "PF14081", "proteins": 1773, "proteomes": 1500, "short_name": "DUF4262", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14081", "structures": 0, "taxa": 2295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 455, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "The function of this protein domain family is yet to be characterised. It is putatively thought to lie in the C-terminal domain of the DNA nucleotide repair protein, Xeroderma pigmentosa complementation group A (XPA). The function of XPA is to bind to DNA and repair any mismatched base pairs. This domain family is often found in eukaryotes, and is approximately 70 amino acids in length. There is a conserved DPE sequence motif. In humans, this protein is encoded for in the chromosomal position, Chromosome 5 open reading frame 65. Mutations in the gene lead to myelodysplastic syndromes, where there is inefficient stem cell production in the bone marrow. This suggests that the protein may have a role in forming blood cells [[cite:PUB00067380]].", "domain_architectures": 10, "interpro_id": "IPR027838", "known_evidence_count": null, "matches": 1772, "name": "Domain of unknown function (DUF4585)", "partial_evidence_count": null, "pfam_id": "PF15232", "proteins": 1772, "proteomes": 702, "short_name": "DUF4585", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15232", "structures": 0, "taxa": 2139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1448, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a short, 30 residue domain, from a family of proteins conserved in fungi. The function is unknown. There is a characteristic DLL sequence motif.", "domain_architectures": 39, "interpro_id": "IPR019417", "known_evidence_count": null, "matches": 1772, "name": "Uncharacterised protein domain (DUF2415)", "partial_evidence_count": null, "pfam_id": "PF10313", "proteins": 1771, "proteomes": 1508, "short_name": "DUF2415", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10313", "structures": 0, "taxa": 3399, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1247, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain of unknown function has a PLP-dependent transferase-like fold. Its genomic context suggests that it may have a role in anaerobic vitamin B12 biosynthesis. This domain is often found at the C-terminus of proteins containing DUF4213, [pfam:PF13938]. The structure of UnioProtKB:B8FUJ5, PDB:3l5o, suggests that the protein has an enolase N-terminal-like fold and this Rossmann-like C-terminal domain. Structural and bioinformatic analyses reveal partial similarities to Rossmann-like methyltransferases, with residues from the enolase-like fold combining to form a unique active site that is likely to be involved in the condensation or hydrolysis of molecules implicated in the synthesis of flavins, pterins or other siderophores. The protein may be playing a role in heavy-metal chelation [[cite:PUB00075371]].", "domain_architectures": 6, "interpro_id": "IPR007161", "known_evidence_count": null, "matches": 1766, "name": "Putative heavy-metal chelation", "partial_evidence_count": null, "pfam_id": "PF04016", "proteins": 1766, "proteomes": 1491, "short_name": "DUF364", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04016", "structures": 2, "taxa": 2706, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1389, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Predicted transmembrane protein found in plants, chloroplasts and cyanobacteria. This family is also known as YCF20.", "domain_architectures": 30, "interpro_id": "IPR007572", "known_evidence_count": null, "matches": 1767, "name": "Protein of unknown function (DUF565)", "partial_evidence_count": null, "pfam_id": "PF04483", "proteins": 1766, "proteomes": 652, "short_name": "DUF565", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04483", "structures": 0, "taxa": 1855, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1362, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised metazoan proteins. This domain has similarity to BAH domains.", "domain_architectures": 38, "interpro_id": "IPR061653", "known_evidence_count": null, "matches": 1763, "name": "Domain of unknown function (DUF8592)", "partial_evidence_count": null, "pfam_id": "PF29857", "proteins": 1763, "proteomes": 195, "short_name": "DUF8592", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29857", "structures": 0, "taxa": 897, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This small domain of about 70 residues is found in a number of bacterial proteins. It is found at the N-terminus the of [swissprot:O28332] protein. The proteins containing this domain are uncharacterised.", "domain_architectures": 23, "interpro_id": "IPR005590", "known_evidence_count": null, "matches": 1856, "name": "Domain of unknown function (DUF333)", "partial_evidence_count": null, "pfam_id": "PF03891", "proteins": 1760, "proteomes": 1423, "short_name": "DUF333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03891", "structures": 0, "taxa": 2223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1485, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 234 and 351 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR031959", "known_evidence_count": null, "matches": 1800, "name": "Domain of unknown function (DUF4779)", "partial_evidence_count": null, "pfam_id": "PF16009", "proteins": 1760, "proteomes": 258, "short_name": "DUF4779", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16009", "structures": 0, "taxa": 979, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 952, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 110 amino acids in length.", "domain_architectures": 31, "interpro_id": "IPR025349", "known_evidence_count": null, "matches": 1759, "name": "Domain of unknown function (DUF4253)", "partial_evidence_count": null, "pfam_id": "PF14062", "proteins": 1759, "proteomes": 1459, "short_name": "DUF4253", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14062", "structures": 0, "taxa": 2236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in a group of plant sequences, whose function is unknown. This domain may adopt a three-helical bundle fold similar to that found in viral Gag proteins.", "domain_architectures": 197, "interpro_id": "IPR056648", "known_evidence_count": null, "matches": 1783, "name": "Domain of unknown function (DUF7746)", "partial_evidence_count": null, "pfam_id": "PF24925", "proteins": 1759, "proteomes": 95, "short_name": "DUF7746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24925", "structures": 0, "taxa": 370, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021338", "known_evidence_count": null, "matches": 1755, "name": "Protein of unknown function (DUF2953)", "partial_evidence_count": null, "pfam_id": "PF11167", "proteins": 1755, "proteomes": 1681, "short_name": "DUF2953", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11167", "structures": 0, "taxa": 2514, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 279 and 322 amino acids in length.", "domain_architectures": 27, "interpro_id": "IPR025131", "known_evidence_count": null, "matches": 1883, "name": "Protein of unknown function (DUF4057)", "partial_evidence_count": null, "pfam_id": "PF13266", "proteins": 1755, "proteomes": 381, "short_name": "DUF4057", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13266", "structures": 0, "taxa": 1069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1098, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins have no known function.", "domain_architectures": 2, "interpro_id": "IPR021249", "known_evidence_count": null, "matches": 1753, "name": "Protein of unknown function (DUF2788)", "partial_evidence_count": null, "pfam_id": "PF10981", "proteins": 1752, "proteomes": 1747, "short_name": "DUF2788", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10981", "structures": 0, "taxa": 2235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function. It occurs as a fusion of ZnR+HTH+SHOCT-like.", "domain_architectures": 4, "interpro_id": "IPR018658", "known_evidence_count": null, "matches": 1748, "name": "Domain of unknown function (DUF2089)-HTH", "partial_evidence_count": null, "pfam_id": "PF09862", "proteins": 1748, "proteomes": 1611, "short_name": "DUF2089", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09862", "structures": 0, "taxa": 2826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1194, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Proteobacteria.", "domain_architectures": 4, "interpro_id": "IPR021335", "known_evidence_count": null, "matches": 1754, "name": "Protein of unknown function (DUF2948)", "partial_evidence_count": null, "pfam_id": "PF11164", "proteins": 1747, "proteomes": 1745, "short_name": "DUF2948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11164", "structures": 0, "taxa": 2428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Firmicutes but also in Actinobacteria and Halobacteria. Members of this family are thought to be DUF1648 domain-containing proteins as they are membrane-components.", "domain_architectures": 7, "interpro_id": "IPR043831", "known_evidence_count": null, "matches": 1747, "name": "Family of unknown function (DUF5808)", "partial_evidence_count": null, "pfam_id": "PF19124", "proteins": 1747, "proteomes": 1627, "short_name": "DUF5808", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19124", "structures": 0, "taxa": 2535, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 857, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000877) is described by MIBiG as an example of the following biosynthetic class, other (unspecified), in particular the polyoxin A biosynthetic gene cluster from Streptomyces cacaoi subsp. asoensis [[cite:PUB00098986]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR046306", "known_evidence_count": null, "matches": 1747, "name": "Family of unknown function (DUF6421)", "partial_evidence_count": null, "pfam_id": "PF19985", "proteins": 1746, "proteomes": 1649, "short_name": "DUF6421", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19985", "structures": 7, "taxa": 1944, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 993, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 115 residues in length. Members of this family are found in Bacillus species and Streptomyces coelicolor, the function of the family is unknown.", "domain_architectures": 3, "interpro_id": "IPR010773", "known_evidence_count": null, "matches": 1745, "name": "Protein of unknown function (DUF1360)", "partial_evidence_count": null, "pfam_id": "PF07098", "proteins": 1745, "proteomes": 1575, "short_name": "DUF1360", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07098", "structures": 0, "taxa": 2166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1441, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 209 and 938 amino acids in length. There is a conserved WCF sequence motif. There is a single completely conserved residue W that may be functionally important.", "domain_architectures": 30, "interpro_id": "IPR027902", "known_evidence_count": null, "matches": 1876, "name": "Domain of unknown function (DUF4487)", "partial_evidence_count": null, "pfam_id": "PF14868", "proteins": 1745, "proteomes": 1084, "short_name": "DUF4487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14868", "structures": 0, "taxa": 3597, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is sometimes associated with a helix-turn-helix domain suggesting that it may be a small molecule ligand binding domain. This family of proteins is found in bacteria.", "domain_architectures": 10, "interpro_id": "IPR045599", "known_evidence_count": null, "matches": 1746, "name": "Domain of unknown function (DUF6456)", "partial_evidence_count": null, "pfam_id": "PF20057", "proteins": 1745, "proteomes": 1714, "short_name": "DUF6456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20057", "structures": 0, "taxa": 2324, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains sequences covering an approximately 270 amino acid stretch of a group of hypothetical proteins. These proteins are expressed by archaeal species of the Methanosarcina genus.", "domain_architectures": 27, "interpro_id": "IPR012437", "known_evidence_count": null, "matches": 1743, "name": "Protein of unknown function (DUF1638)", "partial_evidence_count": null, "pfam_id": "PF07796", "proteins": 1741, "proteomes": 1383, "short_name": "DUF1638", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07796", "structures": 0, "taxa": 2446, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1075, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "DUF3892 is related to the truncated RNaseH fold-containing ribosome hibernation factors. Predicted to function as a possible conflict effector domain at the ribosome, based on comparable genome contextual associations with DUF2188, including repeated association with nucleotide-activated effector conflict systems [[cite:PUB00097693]].", "domain_architectures": 6, "interpro_id": "IPR024997", "known_evidence_count": null, "matches": 1741, "name": "Protein of unknown function (DUF3892)", "partial_evidence_count": null, "pfam_id": "PF13031", "proteins": 1741, "proteomes": 1554, "short_name": "DUF3892", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13031", "structures": 0, "taxa": 2543, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 973, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 118 and 145 amino acids in length.", "domain_architectures": 14, "interpro_id": "IPR025355", "known_evidence_count": null, "matches": 1744, "name": "Domain of unknown function (DUF4259)", "partial_evidence_count": null, "pfam_id": "PF14078", "proteins": 1741, "proteomes": 1469, "short_name": "DUF4259", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14078", "structures": 0, "taxa": 2227, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1067, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 3, "interpro_id": "IPR018743", "known_evidence_count": null, "matches": 1785, "name": "Uncharacterized small protein (DUF2292)", "partial_evidence_count": null, "pfam_id": "PF10055", "proteins": 1739, "proteomes": 1530, "short_name": "DUF2292", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10055", "structures": 0, "taxa": 2165, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1372, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in uncharacterised membrane proteins from plants. The domain is restricted to eudicots, specifically to the rosid clade, and is found in families including Rosaceae (roses, apples), Salicaceae (willows, poplars), and Malvaceae. The proteins containing this domain are predicted to be membrane associated. The function of this domain remains to be determined. This domain contains an helical fold.", "domain_architectures": 41, "interpro_id": "IPR061783", "known_evidence_count": null, "matches": 1876, "name": "Domain of unknown function (DUF8722)", "partial_evidence_count": null, "pfam_id": "PF30749", "proteins": 1739, "proteomes": 194, "short_name": "DUF8722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30749", "structures": 1, "taxa": 505, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1099, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 5, "interpro_id": "IPR021425", "known_evidence_count": null, "matches": 1778, "name": "Protein of unknown function (DUF3072)", "partial_evidence_count": null, "pfam_id": "PF11272", "proteins": 1738, "proteomes": 1662, "short_name": "DUF3072", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11272", "structures": 0, "taxa": 2372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 190 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032577", "known_evidence_count": null, "matches": 1738, "name": "Domain of unknown function (DUF4920)", "partial_evidence_count": null, "pfam_id": "PF16267", "proteins": 1738, "proteomes": 1688, "short_name": "DUF4920", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16267", "structures": 0, "taxa": 2304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised metazoan proteins. It is predicted to adopt a globular structure with lipocalin fold. It also contains several highly conserved cysteine residues that are likely involved in the formation of intra-domain disulfide bridges.", "domain_architectures": 68, "interpro_id": "IPR055471", "known_evidence_count": null, "matches": 1785, "name": "Domain of unknown function (DUF7043)", "partial_evidence_count": null, "pfam_id": "PF23070", "proteins": 1738, "proteomes": 465, "short_name": "DUF7043", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23070", "structures": 0, "taxa": 1666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 666, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in vertebrates. This family includes the human protein C10orf12.", "domain_architectures": 7, "interpro_id": "IPR028104", "known_evidence_count": null, "matches": 1748, "name": "Domain of unknown function (DUF4553)", "partial_evidence_count": null, "pfam_id": "PF15090", "proteins": 1737, "proteomes": 727, "short_name": "DUF4553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15090", "structures": 0, "taxa": 2206, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1043, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and archaea, and is approximately 80 amino acids in length.", "domain_architectures": 27, "interpro_id": "IPR025485", "known_evidence_count": null, "matches": 1784, "name": "Domain of unknown function (DUF4377)", "partial_evidence_count": null, "pfam_id": "PF14302", "proteins": 1734, "proteomes": 1513, "short_name": "DUF4377", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14302", "structures": 0, "taxa": 2239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 977, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "One member in this family is annotated as yrdB which is part of a four gene operon however currently no function is known.", "domain_architectures": 2, "interpro_id": "IPR021214", "known_evidence_count": null, "matches": 1729, "name": "Protein of unknown function (DUF2568)", "partial_evidence_count": null, "pfam_id": "PF10823", "proteins": 1729, "proteomes": 1634, "short_name": "DUF2568", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10823", "structures": 0, "taxa": 2214, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein family. Structure prediction suggests that these proteins form a membrane bound octameric complex. The N-terminus of the protein contains an transmembrane alpha helix and the rest of the protein adopts a four helical bundle domain. This family is often found associated with gliding motility proteins in STRING networks.", "domain_architectures": 1, "interpro_id": "IPR057695", "known_evidence_count": null, "matches": 1729, "name": "Family of unknown function (DUF7935)", "partial_evidence_count": null, "pfam_id": "PF25589", "proteins": 1729, "proteomes": 1727, "short_name": "DUF7935", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25589", "structures": 0, "taxa": 2233, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1082, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins which seem to be found exclusively in Rhizobium and Ralstonia species. Members of this family are typically around 210 residues in length and contain 5 highly conserved cysteine residues at their N-terminus. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009758", "known_evidence_count": null, "matches": 1728, "name": "Protein of unknown function (DUF1326)", "partial_evidence_count": null, "pfam_id": "PF07040", "proteins": 1728, "proteomes": 1401, "short_name": "DUF1326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07040", "structures": 0, "taxa": 2267, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterized proteins. They are predicted to adopt a globular structure that resembles the conserved core of the PPPDE superfamily (after Permuted Papain fold Peptidases of DsRNA viruses and Eukaryotes) consisting of thiol peptidases with a circularly permuted papain-like fold.", "domain_architectures": 28, "interpro_id": "IPR054208", "known_evidence_count": null, "matches": 1760, "name": "Family of unknown function (DUF6914)", "partial_evidence_count": null, "pfam_id": "PF21858", "proteins": 1727, "proteomes": 741, "short_name": "DUF6914", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21858", "structures": 0, "taxa": 1599, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1085, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as transmembrane proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 4, "interpro_id": "IPR021455", "known_evidence_count": null, "matches": 1734, "name": "Protein of unknown function (DUF3106)", "partial_evidence_count": null, "pfam_id": "PF11304", "proteins": 1726, "proteomes": 1517, "short_name": "DUF3106", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11304", "structures": 0, "taxa": 2267, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1582, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This entry represents the HTH domain found in group of uncharacterised archaeal proteins.", "domain_architectures": 27, "interpro_id": "IPR055767", "known_evidence_count": null, "matches": 1726, "name": "Domain of unknown function (DUF7343)", "partial_evidence_count": null, "pfam_id": "PF24034", "proteins": 1726, "proteomes": 597, "short_name": "DUF7343", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24034", "structures": 0, "taxa": 1135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1001, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. Some members annotate the proteins as the permease component of a Mn2+/Zn2+ transport system however this cannot be confirmed.", "domain_architectures": 9, "interpro_id": "IPR021306", "known_evidence_count": null, "matches": 1723, "name": "Protein of unknown function (DUF2878)", "partial_evidence_count": null, "pfam_id": "PF11086", "proteins": 1722, "proteomes": 1693, "short_name": "DUF2878", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11086", "structures": 0, "taxa": 2363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1487, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of small proteins of approximately 150 amino acids of unknown function.", "domain_architectures": 23, "interpro_id": "IPR018794", "known_evidence_count": null, "matches": 1750, "name": "Uncharacterized conserved protein (DUF2340)", "partial_evidence_count": null, "pfam_id": "PF10209", "proteins": 1721, "proteomes": 1406, "short_name": "DUF2340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10209", "structures": 0, "taxa": 3975, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 972, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins.", "domain_architectures": 4, "interpro_id": "IPR015068", "known_evidence_count": null, "matches": 1724, "name": "Domain of unknown function (DUF1877)", "partial_evidence_count": null, "pfam_id": "PF08974", "proteins": 1720, "proteomes": 1368, "short_name": "DUF1877", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08974", "structures": 1, "taxa": 2259, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria. Several members are described as being putative lipoproteins, but otherwise the function is not known.", "domain_architectures": 11, "interpro_id": "IPR021323", "known_evidence_count": null, "matches": 1721, "name": "Protein of unknown function (DUF2927)", "partial_evidence_count": null, "pfam_id": "PF11150", "proteins": 1720, "proteomes": 1137, "short_name": "DUF2927", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11150", "structures": 0, "taxa": 1799, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family contains many hypothetical proteins from bacteria and yeast.", "domain_architectures": 11, "interpro_id": "IPR012550", "known_evidence_count": null, "matches": 1719, "name": "Protein of unknown function (DUF1706)", "partial_evidence_count": null, "pfam_id": "PF08020", "proteins": 1718, "proteomes": 1554, "short_name": "DUF1706", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08020", "structures": 9, "taxa": 2726, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a presumed domain found at the N-terminal of the uncharacterised protein K02A2.6 from C.elegans and similar worm sequences. This domain may adopt a fold similar to retrotransposons.", "domain_architectures": 151, "interpro_id": "IPR055510", "known_evidence_count": null, "matches": 1723, "name": "Domain of unknown function (DUF7083)", "partial_evidence_count": null, "pfam_id": "PF23309", "proteins": 1718, "proteomes": 110, "short_name": "DUF7083", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23309", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1528, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 310 amino acids in length.", "domain_architectures": 28, "interpro_id": "IPR027989", "known_evidence_count": null, "matches": 1755, "name": "Domain of unknown function (DUF4461)", "partial_evidence_count": null, "pfam_id": "PF14688", "proteins": 1717, "proteomes": 1217, "short_name": "DUF4461", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14688", "structures": 1, "taxa": 3983, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1133, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 160 residues in length. Members of this family contain four highly conserved cysteine resides toward the C-terminal region of the protein.", "domain_architectures": 6, "interpro_id": "IPR009912", "known_evidence_count": null, "matches": 1716, "name": "Zinc-ribbon containing domain", "partial_evidence_count": null, "pfam_id": "PF07295", "proteins": 1716, "proteomes": 1679, "short_name": "DUF1451", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07295", "structures": 0, "taxa": 2559, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1089, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a bacterial protein family of unknown function. Proteins in this family adopt an alpha helical structure. Genome context analysis has suggested a high probability of a functional association with histidine kinases, which implicates proteins in this family to play a role in signalling (information from TOPSAN 2Q9R).", "domain_architectures": 4, "interpro_id": "IPR007338", "known_evidence_count": null, "matches": 1714, "name": "Protein of unknown function (DUF416)", "partial_evidence_count": null, "pfam_id": "PF04222", "proteins": 1714, "proteomes": 1695, "short_name": "DUF416", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04222", "structures": 2, "taxa": 2489, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1087, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 190 residues in length. Several members of this family are annotated as being putative lipoproteins and are often known as YceB. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR010835", "known_evidence_count": null, "matches": 1714, "name": "Protein of unknown function (DUF1439)", "partial_evidence_count": null, "pfam_id": "PF07273", "proteins": 1714, "proteomes": 1579, "short_name": "DUF1439", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07273", "structures": 1, "taxa": 2176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are approximately 110 amino acids in length. There is a conserved RSKN sequence motif.", "domain_architectures": 25, "interpro_id": "IPR025496", "known_evidence_count": null, "matches": 1714, "name": "Domain of unknown function (DUF4387)", "partial_evidence_count": null, "pfam_id": "PF14330", "proteins": 1713, "proteomes": 1364, "short_name": "DUF4387", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14330", "structures": 2, "taxa": 2670, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 752, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 100 and 162 amino acids in length. There are two completely conserved residues (P and C) that may be functionally important.", "domain_architectures": 42, "interpro_id": "IPR025475", "known_evidence_count": null, "matches": 1711, "name": "Domain of unknown function (DUF4326)", "partial_evidence_count": null, "pfam_id": "PF14216", "proteins": 1711, "proteomes": 1466, "short_name": "DUF4326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14216", "structures": 0, "taxa": 3226, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1039, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 250 amino acids in length. This domain is found associated with [pfam:PF00884].", "domain_architectures": 3, "interpro_id": "IPR024588", "known_evidence_count": null, "matches": 1710, "name": "Domain of unknown function (DUF3413)", "partial_evidence_count": null, "pfam_id": "PF11893", "proteins": 1710, "proteomes": 1536, "short_name": "DUF3413", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11893", "structures": 6, "taxa": 2262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 80 amino acids in length. The family is found in association with [pfam:PF01609]. There is a single completely conserved residue G that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR025399", "known_evidence_count": null, "matches": 1710, "name": "Domain of unknown function (DUF4372)", "partial_evidence_count": null, "pfam_id": "PF14294", "proteins": 1710, "proteomes": 815, "short_name": "DUF4372", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14294", "structures": 0, "taxa": 1725, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of DUF2834 is not clear.", "domain_architectures": 6, "interpro_id": "IPR021362", "known_evidence_count": null, "matches": 1715, "name": "Protein of unknown function DUF2834", "partial_evidence_count": null, "pfam_id": "PF11196", "proteins": 1709, "proteomes": 1576, "short_name": "DUF2834", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11196", "structures": 0, "taxa": 2672, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 450 amino acids in length. There are two conserved sequence motifs: DVF and SPNGED.", "domain_architectures": 11, "interpro_id": "IPR020958", "known_evidence_count": null, "matches": 1720, "name": "ATPase involved in DNA repair", "partial_evidence_count": null, "pfam_id": "PF12458", "proteins": 1708, "proteomes": 1695, "short_name": "DUF3686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12458", "structures": 0, "taxa": 2410, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 6, "interpro_id": "IPR021274", "known_evidence_count": null, "matches": 1695, "name": "Protein of unknown function (DUF2853)", "partial_evidence_count": null, "pfam_id": "PF11015", "proteins": 1695, "proteomes": 1631, "short_name": "DUF2853", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11015", "structures": 1, "taxa": 2294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1070, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 234 and 251 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046703", "known_evidence_count": null, "matches": 1698, "name": "Family of unknown function (DUF6776)", "partial_evidence_count": null, "pfam_id": "PF20567", "proteins": 1695, "proteomes": 1562, "short_name": "DUF6776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20567", "structures": 0, "taxa": 2239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a three-helical bundle with some topological similarity to spectrin.", "domain_architectures": 12, "interpro_id": "IPR057224", "known_evidence_count": null, "matches": 1694, "name": "Domain of unknown function (DUF7902)", "partial_evidence_count": null, "pfam_id": "PF25472", "proteins": 1694, "proteomes": 1688, "short_name": "DUF7902", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25472", "structures": 0, "taxa": 2393, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1452, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 198 and 469 amino acids in length. There are two completely conserved L residues that may be functionally important.", "domain_architectures": 21, "interpro_id": "IPR032777", "known_evidence_count": null, "matches": 1706, "name": "Domain of unknown function (DUF4515)", "partial_evidence_count": null, "pfam_id": "PF14988", "proteins": 1691, "proteomes": 740, "short_name": "DUF4515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14988", "structures": 0, "taxa": 2474, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 400 residues in length and is mainly found in various Bacteroides species, such as Bacteroides fragilis and Bacteroides sp.These proteins adopt a six stranded beta-propeller domain. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032558", "known_evidence_count": null, "matches": 1687, "name": "Domain of unknown function (DUF4934)", "partial_evidence_count": null, "pfam_id": "PF16288", "proteins": 1687, "proteomes": 319, "short_name": "DUF4934", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16288", "structures": 0, "taxa": 524, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1068, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is composed of a group of large bacterial integral membrane proteins that likely have a transporter function.", "domain_architectures": 6, "interpro_id": "IPR046671", "known_evidence_count": null, "matches": 1743, "name": "Family of unknown function (DUF6541)", "partial_evidence_count": null, "pfam_id": "PF20176", "proteins": 1685, "proteomes": 1221, "short_name": "DUF6541", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20176", "structures": 0, "taxa": 1645, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1385, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is frequently found associated with ([pfam:PF22974]). This domain is predicted to adopt a globular structure with an elongated beta-sandwich topology.", "domain_architectures": 47, "interpro_id": "IPR055647", "known_evidence_count": null, "matches": 1688, "name": "Domain of unknown function (DUF7223)", "partial_evidence_count": null, "pfam_id": "PF23865", "proteins": 1685, "proteomes": 778, "short_name": "DUF7223", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23865", "structures": 0, "taxa": 1679, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 932, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into two sandwiched beta-sheets.", "domain_architectures": 3, "interpro_id": "IPR058333", "known_evidence_count": null, "matches": 1685, "name": "Domain of unknown function (DUF8020)", "partial_evidence_count": null, "pfam_id": "PF26059", "proteins": 1685, "proteomes": 201, "short_name": "DUF8020", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26059", "structures": 0, "taxa": 257, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1421, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This immunoglobulin-like (Ig-like) domain is found at the N-terminal end in a group of uncharacterised proteins from fungi. It shows a highly conserved motif GSWD and several highly conserved Y residues.", "domain_architectures": 9, "interpro_id": "IPR059427", "known_evidence_count": null, "matches": 1691, "name": "Domain of unknown function (DUF8383)", "partial_evidence_count": null, "pfam_id": "PF28357", "proteins": 1685, "proteomes": 860, "short_name": "DUF8383", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28357", "structures": 0, "taxa": 1667, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1341, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is found in eukaryotes but its function is unknown.", "domain_architectures": 15, "interpro_id": "IPR019534", "known_evidence_count": null, "matches": 1698, "name": "Protein of unknown function (DUF2452)", "partial_evidence_count": null, "pfam_id": "PF10504", "proteins": 1684, "proteomes": 1433, "short_name": "DUF2452", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10504", "structures": 0, "taxa": 3855, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1098, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 60 amino acids in length. This domain is frequently found at the C-terminus of [pfam:PF14231].", "domain_architectures": 23, "interpro_id": "IPR025568", "known_evidence_count": null, "matches": 1685, "name": "Domain of unknown function (DUF4334)", "partial_evidence_count": null, "pfam_id": "PF14232", "proteins": 1684, "proteomes": 1347, "short_name": "DUF4334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14232", "structures": 1, "taxa": 2214, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1407, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Fungi. This domain is predicted to adopt a globular structure consisting of a curved beta-sheet and alpha- helices packed on it. This domain is probably distantly related to the N-terminal domain of STE-like transcription factors ([pfam:PF02200]) based on the similarity of their predicted structures. The predicted structure of this domain has a partial similarity to pseudo Winged helix domains.", "domain_architectures": 16, "interpro_id": "IPR055509", "known_evidence_count": null, "matches": 1713, "name": "Domain of unknown function (DUF7082)", "partial_evidence_count": null, "pfam_id": "PF23305", "proteins": 1683, "proteomes": 1330, "short_name": "DUF7082", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23305", "structures": 0, "taxa": 2807, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to contain helix-extended loop-helix (HeH) structure and has similarity to domains containing this motif.", "domain_architectures": 19, "interpro_id": "IPR056139", "known_evidence_count": null, "matches": 1702, "name": "Domain of unknown function (DUF7722)", "partial_evidence_count": null, "pfam_id": "PF24847", "proteins": 1681, "proteomes": 342, "short_name": "DUF7722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24847", "structures": 0, "taxa": 961, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 826, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "AntibioticMech": 1, "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This domain is found in different combinations with cortical patch components EF hand, SH3 and ENTH and is therefore likely to be involved in cytoskeletal processes. This family contains many hypothetical proteins.", "domain_architectures": 113, "interpro_id": "IPR013182", "known_evidence_count": null, "matches": 1877, "name": "Domain of unknown function (DUF1720)", "partial_evidence_count": null, "pfam_id": "PF08226", "proteins": 1675, "proteomes": 1014, "short_name": "DUF1720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08226", "structures": 0, "taxa": 2308, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 992, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in archaea and bacteria.", "domain_architectures": 8, "interpro_id": "IPR025101", "known_evidence_count": null, "matches": 1675, "name": "Protein of unknown function (DUF4012)", "partial_evidence_count": null, "pfam_id": "PF13196", "proteins": 1674, "proteomes": 1284, "short_name": "DUF4012", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13196", "structures": 0, "taxa": 1678, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1009, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in bacteria.", "domain_architectures": 5, "interpro_id": "IPR043749", "known_evidence_count": null, "matches": 1672, "name": "Family of unknown function (DUF5694)", "partial_evidence_count": null, "pfam_id": "PF18950", "proteins": 1672, "proteomes": 1359, "short_name": "DUF5694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18950", "structures": 0, "taxa": 2043, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1082, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021682", "known_evidence_count": null, "matches": 1670, "name": "Protein of unknown function (DUF2933)", "partial_evidence_count": null, "pfam_id": "PF11666", "proteins": 1670, "proteomes": 1359, "short_name": "DUF2933", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11666", "structures": 0, "taxa": 2437, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 936, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "These proteins share a region of homology in their N termini, and are found in several phylogenetically diverse bacteria and in the archaeon Methanosarcina acetivorans. Some of these proteins also contain characterised domains such as [pfam:PF00395] (e.g. [swissprot:Q8YWJ6]) and [pfam:PF03422] (e.g. [swissprot:Q9FBS2]).", "domain_architectures": 149, "interpro_id": "IPR011459", "known_evidence_count": null, "matches": 1702, "name": "Protein of unknown function (DUF1565)", "partial_evidence_count": null, "pfam_id": "PF07602", "proteins": 1666, "proteomes": 992, "short_name": "DUF1565", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07602", "structures": 1, "taxa": 2186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 955, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This hypothetical bacterial gene product has a long hydrophobic segment and is thus likely to be a membrane protein.", "domain_architectures": 5, "interpro_id": "IPR021728", "known_evidence_count": null, "matches": 1665, "name": "Protein of unknown function (DUF3300)", "partial_evidence_count": null, "pfam_id": "PF11737", "proteins": 1664, "proteomes": 1342, "short_name": "DUF3300", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11737", "structures": 0, "taxa": 1956, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1508, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 119 and 168 amino acids in length.", "domain_architectures": 19, "interpro_id": "IPR045501", "known_evidence_count": null, "matches": 1718, "name": "Family of unknown function (DUF6490)", "partial_evidence_count": null, "pfam_id": "PF20100", "proteins": 1664, "proteomes": 135, "short_name": "DUF6490", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20100", "structures": 0, "taxa": 384, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1032, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found at the C-terminal of functionally uncharacterised bacterial proteins. In some short sequences, it covers the full length.", "domain_architectures": 6, "interpro_id": "IPR045443", "known_evidence_count": null, "matches": 1664, "name": "Domain of unknown function (DUF6504)", "partial_evidence_count": null, "pfam_id": "PF20114", "proteins": 1664, "proteomes": 1488, "short_name": "DUF6504", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20114", "structures": 0, "taxa": 2147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 950, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 215 and 226 amino acids in length. Structure prediction shows this family contains 4 alpha helices.", "domain_architectures": 3, "interpro_id": "IPR046657", "known_evidence_count": null, "matches": 1665, "name": "Domain of unknown function (DUF6766)", "partial_evidence_count": null, "pfam_id": "PF20554", "proteins": 1664, "proteomes": 1561, "short_name": "DUF6766", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20554", "structures": 0, "taxa": 2190, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 888, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins frequently in multiple copies. Some proteins containing this domain contain LPXTG cell wall anchor motif [pfam:PF00746] at the C-terminus. It is likely that some members of this entry contain an intramolecular isopeptide bond.", "domain_architectures": 280, "interpro_id": "IPR055353", "known_evidence_count": null, "matches": 1705, "name": "Domain of unknown function (DUF7619)", "partial_evidence_count": null, "pfam_id": "PF24595", "proteins": 1664, "proteomes": 798, "short_name": "DUF7619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24595", "structures": 0, "taxa": 1284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1354, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to adopt an eight-bladed beta-propeller.", "domain_architectures": 41, "interpro_id": "IPR057221", "known_evidence_count": null, "matches": 1745, "name": "Domain of unknown function (DUF7899)", "partial_evidence_count": null, "pfam_id": "PF25463", "proteins": 1662, "proteomes": 458, "short_name": "DUF7899", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25463", "structures": 0, "taxa": 1309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1037, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 12, "interpro_id": "IPR018684", "known_evidence_count": null, "matches": 1660, "name": "Uncharacterized protein conserved in bacteria (DUF2171)", "partial_evidence_count": null, "pfam_id": "PF09939", "proteins": 1659, "proteomes": 1182, "short_name": "DUF2171", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09939", "structures": 0, "taxa": 1680, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria and archaea. This domain is about 130 amino acids in length. This domain is found associated with [pfam:PF01522]. This domain has two completely conserved residues (P and H) that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR022560", "known_evidence_count": null, "matches": 1659, "name": "Domain of unknown function (DUF3473)", "partial_evidence_count": null, "pfam_id": "PF11959", "proteins": 1659, "proteomes": 1588, "short_name": "DUF3473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11959", "structures": 0, "taxa": 2786, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1075, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 4, "interpro_id": "IPR025433", "known_evidence_count": null, "matches": 1780, "name": "Domain of unknown function (DUF4168)", "partial_evidence_count": null, "pfam_id": "PF13767", "proteins": 1659, "proteomes": 1387, "short_name": "DUF4168", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13767", "structures": 0, "taxa": 2446, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 675, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein of unknown function is part of the Borrelidin synthesis genomic cluster. Borrelidin is a polyketide antibiotic [[cite:PUB00078768],[cite:PUB00078769]].", "domain_architectures": 5, "interpro_id": "IPR033457", "known_evidence_count": null, "matches": 1658, "name": "Protein of unknown function (DUF5133)", "partial_evidence_count": null, "pfam_id": "PF17196", "proteins": 1658, "proteomes": 675, "short_name": "DUF5133", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17196", "structures": 0, "taxa": 723, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 953, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a bacterial domain of approximately 220 residues. The domain is predominantly found in Actinomycetes, particularly Streptomycetaceae and related species, as well as in Pseudomonadota. In some proteins, this domain is found N-terminal to the MZB domain ([pfam:PF09369]). The function of this domain remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061785", "known_evidence_count": null, "matches": 1658, "name": "Domain of unknown function (DUF8724)", "partial_evidence_count": null, "pfam_id": "PF30764", "proteins": 1658, "proteomes": 1485, "short_name": "DUF8724", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30764", "structures": 2, "taxa": 2909, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1086, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 192 and 226 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025636", "known_evidence_count": null, "matches": 1655, "name": "Domain of unknown function (DUF4294)", "partial_evidence_count": null, "pfam_id": "PF14127", "proteins": 1655, "proteomes": 1643, "short_name": "DUF4294", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14127", "structures": 0, "taxa": 2149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 940, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this entry are encoded within a conserved gene four-gene neighbourhood found sporadically in a phylogenetically broad range of bacteria including: Nocardia farcinica, Symbiobacterium thermophilum, and Streptomyces avermitilis (Actinobacteria), Geobacillus kaustophilus (Firmicutes), Azoarcus sp. EbN1 and Ralstonia solanacearum (Beta-proteobacteria). Just the C-terminal region is ioncluded here.", "domain_architectures": 7, "interpro_id": "IPR024465", "known_evidence_count": null, "matches": 1653, "name": "Protein of unknown function C-terminus (DUF2399)", "partial_evidence_count": null, "pfam_id": "PF09664", "proteins": 1652, "proteomes": 1471, "short_name": "DUF2399", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09664", "structures": 0, "taxa": 2302, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1086, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR018687", "known_evidence_count": null, "matches": 1652, "name": "Predicted membrane protein (DUF2177)", "partial_evidence_count": null, "pfam_id": "PF09945", "proteins": 1650, "proteomes": 1579, "short_name": "DUF2177", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09945", "structures": 0, "taxa": 2553, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1314, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein domain found in fungi. This domain is frequently encoded within Starship elements, which are large transposable elements that mobilise accessory genes in fungal genomes [[cite:PUB00163731]]. The function of this domain remains to be determined.", "domain_architectures": 46, "interpro_id": "IPR022198", "known_evidence_count": null, "matches": 1857, "name": "Protein of unknown function (DUF3723) central domain", "partial_evidence_count": null, "pfam_id": "PF12520", "proteins": 1644, "proteomes": 486, "short_name": "DUF3723", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12520", "structures": 0, "taxa": 1022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1573, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 4, "interpro_id": "IPR043899", "known_evidence_count": null, "matches": 1643, "name": "Family of unknown function (DUF5789)", "partial_evidence_count": null, "pfam_id": "PF19102", "proteins": 1643, "proteomes": 301, "short_name": "DUF5789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19102", "structures": 0, "taxa": 497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into an alpha/beta structure with unique topology.", "domain_architectures": 116, "interpro_id": "IPR061858", "known_evidence_count": null, "matches": 1674, "name": "Domain of unknown function (DUF8797)", "partial_evidence_count": null, "pfam_id": "PF31063", "proteins": 1636, "proteomes": 107, "short_name": "DUF8797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31063", "structures": 0, "taxa": 394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 747, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 265 and 420 amino acids in length. It appears that these proteins are distantly related to the PDDEXK superfamily and so these domains are likely to be nucleases. This family has a C-terminal cysteine cluster similar to that found in [pfam:PF01930].", "domain_architectures": 11, "interpro_id": "IPR024432", "known_evidence_count": null, "matches": 1633, "name": "PDDEXK-like domain of unknown function (DUF3799)", "partial_evidence_count": null, "pfam_id": "PF12684", "proteins": 1632, "proteomes": 1445, "short_name": "DUF3799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12684", "structures": 2, "taxa": 2970, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1033, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of domains is functionally uncharacterised. This family of proteins is primarily found in bacteria. Proteins in this family are typically between 159 and 170 amino acids in length. The domain is found in some proteins associated with carbohydrate binding domains. The domain has some conserved aromatic residues that may suggest a carbohydrate binding function.", "domain_architectures": 11, "interpro_id": "IPR046232", "known_evidence_count": null, "matches": 1631, "name": "Domain of unknown function (DUF6265)", "partial_evidence_count": null, "pfam_id": "PF19780", "proteins": 1631, "proteomes": 1481, "short_name": "DUF6265", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19780", "structures": 0, "taxa": 2114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is the C-terminal domain of xyloglucan utilization locus (XyGUL) present in Cellvibrio japonicas. XyGUL is required for xyloglucan utilization. It is also the C-terminal domain of PF02449 and PF01301 [[cite:PUB00091233]].", "domain_architectures": 19, "interpro_id": "IPR040719", "known_evidence_count": null, "matches": 1630, "name": "Domain of unknown function (DUF5597)", "partial_evidence_count": null, "pfam_id": "PF18120", "proteins": 1630, "proteomes": 1157, "short_name": "DUF5597", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18120", "structures": 18, "taxa": 2018, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1011, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR009403", "known_evidence_count": null, "matches": 1631, "name": "Domain of unknown function (DUF1054)", "partial_evidence_count": null, "pfam_id": "PF06335", "proteins": 1629, "proteomes": 1575, "short_name": "DUF1054", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06335", "structures": 2, "taxa": 2085, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 992, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is often associated with family Toprim, [pfam:PF01751].", "domain_architectures": 35, "interpro_id": "IPR025054", "known_evidence_count": null, "matches": 1630, "name": "Protein of unknown function (DUF3991)", "partial_evidence_count": null, "pfam_id": "PF13154", "proteins": 1629, "proteomes": 989, "short_name": "DUF3991", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13154", "structures": 0, "taxa": 1888, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1034, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes.", "domain_architectures": 1, "interpro_id": "IPR021637", "known_evidence_count": null, "matches": 1628, "name": "Protein of unknown function (DUF3243)", "partial_evidence_count": null, "pfam_id": "PF11588", "proteins": 1628, "proteomes": 1253, "short_name": "DUF3243", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11588", "structures": 1, "taxa": 1656, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 975, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised bacterial proteins. They are predicted to contain two flttened beta-barrel-like domains that are arranged in a similar way as to these observed in the members of the AttH superfamily.", "domain_architectures": 7, "interpro_id": "IPR061686", "known_evidence_count": null, "matches": 1632, "name": "Family of unknown function (DUF8625)", "partial_evidence_count": null, "pfam_id": "PF30556", "proteins": 1628, "proteomes": 1172, "short_name": "DUF8625", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30556", "structures": 3, "taxa": 1539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 914, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. They may contain a catalytic His residue that could be related to Adenosylmethionine decarboxylases ([pfam:PF01536], PDBe:1jl0) [[cite:PUB00152793]].", "domain_architectures": 3, "interpro_id": "IPR024486", "known_evidence_count": null, "matches": 1630, "name": "Protein of unknown function DUF2617", "partial_evidence_count": null, "pfam_id": "PF10936", "proteins": 1625, "proteomes": 1534, "short_name": "DUF2617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10936", "structures": 0, "taxa": 1919, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 938, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 340 residues in length. Members of this family contain six highly conserved cysteine residues. The function of this family is unknown.", "domain_architectures": 6, "interpro_id": "IPR009560", "known_evidence_count": null, "matches": 1626, "name": "Protein of unknown function (DUF1176)", "partial_evidence_count": null, "pfam_id": "PF06674", "proteins": 1622, "proteomes": 1333, "short_name": "DUF1176", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06674", "structures": 0, "taxa": 2013, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 915, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as YggN which currently has no known function.", "domain_architectures": 2, "interpro_id": "IPR021307", "known_evidence_count": null, "matches": 1627, "name": "Protein of unknown function (DUF2884)", "partial_evidence_count": null, "pfam_id": "PF11101", "proteins": 1622, "proteomes": 1286, "short_name": "DUF2884", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11101", "structures": 0, "taxa": 1735, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 817, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It has a detectable sequence similarity to members of the Mog1p/PsbP-like superfamily and is predicted to adopt similar structure.", "domain_architectures": 4, "interpro_id": "IPR058330", "known_evidence_count": null, "matches": 1622, "name": "Domain of unknown function (DUF8017)", "partial_evidence_count": null, "pfam_id": "PF26056", "proteins": 1622, "proteomes": 1127, "short_name": "DUF8017", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26056", "structures": 0, "taxa": 1312, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021377", "known_evidence_count": null, "matches": 1621, "name": "Protein of unknown function (DUF3006)", "partial_evidence_count": null, "pfam_id": "PF11213", "proteins": 1621, "proteomes": 1360, "short_name": "DUF3006", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11213", "structures": 0, "taxa": 2314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 981, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this entry are found mostly in g-proteobacteria, especially in Vibrio. Strangely enough, there seems to be one eukaryotic homolog in Nematostella vectensis (NEMVEDRAFT_v1g226006), where the PA0388-like domain is fused with a domain homogous to the Methionine biosynthesis protein MetW (see below). In several Pseudomonas species, but also in Vibrio vulnificus and Azotobacter vinelandii PA0388 homologs are genomic neighbors of Nucleoside 5-triphosphatase RdgB (dHAPTP, dITP, XTP-specific) (EC 3.6.1.15) and Methionine biosynthesis protein MetW. On the other hand, in most Vibrio species it appears as a part of a conserved operon involved in possible response to stress.", "domain_architectures": 3, "interpro_id": "IPR025218", "known_evidence_count": null, "matches": 1617, "name": "Domain of unknown function (DUF4426)", "partial_evidence_count": null, "pfam_id": "PF14467", "proteins": 1617, "proteomes": 1606, "short_name": "DUF4426", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14467", "structures": 1, "taxa": 2118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1401, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 399 and 797 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR022162", "known_evidence_count": null, "matches": 1705, "name": "Protein of unknown function (DUF3689)", "partial_evidence_count": null, "pfam_id": "PF12463", "proteins": 1614, "proteomes": 920, "short_name": "DUF3689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12463", "structures": 0, "taxa": 2977, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1353, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 253 and 329 amino acids in length. There are two conserved sequence motifs: LLGYP and SFS.", "domain_architectures": 41, "interpro_id": "IPR027850", "known_evidence_count": null, "matches": 1659, "name": "Domain of unknown function (DUF4504)", "partial_evidence_count": null, "pfam_id": "PF14953", "proteins": 1608, "proteomes": 1239, "short_name": "DUF4504", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14953", "structures": 0, "taxa": 3961, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1280, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region within a number of proteins of unknown function that seem to be specific to Arabidopsis thaliana. Note that some family members contain more than one copy of this region.", "domain_architectures": 24, "interpro_id": "IPR010683", "known_evidence_count": null, "matches": 1664, "name": "Protein of unknown function (DUF1262)", "partial_evidence_count": null, "pfam_id": "PF06880", "proteins": 1604, "proteomes": 333, "short_name": "DUF1262", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06880", "structures": 0, "taxa": 894, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1289, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a fungal domain of unknown function. These domains have a structure that is closely related to the SRA domain found in SRA domains. This suggests this domain is likely to bind to 5-methylcytosine modified DNA.", "domain_architectures": 48, "interpro_id": "IPR046520", "known_evidence_count": null, "matches": 1639, "name": "Domain of unknown function (DUF6697)", "partial_evidence_count": null, "pfam_id": "PF20411", "proteins": 1604, "proteomes": 465, "short_name": "DUF6697", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20411", "structures": 0, "taxa": 1182, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1076, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 229 and 435 amino acids in length.", "domain_architectures": 18, "interpro_id": "IPR025377", "known_evidence_count": null, "matches": 1609, "name": "Domain of unknown function (DUF4367)", "partial_evidence_count": null, "pfam_id": "PF14285", "proteins": 1601, "proteomes": 1003, "short_name": "DUF4367", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14285", "structures": 0, "taxa": 1720, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 913, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family member Shigella flexneri VirK ([swissprot:Q99QA5]) is a virulence protein required for the expression, or correct membrane localisation of IcsA (VirG) on the bacterial cell surface [[cite:PUB00009979]], [[cite:PUB00009980]]. This family also includes Pasteurella haemolytica lapB ([swissprot:P32181]), which is thought to be membrane-associated.", "domain_architectures": 7, "interpro_id": "IPR007488", "known_evidence_count": null, "matches": 1616, "name": "Protein of unknown function (DUF535)", "partial_evidence_count": null, "pfam_id": "PF04393", "proteins": 1600, "proteomes": 1234, "short_name": "DUF535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04393", "structures": 0, "taxa": 1826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1092, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 192 and 203 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025500", "known_evidence_count": null, "matches": 1598, "name": "Domain of unknown function (DUF4390)", "partial_evidence_count": null, "pfam_id": "PF14334", "proteins": 1597, "proteomes": 1595, "short_name": "DUF4390", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14334", "structures": 0, "taxa": 2363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1041, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 165 and 176 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR027981", "known_evidence_count": null, "matches": 1599, "name": "Protein of unknown function (DUF4446)", "partial_evidence_count": null, "pfam_id": "PF14584", "proteins": 1597, "proteomes": 1592, "short_name": "DUF4446", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14584", "structures": 0, "taxa": 2421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 935, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 130 amino acids in length. The family is found in association with [pfam:PF07944], [pfam:PF16375].", "domain_architectures": 52, "interpro_id": "IPR046544", "known_evidence_count": null, "matches": 1597, "name": "Family of unknown function (DUF6805)", "partial_evidence_count": null, "pfam_id": "PF20620", "proteins": 1595, "proteomes": 1327, "short_name": "DUF6805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20620", "structures": 4, "taxa": 1977, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Metazoa lineage. This domain share similarity with the RAG recombinase RNase H domain.", "domain_architectures": 96, "interpro_id": "IPR061764", "known_evidence_count": null, "matches": 1606, "name": "Domain of unknown function (DUF8703)", "partial_evidence_count": null, "pfam_id": "PF30721", "proteins": 1591, "proteomes": 116, "short_name": "DUF8703", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30721", "structures": 0, "taxa": 678, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1276, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in plants. Proteins in this family are typically between 103 and 140 amino acids in length. There are two conserved sequence motifs: LQRS and FRR.", "domain_architectures": 38, "interpro_id": "IPR031421", "known_evidence_count": null, "matches": 1726, "name": "Domain of unknown function (DUF4666)", "partial_evidence_count": null, "pfam_id": "PF15697", "proteins": 1590, "proteomes": 367, "short_name": "DUF4666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15697", "structures": 0, "taxa": 1008, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in putative SANT domain-containing proteins and uncharacterised proteins found in plants. This domain is predicted to adopt an EF-hand-like fold. The EF-hand fold is a helix-loop-helix motif that can bind calcium atoms. The EF-hand fold is usually tandemly repeated, and the number of repeats ranges from two to eight [[cite:PUB00023098]].", "domain_architectures": 29, "interpro_id": "IPR057712", "known_evidence_count": null, "matches": 1598, "name": "Domain of unknown function (DUF7952)", "partial_evidence_count": null, "pfam_id": "PF25826", "proteins": 1589, "proteomes": 373, "short_name": "DUF7952", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25826", "structures": 0, "taxa": 1027, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 964, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021244", "known_evidence_count": null, "matches": 1586, "name": "Protein of unknown function (DUF2802)", "partial_evidence_count": null, "pfam_id": "PF10975", "proteins": 1586, "proteomes": 1581, "short_name": "DUF2802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10975", "structures": 0, "taxa": 2103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 914, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of short proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR018895", "known_evidence_count": null, "matches": 1585, "name": "Protein of unknown function (DUF2474)", "partial_evidence_count": null, "pfam_id": "PF10617", "proteins": 1585, "proteomes": 1452, "short_name": "DUF2474", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10617", "structures": 0, "taxa": 1995, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1009, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane beta-barrel proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes bacteria. Proteins in this family are typically between 300 and 313 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046235", "known_evidence_count": null, "matches": 1585, "name": "Domain of unknown function (DUF6268)", "partial_evidence_count": null, "pfam_id": "PF19783", "proteins": 1585, "proteomes": 1210, "short_name": "DUF6268", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19783", "structures": 0, "taxa": 1771, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family represents the C-terminus of a number of hypothetical plant proteins.", "domain_architectures": 29, "interpro_id": "IPR010543", "known_evidence_count": null, "matches": 1583, "name": "Protein of unknown function (DUF1117)", "partial_evidence_count": null, "pfam_id": "PF06547", "proteins": 1583, "proteomes": 360, "short_name": "DUF1117", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06547", "structures": 0, "taxa": 964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1058, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 95 and 124 amino acids in length. Structural models show this family adopts a structure found in bacterial toxins, suggesting this family are the toxins in a toxin-antitoxin system.", "domain_architectures": 15, "interpro_id": "IPR025354", "known_evidence_count": null, "matches": 1582, "name": "Domain of unknown function (DUF4258)", "partial_evidence_count": null, "pfam_id": "PF14076", "proteins": 1582, "proteomes": 1338, "short_name": "DUF4258", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14076", "structures": 0, "taxa": 2840, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1090, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 100 amino acids in length. This domain has a single completely conserved residue G that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR021959", "known_evidence_count": null, "matches": 1582, "name": "Domain of unknown function (DUF3576)", "partial_evidence_count": null, "pfam_id": "PF12100", "proteins": 1581, "proteomes": 1577, "short_name": "DUF3576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12100", "structures": 0, "taxa": 2282, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to adopt mainly helical structure.", "domain_architectures": 26, "interpro_id": "IPR056067", "known_evidence_count": null, "matches": 1584, "name": "Domain of unknown function (DUF7650)", "partial_evidence_count": null, "pfam_id": "PF24662", "proteins": 1581, "proteomes": 367, "short_name": "DUF7650", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24662", "structures": 0, "taxa": 990, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1321, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins conserved in fungi. The function is unknown.", "domain_architectures": 16, "interpro_id": "IPR018810", "known_evidence_count": null, "matches": 2917, "name": "Protein of unknown function (DUF2408)", "partial_evidence_count": null, "pfam_id": "PF10303", "proteins": 1580, "proteomes": 1452, "short_name": "DUF2408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10303", "structures": 0, "taxa": 3030, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This entry represents a putative domain found in the yeast Transcription factor tau 138 kDa subunit.", "domain_architectures": 82, "interpro_id": "IPR046488", "known_evidence_count": null, "matches": 1633, "name": "Family of unknown function (DUF6581)", "partial_evidence_count": null, "pfam_id": "PF20222", "proteins": 1580, "proteomes": 1463, "short_name": "DUF6581", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20222", "structures": 3, "taxa": 3198, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1044, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region that is found within bacterial proteins, most of which are hypothetical. Some members contain multiple copies.", "domain_architectures": 9, "interpro_id": "IPR010626", "known_evidence_count": null, "matches": 2575, "name": "Protein of unknown function (DUF1217)", "partial_evidence_count": null, "pfam_id": "PF06748", "proteins": 1578, "proteomes": 1348, "short_name": "DUF1217", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06748", "structures": 1, "taxa": 1899, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 862, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR018681", "known_evidence_count": null, "matches": 1578, "name": "Predicted small integral membrane protein (DUF2165)", "partial_evidence_count": null, "pfam_id": "PF09933", "proteins": 1577, "proteomes": 1508, "short_name": "DUF2165", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09933", "structures": 0, "taxa": 2182, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 798, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001514) is described by MIBiG as an example of the following biosynthetic class, other (unspecified), in particular the aristeromycin biosynthetic gene cluster from Streptomyces citricolor [[cite:PUB00098880]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR045635", "known_evidence_count": null, "matches": 1576, "name": "Family of unknown function (DUF6412)", "partial_evidence_count": null, "pfam_id": "PF19950", "proteins": 1576, "proteomes": 1555, "short_name": "DUF6412", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19950", "structures": 0, "taxa": 1779, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1011, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Putative periplasmic protein.", "domain_architectures": 11, "interpro_id": "IPR007407", "known_evidence_count": null, "matches": 1690, "name": "Protein of unknown function (DUF459)", "partial_evidence_count": null, "pfam_id": "PF04311", "proteins": 1575, "proteomes": 1436, "short_name": "DUF459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04311", "structures": 5, "taxa": 2153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1010, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical, bacterial proteins of around 60 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009579", "known_evidence_count": null, "matches": 1574, "name": "Protein of unknown function (DUF1192)", "partial_evidence_count": null, "pfam_id": "PF06698", "proteins": 1574, "proteomes": 1573, "short_name": "DUF1192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06698", "structures": 0, "taxa": 2109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 989, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 396 to 444 amino acids in length. Proteins in this family contain the [S/T]GA[S/T] motif and thus, is flavinylated by ApbE. This suggests that they may be involved in extracytosolic redox activities [[cite:PUB00098250]].", "domain_architectures": 5, "interpro_id": "IPR021953", "known_evidence_count": null, "matches": 1754, "name": "Protein of unknown function (DUF3570)", "partial_evidence_count": null, "pfam_id": "PF12094", "proteins": 1574, "proteomes": 1352, "short_name": "DUF3570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12094", "structures": 0, "taxa": 2021, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1223, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a probable trandmemberane domain found in uncharacterised proteins some of which may be neurotransmitter ligand-gated ion channels and sensory receptors.", "domain_architectures": 27, "interpro_id": "IPR061747", "known_evidence_count": null, "matches": 1584, "name": "Domain of unknown function (DUF8686)", "partial_evidence_count": null, "pfam_id": "PF30641", "proteins": 1574, "proteomes": 667, "short_name": "DUF8686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30641", "structures": 0, "taxa": 1298, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 402, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of conserved bacteriophage proteins of unknown function.", "domain_architectures": 12, "interpro_id": "IPR021739", "known_evidence_count": null, "matches": 1572, "name": "Protein of unknwon function (DUF3310)", "partial_evidence_count": null, "pfam_id": "PF11753", "proteins": 1572, "proteomes": 1487, "short_name": "DUF3310", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11753", "structures": 0, "taxa": 3417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1065, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 149 and 163 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR025494", "known_evidence_count": null, "matches": 1573, "name": "Domain of unknown function (DUF4385)", "partial_evidence_count": null, "pfam_id": "PF14328", "proteins": 1572, "proteomes": 1530, "short_name": "DUF4385", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14328", "structures": 0, "taxa": 2778, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 10, "interpro_id": "IPR021322", "known_evidence_count": null, "matches": 1571, "name": "Protein of unknown function (DUF2924)", "partial_evidence_count": null, "pfam_id": "PF11149", "proteins": 1571, "proteomes": 911, "short_name": "DUF2924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11149", "structures": 0, "taxa": 1768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 128 to 160 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR021823", "known_evidence_count": null, "matches": 1573, "name": "Protein of unknown function (DUF3408)", "partial_evidence_count": null, "pfam_id": "PF11888", "proteins": 1571, "proteomes": 460, "short_name": "DUF3408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11888", "structures": 0, "taxa": 662, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt a globular structure consisting of array of alpha helices. It contains several conserved cysteine residues that are predicted to form disulfide bonds. It is likely that the proteins containing this domain are secreted.", "domain_architectures": 19, "interpro_id": "IPR056146", "known_evidence_count": null, "matches": 1618, "name": "Domain of unknown function (DUF7729)", "partial_evidence_count": null, "pfam_id": "PF24855", "proteins": 1571, "proteomes": 1195, "short_name": "DUF7729", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24855", "structures": 0, "taxa": 2480, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt an alpha/beta structure.", "domain_architectures": 25, "interpro_id": "IPR061852", "known_evidence_count": null, "matches": 1575, "name": "Domain of unknown function (DUF8791)", "partial_evidence_count": null, "pfam_id": "PF31052", "proteins": 1571, "proteomes": 840, "short_name": "DUF8791", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31052", "structures": 0, "taxa": 1633, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1015, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 180 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010848", "known_evidence_count": null, "matches": 1570, "name": "Protein of unknown function (DUF1465)", "partial_evidence_count": null, "pfam_id": "PF07323", "proteins": 1570, "proteomes": 1560, "short_name": "DUF1465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07323", "structures": 1, "taxa": 2039, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1321, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is predominantly found in Basidiomycetes. There are several highly conserved residues: P, W, Q and G.", "domain_architectures": 36, "interpro_id": "IPR049233", "known_evidence_count": null, "matches": 1593, "name": "Domain of unknown function (DUF6830)", "partial_evidence_count": null, "pfam_id": "PF20722", "proteins": 1569, "proteomes": 145, "short_name": "DUF6830", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20722", "structures": 0, "taxa": 392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a domain of unknown function predominantly found in bacteria and fungi. It is often associated with pfam:PF13471 which is located at the N-terminal. This domain forms an all alpha-helical bundle and shows structural similarity to the C-terminal domain of glutathione S-transferase (GST).", "domain_architectures": 51, "interpro_id": "IPR058268", "known_evidence_count": null, "matches": 1586, "name": "Domain of unknown function (DUF7962)", "partial_evidence_count": null, "pfam_id": "PF25907", "proteins": 1569, "proteomes": 955, "short_name": "DUF7962", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25907", "structures": 0, "taxa": 2222, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1101, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This family consists of proteins of proteins belonging to the CpeT/CpcT family. These proteins are around 200 amino acids in length. The proteins contain a conserved motif PYR in the amino terminal half of the protein that may be functionally important. The species distribution of the family is interesting. So far it is restricted to cyanobacteria, cryptomonads and plants. It has been shown that CpcT encodes a bilin lyase responsible for attachment of phycocyanobilin to the beta subunit of phycocyanin [[cite:PUB00056796]].", "domain_architectures": 16, "interpro_id": "IPR010404", "known_evidence_count": null, "matches": 1617, "name": "CpeT/CpcT family (DUF1001)", "partial_evidence_count": null, "pfam_id": "PF06206", "proteins": 1567, "proteomes": 871, "short_name": "CpeT", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06206", "structures": 5, "taxa": 2426, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1050, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial domain often found at the C-terminus of Radical_SAM methylases.", "domain_architectures": 4, "interpro_id": "IPR025274", "known_evidence_count": null, "matches": 1567, "name": "Domain of unknown function (DUF4070)", "partial_evidence_count": null, "pfam_id": "PF13282", "proteins": 1567, "proteomes": 1023, "short_name": "DUF4070", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13282", "structures": 0, "taxa": 2266, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 627, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This a sequence family found in a set of bacterial proteins with no known function. This domain is currently only found in streptomyces bacteria. Most proteins contain two copies of this domain.", "domain_architectures": 4, "interpro_id": "IPR005523", "known_evidence_count": null, "matches": 2630, "name": "Domain of unknown function (DUF317)", "partial_evidence_count": null, "pfam_id": "PF03771", "proteins": 1565, "proteomes": 339, "short_name": "SPDY", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03771", "structures": 0, "taxa": 400, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1023, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial putative membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR009476", "known_evidence_count": null, "matches": 1564, "name": "Protein of unknown function (DUF1097)", "partial_evidence_count": null, "pfam_id": "PF06496", "proteins": 1564, "proteomes": 1411, "short_name": "DUF1097", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06496", "structures": 0, "taxa": 2333, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1092, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 15, "interpro_id": "IPR021276", "known_evidence_count": null, "matches": 1579, "name": "Protein of unknown function (DUF2855)", "partial_evidence_count": null, "pfam_id": "PF11017", "proteins": 1564, "proteomes": 1394, "short_name": "DUF2855", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11017", "structures": 0, "taxa": 2525, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1341, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 120 amino acids in length.", "domain_architectures": 34, "interpro_id": "IPR031941", "known_evidence_count": null, "matches": 1658, "name": "Domain of unknown function (DUF4773)", "partial_evidence_count": null, "pfam_id": "PF15998", "proteins": 1564, "proteomes": 379, "short_name": "DUF4773", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15998", "structures": 0, "taxa": 1379, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 765, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is the C-terminal domain of [pfam:PF18725] domain-containing proteins, whose function is unknown.", "domain_architectures": 11, "interpro_id": "IPR045697", "known_evidence_count": null, "matches": 1564, "name": "Domain of unknown function (DUF5919)", "partial_evidence_count": null, "pfam_id": "PF19319", "proteins": 1564, "proteomes": 1293, "short_name": "DUF5919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19319", "structures": 0, "taxa": 1550, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1016, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018661", "known_evidence_count": null, "matches": 1562, "name": "Uncharacterized protein conserved in bacteria (DUF2093)", "partial_evidence_count": null, "pfam_id": "PF09866", "proteins": 1562, "proteomes": 1503, "short_name": "DUF2093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09866", "structures": 0, "taxa": 1941, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 873, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an immunoglobulin-like domain found in bacteria.", "domain_architectures": 9, "interpro_id": "IPR040680", "known_evidence_count": null, "matches": 1562, "name": "Family of unknown function (DUF5643)", "partial_evidence_count": null, "pfam_id": "PF18705", "proteins": 1562, "proteomes": 802, "short_name": "DUF5643", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18705", "structures": 1, "taxa": 1097, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 816, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of presumed integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 76 and 89 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046550", "known_evidence_count": null, "matches": 1561, "name": "Family of unknown function (DUF6704)", "partial_evidence_count": null, "pfam_id": "PF20447", "proteins": 1561, "proteomes": 1559, "short_name": "DUF6704", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20447", "structures": 0, "taxa": 1763, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1030, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR018730", "known_evidence_count": null, "matches": 1560, "name": "Small integral membrane protein (DUF2273)", "partial_evidence_count": null, "pfam_id": "PF10031", "proteins": 1560, "proteomes": 1434, "short_name": "DUF2273", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10031", "structures": 0, "taxa": 2200, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a predicted ferredoxin-like domain found in a family of uncharacterized plant proteins. This group of proteins typically has this domain duplicated.", "domain_architectures": 31, "interpro_id": "IPR055464", "known_evidence_count": null, "matches": 3014, "name": "Domain of unknown function (DUF7036)", "partial_evidence_count": null, "pfam_id": "PF23041", "proteins": 1558, "proteomes": 364, "short_name": "DUF7036", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23041", "structures": 0, "taxa": 981, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1070, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Alphaproteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021395", "known_evidence_count": null, "matches": 1558, "name": "Protein of unknown function (DUF3035)", "partial_evidence_count": null, "pfam_id": "PF11233", "proteins": 1555, "proteomes": 1551, "short_name": "DUF3035", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11233", "structures": 0, "taxa": 2187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 794, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a beta propeller domain composed of five blades. It is often found in large extracellular proteins in one or more copies. It is uncertain whether this domain might have an enzymatic function or a ligand binding function. Structurally this domain appears to have a sixfold symmetry, but one of the blades takes up the space of normal repeats. This unusual blade is composed of three strands of the first repeat and a final C-terminal strand from the last repeat.", "domain_architectures": 297, "interpro_id": "IPR054215", "known_evidence_count": null, "matches": 1701, "name": "Repeat of unknown function (DUF6923)", "partial_evidence_count": null, "pfam_id": "PF21959", "proteins": 1554, "proteomes": 1295, "short_name": "DUF6923", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21959", "structures": 0, "taxa": 2237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 605, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is distantly related to the PHR domain [pfam:PF08005]. This domain is often found between successive bacterial Ig domains, [pfam:PF13205].", "domain_architectures": 310, "interpro_id": "IPR025141", "known_evidence_count": null, "matches": 3399, "name": "Domain of unknown function (DUF4082)", "partial_evidence_count": null, "pfam_id": "PF13313", "proteins": 1546, "proteomes": 879, "short_name": "DUF4082", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13313", "structures": 0, "taxa": 1433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 890, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small N-terminal domain of approximately 60 residues found in bacterial proteins. This family is found predominantly in Actinomycetota, particularly in the orders Kitasatosporales, Micrococcales, and Streptomycetales. The family is also present in Chloroflexota. Structure prediction suggests that this domain will form a homodimeric structure. The function of this domain remains to be determined.", "domain_architectures": 15, "interpro_id": "IPR061752", "known_evidence_count": null, "matches": 1544, "name": "Domain of unknown function (DUF8691)", "partial_evidence_count": null, "pfam_id": "PF30655", "proteins": 1544, "proteomes": 1053, "short_name": "DUF8691", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30655", "structures": 0, "taxa": 1526, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1291, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Fungi. It is predicted to adopt a beta-sandwich with Ig-like topology and is likely distantly related to the delta subunit of translocon-associated protein (TRAP-delta, [pfam:PF05404]).", "domain_architectures": 32, "interpro_id": "IPR055561", "known_evidence_count": null, "matches": 1553, "name": "Domain of unknown function (DUF7137)", "partial_evidence_count": null, "pfam_id": "PF23585", "proteins": 1542, "proteomes": 1302, "short_name": "DUF7137", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23585", "structures": 0, "taxa": 2712, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 994, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 5, "interpro_id": "IPR018674", "known_evidence_count": null, "matches": 1549, "name": "Predicted membrane protein (DUF2142)", "partial_evidence_count": null, "pfam_id": "PF09913", "proteins": 1541, "proteomes": 1221, "short_name": "DUF2142", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09913", "structures": 0, "taxa": 2033, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1266, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into an alpha-helical structure. It contains three highly conserved cysteine residues and a histidine that may constitute a metal binding site.", "domain_architectures": 26, "interpro_id": "IPR061551", "known_evidence_count": null, "matches": 1569, "name": "Domain of unknown function (DUF8481)", "partial_evidence_count": null, "pfam_id": "PF28924", "proteins": 1541, "proteomes": 358, "short_name": "DUF8481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28924", "structures": 0, "taxa": 975, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1287, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "CellStructureMech": 1, "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of uncharacterised fungal proteins.", "domain_architectures": 32, "interpro_id": "IPR012471", "known_evidence_count": null, "matches": 1696, "name": "Protein of Unknown function (DUF1690)", "partial_evidence_count": null, "pfam_id": "PF07956", "proteins": 1540, "proteomes": 1471, "short_name": "DUF1690", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07956", "structures": 1, "taxa": 3260, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 964, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 16, "interpro_id": "IPR009380", "known_evidence_count": null, "matches": 1712, "name": "Protein of unknown function (DUF1036)", "partial_evidence_count": null, "pfam_id": "PF06282", "proteins": 1539, "proteomes": 1277, "short_name": "DUF1036", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06282", "structures": 0, "taxa": 1982, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1356, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 16, "interpro_id": "IPR028054", "known_evidence_count": null, "matches": 1582, "name": "Domain of unknown function (DUF4481)", "partial_evidence_count": null, "pfam_id": "PF14800", "proteins": 1538, "proteomes": 1037, "short_name": "DUF4481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14800", "structures": 0, "taxa": 3431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 873, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of unknown function found in Actinobacteria with highly conserved motif of FRRKSG found at the C-terminus.", "domain_architectures": 3, "interpro_id": "IPR035172", "known_evidence_count": null, "matches": 1538, "name": "Family of unknown function (DUF5302)", "partial_evidence_count": null, "pfam_id": "PF17227", "proteins": 1538, "proteomes": 1526, "short_name": "DUF5302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17227", "structures": 0, "taxa": 1809, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 911, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "The members of this family are largely confined to the Gammaproteobacteria. The function is not known.", "domain_architectures": 4, "interpro_id": "IPR019635", "known_evidence_count": null, "matches": 1540, "name": "Protein of unknown function (DUF2500)", "partial_evidence_count": null, "pfam_id": "PF10694", "proteins": 1537, "proteomes": 1360, "short_name": "DUF2500", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10694", "structures": 3, "taxa": 1954, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1086, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a four-helical up-and-down bundle. It has a detectable similarity to Talin 1-like four-helical domains.", "domain_architectures": 77, "interpro_id": "IPR056685", "known_evidence_count": null, "matches": 1539, "name": "Domain of unknown function (DUF7783)", "partial_evidence_count": null, "pfam_id": "PF25006", "proteins": 1537, "proteomes": 1233, "short_name": "DUF7783", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25006", "structures": 0, "taxa": 2584, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1080, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 75 residues found in bacterial proteins. This domain is always located C-terminal to AAA+ ATPase domains. The family is found predominantly in Alphaproteobacteria, particularly in the orders Rhodobacterales, and in Planctomycetota. The function of this domain remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061750", "known_evidence_count": null, "matches": 1536, "name": "Domain of unknown function (DUF8689)", "partial_evidence_count": null, "pfam_id": "PF30653", "proteins": 1536, "proteomes": 1295, "short_name": "DUF8689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30653", "structures": 0, "taxa": 1971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This family is found mainly in plants, and is approximately 300 amino acids in length. It contains a predicted transmembrane helix.", "domain_architectures": 20, "interpro_id": "IPR049224", "known_evidence_count": null, "matches": 1558, "name": "Family of unknown function (DUF6821)", "partial_evidence_count": null, "pfam_id": "PF20705", "proteins": 1535, "proteomes": 372, "short_name": "DUF6821", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20705", "structures": 0, "taxa": 1020, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1023, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This region represents a conserved region found in hypothetical proteins from fungi, mycetozoa and entamoebidae.", "domain_architectures": 25, "interpro_id": "IPR013887", "known_evidence_count": null, "matches": 1535, "name": "Protein of unknown function (DUF1765)", "partial_evidence_count": null, "pfam_id": "PF08578", "proteins": 1534, "proteomes": 1267, "short_name": "DUF1765", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08578", "structures": 0, "taxa": 2621, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 962, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, eukaryotes and viruses. Proteins in this family are typically between 126 and 281 amino acids in length. The function of this domain is unknown. The structure of this domain has been found to contain five helices with a long flexible loop between helices one and two.", "domain_architectures": 14, "interpro_id": "IPR022016", "known_evidence_count": null, "matches": 1536, "name": "Domain of unknown function (DUF3597)", "partial_evidence_count": null, "pfam_id": "PF12200", "proteins": 1531, "proteomes": 1384, "short_name": "DUF3597", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12200", "structures": 1, "taxa": 1989, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 943, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "These proteins are functionally uncharacterised.", "domain_architectures": 20, "interpro_id": "IPR014955", "known_evidence_count": null, "matches": 1538, "name": "Protein of unknown function (DUF1826)", "partial_evidence_count": null, "pfam_id": "PF08856", "proteins": 1530, "proteomes": 1396, "short_name": "DUF1826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08856", "structures": 0, "taxa": 2287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 8, "interpro_id": "IPR021516", "known_evidence_count": null, "matches": 1575, "name": "Protein of unknown function (DUF3179)", "partial_evidence_count": null, "pfam_id": "PF11376", "proteins": 1527, "proteomes": 1189, "short_name": "DUF3179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11376", "structures": 0, "taxa": 2292, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 114 and 139 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR031833", "known_evidence_count": null, "matches": 1526, "name": "Domain of unknown function (DUF4748)", "partial_evidence_count": null, "pfam_id": "PF15932", "proteins": 1526, "proteomes": 1432, "short_name": "DUF4748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15932", "structures": 0, "taxa": 3790, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 999, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Family of predicted bacterial membrane protein with unknown function.", "domain_architectures": 2, "interpro_id": "IPR010398", "known_evidence_count": null, "matches": 1525, "name": "Protein of unknown function (DUF997)", "partial_evidence_count": null, "pfam_id": "PF06196", "proteins": 1525, "proteomes": 1486, "short_name": "DUF997", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06196", "structures": 0, "taxa": 2189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 984, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 190 and 224 amino acids in length. There is a single completely conserved residue E that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR025455", "known_evidence_count": null, "matches": 1526, "name": "Domain of unknown function (DUF4276)", "partial_evidence_count": null, "pfam_id": "PF14103", "proteins": 1525, "proteomes": 1164, "short_name": "DUF4276", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14103", "structures": 0, "taxa": 2566, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1002, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 200 residues in length and is mainly found in various Bacteroides and Capnocytophaga species. The function of this family is unknown. Distant homology analysis suggests a possible similarity of proteins from this family to TIM barrel glycoside hydrolases and, subsequently its involvement in carbohydrate metabolism.The domain lies downstream of glycosyl hydrolases 42 suggesting that as a domain it might represent the carbohydrate-binding region of the enzyme.", "domain_architectures": 89, "interpro_id": "IPR032267", "known_evidence_count": null, "matches": 1532, "name": "Domain of unknown function (DUF4832)", "partial_evidence_count": null, "pfam_id": "PF16116", "proteins": 1523, "proteomes": 1070, "short_name": "DUF4832", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16116", "structures": 0, "taxa": 2068, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 963, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed lipoprotein domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 50 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025362", "known_evidence_count": null, "matches": 1522, "name": "Domain of unknown function (DUF4266)", "partial_evidence_count": null, "pfam_id": "PF14086", "proteins": 1522, "proteomes": 1326, "short_name": "DUF4266", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14086", "structures": 0, "taxa": 1979, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Eukaryotes. Family members such as the human CC1D2A protein [swissprot:Q9P2K1], carry the domain architecture where [pfam:PF15625] and [pfam:PF00168] are found at the C-terminal region of this family. However, other family members such as [swissprot:D6R9V3], do not carry either of the above mentioned Pfam families.", "domain_architectures": 39, "interpro_id": "IPR041510", "known_evidence_count": null, "matches": 1553, "name": "Family of unknown function (DUF5523)", "partial_evidence_count": null, "pfam_id": "PF17661", "proteins": 1522, "proteomes": 645, "short_name": "DUF5523", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17661", "structures": 0, "taxa": 2391, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 781, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 215 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046646", "known_evidence_count": null, "matches": 1524, "name": "Family of unknown function (DUF6758)", "partial_evidence_count": null, "pfam_id": "PF20544", "proteins": 1519, "proteomes": 1512, "short_name": "DUF6758", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20544", "structures": 0, "taxa": 1709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1255, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a four helical up-and-down bundle.", "domain_architectures": 28, "interpro_id": "IPR061820", "known_evidence_count": null, "matches": 1519, "name": "Domain of unknown function (DUF8759)", "partial_evidence_count": null, "pfam_id": "PF30922", "proteins": 1514, "proteomes": 629, "short_name": "DUF8759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30922", "structures": 0, "taxa": 1287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 944, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins appears to be restricted to Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021317", "known_evidence_count": null, "matches": 1513, "name": "Protein of unknown function (DUF2917)", "partial_evidence_count": null, "pfam_id": "PF11142", "proteins": 1513, "proteomes": 765, "short_name": "DUF2917", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11142", "structures": 0, "taxa": 1040, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 973, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 238 and 271 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045444", "known_evidence_count": null, "matches": 1513, "name": "Family of unknown function (DUF6503)", "partial_evidence_count": null, "pfam_id": "PF20113", "proteins": 1513, "proteomes": 696, "short_name": "DUF6503", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20113", "structures": 0, "taxa": 983, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1181, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family includes members such as low psii accumulation1 (lpa1) from plants as well as Rep27 proteins found in unicellular green alga Chlamydomonas reinhardtii. The Arabidopsis LPA1 is a chaperone required for efficient photosystem II (PSII) assembly. It binds to psbA during de novo biogenesis of PSII [[cite:PUB00086019]]. Other studies show that REP27 in Chlamydomonas reinhardtii chloroplast thylakoids, plays a dual role in the regulation of D1 protein turnover by facilitating cotranslational biosynthesis insertion (C-terminal domain) and activation (tetratricopeptide repeat [TPR] motifs) of the nascent D1 during the PSII repair process [[cite:PUB00138194]].", "domain_architectures": 38, "interpro_id": "IPR021883", "known_evidence_count": null, "matches": 1514, "name": "Low psii accumulation1 / Rep27", "partial_evidence_count": null, "pfam_id": "PF11998", "proteins": 1512, "proteomes": 698, "short_name": "DUF3493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11998", "structures": 0, "taxa": 1944, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 960, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 158 and 187 amino acids in length. This family includes the PcfB protein.", "domain_architectures": 4, "interpro_id": "IPR024234", "known_evidence_count": null, "matches": 1512, "name": "Protein of unknown function (DUF3801)", "partial_evidence_count": null, "pfam_id": "PF12687", "proteins": 1512, "proteomes": 638, "short_name": "DUF3801", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12687", "structures": 0, "taxa": 1128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 996, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 210 amino acids in length. There are two conserved sequence motifs: AMSY and DNS.", "domain_architectures": 3, "interpro_id": "IPR046233", "known_evidence_count": null, "matches": 1508, "name": "Family of unknown function (DUF6266)", "partial_evidence_count": null, "pfam_id": "PF19781", "proteins": 1508, "proteomes": 470, "short_name": "DUF6266", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19781", "structures": 0, "taxa": 706, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 993, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised protein.", "domain_architectures": 4, "interpro_id": "IPR021233", "known_evidence_count": null, "matches": 1508, "name": "Protein of unknown function (DUF2783)", "partial_evidence_count": null, "pfam_id": "PF10932", "proteins": 1507, "proteomes": 1377, "short_name": "DUF2783", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10932", "structures": 0, "taxa": 1930, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1046, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021273", "known_evidence_count": null, "matches": 1507, "name": "Protein of unknown function (DUF2852)", "partial_evidence_count": null, "pfam_id": "PF11014", "proteins": 1507, "proteomes": 1465, "short_name": "DUF2852", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11014", "structures": 0, "taxa": 2034, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 933, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of uncharacterised bacterial proteins.", "domain_architectures": 7, "interpro_id": "IPR016097", "known_evidence_count": null, "matches": 1506, "name": "Family of unknown function (DUF695)", "partial_evidence_count": null, "pfam_id": "PF05117", "proteins": 1506, "proteomes": 1382, "short_name": "DUF695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05117", "structures": 0, "taxa": 2206, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 985, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 90 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009983", "known_evidence_count": null, "matches": 1503, "name": "Protein of unknown function (DUF1507)", "partial_evidence_count": null, "pfam_id": "PF07408", "proteins": 1503, "proteomes": 1464, "short_name": "DUF1507", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07408", "structures": 2, "taxa": 1894, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a domain of unknown function in putative HSP20-like chaperone proteins mostly found in plants. HSP20-like chaperones are a ubiquitous and abundant class of small Heat shock proteins (sHsps) that function as ATP-independent molecular chaperones in plants, protecting proteins from stress-induced denaturation and aggregation [[cite:PUB00161222]]. This domain contains a helix-turn-helix (HTH) like fold.", "domain_architectures": 23, "interpro_id": "IPR058354", "known_evidence_count": null, "matches": 1514, "name": "Domain of unknown function (DUF8041)", "partial_evidence_count": null, "pfam_id": "PF26145", "proteins": 1503, "proteomes": 369, "short_name": "DUF8041", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26145", "structures": 0, "taxa": 1003, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 903, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 134 and 145 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR025459", "known_evidence_count": null, "matches": 1508, "name": "Domain of unknown function (DUF4279)", "partial_evidence_count": null, "pfam_id": "PF14106", "proteins": 1502, "proteomes": 1269, "short_name": "DUF4279", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14106", "structures": 0, "taxa": 2242, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised metazoan proteins. It is predicted to adopt a globular structure with lipocalin fold. It also contains several highly conserved cysteine residues that are likely involved in the formation of intra-domain disulfide bridges.", "domain_architectures": 52, "interpro_id": "IPR055472", "known_evidence_count": null, "matches": 1516, "name": "Domain of unknown function (DUF7044)", "partial_evidence_count": null, "pfam_id": "PF23071", "proteins": 1502, "proteomes": 451, "short_name": "DUF7044", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23071", "structures": 0, "taxa": 1635, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1009, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR019219", "known_evidence_count": null, "matches": 1500, "name": "Uncharacterized protein conserved in bacteria (DUF2130)", "partial_evidence_count": null, "pfam_id": "PF09903", "proteins": 1500, "proteomes": 1437, "short_name": "DUF2130", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09903", "structures": 0, "taxa": 2509, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a four helical bundle with two alpha-helices significantly longer than the others.", "domain_architectures": 15, "interpro_id": "IPR061823", "known_evidence_count": null, "matches": 1507, "name": "Domain of unknown function (DUF8762)", "partial_evidence_count": null, "pfam_id": "PF30929", "proteins": 1500, "proteomes": 873, "short_name": "DUF8762", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30929", "structures": 0, "taxa": 1715, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1407, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea.", "domain_architectures": 4, "interpro_id": "IPR055943", "known_evidence_count": null, "matches": 1504, "name": "Family of unknown function (DUF7521)", "partial_evidence_count": null, "pfam_id": "PF24365", "proteins": 1499, "proteomes": 306, "short_name": "DUF7521", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24365", "structures": 0, "taxa": 526, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1302, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 106 and 135 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR032073", "known_evidence_count": null, "matches": 1524, "name": "Domain of unknown function (DUF4808)", "partial_evidence_count": null, "pfam_id": "PF16066", "proteins": 1498, "proteomes": 712, "short_name": "DUF4808", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16066", "structures": 0, "taxa": 2546, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 936, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 114 to 128 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR024515", "known_evidence_count": null, "matches": 1495, "name": "Protein of unknown function (DUF3397)", "partial_evidence_count": null, "pfam_id": "PF11877", "proteins": 1495, "proteomes": 1492, "short_name": "DUF3397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11877", "structures": 0, "taxa": 1920, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1414, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins. They contain the typical P-loop motif and are probably structurally related to the P-loop NTPases.", "domain_architectures": 12, "interpro_id": "IPR055927", "known_evidence_count": null, "matches": 1497, "name": "Family of unknown function (DUF7504)", "partial_evidence_count": null, "pfam_id": "PF24336", "proteins": 1495, "proteomes": 340, "short_name": "DUF7504", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24336", "structures": 0, "taxa": 561, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 957, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry contains integral membrane beta barrel proteins.", "domain_architectures": 5, "interpro_id": "IPR045916", "known_evidence_count": null, "matches": 1494, "name": "Membrane bound beta barrel domain (DUF5777)", "partial_evidence_count": null, "pfam_id": "PF19089", "proteins": 1491, "proteomes": 1176, "short_name": "DUF5777", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19089", "structures": 0, "taxa": 1632, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1011, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 3, "interpro_id": "IPR014993", "known_evidence_count": null, "matches": 1485, "name": "Domain of unknown function (DUF1841)", "partial_evidence_count": null, "pfam_id": "PF08897", "proteins": 1485, "proteomes": 1478, "short_name": "DUF1841", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08897", "structures": 0, "taxa": 2085, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 822, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 205 and 315 amino acids in length. There is a conserved GDG sequence motif at the C-terminus.", "domain_architectures": 14, "interpro_id": "IPR025335", "known_evidence_count": null, "matches": 1493, "name": "Protein of unknown function (DUF4241)", "partial_evidence_count": null, "pfam_id": "PF14025", "proteins": 1485, "proteomes": 1242, "short_name": "DUF4241", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14025", "structures": 0, "taxa": 1943, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 847, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family are annotated as hypothetical membrane spanning proteins however this cannot be confirmed. The family has no known function.", "domain_architectures": 9, "interpro_id": "IPR021247", "known_evidence_count": null, "matches": 1484, "name": "Protein of unknown function (DUF2785)", "partial_evidence_count": null, "pfam_id": "PF10978", "proteins": 1484, "proteomes": 1246, "short_name": "DUF2785", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10978", "structures": 0, "taxa": 1845, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 771, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a small domain of approximately 69 amino acids found in uncharacterised proteins from Actinobacteria, particularly Streptomyces, Micromonospora, and Pseudonocardiaceae. It contains a conserved FxGGpxDG sequence motif. This domain is predicted to fold into an open five-stranded beta-barrel.", "domain_architectures": 1, "interpro_id": "IPR061908", "known_evidence_count": null, "matches": 1484, "name": "Domain of unknown function (DUF8847)", "partial_evidence_count": null, "pfam_id": "PF31259", "proteins": 1484, "proteomes": 1231, "short_name": "DUF8847", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31259", "structures": 0, "taxa": 1384, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1004, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in bacterial proteins. The function of this domain remains to be determined. The predicted structure shows strong similarity to dipeptidyl peptidase III. This suggests proteins of this family are likely to be peptidase enzymes.", "domain_architectures": 13, "interpro_id": "IPR061675", "known_evidence_count": null, "matches": 1483, "name": "Domain of unknown function (DUF8614)", "partial_evidence_count": null, "pfam_id": "PF30221", "proteins": 1483, "proteomes": 1278, "short_name": "DUF8614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30221", "structures": 2, "taxa": 2481, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1251, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family includes the Cep120 protein which is associated with centriole structure and function [[cite:PUB00057426]].", "domain_architectures": 30, "interpro_id": "IPR022136", "known_evidence_count": null, "matches": 1483, "name": "Cep120 protein", "partial_evidence_count": null, "pfam_id": "PF12416", "proteins": 1481, "proteomes": 1021, "short_name": "DUF3668", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12416", "structures": 3, "taxa": 3469, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 862, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is uncharacterised.", "domain_architectures": 27, "interpro_id": "IPR049249", "known_evidence_count": null, "matches": 1487, "name": "Family of unknown function (DUF6882)", "partial_evidence_count": null, "pfam_id": "PF21813", "proteins": 1481, "proteomes": 1319, "short_name": "DUF6882", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21813", "structures": 0, "taxa": 2111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 949, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of functionally uncharacterised domains are found in bacterial glycosyltransferases and rhamnosyltransferases.", "domain_architectures": 16, "interpro_id": "IPR015393", "known_evidence_count": null, "matches": 1485, "name": "Domain of unknown function (DUF1972)", "partial_evidence_count": null, "pfam_id": "PF09314", "proteins": 1478, "proteomes": 1333, "short_name": "DUF1972", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09314", "structures": 0, "taxa": 2380, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 666, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR043857", "known_evidence_count": null, "matches": 1471, "name": "Family of unknown function (DUF5819)", "partial_evidence_count": null, "pfam_id": "PF19136", "proteins": 1471, "proteomes": 1150, "short_name": "DUF5819", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19136", "structures": 0, "taxa": 1432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1310, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 80 amino acids in length. This domain is found associated with [pfam:PF00023]. This domain has a conserved SHN sequence motif. It seems likely that this region represents divergent Ankyrin repeats.", "domain_architectures": 249, "interpro_id": "IPR020683", "known_evidence_count": null, "matches": 1471, "name": "Domain of unknown function (DUF3447)", "partial_evidence_count": null, "pfam_id": "PF11929", "proteins": 1470, "proteomes": 3, "short_name": "DUF3447", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11929", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 870, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is the lppY/lpqO homologue family.", "domain_architectures": 6, "interpro_id": "IPR011094", "known_evidence_count": null, "matches": 2221, "name": "Domain of Unknown Function (DUF1259)", "partial_evidence_count": null, "pfam_id": "PF07485", "proteins": 1469, "proteomes": 1111, "short_name": "DUF1529", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07485", "structures": 0, "taxa": 1766, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 915, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021269", "known_evidence_count": null, "matches": 1470, "name": "Protein of unknown function (DUF2848)", "partial_evidence_count": null, "pfam_id": "PF11010", "proteins": 1469, "proteomes": 1374, "short_name": "DUF2848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11010", "structures": 0, "taxa": 2072, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 968, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 621 and 693 amino acids in length.", "domain_architectures": 18, "interpro_id": "IPR022028", "known_evidence_count": null, "matches": 1586, "name": "Protein of unknown function (DUF3604)", "partial_evidence_count": null, "pfam_id": "PF12228", "proteins": 1466, "proteomes": 795, "short_name": "DUF3604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12228", "structures": 0, "taxa": 1622, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 951, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR035165", "known_evidence_count": null, "matches": 1465, "name": "Family of unknown function (DUF5319)", "partial_evidence_count": null, "pfam_id": "PF17252", "proteins": 1465, "proteomes": 1459, "short_name": "DUF5319", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17252", "structures": 0, "taxa": 1746, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant proteins. It has remote similarity to some glucanases and it is predicted to adopt similar beta-sandwich structure but elaborated with additional strands.", "domain_architectures": 37, "interpro_id": "IPR056122", "known_evidence_count": null, "matches": 1589, "name": "Domain of unknown function (DUF7705)", "partial_evidence_count": null, "pfam_id": "PF24804", "proteins": 1464, "proteomes": 370, "short_name": "DUF7705", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24804", "structures": 0, "taxa": 1034, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of arthropod proteins is functionally uncharacterised.", "domain_architectures": 16, "interpro_id": "IPR031720", "known_evidence_count": null, "matches": 1467, "name": "Domain of unknown function (DUF4728)", "partial_evidence_count": null, "pfam_id": "PF15860", "proteins": 1462, "proteomes": 328, "short_name": "DUF4728", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15860", "structures": 0, "taxa": 1348, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 6, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family is found at the N-terminus of metazoan proteins that carry PHD-like zinc-finger domains. The function is not known.", "domain_architectures": 12, "interpro_id": "IPR025243", "known_evidence_count": null, "matches": 1522, "name": "Domain of unknown function (DUF4195)", "partial_evidence_count": null, "pfam_id": "PF13836", "proteins": 1459, "proteomes": 422, "short_name": "DUF4195", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13836", "structures": 0, "taxa": 1314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 976, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 2, "interpro_id": "IPR014991", "known_evidence_count": null, "matches": 1458, "name": "Domain of unknown function (DUF1840)", "partial_evidence_count": null, "pfam_id": "PF08895", "proteins": 1458, "proteomes": 1323, "short_name": "DUF1840", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08895", "structures": 0, "taxa": 1746, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 327, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in fungal multidomain proteins.", "domain_architectures": 45, "interpro_id": "IPR059392", "known_evidence_count": null, "matches": 1463, "name": "Domain of unknown function (DUF8348)", "partial_evidence_count": null, "pfam_id": "PF27504", "proteins": 1457, "proteomes": 567, "short_name": "DUF8348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27504", "structures": 0, "taxa": 1219, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins.", "domain_architectures": 24, "interpro_id": "IPR061827", "known_evidence_count": null, "matches": 1482, "name": "Domain of unknown function (DUF8766)", "partial_evidence_count": null, "pfam_id": "PF30968", "proteins": 1457, "proteomes": 927, "short_name": "DUF8766", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30968", "structures": 0, "taxa": 1885, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1020, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains many hypothetical bacterial and archaeal proteins. A few members of this family are annotated as being putative transmembrane proteins, and the region in question in fact contains many hydrophobic residues.", "domain_architectures": 3, "interpro_id": "IPR012861", "known_evidence_count": null, "matches": 1456, "name": "Protein of unknown function (DUF1634)", "partial_evidence_count": null, "pfam_id": "PF07843", "proteins": 1456, "proteomes": 1318, "short_name": "DUF1634", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07843", "structures": 0, "taxa": 2255, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 705, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a repeated domain that is found towards the C-terminal of many different types of bacterial proteins. There are highly conserved glutamate and aspartate residues suggesting that this domain might carry enzymic activity.", "domain_architectures": 449, "interpro_id": "IPR025193", "known_evidence_count": null, "matches": 1560, "name": "Domain of unknown function (DUF4114)", "partial_evidence_count": null, "pfam_id": "PF13448", "proteins": 1456, "proteomes": 809, "short_name": "DUF4114", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13448", "structures": 0, "taxa": 1805, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 980, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised, found in bacteria and plants. It is approximately 160 amino acids in length and it has two conserved sequence motifs, HL and GLxHxxY. Several members of this entry also has TPR regions.", "domain_architectures": 38, "interpro_id": "IPR049202", "known_evidence_count": null, "matches": 1461, "name": "Domain of unknown function (DUF6817)", "partial_evidence_count": null, "pfam_id": "PF20680", "proteins": 1456, "proteomes": 1125, "short_name": "DUF6817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20680", "structures": 0, "taxa": 2346, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 855, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 194 and 339 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR045398", "known_evidence_count": null, "matches": 1474, "name": "Family of unknown function (DUF6515)", "partial_evidence_count": null, "pfam_id": "PF20125", "proteins": 1455, "proteomes": 1253, "short_name": "DUF6515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20125", "structures": 0, "taxa": 1886, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1296, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This small. approximately 100 residue, family is conserved from worms to humans. It is cysteine-rich with a characteristic FDxCEC sequence motif. The function is not known.", "domain_architectures": 20, "interpro_id": "IPR020309", "known_evidence_count": null, "matches": 1458, "name": "Protein of unknown function (DUF2615)", "partial_evidence_count": null, "pfam_id": "PF11027", "proteins": 1453, "proteomes": 1169, "short_name": "DUF2615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11027", "structures": 0, "taxa": 3849, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 983, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. This family includes human protein CXorf38.", "domain_architectures": 99, "interpro_id": "IPR027897", "known_evidence_count": null, "matches": 1499, "name": "Domain of unknown function (DUF4559)", "partial_evidence_count": null, "pfam_id": "PF15112", "proteins": 1453, "proteomes": 412, "short_name": "DUF4559", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15112", "structures": 0, "taxa": 1431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a conserved 100 residue central region of a family of proteins found in fungi. It carries a characteristic EYD sequence motif. The function is not known.", "domain_architectures": 21, "interpro_id": "IPR018819", "known_evidence_count": null, "matches": 1448, "name": "Protein of unknown function (DUF2418)", "partial_evidence_count": null, "pfam_id": "PF10332", "proteins": 1447, "proteomes": 1387, "short_name": "DUF2418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10332", "structures": 0, "taxa": 2952, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 880, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 7, "interpro_id": "IPR024501", "known_evidence_count": null, "matches": 1446, "name": "Protein of unknown function (DUF3141)", "partial_evidence_count": null, "pfam_id": "PF11339", "proteins": 1446, "proteomes": 1169, "short_name": "DUF3141", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11339", "structures": 0, "taxa": 1754, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 933, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This coiled coil domain is found in uncharacterised proteins mainly from gram-negative bacteria. It is usually followed by and Ig-like domain.", "domain_architectures": 8, "interpro_id": "IPR059473", "known_evidence_count": null, "matches": 1446, "name": "Coiled-coil region of unknown function (DUF8429)", "partial_evidence_count": null, "pfam_id": "PF28533", "proteins": 1446, "proteomes": 1264, "short_name": "DUF8429", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28533", "structures": 0, "taxa": 1768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 831, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this entry are encoded within a conserved gene four-gene neighbourhood found sporadically in a phylogenetically broad range of bacteria including: Nocardia farcinica, Symbiobacterium thermophilum, and Streptomyces avermitilis (Actinobacteria), Geobacillus kaustophilus (Firmicutes), Azoarcus sp. EbN1 and Ralstonia solanacearum (Beta-proteobacteria).", "domain_architectures": 9, "interpro_id": "IPR024466", "known_evidence_count": null, "matches": 1450, "name": "Protein of unknown function N-terminus (DUF3323)", "partial_evidence_count": null, "pfam_id": "PF11796", "proteins": 1445, "proteomes": 1297, "short_name": "DUF3323", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11796", "structures": 0, "taxa": 2048, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1136, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 16, "interpro_id": "IPR003748", "known_evidence_count": null, "matches": 1458, "name": "Uncharacterised ArCR, COG2043", "partial_evidence_count": null, "pfam_id": "PF02596", "proteins": 1443, "proteomes": 978, "short_name": "DUF169", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02596", "structures": 0, "taxa": 2039, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 945, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is mostly found in Actinobacteria. Its fold was identified as part of the zinc-ribbon superfamily [[cite:PUB00152793],[cite:PUB00017144]].", "domain_architectures": 1, "interpro_id": "IPR035169", "known_evidence_count": null, "matches": 1443, "name": "Family of unknown function (DUF5318)", "partial_evidence_count": null, "pfam_id": "PF17249", "proteins": 1443, "proteomes": 1438, "short_name": "DUF5318", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17249", "structures": 0, "taxa": 1799, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a small three stranded beta-sheet and alpha helices. It contains a highly conserved SD[ED]E sequence motif.", "domain_architectures": 12, "interpro_id": "IPR059307", "known_evidence_count": null, "matches": 1475, "name": "Domain of unknown function (DUF8263)", "partial_evidence_count": null, "pfam_id": "PF26792", "proteins": 1442, "proteomes": 144, "short_name": "DUF8263", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26792", "structures": 0, "taxa": 409, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 13, "interpro_id": "IPR021460", "known_evidence_count": null, "matches": 1535, "name": "Protein of unknown function (DUF3112)", "partial_evidence_count": null, "pfam_id": "PF11309", "proteins": 1441, "proteomes": 875, "short_name": "DUF3112", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11309", "structures": 0, "taxa": 1725, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 921, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 93 and 155 amino acids in length. There is a single completely conserved residue E that may be functionally important.", "domain_architectures": 10, "interpro_id": "IPR025557", "known_evidence_count": null, "matches": 1442, "name": "Domain of unknown function (DUF4282)", "partial_evidence_count": null, "pfam_id": "PF14110", "proteins": 1441, "proteomes": 1348, "short_name": "DUF4282", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14110", "structures": 0, "taxa": 2287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 891, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial protein of unknown function. It is rich in conserved tryptophan residues and contains a central HYGRW motif that may be of functional importance.", "domain_architectures": 5, "interpro_id": "IPR046535", "known_evidence_count": null, "matches": 1438, "name": "Family of unknown function (DUF6600)", "partial_evidence_count": null, "pfam_id": "PF20245", "proteins": 1438, "proteomes": 1351, "short_name": "DUF6600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20245", "structures": 0, "taxa": 1931, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 873, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000223) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the rabelomycin biosynthetic gene cluster from uncultured bacterium BAC AB649/1850 [[cite:PUB00098876]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 4, "interpro_id": "IPR045629", "known_evidence_count": null, "matches": 1437, "name": "Family of unknown function (DUF6232)", "partial_evidence_count": null, "pfam_id": "PF19744", "proteins": 1437, "proteomes": 877, "short_name": "DUF6232", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19744", "structures": 0, "taxa": 1345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function. Family members found in Saccharomyces cerevisiae, are synthetic lethal with genes involved in maintenance of telomere capping [[cite:PUB00035474],[cite:PUB00059200]]. However, experimental evidence is yet to verify the exact function of family members and the domain.", "domain_architectures": 10, "interpro_id": "IPR018814", "known_evidence_count": null, "matches": 1472, "name": "Domain of unknown function (DUF5427)", "partial_evidence_count": null, "pfam_id": "PF10310", "proteins": 1436, "proteomes": 1389, "short_name": "DUF5427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10310", "structures": 0, "taxa": 2883, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 964, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length and they seem to belong to the toxin-antitoxin system. They are likely to contain a ribbon-helix-helix DNA-binding motif.", "domain_architectures": 2, "interpro_id": "IPR045944", "known_evidence_count": null, "matches": 1436, "name": "Family of unknown function (DUF6364)", "partial_evidence_count": null, "pfam_id": "PF19891", "proteins": 1436, "proteomes": 1057, "short_name": "DUF6364", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19891", "structures": 0, "taxa": 2046, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1006, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised prokaryotic proteins.", "domain_architectures": 10, "interpro_id": "IPR007549", "known_evidence_count": null, "matches": 1450, "name": "Protein of unknown function (DUF512)", "partial_evidence_count": null, "pfam_id": "PF04459", "proteins": 1433, "proteomes": 1379, "short_name": "DUF512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04459", "structures": 2, "taxa": 2766, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 876, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed integral membrane domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 300 amino acids in length. This domain appears to be related to glycosyltransferase enzymes, such as those in [pfam:PF09594]. This suggests that his domain is an as yet uncharacterised glycosyltransferase.", "domain_architectures": 8, "interpro_id": "IPR046278", "known_evidence_count": null, "matches": 1431, "name": "Domain of unknown function (DUF6311)", "partial_evidence_count": null, "pfam_id": "PF19830", "proteins": 1430, "proteomes": 717, "short_name": "DUF6311", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19830", "structures": 0, "taxa": 1250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 934, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacterial proteins, functionally uncharacterised. Proteins in this family are typically between 174 and 239 amino acids in length. This domain is thought to contain transmembrane regions. This family is distantly related to [pfam:PF11239].", "domain_architectures": 1, "interpro_id": "IPR046216", "known_evidence_count": null, "matches": 1429, "name": "Domain of unknown function (DUF6249)", "partial_evidence_count": null, "pfam_id": "PF19762", "proteins": 1429, "proteomes": 1251, "short_name": "DUF6249", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19762", "structures": 0, "taxa": 1894, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 906, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function but appears to have an alpha/beta hydrolase domain and so is likely to be enzymatic.", "domain_architectures": 21, "interpro_id": "IPR021440", "known_evidence_count": null, "matches": 1430, "name": "Protein of unknown function (DUF3089)", "partial_evidence_count": null, "pfam_id": "PF11288", "proteins": 1428, "proteomes": 1167, "short_name": "DUF3089", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11288", "structures": 0, "taxa": 1903, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 853, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised bacterial protein.", "domain_architectures": 9, "interpro_id": "IPR010328", "known_evidence_count": null, "matches": 1432, "name": "Domain of Unknown Function (DUF928)", "partial_evidence_count": null, "pfam_id": "PF06051", "proteins": 1423, "proteomes": 238, "short_name": "DUF928", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06051", "structures": 0, "taxa": 688, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 882, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of proteins whose function is unknown.", "domain_architectures": 1, "interpro_id": "IPR021357", "known_evidence_count": null, "matches": 1423, "name": "Protein of unknown function (DUF2782)", "partial_evidence_count": null, "pfam_id": "PF11191", "proteins": 1423, "proteomes": 1412, "short_name": "DUF2782", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11191", "structures": 1, "taxa": 1901, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 895, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in bacteria is functionally uncharacterised. Proteins in this family are typically between 166 and 277 amino acids in length. A conserved glycine residue and the conserved sequences GTF and GxF can be found at the C-terminal.", "domain_architectures": 9, "interpro_id": "IPR046219", "known_evidence_count": null, "matches": 1650, "name": "Domain of unknown function (DUF6252)", "partial_evidence_count": null, "pfam_id": "PF19765", "proteins": 1423, "proteomes": 820, "short_name": "DUF6252", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19765", "structures": 0, "taxa": 1105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 872, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR018741", "known_evidence_count": null, "matches": 1421, "name": "Protein of unknown function (DUF2288)", "partial_evidence_count": null, "pfam_id": "PF10052", "proteins": 1421, "proteomes": 1415, "short_name": "DUF2288", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10052", "structures": 1, "taxa": 2131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 25, "interpro_id": "IPR021709", "known_evidence_count": null, "matches": 1574, "name": "Protein of unknown function (DUF3292)", "partial_evidence_count": null, "pfam_id": "PF11696", "proteins": 1421, "proteomes": 998, "short_name": "DUF3292", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11696", "structures": 0, "taxa": 2060, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 856, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry is a small alpha-helical domain found at the C-terminus of proteins a family of uncharacterised bacterial proteins that have a set of beta sandwich domains towards the N-terminus including [pfam:PF13584].", "domain_architectures": 9, "interpro_id": "IPR057699", "known_evidence_count": null, "matches": 1421, "name": "Domain of unknown function (DUF7939)", "partial_evidence_count": null, "pfam_id": "PF25607", "proteins": 1421, "proteomes": 1397, "short_name": "DUF7939", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25607", "structures": 0, "taxa": 1953, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 820, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045508", "known_evidence_count": null, "matches": 1420, "name": "Family of unknown function (DUF6482)", "partial_evidence_count": null, "pfam_id": "PF20090", "proteins": 1420, "proteomes": 1075, "short_name": "DUF6482", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20090", "structures": 0, "taxa": 1357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 498 and 775 amino acids in length. There is a conserved DLK sequence motif.", "domain_architectures": 10, "interpro_id": "IPR031476", "known_evidence_count": null, "matches": 1450, "name": "Domain of unknown function (DUF4686)", "partial_evidence_count": null, "pfam_id": "PF15742", "proteins": 1419, "proteomes": 741, "short_name": "DUF4686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15742", "structures": 0, "taxa": 2443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 913, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 455 and 518 amino acids in length. There is a single completely conserved residue W that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR025515", "known_evidence_count": null, "matches": 1419, "name": "Domain of unknown function (DUF4403)", "partial_evidence_count": null, "pfam_id": "PF14356", "proteins": 1418, "proteomes": 1268, "short_name": "DUF4403", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14356", "structures": 0, "taxa": 1785, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 965, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 32, "interpro_id": "IPR018708", "known_evidence_count": null, "matches": 1417, "name": "Uncharacterized protein conserved in bacteria (DUF2225)", "partial_evidence_count": null, "pfam_id": "PF09986", "proteins": 1416, "proteomes": 1326, "short_name": "DUF2225", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09986", "structures": 0, "taxa": 2324, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 902, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 70 amino acids in length. The family is found in association with [pfam:PF01588].", "domain_architectures": 2, "interpro_id": "IPR027855", "known_evidence_count": null, "matches": 1413, "name": "Domain of unknown function (DUF4479)", "partial_evidence_count": null, "pfam_id": "PF14794", "proteins": 1413, "proteomes": 1411, "short_name": "DUF4479", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14794", "structures": 1, "taxa": 1948, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 953, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 132 and 144 amino acids in length. There is a single completely conserved residue W that may be functionally important.", "domain_architectures": 74, "interpro_id": "IPR031961", "known_evidence_count": null, "matches": 1591, "name": "Domain of unknown function (DUF4780)", "partial_evidence_count": null, "pfam_id": "PF16012", "proteins": 1413, "proteomes": 159, "short_name": "DUF4780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16012", "structures": 0, "taxa": 673, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in fungi but the function is not known.", "domain_architectures": 23, "interpro_id": "IPR021711", "known_evidence_count": null, "matches": 1542, "name": "Protein of unknown function (DUF3295)", "partial_evidence_count": null, "pfam_id": "PF11702", "proteins": 1412, "proteomes": 1105, "short_name": "DUF3295", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11702", "structures": 0, "taxa": 2351, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 925, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain found in RDD family proteins, which follows the RDD domain ([pfam:PF06271]). This family is found predominantly in Bacteroidota, particularly in the orders Flavobacteriales and Cytophagales. The domain is approximately 65-85 residues in length. The function of this domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061554", "known_evidence_count": null, "matches": 1412, "name": "Domain of unknown function (DUF8484)", "partial_evidence_count": null, "pfam_id": "PF28959", "proteins": 1412, "proteomes": 1406, "short_name": "DUF8484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28959", "structures": 0, "taxa": 1855, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 784, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of unknown function and is known as YqjC in E. coli.", "domain_architectures": 3, "interpro_id": "IPR009468", "known_evidence_count": null, "matches": 1411, "name": "Protein of unknown function (DUF1090)", "partial_evidence_count": null, "pfam_id": "PF06476", "proteins": 1409, "proteomes": 1219, "short_name": "DUF1090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06476", "structures": 0, "taxa": 1621, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1080, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from fungi. It contains two pairs of conserved cysteine and histidine residues that may be involved in metal coordination.", "domain_architectures": 40, "interpro_id": "IPR057218", "known_evidence_count": null, "matches": 1414, "name": "Domain of unknown function (DUF7896)", "partial_evidence_count": null, "pfam_id": "PF25438", "proteins": 1408, "proteomes": 853, "short_name": "DUF7896", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25438", "structures": 0, "taxa": 1646, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 843, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 110 amino acids in length. The family is found in association with [pfam:PF08874]. There are two completely conserved residues (D and R) that may be functionally important.", "domain_architectures": 10, "interpro_id": "IPR022123", "known_evidence_count": null, "matches": 1407, "name": "Protein of unknown function", "partial_evidence_count": null, "pfam_id": "PF12395", "proteins": 1407, "proteomes": 1246, "short_name": "DUF3658", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12395", "structures": 0, "taxa": 1906, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 913, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in TIGR00341 family proteins. This domain follows the TIGR00341/DUF389 domain ([pfam:PF04087]) and is approximately 70-80 residues in length. The family is found predominantly in Bacteroidota, particularly in Flavobacteriales. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061562", "known_evidence_count": null, "matches": 1407, "name": "Domain of unknown function (DUF8492)", "partial_evidence_count": null, "pfam_id": "PF29025", "proteins": 1407, "proteomes": 1386, "short_name": "DUF8492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29025", "structures": 0, "taxa": 1965, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 913, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal helical domain found in DUF4350 family proteins. This domain follows the DUF4350 domain ([pfam:PF14258]) and is approximately 85-100 residues in length. The family is found almost exclusively in Bacteroidota, particularly in Flavobacteriales. The function of this domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR062916", "known_evidence_count": null, "matches": 1407, "name": "DUF4350 C-terminal helical domain", "partial_evidence_count": null, "pfam_id": "PF29026", "proteins": 1407, "proteomes": 1402, "short_name": "DUF4350_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29026", "structures": 0, "taxa": 1857, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 919, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in prokaryotes. Advanced homology-detection methods supported with superfamily-wide domain architecture and horizontal gene transfer analyses s have established this family to be a member of the PD-(D/E)XK superfamily.", "domain_architectures": 2, "interpro_id": "IPR018679", "known_evidence_count": null, "matches": 1441, "name": "Putative PD-(D/E)XK phosphodiesterase (DUF2161)", "partial_evidence_count": null, "pfam_id": "PF09929", "proteins": 1406, "proteomes": 1395, "short_name": "DUF2161", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09929", "structures": 0, "taxa": 1996, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 868, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function, found mostly in Actinobacteria and composed of trans-membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR035197", "known_evidence_count": null, "matches": 1405, "name": "Family of unknown function (DUF5313)", "partial_evidence_count": null, "pfam_id": "PF17240", "proteins": 1405, "proteomes": 847, "short_name": "DUF5313", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17240", "structures": 0, "taxa": 1017, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry describes the N-terminal domain of unknown function of DNA polymerase theta subunit (PolQ) majoritarily from fungal and and yeast proteins. Structural predictions suggest that this family adopts Helix-Helix-Helix (HHH) motifs. Proteins containing HHH motifs are typically associated with DNA-binding functions. These structural elements are often found in enzymes involved in DNA metabolism, such as DNA polymerases and helicases [[cite:PUB00101275],[cite:PUB00021052]].", "domain_architectures": 52, "interpro_id": "IPR057220", "known_evidence_count": null, "matches": 1406, "name": "Domain of unknown function (DUF7898)", "partial_evidence_count": null, "pfam_id": "PF25453", "proteins": 1405, "proteomes": 1148, "short_name": "DUF7898", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25453", "structures": 17, "taxa": 2960, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 713, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a set of lipoproteins that contain an N-terminal lipoprotein attachment site.", "domain_architectures": 4, "interpro_id": "IPR021326", "known_evidence_count": null, "matches": 1415, "name": "Protein of unknown function (DUF2931)", "partial_evidence_count": null, "pfam_id": "PF11153", "proteins": 1404, "proteomes": 677, "short_name": "DUF2931", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11153", "structures": 0, "taxa": 1014, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 963, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed.", "domain_architectures": 11, "interpro_id": "IPR021417", "known_evidence_count": null, "matches": 1450, "name": "Protein of unknown function (DUF3060)", "partial_evidence_count": null, "pfam_id": "PF11259", "proteins": 1404, "proteomes": 828, "short_name": "DUF3060", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11259", "structures": 0, "taxa": 1231, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 895, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018672", "known_evidence_count": null, "matches": 1402, "name": "Uncharacterized protein conserved in bacteria (DUF2140)", "partial_evidence_count": null, "pfam_id": "PF09911", "proteins": 1402, "proteomes": 1370, "short_name": "DUF2140", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09911", "structures": 0, "taxa": 1870, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 921, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR007335", "known_evidence_count": null, "matches": 1400, "name": "Protein of unknown function, DUF", "partial_evidence_count": null, "pfam_id": "PF04219", "proteins": 1400, "proteomes": 1295, "short_name": "DUF413", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04219", "structures": 0, "taxa": 1864, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 769, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 16, "interpro_id": "IPR021478", "known_evidence_count": null, "matches": 1454, "name": "Protein of unknown function (DUF3131)", "partial_evidence_count": null, "pfam_id": "PF11329", "proteins": 1397, "proteomes": 929, "short_name": "DUF3131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11329", "structures": 1, "taxa": 1627, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant proteins. It shares a significant sequence similarity with members of the GDP-fucose protein O-fucosyltransferase family ([pfam:PF10250]) and it is predicted to adopt similar structure.", "domain_architectures": 31, "interpro_id": "IPR055503", "known_evidence_count": null, "matches": 1427, "name": "Domain of unknown function (DUF7075)", "partial_evidence_count": null, "pfam_id": "PF23272", "proteins": 1396, "proteomes": 372, "short_name": "DUF7075", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23272", "structures": 0, "taxa": 1027, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 879, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 96 and 110 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR017259", "known_evidence_count": null, "matches": 1395, "name": "Domain of unknown function (DUF3784)", "partial_evidence_count": null, "pfam_id": "PF12650", "proteins": 1395, "proteomes": 1116, "short_name": "DUF3784", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12650", "structures": 0, "taxa": 1900, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 938, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 80 amino acids in length. There is a single completely conserved residue G that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR022254", "known_evidence_count": null, "matches": 1393, "name": "Protein of unknown function (DUF3775)", "partial_evidence_count": null, "pfam_id": "PF12616", "proteins": 1393, "proteomes": 1293, "short_name": "DUF3775", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12616", "structures": 0, "taxa": 1916, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a fungal family of uncharacterised proteins.", "domain_architectures": 14, "interpro_id": "IPR018559", "known_evidence_count": null, "matches": 1393, "name": "Fungal protein of unknown function (DUF2015)", "partial_evidence_count": null, "pfam_id": "PF09435", "proteins": 1392, "proteomes": 1354, "short_name": "DUF2015", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09435", "structures": 0, "taxa": 2871, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 781, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins, found in bacteria, is functionally uncharacterised. Proteins in this family are typically between 280 and 295 amino acids in length. There is a conserved WHxxxxLP sequence motif and a conserved Q residue.", "domain_architectures": 4, "interpro_id": "", "known_evidence_count": null, "matches": 1392, "name": "Family of unknown function (DUF6279)", "partial_evidence_count": null, "pfam_id": "PF19795", "proteins": 1392, "proteomes": 1379, "short_name": "DUF6279", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19795", "structures": 0, "taxa": 1825, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 879, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR021560", "known_evidence_count": null, "matches": 1391, "name": "Protein of unknown function (DUF3021)", "partial_evidence_count": null, "pfam_id": "PF11457", "proteins": 1391, "proteomes": 1130, "short_name": "DUF3021", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11457", "structures": 0, "taxa": 1751, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 896, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a large set of plasmodium proteins found in high copy number in subtelomeric repeats[[cite:PUB00151585]]. It has been suggested that these proteins may pair to form heterodimers [[cite:PUB00151585]]. Structure prediction suggests these proteins are related to RH5 and therefore may also have an adhesion role, possibly binding host receptors [[cite:PUB00151585]].", "domain_architectures": 3, "interpro_id": "IPR022139", "known_evidence_count": null, "matches": 1408, "name": "Fam-L, Fam-M like protein", "partial_evidence_count": null, "pfam_id": "PF12420", "proteins": 1391, "proteomes": 22, "short_name": "DUF3671", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12420", "structures": 0, "taxa": 78, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 909, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 352 and 374 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR024479", "known_evidence_count": null, "matches": 1402, "name": "Protein of unknown function (DUF3866)", "partial_evidence_count": null, "pfam_id": "PF12982", "proteins": 1391, "proteomes": 1373, "short_name": "DUF3866", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12982", "structures": 0, "taxa": 2022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This domain is found in the Polycomb group protein EMBRYONIC FLOWER 2 (EMF2) from Arabidopsis thaliana and related proteins. EMF2 is involved in flowering processes by repressing unknown target genes and preventing reproductive development. This domain is predicted to adopt a globular structure that resembles barrel-sandwich hybrid. The beta-sandwich has a topology most similar to C2 domains found in diverse proteins such as CEP120, Dysferlin and Myoferlin.", "domain_architectures": 30, "interpro_id": "IPR056068", "known_evidence_count": null, "matches": 1414, "name": "Domain of unknown function (DUF7651)", "partial_evidence_count": null, "pfam_id": "PF24663", "proteins": 1391, "proteomes": 363, "short_name": "DUF7651", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24663", "structures": 0, "taxa": 1046, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 690, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001558) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the cosmomycin C biosynthetic gene cluster from Streptomyces sp. CNT302 [[cite:PUB00099411]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR045924", "known_evidence_count": null, "matches": 1390, "name": "Family of unknown function (DUF6343)", "partial_evidence_count": null, "pfam_id": "PF19870", "proteins": 1390, "proteomes": 1282, "short_name": "DUF6343", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19870", "structures": 0, "taxa": 1466, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 913, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "The function of this domain family is unknown. It is found in eukaryotes, and is typically between 119 and 141 amino acids in length. In humans, it is found in the chromosomal position C11orf16.", "domain_architectures": 34, "interpro_id": "IPR032770", "known_evidence_count": null, "matches": 1644, "name": "Domain of unknown function (DUF4537)", "partial_evidence_count": null, "pfam_id": "PF15057", "proteins": 1387, "proteomes": 542, "short_name": "DUF4537", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15057", "structures": 0, "taxa": 1938, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 888, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members are annotated as lipoproteins however this cannot be confirmed. This family of proteins has no known function.", "domain_architectures": 26, "interpro_id": "IPR021341", "known_evidence_count": null, "matches": 1386, "name": "Protein of unknown function (DUF2958)", "partial_evidence_count": null, "pfam_id": "PF11171", "proteins": 1386, "proteomes": 945, "short_name": "DUF2958", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11171", "structures": 0, "taxa": 1786, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 843, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as yfiL which has no known function.", "domain_architectures": 4, "interpro_id": "IPR021242", "known_evidence_count": null, "matches": 1393, "name": "Protein of unknown function (DUF2799)", "partial_evidence_count": null, "pfam_id": "PF10973", "proteins": 1385, "proteomes": 1071, "short_name": "DUF2799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10973", "structures": 0, "taxa": 1646, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 867, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. However, based on similarity to other families it is likely to be involved in lipoprotein biosynthesis. This family of proteins is found in bacteria. Proteins in this family are typically between 263 and 293 amino acids in length.", "domain_architectures": 16, "interpro_id": "IPR046720", "known_evidence_count": null, "matches": 1398, "name": "Family of unknown function (DUF6612)", "partial_evidence_count": null, "pfam_id": "PF20316", "proteins": 1385, "proteomes": 1008, "short_name": "DUF6612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20316", "structures": 0, "taxa": 1590, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1097, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a conserved 120 residue region of a family of proteins found in fungi. The function is not known.", "domain_architectures": 28, "interpro_id": "IPR018829", "known_evidence_count": null, "matches": 1386, "name": "Protein of unknown function (DUF2433)", "partial_evidence_count": null, "pfam_id": "PF10360", "proteins": 1384, "proteomes": 1326, "short_name": "DUF2433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10360", "structures": 0, "taxa": 2784, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 943, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_4769, a conserved protein found in a conjugate transposon. As seem in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231). It appears to be upregulated in the presence of host or other bacterial species vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 6, "interpro_id": "IPR024451", "known_evidence_count": null, "matches": 1383, "name": "Domain of unknown function, B. Theta Gene description (DUF3875)", "partial_evidence_count": null, "pfam_id": "PF12991", "proteins": 1383, "proteomes": 828, "short_name": "DUF3875", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12991", "structures": 0, "taxa": 1127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1155, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a putative redox protein which is predicted to have a thioredoxin fold containing a single active cysteine [[cite:PUB00033654]].", "domain_architectures": 23, "interpro_id": "IPR012882", "known_evidence_count": null, "matches": 1382, "name": "Protein of unknown function (DUF1687)", "partial_evidence_count": null, "pfam_id": "PF07955", "proteins": 1382, "proteomes": 1270, "short_name": "DUF1687", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07955", "structures": 1, "taxa": 2652, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 288 and 410 amino acids in length. There are two completely conserved C residues that may be functionally important. In mammals this protein family is thyroid-specific [[cite:PUB00076024]].", "domain_architectures": 29, "interpro_id": "IPR031751", "known_evidence_count": null, "matches": 1461, "name": "Domain of unknown function (DUF4735)", "partial_evidence_count": null, "pfam_id": "PF15882", "proteins": 1382, "proteomes": 782, "short_name": "DUF4735", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15882", "structures": 0, "taxa": 2727, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 909, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Several members of this family are annotated as being molybdopterin-guanine dinucleotide biosynthesis protein A; however, this could not be confirmed. The family is found in proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021736", "known_evidence_count": null, "matches": 1381, "name": "Protein of unknown function (DUF3305)", "partial_evidence_count": null, "pfam_id": "PF11749", "proteins": 1381, "proteomes": 1336, "short_name": "DUF3305", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11749", "structures": 0, "taxa": 1878, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 640, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0002014) is described by MIBiG as an example of the following biosynthetic classes, polyketide and NRP (non-ribosomal peptide). It includes a member of the pepticinnamin E biosynthetic gene cluster from Actinobacteria bacterium OK006 [[cite:PUB00098920]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 6, "interpro_id": "IPR045684", "known_evidence_count": null, "matches": 1379, "name": "Family of unknown function (DUF6191)", "partial_evidence_count": null, "pfam_id": "PF19690", "proteins": 1379, "proteomes": 1060, "short_name": "DUF6191", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19690", "structures": 0, "taxa": 1250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 784, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 70 amino acids in length.", "domain_architectures": 75, "interpro_id": "IPR022124", "known_evidence_count": null, "matches": 9374, "name": "Protein of unknown function (DUF3659)", "partial_evidence_count": null, "pfam_id": "PF12396", "proteins": 1378, "proteomes": 824, "short_name": "DUF3659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12396", "structures": 0, "taxa": 1647, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 803, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Firmicutes. Several members are annotated as YppC. The function is not known.", "domain_architectures": 9, "interpro_id": "IPR019658", "known_evidence_count": null, "matches": 1415, "name": "Protein of unknown function (DUF2515)", "partial_evidence_count": null, "pfam_id": "PF10720", "proteins": 1377, "proteomes": 1025, "short_name": "DUF2515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10720", "structures": 0, "taxa": 1392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 915, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins have no known function.", "domain_architectures": 2, "interpro_id": "IPR021263", "known_evidence_count": null, "matches": 1377, "name": "Protein of unknown function (DUF2840)", "partial_evidence_count": null, "pfam_id": "PF11000", "proteins": 1377, "proteomes": 862, "short_name": "DUF2840", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11000", "structures": 0, "taxa": 1441, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharcaterised fungal proteins.", "domain_architectures": 17, "interpro_id": "IPR061828", "known_evidence_count": null, "matches": 1379, "name": "Family of unknown function (DUF8767)", "partial_evidence_count": null, "pfam_id": "PF30969", "proteins": 1377, "proteomes": 1321, "short_name": "DUF8767", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30969", "structures": 0, "taxa": 2918, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1234, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical eukaryotic proteins of around 125 residues in length. The function of this family is unknown.", "domain_architectures": 15, "interpro_id": "IPR009792", "known_evidence_count": null, "matches": 1386, "name": "Protein of unknown function (DUF1358)", "partial_evidence_count": null, "pfam_id": "PF07096", "proteins": 1375, "proteomes": 1116, "short_name": "DUF1358", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07096", "structures": 0, "taxa": 3770, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 819, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in bacteroides. Proteins in this family are typically around 440 amino acids in length.", "domain_architectures": 71, "interpro_id": "IPR032169", "known_evidence_count": null, "matches": 1384, "name": "Domain of unknown function (DUF5005)", "partial_evidence_count": null, "pfam_id": "PF16396", "proteins": 1375, "proteomes": 1080, "short_name": "DUF5005", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16396", "structures": 1, "taxa": 1728, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 843, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 80 amino acids in length. The family is found in association with [pfam:PF00883]. There is a conserved WAF sequence motif.", "domain_architectures": 3, "interpro_id": "IPR047620", "known_evidence_count": null, "matches": 1373, "name": "Peptidase", "partial_evidence_count": null, "pfam_id": "PF12404", "proteins": 1373, "proteomes": 1262, "short_name": "DUF3663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12404", "structures": 3, "taxa": 1750, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 881, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 164 and 196 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025347", "known_evidence_count": null, "matches": 1373, "name": "Domain of unknown function (DUF4251)", "partial_evidence_count": null, "pfam_id": "PF14059", "proteins": 1373, "proteomes": 1123, "short_name": "DUF4251", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14059", "structures": 2, "taxa": 1452, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 428, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a large potential domain found in a wide range of uncharacterised fungal proteins.", "domain_architectures": 21, "interpro_id": "IPR046538", "known_evidence_count": null, "matches": 1408, "name": "Family of unknown function (DUF6603)", "partial_evidence_count": null, "pfam_id": "PF20248", "proteins": 1372, "proteomes": 1008, "short_name": "DUF6603", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20248", "structures": 0, "taxa": 2043, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 633, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins that belong to the GT- superfamily of glycosyltransferases.", "domain_architectures": 4, "interpro_id": "IPR046561", "known_evidence_count": null, "matches": 1388, "name": "Putative glycosyltransferase (DUF6716)", "partial_evidence_count": null, "pfam_id": "PF20471", "proteins": 1371, "proteomes": 1268, "short_name": "DUF6716", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20471", "structures": 0, "taxa": 1548, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 882, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 9, "interpro_id": "IPR018739", "known_evidence_count": null, "matches": 1372, "name": "Protein of unknown function (DUF2281)", "partial_evidence_count": null, "pfam_id": "PF10047", "proteins": 1368, "proteomes": 709, "short_name": "DUF2281", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10047", "structures": 0, "taxa": 1697, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is an N-terminal domain found in C7orf25 protein UPF0415. It is distantly related to the PD-(D/E)XK nucleases [[cite:PUB00091006]].", "domain_architectures": 27, "interpro_id": "IPR041076", "known_evidence_count": null, "matches": 1375, "name": "Family of unknown function (DUF5614)", "partial_evidence_count": null, "pfam_id": "PF18474", "proteins": 1368, "proteomes": 1160, "short_name": "DUF5614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18474", "structures": 0, "taxa": 3892, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 850, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in diverse proteins across Bacteria. The domain is around 95-100 residues in length and is found in mechanosensitive channel proteins, where it is located N-terminal to the mechanosensitive channel second transmembrane helix domain ([pfam:PF00924]), and in endolytic peptidoglycan transglycosylases such as RlpA, where it precedes the double-psi beta-barrel domain ([pfam:PF03330]). The domain is found across Cyanobacteriota, Bacteroidota and Pseudomonadota. The function of this domain remains to be determined.", "domain_architectures": 17, "interpro_id": "IPR061529", "known_evidence_count": null, "matches": 1367, "name": "Domain of unknown function (DUF8459)", "partial_evidence_count": null, "pfam_id": "PF28776", "proteins": 1367, "proteomes": 1025, "short_name": "DUF8459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28776", "structures": 0, "taxa": 1991, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 748, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical bacterial proteins of unknown function.", "domain_architectures": 5, "interpro_id": "IPR010595", "known_evidence_count": null, "matches": 1372, "name": "Protein of unknown function (DUF1161)", "partial_evidence_count": null, "pfam_id": "PF06649", "proteins": 1366, "proteomes": 1038, "short_name": "DUF1161", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06649", "structures": 0, "taxa": 1354, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 871, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR033437", "known_evidence_count": null, "matches": 1365, "name": "Domain of unknown function (DUF5130)", "partial_evidence_count": null, "pfam_id": "PF17174", "proteins": 1365, "proteomes": 1359, "short_name": "DUF5130", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17174", "structures": 16, "taxa": 1633, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 830, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR006542", "known_evidence_count": null, "matches": 1364, "name": "Protein of unknown function (DUF1093)", "partial_evidence_count": null, "pfam_id": "PF06486", "proteins": 1364, "proteomes": 741, "short_name": "DUF1093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06486", "structures": 3, "taxa": 1141, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 872, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 90 residues in length and is mainly found in various Parabacteroides and Bacteroides species. Protein in this family are characterized by a strongly conserved KDEGEYVD motif on the C-terminal and a very divergent N-terminal. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032272", "known_evidence_count": null, "matches": 1362, "name": "Domain of unknown function (DUF4834)", "partial_evidence_count": null, "pfam_id": "PF16118", "proteins": 1362, "proteomes": 1351, "short_name": "DUF4834", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16118", "structures": 0, "taxa": 1836, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins, mainly from fungi. This domain may consist of beta-solenoid repeats. This entry shows distant similarity to [pfam:PF13349].", "domain_architectures": 29, "interpro_id": "IPR055754", "known_evidence_count": null, "matches": 1388, "name": "Domain of unknown function (DUF7330)", "partial_evidence_count": null, "pfam_id": "PF24016", "proteins": 1359, "proteomes": 302, "short_name": "DUF7330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24016", "structures": 0, "taxa": 812, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family represents the N-terminal domain of the RING finger protein 37 (RNF37), an U-box domain-containing protein. This is a variable region that probably has a role in function regulation [[cite:PUB00054319]].", "domain_architectures": 36, "interpro_id": "IPR045696", "known_evidence_count": null, "matches": 1492, "name": "Family of unknown function (DUF5918)", "partial_evidence_count": null, "pfam_id": "PF19318", "proteins": 1357, "proteomes": 1020, "short_name": "DUF5918", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19318", "structures": 0, "taxa": 3390, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 659, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in actinobacteria. The family is found in association with [pfam:PF01066]. This entry contains several transmembrane helices.", "domain_architectures": 4, "interpro_id": "IPR045985", "known_evidence_count": null, "matches": 1357, "name": "Family of unknown function (DUF5941)", "partial_evidence_count": null, "pfam_id": "PF19365", "proteins": 1356, "proteomes": 1216, "short_name": "DUF5941", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19365", "structures": 0, "taxa": 1375, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 876, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 200 residues in length. The function of this family is unknown. This family is related to [pfam:PF00877].", "domain_architectures": 3, "interpro_id": "IPR009706", "known_evidence_count": null, "matches": 1355, "name": "Domain of unknown function (DUF1287)", "partial_evidence_count": null, "pfam_id": "PF06940", "proteins": 1355, "proteomes": 1291, "short_name": "DUF1287", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06940", "structures": 0, "taxa": 2188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 120 amino acids in length. The family is found in association with [pfam:PF02754], [pfam:PF01565], [pfam:PF02913].", "domain_architectures": 10, "interpro_id": "IPR022153", "known_evidence_count": null, "matches": 1355, "name": "Protein of unknown function (DUF3683)", "partial_evidence_count": null, "pfam_id": "PF12447", "proteins": 1355, "proteomes": 1350, "short_name": "DUF3683", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12447", "structures": 0, "taxa": 1891, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 848, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes uncharacterised fungal sequences which consist of repeats that may adopt an alpha-solenoid structure related to ankirin repeats. The overall arrangement of these repeats may have a horseshoe conformation similar to that in leucine-rich repeats.", "domain_architectures": 465, "interpro_id": "IPR055530", "known_evidence_count": null, "matches": 8146, "name": "Domain of unknown function (DUF7104)", "partial_evidence_count": null, "pfam_id": "PF23397", "proteins": 1355, "proteomes": 441, "short_name": "DUF7104", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23397", "structures": 0, "taxa": 904, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to fold into a structure consisting of six transmembrane helices.", "domain_architectures": 14, "interpro_id": "IPR056635", "known_evidence_count": null, "matches": 1382, "name": "Domain of unknown function (DUF7733)", "partial_evidence_count": null, "pfam_id": "PF24867", "proteins": 1354, "proteomes": 396, "short_name": "DUF7733", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24867", "structures": 0, "taxa": 1133, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function. The precise function of the protein domain remains to be elucidated. This family of proteins is found in eukaryotes and are typically between 215 and 293 amino acids in length. The protein contains two conserved sequence motifs: SSS and KST.", "domain_architectures": 5, "interpro_id": "IPR027997", "known_evidence_count": null, "matches": 1493, "name": "Domain of unknown function (DUF4589)", "partial_evidence_count": null, "pfam_id": "PF15252", "proteins": 1353, "proteomes": 679, "short_name": "DUF4589", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15252", "structures": 0, "taxa": 2095, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 753, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins remains to be characterised and is a domain of unknown function. This domain family is found in eukaryotes, and is approximately 120 amino acids in length. There are two conserved sequence motifs: CCE and PCY. In humans, the gene encoding this protein lies in the position, chromosome 1 open reading frame 173.", "domain_architectures": 46, "interpro_id": "IPR048257", "known_evidence_count": null, "matches": 1354, "name": "Domain of unknown function (DUF4590)", "partial_evidence_count": null, "pfam_id": "PF15257", "proteins": 1352, "proteomes": 814, "short_name": "DUF4590", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15257", "structures": 0, "taxa": 2665, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 885, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Alphaproteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021473", "known_evidence_count": null, "matches": 1382, "name": "Protein of unknown function (DUF3126)", "partial_evidence_count": null, "pfam_id": "PF11324", "proteins": 1349, "proteomes": 1349, "short_name": "DUF3126", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11324", "structures": 0, "taxa": 1869, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 828, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family consists of uncharacterised bacterial proteins mainly found in Proteobacteria, including YcfL from Escherichia coli and Putative lipoprotein from Campylobacter jejuni. This protein adopts a single domain configuration with two beta-sheets formed respectively by three and four beta-strands (beta-sandwich) and contains a Greek key motif, representing a singular variant of the Ig-like fold. Many proteins of this group have a lipid attachment site at the N-terminal of this domain, which together with the structure solved, suggests a role in bacterial lipoproteins [[cite:PUB00100676]].", "domain_architectures": 5, "interpro_id": "IPR010824", "known_evidence_count": null, "matches": 1348, "name": "Protein of unknown function (DUF1425)", "partial_evidence_count": null, "pfam_id": "PF07233", "proteins": 1348, "proteomes": 1336, "short_name": "DUF1425", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07233", "structures": 2, "taxa": 1945, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 714, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 180 residues in length and is mainly found in various Bacillus species. Distant homology and fold prediction suggests proteins from this family would have a ferrodoxin dimeric fold and specifically be related to the putative mono-oxygenase ydhR family PF08803, however this prediction has not been verified by experiment", "domain_architectures": 2, "interpro_id": "IPR032349", "known_evidence_count": null, "matches": 1354, "name": "Domain of unknown function (DUF4865)", "partial_evidence_count": null, "pfam_id": "PF16157", "proteins": 1348, "proteomes": 1328, "short_name": "DUF4865", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16157", "structures": 0, "taxa": 1903, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 915, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is the C-terminal domain found in the uncharacterised protein family UPF0371. It has a cytidine deaminase-like fold (pdbe:3bh1).", "domain_architectures": 3, "interpro_id": "IPR048441", "known_evidence_count": null, "matches": 1348, "name": "Domain of unknown function DUF1846, C-terminal", "partial_evidence_count": null, "pfam_id": "PF20921", "proteins": 1348, "proteomes": 1316, "short_name": "DUF1846_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20921", "structures": 2, "taxa": 2139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 915, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in a family of proteins that are functionally uncharacterised, known as UPF0371. Some members of the family are annotated as ATP-dependent peptidases. This is a P-loop-like domain (pdbe:3BH1).", "domain_architectures": 3, "interpro_id": "IPR048496", "known_evidence_count": null, "matches": 1347, "name": "Domain of unknown function DUF1846, N-terminal", "partial_evidence_count": null, "pfam_id": "PF08903", "proteins": 1347, "proteomes": 1315, "short_name": "DUF1846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08903", "structures": 2, "taxa": 2136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 861, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 80 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR024568", "known_evidence_count": null, "matches": 1347, "name": "Domain of unknown function (DUF3378)", "partial_evidence_count": null, "pfam_id": "PF11858", "proteins": 1347, "proteomes": 1291, "short_name": "DUF3378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11858", "structures": 5, "taxa": 1944, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 711, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 150 residues in length and is mainly found in various Arthrobacter species. The function of this family may be functional in enableing the growth of Arthrobacter sp. strain JBH1 with nitroglycerin as the sole source of carbon and nitrogen [[cite:PUB00076537]].", "domain_architectures": 5, "interpro_id": "IPR032584", "known_evidence_count": null, "matches": 1388, "name": "Domain of unknown function (DUF4913)", "partial_evidence_count": null, "pfam_id": "PF16259", "proteins": 1346, "proteomes": 955, "short_name": "DUF4913", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16259", "structures": 0, "taxa": 1261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1022, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 68 and 87 amino acids in length. There are two completely conserved residues (G and E) that may be functionally important.", "domain_architectures": 19, "interpro_id": "IPR025016", "known_evidence_count": null, "matches": 1345, "name": "Protein of unknown function (DUF3955)", "partial_evidence_count": null, "pfam_id": "PF13127", "proteins": 1345, "proteomes": 1284, "short_name": "DUF3955", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13127", "structures": 0, "taxa": 2539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1099, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha- helical array flanked on one side with a three- stranded small beta-sheet.", "domain_architectures": 26, "interpro_id": "IPR058345", "known_evidence_count": null, "matches": 2102, "name": "Domain of unknown function (DUF8032)", "partial_evidence_count": null, "pfam_id": "PF26087", "proteins": 1344, "proteomes": 1042, "short_name": "DUF8032", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26087", "structures": 0, "taxa": 2102, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 818, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria and eukaryotes. This domain is typically between 289 to 301 amino acids in length. This domain is found associated with [pfam:PF01926]. The central region of these proteins contains a hydrophobic region that is similar to [pfam:PF05433].", "domain_architectures": 6, "interpro_id": "IPR021871", "known_evidence_count": null, "matches": 1344, "name": "Domain of unknown function (DUF3482)", "partial_evidence_count": null, "pfam_id": "PF11981", "proteins": 1343, "proteomes": 1337, "short_name": "DUF3482", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11981", "structures": 0, "taxa": 1913, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 963, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Hypothetical archaeal and bacterial proteins make up this family. A few proteins are annotated as being potential metal-binding proteins, and in fact the members of this family have four highly conserved cysteine residues, but no further literature evidence was found in this regard.", "domain_architectures": 6, "interpro_id": "IPR012460", "known_evidence_count": null, "matches": 1342, "name": "Protein of unknown function (DUF1667)", "partial_evidence_count": null, "pfam_id": "PF07892", "proteins": 1342, "proteomes": 961, "short_name": "DUF1667", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07892", "structures": 1, "taxa": 1865, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 906, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The function of this family is unknown but members are annotated as putative lipoprotein outer membrane proteins.", "domain_architectures": 2, "interpro_id": "IPR025294", "known_evidence_count": null, "matches": 1342, "name": "Domain of unknown function (DUF4156)", "partial_evidence_count": null, "pfam_id": "PF13698", "proteins": 1342, "proteomes": 1228, "short_name": "DUF4156", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13698", "structures": 0, "taxa": 1826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 865, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteobacterial species proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021735", "known_evidence_count": null, "matches": 1341, "name": "Protein of unknown function (DUF3306)", "partial_evidence_count": null, "pfam_id": "PF11748", "proteins": 1341, "proteomes": 1304, "short_name": "DUF3306", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11748", "structures": 0, "taxa": 1847, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 896, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal putative sensor domain found in histidine kinase proteins. This domain precedes the histidine kinase A (HisKA) phosphoacceptor domain ([pfam:PF00512]) and the histidine kinase ATPase C-terminal domain ([pfam:PF02518]). The domain is approximately 145-155 residues in length. This family is found predominantly in Bacteroidota, particularly in the orders Flavobacteriales, Cytophagales and Sphingobacteriales. The function of this sensor domain remains to be determined.", "domain_architectures": 7, "interpro_id": "IPR061556", "known_evidence_count": null, "matches": 1341, "name": "Domain of unknown function (DUF8486)", "partial_evidence_count": null, "pfam_id": "PF28961", "proteins": 1341, "proteomes": 1029, "short_name": "DUF8486", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28961", "structures": 0, "taxa": 1399, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 912, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 99 to 124 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR021784", "known_evidence_count": null, "matches": 1400, "name": "Protein of unknown function (DUF3349)", "partial_evidence_count": null, "pfam_id": "PF11829", "proteins": 1336, "proteomes": 732, "short_name": "DUF3349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11829", "structures": 5, "taxa": 1006, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 942, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in bacteria is functionally uncharacterised. Proteins in this family are approximately 180 amino acids in length. There are two conserved sequence motifs, ExxQN and GAGLG.", "domain_architectures": 3, "interpro_id": "IPR046239", "known_evidence_count": null, "matches": 1338, "name": "Family of unknown function (DUF6272)", "partial_evidence_count": null, "pfam_id": "PF19788", "proteins": 1335, "proteomes": 1049, "short_name": "DUF6272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19788", "structures": 1, "taxa": 1890, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 911, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 98 to 126 amino acids in length. This protein has a conserved FRP sequence motif.", "domain_architectures": 2, "interpro_id": "IPR021969", "known_evidence_count": null, "matches": 1334, "name": "Protein of unknown function (DUF3579)", "partial_evidence_count": null, "pfam_id": "PF12112", "proteins": 1334, "proteomes": 1248, "short_name": "DUF3579", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12112", "structures": 1, "taxa": 1666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 847, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 2, "interpro_id": "IPR014582", "known_evidence_count": null, "matches": 1333, "name": "Predicted periplasmic lipoprotein (DUF2291)", "partial_evidence_count": null, "pfam_id": "PF10054", "proteins": 1333, "proteomes": 1101, "short_name": "DUF2291", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10054", "structures": 1, "taxa": 1831, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 899, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_0094, a putative uncharacterized protein as seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), It appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011]][[cite:PUB00056012]].", "domain_architectures": 2, "interpro_id": "IPR025407", "known_evidence_count": null, "matches": 1333, "name": "Domain of unknown function (DUF4133)", "partial_evidence_count": null, "pfam_id": "PF13571", "proteins": 1333, "proteomes": 772, "short_name": "DUF4133", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13571", "structures": 0, "taxa": 1036, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 772, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. Some members are thought to be membrane proteins however this cannot be confirmed.", "domain_architectures": 1, "interpro_id": "IPR021329", "known_evidence_count": null, "matches": 1332, "name": "Protein of unknown function (DUF2938)", "partial_evidence_count": null, "pfam_id": "PF11158", "proteins": 1332, "proteomes": 1267, "short_name": "DUF2938", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11158", "structures": 0, "taxa": 1990, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 833, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021330", "known_evidence_count": null, "matches": 1331, "name": "Protein of unknown function (DUF2939)", "partial_evidence_count": null, "pfam_id": "PF11159", "proteins": 1331, "proteomes": 1193, "short_name": "DUF2939", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11159", "structures": 0, "taxa": 1711, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 964, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in a group of uncharacterised prokaryotic proteins. Proteins in this group are thought to mediate flavinylation-associated electron transfer in the cytoplasmic membrane and constitute a novel class of cytochromes. There are two conserved histidines in this domain, which are predicted to bind to two haem cofactors [[cite:PUB00160945]].", "domain_architectures": 10, "interpro_id": "IPR025517", "known_evidence_count": null, "matches": 1335, "name": "Domain of unknown function (DUF4405)", "partial_evidence_count": null, "pfam_id": "PF14358", "proteins": 1330, "proteomes": 1115, "short_name": "DUF4405", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14358", "structures": 0, "taxa": 2418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 846, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes small functionally uncharacterised proteins around 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR014949", "known_evidence_count": null, "matches": 1329, "name": "Domain of unknown function (DUF1820)", "partial_evidence_count": null, "pfam_id": "PF08850", "proteins": 1329, "proteomes": 1328, "short_name": "DUF1820", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08850", "structures": 0, "taxa": 1908, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 867, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes.", "domain_architectures": 1, "interpro_id": "IPR021324", "known_evidence_count": null, "matches": 1329, "name": "Protein of unknown function (DUF2929)", "partial_evidence_count": null, "pfam_id": "PF11151", "proteins": 1329, "proteomes": 1328, "short_name": "DUF2929", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11151", "structures": 0, "taxa": 1752, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 894, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a region of unknown function found in proteins from fungi and bacteria. This region is composed of a pair of two flattened, orthogonally packed, beta-barrels that share significant global similarity to members of the AttH-like superfamily. It is likely that this region possesses enzymatic activity.", "domain_architectures": 14, "interpro_id": "IPR055492", "known_evidence_count": null, "matches": 1330, "name": "Domain of unknown function (DUF7064)", "partial_evidence_count": null, "pfam_id": "PF23212", "proteins": 1329, "proteomes": 711, "short_name": "DUF7064", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23212", "structures": 0, "taxa": 1353, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 904, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 16, "interpro_id": "IPR019268", "known_evidence_count": null, "matches": 1332, "name": "Uncharacterized conserved protein (DUF2278)", "partial_evidence_count": null, "pfam_id": "PF10042", "proteins": 1328, "proteomes": 1146, "short_name": "DUF2278", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10042", "structures": 0, "taxa": 2003, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 813, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 310 and 334 amino acids in length. Advanced homology-detection methods supported with superfamily-wide domain architecture and horizontal gene transfer analyses have established this family to be a member of the PD-(D/E)XK superfamily.", "domain_architectures": 1, "interpro_id": "IPR025534", "known_evidence_count": null, "matches": 1328, "name": "Putative PD-(D/E)XK family member, (DUF4420)", "partial_evidence_count": null, "pfam_id": "PF14390", "proteins": 1328, "proteomes": 1294, "short_name": "DUF4420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14390", "structures": 0, "taxa": 2497, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is a fungal domain of unknown function. This domain can be found in DSC E3 ubiquitin ligase complex subunit 4 (Dsc4) from S. pombe, a component of the DSC E3 ubiquitin ligase complex required for the sre1 transcriptional activator proteolytic cleavage to release the soluble transcription factor from the membrane in low oxygen or sterol conditions. The complex plays also an important role in the multivesicular body (MVB) pathway and functions in a post-endoplasmic reticulum pathway for protein degradation [[cite:PUB00075404]]. This domain is also found in GLD1 from S. cerevisiae, also a component of the DSC E3 ubiquitin ligase complex involved in the targeting of the DSC complex to the Golgi apparatus and endosome membranes via the AP3 pathway to ubiquitinate Golgi/endosome membrane proteins [[cite:PUB00098082]].", "domain_architectures": 20, "interpro_id": "IPR013715", "known_evidence_count": null, "matches": 1353, "name": "Fungal domain of unknown function (DUF1746)", "partial_evidence_count": null, "pfam_id": "PF08508", "proteins": 1326, "proteomes": 1282, "short_name": "DUF1746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08508", "structures": 0, "taxa": 2736, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 816, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009525", "known_evidence_count": null, "matches": 1323, "name": "Protein of unknown function (DUF1145)", "partial_evidence_count": null, "pfam_id": "PF06611", "proteins": 1323, "proteomes": 1279, "short_name": "DUF1145", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06611", "structures": 0, "taxa": 1657, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The function of this protein remains unknown. This family of proteins is found in eukaryotes and are typically between 160 and 182 amino acids in length.", "domain_architectures": 22, "interpro_id": "IPR026794", "known_evidence_count": null, "matches": 1344, "name": "Domain of unknown function (DUF4517)", "partial_evidence_count": null, "pfam_id": "PF15006", "proteins": 1321, "proteomes": 887, "short_name": "DUF4517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15006", "structures": 0, "taxa": 3033, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 794, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as putative membrane proteins. However, this cannot be confirmed.", "domain_architectures": 5, "interpro_id": "IPR021296", "known_evidence_count": null, "matches": 1334, "name": "Protein of unknown function (DUF2868)", "partial_evidence_count": null, "pfam_id": "PF11067", "proteins": 1319, "proteomes": 1310, "short_name": "DUF2868", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11067", "structures": 0, "taxa": 1867, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 771, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 335 and 392 amino acids in length. There is a conserved GLRGPV sequence motif.", "domain_architectures": 40, "interpro_id": "IPR022060", "known_evidence_count": null, "matches": 1425, "name": "Protein of unknown function (DUF3616)", "partial_evidence_count": null, "pfam_id": "PF12275", "proteins": 1318, "proteomes": 1200, "short_name": "DUF3616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12275", "structures": 0, "taxa": 2029, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 166 and 225 amino acids in length.", "domain_architectures": 30, "interpro_id": "IPR028108", "known_evidence_count": null, "matches": 1368, "name": "Domain of unknown function (DUF4505)", "partial_evidence_count": null, "pfam_id": "PF14956", "proteins": 1318, "proteomes": 1151, "short_name": "DUF4505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14956", "structures": 0, "taxa": 3844, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 785, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 5, "interpro_id": "IPR018715", "known_evidence_count": null, "matches": 1326, "name": "Uncharacterized protein conserved in bacteria (DUF2239)", "partial_evidence_count": null, "pfam_id": "PF09998", "proteins": 1317, "proteomes": 1284, "short_name": "DUF2239", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09998", "structures": 0, "taxa": 1934, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 867, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 505 and 516 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025393", "known_evidence_count": null, "matches": 1319, "name": "Domain of unknown function (DUF4301)", "partial_evidence_count": null, "pfam_id": "PF14134", "proteins": 1316, "proteomes": 1292, "short_name": "DUF4301", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14134", "structures": 0, "taxa": 1860, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 884, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 6, "interpro_id": "IPR021409", "known_evidence_count": null, "matches": 1317, "name": "Protein of unknown function (DUF3047)", "partial_evidence_count": null, "pfam_id": "PF11249", "proteins": 1314, "proteomes": 1129, "short_name": "DUF3047", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11249", "structures": 0, "taxa": 1944, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 50 amino acids in length. This domain is found associated with [pfam:PF02754], [pfam:PF02913], [pfam:PF01565].", "domain_architectures": 9, "interpro_id": "IPR021817", "known_evidence_count": null, "matches": 1312, "name": "Domain of unknown function (DUF3400)", "partial_evidence_count": null, "pfam_id": "PF11880", "proteins": 1312, "proteomes": 1301, "short_name": "DUF3400", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11880", "structures": 0, "taxa": 1767, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 849, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised membrane spanning beta barrel proteins. This family of proteins is primarily found in Bacteroidetes bacteria. Proteins in this family are typically between 228 and 255 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046111", "known_evidence_count": null, "matches": 1312, "name": "Domain of unknown function (DUF6048)", "partial_evidence_count": null, "pfam_id": "PF19515", "proteins": 1312, "proteomes": 1284, "short_name": "DUF6048", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19515", "structures": 0, "taxa": 1672, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 181 and 876 amino acids in length.", "domain_architectures": 19, "interpro_id": "IPR028026", "known_evidence_count": null, "matches": 1362, "name": "Domain of unknown function (DUF4502)", "partial_evidence_count": null, "pfam_id": "PF14950", "proteins": 1311, "proteomes": 745, "short_name": "DUF4502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14950", "structures": 0, "taxa": 2416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1092, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in the uncharacterised protein At4g14100 from Arabidopsis thaliana and similar plant sequences. It is predicted to form unclosed beta-barrel and an alpha-helical lid. Its function is unknown.", "domain_architectures": 29, "interpro_id": "IPR059439", "known_evidence_count": null, "matches": 1332, "name": "Domain of unknown function (DUF8395)", "partial_evidence_count": null, "pfam_id": "PF28435", "proteins": 1309, "proteomes": 431, "short_name": "DUF8395", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28435", "structures": 0, "taxa": 1287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 788, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in various bacterial hypothetical proteins, as well as putative ankyrin repeat proteins. The exact function of the domains comprising this family has not, as yet, been determined.", "domain_architectures": 13, "interpro_id": "IPR018756", "known_evidence_count": null, "matches": 1308, "name": "Uncharacterized protein conserved in bacteria (DUF2314)", "partial_evidence_count": null, "pfam_id": "PF10077", "proteins": 1308, "proteomes": 1117, "short_name": "DUF2314", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10077", "structures": 0, "taxa": 1833, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1016, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 149 to 199 amino acids in length.", "domain_architectures": 26, "interpro_id": "IPR021920", "known_evidence_count": null, "matches": 1318, "name": "Protein of unknown function (DUF3531)", "partial_evidence_count": null, "pfam_id": "PF12049", "proteins": 1308, "proteomes": 657, "short_name": "DUF3531", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12049", "structures": 0, "taxa": 1795, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 836, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR043742", "known_evidence_count": null, "matches": 1308, "name": "Family of unknown function (DUF5687)", "partial_evidence_count": null, "pfam_id": "PF18940", "proteins": 1308, "proteomes": 1290, "short_name": "DUF5687", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18940", "structures": 0, "taxa": 1646, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 710, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of bacterial proteins of unknown function.", "domain_architectures": 5, "interpro_id": "IPR021733", "known_evidence_count": null, "matches": 1313, "name": "Protein of unknown function (DUF3304)", "partial_evidence_count": null, "pfam_id": "PF11745", "proteins": 1305, "proteomes": 456, "short_name": "DUF3304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11745", "structures": 0, "taxa": 728, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 990, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 180 and 205 amino acids in length. There are two completely conserved residues (W and G) that may be functionally important.", "domain_architectures": 19, "interpro_id": "IPR022051", "known_evidence_count": null, "matches": 1331, "name": "Protein of unknown function (DUF3611)", "partial_evidence_count": null, "pfam_id": "PF12263", "proteins": 1305, "proteomes": 735, "short_name": "DUF3611", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12263", "structures": 0, "taxa": 2058, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 826, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 187 and 201 amino acids in length. There is a single completely conserved residue Q that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR025570", "known_evidence_count": null, "matches": 1309, "name": "Domain of unknown function (DUF4337)", "partial_evidence_count": null, "pfam_id": "PF14235", "proteins": 1305, "proteomes": 1149, "short_name": "DUF4337", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14235", "structures": 0, "taxa": 1789, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1080, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised fungal proteins. It is predicted to adopt an all-alpha configuration.", "domain_architectures": 16, "interpro_id": "IPR056019", "known_evidence_count": null, "matches": 1306, "name": "Domain of unknown function (DUF7598)", "partial_evidence_count": null, "pfam_id": "PF24535", "proteins": 1304, "proteomes": 1084, "short_name": "DUF7598", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24535", "structures": 0, "taxa": 2246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 793, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in bacteria. The function is not known, but several members are annotated as being YdgK or a homologue thereof.", "domain_architectures": 13, "interpro_id": "IPR019690", "known_evidence_count": null, "matches": 1301, "name": "Protein of unknown function (DUF2569)", "partial_evidence_count": null, "pfam_id": "PF10754", "proteins": 1301, "proteomes": 1104, "short_name": "DUF2569", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10754", "structures": 0, "taxa": 1736, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 851, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins. They are predicted to adopt a globular structure consisting of two domains. The predicted C-terminal domain share similarity with the catalytic domains of purine and uridine phosphorylases.", "domain_architectures": 5, "interpro_id": "IPR054204", "known_evidence_count": null, "matches": 2471, "name": "Family of unknown function (DUF6909)", "partial_evidence_count": null, "pfam_id": "PF21850", "proteins": 1301, "proteomes": 1262, "short_name": "DUF6909", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21850", "structures": 0, "taxa": 1816, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1051, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of fungal domains adopt a structure that consists of an alpha/beta motif. Their exact function has not, as yet, been determined [[cite:PUB00027613]].", "domain_architectures": 28, "interpro_id": "IPR015328", "known_evidence_count": null, "matches": 1300, "name": "Domain of unknown function (DUF1965)", "partial_evidence_count": null, "pfam_id": "PF09248", "proteins": 1300, "proteomes": 815, "short_name": "DUF1965", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09248", "structures": 4, "taxa": 2003, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 870, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function. They have similarity to catalytic domains of enzymes members of the Zn-dependent exopeptidases clan.", "domain_architectures": 13, "interpro_id": "IPR021259", "known_evidence_count": null, "matches": 1329, "name": "Protein of unknown function (DUF2817)", "partial_evidence_count": null, "pfam_id": "PF10994", "proteins": 1300, "proteomes": 1071, "short_name": "DUF2817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10994", "structures": 0, "taxa": 1886, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1058, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 8 } }, "demotion_reasons": [], "description": "This is a C-terminal domain conserved in fungi.", "domain_architectures": 23, "interpro_id": "IPR024325", "known_evidence_count": null, "matches": 1791, "name": "Domain of unknown function (DUF3835)", "partial_evidence_count": null, "pfam_id": "PF12927", "proteins": 1300, "proteomes": 1263, "short_name": "DUF3835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12927", "structures": 0, "taxa": 2677, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 777, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR022606", "known_evidence_count": null, "matches": 1299, "name": "Protein of unknown function (DUF2914)", "partial_evidence_count": null, "pfam_id": "PF11141", "proteins": 1299, "proteomes": 1214, "short_name": "DUF2914", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11141", "structures": 0, "taxa": 1812, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 862, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 260 residues in length. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR009574", "known_evidence_count": null, "matches": 1334, "name": "Protein of unknown function (DUF1189)", "partial_evidence_count": null, "pfam_id": "PF06691", "proteins": 1298, "proteomes": 1167, "short_name": "DUF1189", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06691", "structures": 0, "taxa": 1671, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1045, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant proteins. It is predicted to adopt a globular structure with a Cystatin-like topology consisting of a curved four-stranded beta-sheet and an alpha-helix packed on the concave side of it.", "domain_architectures": 27, "interpro_id": "IPR055502", "known_evidence_count": null, "matches": 1304, "name": "Domain of unknown function (DUF7074)", "partial_evidence_count": null, "pfam_id": "PF23269", "proteins": 1298, "proteomes": 371, "short_name": "DUF7074", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23269", "structures": 0, "taxa": 1019, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 619, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001435) is described by MIBiG as an example of the following biosynthetic classes, polyketide and NRP (non-ribosomal peptide). It includes a member from the ikarugamycin biosynthetic gene cluster from Streptomyces sp. ZJ306 and appears to be predominantly found in Actinobacteria [[cite:PUB00099375],[cite:PUB00099373]].", "domain_architectures": 2, "interpro_id": "IPR046151", "known_evidence_count": null, "matches": 1297, "name": "Family of unknown function (DUF6153)", "partial_evidence_count": null, "pfam_id": "PF19650", "proteins": 1296, "proteomes": 1078, "short_name": "DUF6153", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19650", "structures": 0, "taxa": 1335, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 852, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of bacterial proteins, including yfbV from E. coli. YfbV is a membrane protein involved in insulating the chromosome from the TerR macrodomain [[cite:PUB00104115]].", "domain_architectures": 1, "interpro_id": "IPR007334", "known_evidence_count": null, "matches": 1295, "name": "Protein of unknown function, DUF412", "partial_evidence_count": null, "pfam_id": "PF04217", "proteins": 1295, "proteomes": 1250, "short_name": "DUF412", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04217", "structures": 0, "taxa": 1757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 693, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria and viruses. Proteins in this family are typically between 144 to 163 amino acids in length. This protein has a conserved TPRF sequence motif.", "domain_architectures": 7, "interpro_id": "IPR021957", "known_evidence_count": null, "matches": 1308, "name": "Protein of unknown function (DUF3574)", "partial_evidence_count": null, "pfam_id": "PF12098", "proteins": 1295, "proteomes": 1262, "short_name": "DUF3574", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12098", "structures": 0, "taxa": 1992, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria and Chlorobi families. Many members are annotated as being putative DNA helicase-related proteins.", "domain_architectures": 31, "interpro_id": "IPR021754", "known_evidence_count": null, "matches": 1293, "name": "Protein of unknown function (DUF3320)", "partial_evidence_count": null, "pfam_id": "PF11784", "proteins": 1293, "proteomes": 1250, "short_name": "DUF3320", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11784", "structures": 0, "taxa": 2256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 801, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 261 to 275 amino acids in length. This protein is found associated with [pfam:PF01842].", "domain_architectures": 2, "interpro_id": "IPR024514", "known_evidence_count": null, "matches": 1293, "name": "Protein of unknown function (DUF3388)", "partial_evidence_count": null, "pfam_id": "PF11868", "proteins": 1293, "proteomes": 1288, "short_name": "DUF3388", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11868", "structures": 0, "taxa": 1612, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 814, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009507", "known_evidence_count": null, "matches": 1292, "name": "Protein of unknown function (DUF1128)", "partial_evidence_count": null, "pfam_id": "PF06569", "proteins": 1292, "proteomes": 1260, "short_name": "DUF1128", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06569", "structures": 0, "taxa": 1579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 880, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents two tandem domains found at the N-terminal of [swissprot:Q89YF2] described as TraN and related sequences. TraN is encoded by transfer region genes of conjugative transposons of Bacteroides. These tandem domains may have a Ig-like fold.", "domain_architectures": 4, "interpro_id": "IPR061543", "known_evidence_count": null, "matches": 1315, "name": "Domain of unknown function (DUF8473)", "partial_evidence_count": null, "pfam_id": "PF28882", "proteins": 1289, "proteomes": 734, "short_name": "DUF8473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28882", "structures": 0, "taxa": 1018, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 936, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, archaea and eukaryotes, and is approximately 60 amino acids in length.", "domain_architectures": 25, "interpro_id": "IPR016621", "known_evidence_count": null, "matches": 1290, "name": "Domain of unknown function (DUF3783)", "partial_evidence_count": null, "pfam_id": "PF12646", "proteins": 1288, "proteomes": 1077, "short_name": "DUF3783", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12646", "structures": 0, "taxa": 2304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1020, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal beta barrel domain found in DUF3723 proteins found mainly in fungi. This domain is frequently encoded within Starship elements, which are large transposable elements that mobilise accessory genes in fungal genomes [[cite:PUB00163731]]. This domain shows structural similarity to bacterial proteins involved in chromosome stabilisation such as ParB. This suggests this domain may bind to CTP. The function of this domain remains to be determined.", "domain_architectures": 41, "interpro_id": "IPR062922", "known_evidence_count": null, "matches": 1291, "name": "Protein of unknown function (DUF3723) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF29418", "proteins": 1288, "proteomes": 472, "short_name": "DUF3723_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29418", "structures": 0, "taxa": 1054, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 887, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 120 residues in length and is mainly found in various Anabaena and Nostoc species. Distant homology analysis suggests this family is related to NTF2-like proteins and specifically to proteins that bind small molecules.", "domain_architectures": 13, "interpro_id": "IPR032347", "known_evidence_count": null, "matches": 1294, "name": "Domain of unknown function (DUF4864)", "partial_evidence_count": null, "pfam_id": "PF16156", "proteins": 1286, "proteomes": 1242, "short_name": "DUF4864", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16156", "structures": 0, "taxa": 2089, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 488, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in proteins that contain [pfam:PF13569]. The function of this domain is unknown.", "domain_architectures": 9, "interpro_id": "IPR056639", "known_evidence_count": null, "matches": 1286, "name": "Domain of unknown function (DUF7737)", "partial_evidence_count": null, "pfam_id": "PF24879", "proteins": 1286, "proteomes": 1041, "short_name": "DUF7737", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24879", "structures": 0, "taxa": 1672, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 745, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 9, "interpro_id": "IPR016888", "known_evidence_count": null, "matches": 1286, "name": "Uncharacterized protein conserved in bacteria (DUF2255)", "partial_evidence_count": null, "pfam_id": "PF10012", "proteins": 1285, "proteomes": 1092, "short_name": "DUF2255", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10012", "structures": 0, "taxa": 1805, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 224 and 241 amino acids in length. There is a conserved YID sequence motif.", "domain_architectures": 17, "interpro_id": "IPR027887", "known_evidence_count": null, "matches": 1345, "name": "Domain of unknown function (DUF4464)", "partial_evidence_count": null, "pfam_id": "PF14713", "proteins": 1285, "proteomes": 876, "short_name": "DUF4464", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14713", "structures": 5, "taxa": 3040, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 836, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009333", "known_evidence_count": null, "matches": 1283, "name": "Protein of unknown function (DUF992)", "partial_evidence_count": null, "pfam_id": "PF06186", "proteins": 1283, "proteomes": 790, "short_name": "DUF992", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06186", "structures": 0, "taxa": 1079, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 327, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from fungi. It shares a weak sequence similarity with the Ig-like domains found in Trs130, particularly the second Ig-like domain, and it is predicted to adopt a structure with a similar topology.", "domain_architectures": 103, "interpro_id": "IPR055505", "known_evidence_count": null, "matches": 1283, "name": "Domain of unknown function (DUF7077)", "partial_evidence_count": null, "pfam_id": "PF23274", "proteins": 1283, "proteomes": 1257, "short_name": "DUF7077", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23274", "structures": 0, "taxa": 2633, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 920, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a set of bacterial and archaeal proteins that are uncharacterised. Many proteins in the family have a CC-Star motif (Cys-Cys-COOH).", "domain_architectures": 1, "interpro_id": "IPR058303", "known_evidence_count": null, "matches": 1281, "name": "Family of unknown function (DUF7990)", "partial_evidence_count": null, "pfam_id": "PF25952", "proteins": 1281, "proteomes": 1245, "short_name": "DUF7990", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25952", "structures": 0, "taxa": 2044, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 830, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains many hypothetical proteins.", "domain_architectures": 2, "interpro_id": "IPR012543", "known_evidence_count": null, "matches": 1280, "name": "Protein of unknown function (DUF1694)", "partial_evidence_count": null, "pfam_id": "PF07997", "proteins": 1280, "proteomes": 1208, "short_name": "DUF1694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07997", "structures": 1, "taxa": 1712, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 886, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. It belongs to the nucleotidyltransferase superfamily. This family of proteins is found in bacteria, archaea and viruses. Proteins in this family are typically between 172 and 232 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR045792", "known_evidence_count": null, "matches": 1280, "name": "Nucleotidyltransferase of unknown function (DUF6036)", "partial_evidence_count": null, "pfam_id": "PF19502", "proteins": 1280, "proteomes": 1148, "short_name": "DUF6036", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19502", "structures": 0, "taxa": 2460, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 790, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR019617", "known_evidence_count": null, "matches": 1278, "name": "Protein of unknown function (DUF2489)", "partial_evidence_count": null, "pfam_id": "PF10675", "proteins": 1278, "proteomes": 1273, "short_name": "DUF2489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10675", "structures": 0, "taxa": 1732, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 821, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is often found in the N-terminal region of proteins carrying the SET domain ([pfam:PF00856]), such as the SETDB1 protein present in Homo sapiens. SETDB1 is a histone methyltransferase that suppresses gene expression and modulates heterochromatin formation through H3K9me2/3 [[cite:PUB00091314]].", "domain_architectures": 50, "interpro_id": "IPR040880", "known_evidence_count": null, "matches": 1296, "name": "Domain of unknown function (DUF5604)", "partial_evidence_count": null, "pfam_id": "PF18300", "proteins": 1278, "proteomes": 604, "short_name": "DUF5604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18300", "structures": 24, "taxa": 1964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 809, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family contains several hypothetical bacterial proteins of unknown function that are approximately 250 residues long.", "domain_architectures": 3, "interpro_id": "IPR010838", "known_evidence_count": null, "matches": 1278, "name": "Protein of unknown function (DUF1444)", "partial_evidence_count": null, "pfam_id": "PF07285", "proteins": 1277, "proteomes": 1224, "short_name": "DUF1444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07285", "structures": 0, "taxa": 1856, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 864, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in bacteria and archaea, and is approximately 100 amino acids in length. There is a conserved NGPCGG sequence motif. This family is the C terminal of methylene-tetrahydrofolate reductase. This protein reduces FAD using the reducing equivalents from reduced FAD, subsequently reduces tetrahydrofolate. The C terminal of MTHFR contains the FAD binding site and is the catalytic portion of the enzyme.", "domain_architectures": 9, "interpro_id": "IPR022026", "known_evidence_count": null, "matches": 1276, "name": "Methylene-tetrahydrofolate reductase C terminal", "partial_evidence_count": null, "pfam_id": "PF12225", "proteins": 1276, "proteomes": 1049, "short_name": "DUF5981", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12225", "structures": 0, "taxa": 1917, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 769, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 2, "interpro_id": "IPR021450", "known_evidence_count": null, "matches": 1275, "name": "Protein of unknown function (DUF3100)", "partial_evidence_count": null, "pfam_id": "PF11299", "proteins": 1275, "proteomes": 1166, "short_name": "DUF3100", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11299", "structures": 0, "taxa": 1921, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 692, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 294 and 374 amino acids in length.", "domain_architectures": 42, "interpro_id": "IPR022074", "known_evidence_count": null, "matches": 1802, "name": "Protein of unknown function (DUF3626)", "partial_evidence_count": null, "pfam_id": "PF12294", "proteins": 1275, "proteomes": 1115, "short_name": "DUF3626", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12294", "structures": 2, "taxa": 1746, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1118, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins conserved from worms to humans. Its function is unknown.", "domain_architectures": 26, "interpro_id": "IPR018795", "known_evidence_count": null, "matches": 1353, "name": "Uncharacterized conserved protein (DUF2152)", "partial_evidence_count": null, "pfam_id": "PF10222", "proteins": 1274, "proteomes": 909, "short_name": "DUF2152", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10222", "structures": 0, "taxa": 3157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 75 and 88 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR045512", "known_evidence_count": null, "matches": 1272, "name": "Family of unknown function (DUF6480)", "partial_evidence_count": null, "pfam_id": "PF20088", "proteins": 1272, "proteomes": 1143, "short_name": "DUF6480", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20088", "structures": 0, "taxa": 1351, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 803, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found predominantly in Pseudomonadota and Bacillota. Family member SMc00801 from Sinorhizobium meliloti is annotated as a transmembrane protein and is regulated by PhoB, being repressed during phosphate starvation.", "domain_architectures": 6, "interpro_id": "IPR061753", "known_evidence_count": null, "matches": 1280, "name": "Domain of unknown function (DUF8692)", "partial_evidence_count": null, "pfam_id": "PF30663", "proteins": 1272, "proteomes": 1016, "short_name": "DUF8692", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30663", "structures": 0, "taxa": 2109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 776, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 538 to 575 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR021787", "known_evidence_count": null, "matches": 1344, "name": "Protein of unknown function (DUF3352)", "partial_evidence_count": null, "pfam_id": "PF11832", "proteins": 1270, "proteomes": 856, "short_name": "DUF3352", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11832", "structures": 0, "taxa": 1644, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 878, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]]. The C-terminal repeat region of this family is DUF4098, [pfam:PF13345].", "domain_architectures": 9, "interpro_id": "IPR025343", "known_evidence_count": null, "matches": 1271, "name": "Protein of unknown function (DUF4099)", "partial_evidence_count": null, "pfam_id": "PF13351", "proteins": 1269, "proteomes": 610, "short_name": "DUF4099", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13351", "structures": 0, "taxa": 843, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 749, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 14, "interpro_id": "IPR021710", "known_evidence_count": null, "matches": 1268, "name": "Protein of unknown function (DUF3293)", "partial_evidence_count": null, "pfam_id": "PF11697", "proteins": 1268, "proteomes": 1243, "short_name": "DUF3293", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11697", "structures": 0, "taxa": 2023, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 862, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 160 residues in length and is mainly found in various Clostridium species. The function of this family is unknown.", "domain_architectures": 26, "interpro_id": "IPR032585", "known_evidence_count": null, "matches": 1487, "name": "Domain of unknown function (DUF4912)", "partial_evidence_count": null, "pfam_id": "PF16258", "proteins": 1267, "proteomes": 991, "short_name": "DUF4912", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16258", "structures": 0, "taxa": 2005, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1057, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from fungi. It is predicted to adopt globular structure consisting of array of helices.", "domain_architectures": 23, "interpro_id": "IPR056138", "known_evidence_count": null, "matches": 1274, "name": "Domain of unknown function (DUF7721)", "partial_evidence_count": null, "pfam_id": "PF24845", "proteins": 1267, "proteomes": 1171, "short_name": "DUF7721", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24845", "structures": 0, "taxa": 2453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 985, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry includes chloroplastic protein PAM68 and the Sll0933 homolog from Cyanobacteria (blue-green algae) [[cite:PUB00067687]]. PAM68 is involved in early steps in photosystem II (PSII) biogenesis and in maturation and stability of newly synthesized psbA protein [[cite:PUB00086018]].", "domain_architectures": 18, "interpro_id": "IPR021855", "known_evidence_count": null, "matches": 1269, "name": "Photosynthesis affected mutant 68", "partial_evidence_count": null, "pfam_id": "PF11947", "proteins": 1265, "proteomes": 711, "short_name": "DUF3464", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11947", "structures": 0, "taxa": 2035, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 855, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 70 residues in length. Members of this family are often referred to as YejL. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009857", "known_evidence_count": null, "matches": 1264, "name": "Protein of unknown function (DUF1414)", "partial_evidence_count": null, "pfam_id": "PF07208", "proteins": 1264, "proteomes": 1213, "short_name": "DUF1414", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07208", "structures": 7, "taxa": 1690, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function, which is found in eukaryotes. Proteins in this family are typically between 161 and 229 amino acids in length. There is a single completely conserved residue F that may be functionally important.", "domain_architectures": 30, "interpro_id": "IPR029274", "known_evidence_count": null, "matches": 1367, "name": "Domain of unknown function (DUF4615)", "partial_evidence_count": null, "pfam_id": "PF15393", "proteins": 1264, "proteomes": 1023, "short_name": "DUF4615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15393", "structures": 0, "taxa": 3417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1058, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in fungal sequences. It may adopt a Ig-like fold similar to that in Auxiliary Activity family 9 (AA9), [pfam:PF03443].", "domain_architectures": 21, "interpro_id": "IPR055915", "known_evidence_count": null, "matches": 1282, "name": "Domain of unknown function (DUF7492)", "partial_evidence_count": null, "pfam_id": "PF24320", "proteins": 1264, "proteomes": 952, "short_name": "DUF7492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24320", "structures": 0, "taxa": 1865, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 849, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 84 to 211 amino acids in length. This protein has a single completely conserved residue W that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR021880", "known_evidence_count": null, "matches": 1263, "name": "Protein of unknown function (DUF3489)", "partial_evidence_count": null, "pfam_id": "PF11994", "proteins": 1263, "proteomes": 720, "short_name": "DUF3489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11994", "structures": 0, "taxa": 1310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 731, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to adopt a globular structure consisting of five alpha-helices. It is probably distantly related to Wnt domains.", "domain_architectures": 75, "interpro_id": "IPR054246", "known_evidence_count": null, "matches": 1263, "name": "Domain of unknown function (DUF6973)", "partial_evidence_count": null, "pfam_id": "PF22322", "proteins": 1263, "proteomes": 1121, "short_name": "DUF6973", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22322", "structures": 1, "taxa": 1967, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 886, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain found in a family of uncharacterised hypothetical prokaryotic proteins. This domain shows similarity to helicase domains.", "domain_architectures": 25, "interpro_id": "IPR007555", "known_evidence_count": null, "matches": 1331, "name": "DUF499 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF04465", "proteins": 1262, "proteomes": 1122, "short_name": "DUF499", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04465", "structures": 0, "taxa": 2686, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1028, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several plant specific hypothetical proteins of around 160 residues in length. The function of this family is unknown.", "domain_architectures": 19, "interpro_id": "IPR010608", "known_evidence_count": null, "matches": 1275, "name": "Protein of unknown function (DUF1195)", "partial_evidence_count": null, "pfam_id": "PF06708", "proteins": 1262, "proteomes": 363, "short_name": "DUF1195", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06708", "structures": 0, "taxa": 985, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 817, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes. Proteins in this family are typically between 159 and 189 amino acids in length. This proteins contain the conserved motifs PL and SxxCG.", "domain_architectures": 2, "interpro_id": "IPR045607", "known_evidence_count": null, "matches": 1262, "name": "Family of unknown function (DUF6452)", "partial_evidence_count": null, "pfam_id": "PF20050", "proteins": 1262, "proteomes": 1258, "short_name": "DUF6452", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20050", "structures": 0, "taxa": 1630, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 814, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of a group of uncharacterised sequences from actinobacteria. It is normally found associated with [pfam:PF23715].", "domain_architectures": 6, "interpro_id": "IPR055583", "known_evidence_count": null, "matches": 1281, "name": "Family of unknown function (DUF7159)", "partial_evidence_count": null, "pfam_id": "PF23717", "proteins": 1262, "proteomes": 373, "short_name": "DUF7159", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23717", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 688, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is found in bacteria. Proteins in this family are typically between 180 to 701 amino acids in length.", "domain_architectures": 19, "interpro_id": "IPR022081", "known_evidence_count": null, "matches": 1262, "name": "Protein of unknown function (DUF3631)", "partial_evidence_count": null, "pfam_id": "PF12307", "proteins": 1261, "proteomes": 966, "short_name": "DUF3631", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12307", "structures": 0, "taxa": 1476, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 805, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal alpha-helical domain of approximately 130 residues. The domain is found at the C-terminus of proteins that typically contain an AAA_5 domain ([pfam:PF07728]) and sometimes an MrcB_N domain ([pfam:PF12102]). These proteins are often annotated as restriction endonucleases or dynein-related ATPases. This family is found in bacteria including Bacillota, Pseudomonadota and Bacteroidota. The function of this domain remains to be determined.", "domain_architectures": 36, "interpro_id": "IPR061788", "known_evidence_count": null, "matches": 1262, "name": "Domain of unknown function (DUF8727)", "partial_evidence_count": null, "pfam_id": "PF30768", "proteins": 1261, "proteomes": 1172, "short_name": "DUF8727", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30768", "structures": 0, "taxa": 2440, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 814, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family contains a number of hypothetical bacterial proteins of unknown function approximately 120 residues long.", "domain_architectures": 1, "interpro_id": "IPR010899", "known_evidence_count": null, "matches": 1260, "name": "Protein of unknown function (DUF1516)", "partial_evidence_count": null, "pfam_id": "PF07457", "proteins": 1260, "proteomes": 1122, "short_name": "DUF1516", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07457", "structures": 0, "taxa": 1527, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several highly related mouse and human proteins of unknown function.", "domain_architectures": 8, "interpro_id": "IPR008494", "known_evidence_count": null, "matches": 1267, "name": "Protein of unknown function (DUF776)", "partial_evidence_count": null, "pfam_id": "PF05604", "proteins": 1258, "proteomes": 734, "short_name": "DUF776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05604", "structures": 0, "taxa": 2229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 593, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 480 amino acids in length. There are two completely conserved residues (W and P) that may be functionally important.", "domain_architectures": 37, "interpro_id": "IPR028089", "known_evidence_count": null, "matches": 1384, "name": "Domain of unknown function (DUF4455)", "partial_evidence_count": null, "pfam_id": "PF14643", "proteins": 1258, "proteomes": 923, "short_name": "DUF4455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14643", "structures": 3, "taxa": 3090, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 743, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in Rhamnogalacturonan lyase from Bacteroides thetaiotaomicron ([swissprot:Q8AAW3]) and other bacterial proteins. It shows an alpha/beta structure [[cite:PUB00100662]] and locates C-terminal to [pfam:PF07944]. The specific function of this domain is still unknown.", "domain_architectures": 36, "interpro_id": "IPR032275", "known_evidence_count": null, "matches": 1259, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16375", "proteins": 1258, "proteomes": 1087, "short_name": "DUF4986", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16375", "structures": 3, "taxa": 1655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1012, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Fungi. It is predicted to fold into a beta-sandwich with Ig-like topology.", "domain_architectures": 38, "interpro_id": "IPR055560", "known_evidence_count": null, "matches": 1292, "name": "Domain of unknown function (DUF7136)", "partial_evidence_count": null, "pfam_id": "PF23584", "proteins": 1258, "proteomes": 484, "short_name": "DUF7136", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23584", "structures": 0, "taxa": 886, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 799, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They contain highly conserved acidic residues and G[S/A]ID motif at the C terminus.", "domain_architectures": 1, "interpro_id": "IPR053810", "known_evidence_count": null, "matches": 1257, "name": "Family of unknown function (DUF6952)", "partial_evidence_count": null, "pfam_id": "PF22264", "proteins": 1257, "proteomes": 1247, "short_name": "DUF6952", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22264", "structures": 0, "taxa": 1575, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 776, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Proteins in this family are predicted to be integral membrane proteins, and many of them are annotated as being YndM protein. They are all found in Firmicutes. The true function is not known.", "domain_architectures": 2, "interpro_id": "IPR019649", "known_evidence_count": null, "matches": 1263, "name": "Protein of unknown function (DUF2512)", "partial_evidence_count": null, "pfam_id": "PF10710", "proteins": 1256, "proteomes": 790, "short_name": "DUF2512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10710", "structures": 0, "taxa": 1136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 827, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 322 and 336 amino acids in length. There are two conserved sequence motifs: QMW and DLW. Proteins in this family vary in length from 793 to 1184 amino acids.", "domain_architectures": 17, "interpro_id": "IPR027993", "known_evidence_count": null, "matches": 1316, "name": "Domain of unknown function (DUF4495)", "partial_evidence_count": null, "pfam_id": "PF14906", "proteins": 1255, "proteomes": 729, "short_name": "DUF4495", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14906", "structures": 0, "taxa": 2685, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 686, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 139 and 168 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR025361", "known_evidence_count": null, "matches": 1255, "name": "Domain of unknown function (DUF4265)", "partial_evidence_count": null, "pfam_id": "PF14085", "proteins": 1253, "proteomes": 1103, "short_name": "DUF4265", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14085", "structures": 1, "taxa": 1761, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 775, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in bacteria, archaea, alveolata and caudoviruses. Proteins in this family are typically between 133 and 179 amino acids in length.", "domain_architectures": 18, "interpro_id": "IPR043732", "known_evidence_count": null, "matches": 1256, "name": "Family of unknown function (DUF5675)", "partial_evidence_count": null, "pfam_id": "PF18925", "proteins": 1253, "proteomes": 807, "short_name": "DUF5675", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18925", "structures": 0, "taxa": 1485, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 980, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is family consists of a region in several Arabidopsis thaliana hypothetical proteins none of which have any known function. The aligned region contains two cysteine residues. This domain shows structural similarity to members of the Bet v1-like superfamily [[cite:PUB00099734]] and may be involved in lipid binding.", "domain_architectures": 39, "interpro_id": "IPR003863", "known_evidence_count": null, "matches": 1325, "name": "Domain of unknown function DUF220", "partial_evidence_count": null, "pfam_id": "PF02713", "proteins": 1251, "proteomes": 409, "short_name": "DUF220", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02713", "structures": 0, "taxa": 1120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 150 amino acids in length.", "domain_architectures": 24, "interpro_id": "IPR021942", "known_evidence_count": null, "matches": 1437, "name": "Domain of unknown function (DUF3557)", "partial_evidence_count": null, "pfam_id": "PF12078", "proteins": 1251, "proteomes": 11, "short_name": "DUF3557", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12078", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 761, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 113 and 127 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR056091", "known_evidence_count": null, "matches": 1253, "name": "Domain of unknown function (DUF7674)", "partial_evidence_count": null, "pfam_id": "PF24722", "proteins": 1250, "proteomes": 974, "short_name": "DUF7674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24722", "structures": 0, "taxa": 1601, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 686, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically 200 amino acids in length.", "domain_architectures": 37, "interpro_id": "IPR046633", "known_evidence_count": null, "matches": 1257, "name": "Domain of unknown function (DUF6745)", "partial_evidence_count": null, "pfam_id": "PF20530", "proteins": 1248, "proteomes": 949, "short_name": "DUF6745", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20530", "structures": 0, "taxa": 1479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 762, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain represents a small beta barrel domain that is found at the N-terminus of some bacterial peptidase M48 proteins. It has a PH-domain like structure. It likely acts as a chaperone for membrane protein complexes. May interact with [pfam:PF05987] members based on AlphaFold predictions.", "domain_architectures": 3, "interpro_id": "IPR055518", "known_evidence_count": null, "matches": 1247, "name": "Domain of unknown function (DUF7092)", "partial_evidence_count": null, "pfam_id": "PF23368", "proteins": 1247, "proteomes": 1229, "short_name": "DUF7092", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23368", "structures": 0, "taxa": 1955, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 47, "interpro_id": "IPR004988", "known_evidence_count": null, "matches": 1337, "name": "Protein of unknown function, DUF273", "partial_evidence_count": null, "pfam_id": "PF03314", "proteins": 1245, "proteomes": 143, "short_name": "DUF273", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03314", "structures": 0, "taxa": 414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1048, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 147 and 160 amino acids in length. The proteins in this family are frequently annotated as pherophorins however there is little accompanying literature to confirm this.", "domain_architectures": 22, "interpro_id": "IPR024616", "known_evidence_count": null, "matches": 1803, "name": "Pherophorin", "partial_evidence_count": null, "pfam_id": "PF12499", "proteins": 1245, "proteomes": 18, "short_name": "DUF3707", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12499", "structures": 0, "taxa": 49, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 881, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain family which forms a four helical bundle structure. This family includes the B. subtilis YvzG protein ([swissprot:C0H3R9]).", "domain_architectures": 16, "interpro_id": "IPR058355", "known_evidence_count": null, "matches": 1245, "name": "Domain of unknown function (DUF8042)", "partial_evidence_count": null, "pfam_id": "PF26154", "proteins": 1245, "proteomes": 1131, "short_name": "DUF8042", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26154", "structures": 0, "taxa": 1925, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1031, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a fungal family of unknown function. One of the proteins in this family [swissprot:P32792] has been localised to the mitochondria [[cite:PUB00033287]].", "domain_architectures": 24, "interpro_id": "IPR013952", "known_evidence_count": null, "matches": 1309, "name": "Fungal family of unknown function (DUF1776)", "partial_evidence_count": null, "pfam_id": "PF08643", "proteins": 1243, "proteomes": 1207, "short_name": "DUF1776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08643", "structures": 0, "taxa": 2495, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 816, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry consists of uncharacterized proteins from bacteria. It is found at the C-terminal and may adopt a fold related to Bet_v_1_like superfamily.", "domain_architectures": 5, "interpro_id": "IPR032286", "known_evidence_count": null, "matches": 1244, "name": "Domain of unknown function (DUF4837)", "partial_evidence_count": null, "pfam_id": "PF16125", "proteins": 1243, "proteomes": 1214, "short_name": "DUF4837", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16125", "structures": 0, "taxa": 1725, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 870, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, as well as some Zn-ribbon nucleic-acid-binding proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR018652", "known_evidence_count": null, "matches": 1242, "name": "Nucleic-acid-binding protein containing Zn-ribbon domain (DUF2082)", "partial_evidence_count": null, "pfam_id": "PF09855", "proteins": 1242, "proteomes": 1202, "short_name": "Zn_ribbon_13", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09855", "structures": 0, "taxa": 1975, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 786, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 122 and 152 amino acids in length. There are two conserved sequence motifs: AHH and NPH.", "domain_architectures": 2, "interpro_id": "IPR046150", "known_evidence_count": null, "matches": 1241, "name": "Family of unknown function (DUF6152)", "partial_evidence_count": null, "pfam_id": "PF19649", "proteins": 1241, "proteomes": 1011, "short_name": "DUF6152", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19649", "structures": 0, "taxa": 1618, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 973, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It has similarity to the N-terminal domain of Heparinase II/III.", "domain_architectures": 23, "interpro_id": "IPR061830", "known_evidence_count": null, "matches": 1288, "name": "Domain of unknown function (DUF8769)", "partial_evidence_count": null, "pfam_id": "PF30971", "proteins": 1241, "proteomes": 805, "short_name": "DUF8769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30971", "structures": 0, "taxa": 1622, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1089, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Platyhelminthes. It shows homology with the calponin homology (CH) domain.", "domain_architectures": 11, "interpro_id": "IPR044039", "known_evidence_count": null, "matches": 1241, "name": "Domain of unknown function (DUF5745)", "partial_evidence_count": null, "pfam_id": "PF19016", "proteins": 1238, "proteomes": 855, "short_name": "DUF5745", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19016", "structures": 0, "taxa": 2817, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1036, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into three transmembrane helices.", "domain_architectures": 12, "interpro_id": "IPR056136", "known_evidence_count": null, "matches": 1239, "name": "Domain of unknown function (DUF7719)", "partial_evidence_count": null, "pfam_id": "PF24841", "proteins": 1238, "proteomes": 1204, "short_name": "DUF7719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24841", "structures": 0, "taxa": 2553, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 862, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 840 residues in length and is mainly found in various Bacteroides species. Several proteins in this family are annotated as Glutaminases, but the function of this protein is unknown.", "domain_architectures": 31, "interpro_id": "IPR032515", "known_evidence_count": null, "matches": 1238, "name": "Domain of unknown function (DUF4964)", "partial_evidence_count": null, "pfam_id": "PF16334", "proteins": 1237, "proteomes": 989, "short_name": "DUF4964", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16334", "structures": 0, "taxa": 1823, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 754, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR022584", "known_evidence_count": null, "matches": 1240, "name": "Protein of unknown function (DUF2937)", "partial_evidence_count": null, "pfam_id": "PF11157", "proteins": 1235, "proteomes": 1233, "short_name": "DUF2937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11157", "structures": 0, "taxa": 1709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 857, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in fungi and bacteria.", "domain_architectures": 70, "interpro_id": "IPR043750", "known_evidence_count": null, "matches": 1423, "name": "Family of unknown function (DUF5695)", "partial_evidence_count": null, "pfam_id": "PF18951", "proteins": 1235, "proteomes": 1002, "short_name": "DUF5695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18951", "structures": 0, "taxa": 1894, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 975, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the domain of unknown function found in putative BED-type domain containing proteins and in uncharacterised plant proteins. This domain is predicted to adopt a beta-beta-alpha zinc finger fold.", "domain_architectures": 10, "interpro_id": "IPR058269", "known_evidence_count": null, "matches": 1236, "name": "Domain of unknown function (DUF7963)", "partial_evidence_count": null, "pfam_id": "PF25908", "proteins": 1235, "proteomes": 357, "short_name": "DUF7963", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25908", "structures": 0, "taxa": 1000, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1030, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of small proteins conserved in fungi. The function is not known.", "domain_architectures": 10, "interpro_id": "IPR018809", "known_evidence_count": null, "matches": 1232, "name": "Uncharacterised protein (DUF2406)", "partial_evidence_count": null, "pfam_id": "PF10295", "proteins": 1232, "proteomes": 1020, "short_name": "DUF2406", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10295", "structures": 6, "taxa": 2008, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 809, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of a group of uncharacterised bacterial sequences. This domain is related to Sugar ISomerase (SIS) domains found associated with [pfam:PF16125] at the C-terminal.", "domain_architectures": 4, "interpro_id": "IPR061602", "known_evidence_count": null, "matches": 1232, "name": "Domain of unknown function (DUF8532)", "partial_evidence_count": null, "pfam_id": "PF29354", "proteins": 1232, "proteomes": 1204, "short_name": "DUF8532", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29354", "structures": 0, "taxa": 1683, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 825, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. There are two completely conserved residues (N and R) that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR025346", "known_evidence_count": null, "matches": 1230, "name": "Domain of unknown function (DUF4250)", "partial_evidence_count": null, "pfam_id": "PF14056", "proteins": 1230, "proteomes": 975, "short_name": "DUF4250", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14056", "structures": 0, "taxa": 1453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 771, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 155 and 182 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025514", "known_evidence_count": null, "matches": 1235, "name": "Domain of unknown function (DUF4402)", "partial_evidence_count": null, "pfam_id": "PF14352", "proteins": 1230, "proteomes": 466, "short_name": "DUF4402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14352", "structures": 0, "taxa": 836, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 865, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region within hypothetical prokaryotic and archaeal proteins of unknown function. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 16, "interpro_id": "IPR009537", "known_evidence_count": null, "matches": 1227, "name": "Protein of unknown function (DUF1156)", "partial_evidence_count": null, "pfam_id": "PF06634", "proteins": 1227, "proteomes": 1055, "short_name": "DUF1156", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06634", "structures": 0, "taxa": 2589, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 645, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. These proteins may be distantly related to the PD(D/E)XK superfamily.", "domain_architectures": 8, "interpro_id": "IPR022573", "known_evidence_count": null, "matches": 1232, "name": "Protein of unknown function (DUF2887)", "partial_evidence_count": null, "pfam_id": "PF11103", "proteins": 1227, "proteomes": 232, "short_name": "DUF2887", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11103", "structures": 0, "taxa": 628, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 975, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plan proteins. It has detectable similarity to winged helix HTH domains and it is predicted to adopt similar structure.", "domain_architectures": 16, "interpro_id": "IPR056142", "known_evidence_count": null, "matches": 1229, "name": "Domain of unknown function (DUF7725)", "partial_evidence_count": null, "pfam_id": "PF24851", "proteins": 1227, "proteomes": 359, "short_name": "DUF7725", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24851", "structures": 0, "taxa": 1007, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1099, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved from nematodes to humans. The function is not known.", "domain_architectures": 17, "interpro_id": "IPR019319", "known_evidence_count": null, "matches": 1242, "name": "Uncharacterised conserved protein (DUF2368)", "partial_evidence_count": null, "pfam_id": "PF10166", "proteins": 1226, "proteomes": 960, "short_name": "DUF2368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10166", "structures": 0, "taxa": 3258, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 814, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function. The family represents just the N-terminus.", "domain_architectures": 10, "interpro_id": "IPR024537", "known_evidence_count": null, "matches": 1229, "name": "Uncharacterized protein conserved in bacteria N-term (DUF3322)", "partial_evidence_count": null, "pfam_id": "PF11795", "proteins": 1226, "proteomes": 1179, "short_name": "DUF3322", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11795", "structures": 3, "taxa": 2200, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1059, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function, which is found in eukaryotes. Proteins in this family are typically between 109 and 323 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR027967", "known_evidence_count": null, "matches": 1247, "name": "Domain of unknown function (DUF4612)", "partial_evidence_count": null, "pfam_id": "PF15389", "proteins": 1226, "proteomes": 760, "short_name": "DUF4612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15389", "structures": 0, "taxa": 2719, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 816, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of hypothetical bacterial proteins found in the vicinity of Molybdenum ABC transporter ATP-binding gene-products MobA MobB and MobC. However the function could not be confirmed. This family appears to belong to the P-loop superfamily by alignment to [pfam:PF03266]. However, the characteristic P-loop sequence motif appears to have diverged beyond recognition in this family.", "domain_architectures": 9, "interpro_id": "IPR018912", "known_evidence_count": null, "matches": 1232, "name": "Protein of unknown function (DUF2478)", "partial_evidence_count": null, "pfam_id": "PF10649", "proteins": 1225, "proteomes": 903, "short_name": "DUF2478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10649", "structures": 0, "taxa": 1393, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 986, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea and viruses. Proteins in this family are typically between 101 and 135 amino acids in length. There is a completely conserved aspartate and a conserved EXNP motif that may be functionally important. These and others residues form a deep pocket that may bind to an as yet unidentified ligand. This family is related to [pfam:PF01889].", "domain_architectures": 4, "interpro_id": "IPR043717", "known_evidence_count": null, "matches": 1225, "name": "Domain of unknown function (DUF5658)", "partial_evidence_count": null, "pfam_id": "PF18902", "proteins": 1225, "proteomes": 872, "short_name": "DUF5658", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18902", "structures": 0, "taxa": 1602, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 806, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 60 amino acids in length. This protein has two conserved sequence motifs: GQVQS and TVNF.", "domain_architectures": 15, "interpro_id": "IPR021938", "known_evidence_count": null, "matches": 1224, "name": "Protein of unknown function (DUF3553)", "partial_evidence_count": null, "pfam_id": "PF12073", "proteins": 1224, "proteomes": 1209, "short_name": "DUF3553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12073", "structures": 0, "taxa": 1883, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1024, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into four helical bundle composed of helices which are predicted as transmembrane. It contains two highly conserved cyateine residues which are predicted to form a disulfide bond.", "domain_architectures": 18, "interpro_id": "IPR061854", "known_evidence_count": null, "matches": 1238, "name": "Domain of unknown function (DUF8793)", "partial_evidence_count": null, "pfam_id": "PF31054", "proteins": 1221, "proteomes": 1192, "short_name": "DUF8793", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31054", "structures": 0, "taxa": 2548, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 142 and 156 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR046288", "known_evidence_count": null, "matches": 1221, "name": "Family of unknown function (DUF6325)", "partial_evidence_count": null, "pfam_id": "PF19850", "proteins": 1220, "proteomes": 886, "short_name": "DUF6325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19850", "structures": 0, "taxa": 1154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1079, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised and is found in eukaryotes. Proteins with this domain are typically between 194 and 289 amino acids in length. There is a single completely conserved residue C that may be functionally important. This domain has been identified as structurally similar to peptidase C97 domain ([pfam:PF05903]) [[cite:PUB00152793]].", "domain_architectures": 25, "interpro_id": "IPR053921", "known_evidence_count": null, "matches": 1244, "name": "DUF4796 C-terminal", "partial_evidence_count": null, "pfam_id": "PF16044", "proteins": 1219, "proteomes": 1051, "short_name": "DUF4796_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16044", "structures": 0, "taxa": 3551, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 773, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 6, "interpro_id": "IPR019207", "known_evidence_count": null, "matches": 1216, "name": "Predicted periplasmic protein (DUF2092)", "partial_evidence_count": null, "pfam_id": "PF09865", "proteins": 1216, "proteomes": 991, "short_name": "DUF2092", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09865", "structures": 0, "taxa": 1719, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 806, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is s bacterial family of proteins with unknown function.", "domain_architectures": 2, "interpro_id": "IPR024341", "known_evidence_count": null, "matches": 1215, "name": "Protein of unknown function (DUF2631)", "partial_evidence_count": null, "pfam_id": "PF10939", "proteins": 1215, "proteomes": 1205, "short_name": "DUF2631", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10939", "structures": 17, "taxa": 1443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes uncharacterised archaeal proteins that contain a HTH domain.", "domain_architectures": 5, "interpro_id": "IPR055766", "known_evidence_count": null, "matches": 1215, "name": "Family of unknown function (DUF7342)", "partial_evidence_count": null, "pfam_id": "PF24033", "proteins": 1214, "proteomes": 292, "short_name": "DUF7342", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24033", "structures": 0, "taxa": 449, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 665, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function expressed by various bacterial species. Some members of this family (e.g. [swissprot:Q8Z8Z7], [swissprot:Q8ZRF4]) are thought to be lipoproteins. Another member of this family ([swissprot:Q93SV8]) is thought to be involved in photosynthesis [[cite:PUB00015226]]. Based on structure predictions (from AlphaFold and structural comparisons using DALI server), this family may have a lysozyme-like fold.", "domain_architectures": 2, "interpro_id": "IPR011673", "known_evidence_count": null, "matches": 1214, "name": "Protein of unknown function (DUF1615)", "partial_evidence_count": null, "pfam_id": "PF07759", "proteins": 1213, "proteomes": 1186, "short_name": "DUF1615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07759", "structures": 0, "taxa": 1593, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 724, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR018706", "known_evidence_count": null, "matches": 1212, "name": "Predicted membrane protein (DUF2214)", "partial_evidence_count": null, "pfam_id": "PF09980", "proteins": 1212, "proteomes": 1199, "short_name": "DUF2214", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09980", "structures": 0, "taxa": 1815, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1014, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins.", "domain_architectures": 40, "interpro_id": "IPR061797", "known_evidence_count": null, "matches": 1227, "name": "Domain of unknown function (DUF8736)", "partial_evidence_count": null, "pfam_id": "PF30783", "proteins": 1212, "proteomes": 206, "short_name": "DUF8736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30783", "structures": 0, "taxa": 617, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 364, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the N-terminal region of several plant proteins of unknown function.", "domain_architectures": 39, "interpro_id": "IPR006866", "known_evidence_count": null, "matches": 1226, "name": "Protein of unknown function (DUF627)", "partial_evidence_count": null, "pfam_id": "PF04781", "proteins": 1211, "proteomes": 341, "short_name": "DUF627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04781", "structures": 0, "taxa": 947, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 987, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 16 } }, "demotion_reasons": [], "description": "Members of this family of functionally uncharacterised domains are found at the C-terminus of plant phytochelatin synthases.", "domain_architectures": 27, "interpro_id": "IPR015407", "known_evidence_count": null, "matches": 1305, "name": "Domain of unknown function (DUF1984)", "partial_evidence_count": null, "pfam_id": "PF09328", "proteins": 1211, "proteomes": 367, "short_name": "Phytochelatin_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09328", "structures": 0, "taxa": 1090, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 805, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain that is generally found in two copies in YcdB and YcdC from B. subtilis. These proteins are uncharacterised. The C-terminal half of this domain appears to show similarity at the sequence level to the PEPSY domain.", "domain_architectures": 22, "interpro_id": "IPR032599", "known_evidence_count": null, "matches": 2002, "name": "YcdB, YcdC repeated domain", "partial_evidence_count": null, "pfam_id": "PF16244", "proteins": 1211, "proteomes": 732, "short_name": "DUF4901", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16244", "structures": 0, "taxa": 1130, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 804, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR009214", "known_evidence_count": null, "matches": 1210, "name": "Protein of unknown function (DUF1129)", "partial_evidence_count": null, "pfam_id": "PF06570", "proteins": 1210, "proteomes": 1152, "short_name": "DUF1129", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06570", "structures": 0, "taxa": 1639, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 706, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical membrane-anchored prokaryotic proteins, has no known function.", "domain_architectures": 4, "interpro_id": "IPR018682", "known_evidence_count": null, "matches": 1211, "name": "Protein of unknown function (DUF2167)", "partial_evidence_count": null, "pfam_id": "PF09935", "proteins": 1209, "proteomes": 1162, "short_name": "DUF2167", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09935", "structures": 0, "taxa": 1865, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1088, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The sequences making up this family are all derived from hypothetical proteins expressed by C. elegans. The region in question is approximately 160 amino acids long. The GO annotation for this protein indicates the protein to be involved in nematode larval development and to have a positive regulation on growth rate.", "domain_architectures": 40, "interpro_id": "IPR012444", "known_evidence_count": null, "matches": 1235, "name": "Protein of unknown function (DUF1647)", "partial_evidence_count": null, "pfam_id": "PF07801", "proteins": 1208, "proteomes": 280, "short_name": "DUF1647", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07801", "structures": 0, "taxa": 1008, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 753, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found as 1-2 copies in a small family of proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR011440", "known_evidence_count": null, "matches": 1572, "name": "Domain of Unknown Function (DUF1543)", "partial_evidence_count": null, "pfam_id": "PF07566", "proteins": 1207, "proteomes": 1174, "short_name": "DUF1543", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07566", "structures": 1, "taxa": 1622, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 720, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins. The structure of one of the proteins in this family has been solved and it adopts a beta barrel-like structure.", "domain_architectures": 2, "interpro_id": "IPR014934", "known_evidence_count": null, "matches": 1207, "name": "Protein of unknown function (DUF1806)", "partial_evidence_count": null, "pfam_id": "PF08830", "proteins": 1207, "proteomes": 1126, "short_name": "DUF1806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08830", "structures": 1, "taxa": 1398, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1025, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 64 and 80 amino acids in length.", "domain_architectures": 33, "interpro_id": "IPR022137", "known_evidence_count": null, "matches": 1210, "name": "Zinc finger protein", "partial_evidence_count": null, "pfam_id": "PF12417", "proteins": 1207, "proteomes": 619, "short_name": "DUF3669", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12417", "structures": 0, "taxa": 1329, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 769, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018736", "known_evidence_count": null, "matches": 1205, "name": "Predicted periplasmic lipoprotein (DUF2279)", "partial_evidence_count": null, "pfam_id": "PF10043", "proteins": 1205, "proteomes": 1144, "short_name": "DUF2279", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10043", "structures": 0, "taxa": 1724, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 798, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 70 amino acids in length. This protein has a conserved WDK sequence motif.", "domain_architectures": 2, "interpro_id": "IPR021853", "known_evidence_count": null, "matches": 1205, "name": "Protein of unknown function (DUF3460)", "partial_evidence_count": null, "pfam_id": "PF11943", "proteins": 1205, "proteomes": 1133, "short_name": "DUF3460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11943", "structures": 0, "taxa": 1436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 828, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised bacterial and archaeal proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR008482", "known_evidence_count": null, "matches": 1205, "name": "Protein of unknown function (DUF763)", "partial_evidence_count": null, "pfam_id": "PF05559", "proteins": 1204, "proteomes": 1187, "short_name": "DUF763", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05559", "structures": 0, "taxa": 1917, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1050, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins that is found in archaea and bacteria.", "domain_architectures": 9, "interpro_id": "IPR025098", "known_evidence_count": null, "matches": 1209, "name": "Protein of unknown function (DUF4013)", "partial_evidence_count": null, "pfam_id": "PF13197", "proteins": 1204, "proteomes": 584, "short_name": "DUF4013", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13197", "structures": 0, "taxa": 1089, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 770, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised and it is found in bacteria and archaea. Proteins in this family are typically between 280 and 313 amino acids in length. This family has some overlaps with families from the clan CL0034.", "domain_architectures": 5, "interpro_id": "IPR046249", "known_evidence_count": null, "matches": 1213, "name": "Family of unknown function (DUF6282)", "partial_evidence_count": null, "pfam_id": "PF19799", "proteins": 1204, "proteomes": 953, "short_name": "DUF6282", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19799", "structures": 0, "taxa": 1760, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 792, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021383", "known_evidence_count": null, "matches": 1203, "name": "Protein of unknown function (DUF3015)", "partial_evidence_count": null, "pfam_id": "PF11220", "proteins": 1203, "proteomes": 988, "short_name": "DUF3015", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11220", "structures": 0, "taxa": 1483, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 858, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a region that is sometimes found a the N-terminus of transposon proteins. It is also sometimes found as part of a shorter protein, presumably involved in transposition.", "domain_architectures": 11, "interpro_id": "IPR045618", "known_evidence_count": null, "matches": 1201, "name": "Family of unknown function (DUF6444)", "partial_evidence_count": null, "pfam_id": "PF20042", "proteins": 1201, "proteomes": 547, "short_name": "DUF6444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20042", "structures": 0, "taxa": 1378, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 760, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, predominantly in Firmicutes, but also in eukaryotes. Proteins in this family are typically between 185 and 202 amino acids in length. There is a conserved motif ID.", "domain_architectures": 2, "interpro_id": "IPR045527", "known_evidence_count": null, "matches": 1201, "name": "Family of unknown function (DUF6470)", "partial_evidence_count": null, "pfam_id": "PF20074", "proteins": 1201, "proteomes": 1192, "short_name": "DUF6470", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20074", "structures": 0, "taxa": 1779, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 754, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised sequences from bacteria. This domain may adopt a beta-sandwich fold.", "domain_architectures": 7, "interpro_id": "IPR061523", "known_evidence_count": null, "matches": 1200, "name": "Domain of unknown function (DUF8453)", "partial_evidence_count": null, "pfam_id": "PF28748", "proteins": 1200, "proteomes": 1137, "short_name": "DUF8453", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28748", "structures": 0, "taxa": 2268, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 679, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 148 and 288 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR025325", "known_evidence_count": null, "matches": 1199, "name": "Protein of unknown function (DUF4231)", "partial_evidence_count": null, "pfam_id": "PF14015", "proteins": 1199, "proteomes": 1027, "short_name": "DUF4231", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14015", "structures": 0, "taxa": 1967, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 640, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal zinc binding domain found in bacteriophage and bacterial proteins. These proteins typically contain this N-terminal zinc binding domain, a C-terminal HNH domain with likely nuclease activity ([pfam:PF01844]). The specific function of this N-terminal zinc binding domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061663", "known_evidence_count": null, "matches": 1194, "name": "Domain of unknown function (DUF8602)", "partial_evidence_count": null, "pfam_id": "PF29900", "proteins": 1194, "proteomes": 987, "short_name": "DUF8602", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29900", "structures": 2, "taxa": 1997, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 765, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and archaea, and is approximately 90 amino acids in length.", "domain_architectures": 33, "interpro_id": "IPR024981", "known_evidence_count": null, "matches": 1204, "name": "Protein of unknown function (DUF3887)", "partial_evidence_count": null, "pfam_id": "PF13026", "proteins": 1193, "proteomes": 1108, "short_name": "DUF3887", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13026", "structures": 2, "taxa": 1957, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 801, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in bacteria is functionally uncharacterised and is approximately 100 amino acids in length. Some members of this family are putative diacylglyceryl transferases.", "domain_architectures": 8, "interpro_id": "IPR046714", "known_evidence_count": null, "matches": 1192, "name": "Family of unknown function (DUF6787)", "partial_evidence_count": null, "pfam_id": "PF20584", "proteins": 1192, "proteomes": 1131, "short_name": "DUF6787", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20584", "structures": 0, "taxa": 1719, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 721, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 250 and 347 amino acids in length. These proteins contain a conserved RXXXE motif an invariant Histidine that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR043733", "known_evidence_count": null, "matches": 1191, "name": "Family of unknown function (DUF5677)", "partial_evidence_count": null, "pfam_id": "PF18928", "proteins": 1191, "proteomes": 1117, "short_name": "DUF5677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18928", "structures": 0, "taxa": 2341, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 741, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of proteins conserved in the Bacillaceae family. Some members are annotated as being protein YgzB. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR020912", "known_evidence_count": null, "matches": 1188, "name": "Zinc-ribbon containing domain", "partial_evidence_count": null, "pfam_id": "PF11023", "proteins": 1188, "proteomes": 1165, "short_name": "DUF2614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11023", "structures": 0, "taxa": 1550, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 760, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in bacteria and archaea and has an N terminal tetramerisation region that is composed of beta sheets.", "domain_architectures": 1, "interpro_id": "IPR014931", "known_evidence_count": null, "matches": 1187, "name": "Domain of unknown function (DUF1805)", "partial_evidence_count": null, "pfam_id": "PF08827", "proteins": 1187, "proteomes": 1166, "short_name": "DUF1805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08827", "structures": 1, "taxa": 1659, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 643, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 229 and 242 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR045617", "known_evidence_count": null, "matches": 1202, "name": "Family of unknown function (DUF6445)", "partial_evidence_count": null, "pfam_id": "PF20043", "proteins": 1186, "proteomes": 911, "short_name": "DUF6445", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20043", "structures": 0, "taxa": 1375, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1024, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This region of similarity is found in the vertebrate homologues of the drosophila Bobby Sox.", "domain_architectures": 12, "interpro_id": "IPR019102", "known_evidence_count": null, "matches": 1357, "name": "Domain of unknown function (DUF2028)", "partial_evidence_count": null, "pfam_id": "PF09667", "proteins": 1184, "proteomes": 495, "short_name": "DUF2028", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09667", "structures": 0, "taxa": 1680, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 964, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in the uncharacterised protein At4g37920 from Arabidopsis thaliana and similar proteins. This domain is predicted to adopt an all-alpha configuration. Its specific function is unknown.", "domain_architectures": 45, "interpro_id": "IPR059290", "known_evidence_count": null, "matches": 1195, "name": "Domain of unknown function (DUF8246)", "partial_evidence_count": null, "pfam_id": "PF26740", "proteins": 1182, "proteomes": 420, "short_name": "DUF8246", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26740", "structures": 0, "taxa": 1161, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 663, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function annotate the proteins as membrane protein. However, this cannot be confirmed.", "domain_architectures": 5, "interpro_id": "IPR022604", "known_evidence_count": null, "matches": 1181, "name": "Protein of unknown function (DUF2955)", "partial_evidence_count": null, "pfam_id": "PF11168", "proteins": 1181, "proteomes": 1012, "short_name": "DUF2955", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11168", "structures": 0, "taxa": 1405, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 644, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This alpha helical domain is usually found at the C-terminus of proteins containing repeats of [pfam:PF12396].", "domain_architectures": 45, "interpro_id": "IPR054256", "known_evidence_count": null, "matches": 1187, "name": "Domain of unknown function (DUF6987)", "partial_evidence_count": null, "pfam_id": "PF22485", "proteins": 1179, "proteomes": 902, "short_name": "DUF6987", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22485", "structures": 0, "taxa": 1829, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 998, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It has detectable similarity to proteins members of the Cytochrome b558 subunit alpha family and it is predicted to adopt similar structure composed of four helices.", "domain_architectures": 10, "interpro_id": "IPR056144", "known_evidence_count": null, "matches": 1191, "name": "Domain of unknown function (DUF7727)", "partial_evidence_count": null, "pfam_id": "PF24853", "proteins": 1179, "proteomes": 1110, "short_name": "DUF7727", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24853", "structures": 0, "taxa": 2328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 664, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a variety of bacterial extracellular proteins. It contains a beta barrel structure.", "domain_architectures": 55, "interpro_id": "IPR046542", "known_evidence_count": null, "matches": 1256, "name": "Family of unknown function (DUF6801)", "partial_evidence_count": null, "pfam_id": "PF20611", "proteins": 1178, "proteomes": 556, "short_name": "DUF6801", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20611", "structures": 0, "taxa": 732, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 802, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 134 and 356 amino acids in length. This domain contains helix-hairpin-helix motifs.", "domain_architectures": 24, "interpro_id": "IPR025567", "known_evidence_count": null, "matches": 1243, "name": "Domain of unknown function (DUF4332)", "partial_evidence_count": null, "pfam_id": "PF14229", "proteins": 1177, "proteomes": 1053, "short_name": "DUF4332", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14229", "structures": 0, "taxa": 2197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 698, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold onto a meander beta-barrel and it is likely associated with the membrane. It is frequently found in combination with [pfam:PF13387].", "domain_architectures": 8, "interpro_id": "IPR057162", "known_evidence_count": null, "matches": 1179, "name": "Domain of unknown function (DUF7840)", "partial_evidence_count": null, "pfam_id": "PF25222", "proteins": 1177, "proteomes": 1096, "short_name": "DUF7840", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25222", "structures": 0, "taxa": 1671, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 708, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial and occurs as a tandem repeat.", "domain_architectures": 10, "interpro_id": "IPR011438", "known_evidence_count": null, "matches": 2321, "name": "Protein of unknown function (DUF1541)", "partial_evidence_count": null, "pfam_id": "PF07563", "proteins": 1174, "proteomes": 913, "short_name": "DUF1541", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07563", "structures": 3, "taxa": 1279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 695, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are small hypothetical proteins of 60 to 100 residues from Cyanobacteria and some Proteobacteria. Prochlorococcus marinus strains have two members, other species one only. Interestingly, of the eight most conserved residues, four are aromatic and three are invariant tryptophans. It appears all species that encode this protein can synthesise tryptophan de novo.", "domain_architectures": 3, "interpro_id": "IPR012663", "known_evidence_count": null, "matches": 1174, "name": "Tryptophan-rich protein (DUF2389)", "partial_evidence_count": null, "pfam_id": "PF09493", "proteins": 1174, "proteomes": 1152, "short_name": "DUF2389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09493", "structures": 0, "taxa": 2018, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 705, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Actinobacteria.", "domain_architectures": 4, "interpro_id": "IPR046281", "known_evidence_count": null, "matches": 1177, "name": "Family of unknown function (DUF6318)", "partial_evidence_count": null, "pfam_id": "PF19843", "proteins": 1173, "proteomes": 682, "short_name": "DUF6318", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19843", "structures": 0, "taxa": 881, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 950, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to adopt a globular structure with similarity to Fibronectin type III-like domains.", "domain_architectures": 12, "interpro_id": "IPR055780", "known_evidence_count": null, "matches": 1177, "name": "Domain of unknown function (DUF7356)", "partial_evidence_count": null, "pfam_id": "PF24053", "proteins": 1173, "proteomes": 363, "short_name": "DUF7356", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24053", "structures": 0, "taxa": 992, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 948, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of proteins conserved in fungi. The function is not known.", "domain_architectures": 12, "interpro_id": "IPR018822", "known_evidence_count": null, "matches": 1174, "name": "Protein of unknown function (DUF2420)", "partial_evidence_count": null, "pfam_id": "PF10336", "proteins": 1171, "proteomes": 1116, "short_name": "DUF2420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10336", "structures": 0, "taxa": 2357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 550, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 136 and 154 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046095", "known_evidence_count": null, "matches": 1169, "name": "Family of unknown function (DUF6113)", "partial_evidence_count": null, "pfam_id": "PF19608", "proteins": 1169, "proteomes": 1164, "short_name": "DUF6113", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19608", "structures": 0, "taxa": 1335, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 858, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It has detectable similarity to members of the CYTH-like phosphatase superfamily and it is predicted to adopt similar structure.", "domain_architectures": 37, "interpro_id": "IPR057225", "known_evidence_count": null, "matches": 1351, "name": "Domain of unknown function (DUF7903)", "partial_evidence_count": null, "pfam_id": "PF25475", "proteins": 1167, "proteomes": 288, "short_name": "DUF7903", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25475", "structures": 0, "taxa": 754, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 790, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR018699", "known_evidence_count": null, "matches": 1165, "name": "Uncharacterized conserved protein (DUF2203)", "partial_evidence_count": null, "pfam_id": "PF09969", "proteins": 1165, "proteomes": 1149, "short_name": "DUF2203", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09969", "structures": 0, "taxa": 1828, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 708, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in the Bacillaceae family. Several members are named as YneK. The function is not known.", "domain_architectures": 3, "interpro_id": "IPR020203", "known_evidence_count": null, "matches": 1165, "name": "Protein of unknown function (DUF2621)", "partial_evidence_count": null, "pfam_id": "PF11084", "proteins": 1165, "proteomes": 1143, "short_name": "DUF2621", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11084", "structures": 0, "taxa": 1416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 688, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as transmembrane proteins however this cannot be confirmed. Currently this family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021390", "known_evidence_count": null, "matches": 1193, "name": "Protein of unknown function (DUF3025)", "partial_evidence_count": null, "pfam_id": "PF11227", "proteins": 1165, "proteomes": 1162, "short_name": "DUF3025", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11227", "structures": 0, "taxa": 1541, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 816, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the second domain found in a family of uncharacterised hypothetical prokaryotic proteins.", "domain_architectures": 24, "interpro_id": "IPR062920", "known_evidence_count": null, "matches": 1165, "name": "DUF499 second domain", "partial_evidence_count": null, "pfam_id": "PF30797", "proteins": 1165, "proteomes": 1060, "short_name": "DUF499_2nd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30797", "structures": 0, "taxa": 2538, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 414, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found as tandem repeats in bacterial cell surface proteins, associated with TED adhesive domains. This domain contains a conserved lysine, glutamic acid and asparagine diagnostic of an intradomain isopeptide bond.", "domain_architectures": 260, "interpro_id": "IPR046022", "known_evidence_count": null, "matches": 4440, "name": "Domain of unknown function (DUF5979)", "partial_evidence_count": null, "pfam_id": "PF19407", "proteins": 1164, "proteomes": 615, "short_name": "DUF5979", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19407", "structures": 2, "taxa": 966, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 668, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and viruses, and is approximately 110 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR025484", "known_evidence_count": null, "matches": 1163, "name": "Domain of unknown function (DUF4376)", "partial_evidence_count": null, "pfam_id": "PF14301", "proteins": 1163, "proteomes": 914, "short_name": "DUF4376", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14301", "structures": 0, "taxa": 1863, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 992, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 427 and 674 amino acids in length. There are two completely conserved residues (D and I) that may be functionally important.", "domain_architectures": 12, "interpro_id": "IPR029090", "known_evidence_count": null, "matches": 1190, "name": "Domain of unknown function (DUF4659)", "partial_evidence_count": null, "pfam_id": "PF15558", "proteins": 1162, "proteomes": 768, "short_name": "DUF4659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15558", "structures": 0, "taxa": 2604, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1037, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is found in eukaryotes. The function of this protein remains unknown. The gene which encodes for this protein is named chromosome 6 open reading frame 162 (C6orf162) and is found between the chromosomal positions 6q15-q16.1. It is thought that this protein may be an important part of membrane function.", "domain_architectures": 18, "interpro_id": "IPR026686", "known_evidence_count": null, "matches": 1164, "name": "Domain of unknown function (DUF4500)", "partial_evidence_count": null, "pfam_id": "PF14937", "proteins": 1160, "proteomes": 1039, "short_name": "DUF4500", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14937", "structures": 0, "taxa": 3467, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 921, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical plant proteins of around 250 residues in length. Members of this family seem to be found exclusively in Arabidopsis thaliana. The function of this family is unknown.", "domain_architectures": 32, "interpro_id": "IPR009943", "known_evidence_count": null, "matches": 1511, "name": "Protein of unknown function (DUF1475)", "partial_evidence_count": null, "pfam_id": "PF07343", "proteins": 1159, "proteomes": 514, "short_name": "DUF1475", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07343", "structures": 0, "taxa": 1396, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 805, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial lipoproteins contain a beta propeller structure.", "domain_architectures": 3, "interpro_id": "IPR025316", "known_evidence_count": null, "matches": 1162, "name": "Domain of unknown function (DUF4221)", "partial_evidence_count": null, "pfam_id": "PF13970", "proteins": 1159, "proteomes": 210, "short_name": "DUF4221", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13970", "structures": 1, "taxa": 372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 623, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR009412", "known_evidence_count": null, "matches": 1161, "name": "Protein of unknown function (DUF1062)", "partial_evidence_count": null, "pfam_id": "PF06353", "proteins": 1157, "proteomes": 1133, "short_name": "DUF1062", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06353", "structures": 0, "taxa": 1579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 564, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family containing hypothetical bacterial proteins.", "domain_architectures": 1, "interpro_id": "IPR012448", "known_evidence_count": null, "matches": 1157, "name": "Protein of unknown function (DUF1652)", "partial_evidence_count": null, "pfam_id": "PF07865", "proteins": 1157, "proteomes": 347, "short_name": "DUF1652", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07865", "structures": 0, "taxa": 390, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 569, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 180 amino acids in length. The family is found to the N-terminus of [pfam:PF00004]. There are three conserved sequence motifs: GWT, ELA and MGFW. Proteins in this family vary in length from 364 to 384 amino acids. The domains in this family vary in length from 177 to 180 amino acids.", "domain_architectures": 5, "interpro_id": "IPR045969", "known_evidence_count": null, "matches": 1157, "name": "Domain of unknown function (DUF5925)", "partial_evidence_count": null, "pfam_id": "PF19347", "proteins": 1157, "proteomes": 1141, "short_name": "DUF5925", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19347", "structures": 0, "taxa": 1307, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 726, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Firmicutes. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019642", "known_evidence_count": null, "matches": 1156, "name": "Protein of unknown function (DUF2507)", "partial_evidence_count": null, "pfam_id": "PF10702", "proteins": 1156, "proteomes": 1153, "short_name": "DUF2507", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10702", "structures": 1, "taxa": 1529, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 570, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Mycobacterium.", "domain_architectures": 1, "interpro_id": "IPR022534", "known_evidence_count": null, "matches": 1155, "name": "Protein of unknown function (DUF2563)", "partial_evidence_count": null, "pfam_id": "PF10817", "proteins": 1155, "proteomes": 892, "short_name": "DUF2563", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10817", "structures": 0, "taxa": 1024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 533, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a potential adhesive domain found at the N-terminus of a variety of bacterial cell surface proteins. The structure shows a large beta sandwich fold.", "domain_architectures": 310, "interpro_id": "IPR057708", "known_evidence_count": null, "matches": 1159, "name": "Domain of unknown function (DUF7948)", "partial_evidence_count": null, "pfam_id": "PF25778", "proteins": 1155, "proteomes": 729, "short_name": "DUF7948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25778", "structures": 0, "taxa": 1338, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 509, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 160 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR046704", "known_evidence_count": null, "matches": 1156, "name": "Domain of unknown function (DUF6777)", "partial_evidence_count": null, "pfam_id": "PF20568", "proteins": 1154, "proteomes": 770, "short_name": "DUF6777", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20568", "structures": 0, "taxa": 903, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 685, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha-helical array. It is frequently found in combination with [pfam:PF13387] and [pfam:PF25222].", "domain_architectures": 7, "interpro_id": "IPR057165", "known_evidence_count": null, "matches": 1153, "name": "Domain of unknown function (DUF7843)", "partial_evidence_count": null, "pfam_id": "PF25225", "proteins": 1153, "proteomes": 1087, "short_name": "DUF7843", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25225", "structures": 0, "taxa": 1649, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 704, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in the Bacillaceae family. Several members are named as YqzF. The function is not known.", "domain_architectures": 2, "interpro_id": "IPR020138", "known_evidence_count": null, "matches": 1152, "name": "Protein of unknown function (DUF2627)", "partial_evidence_count": null, "pfam_id": "PF11118", "proteins": 1151, "proteomes": 1147, "short_name": "DUF2627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11118", "structures": 0, "taxa": 1419, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 661, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 440 and 470 amino acids in length. There is a single completely conserved residue D that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR025060", "known_evidence_count": null, "matches": 1165, "name": "Protein of unknown function (DUF3999)", "partial_evidence_count": null, "pfam_id": "PF13163", "proteins": 1151, "proteomes": 1143, "short_name": "DUF3999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13163", "structures": 0, "taxa": 1742, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 712, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small beta sandwich domain of approximately 82 residues found in large outer membrane proteins in Bacteroidota (Flavobacteriaceae, Cytophagales). The domain is inserted within larger beta-barrel structures. These proteins are associated with the type IX secretion system (T9SS). The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061879", "known_evidence_count": null, "matches": 1151, "name": "Domain of unknown function (DUF8818)", "partial_evidence_count": null, "pfam_id": "PF31125", "proteins": 1151, "proteomes": 1147, "short_name": "DUF8818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31125", "structures": 0, "taxa": 1601, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 721, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 250 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR024992", "known_evidence_count": null, "matches": 1154, "name": "Protein of unknown function (DUF3891)", "partial_evidence_count": null, "pfam_id": "PF13030", "proteins": 1149, "proteomes": 1057, "short_name": "DUF3891", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13030", "structures": 0, "taxa": 1722, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 480, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 39 and 51 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR045513", "known_evidence_count": null, "matches": 1148, "name": "Family of unknown function (DUF6479)", "partial_evidence_count": null, "pfam_id": "PF20087", "proteins": 1148, "proteomes": 749, "short_name": "DUF6479", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20087", "structures": 0, "taxa": 887, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 617, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha/beta structure composed of an open beta-barrel with alpha-helices packed on one side. It contains highly conserved G[FWY][DE] sequence motif that may be important for function.", "domain_architectures": 156, "interpro_id": "IPR059416", "known_evidence_count": null, "matches": 1167, "name": "Domain of unknown function (DUF8372)", "partial_evidence_count": null, "pfam_id": "PF28131", "proteins": 1148, "proteomes": 509, "short_name": "DUF8372", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28131", "structures": 0, "taxa": 1032, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 712, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 175 and 265 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR022224", "known_evidence_count": null, "matches": 1147, "name": "Protein of unknown function (DUF3750)", "partial_evidence_count": null, "pfam_id": "PF12570", "proteins": 1147, "proteomes": 1131, "short_name": "DUF3750", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12570", "structures": 0, "taxa": 1705, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 751, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved region found at the C-terminal end of uncharacterised proteins mainly from gram negative bacteria. This domain contains a highly conserved KNP sequence motif.", "domain_architectures": 9, "interpro_id": "IPR061563", "known_evidence_count": null, "matches": 1147, "name": "Domain of unknown function (DUF8493)", "partial_evidence_count": null, "pfam_id": "PF29027", "proteins": 1147, "proteomes": 1145, "short_name": "DUF8493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29027", "structures": 0, "taxa": 1565, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 657, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 5, "interpro_id": "IPR021770", "known_evidence_count": null, "matches": 1146, "name": "Peptidase_C39 like family", "partial_evidence_count": null, "pfam_id": "PF11814", "proteins": 1145, "proteomes": 1127, "short_name": "DUF3335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11814", "structures": 0, "taxa": 1733, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 876, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt beta-Trefoil fold.", "domain_architectures": 80, "interpro_id": "IPR057230", "known_evidence_count": null, "matches": 1182, "name": "Domain of unknown function (DUF7908)", "partial_evidence_count": null, "pfam_id": "PF25485", "proteins": 1145, "proteomes": 398, "short_name": "DUF7908", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25485", "structures": 0, "taxa": 848, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 588, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Presumed stalk domain found in bacterial surface proteins forming tandem repeats with high sequence identity. This domain is also associated with other known bacterial surface protein stalks and adhesive domains.", "domain_architectures": 167, "interpro_id": "IPR044081", "known_evidence_count": null, "matches": 1620, "name": "Domain of unknown function (DUF5776)", "partial_evidence_count": null, "pfam_id": "PF19087", "proteins": 1144, "proteomes": 333, "short_name": "DUF5776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19087", "structures": 4, "taxa": 537, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 945, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised fungal proteins. They are predicted to fold into an up-and-down bundle of four transmembrane helices that is similar to the bundle of p53-inducible protein 11.", "domain_architectures": 31, "interpro_id": "IPR061853", "known_evidence_count": null, "matches": 1158, "name": "Domain of unknown function (DUF8792)", "partial_evidence_count": null, "pfam_id": "PF31053", "proteins": 1144, "proteomes": 1002, "short_name": "DUF8792", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31053", "structures": 0, "taxa": 2109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 858, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are typically between 246 and 334 amino acids in length. Some members are thought to be hemagglutinin-related proteins.", "domain_architectures": 2, "interpro_id": "IPR046228", "known_evidence_count": null, "matches": 1142, "name": "Family of unknown function (DUF6261)", "partial_evidence_count": null, "pfam_id": "PF19775", "proteins": 1142, "proteomes": 294, "short_name": "DUF6261", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19775", "structures": 0, "taxa": 489, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 707, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain found in mannose-6- phosphate isomerase family proteins. The domain is approximately 190-220 residues in length. The family is found in diverse bacteria including Bacillota, Bacteroidota and Actinomycetota. The function of this domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061555", "known_evidence_count": null, "matches": 1148, "name": "Domain of unknown function (DUF8485)", "partial_evidence_count": null, "pfam_id": "PF28960", "proteins": 1142, "proteomes": 1058, "short_name": "DUF8485", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28960", "structures": 0, "taxa": 1734, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 714, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 221 and 399 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR025368", "known_evidence_count": null, "matches": 1142, "name": "Domain of unknown function (DUF4272)", "partial_evidence_count": null, "pfam_id": "PF14094", "proteins": 1141, "proteomes": 1084, "short_name": "DUF4272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14094", "structures": 0, "taxa": 1847, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 723, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a set of uncharacterised bacterial proteins that are likely integral membrane proteins.", "domain_architectures": 2, "interpro_id": "IPR045625", "known_evidence_count": null, "matches": 1140, "name": "Family of unknown function (DUF6427)", "partial_evidence_count": null, "pfam_id": "PF19992", "proteins": 1140, "proteomes": 1140, "short_name": "DUF6427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19992", "structures": 0, "taxa": 1450, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 756, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial and archaeal proteins of around 130 residues in length. The function of this family is unknown, although it is thought that they may be iron-sulphur binding proteins.", "domain_architectures": 7, "interpro_id": "IPR009702", "known_evidence_count": null, "matches": 1143, "name": "Protein of unknown function (DUF1284)", "partial_evidence_count": null, "pfam_id": "PF06935", "proteins": 1139, "proteomes": 1127, "short_name": "DUF1284", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06935", "structures": 0, "taxa": 1882, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 696, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of NTF2-like proteins of unknown function.", "domain_architectures": 6, "interpro_id": "IPR049219", "known_evidence_count": null, "matches": 1139, "name": "NTF2-like protein (DUF6841)", "partial_evidence_count": null, "pfam_id": "PF20795", "proteins": 1139, "proteomes": 1064, "short_name": "DUF6841", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20795", "structures": 0, "taxa": 1799, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 919, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Archaeal protein of unknown function. A fungal member UniProtKB:M2LN89 is clearly a Flavine-reductase enzyme by homology, and UniProtKB:O28442 has been shown to bind riboflavin 5'-phosphate (unpublished structural Xray analysis).", "domain_architectures": 3, "interpro_id": "IPR007386", "known_evidence_count": null, "matches": 1138, "name": "Protein of unknown function (DUF447) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF04289", "proteins": 1138, "proteomes": 1103, "short_name": "DUF447_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04289", "structures": 4, "taxa": 1783, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 910, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial and archaeal proteins. It is predicted to adopt a beta-sandwich with an Ig-like topology, similar to domains members of clan CL0073. Some proteins contain multiple copies of this domain.", "domain_architectures": 65, "interpro_id": "IPR055706", "known_evidence_count": null, "matches": 1629, "name": "Domain of unknown function (DUF7282)", "partial_evidence_count": null, "pfam_id": "PF23951", "proteins": 1137, "proteomes": 644, "short_name": "DUF7282", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23951", "structures": 0, "taxa": 1134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 988, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domainis found in uncharacterised fungal proteins. It shares significant similarity to known AAA domains.", "domain_architectures": 38, "interpro_id": "IPR061796", "known_evidence_count": null, "matches": 1206, "name": "Domain of unknown function (DUF8735)", "partial_evidence_count": null, "pfam_id": "PF30782", "proteins": 1137, "proteomes": 193, "short_name": "DUF8735", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30782", "structures": 0, "taxa": 579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 976, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of eukaryotic proteins of unknown function. This family contains many hypothetical proteins.", "domain_architectures": 26, "interpro_id": "IPR013885", "known_evidence_count": null, "matches": 1136, "name": "Eukaryotic protein of unknown function (DUF1764)", "partial_evidence_count": null, "pfam_id": "PF08576", "proteins": 1136, "proteomes": 965, "short_name": "DUF1764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08576", "structures": 0, "taxa": 2579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 715, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacteria, eukaryotes and viruses, and is approximately 60 amino acids in length. It contains a CXXCXH motif and a CPXC motif. It is predicted to adopt treble clef fold. Some members have the second probable zinc binding residue replaced by histidine.", "domain_architectures": 75, "interpro_id": "IPR025487", "known_evidence_count": null, "matches": 2987, "name": "Probable Treble clef zinc finger domain", "partial_evidence_count": null, "pfam_id": "PF14311", "proteins": 1134, "proteomes": 743, "short_name": "DUF4379", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14311", "structures": 11, "taxa": 1589, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 556, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in bacteria and viruses. Some members of this family are annotated as being Phi APSE P51-like proteins.", "domain_architectures": 5, "interpro_id": "IPR021229", "known_evidence_count": null, "matches": 1160, "name": "Protein of unknown function (DUF2800)", "partial_evidence_count": null, "pfam_id": "PF10926", "proteins": 1132, "proteomes": 939, "short_name": "DUF2800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10926", "structures": 0, "taxa": 2170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 962, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family is conserved from fungi to Metazoa and includes plants. The function is not known, but several members have zinc-finger domain, zf-MYND, [pfam:PF01753], at their very C-terminus. Others are also associated with DUF1279, [pfam:PF06916]. This domain is more C-terminal in many members to DUF4470, [pfam:PF14737].", "domain_architectures": 33, "interpro_id": "IPR028235", "known_evidence_count": null, "matches": 1239, "name": "Domain of unknown function (DUF4471)", "partial_evidence_count": null, "pfam_id": "PF14740", "proteins": 1131, "proteomes": 885, "short_name": "DUF4471", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14740", "structures": 0, "taxa": 3107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 731, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This uncharacterised domain is found in a group of polysaccharide deacetylases and similar proteins from bacteria. It is predicted to adopt an alpha-helical configuration.", "domain_architectures": 3, "interpro_id": "IPR054297", "known_evidence_count": null, "matches": 1132, "name": "Family of unknown function (DUF7033)", "partial_evidence_count": null, "pfam_id": "PF23019", "proteins": 1131, "proteomes": 1105, "short_name": "DUF7033", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23019", "structures": 0, "taxa": 1795, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 927, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of fungal proteins whose function is unknown. They are distantly related to CUSTOS proteins [pfam:PF23999] from animals.", "domain_architectures": 29, "interpro_id": "IPR018555", "known_evidence_count": null, "matches": 1134, "name": "Fungal protein of unknown function (DUF2011)", "partial_evidence_count": null, "pfam_id": "PF09428", "proteins": 1130, "proteomes": 1107, "short_name": "DUF2011", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09428", "structures": 0, "taxa": 2216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain is found towards the C terminus of human NEDD4 -binding protein 2 (N4BP2), which has 5'-polynucleotide kinase and nicking endonuclease activity and may play a role in DNA repair or recombination. This domain is often found associated with [pfam:PF25124] and [pfam:PF08590].", "domain_architectures": 39, "interpro_id": "IPR056720", "known_evidence_count": null, "matches": 1129, "name": "Domain of unknown function (DUF7818)", "partial_evidence_count": null, "pfam_id": "PF25126", "proteins": 1129, "proteomes": 680, "short_name": "DUF7818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25126", "structures": 0, "taxa": 2097, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 703, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in the Bacillaceae family. Several members are named as YqgY. The function is not known.", "domain_architectures": 2, "interpro_id": "IPR020254", "known_evidence_count": null, "matches": 1136, "name": "Protein of unknown function (DUF2626)", "partial_evidence_count": null, "pfam_id": "PF11117", "proteins": 1128, "proteomes": 1126, "short_name": "DUF2626", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11117", "structures": 0, "taxa": 1379, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1049, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Archaea. Family members have multiple predicted trans-membrane regions.", "domain_architectures": 5, "interpro_id": "IPR040493", "known_evidence_count": null, "matches": 1127, "name": "Family of unknown function (DUF5518)", "partial_evidence_count": null, "pfam_id": "PF17647", "proteins": 1127, "proteomes": 371, "short_name": "DUF5518", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17647", "structures": 0, "taxa": 633, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 716, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacterial proteins and it is functionally uncharacterised. In some members of this family, thought to be aminoglycoside phosphotransferases, it is located at the C-terminal.", "domain_architectures": 6, "interpro_id": "IPR046252", "known_evidence_count": null, "matches": 1126, "name": "Domain of unknown function (DUF6285)", "partial_evidence_count": null, "pfam_id": "PF19802", "proteins": 1126, "proteomes": 1063, "short_name": "DUF6285", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19802", "structures": 0, "taxa": 1546, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1015, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 74 and 104 amino acids in length. There are two completely conserved residues (C and P) that may be functionally important.", "domain_architectures": 17, "interpro_id": "IPR026776", "known_evidence_count": null, "matches": 1125, "name": "Domain of unknown function (DUF4512)", "partial_evidence_count": null, "pfam_id": "PF14975", "proteins": 1124, "proteomes": 900, "short_name": "DUF4512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14975", "structures": 0, "taxa": 3064, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 754, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 220 residues in length and is mainly found in various Bacteroides species. Distant homology analysis suggest distant relation between this family and other families of proteins with immunoglobulin-like folds, which are often involved in substrate binding. However, specific function of this family is unknown. There is distant homology to the Calx-beta family [pfam:PF03160].", "domain_architectures": 5, "interpro_id": "IPR032299", "known_evidence_count": null, "matches": 1126, "name": "Domain of unknown function (DUF4843)", "partial_evidence_count": null, "pfam_id": "PF16132", "proteins": 1124, "proteomes": 351, "short_name": "DUF4843", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16132", "structures": 0, "taxa": 508, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 759, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from prokaryotes. It is usually found associated with [pfam:PF04851], [pfam:PF00271] and [pfam:PF18766]. It is predicted to fold into array of alpha-helices.", "domain_architectures": 17, "interpro_id": "IPR058403", "known_evidence_count": null, "matches": 1155, "name": "Domain of unknown function (DUF8090)", "partial_evidence_count": null, "pfam_id": "PF26350", "proteins": 1124, "proteomes": 1093, "short_name": "DUF8090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26350", "structures": 1, "taxa": 1860, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 764, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is mainly found in various Bacteroides species. The members in this family are around 470 residues in length.", "domain_architectures": 3, "interpro_id": "IPR032176", "known_evidence_count": null, "matches": 1124, "name": "Domain of unknown function (DUF5009)", "partial_evidence_count": null, "pfam_id": "PF16401", "proteins": 1123, "proteomes": 832, "short_name": "DUF5009", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16401", "structures": 0, "taxa": 1642, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 675, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a bacterial domain of unknown function. This domain is sometimes associated with a [pfam:PF14464] domain. This could suggest this domain has a role in a bacterial cognate of a Ubiquitin-like pathway.", "domain_architectures": 9, "interpro_id": "IPR046537", "known_evidence_count": null, "matches": 1123, "name": "Domain of unknown function (DUF6602)", "partial_evidence_count": null, "pfam_id": "PF20247", "proteins": 1123, "proteomes": 1045, "short_name": "DUF6602", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20247", "structures": 8, "taxa": 2214, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 284, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function. In particular, this domain lies at the C-terminal end of a protein found in eukaryotes.", "domain_architectures": 16, "interpro_id": "IPR027871", "known_evidence_count": null, "matches": 1168, "name": "Domain of unknown function (DUF4603)", "partial_evidence_count": null, "pfam_id": "PF15376", "proteins": 1121, "proteomes": 611, "short_name": "DUF4603", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15376", "structures": 0, "taxa": 2203, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 681, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 113 and 135 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR022172", "known_evidence_count": null, "matches": 1120, "name": "Protein of unknown function (DUF3703)", "partial_evidence_count": null, "pfam_id": "PF12487", "proteins": 1120, "proteomes": 983, "short_name": "DUF3703", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12487", "structures": 0, "taxa": 1606, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 910, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised plant sequences which may adopt a structure similar to spectrin repeats.", "domain_architectures": 14, "interpro_id": "IPR061515", "known_evidence_count": null, "matches": 1140, "name": "Domain of unknown function (DUF8445)", "partial_evidence_count": null, "pfam_id": "PF28715", "proteins": 1120, "proteomes": 360, "short_name": "DUF8445", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28715", "structures": 0, "taxa": 982, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 675, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR019615", "known_evidence_count": null, "matches": 1119, "name": "Protein of unknown function (DUF2487)", "partial_evidence_count": null, "pfam_id": "PF10673", "proteins": 1119, "proteomes": 1117, "short_name": "DUF2487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10673", "structures": 0, "taxa": 1369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 714, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR016768", "known_evidence_count": null, "matches": 1147, "name": "Protein of unknown function (DUF2818)", "partial_evidence_count": null, "pfam_id": "PF10993", "proteins": 1118, "proteomes": 1109, "short_name": "DUF2818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10993", "structures": 0, "taxa": 1423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 711, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is related to proteins in the Cupin superfamily. These proteins contain 1 or 2 copies of the domain. This family of proteins is found in Proteobacteria and Bacteroidetes. Proteins in this family are typically between 132 and 162 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046058", "known_evidence_count": null, "matches": 1119, "name": "Domain of unknown function (DUF6016)", "partial_evidence_count": null, "pfam_id": "PF19480", "proteins": 1118, "proteomes": 1000, "short_name": "DUF6016", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19480", "structures": 0, "taxa": 1772, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 737, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 6, "interpro_id": "IPR021505", "known_evidence_count": null, "matches": 1117, "name": "Protein of unknown function (DUF3164)", "partial_evidence_count": null, "pfam_id": "PF11363", "proteins": 1117, "proteomes": 915, "short_name": "DUF3164", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11363", "structures": 0, "taxa": 1801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 634, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR021557", "known_evidence_count": null, "matches": 1116, "name": "Protein of unknown function (DUF3016)", "partial_evidence_count": null, "pfam_id": "PF11454", "proteins": 1116, "proteomes": 1034, "short_name": "DUF3016", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11454", "structures": 0, "taxa": 1376, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 678, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a domain of unknown function which can be found in DNA primases such as TraC.", "domain_architectures": 87, "interpro_id": "IPR043764", "known_evidence_count": null, "matches": 1278, "name": "Domain of unknown function (DUF5710)", "partial_evidence_count": null, "pfam_id": "PF18974", "proteins": 1116, "proteomes": 888, "short_name": "DUF5710", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18974", "structures": 0, "taxa": 1759, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria. The family is related to the LolB family suggesting a role in lipoprotein insertion in the outer membrane.", "domain_architectures": 4, "interpro_id": "IPR021675", "known_evidence_count": null, "matches": 1115, "name": "Protein of unknown function (DUF3261)", "partial_evidence_count": null, "pfam_id": "PF11659", "proteins": 1115, "proteomes": 1115, "short_name": "DUF3261", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11659", "structures": 0, "taxa": 1721, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 691, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of proteins. Some members in the family are annotated as YtpB however currently no function is known.", "domain_architectures": 2, "interpro_id": "IPR019712", "known_evidence_count": null, "matches": 1119, "name": "Protein of unknown function (DUF2600)", "partial_evidence_count": null, "pfam_id": "PF10776", "proteins": 1114, "proteomes": 1073, "short_name": "DUF2600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10776", "structures": 3, "taxa": 1480, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 787, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is approximately 110 amino acids in length. There is a conserved NGLGF sequence motif.", "domain_architectures": 8, "interpro_id": "IPR025457", "known_evidence_count": null, "matches": 1112, "name": "Domain of unknown function (DUF4277)", "partial_evidence_count": null, "pfam_id": "PF14104", "proteins": 1112, "proteomes": 445, "short_name": "DUF4277", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14104", "structures": 0, "taxa": 1124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 913, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 313 and 876 amino acids in length.", "domain_architectures": 21, "interpro_id": "IPR028032", "known_evidence_count": null, "matches": 1172, "name": "Domain of unknown function (DUF4503)", "partial_evidence_count": null, "pfam_id": "PF14951", "proteins": 1112, "proteomes": 703, "short_name": "DUF4503", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14951", "structures": 0, "taxa": 2387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 639, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 115 residues in length. Members of this family seem to be found exclusively in Salmonella and Yersinia species and several have been described as being putative cytoplasmic proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010862", "known_evidence_count": null, "matches": 1111, "name": "Protein of unknown function (DUF1493)", "partial_evidence_count": null, "pfam_id": "PF07377", "proteins": 1111, "proteomes": 695, "short_name": "DUF1493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07377", "structures": 0, "taxa": 1083, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 918, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins conserved in fungi. The function is not known, and there is no S. cerevisiae member.", "domain_architectures": 21, "interpro_id": "IPR021641", "known_evidence_count": null, "matches": 1116, "name": "Protein of unknown function (DUF3245)", "partial_evidence_count": null, "pfam_id": "PF11595", "proteins": 1111, "proteomes": 867, "short_name": "DUF3245", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11595", "structures": 0, "taxa": 2136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 518, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR010546", "known_evidence_count": null, "matches": 1110, "name": "Protein of unknown function (DUF1120)", "partial_evidence_count": null, "pfam_id": "PF06551", "proteins": 1110, "proteomes": 296, "short_name": "DUF1120", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06551", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 670, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as lipoproteins however this cannot be confirmed.", "domain_architectures": 6, "interpro_id": "IPR022548", "known_evidence_count": null, "matches": 1110, "name": "Protein of unknown function (DUF2846)", "partial_evidence_count": null, "pfam_id": "PF11008", "proteins": 1110, "proteomes": 994, "short_name": "DUF2846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11008", "structures": 0, "taxa": 1565, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021293", "known_evidence_count": null, "matches": 1110, "name": "Protein of unknown function (DUF2865)", "partial_evidence_count": null, "pfam_id": "PF11064", "proteins": 1110, "proteomes": 743, "short_name": "DUF2865", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11064", "structures": 0, "taxa": 956, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 702, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 100 residues in length. The function of this family is unknown.", "domain_architectures": 7, "interpro_id": "IPR010767", "known_evidence_count": null, "matches": 1109, "name": "Protein of unknown function (DUF1353)", "partial_evidence_count": null, "pfam_id": "PF07087", "proteins": 1107, "proteomes": 962, "short_name": "DUF1353", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07087", "structures": 0, "taxa": 1841, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 934, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 107 and 124 amino acids in length. There is a single completely conserved residue V that may be functionally important.", "domain_architectures": 8, "interpro_id": "IPR031940", "known_evidence_count": null, "matches": 1146, "name": "Domain of unknown function (DUF4772)", "partial_evidence_count": null, "pfam_id": "PF15997", "proteins": 1107, "proteomes": 795, "short_name": "DUF4772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15997", "structures": 0, "taxa": 2840, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 972, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function. The precise function of this protein domain remains to be elucidated. This domain family is found in eukaryotes, and is typically between 64 and 79 amino acids in length. There are two conserved sequence motifs: QNAQ and HHH. In humans, it is found in the position, chromosome 21 open reading frame 58.", "domain_architectures": 15, "interpro_id": "IPR027904", "known_evidence_count": null, "matches": 1105, "name": "Domain of unknown function (DUF4587)", "partial_evidence_count": null, "pfam_id": "PF15248", "proteins": 1105, "proteomes": 544, "short_name": "DUF4587", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15248", "structures": 0, "taxa": 1821, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 886, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This entry represents a spectrin-like domain found in the DUF447 family of proteins.", "domain_architectures": 3, "interpro_id": "IPR049288", "known_evidence_count": null, "matches": 1105, "name": "Protein of unknown function (DUF447)", "partial_evidence_count": null, "pfam_id": "PF20766", "proteins": 1105, "proteomes": 1072, "short_name": "DUF447_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20766", "structures": 4, "taxa": 1720, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 664, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 225 and 451 amino acids in length. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR025466", "known_evidence_count": null, "matches": 1135, "name": "Domain of unknown function (DUF4317)", "partial_evidence_count": null, "pfam_id": "PF14199", "proteins": 1104, "proteomes": 979, "short_name": "DUF4317", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14199", "structures": 0, "taxa": 1375, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 655, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]]. This domain is found associated with an [pfam:PF07275] like domain. This suggests that this family may also be involved in evading host restriction.", "domain_architectures": 22, "interpro_id": "IPR024559", "known_evidence_count": null, "matches": 1104, "name": "Domain of unknown function (DUF3846)", "partial_evidence_count": null, "pfam_id": "PF12957", "proteins": 1103, "proteomes": 799, "short_name": "DUF3846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12957", "structures": 0, "taxa": 1544, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 924, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a region of a family of proteins conserved in fungi some of whose members also have the Abhydrolase_1, [pfam:PF00561], domain in their sequence. The function of this region is not known.", "domain_architectures": 17, "interpro_id": "IPR019431", "known_evidence_count": null, "matches": 1107, "name": "Region of unknown function (DUF2417)", "partial_evidence_count": null, "pfam_id": "PF10329", "proteins": 1102, "proteomes": 1059, "short_name": "DUF2417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10329", "structures": 0, "taxa": 2170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 697, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised proteins from bacteria and archaea. This domain is about 75 amino acids in length and it contains the conserved motif CxxxGxCP. Towards the C-terminal there are two conserved residues, a Glycine and an Aspartate. Some of the proteins containing this domain also have an ankyrin repeat-containing region. This domain is related to the Emfourin proteins [pfam:PF20242] and may have a related peptidase inhibitor function.", "domain_architectures": 13, "interpro_id": "IPR045497", "known_evidence_count": null, "matches": 1103, "name": "Domain of unknown function (DUF6438)", "partial_evidence_count": null, "pfam_id": "PF20033", "proteins": 1102, "proteomes": 934, "short_name": "DUF6438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20033", "structures": 0, "taxa": 1497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 414, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021427", "known_evidence_count": null, "matches": 1101, "name": "Protein of unknown function (DUF3077)", "partial_evidence_count": null, "pfam_id": "PF11275", "proteins": 1101, "proteomes": 269, "short_name": "DUF3077", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11275", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 684, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR024510", "known_evidence_count": null, "matches": 1117, "name": "Protein of unknown function (DUF2589)", "partial_evidence_count": null, "pfam_id": "PF11655", "proteins": 1101, "proteomes": 589, "short_name": "DUF2589", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11655", "structures": 0, "taxa": 1164, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 684, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045510", "known_evidence_count": null, "matches": 1101, "name": "Family of unknown function (DUF6481)", "partial_evidence_count": null, "pfam_id": "PF20089", "proteins": 1101, "proteomes": 957, "short_name": "DUF6481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20089", "structures": 0, "taxa": 1289, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 908, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant proteins. It is predicted to adopt a globular structure consisting of a rubredoxin-like zinc finger capped with an elaborated alpha-helical subdomain. This arrangement is similar to the zinc finger domain found in hypA ([pfam:PF01155]).", "domain_architectures": 9, "interpro_id": "IPR055513", "known_evidence_count": null, "matches": 1116, "name": "Domain of unknown function (DUF7086)", "partial_evidence_count": null, "pfam_id": "PF23324", "proteins": 1101, "proteomes": 346, "short_name": "DUF7086", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23324", "structures": 0, "taxa": 961, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 652, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 4, "interpro_id": "IPR021556", "known_evidence_count": null, "matches": 1126, "name": "Protein of unknown function (DUF2950)", "partial_evidence_count": null, "pfam_id": "PF11453", "proteins": 1099, "proteomes": 852, "short_name": "DUF2950", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11453", "structures": 0, "taxa": 1257, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 865, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in a group of plant sequences related to Oberon-like proteins. According to structure predictions this domain may consist of mainly three beta-sheets and two alpha-helices.", "domain_architectures": 29, "interpro_id": "IPR055508", "known_evidence_count": null, "matches": 1127, "name": "Domain of unknown function (DUF7081)", "partial_evidence_count": null, "pfam_id": "PF23299", "proteins": 1097, "proteomes": 348, "short_name": "DUF7081", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23299", "structures": 0, "taxa": 968, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 759, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 97 and 206 amino acids in length. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR025642", "known_evidence_count": null, "matches": 1094, "name": "Domain of unknown function (DUF4342)", "partial_evidence_count": null, "pfam_id": "PF14242", "proteins": 1094, "proteomes": 921, "short_name": "DUF4342", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14242", "structures": 0, "taxa": 1769, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 641, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "", "domain_architectures": 12, "interpro_id": "IPR032589", "known_evidence_count": null, "matches": 1103, "name": "Domain of unknown function (DUF4910)", "partial_evidence_count": null, "pfam_id": "PF16254", "proteins": 1094, "proteomes": 1059, "short_name": "DUF4910", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16254", "structures": 1, "taxa": 1856, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 734, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 110 residues. The domain is found at the C-terminus of proteins annotated as RgtA-like glycosyltransferases. This family is found in diverse bacteria including Pseudomonadota (particularly Legionella), Actinomycetota, Myxococcota and Chloroflexota. The function of this domain remains to be determined.", "domain_architectures": 9, "interpro_id": "IPR061789", "known_evidence_count": null, "matches": 1094, "name": "Domain of unknown function (DUF8728)", "partial_evidence_count": null, "pfam_id": "PF30772", "proteins": 1094, "proteomes": 706, "short_name": "DUF8728", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30772", "structures": 0, "taxa": 1252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 896, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical plant proteins of unknown function.", "domain_architectures": 23, "interpro_id": "IPR009500", "known_evidence_count": null, "matches": 1104, "name": "Protein of unknown function (DUF1118)", "partial_evidence_count": null, "pfam_id": "PF06549", "proteins": 1093, "proteomes": 432, "short_name": "DUF1118", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06549", "structures": 0, "taxa": 1271, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 707, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Enterobacterial proteins of around 130 residues in length. Members of this family seem to be found exclusively in Escherichia coli and Salmonella species. The function of this family is unknown.", "domain_architectures": 6, "interpro_id": "IPR009833", "known_evidence_count": null, "matches": 1095, "name": "Protein of unknown function (DUF1398)", "partial_evidence_count": null, "pfam_id": "PF07166", "proteins": 1093, "proteomes": 1034, "short_name": "DUF1398", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07166", "structures": 1, "taxa": 1693, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 875, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry is a domain of unknown function found in some PA-PLA1 family members, which consists of mitochondrial proteins that are probable phospholipases with a specific function to hydrolyze phosphatidic acid. Members of this family are involved in the metabolism of phospholipids, which are critical components of cell membranes. By hydrolyzing phosphatidic acid, these enzymes may play a role in the regulation of mitochondrial membrane composition and dynamics, as well as in signaling pathways related to lipid metabolism.", "domain_architectures": 33, "interpro_id": "IPR055555", "known_evidence_count": null, "matches": 1093, "name": "Domain of unknown function (DUF7131)", "partial_evidence_count": null, "pfam_id": "PF23465", "proteins": 1093, "proteomes": 1013, "short_name": "DUF7131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23465", "structures": 0, "taxa": 2049, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 680, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 305 and 329 amino acids in length.", "domain_architectures": 25, "interpro_id": "IPR045499", "known_evidence_count": null, "matches": 1097, "name": "Family of unknown function (DUF6492)", "partial_evidence_count": null, "pfam_id": "PF20102", "proteins": 1092, "proteomes": 959, "short_name": "DUF6492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20102", "structures": 0, "taxa": 1745, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 606, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial protein of unknown function.", "domain_architectures": 15, "interpro_id": "IPR054186", "known_evidence_count": null, "matches": 1099, "name": "Domain of unknown function (DUF6891)", "partial_evidence_count": null, "pfam_id": "PF21831", "proteins": 1092, "proteomes": 997, "short_name": "DUF6891", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21831", "structures": 0, "taxa": 1551, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1005, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed HTH domain found at the N-terminal of a group of uncharacterised archaeal sequences.", "domain_architectures": 11, "interpro_id": "IPR055771", "known_evidence_count": null, "matches": 1093, "name": "Domain of unknown function (DUF7347)", "partial_evidence_count": null, "pfam_id": "PF24038", "proteins": 1091, "proteomes": 411, "short_name": "DUF7347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24038", "structures": 0, "taxa": 776, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 680, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function. Family members are mostly found in gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR013468", "known_evidence_count": null, "matches": 1090, "name": "Family of unknown function (DUF5669)", "partial_evidence_count": null, "pfam_id": "PF18918", "proteins": 1090, "proteomes": 1088, "short_name": "DUF5669", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18918", "structures": 0, "taxa": 1391, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 870, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain of unknown function is found N-terminal in a group of uncharacterised proteins mainly from plants. This domain is predicted to adopt a beta-barrel with topology typical for PH domains. It has a weak sequence similarity to Dcp1 PH domain.", "domain_architectures": 22, "interpro_id": "IPR055559", "known_evidence_count": null, "matches": 1097, "name": "Domain of unknown function (DUF7135)", "partial_evidence_count": null, "pfam_id": "PF23581", "proteins": 1090, "proteomes": 413, "short_name": "DUF7135", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23581", "structures": 0, "taxa": 1122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 678, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins. One member of this family ([swissprot:A4VM42]) is annotated as the A subunit of Type IIA topoisomerase (DNA gyrase/topo II, topoisomerase IV).", "domain_architectures": 1, "interpro_id": "IPR021363", "known_evidence_count": null, "matches": 1089, "name": "Protein of unknown function (DUF2835)", "partial_evidence_count": null, "pfam_id": "PF11197", "proteins": 1089, "proteomes": 1086, "short_name": "DUF2835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11197", "structures": 0, "taxa": 1511, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 607, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins, functionally uncharacterised, is found in bacteria. Proteins in this family are typically between 124 and 143 amino acids in length. Some members included in this family are hypothetical transposases, associated with transposon Tn554 [[cite:PUB00099532]]. There is a conserved sequence GV/LSR/K and a highly conserved tyrosine residue.", "domain_architectures": 5, "interpro_id": "IPR046229", "known_evidence_count": null, "matches": 1089, "name": "Family of unknown function (DUF6262)", "partial_evidence_count": null, "pfam_id": "PF19776", "proteins": 1089, "proteomes": 809, "short_name": "DUF6262", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19776", "structures": 0, "taxa": 1414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 541, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000345) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the eponemycin biosynthetic gene cluster from Streptomyces hygroscopicus [[cite:PUB00099457],[cite:PUB00099416]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 4, "interpro_id": "IPR046214", "known_evidence_count": null, "matches": 1096, "name": "Family of unknown function (DUF6247)", "partial_evidence_count": null, "pfam_id": "PF19760", "proteins": 1088, "proteomes": 670, "short_name": "DUF6247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19760", "structures": 0, "taxa": 841, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 723, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains a number of bacterial proteins of unknown function approximately 180 residues long. These are possibly integral membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR009898", "known_evidence_count": null, "matches": 1086, "name": "Protein of unknown function (DUF1440)", "partial_evidence_count": null, "pfam_id": "PF07274", "proteins": 1086, "proteomes": 969, "short_name": "DUF1440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07274", "structures": 0, "taxa": 1599, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 694, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents bacterial uncharacterised proteins such as Uncharacterized conserved protein Dip1984 from Corynebacterium diphtheriae, which shows an all-alpha structure. Some members of this family are annotated as septicolysin, such as [swissprot:H6NMB2], a cholesterol-dependent pore-forming cytolysin that acts to facilitate the infection of certain pathogenic gram-positive bacteria.", "domain_architectures": 3, "interpro_id": "IPR047741", "known_evidence_count": null, "matches": 1092, "name": "Family of unknown function (DUF6847)", "partial_evidence_count": null, "pfam_id": "PF20935", "proteins": 1085, "proteomes": 1032, "short_name": "DUF6847", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20935", "structures": 1, "taxa": 1824, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 737, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a domain of unknown function that is found either as a standalone protein or in combination with other domains. Members of this family possess a highly conserved LSAXXG motif that may constitute an active site. This domain may be distantly related to oxidative stress response YaaA proteins.", "domain_architectures": 21, "interpro_id": "IPR049251", "known_evidence_count": null, "matches": 1085, "name": "Family of unknown function (DUF6884)", "partial_evidence_count": null, "pfam_id": "PF21818", "proteins": 1085, "proteomes": 989, "short_name": "DUF6884", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21818", "structures": 0, "taxa": 1965, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 660, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Bacillus spp.", "domain_architectures": 1, "interpro_id": "IPR020076", "known_evidence_count": null, "matches": 1084, "name": "Protein of unknown function (DUF2768)", "partial_evidence_count": null, "pfam_id": "PF10966", "proteins": 1084, "proteomes": 1080, "short_name": "DUF2768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10966", "structures": 0, "taxa": 1315, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 703, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Members of this family appear to be found only in gamma proteobacteria. The function of this protein family is undetermined. Solution of the structures of the two members of this family investigated bear some resemblance to that of the single domain enzyme pterin-4a-carbinolamine dehydratase, PDC. Although the residues of PCDs involved in binding of metabolite are not conserved in the two structures under study, they do correspond to a surface-region structurally aligned with residues that are highly conserved, eg Glu 89, suggesting that this region is also involved in binding of a ligand, thereby possibly constituting a catalytic site of a yet uncharacterised enzyme specific for gamma proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR005272", "known_evidence_count": null, "matches": 1083, "name": "Protein of unknown function (DUF406)", "partial_evidence_count": null, "pfam_id": "PF04175", "proteins": 1083, "proteomes": 977, "short_name": "DUF406", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04175", "structures": 3, "taxa": 1360, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 879, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It has detectable similarity to HTH domains and it is predicted to adopt similar structure.", "domain_architectures": 41, "interpro_id": "IPR056143", "known_evidence_count": null, "matches": 1643, "name": "Domain of unknown function (DUF7726)", "partial_evidence_count": null, "pfam_id": "PF24852", "proteins": 1083, "proteomes": 685, "short_name": "DUF7726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24852", "structures": 0, "taxa": 1545, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 700, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR021553", "known_evidence_count": null, "matches": 1082, "name": "Protein of unknwon function (DUF3008)", "partial_evidence_count": null, "pfam_id": "PF11450", "proteins": 1082, "proteomes": 1018, "short_name": "DUF3008", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11450", "structures": 0, "taxa": 1473, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins from Bacteroidota, particularly in Flavobacteriaceae. These proteins are approximately 200 amino acids in length and are predicted to be membrane-associated. STRING analysis shows these proteins are functionally associated with sigma-70 factors ([pfam:PF04542] and [pfam:PF08281]) and other regulatory proteins. The function of this protein family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061906", "known_evidence_count": null, "matches": 1079, "name": "Domain of unknown function (DUF8845)", "partial_evidence_count": null, "pfam_id": "PF31253", "proteins": 1079, "proteomes": 1028, "short_name": "DUF8845", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31253", "structures": 0, "taxa": 1277, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 716, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 60 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR024564", "known_evidence_count": null, "matches": 1078, "name": "Domain of unknown function (DUF3364)", "partial_evidence_count": null, "pfam_id": "PF11844", "proteins": 1078, "proteomes": 999, "short_name": "DUF3364", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11844", "structures": 97, "taxa": 1824, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 722, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found on the C-terminal of large number of uncharacterized proteins with broad phylogenetic distribution, which includes human gut Bacteroides, g-proteobacteria (Vibrio and Shewanella) and also spirochetes from Leptospira genus. Solved structure of Bacteroides ovatus protein BACOVA_00967 shows a large beta barrel with an immunoglobulin-like fold and significant structural similarity to collagen-binding domain of adhesin from S. aureus (1amx), but with several additional long loops and secondary structure elements. Function of this domain is unknown.", "domain_architectures": 22, "interpro_id": "IPR032295", "known_evidence_count": null, "matches": 1079, "name": "Domain of unknown function (DUF4842)", "partial_evidence_count": null, "pfam_id": "PF16130", "proteins": 1078, "proteomes": 601, "short_name": "DUF4842", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16130", "structures": 1, "taxa": 1009, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 693, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of ig-like domains found at the N-terminus of putative phage proteins.", "domain_architectures": 92, "interpro_id": "IPR061801", "known_evidence_count": null, "matches": 1078, "name": "Domain of unknown function (DUF8740)", "partial_evidence_count": null, "pfam_id": "PF30789", "proteins": 1077, "proteomes": 611, "short_name": "DUF8740", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30789", "structures": 0, "taxa": 1137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 886, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It shares similarity with known ARM domains. It is frequently found next to an RRM domain.", "domain_architectures": 26, "interpro_id": "IPR059443", "known_evidence_count": null, "matches": 1085, "name": "Domain of unknown function (DUF8399)", "partial_evidence_count": null, "pfam_id": "PF28440", "proteins": 1076, "proteomes": 988, "short_name": "DUF8399", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28440", "structures": 0, "taxa": 2044, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 627, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function. An aminopeptidase domain is conserved within the family, but its relevance has not been established yet. Rebuilding from PDB:3kt9 shows this is an inserted (nested domain within the amino-peptidase). The function of this small domain is not known.", "domain_architectures": 11, "interpro_id": "IPR032610", "known_evidence_count": null, "matches": 1074, "name": "Domain of unknown function (DUF2172)", "partial_evidence_count": null, "pfam_id": "PF09940", "proteins": 1074, "proteomes": 1045, "short_name": "DUF2172", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09940", "structures": 1, "taxa": 1816, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 686, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. It has a detectable similarity to domains members of N-(deoxy)ribosyltransferase-like superfamily and is predicted to adopt similar structure.", "domain_architectures": 6, "interpro_id": "IPR056670", "known_evidence_count": null, "matches": 1073, "name": "Domain of unknown function (DUF7768)", "partial_evidence_count": null, "pfam_id": "PF24963", "proteins": 1073, "proteomes": 706, "short_name": "DUF7768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24963", "structures": 0, "taxa": 1577, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 825, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 13, "interpro_id": "IPR021434", "known_evidence_count": null, "matches": 1085, "name": "Protein of unknown function (DUF3082)", "partial_evidence_count": null, "pfam_id": "PF11282", "proteins": 1072, "proteomes": 678, "short_name": "DUF3082", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11282", "structures": 0, "taxa": 1914, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 597, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 272 to 336 amino acids in length. These proteins are distantly related to alpa/beta hydrolases so they may act as enzymes.", "domain_architectures": 5, "interpro_id": "IPR022529", "known_evidence_count": null, "matches": 1197, "name": "Protein of unknown function (DUF3530)", "partial_evidence_count": null, "pfam_id": "PF12048", "proteins": 1072, "proteomes": 1058, "short_name": "DUF3530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12048", "structures": 0, "taxa": 1396, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 687, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 200 residues locates in the C-terminal of some uncharacterized proteins in various Bacteroides and Parabacteroides species. The function of this family remains unknown.", "domain_architectures": 9, "interpro_id": "IPR032164", "known_evidence_count": null, "matches": 1072, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16391", "proteins": 1072, "proteomes": 346, "short_name": "DUF5000", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16391", "structures": 2, "taxa": 504, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 669, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function. The proteins are composed of a compact alpha/beta fold with five beta strands and two alpha helices. STRING networks suggest this protein may play a role in nitrogen fixation.", "domain_architectures": 3, "interpro_id": "IPR021388", "known_evidence_count": null, "matches": 1070, "name": "Domain of unknown function (DUF3024)", "partial_evidence_count": null, "pfam_id": "PF11225", "proteins": 1070, "proteomes": 984, "short_name": "DUF3024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11225", "structures": 0, "taxa": 1775, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 738, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the zinc ribbon found at the N-terminal of DUF2089, which usually occurs as a fusion of ZnR+HTH+SHOCT-like.", "domain_architectures": 4, "interpro_id": "IPR053957", "known_evidence_count": null, "matches": 1070, "name": "DUF2089 zinc ribbon", "partial_evidence_count": null, "pfam_id": "PF22747", "proteins": 1070, "proteomes": 1041, "short_name": "Zn_ribbon_DUF2089", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22747", "structures": 0, "taxa": 1926, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 869, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It has significant similarity to known RRM domains and it is predicted to adopt similar structure.", "domain_architectures": 22, "interpro_id": "IPR059444", "known_evidence_count": null, "matches": 1066, "name": "Domain of unknown function (DUF8400)", "partial_evidence_count": null, "pfam_id": "PF28442", "proteins": 1066, "proteomes": 995, "short_name": "DUF8400", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28442", "structures": 0, "taxa": 2054, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 671, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018690", "known_evidence_count": null, "matches": 1065, "name": "Uncharacterized protein conserved in bacteria (DUF2187)", "partial_evidence_count": null, "pfam_id": "PF09953", "proteins": 1065, "proteomes": 776, "short_name": "DUF2187", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09953", "structures": 0, "taxa": 1015, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 552, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001065) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the herboxidiene biosynthetic gene cluster from Streptomyces chromofuscus [[cite:PUB00098901]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 7, "interpro_id": "IPR046193", "known_evidence_count": null, "matches": 1066, "name": "Family of unknown function (DUF6221)", "partial_evidence_count": null, "pfam_id": "PF19730", "proteins": 1065, "proteomes": 777, "short_name": "DUF6221", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19730", "structures": 0, "taxa": 1042, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 717, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family is unknown. This region is found associated with a [pfam:PF04471] suggesting they could be part of a restriction modification system..", "domain_architectures": 11, "interpro_id": "IPR014923", "known_evidence_count": null, "matches": 1069, "name": "Domain of unknown function (DUF1802)", "partial_evidence_count": null, "pfam_id": "PF08819", "proteins": 1064, "proteomes": 961, "short_name": "DUF1802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08819", "structures": 0, "taxa": 1658, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 969, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins. Their genes occur in pilB/pilC operons.", "domain_architectures": 14, "interpro_id": "IPR055713", "known_evidence_count": null, "matches": 1063, "name": "Family of unknown function (DUF7289)", "partial_evidence_count": null, "pfam_id": "PF23960", "proteins": 1063, "proteomes": 360, "short_name": "DUF7289", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23960", "structures": 0, "taxa": 589, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 987, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function. It may have a role in ATPase activation.", "domain_architectures": 18, "interpro_id": "IPR013181", "known_evidence_count": null, "matches": 1177, "name": "Domain of unknown function (DUF1719)", "partial_evidence_count": null, "pfam_id": "PF08224", "proteins": 1062, "proteomes": 36, "short_name": "DUF1719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08224", "structures": 0, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 439, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 210 amino acids in length. There is a single completely conserved residue E that may be functionally important.", "domain_architectures": 31, "interpro_id": "IPR027914", "known_evidence_count": null, "matches": 1079, "name": "Domain of unknown function (DUF4456)", "partial_evidence_count": null, "pfam_id": "PF14644", "proteins": 1062, "proteomes": 828, "short_name": "DUF4456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14644", "structures": 3, "taxa": 2681, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 692, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised, they are predominantly found in bacteria but also in viruses. Proteins in this family are approximately 80 amino acids in length and presumably contain a ribbon-helix-helix DNA-binding motif.", "domain_architectures": 2, "interpro_id": "IPR046257", "known_evidence_count": null, "matches": 1062, "name": "Family of unknown function (DUF6290)", "partial_evidence_count": null, "pfam_id": "PF19807", "proteins": 1062, "proteomes": 848, "short_name": "DUF6290", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19807", "structures": 0, "taxa": 1732, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 701, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009491", "known_evidence_count": null, "matches": 1061, "name": "Protein of unknown function (DUF1107)", "partial_evidence_count": null, "pfam_id": "PF06526", "proteins": 1061, "proteomes": 889, "short_name": "DUF1107", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06526", "structures": 1, "taxa": 1195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 947, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 9, "interpro_id": "IPR022564", "known_evidence_count": null, "matches": 1068, "name": "Protein of unknown function (DUF2678)", "partial_evidence_count": null, "pfam_id": "PF10856", "proteins": 1057, "proteomes": 853, "short_name": "DUF2678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10856", "structures": 0, "taxa": 2833, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 929, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 11, "interpro_id": "IPR028022", "known_evidence_count": null, "matches": 1095, "name": "Domain of unknown function (DUF4600)", "partial_evidence_count": null, "pfam_id": "PF15372", "proteins": 1057, "proteomes": 754, "short_name": "DUF4600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15372", "structures": 0, "taxa": 2601, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 634, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, archaea and viruses, and is typically between 75 and 86 amino acids in length. There is a conserved SGNP sequence motif. There are two completely conserved G residues that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR043736", "known_evidence_count": null, "matches": 1057, "name": "Family of unknown function (DUF5681)", "partial_evidence_count": null, "pfam_id": "PF18932", "proteins": 1057, "proteomes": 768, "short_name": "DUF5681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18932", "structures": 0, "taxa": 1526, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 857, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from plants. It is predicted to fold into a three-stranded antiparallel twisted beta-sheet. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 14, "interpro_id": "IPR057188", "known_evidence_count": null, "matches": 1063, "name": "Domain of unknown function (DUF7866)", "partial_evidence_count": null, "pfam_id": "PF25268", "proteins": 1057, "proteomes": 341, "short_name": "DUF7866", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25268", "structures": 0, "taxa": 942, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 671, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 99 and 341 amino acids in length. This domain is distantly related to the STAS domain.", "domain_architectures": 19, "interpro_id": "IPR025474", "known_evidence_count": null, "matches": 1056, "name": "STAS-like domain of unknown function (DUF4325)", "partial_evidence_count": null, "pfam_id": "PF14213", "proteins": 1056, "proteomes": 967, "short_name": "DUF4325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14213", "structures": 1, "taxa": 2109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This gelsolin-like domain is found in a group of uncharacterised fungal proteins. Its function is unknown.", "domain_architectures": 43, "interpro_id": "IPR057226", "known_evidence_count": null, "matches": 1056, "name": "Domain of unknown function (DUF7904)", "partial_evidence_count": null, "pfam_id": "PF25480", "proteins": 1055, "proteomes": 989, "short_name": "DUF7904", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25480", "structures": 0, "taxa": 2323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 472, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins predominantly from Actinomycetes. It is predicted to fold into array of alpha-helices.", "domain_architectures": 4, "interpro_id": "IPR057705", "known_evidence_count": null, "matches": 1056, "name": "Domain of unknown function (DUF7945)", "partial_evidence_count": null, "pfam_id": "PF25656", "proteins": 1055, "proteomes": 957, "short_name": "DUF7945", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25656", "structures": 0, "taxa": 1193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 649, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 104 and 120 amino acids in length. There are two conserved sequence motifs: HYG and RCSI.", "domain_architectures": 3, "interpro_id": "IPR046125", "known_evidence_count": null, "matches": 1054, "name": "Family of unknown function (DUF6122)", "partial_evidence_count": null, "pfam_id": "PF19617", "proteins": 1054, "proteomes": 1019, "short_name": "DUF6122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19617", "structures": 0, "taxa": 1462, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 580, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001065) is described by MIBiG as an example of the following biosynthetic class, polyketide.", "domain_architectures": 4, "interpro_id": "IPR045991", "known_evidence_count": null, "matches": 1063, "name": "Family of unknown function (DUF5947)", "partial_evidence_count": null, "pfam_id": "PF19372", "proteins": 1052, "proteomes": 1032, "short_name": "DUF5947", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19372", "structures": 0, "taxa": 1364, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 669, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry was previously the N terminal portion of DUF524 ([pfam:PF04411]) before it was split into two. This domain has no known function. It is predicted to adopt an all beta secondary structure pattern followed by mainly alpha-helical structures [[cite:PUB00044133]].", "domain_architectures": 9, "interpro_id": "IPR018633", "known_evidence_count": null, "matches": 1054, "name": "Domain of unknown function (DUF2357)", "partial_evidence_count": null, "pfam_id": "PF09823", "proteins": 1051, "proteomes": 988, "short_name": "DUF2357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09823", "structures": 0, "taxa": 2075, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 643, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021268", "known_evidence_count": null, "matches": 1172, "name": "Protein of unknown function (DUF2845)", "partial_evidence_count": null, "pfam_id": "PF11006", "proteins": 1051, "proteomes": 773, "short_name": "DUF2845", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11006", "structures": 0, "taxa": 1185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 600, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a family of bacterial proteins of unknown function.", "domain_architectures": 4, "interpro_id": "IPR024289", "known_evidence_count": null, "matches": 1074, "name": "Protein of unknown function (DUF3828)", "partial_evidence_count": null, "pfam_id": "PF12883", "proteins": 1051, "proteomes": 810, "short_name": "DUF3828", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12883", "structures": 7, "taxa": 1215, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 546, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 92 to 110 amino acids in length. This protein has two completely conserved residues (G and R) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR021898", "known_evidence_count": null, "matches": 1050, "name": "Protein of unknown function (DUF3509)", "partial_evidence_count": null, "pfam_id": "PF12021", "proteins": 1050, "proteomes": 395, "short_name": "DUF3509", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12021", "structures": 0, "taxa": 437, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 931, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 14 } }, "demotion_reasons": [], "description": "This domain is found in Nude C 80 (Ndc80) proteins which can be found in species such as Homo sapiens. Ndc80 protein complexes are a core component of the end-on attachment sites for kinetochore microtubules. Ndc80 is also known as Hec1, for highly expressed in cancer 1 [[cite:PUB00049694]].", "domain_architectures": 23, "interpro_id": "IPR040967", "known_evidence_count": null, "matches": 1048, "name": "Domain of unknown function (DUF5595)", "partial_evidence_count": null, "pfam_id": "PF18077", "proteins": 1048, "proteomes": 866, "short_name": "DUF5595", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18077", "structures": 12, "taxa": 2717, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 944, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 286 and 398 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR028003", "known_evidence_count": null, "matches": 1135, "name": "Domain of unknown function (DUF4656)", "partial_evidence_count": null, "pfam_id": "PF15551", "proteins": 1046, "proteomes": 734, "short_name": "DUF4656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15551", "structures": 0, "taxa": 2233, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 816, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR014470", "known_evidence_count": null, "matches": 1047, "name": "Predicted integral membrane protein (DUF2270)", "partial_evidence_count": null, "pfam_id": "PF10028", "proteins": 1045, "proteomes": 864, "short_name": "DUF2270", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10028", "structures": 0, "taxa": 1370, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 654, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is expressed by proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR011223", "known_evidence_count": null, "matches": 1042, "name": "Protein of unknown function (DUF3302)", "partial_evidence_count": null, "pfam_id": "PF11742", "proteins": 1042, "proteomes": 898, "short_name": "DUF3302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11742", "structures": 0, "taxa": 1363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 658, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterised proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]].", "domain_architectures": 47, "interpro_id": "IPR025051", "known_evidence_count": null, "matches": 1043, "name": "Protein of unknown function (DUF3990)", "partial_evidence_count": null, "pfam_id": "PF13151", "proteins": 1041, "proteomes": 650, "short_name": "DUF3990", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13151", "structures": 0, "taxa": 1301, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 643, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 70 residues in length and is mainly found in various Caulobacter, Microcystis and Cyanothece species. The function of this family is unknown.", "domain_architectures": 7, "interpro_id": "IPR032568", "known_evidence_count": null, "matches": 1041, "name": "Domain of unknown function (DUF4926)", "partial_evidence_count": null, "pfam_id": "PF16277", "proteins": 1041, "proteomes": 681, "short_name": "DUF4926", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16277", "structures": 0, "taxa": 1682, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 657, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 143 and 271 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025341", "known_evidence_count": null, "matches": 1040, "name": "Domain of unknown function (DUF4247)", "partial_evidence_count": null, "pfam_id": "PF14042", "proteins": 1040, "proteomes": 1024, "short_name": "DUF4247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14042", "structures": 0, "taxa": 1283, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 642, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 117 and 134 amino acids in length. There is a conserved PES sequence motif. It is a putative lipoprotein.", "domain_architectures": 5, "interpro_id": "IPR014508", "known_evidence_count": null, "matches": 1040, "name": "Domain of unknown function (DUF4810)", "partial_evidence_count": null, "pfam_id": "PF16068", "proteins": 1040, "proteomes": 1031, "short_name": "DUF4810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16068", "structures": 0, "taxa": 1645, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 675, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 70 residues found in uncharacterized proteins in Bacteroidota, predominantly Flavobacteriaceae. These are small single-domain proteins. Some entries are annotated as 3-hydroxybutyryl-CoA dehydrogenase, but this annotation appears to be erroneous given the small size and lack of typical dehydrogenase features.", "domain_architectures": 1, "interpro_id": "IPR061889", "known_evidence_count": null, "matches": 1040, "name": "Domain of unknown function (DUF8828)", "partial_evidence_count": null, "pfam_id": "PF31163", "proteins": 1040, "proteomes": 1038, "short_name": "DUF8828", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31163", "structures": 0, "taxa": 1281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 683, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacterial and archaeal uncharacterised proteins. It is typically between 150 and 160 amino acids in length. It is remotely related to ribonuclease H-like nucleases but it is unlikely to possess any enzymatic activity.", "domain_architectures": 10, "interpro_id": "IPR053864", "known_evidence_count": null, "matches": 1039, "name": "Domain of unknown function (DUF6933)", "partial_evidence_count": null, "pfam_id": "PF22016", "proteins": 1039, "proteomes": 971, "short_name": "DUF6933", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22016", "structures": 0, "taxa": 1912, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 815, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised metazoan protein. It is predicted to adopt an alpha/beta structure composed of curved beta-sheet and alpha-helices packed on it.", "domain_architectures": 48, "interpro_id": "IPR058520", "known_evidence_count": null, "matches": 1043, "name": "Domain of unknown function (DUF8207)", "partial_evidence_count": null, "pfam_id": "PF26634", "proteins": 1039, "proteomes": 90, "short_name": "DUF8207", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26634", "structures": 0, "taxa": 426, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 665, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised bacterial proteins. It is predicted to adopt a seven-stranded antiparallel beta-sheet with similarity to Mog1p/PsbP-like domains. Some proteins containing this domain have a lipoprotein attachment motif at the N-terminus suggesting they may be associated with the membrane. This domain is usually found in two copies that share little if any sequence similarity to each other.", "domain_architectures": 4, "interpro_id": "IPR055797", "known_evidence_count": null, "matches": 1038, "name": "Domain of unknown function (DUF7373) N-terminal", "partial_evidence_count": null, "pfam_id": "PF24088", "proteins": 1038, "proteomes": 310, "short_name": "DUF7373", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24088", "structures": 0, "taxa": 392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 598, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001597) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the fluvirucin B2 biosynthetic gene cluster from Actinomadura fulva subsp. indica [[cite:PUB00098915]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 5, "interpro_id": "IPR045676", "known_evidence_count": null, "matches": 1037, "name": "Family of unknown function (DUF6194)", "partial_evidence_count": null, "pfam_id": "PF19694", "proteins": 1037, "proteomes": 1018, "short_name": "DUF6194", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19694", "structures": 0, "taxa": 1595, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 837, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plan proteins. It is predicted to contain four transmembrane helices.", "domain_architectures": 21, "interpro_id": "IPR057187", "known_evidence_count": null, "matches": 1042, "name": "Domain of unknown function (DUF7865)", "partial_evidence_count": null, "pfam_id": "PF25266", "proteins": 1035, "proteomes": 322, "short_name": "DUF7865", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25266", "structures": 0, "taxa": 876, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 967, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 100 residues found exclusively in Trichomonas (Parabasalia). This domain is found C-terminal to a KilA-N domain ([pfam:PF04383]). These proteins are present in numerous copies within the Trichomonas genome, suggesting lineage-specific gene family expansion. The function of this domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061865", "known_evidence_count": null, "matches": 1035, "name": "Domain of unknown function (DUF8804)", "partial_evidence_count": null, "pfam_id": "PF31079", "proteins": 1035, "proteomes": 2, "short_name": "DUF8804", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31079", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 609, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 88 and 112 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046094", "known_evidence_count": null, "matches": 1034, "name": "Family of unknown function (DUF6112)", "partial_evidence_count": null, "pfam_id": "PF19607", "proteins": 1034, "proteomes": 550, "short_name": "DUF6112", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19607", "structures": 0, "taxa": 782, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in bacterial proteins. It is predicted to adopt a RIFT-type beta(6)-barrel topology with a greater similarity to FAD-binding domains.", "domain_architectures": 5, "interpro_id": "IPR054209", "known_evidence_count": null, "matches": 1033, "name": "Domain of unknown function (DUF6916)", "partial_evidence_count": null, "pfam_id": "PF21880", "proteins": 1033, "proteomes": 884, "short_name": "DUF6916", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21880", "structures": 0, "taxa": 1552, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 638, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family based on the C-terminal domain of 3KOG which shows structural similarity to pore-forming proteins [[cite:PUB00031944]][[cite:PUB00032169]], suggesting it may have a lytic function.", "domain_architectures": 3, "interpro_id": "IPR024617", "known_evidence_count": null, "matches": 1031, "name": "Domain of unknown function (DUF3870)", "partial_evidence_count": null, "pfam_id": "PF12986", "proteins": 1031, "proteomes": 744, "short_name": "DUF3870", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12986", "structures": 0, "taxa": 1163, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 646, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in some glycosyl hydrolase family 2 proteins. This domain follows the N-terminal ([pfam:PF02837]), catalytic ([pfam:PF00703]) and C-terminal ([pfam:PF02836]) domains characteristic of this family. The domain is approximately 170-185 residues in length. These proteins include exo-beta-1,4-galactosidases involved in degrading galactan substituents from plant cell wall polysaccharides. The family is found in diverse bacteria including Bacteroidota and Bacillota. The function of this domain remains to be determined.", "domain_architectures": 50, "interpro_id": "IPR061557", "known_evidence_count": null, "matches": 1032, "name": "Domain of unknown function (DUF8487)", "partial_evidence_count": null, "pfam_id": "PF28964", "proteins": 1031, "proteomes": 716, "short_name": "DUF8487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28964", "structures": 1, "taxa": 1244, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 856, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 76 and 92 amino acids in length. There are two completely conserved W residues that may be functionally important.", "domain_architectures": 17, "interpro_id": "IPR031851", "known_evidence_count": null, "matches": 1030, "name": "Domain of unknown function (DUF4750)", "partial_evidence_count": null, "pfam_id": "PF15938", "proteins": 1030, "proteomes": 860, "short_name": "DUF4750", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15938", "structures": 0, "taxa": 3037, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 610, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 168 and 270 amino acids in length.", "domain_architectures": 21, "interpro_id": "IPR046582", "known_evidence_count": null, "matches": 1031, "name": "Domain of unknown function (DUF6630)", "partial_evidence_count": null, "pfam_id": "PF20335", "proteins": 1030, "proteomes": 935, "short_name": "DUF6630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20335", "structures": 0, "taxa": 1537, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 808, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is mainly found in bacteria and archaea. Proteins in this family are around 100 amino acids in length. There are two conserved sequence motifs, CGxxxCxC containing three conserved Cys residues and HGP. AlphaFold3 predicts a confident homodimer for A0A133VII6 (ipTM=0.82 pTM=0.83). These proteins have a positively charged surface patch and some members appear likely to bind DNA according to AlphaFold 3 predictions. This family is related to [pfam:PF07913].", "domain_architectures": 27, "interpro_id": "IPR046738", "known_evidence_count": null, "matches": 1030, "name": "Domain of unknown function (DUF6788)", "partial_evidence_count": null, "pfam_id": "PF20586", "proteins": 1030, "proteomes": 642, "short_name": "DUF6788", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20586", "structures": 0, "taxa": 1410, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 848, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in uncharacterised sequences from fungi. Some of these sequences are annotated as sphingosine kinases. This domain may adopt a PH-like fold.", "domain_architectures": 21, "interpro_id": "IPR055916", "known_evidence_count": null, "matches": 1029, "name": "Domain of unknown function (DUF7493)", "partial_evidence_count": null, "pfam_id": "PF24321", "proteins": 1029, "proteomes": 935, "short_name": "DUF7493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24321", "structures": 0, "taxa": 1913, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 944, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain has no known function. It is found in one or two copies in several Caenorhabditis elegans proteins. It is roughly 130 amino acids long. The domain contains 12 conserved cysteines which suggests that the domain is an extracellular domain and that these cysteines form six intradomain disulphide bridges. The GO annotation for this protein indicates that it has a function in nematode larval development and has a positive regulation of growth rate.", "domain_architectures": 27, "interpro_id": "IPR002542", "known_evidence_count": null, "matches": 1261, "name": "Domain of unknown function (DUF19)", "partial_evidence_count": null, "pfam_id": "PF01579", "proteins": 1028, "proteomes": 126, "short_name": "DUF19", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01579", "structures": 0, "taxa": 389, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 673, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as adenylyl cyclase however this cannot be confirmed. Currently no function is known.", "domain_architectures": 4, "interpro_id": "IPR021445", "known_evidence_count": null, "matches": 1085, "name": "Protein of unknown function (DUF3095)", "partial_evidence_count": null, "pfam_id": "PF11294", "proteins": 1027, "proteomes": 944, "short_name": "DUF3095", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11294", "structures": 0, "taxa": 1451, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 977, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of proteins mainly from halobacteria. It is predicted to show an HTH fold.", "domain_architectures": 2, "interpro_id": "IPR055547", "known_evidence_count": null, "matches": 1027, "name": "Domain of unknown function (DUF7123)", "partial_evidence_count": null, "pfam_id": "PF23438", "proteins": 1027, "proteomes": 328, "short_name": "DUF7123", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23438", "structures": 0, "taxa": 531, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 648, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the fourth domain found in some glycosyl hydrolase family 2 proteins. This immunoglobulin-like domain follows the N-terminal ([pfam:PF02837]), catalytic ([pfam:PF00703]) and C-terminal ([pfam:PF02836]) domains characteristic of this family. The domain is approximately 85-110 residues in length. These proteins include exo-beta-1,4-galactosidases involved in degrading galactan substituents from plant cell wall polysaccharides. The family is found in diverse bacteria including Bacteroidota and Bacillota. The function of this domain remains to be determined.", "domain_architectures": 52, "interpro_id": "IPR061558", "known_evidence_count": null, "matches": 1028, "name": "Domain of unknown function (DUF8488)", "partial_evidence_count": null, "pfam_id": "PF28967", "proteins": 1027, "proteomes": 718, "short_name": "DUF8488", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28967", "structures": 1, "taxa": 1249, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 603, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 80 amino acids in length.", "domain_architectures": 15, "interpro_id": "IPR025357", "known_evidence_count": null, "matches": 1026, "name": "Domain of unknown function (DUF4261)", "partial_evidence_count": null, "pfam_id": "PF14080", "proteins": 1026, "proteomes": 777, "short_name": "DUF4261", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14080", "structures": 0, "taxa": 1405, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 581, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 200 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046554", "known_evidence_count": null, "matches": 1025, "name": "Family of unknown function (DUF6708)", "partial_evidence_count": null, "pfam_id": "PF20455", "proteins": 1025, "proteomes": 416, "short_name": "DUF6708", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20455", "structures": 0, "taxa": 700, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 576, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a small domain of approximately 93 amino acids found predominantly in Actinobacteria including Streptomyces, Thermomonosporaceae, and Streptosporangiaceae. The domain is also found in some cyanobacteria. The domain is typically found as the sole domain in uncharacterized proteins and shows genomic context association with DUF6745 domain proteins.", "domain_architectures": 1, "interpro_id": "IPR061881", "known_evidence_count": null, "matches": 1024, "name": "Domain of unknown function (DUF8820)", "partial_evidence_count": null, "pfam_id": "PF31129", "proteins": 1024, "proteomes": 893, "short_name": "DUF8820", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31129", "structures": 0, "taxa": 1412, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 586, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 6, "interpro_id": "IPR018697", "known_evidence_count": null, "matches": 1023, "name": "Uncharacterized protein conserved in bacteria (DUF2199)", "partial_evidence_count": null, "pfam_id": "PF09965", "proteins": 1023, "proteomes": 961, "short_name": "DUF2199", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09965", "structures": 0, "taxa": 1570, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045502", "known_evidence_count": null, "matches": 1019, "name": "Family of unknown function (DUF6489)", "partial_evidence_count": null, "pfam_id": "PF20099", "proteins": 1019, "proteomes": 1001, "short_name": "DUF6489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20099", "structures": 0, "taxa": 1431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 603, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 176 and 187 amino acids in length. There is a conserved KTE sequence motif.", "domain_architectures": 6, "interpro_id": "IPR025365", "known_evidence_count": null, "matches": 1018, "name": "Domain of unknown function (DUF4269)", "partial_evidence_count": null, "pfam_id": "PF14091", "proteins": 1018, "proteomes": 997, "short_name": "DUF4269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14091", "structures": 0, "taxa": 1491, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 905, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 56 and 69 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR027858", "known_evidence_count": null, "matches": 1017, "name": "Domain of unknown function (DUF4516)", "partial_evidence_count": null, "pfam_id": "PF14990", "proteins": 1017, "proteomes": 804, "short_name": "DUF4516", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14990", "structures": 0, "taxa": 2841, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 621, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins found in various Bacteroides and Chloroflexus species. The function of this family is unknown.", "domain_architectures": 72, "interpro_id": "IPR032287", "known_evidence_count": null, "matches": 1023, "name": "Domain of unknown function (DUF4838)", "partial_evidence_count": null, "pfam_id": "PF16126", "proteins": 1017, "proteomes": 617, "short_name": "DUF4838", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16126", "structures": 0, "taxa": 1268, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 658, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in bacteria.", "domain_architectures": 7, "interpro_id": "IPR043745", "known_evidence_count": null, "matches": 1018, "name": "Family of unknown function (DUF5690)", "partial_evidence_count": null, "pfam_id": "PF18943", "proteins": 1017, "proteomes": 860, "short_name": "DUF5690", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18943", "structures": 0, "taxa": 1366, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 668, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterized proteins. They share remote similarity to both domains of proteins members of UDP-glycosyltransferase superfamily. In contrast to them, these proteins are predicted to consist of a single standalone domain.", "domain_architectures": 1, "interpro_id": "IPR054207", "known_evidence_count": null, "matches": 1017, "name": "Family of unknown function (DUF6913)", "partial_evidence_count": null, "pfam_id": "PF21857", "proteins": 1017, "proteomes": 1017, "short_name": "DUF6913", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21857", "structures": 0, "taxa": 1421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 710, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length. This presumed domain contains a conserved histidine and four conserved cysteines suggestive of zinc binding.", "domain_architectures": 2, "interpro_id": "IPR045601", "known_evidence_count": null, "matches": 1016, "name": "Family of unknown function (DUF6455)", "partial_evidence_count": null, "pfam_id": "PF20056", "proteins": 1016, "proteomes": 637, "short_name": "DUF6455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20056", "structures": 0, "taxa": 971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 609, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a number of hypothetical proteins of unknown function that seem to be specific to cyanobacteria. Members of this family have an alpha/beta hydrolase fold.", "domain_architectures": 22, "interpro_id": "IPR010802", "known_evidence_count": null, "matches": 1021, "name": "Alpha/beta hydrolase of unknown function (DUF1400)", "partial_evidence_count": null, "pfam_id": "PF07176", "proteins": 1014, "proteomes": 240, "short_name": "DUF1400", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07176", "structures": 0, "taxa": 651, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 581, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR019231", "known_evidence_count": null, "matches": 1013, "name": "Uncharacterized protein conserved in bacteria (DUF2170)", "partial_evidence_count": null, "pfam_id": "PF09938", "proteins": 1013, "proteomes": 969, "short_name": "DUF2170", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09938", "structures": 1, "taxa": 1381, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 719, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and fungi. Proteins in this family are typically between 431 and 744 amino acids in length. Protein in this family often contain a C-terminal [pfam:PF16151] domain. These proteins are likely to be cell surface proteins.", "domain_architectures": 40, "interpro_id": "IPR045690", "known_evidence_count": null, "matches": 1023, "name": "Family of unknown function (DUF6055)", "partial_evidence_count": null, "pfam_id": "PF19527", "proteins": 1013, "proteomes": 801, "short_name": "DUF6055", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19527", "structures": 0, "taxa": 1532, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 13 } }, "demotion_reasons": [], "description": "This domain is found in two tandem copies in the Alpha-glucan water dikinase (GWD1 and GWD2) from Arabidopsis thaliana and related proteins. It is predicted to adopt a globular structure consisting of three helical bundle. GWD1 is involved in the incorporation of phosphate into starch-like alpha-glucan, mostly at the C-6 position of glucose units [[cite:PUB00153995]]. This enzyme acts as regulator of starch mobilization by controlling the phosphate content of starch. The function of the domain represented in this entry is unknown.", "domain_architectures": 50, "interpro_id": "IPR055495", "known_evidence_count": null, "matches": 1603, "name": "Alpha-glucan water dikinase, DUF7067", "partial_evidence_count": null, "pfam_id": "PF23229", "proteins": 1012, "proteomes": 409, "short_name": "DUF7067", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23229", "structures": 0, "taxa": 1119, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 658, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain on unknown function is found at the C-terminal of uncharacterised proteins, found in Alphaproteobacteria. Proteins containing this domain are typically between 88 and 109 amino acids in length. There is a conserved motif GAxI/VVxP. Some members of this entry are likely integrases.", "domain_architectures": 1, "interpro_id": "IPR045594", "known_evidence_count": null, "matches": 1011, "name": "Domain of unknown function (DUF6460)", "partial_evidence_count": null, "pfam_id": "PF20061", "proteins": 1011, "proteomes": 956, "short_name": "DUF6460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20061", "structures": 0, "taxa": 1298, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 542, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain family that is found in bacteria. There is a conserved YDDRG sequence motif. The family includes YnaE from B. subtilis.", "domain_architectures": 5, "interpro_id": "IPR024976", "known_evidence_count": null, "matches": 1012, "name": "Domain of unknown function (DUF3885)", "partial_evidence_count": null, "pfam_id": "PF13021", "proteins": 1010, "proteomes": 928, "short_name": "DUF3885", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13021", "structures": 0, "taxa": 1630, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 823, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised plant proteins. It contains a set of conserved cysteines that are predicted to form disulfide bonds.", "domain_architectures": 35, "interpro_id": "IPR056633", "known_evidence_count": null, "matches": 1013, "name": "Domain of unknown function (DUF7731)", "partial_evidence_count": null, "pfam_id": "PF24865", "proteins": 1010, "proteomes": 351, "short_name": "DUF7731", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24865", "structures": 0, "taxa": 963, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 681, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family consists of uncharacterised bacterial proteins.", "domain_architectures": 1, "interpro_id": "IPR007376", "known_evidence_count": null, "matches": 1009, "name": "Protein of unknown function, DUF440", "partial_evidence_count": null, "pfam_id": "PF04269", "proteins": 1009, "proteomes": 947, "short_name": "DUF440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04269", "structures": 1, "taxa": 1356, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 418, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 9, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "The function of this family of eukaryotic proteins is not known.", "domain_architectures": 14, "interpro_id": "IPR027970", "known_evidence_count": null, "matches": 1015, "name": "Domain of unknown function (DUF4599)", "partial_evidence_count": null, "pfam_id": "PF15371", "proteins": 1009, "proteomes": 152, "short_name": "DUF4599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15371", "structures": 0, "taxa": 476, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 766, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are found in plants, lower eukaryotes, and bacteria and the chloroplast where it is annotated as Ycf49 or Ycf49-like. The function is not known though several members are annotated as putative membrane proteins.", "domain_architectures": 21, "interpro_id": "IPR019634", "known_evidence_count": null, "matches": 1011, "name": "Protein of unknown function (DUF2499)", "partial_evidence_count": null, "pfam_id": "PF10693", "proteins": 1008, "proteomes": 722, "short_name": "DUF2499", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10693", "structures": 0, "taxa": 2030, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 907, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 17, "interpro_id": "IPR040419", "known_evidence_count": null, "matches": 1037, "name": "Family of unknown function (DUF5568)", "partial_evidence_count": null, "pfam_id": "PF17724", "proteins": 1008, "proteomes": 731, "short_name": "DUF5568", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17724", "structures": 0, "taxa": 2240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 310, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. This domain is found in one or multiple copies and in combination with [pfam:PF01345], [pfam:PF13585] and others. It has a significant structural similarity to known ZU5 and Gain domains suggesting it may be involved in adhesion.", "domain_architectures": 301, "interpro_id": "IPR058515", "known_evidence_count": null, "matches": 1566, "name": "Domain of unknown function (DUF8202)", "partial_evidence_count": null, "pfam_id": "PF26628", "proteins": 1008, "proteomes": 675, "short_name": "DUF8202", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26628", "structures": 0, "taxa": 1024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 668, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 187 and 211 amino acids in length. There are two conserved sequence motifs: PHE and LGYP.", "domain_architectures": 3, "interpro_id": "IPR024523", "known_evidence_count": null, "matches": 1008, "name": "Protein of unknown function (DUF3793)", "partial_evidence_count": null, "pfam_id": "PF12672", "proteins": 1007, "proteomes": 928, "short_name": "DUF3793", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12672", "structures": 0, "taxa": 1596, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 659, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of short, approx 100 residue-long, bacterial proteins of unknown function. There is several conserved LE/LD sequence pairs.", "domain_architectures": 3, "interpro_id": "IPR025310", "known_evidence_count": null, "matches": 1007, "name": "Domain of unknown function (DUF4164)", "partial_evidence_count": null, "pfam_id": "PF13747", "proteins": 1007, "proteomes": 1006, "short_name": "DUF4164", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13747", "structures": 0, "taxa": 1414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 352, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in a wide range of bacterial cell surface proteins. It is predicted to adopt a beta-sandwich with Ig-like topology.", "domain_architectures": 171, "interpro_id": "IPR059807", "known_evidence_count": null, "matches": 1007, "name": "DUF6701, fourth domain", "partial_evidence_count": null, "pfam_id": "PF28238", "proteins": 1007, "proteomes": 919, "short_name": "DUF6701_4th", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28238", "structures": 0, "taxa": 1344, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 581, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 154 and 223 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR025412", "known_evidence_count": null, "matches": 1007, "name": "Domain of unknown function (DUF4304)", "partial_evidence_count": null, "pfam_id": "PF14137", "proteins": 1006, "proteomes": 916, "short_name": "DUF4304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14137", "structures": 0, "taxa": 1658, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 829, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found, in a few members, a the the C-terminus of family Avl9, [pfam:PF09794]. The function is not known.", "domain_architectures": 16, "interpro_id": "IPR028115", "known_evidence_count": null, "matches": 1048, "name": "Domain of unknown function (DUF4484)", "partial_evidence_count": null, "pfam_id": "PF14831", "proteins": 1005, "proteomes": 979, "short_name": "DUF4484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14831", "structures": 0, "taxa": 1945, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 563, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha-helical structure and it is frequently found in combination with [pfam:PF09977] and and [pfam:PF13400] which are likely involved in pilus biogenesis.", "domain_architectures": 16, "interpro_id": "IPR059337", "known_evidence_count": null, "matches": 1005, "name": "Domain of unknown function (DUF8293)", "partial_evidence_count": null, "pfam_id": "PF26942", "proteins": 1005, "proteomes": 961, "short_name": "DUF8293", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26942", "structures": 0, "taxa": 1367, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant sequences. It may adopt a HTH fold and it is found associated with [pfam:PF13831]),", "domain_architectures": 39, "interpro_id": "IPR061564", "known_evidence_count": null, "matches": 1007, "name": "Domain of unknown function (DUF8494)", "partial_evidence_count": null, "pfam_id": "PF29035", "proteins": 1005, "proteomes": 343, "short_name": "DUF8494", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29035", "structures": 0, "taxa": 947, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 422, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]]. Structure prediction suggests these proteins contain five alpha helices forming a compact domain.", "domain_architectures": 8, "interpro_id": "IPR045677", "known_evidence_count": null, "matches": 1008, "name": "Family of unknown function (DUF6197)", "partial_evidence_count": null, "pfam_id": "PF19698", "proteins": 1004, "proteomes": 720, "short_name": "DUF6197", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19698", "structures": 0, "taxa": 1152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 685, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a set of uncharacterised proteins found in bacteria. They share remote similarity to LolA, LolB outer-membrane lipoproteins.", "domain_architectures": 13, "interpro_id": "IPR046674", "known_evidence_count": null, "matches": 1002, "name": "Family of unknown function (DUF6544)", "partial_evidence_count": null, "pfam_id": "PF20181", "proteins": 1002, "proteomes": 944, "short_name": "DUF6544", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20181", "structures": 0, "taxa": 1993, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 637, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in uncharacterised bacterial proteins. It is predicted to adopt a seven-stranded antiparallel beta-sheet with similarity to Mog1p/PsbP-like domains. Some proteins containing this domain have a lipoprotein attachment motif at the N-terminus suggesting they may be associated with the membrane. This domain is usually found in two copies that share little if any sequence similarity to each other.", "domain_architectures": 5, "interpro_id": "IPR056463", "known_evidence_count": null, "matches": 1002, "name": "Domain of unknown function (DUF7373) C-terminal", "partial_evidence_count": null, "pfam_id": "PF24092", "proteins": 1002, "proteomes": 289, "short_name": "DUF7373_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24092", "structures": 0, "taxa": 356, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 716, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry is found in Nostoc sp. PCC 7120, Agrobacterium tumefaciens, Rhizobium meliloti, and Gloeobacter violaceus in a conserved two-gene neighbourhood. Proteins containing this entry appear to span the membrane seven times.", "domain_architectures": 1, "interpro_id": "IPR024464", "known_evidence_count": null, "matches": 1001, "name": "Putative integral membrane protein (DUF2391)", "partial_evidence_count": null, "pfam_id": "PF09622", "proteins": 1001, "proteomes": 917, "short_name": "DUF2391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09622", "structures": 0, "taxa": 1729, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 646, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists mostly of short uncharacterized proteins found in various high GC Gram positive bacteria, primarily Mycobacterium species. However in some proteins, such as for instance Rv0943c proteins from Mycobacterium tuberculosis H37Rv, DUF4873 domain is found at the C-terminus, following the flavin-binding monooxygenase-like domain [pfam:PF00743], which is why probably many proteins with DUF4873 domains are annotated as monooxygenases. However these functions are not confirmed experimentally and the function of DUF4873 domain is still unknown.", "domain_architectures": 10, "interpro_id": "IPR032371", "known_evidence_count": null, "matches": 1001, "name": "Domain of unknown function (DUF4873)", "partial_evidence_count": null, "pfam_id": "PF16170", "proteins": 1001, "proteomes": 899, "short_name": "DUF4873", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16170", "structures": 0, "taxa": 1094, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 781, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in Zinc finger CCCH domain-containing protein 62 from Oryza sativa (C3H62) and similar proteins from plants. Members of this family also show a SAP domain ([pfam:PF02037]). This domain is predicted to adopt a mainly beta configuration.", "domain_architectures": 56, "interpro_id": "IPR056116", "known_evidence_count": null, "matches": 1021, "name": "Domain of unknown function (DUF7699)", "partial_evidence_count": null, "pfam_id": "PF24766", "proteins": 1001, "proteomes": 383, "short_name": "DUF7699", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24766", "structures": 0, "taxa": 1054, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 689, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 7, "interpro_id": "IPR021484", "known_evidence_count": null, "matches": 1012, "name": "Protein of unknown function (DUF3137)", "partial_evidence_count": null, "pfam_id": "PF11335", "proteins": 998, "proteomes": 787, "short_name": "DUF3137", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11335", "structures": 0, "taxa": 1510, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 711, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is predominantly found at the N-terminal end of proteins from cyanobacteria and plants, including Biogenesis factor required for ATP synthase 1 (BFA1, [swissprot:F4J1U2]) from Arabidopsis thaliana. BFA1 promotes the assembly of the CF1 subcomplex of the chloroplast ATP synthase by specifically interacting with the gamma and beta subunits. This domain consists of nine beta-sheets and two alpha- helices forming an atypical beta-barrel, which locates perpendicularly to the typical beta-barrel formed by the C-terminal domain [[cite:PUB00100989]].", "domain_architectures": 16, "interpro_id": "IPR022017", "known_evidence_count": null, "matches": 1001, "name": "Domain of unknown function (DUF3598), N-terminal", "partial_evidence_count": null, "pfam_id": "PF12204", "proteins": 998, "proteomes": 627, "short_name": "DUF3598_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12204", "structures": 2, "taxa": 1801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and archaea, and is approximately 50 amino acids in length.", "domain_architectures": 15, "interpro_id": "IPR022532", "known_evidence_count": null, "matches": 998, "name": "Protein of unknown function (DUF3696)", "partial_evidence_count": null, "pfam_id": "PF12476", "proteins": 998, "proteomes": 914, "short_name": "DUF3696", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12476", "structures": 0, "taxa": 2024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 730, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of metal-binding hypothetical bacterial proteins have no known function.", "domain_architectures": 10, "interpro_id": "IPR019271", "known_evidence_count": null, "matches": 997, "name": "Predicted metal-binding protein (DUF2284)", "partial_evidence_count": null, "pfam_id": "PF10050", "proteins": 996, "proteomes": 637, "short_name": "DUF2284", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10050", "structures": 0, "taxa": 1338, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 655, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR024495", "known_evidence_count": null, "matches": 1004, "name": "Protein of unknown function (DUF2771)", "partial_evidence_count": null, "pfam_id": "PF10969", "proteins": 996, "proteomes": 988, "short_name": "DUF2771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10969", "structures": 0, "taxa": 1204, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 653, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000087) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the lasalocid biosynthetic gene cluster from Streptomyces lasaliensis [[cite:PUB00098916]].", "domain_architectures": 3, "interpro_id": "IPR045679", "known_evidence_count": null, "matches": 996, "name": "Family of unknown function (DUF6199)", "partial_evidence_count": null, "pfam_id": "PF19701", "proteins": 996, "proteomes": 769, "short_name": "DUF6199", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19701", "structures": 0, "taxa": 1223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 600, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 11, "interpro_id": "IPR014951", "known_evidence_count": null, "matches": 1032, "name": "Protein of unknown function (DUF1822)", "partial_evidence_count": null, "pfam_id": "PF08852", "proteins": 995, "proteomes": 198, "short_name": "DUF1822", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08852", "structures": 0, "taxa": 557, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 832, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found mostly in Saccharomycetales.", "domain_architectures": 4, "interpro_id": "", "known_evidence_count": null, "matches": 1007, "name": "Disordered region of unknown function (DUF5315)", "partial_evidence_count": null, "pfam_id": "PF17242", "proteins": 995, "proteomes": 956, "short_name": "DUF5315", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17242", "structures": 0, "taxa": 1886, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 610, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 247 and 291 amino acids in length. There is a conserved EED sequence motif. This is a putative metallopeptidase.", "domain_architectures": 7, "interpro_id": "IPR025644", "known_evidence_count": null, "matches": 1288, "name": "Putative metallopeptidase", "partial_evidence_count": null, "pfam_id": "PF14247", "proteins": 994, "proteomes": 887, "short_name": "DUF4344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14247", "structures": 0, "taxa": 1446, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 620, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family includes uncharacterised proteins predominantly found in Firmicutes, including Uncharacterized protein YfhH from Bacillus subtilis and protein GK0453 from Geobacillus kaustophilus. GK0453 shows two small domains: an helix-turn-helix like motif is found in its N-terminal domain while an SH3-like beta-barrel like structure is observed its C-terminal region. Its specific function is unknown [[cite:PUB00100670]]. Some of the members of this protein family are annotated as transcriptional regulators (see Q3EXU7, Q81I96).", "domain_architectures": 1, "interpro_id": "IPR014938", "known_evidence_count": null, "matches": 993, "name": "Protein of unknown function (DUF1811)", "partial_evidence_count": null, "pfam_id": "PF08838", "proteins": 993, "proteomes": 990, "short_name": "DUF1811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08838", "structures": 2, "taxa": 1249, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 120 residues in length and is mainly found in various Bacillus species, such as Bacillus subtilis and Bacillus amyloliquefaciens. Several members are annotated as ydbC, but the specific function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR032555", "known_evidence_count": null, "matches": 994, "name": "Domain of unknown function (DUF4937)", "partial_evidence_count": null, "pfam_id": "PF16291", "proteins": 992, "proteomes": 983, "short_name": "DUF4937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16291", "structures": 0, "taxa": 1184, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 869, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 12, "interpro_id": "IPR040687", "known_evidence_count": null, "matches": 1339, "name": "Family of unknown function (DUF5586)", "partial_evidence_count": null, "pfam_id": "PF17824", "proteins": 992, "proteomes": 509, "short_name": "DUF5586", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17824", "structures": 0, "taxa": 1821, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 423, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 95 residues found as a single-domain protein in Streptomycetaceae. The function of this domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061886", "known_evidence_count": null, "matches": 992, "name": "Domain if unknown function (DUF8825)", "partial_evidence_count": null, "pfam_id": "PF31154", "proteins": 992, "proteomes": 632, "short_name": "DUF8825", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31154", "structures": 0, "taxa": 708, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 651, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria. The function is not known.", "domain_architectures": 5, "interpro_id": "IPR019691", "known_evidence_count": null, "matches": 990, "name": "Protein of unknown function (DUF2585)", "partial_evidence_count": null, "pfam_id": "PF10755", "proteins": 989, "proteomes": 934, "short_name": "DUF2585", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10755", "structures": 0, "taxa": 1368, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 608, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021332", "known_evidence_count": null, "matches": 989, "name": "Protein of unknown function (DUF2946)", "partial_evidence_count": null, "pfam_id": "PF11161", "proteins": 989, "proteomes": 988, "short_name": "DUF2944", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11161", "structures": 0, "taxa": 1240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised proteins from plants and some fungal species. This domain is usually found associated with [pfam:PF23704] and [pfam:PF04182].", "domain_architectures": 81, "interpro_id": "IPR056020", "known_evidence_count": null, "matches": 994, "name": "Domain of unknown function (DUF7599)", "partial_evidence_count": null, "pfam_id": "PF24538", "proteins": 989, "proteomes": 482, "short_name": "DUF7599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24538", "structures": 0, "taxa": 1363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 617, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR025273", "known_evidence_count": null, "matches": 988, "name": "Protein of unknown function (DUF4064)", "partial_evidence_count": null, "pfam_id": "PF13273", "proteins": 988, "proteomes": 627, "short_name": "DUF4064", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13273", "structures": 0, "taxa": 970, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 620, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in primarily found in Bacteroidetes and proteobacteria. Proteins in this family are typically between 300 and 331 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046715", "known_evidence_count": null, "matches": 988, "name": "Family of unknown function (DUF6607)", "partial_evidence_count": null, "pfam_id": "PF20311", "proteins": 988, "proteomes": 971, "short_name": "DUF6607", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20311", "structures": 1, "taxa": 1493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 338, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in a wide range of bacterial cell surface proteins. It is predicted to adopt a beta-sandwich with Ig-like topology.", "domain_architectures": 170, "interpro_id": "IPR059819", "known_evidence_count": null, "matches": 990, "name": "DUF6701, third domain", "partial_evidence_count": null, "pfam_id": "PF28247", "proteins": 988, "proteomes": 905, "short_name": "DUF6701_3rd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28247", "structures": 0, "taxa": 1358, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 710, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 10, "interpro_id": "IPR007380", "known_evidence_count": null, "matches": 986, "name": "Family of unknown function (DUF438)", "partial_evidence_count": null, "pfam_id": "PF04282", "proteins": 986, "proteomes": 957, "short_name": "DUF438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04282", "structures": 0, "taxa": 1757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from fungi. This domain has several conserved residues G, W and P and is predicted to adopt an OB-like fold.", "domain_architectures": 25, "interpro_id": "IPR061572", "known_evidence_count": null, "matches": 987, "name": "Domain of unknown function (DUF8502)", "partial_evidence_count": null, "pfam_id": "PF29077", "proteins": 986, "proteomes": 944, "short_name": "DUF8502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29077", "structures": 0, "taxa": 1920, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 640, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 64 and 166 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045468", "known_evidence_count": null, "matches": 985, "name": "Family of unknown function (DUF6496)", "partial_evidence_count": null, "pfam_id": "PF20106", "proteins": 985, "proteomes": 869, "short_name": "DUF6496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20106", "structures": 0, "taxa": 1275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 709, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. The C-terminus contains a cluster of cysteines that are similar to the iron-sulfur cluster found at the N-terminus of [pfam:PF04055].", "domain_architectures": 8, "interpro_id": "IPR014998", "known_evidence_count": null, "matches": 987, "name": "Domain of unknown function (DUF1848)", "partial_evidence_count": null, "pfam_id": "PF08902", "proteins": 984, "proteomes": 893, "short_name": "DUF1848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08902", "structures": 0, "taxa": 1967, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 599, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a family of phage tail tube proteins including protein XkdM from phage-like element PBSX protein ([swissprot:P54332]) whose structure adopts a beta barrel flanked with alpha helical regions.", "domain_architectures": 1, "interpro_id": "IPR018989", "known_evidence_count": null, "matches": 984, "name": "Phage tail tube protein", "partial_evidence_count": null, "pfam_id": "PF09393", "proteins": 984, "proteomes": 707, "short_name": "DUF2001", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09393", "structures": 13, "taxa": 1216, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 949, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found exclusively in Trichomonas proteins. It is predicted to fold into an alpha/beta structure.", "domain_architectures": 1, "interpro_id": "IPR056679", "known_evidence_count": null, "matches": 982, "name": "Domain of unknown function (DUF7777)", "partial_evidence_count": null, "pfam_id": "PF24992", "proteins": 982, "proteomes": 1, "short_name": "DUF7777", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24992", "structures": 0, "taxa": 10, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 593, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021393", "known_evidence_count": null, "matches": 982, "name": "Protein of unknown function (DUF3034)", "partial_evidence_count": null, "pfam_id": "PF11231", "proteins": 981, "proteomes": 932, "short_name": "DUF3034", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11231", "structures": 0, "taxa": 1394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 451, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents small uncharacterized proteins of approximately 108 residues found in Actinomycetes, particularly Streptomyces and Nocardioides. These proteins typically consist of this single domain only. STRING network analysis shows strong functional association with SIS domains ([pfam:PF01380]) and HTH_6 transcription factors ([pfam:PF01418]), suggesting a possible role in sugar metabolism regulation.", "domain_architectures": 1, "interpro_id": "IPR061880", "known_evidence_count": null, "matches": 981, "name": "Domain of unknown function (DUF8819)", "partial_evidence_count": null, "pfam_id": "PF31126", "proteins": 981, "proteomes": 974, "short_name": "DUF8819", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31126", "structures": 0, "taxa": 1059, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 852, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 180 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR031813", "known_evidence_count": null, "matches": 980, "name": "Domain of unknown function (DUF4745)", "partial_evidence_count": null, "pfam_id": "PF15923", "proteins": 980, "proteomes": 646, "short_name": "DUF4745", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15923", "structures": 1, "taxa": 2291, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus and appears to be predominantly found in actinobacteria [[cite:PUB00098882]].", "domain_architectures": 6, "interpro_id": "IPR046156", "known_evidence_count": null, "matches": 980, "name": "Family of unknown function (DUF6158)", "partial_evidence_count": null, "pfam_id": "PF19655", "proteins": 980, "proteomes": 954, "short_name": "DUF6158", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19655", "structures": 0, "taxa": 1116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 622, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of prokaryotic proteins have no known function.", "domain_architectures": 5, "interpro_id": "IPR019226", "known_evidence_count": null, "matches": 980, "name": "Uncharacterized small protein (DUF2158)", "partial_evidence_count": null, "pfam_id": "PF09926", "proteins": 979, "proteomes": 858, "short_name": "DUF2158", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09926", "structures": 0, "taxa": 1457, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 636, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of transmembrane proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 576 to 592 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR021941", "known_evidence_count": null, "matches": 982, "name": "Transmembrane protein of unknown function (DUF3556)", "partial_evidence_count": null, "pfam_id": "PF12077", "proteins": 979, "proteomes": 605, "short_name": "DUF3556", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12077", "structures": 0, "taxa": 835, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 699, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 108 and 129 amino acids in length. There are two conserved sequence motifs: NDP and RVLT.", "domain_architectures": 4, "interpro_id": "IPR022243", "known_evidence_count": null, "matches": 979, "name": "Protein of unknown function (DUF3768)", "partial_evidence_count": null, "pfam_id": "PF12599", "proteins": 979, "proteomes": 644, "short_name": "DUF3768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12599", "structures": 0, "taxa": 1102, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry contains YjbD from Escherichia coli ([swissprot:P75828]), which is annotated as a nucleotide triphosphate hydrolase.", "domain_architectures": 16, "interpro_id": "IPR022602", "known_evidence_count": null, "matches": 1022, "name": "Protein of unknown function (DUF2813)", "partial_evidence_count": null, "pfam_id": "PF11398", "proteins": 977, "proteomes": 942, "short_name": "DUF2813", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11398", "structures": 0, "taxa": 1628, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 719, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 13, "interpro_id": "IPR019275", "known_evidence_count": null, "matches": 987, "name": "Uncharacterized integral membrane protein (DUF2301)", "partial_evidence_count": null, "pfam_id": "PF10063", "proteins": 976, "proteomes": 832, "short_name": "DUF2301", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10063", "structures": 0, "taxa": 2091, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 573, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised bacterial proteins. They are predicted to adopt alpha-helical structure composed of six up-and-down helices. It is likely that these proteins are associated with the membrane.", "domain_architectures": 3, "interpro_id": "IPR053824", "known_evidence_count": null, "matches": 976, "name": "Family of unknown function (DUF7010)", "partial_evidence_count": null, "pfam_id": "PF22765", "proteins": 976, "proteomes": 915, "short_name": "DUF7010", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22765", "structures": 0, "taxa": 1558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 508, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found to the C-terminus of [pfam:PF00355]. This family includes a protein called CrtV that may be a methyltransferase or demethylase.", "domain_architectures": 6, "interpro_id": "IPR045612", "known_evidence_count": null, "matches": 981, "name": "Domain of unknown function (DUF5914)", "partial_evidence_count": null, "pfam_id": "PF19299", "proteins": 975, "proteomes": 941, "short_name": "DUF5914", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19299", "structures": 0, "taxa": 1132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised although it is found in the Type 2 secretion protein F. This domain family is found in Actinobacteria, and is approximately 140 amino acids in length. The family is found in association with [pfam:PF00482].", "domain_architectures": 2, "interpro_id": "IPR045980", "known_evidence_count": null, "matches": 975, "name": "Family of unknown function (DUF5936)", "partial_evidence_count": null, "pfam_id": "PF19359", "proteins": 975, "proteomes": 969, "short_name": "DUF5936", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19359", "structures": 0, "taxa": 1092, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 785, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to adopt an SH3-like fold.", "domain_architectures": 25, "interpro_id": "IPR057234", "known_evidence_count": null, "matches": 977, "name": "Domain of unknown function (DUF7912)", "partial_evidence_count": null, "pfam_id": "PF25498", "proteins": 975, "proteomes": 415, "short_name": "DUF7912", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25498", "structures": 0, "taxa": 1126, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 794, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This archaebacterial protein has no known function. The protein contains seven conserved cysteines containing a CxxCxxC motif and may also be an integral membrane protein [[cite:PUB00096938]].", "domain_architectures": 5, "interpro_id": "IPR002829", "known_evidence_count": null, "matches": 983, "name": "Protein of unknown function DUF116", "partial_evidence_count": null, "pfam_id": "PF01976", "proteins": 974, "proteomes": 868, "short_name": "DUF116", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01976", "structures": 0, "taxa": 1755, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family has a TIM-barrel structure and appears to be related to a variety of glycosyl hydrolase enzymes.", "domain_architectures": 16, "interpro_id": "IPR027849", "known_evidence_count": null, "matches": 977, "name": "Domain of unknown function (DUF4434)", "partial_evidence_count": null, "pfam_id": "PF14488", "proteins": 974, "proteomes": 765, "short_name": "DUF4434", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14488", "structures": 1, "taxa": 1375, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Putative Tryptophanyl-tRNA synthetase.", "domain_architectures": 1, "interpro_id": "IPR025007", "known_evidence_count": null, "matches": 973, "name": "Domain of unknown function (DUF3899)", "partial_evidence_count": null, "pfam_id": "PF13038", "proteins": 973, "proteomes": 889, "short_name": "DUF3899", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13038", "structures": 0, "taxa": 1246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 583, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001203) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the clarexpoxcin biosynthetic gene cluster from uncultured bacterium AR_456 [[cite:PUB00099430]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 7, "interpro_id": "IPR046259", "known_evidence_count": null, "matches": 973, "name": "Family of unknown function (DUF6292)", "partial_evidence_count": null, "pfam_id": "PF19809", "proteins": 973, "proteomes": 464, "short_name": "DUF6292", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19809", "structures": 0, "taxa": 604, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 614, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2, "TraitMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 5, "interpro_id": "IPR018760", "known_evidence_count": null, "matches": 972, "name": "Uncharacterised protein conserved in bacteria (DUF2326)", "partial_evidence_count": null, "pfam_id": "PF10088", "proteins": 972, "proteomes": 935, "short_name": "DUF2326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10088", "structures": 0, "taxa": 2158, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 800, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from plants. This domain is predicted to fold into a globular structure that adopts a ferredoxin-like fold.", "domain_architectures": 20, "interpro_id": "IPR055477", "known_evidence_count": null, "matches": 972, "name": "Domain of unknown function (DUF7049)", "partial_evidence_count": null, "pfam_id": "PF23132", "proteins": 972, "proteomes": 341, "short_name": "DUF7049", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23132", "structures": 0, "taxa": 956, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 560, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins contains many bacterial proteins that are encoded by the UnbL gene. The function of these proteins is unknown.", "domain_architectures": 2, "interpro_id": "IPR012964", "known_evidence_count": null, "matches": 971, "name": "Protein of unknown function (DUF1702)", "partial_evidence_count": null, "pfam_id": "PF08012", "proteins": 971, "proteomes": 562, "short_name": "DUF1702", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08012", "structures": 0, "taxa": 889, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 555, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 523 and 552 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR026487", "known_evidence_count": null, "matches": 975, "name": "Family of unknown function (DUF6119)", "partial_evidence_count": null, "pfam_id": "PF19614", "proteins": 971, "proteomes": 877, "short_name": "DUF6119", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19614", "structures": 0, "taxa": 1772, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 577, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR021550", "known_evidence_count": null, "matches": 970, "name": "Protein of unknown function (DUF2897)", "partial_evidence_count": null, "pfam_id": "PF11446", "proteins": 970, "proteomes": 965, "short_name": "DUF2897", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11446", "structures": 0, "taxa": 1139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 608, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 138 and 158 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046144", "known_evidence_count": null, "matches": 970, "name": "Family of unknown function (DUF6146)", "partial_evidence_count": null, "pfam_id": "PF19643", "proteins": 970, "proteomes": 966, "short_name": "DUF6146", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19643", "structures": 0, "taxa": 1209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 550, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found mainly in bacterial proteins, either standalone or in combination with other domains. It is probably remotely related to the anticodon binding domain observed in histidyl, glycyl, threonyl and prolyl tRNA synthetases.", "domain_architectures": 18, "interpro_id": "IPR053832", "known_evidence_count": null, "matches": 1033, "name": "Domain of unknown function (DUF6924)", "partial_evidence_count": null, "pfam_id": "PF21962", "proteins": 970, "proteomes": 753, "short_name": "DUF6924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21962", "structures": 0, "taxa": 1308, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 685, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "CellStructureMech": 2, "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "", "domain_architectures": 3, "interpro_id": "IPR007458", "known_evidence_count": null, "matches": 969, "name": "Protein of unknown function (DUF496)", "partial_evidence_count": null, "pfam_id": "PF04363", "proteins": 969, "proteomes": 923, "short_name": "DUF496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04363", "structures": 0, "taxa": 1393, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 661, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021446", "known_evidence_count": null, "matches": 985, "name": "Protein of unknown function (DUF3096)", "partial_evidence_count": null, "pfam_id": "PF11295", "proteins": 969, "proteomes": 902, "short_name": "DUF3096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11295", "structures": 0, "taxa": 1447, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 761, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised.This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 98 and 228 amino acids in length. There is a conserved LHG sequence motif.", "domain_architectures": 24, "interpro_id": "IPR021995", "known_evidence_count": null, "matches": 992, "name": "Protein of unknown function (DUF3593)", "partial_evidence_count": null, "pfam_id": "PF12159", "proteins": 969, "proteomes": 714, "short_name": "DUF3593", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12159", "structures": 0, "taxa": 2013, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 552, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins of approximately 145 residues found in Bacillota (particularly Paenibacillaceae and Bacillaceae) and Actinomycetota (including Streptomycetaceae). The proteins occur as single-domain proteins. While computationally annotated as phage tail proteins in UniProt, there is no experimental evidence supporting this function, and the annotation likely reflects genomic proximity to prophage regions rather than demonstrated function. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061882", "known_evidence_count": null, "matches": 969, "name": "Domain of unknown function (DUF8821)", "partial_evidence_count": null, "pfam_id": "PF31136", "proteins": 969, "proteomes": 907, "short_name": "DUF8821", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31136", "structures": 0, "taxa": 1299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 610, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this uncharacterised protein family are found in a number of alphaproteobacteria, including root nodule bacteria, Brucella suis, Caulobacter crescentus, and Rhodopseudomonas palustris. Conserved residues include two well-separated cysteines, suggesting a disulfide bond. The function is unknown.", "domain_architectures": 1, "interpro_id": "IPR012645", "known_evidence_count": null, "matches": 968, "name": "Protein of unknown function (DUF2385)", "partial_evidence_count": null, "pfam_id": "PF09539", "proteins": 968, "proteomes": 966, "short_name": "DUF2385", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09539", "structures": 0, "taxa": 1288, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 519, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Members of this family are found in various bacterial proteins, including MotA/TolQ/ExbB proton channels and other transport proteins. The exact function of this set of domains has not, as yet, been determined.", "domain_architectures": 151, "interpro_id": "IPR018765", "known_evidence_count": null, "matches": 1013, "name": "Domain of unknown function (DUF2341)", "partial_evidence_count": null, "pfam_id": "PF10102", "proteins": 967, "proteomes": 814, "short_name": "DUF2341", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10102", "structures": 0, "taxa": 1576, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 601, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised bacterial proteins are about 500 amino acids in length.", "domain_architectures": 14, "interpro_id": "IPR025394", "known_evidence_count": null, "matches": 1027, "name": "Protein of unknown function (DUF4127)", "partial_evidence_count": null, "pfam_id": "PF13552", "proteins": 967, "proteomes": 746, "short_name": "DUF4127", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13552", "structures": 0, "taxa": 1363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 650, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 336 and 370 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025535", "known_evidence_count": null, "matches": 967, "name": "Domain of unknown function (DUF4421)", "partial_evidence_count": null, "pfam_id": "PF14391", "proteins": 967, "proteomes": 795, "short_name": "DUF4421", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14391", "structures": 0, "taxa": 1156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 861, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "The family DUF2349 is the N-terminal part of this family. This protein is found in eukaryotes but its function is not known.", "domain_architectures": 12, "interpro_id": "IPR018861", "known_evidence_count": null, "matches": 973, "name": "Protein of unknown function C-terminus (DUF2448)", "partial_evidence_count": null, "pfam_id": "PF10476", "proteins": 966, "proteomes": 725, "short_name": "DUF2448", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10476", "structures": 0, "taxa": 2242, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 801, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function. Most of the members seem to carry one trans-membrane region.", "domain_architectures": 7, "interpro_id": "IPR035213", "known_evidence_count": null, "matches": 968, "name": "Family of unknown function (DUF5321)", "partial_evidence_count": null, "pfam_id": "PF17254", "proteins": 966, "proteomes": 954, "short_name": "DUF5321", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17254", "structures": 0, "taxa": 1943, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 616, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed integral membrane protein domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is approximately 70 amino acids in length.", "domain_architectures": 14, "interpro_id": "IPR025328", "known_evidence_count": null, "matches": 1007, "name": "Domain of unknown function (DUF4234)", "partial_evidence_count": null, "pfam_id": "PF14018", "proteins": 965, "proteomes": 881, "short_name": "DUF4234", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14018", "structures": 0, "taxa": 1649, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 677, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 200 amino acids in length. Some members are hypothetical ECF transporters related to the Gx transporter superfamily (CL0315).", "domain_architectures": 2, "interpro_id": "IPR046487", "known_evidence_count": null, "matches": 965, "name": "Family of unknown function (DUF6580)", "partial_evidence_count": null, "pfam_id": "PF20221", "proteins": 965, "proteomes": 870, "short_name": "DUF6580", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20221", "structures": 0, "taxa": 1493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 773, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found once or twice in a group of fungal uncharacterised proteins. It is predicted to adopt a mainly beta configuration.", "domain_architectures": 44, "interpro_id": "IPR056021", "known_evidence_count": null, "matches": 968, "name": "Domain of unknown function (DUF7600)", "partial_evidence_count": null, "pfam_id": "PF24539", "proteins": 963, "proteomes": 426, "short_name": "DUF7600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24539", "structures": 0, "taxa": 833, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 771, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of plant proteins, most of which are hypothetical and of unknown function. All members contain the [pfam:PF00069] domain, suggesting that they may possess kinase activity.", "domain_architectures": 22, "interpro_id": "IPR010632", "known_evidence_count": null, "matches": 972, "name": "Protein of unknown function (DUF1221)", "partial_evidence_count": null, "pfam_id": "PF06760", "proteins": 961, "proteomes": 344, "short_name": "DUF1221", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06760", "structures": 2, "taxa": 928, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 408, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal globular domain of approximately 110 residues found in large integral membrane proteins from Actinomycetota, particularly Streptomycetaceae (Streptomyces and related genera). The parent proteins are approximately 500-700 residues in length with this domain positioned at the C-terminus. While the proteins are annotated as membrane transporters, the specific function of this C-terminal domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061884", "known_evidence_count": null, "matches": 966, "name": "Domain of unknown function (DUF8823)", "partial_evidence_count": null, "pfam_id": "PF31138", "proteins": 961, "proteomes": 793, "short_name": "DUF8823", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31138", "structures": 0, "taxa": 867, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 668, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 255 and 371 amino acids in length.", "domain_architectures": 16, "interpro_id": "IPR025536", "known_evidence_count": null, "matches": 967, "name": "Domain of unknown function (DUF4422)", "partial_evidence_count": null, "pfam_id": "PF14393", "proteins": 960, "proteomes": 774, "short_name": "DUF4422", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14393", "structures": 1, "taxa": 1505, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 354, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000663) is described by MIBiG as an example of the following biosynthetic class, terpene. It includes a member from the hopene biosynthetic gene cluster from Streptomyces coelicolor A3(2) and appears to be predominantly found in actinobacteria [[cite:PUB00098991],[cite:PUB00098992]].", "domain_architectures": 1, "interpro_id": "IPR046129", "known_evidence_count": null, "matches": 959, "name": "Family of unknown function (DUF6126)", "partial_evidence_count": null, "pfam_id": "PF19621", "proteins": 959, "proteomes": 734, "short_name": "DUF6126", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19621", "structures": 0, "taxa": 781, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 633, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of domains is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 48 and 68 amino acids in length. These domains contain four conserved cysteines suggesting that this domain is zinc binding", "domain_architectures": 16, "interpro_id": "IPR044044", "known_evidence_count": null, "matches": 958, "name": "Domain of unknown function (DUF5679)", "partial_evidence_count": null, "pfam_id": "PF18930", "proteins": 958, "proteomes": 854, "short_name": "DUF5679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18930", "structures": 0, "taxa": 1395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 584, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It shares detectable similarity to SpoIIAA-like domains.", "domain_architectures": 4, "interpro_id": "IPR056695", "known_evidence_count": null, "matches": 960, "name": "Domain of unknown function (DUF7793)", "partial_evidence_count": null, "pfam_id": "PF25056", "proteins": 958, "proteomes": 557, "short_name": "DUF7793", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25056", "structures": 1, "taxa": 857, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 592, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in Bacteroidetes.", "domain_architectures": 3, "interpro_id": "IPR043766", "known_evidence_count": null, "matches": 972, "name": "Family of unknown function (DUF5712)", "partial_evidence_count": null, "pfam_id": "PF18976", "proteins": 957, "proteomes": 538, "short_name": "DUF5712", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18976", "structures": 0, "taxa": 755, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 567, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 139 and 155 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045500", "known_evidence_count": null, "matches": 957, "name": "Family of unknown function (DUF6491)", "partial_evidence_count": null, "pfam_id": "PF20101", "proteins": 957, "proteomes": 713, "short_name": "DUF6491", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20101", "structures": 0, "taxa": 1045, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 850, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This short family is frequently found at the N-terminus of Homeobox proteins.", "domain_architectures": 15, "interpro_id": "IPR025228", "known_evidence_count": null, "matches": 962, "name": "Domain of unknown function (DUF4171)", "partial_evidence_count": null, "pfam_id": "PF13775", "proteins": 956, "proteomes": 691, "short_name": "DUF4171", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13775", "structures": 0, "taxa": 2099, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 638, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 210 and 241 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR045767", "known_evidence_count": null, "matches": 956, "name": "Domain of unknown function (DUF6134)", "partial_evidence_count": null, "pfam_id": "PF19630", "proteins": 956, "proteomes": 859, "short_name": "DUF6134", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19630", "structures": 0, "taxa": 1395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 496, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in various hypothetical bacterial proteins, and has no known function.", "domain_architectures": 2, "interpro_id": "IPR018718", "known_evidence_count": null, "matches": 954, "name": "Uncharacterized protein conserved in bacteria (DUF2242)", "partial_evidence_count": null, "pfam_id": "PF10001", "proteins": 953, "proteomes": 932, "short_name": "DUF2242", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10001", "structures": 0, "taxa": 1117, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 760, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in a group of uncharacterised proteins mainly from fungi. It is predicted to adopt a globular structure consisting of two alpha-helical repeats.", "domain_architectures": 21, "interpro_id": "IPR055499", "known_evidence_count": null, "matches": 957, "name": "Domain of unknown function (DUF7071)", "partial_evidence_count": null, "pfam_id": "PF23257", "proteins": 952, "proteomes": 820, "short_name": "DUF7071", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23257", "structures": 0, "taxa": 1597, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into an alpha-helical structure composed of three helices.", "domain_architectures": 21, "interpro_id": "IPR056026", "known_evidence_count": null, "matches": 953, "name": "Domain of unknown function (DUF7607)", "partial_evidence_count": null, "pfam_id": "PF24580", "proteins": 952, "proteomes": 910, "short_name": "DUF7607", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24580", "structures": 0, "taxa": 1842, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 751, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt an up-and-down four-helical bundle.", "domain_architectures": 34, "interpro_id": "IPR056686", "known_evidence_count": null, "matches": 955, "name": "Domain of unknown function (DUF7784)", "partial_evidence_count": null, "pfam_id": "PF25008", "proteins": 952, "proteomes": 908, "short_name": "DUF7784", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25008", "structures": 0, "taxa": 1794, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 811, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins from Fungi which may adopt a similar structure to the hyaluronidase post-catalytic domain, consisting of a five helical bundle with an up-and-down topology. In some members, this domain is duplicated, while other members are mono domain proteins.", "domain_architectures": 13, "interpro_id": "IPR061524", "known_evidence_count": null, "matches": 992, "name": "Domain of unknown function (DUF8454)", "partial_evidence_count": null, "pfam_id": "PF28751", "proteins": 952, "proteomes": 605, "short_name": "DUF8454", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28751", "structures": 0, "taxa": 1290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 828, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterized proteins. It is predicted to adopt a globular structure that resembles the conserved core of the PPPDE superfamily (after Permuted Papain fold Peptidases of DsRNA viruses and Eukaryotes) which consists of thiol peptidases with a circularly permuted papain-like fold. This domain is found either standalone or in combination with other domains.", "domain_architectures": 21, "interpro_id": "IPR056672", "known_evidence_count": null, "matches": 953, "name": "Domain of unknown function (DUF7770)", "partial_evidence_count": null, "pfam_id": "PF24968", "proteins": 949, "proteomes": 496, "short_name": "DUF7770", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24968", "structures": 0, "taxa": 1177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 811, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Eukaryotes.", "domain_architectures": 30, "interpro_id": "IPR041090", "known_evidence_count": null, "matches": 978, "name": "Family of unknown function (DUF5578)", "partial_evidence_count": null, "pfam_id": "PF17741", "proteins": 948, "proteomes": 704, "short_name": "DUF5578", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17741", "structures": 1, "taxa": 2374, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 564, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR021302", "known_evidence_count": null, "matches": 949, "name": "Protein of unknown function VcgC/VcgE (DUF2780)", "partial_evidence_count": null, "pfam_id": "PF11075", "proteins": 947, "proteomes": 906, "short_name": "DUF2780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11075", "structures": 0, "taxa": 1342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 581, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025321", "known_evidence_count": null, "matches": 947, "name": "Protein of unknown function (DUF4227)", "partial_evidence_count": null, "pfam_id": "PF14004", "proteins": 947, "proteomes": 945, "short_name": "DUF4227", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14004", "structures": 0, "taxa": 1155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 660, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in bacteria is functionally uncharacterised. Proteins in this family are typically between 298 and 349 amino acids in length. There is a conserved sequence pattern PxxxI/VxxGxxW.", "domain_architectures": 6, "interpro_id": "IPR046230", "known_evidence_count": null, "matches": 970, "name": "Family of unknown function (DUF6263)", "partial_evidence_count": null, "pfam_id": "PF19777", "proteins": 947, "proteomes": 834, "short_name": "DUF6263", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19777", "structures": 0, "taxa": 1330, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain is found towards the C terminus of human NEDD4 -binding protein 2 (N4BP2), which has 5'-polynucleotide kinase and nicking endonuclease activity and may play a role in DNA repair or recombination. This domain is predicted to adopt an alpha configuration. Its specific function is unknown. It is normally found N-terminal to [pfam:PF08590].", "domain_architectures": 41, "interpro_id": "IPR056718", "known_evidence_count": null, "matches": 948, "name": "Domain of unknown function (DUF7816)", "partial_evidence_count": null, "pfam_id": "PF25124", "proteins": 947, "proteomes": 678, "short_name": "DUF7816", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25124", "structures": 0, "taxa": 2199, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 797, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 87 and 100 amino acids in length. There is a conserved GPC sequence motif. There are two completely conserved C residues that may be functionally important.", "domain_architectures": 25, "interpro_id": "IPR031993", "known_evidence_count": null, "matches": 1370, "name": "Domain of unknown function (DUF4789)", "partial_evidence_count": null, "pfam_id": "PF16033", "proteins": 946, "proteomes": 258, "short_name": "DUF4789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16033", "structures": 0, "taxa": 971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 777, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 120 residues found in uncharacterized proteins in Ascomycota fungi, including Sordariomycetes (Fusarium, Nectriaceae), Eurotiomycetes (Aspergillus), and Dothideomycetes. The function of this domain is unknown.", "domain_architectures": 11, "interpro_id": "IPR061904", "known_evidence_count": null, "matches": 947, "name": "Domain of unknown function (DUF8843)", "partial_evidence_count": null, "pfam_id": "PF31246", "proteins": 946, "proteomes": 658, "short_name": "DUF8843", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31246", "structures": 0, "taxa": 1292, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 561, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, mainly in Proteobacteria. Proteins in this family are approximately 150 amino acids in length. There is a conserved motif NQ and a highly conserved Tryptophan residue.", "domain_architectures": 2, "interpro_id": "IPR046493", "known_evidence_count": null, "matches": 944, "name": "Family of unknown function (DUF6586)", "partial_evidence_count": null, "pfam_id": "PF20227", "proteins": 944, "proteomes": 941, "short_name": "DUF6586", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20227", "structures": 0, "taxa": 1156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 597, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in a fro up of fungal proteins. It is often N-terminal to several copies of ankyrin repeats. It is predicted to adopt an alpha-helical configuration.", "domain_architectures": 384, "interpro_id": "IPR055497", "known_evidence_count": null, "matches": 944, "name": "Domain of unknown function (DUF7069)", "partial_evidence_count": null, "pfam_id": "PF23239", "proteins": 944, "proteomes": 443, "short_name": "DUF7069", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23239", "structures": 0, "taxa": 896, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 784, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins.", "domain_architectures": 14, "interpro_id": "IPR061826", "known_evidence_count": null, "matches": 1022, "name": "Domain of unknown function (DUF8765)", "partial_evidence_count": null, "pfam_id": "PF30967", "proteins": 944, "proteomes": 869, "short_name": "DUF8765", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30967", "structures": 0, "taxa": 1757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 611, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins mainly from bacteria. These proteins are small in size and are predicted to adopt a single alpha-helix. One member, PA3496 from Pseudomonas aeruginosa, was shown to be upregulated in the presence of inulin or inulin-derived fructooligosaccharide.", "domain_architectures": 1, "interpro_id": "IPR058510", "known_evidence_count": null, "matches": 943, "name": "Family of unknown function (DUF8197)", "partial_evidence_count": null, "pfam_id": "PF26620", "proteins": 943, "proteomes": 898, "short_name": "DUF8197", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26620", "structures": 0, "taxa": 1101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 778, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharcaterised proteins mainly from fungi. It shares similarity to the C-terminal domain of Heparinase II/III.", "domain_architectures": 21, "interpro_id": "IPR061831", "known_evidence_count": null, "matches": 947, "name": "Domain of unknown function (DUF8770)", "partial_evidence_count": null, "pfam_id": "PF30972", "proteins": 943, "proteomes": 575, "short_name": "DUF8770", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30972", "structures": 0, "taxa": 1170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 572, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR019241", "known_evidence_count": null, "matches": 942, "name": "Uncharacterized protein conserved in bacteria (DUF2197)", "partial_evidence_count": null, "pfam_id": "PF09963", "proteins": 942, "proteomes": 889, "short_name": "DUF2197", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09963", "structures": 0, "taxa": 1202, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 595, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 770 to 1142 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR024282", "known_evidence_count": null, "matches": 951, "name": "Protein of unknown function (DUF3376)", "partial_evidence_count": null, "pfam_id": "PF11856", "proteins": 942, "proteomes": 911, "short_name": "DUF3376", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11856", "structures": 0, "taxa": 1332, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 724, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 10, "interpro_id": "IPR031885", "known_evidence_count": null, "matches": 1184, "name": "Domain of unknown function (DUF4764)", "partial_evidence_count": null, "pfam_id": "PF15961", "proteins": 942, "proteomes": 650, "short_name": "DUF4764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15961", "structures": 0, "taxa": 2345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 614, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 208 and 230 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045522", "known_evidence_count": null, "matches": 943, "name": "Family of unknown function (DUF6474)", "partial_evidence_count": null, "pfam_id": "PF20079", "proteins": 942, "proteomes": 938, "short_name": "DUF6474", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20079", "structures": 0, "taxa": 1125, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 593, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function mostly found in bacteria. According to structure predictions it might adopt a phospholipase D/nuclease fold. Whilst the typical phospholipase D motif HxK(x)4D(x)6GSxN is not strictly conserved the overall fold suggests a potential distant evolutionary relationship to the PLD superfamily. The PLD nucleases can have endonuclease or exonuclease activity. These enzymes use the imidazole group of histidine as a nucleophile in their catalytic mechanism [[cite:PUB00152066],[cite:PUB00160607],[cite:PUB00024729]].", "domain_architectures": 6, "interpro_id": "IPR057691", "known_evidence_count": null, "matches": 941, "name": "Domain of unknown function (DUF7931)", "partial_evidence_count": null, "pfam_id": "PF25559", "proteins": 941, "proteomes": 938, "short_name": "DUF7931", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25559", "structures": 0, "taxa": 1387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 528, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 230 amino acids in length. This domain is found associated with [pfam:PF02754].", "domain_architectures": 9, "interpro_id": "IPR021872", "known_evidence_count": null, "matches": 940, "name": "Domain of unknown function (DUF3483)", "partial_evidence_count": null, "pfam_id": "PF11982", "proteins": 939, "proteomes": 930, "short_name": "DUF3483", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11982", "structures": 0, "taxa": 1192, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 804, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Metazoa.", "domain_architectures": 14, "interpro_id": "IPR040247", "known_evidence_count": null, "matches": 952, "name": "Family of unknown function (DUF5524)", "partial_evidence_count": null, "pfam_id": "PF17662", "proteins": 939, "proteomes": 515, "short_name": "DUF5524", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17662", "structures": 0, "taxa": 1804, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 574, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins found mainly in metazoan lineages. They are predicted to contain two flttened beta-barrel-like domains that are arranged in a similar way as these observed in the members of the AttH-like superfamily.", "domain_architectures": 43, "interpro_id": "IPR061688", "known_evidence_count": null, "matches": 952, "name": "Family of unknown function (DUF8627)", "partial_evidence_count": null, "pfam_id": "PF30558", "proteins": 939, "proteomes": 339, "short_name": "DUF8627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30558", "structures": 0, "taxa": 1372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 782, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins.", "domain_architectures": 15, "interpro_id": "IPR061834", "known_evidence_count": null, "matches": 1019, "name": "Domain of unknown function (DUF8773)", "partial_evidence_count": null, "pfam_id": "PF30975", "proteins": 939, "proteomes": 921, "short_name": "DUF8773", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30975", "structures": 0, "taxa": 1863, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 512, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal proteins of unknown function.", "domain_architectures": 4, "interpro_id": "IPR010581", "known_evidence_count": null, "matches": 939, "name": "Protein of unknown function (DUF1152)", "partial_evidence_count": null, "pfam_id": "PF06626", "proteins": 938, "proteomes": 789, "short_name": "DUF1152", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06626", "structures": 0, "taxa": 1285, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 778, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in the Uncharacterized protein C582.04c from Schizosaccharomyces pombe and related proteins. It has detectable similarity to domains members of the CYTH-like phosphatase superfamily and it is predicted to adopt similar structure.", "domain_architectures": 19, "interpro_id": "IPR057227", "known_evidence_count": null, "matches": 954, "name": "Domain of unknown function (DUF7905)", "partial_evidence_count": null, "pfam_id": "PF25482", "proteins": 938, "proteomes": 702, "short_name": "DUF7905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25482", "structures": 0, "taxa": 1499, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 690, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 18, "interpro_id": "IPR021275", "known_evidence_count": null, "matches": 957, "name": "Protein of unknown function (DUF2854)", "partial_evidence_count": null, "pfam_id": "PF11016", "proteins": 937, "proteomes": 682, "short_name": "DUF2854", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11016", "structures": 0, "taxa": 1938, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 585, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. However, the cis-regulatory yjdF motif, just upstream from the gene encoding the proteins for this family, is a small non-coding RNA, Rfam:RF01764. The yjdF motif is found in many Firmicutes, including Bacillus subtilis. In most cases, it resides in potential 5' UTRs of homologues of the yjdF gene whose function is unknown. However, in Streptococcus thermophilus, a yjdF RNA motif is associated with an operon whose protein products synthesise nicotinamide adenine dinucleotide (NAD+). Also, the S. thermophilus yjdF RNA lacks typical yjdF motif consensus features downstream of and including the P4 stem. Thus, if yjdF RNAs are riboswitch aptamers, the S. thermophilus RNAs might sense a distinct compound that structurally resembles the ligand bound by other yjdF RNAs. On the ohter hand, perhaps these RNAs have an alternative solution forming a similar binding site, as is observed with some SAM riboswitches [[cite:PUB00109804]].", "domain_architectures": 4, "interpro_id": "IPR016787", "known_evidence_count": null, "matches": 937, "name": "Protein of unknown function (DUF2992)", "partial_evidence_count": null, "pfam_id": "PF11208", "proteins": 936, "proteomes": 873, "short_name": "DUF2992", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11208", "structures": 0, "taxa": 1561, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 678, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a family of membrane and transmembrane proteins from mycobacterial and related species. This domain has similarity to the ligand-binding domains of neurotransmitter ligand-gated ion channels and sensory receptors and it is likely to have similar function.", "domain_architectures": 11, "interpro_id": "IPR027948", "known_evidence_count": null, "matches": 936, "name": "Domain of unknown function (DUF4436)", "partial_evidence_count": null, "pfam_id": "PF14494", "proteins": 936, "proteomes": 500, "short_name": "DUF4436", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14494", "structures": 0, "taxa": 869, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 636, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 3, "interpro_id": "IPR021212", "known_evidence_count": null, "matches": 935, "name": "Domain of unknown function (DUF2760)", "partial_evidence_count": null, "pfam_id": "PF10816", "proteins": 935, "proteomes": 931, "short_name": "DUF2760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10816", "structures": 0, "taxa": 1433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 755, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised fungal proteins. This domain is often found associated with [pfam:PF15456] and is predicted to show a helical configuration.", "domain_architectures": 17, "interpro_id": "IPR056703", "known_evidence_count": null, "matches": 965, "name": "Domain of unknown function (DUF7801)", "partial_evidence_count": null, "pfam_id": "PF25078", "proteins": 935, "proteomes": 907, "short_name": "DUF7801", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25078", "structures": 0, "taxa": 1814, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 547, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus. Some members in this family of proteins are annotated as YobA however this cannot be confirmed. YobA is a protein with unknown function.", "domain_architectures": 16, "interpro_id": "IPR021598", "known_evidence_count": null, "matches": 936, "name": "Protein of unknown function (DUF3221)", "partial_evidence_count": null, "pfam_id": "PF11518", "proteins": 934, "proteomes": 660, "short_name": "DUF3221", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11518", "structures": 2, "taxa": 971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 598, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 50 amino acids in length. The family is found in association with [pfam:PF02502]. There are two completely conserved residues (D and F) that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR022133", "known_evidence_count": null, "matches": 934, "name": "Ribose-5-phosphate isomerase", "partial_evidence_count": null, "pfam_id": "PF12408", "proteins": 934, "proteomes": 901, "short_name": "DUF3666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12408", "structures": 5, "taxa": 1427, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 638, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of proteins that form an alpha-helical solenoid structure of HEAT-like repeats. Proteins in this family are found in various bacterial species, but most commonly in proteobacteria.", "domain_architectures": 7, "interpro_id": "IPR049245", "known_evidence_count": null, "matches": 1029, "name": "Family of unknown function (DUF6880)", "partial_evidence_count": null, "pfam_id": "PF21810", "proteins": 934, "proteomes": 822, "short_name": "DUF6880", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21810", "structures": 0, "taxa": 1580, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 807, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 19 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes. This domain is about 100 amino acids in length. This domain is found associated with [pfam:PF00096]. This domain has two conserved sequence motifs: YPSPV and PSP.", "domain_architectures": 24, "interpro_id": "IPR021839", "known_evidence_count": null, "matches": 935, "name": "Domain of unknown function (DUF3432)", "partial_evidence_count": null, "pfam_id": "PF11914", "proteins": 933, "proteomes": 684, "short_name": "DUF3432", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11914", "structures": 0, "taxa": 2412, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 602, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A large family of (predicted) secreted proteins with unknown functions from human gut and oral cavity. Typically forms a N-terminal domain with FMN binding domain at the C-terminus. Experimentaly determined 3D structure of this domain shows a variant of a TATA box binding - like fold, but no detectable sequence similarity to other proteins with this fold", "domain_architectures": 4, "interpro_id": "IPR027823", "known_evidence_count": null, "matches": 934, "name": "Domain of unknown function (DUF4468) with TBP-like fold", "partial_evidence_count": null, "pfam_id": "PF14730", "proteins": 933, "proteomes": 713, "short_name": "DUF4468", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14730", "structures": 2, "taxa": 1117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 600, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an Ig-like domain found in a family consists of uncharacterised proteins around 400 residues in length and is mainly found in various Bacteroides, Pedobacter and Parabacteroides species. This domain is generally found at the N-terminus of these proteins.", "domain_architectures": 6, "interpro_id": "IPR032527", "known_evidence_count": null, "matches": 933, "name": "Domain of unknown function (DUF4959)", "partial_evidence_count": null, "pfam_id": "PF16323", "proteins": 933, "proteomes": 372, "short_name": "DUF4959", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16323", "structures": 1, "taxa": 550, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 635, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]]. This is a C-terminal repeated region.", "domain_architectures": 15, "interpro_id": "IPR025222", "known_evidence_count": null, "matches": 1737, "name": "Protein of unknown function (DUF3945)", "partial_evidence_count": null, "pfam_id": "PF13101", "proteins": 932, "proteomes": 517, "short_name": "DUF3945", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13101", "structures": 0, "taxa": 807, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 531, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 270 residues in length and is mainly found in various Pseudomonas aeruginosa species. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR032608", "known_evidence_count": null, "matches": 943, "name": "Domain of unknown function (DUF4892)", "partial_evidence_count": null, "pfam_id": "PF16234", "proteins": 932, "proteomes": 909, "short_name": "DUF4892", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16234", "structures": 1, "taxa": 1311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 799, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal alpha helical domain found in proteins belonging to the DUF4518 family.", "domain_architectures": 19, "interpro_id": "IPR063725", "known_evidence_count": null, "matches": 935, "name": "DUF4518 family N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF29669", "proteins": 932, "proteomes": 680, "short_name": "DUF4518_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29669", "structures": 0, "taxa": 2497, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 529, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length. There is a conserved RCP sequence motif. These proteins are predicted to resemble zinc beta-ribbon domains.", "domain_architectures": 3, "interpro_id": "IPR045423", "known_evidence_count": null, "matches": 931, "name": "Family of unknown function (DUF6510)", "partial_evidence_count": null, "pfam_id": "PF20120", "proteins": 931, "proteomes": 853, "short_name": "DUF6510", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20120", "structures": 0, "taxa": 1139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 766, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an alpha helical domain from a family of uncharacterised proteins in the Stenosarchaea group. The proteins in this family are primarily found in archaea, particularly within the Halobacteriales and Methanobacteriota. The domain is approximately 180 amino acids in length. Proteins containing this domain are predicted to be integral membrane proteins, as suggested by the presence of multiple transmembrane helices.", "domain_architectures": 7, "interpro_id": "IPR058486", "known_evidence_count": null, "matches": 931, "name": "Domain of unknown function (DUF8173)", "partial_evidence_count": null, "pfam_id": "PF26514", "proteins": 931, "proteomes": 712, "short_name": "DUF8173", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26514", "structures": 0, "taxa": 1494, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 547, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Predicted ligand-binding domain of the PPC-like beta-sandwich fold. Observed in conserved gene neighbourhoods with diverse nucleotide-activated effector and related conflict systems, potentially recognises invasive molecules and initiates system responses or directly triggers directly-associated effector domains [[cite:PUB00097693]].", "domain_architectures": 4, "interpro_id": "IPR015073", "known_evidence_count": null, "matches": 930, "name": "Domain of unknown function (DUF1883)", "partial_evidence_count": null, "pfam_id": "PF08980", "proteins": 930, "proteomes": 889, "short_name": "DUF1883", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08980", "structures": 1, "taxa": 1349, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 485, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a set of at least 17 paralogous proteins in Myxococcus xanthus DK 1622 and and 12 in Stigmatella aurantiaca DW4/3-1. Members are about 200 amino acids in length. The function is unknown.", "domain_architectures": 3, "interpro_id": "IPR011751", "known_evidence_count": null, "matches": 930, "name": "Protein of unknown function (DUF2378)", "partial_evidence_count": null, "pfam_id": "PF09536", "proteins": 930, "proteomes": 54, "short_name": "DUF2378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09536", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 555, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 100 and 157 amino acids in length. This entry represents a likely zinc-binding domain.", "domain_architectures": 17, "interpro_id": "IPR022236", "known_evidence_count": null, "matches": 940, "name": "Domain of unknown function (DUF3761)", "partial_evidence_count": null, "pfam_id": "PF12587", "proteins": 930, "proteomes": 822, "short_name": "DUF3761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12587", "structures": 0, "taxa": 1315, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 563, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 130 and 183 amino acids in length. There is a single completely conserved residue E that may be functionally important.", "domain_architectures": 11, "interpro_id": "IPR025091", "known_evidence_count": null, "matches": 932, "name": "Protein of unknown function (DUF4019)", "partial_evidence_count": null, "pfam_id": "PF13211", "proteins": 930, "proteomes": 840, "short_name": "DUF4019", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13211", "structures": 0, "taxa": 1329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 622, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 154 and 172 amino acids in length. There are two conserved sequence motifs: VDA and EAE. This entry contains two domains which share a similar topology. AlphaFold3 prediction suggests this family may form a DNA-binding homotetrameric complex.", "domain_architectures": 3, "interpro_id": "IPR027848", "known_evidence_count": null, "matches": 929, "name": "Domain of unknown function (DUF4494)", "partial_evidence_count": null, "pfam_id": "PF14902", "proteins": 929, "proteomes": 839, "short_name": "DUF4494", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14902", "structures": 0, "taxa": 1217, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 614, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family may be involved in nitrogen fixation, since they are found within nitrogen fixation operons.", "domain_architectures": 3, "interpro_id": "IPR004952", "known_evidence_count": null, "matches": 929, "name": "Protein of unknown function, DUF269", "partial_evidence_count": null, "pfam_id": "PF03270", "proteins": 928, "proteomes": 833, "short_name": "DUF269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03270", "structures": 2, "taxa": 1555, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 764, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a fungal family of unknown function.", "domain_architectures": 18, "interpro_id": "IPR013920", "known_evidence_count": null, "matches": 931, "name": "Fungal protein of unknown function (DUF1774)", "partial_evidence_count": null, "pfam_id": "PF08611", "proteins": 928, "proteomes": 888, "short_name": "DUF1774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08611", "structures": 0, "taxa": 1761, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 582, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 153 and 170 amino acids in length. There is a single completely conserved residue D that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR016541", "known_evidence_count": null, "matches": 928, "name": "Domain of unknown function (DUF4411)", "partial_evidence_count": null, "pfam_id": "PF14367", "proteins": 928, "proteomes": 878, "short_name": "DUF4411", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14367", "structures": 0, "taxa": 1976, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 826, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in plant sequences. It may consist in a tri-helical fold.", "domain_architectures": 32, "interpro_id": "IPR056671", "known_evidence_count": null, "matches": 930, "name": "Domain of unknown function (DUF7769)", "partial_evidence_count": null, "pfam_id": "PF24964", "proteins": 928, "proteomes": 141, "short_name": "DUF7769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24964", "structures": 0, "taxa": 507, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 774, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha/beta structure composed of a four-stranded antiparallel beta-sheet packed on both sides with alpha-helices. It also contains a long alpha-hairpin, stabilised by conserved interactions, which is inserted after the first strand and may be functionally important. In addition, it contains a highly conserved KTGYx(5-6)[FW]DLD sequence motif which may constitute a part of a binding interface.", "domain_architectures": 10, "interpro_id": "IPR059413", "known_evidence_count": null, "matches": 932, "name": "Domain of unknown function (DUF8369)", "partial_evidence_count": null, "pfam_id": "PF28122", "proteins": 928, "proteomes": 893, "short_name": "DUF8369", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28122", "structures": 0, "taxa": 1779, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 544, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. Most members belong to Proteobacteria.", "domain_architectures": 32, "interpro_id": "IPR021381", "known_evidence_count": null, "matches": 1081, "name": "Protein of unknown function (DUF3011)", "partial_evidence_count": null, "pfam_id": "PF11218", "proteins": 927, "proteomes": 478, "short_name": "DUF3011", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11218", "structures": 0, "taxa": 956, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 646, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 2, "interpro_id": "IPR011088", "known_evidence_count": null, "matches": 926, "name": "Protein of unknown function (DUF1523)", "partial_evidence_count": null, "pfam_id": "PF07509", "proteins": 926, "proteomes": 895, "short_name": "DUF1523", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07509", "structures": 0, "taxa": 1377, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 546, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021378", "known_evidence_count": null, "matches": 926, "name": "Protein of unknown function (DUF3010)", "partial_evidence_count": null, "pfam_id": "PF11215", "proteins": 926, "proteomes": 892, "short_name": "DUF3010", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11215", "structures": 0, "taxa": 1230, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 747, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised sequences from plants.", "domain_architectures": 13, "interpro_id": "IPR056059", "known_evidence_count": null, "matches": 940, "name": "Domain of unknown function (DUF7642)", "partial_evidence_count": null, "pfam_id": "PF24649", "proteins": 926, "proteomes": 317, "short_name": "DUF7642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24649", "structures": 0, "taxa": 880, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 696, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 99 and 171 amino acids in length. This protein is likely to be zinc binding given the conserved cysteines.", "domain_architectures": 22, "interpro_id": "IPR024227", "known_evidence_count": null, "matches": 926, "name": "Protein of unknown function (DUF3795)", "partial_evidence_count": null, "pfam_id": "PF12675", "proteins": 925, "proteomes": 554, "short_name": "DUF3795", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12675", "structures": 0, "taxa": 1228, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 608, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised, but is is found in O-antigen polymerase proteins. This domain family is mainly found in proteobacteria, and is approximately 190 amino acids in length. The family is found in association with [pfam:PF04932].", "domain_architectures": 2, "interpro_id": "IPR045979", "known_evidence_count": null, "matches": 925, "name": "Family of unknown function (DUF5935)", "partial_evidence_count": null, "pfam_id": "PF19358", "proteins": 925, "proteomes": 909, "short_name": "DUF5935", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19358", "structures": 0, "taxa": 1426, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 790, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This archaebacterial domain has no known function. It is attached to an endonuclease domain in [swissprot:Q58030]. The domain contains several conserved cysteines and histidines. This suggests that the domain may be a zinc binding nucleic acid interaction domain (Bateman A unpubl.).", "domain_architectures": 10, "interpro_id": "IPR002837", "known_evidence_count": null, "matches": 931, "name": "Domain of unknown function DUF123", "partial_evidence_count": null, "pfam_id": "PF01986", "proteins": 924, "proteomes": 912, "short_name": "DUF123", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01986", "structures": 0, "taxa": 1943, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 769, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a novel family of non-canonical E2 ubiquitin-conjugating enzymes that lack the typical HPN motif found in other E2 enzymes. The domain contains a highly conserved catalytic cysteine (C572 in PF3D7_0811400) that forms a thioester bond with ubiquitin. This was experimentally validated through mutational analysis and biochemical assays [[cite:PUB00160741]]. The domain is found in the C-terminal region of proteins, while the N-terminal region contains coiled helices involved in protein-protein interactions with other ubiquitin pathway components like Rbx1. The domain represents a new class of E2 enzymes particularly found in Apicomplexan parasites.", "domain_architectures": 37, "interpro_id": "IPR057668", "known_evidence_count": null, "matches": 1077, "name": "Non-canonical E2 ubiquitin-conjugating enzyme, DUF2009 family", "partial_evidence_count": null, "pfam_id": "PF09418", "proteins": 924, "proteomes": 659, "short_name": "DUF2009", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09418", "structures": 0, "taxa": 1643, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 609, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 6, "interpro_id": "IPR021698", "known_evidence_count": null, "matches": 948, "name": "Protein of unknown function (DUF2380)", "partial_evidence_count": null, "pfam_id": "PF11684", "proteins": 924, "proteomes": 650, "short_name": "DUF3280", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11684", "structures": 0, "taxa": 963, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 642, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 130 amino acids in length. This protein has two conserved sequence motifs: KFK and HLE.", "domain_architectures": 2, "interpro_id": "IPR020911", "known_evidence_count": null, "matches": 926, "name": "Protein of unknown function (DUF3461)", "partial_evidence_count": null, "pfam_id": "PF11944", "proteins": 924, "proteomes": 844, "short_name": "DUF3461", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11944", "structures": 0, "taxa": 1256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 599, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR020378", "known_evidence_count": null, "matches": 924, "name": "Domain of unknown function (DUF4186)", "partial_evidence_count": null, "pfam_id": "PF13811", "proteins": 924, "proteomes": 912, "short_name": "DUF4186", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13811", "structures": 0, "taxa": 1534, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 557, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. It is found to the C-terminus of a helix-turn-helix domain which strongly suggests that it is a transcriptional regulatory protein. These domains associated with HTH domains often bind to a ligand. This domain family is found in firmicutes, and is approximately 150 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR046059", "known_evidence_count": null, "matches": 924, "name": "Family of unknown function (DUF6017)", "partial_evidence_count": null, "pfam_id": "PF19481", "proteins": 924, "proteomes": 387, "short_name": "DUF6017", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19481", "structures": 0, "taxa": 711, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 870, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are about 350-400 amino acids in length. These proteins form a large all alpha helical fold. These proteins may be integral membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR058278", "known_evidence_count": null, "matches": 924, "name": "Family of unknown function (DUF7972)", "partial_evidence_count": null, "pfam_id": "PF25927", "proteins": 923, "proteomes": 264, "short_name": "DUF7972", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25927", "structures": 0, "taxa": 416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 871, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised protein domains found in archaea. Proteins in this family are typically between 210 and 252 amino acids in length. These proteins contain an N-terminal TAT signal. This domain belongs to the Mog1p/PsbP superfamily.", "domain_architectures": 2, "interpro_id": "IPR045396", "known_evidence_count": null, "matches": 926, "name": "Domain of unknown function (DUF6517)", "partial_evidence_count": null, "pfam_id": "PF20127", "proteins": 922, "proteomes": 291, "short_name": "DUF6517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20127", "structures": 0, "taxa": 455, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 602, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane bacterial proteins of approximately 125 residues. These proteins contain five potential transmembrane helices. AlphaFold3 prediction suggests these proteins form a homotrimeric arrangement ([swissprot:A9WFT2] ipTM = 0.86 pTM = 0.87). The protein has a small variable C-terminal tail that is likely to be intracellular.", "domain_architectures": 2, "interpro_id": "IPR061798", "known_evidence_count": null, "matches": 921, "name": "Domain of unknown function (DUF8737)", "partial_evidence_count": null, "pfam_id": "PF30786", "proteins": 921, "proteomes": 819, "short_name": "DUF8737", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30786", "structures": 0, "taxa": 1415, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 799, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are around 350 amino acids in length. They are found in archaebacteria and have no known function.", "domain_architectures": 3, "interpro_id": "IPR007152", "known_evidence_count": null, "matches": 920, "name": "Protein of unknown function (DUF354)", "partial_evidence_count": null, "pfam_id": "PF04007", "proteins": 920, "proteomes": 661, "short_name": "DUF354", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04007", "structures": 0, "taxa": 1392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 752, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found at the C terminal of a family of ER membrane bound transcription factors called sterol regulatory element binding proteins (SREBP).", "domain_architectures": 11, "interpro_id": "IPR019006", "known_evidence_count": null, "matches": 936, "name": "Domain of unknown function (DUF2014)", "partial_evidence_count": null, "pfam_id": "PF09427", "proteins": 920, "proteomes": 882, "short_name": "DUF2014", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09427", "structures": 2, "taxa": 1757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 780, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 66 and 78 amino acids in length. There are two conserved sequence motifs: FCK and RTL.", "domain_architectures": 9, "interpro_id": "IPR029367", "known_evidence_count": null, "matches": 920, "name": "Domain of unknown function (DUF4560)", "partial_evidence_count": null, "pfam_id": "PF15118", "proteins": 920, "proteomes": 517, "short_name": "DUF4560", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15118", "structures": 0, "taxa": 1736, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 678, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found towards the N-terminal of fungal proteins. This domain adopts a beta-propeller like fold and may be found in association with an N-terminal F-box motif.", "domain_architectures": 30, "interpro_id": "IPR055589", "known_evidence_count": null, "matches": 1000, "name": "Domain of unknown function (DUF7165)", "partial_evidence_count": null, "pfam_id": "PF23749", "proteins": 920, "proteomes": 895, "short_name": "DUF7165", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23749", "structures": 0, "taxa": 1852, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 584, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is found in bacteria. Proteins in this family are about 140 amino acids in length. This protein has two conserved sequence motifs: AAR and DDLP.", "domain_architectures": 2, "interpro_id": "IPR022064", "known_evidence_count": null, "matches": 919, "name": "Protein of unknown function (DUF3619)", "partial_evidence_count": null, "pfam_id": "PF12279", "proteins": 919, "proteomes": 917, "short_name": "DUF3619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12279", "structures": 0, "taxa": 1221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 760, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 351 and 686 amino acids in length. There is a conserved RRY sequence motif.", "domain_architectures": 26, "interpro_id": "IPR032062", "known_evidence_count": null, "matches": 1002, "name": "Domain of unknown function (DUF4803)", "partial_evidence_count": null, "pfam_id": "PF16061", "proteins": 919, "proteomes": 251, "short_name": "DUF4803", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16061", "structures": 0, "taxa": 987, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 762, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from fungi. It contains three pairs of conserved cysteine residues that are predicted to form disulfide bonds. It also contains a long region that is predicted to be disordered.", "domain_architectures": 8, "interpro_id": "IPR056722", "known_evidence_count": null, "matches": 982, "name": "Domain of unknown function (DUF7820)", "partial_evidence_count": null, "pfam_id": "PF25130", "proteins": 918, "proteomes": 830, "short_name": "DUF7820", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25130", "structures": 0, "taxa": 1617, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 579, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 100 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009190", "known_evidence_count": null, "matches": 917, "name": "Protein of unknown function (DUF1462)", "partial_evidence_count": null, "pfam_id": "PF07315", "proteins": 917, "proteomes": 915, "short_name": "DUF1462", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07315", "structures": 1, "taxa": 1192, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 589, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 200 residues locates in the N-terminal of some uncharacterized proteins in various Bacteroides and Parabacteroides species. The function of this family remains unknown.", "domain_architectures": 23, "interpro_id": "", "known_evidence_count": null, "matches": 917, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16389", "proteins": 917, "proteomes": 358, "short_name": "DUF4998", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16389", "structures": 0, "taxa": 531, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 575, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. There are two conserved sequence motifs, WIF and YW. Probably, they are Uracil phosphoribosyltransferases.", "domain_architectures": 1, "interpro_id": "IPR045922", "known_evidence_count": null, "matches": 917, "name": "Family of unknown function (DUF6341)", "partial_evidence_count": null, "pfam_id": "PF19868", "proteins": 917, "proteomes": 915, "short_name": "DUF6341", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19868", "structures": 0, "taxa": 1100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 531, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain if found in a group of uncharacterised bacterial proteins. It is related to NlpC/P60 domains and it is likely to adopt similar structure as well as to possess an endopeptidase activity. All members of this family contain a conserved cysteine residue that is predicted to occupy equivalent spatial position as in the NlpC/P60 domains.", "domain_architectures": 2, "interpro_id": "IPR053802", "known_evidence_count": null, "matches": 957, "name": "Domain of unknown function (DUF6950)", "partial_evidence_count": null, "pfam_id": "PF22262", "proteins": 917, "proteomes": 718, "short_name": "DUF6950", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22262", "structures": 0, "taxa": 1305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 459, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is primarily found in bacteria. This entry may represent an Ig-like fold.", "domain_architectures": 135, "interpro_id": "IPR045939", "known_evidence_count": null, "matches": 986, "name": "Domain of unknown function (DUF6359)", "partial_evidence_count": null, "pfam_id": "PF19886", "proteins": 916, "proteomes": 832, "short_name": "DUF6359", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19886", "structures": 0, "taxa": 1196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 808, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 95 and 154 amino acids in length. This family includes Human C15orf61.", "domain_architectures": 21, "interpro_id": "IPR029245", "known_evidence_count": null, "matches": 927, "name": "Domain of unknown function (DUF4528)", "partial_evidence_count": null, "pfam_id": "PF15031", "proteins": 915, "proteomes": 771, "short_name": "DUF4528", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15031", "structures": 0, "taxa": 2791, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 548, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This immunoglobulin-like (Ig-like) domain is found in a group of uncharacterised proteobacterial proteins. It is often found associated with [pfam:PF13899], [pfam:PF02683] and [pfam:PF11412] and has conserved P, L, F and D residues. Its function is unknown.", "domain_architectures": 9, "interpro_id": "IPR059437", "known_evidence_count": null, "matches": 915, "name": "Domain of unknown function (DUF8393)", "partial_evidence_count": null, "pfam_id": "PF28432", "proteins": 915, "proteomes": 871, "short_name": "DUF8393", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28432", "structures": 1, "taxa": 1336, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 576, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of short uncharacterised proteins predominantly found in bacteria. This model matches four of the twelve transmembrane helices of cytochrome c and quinol oxidase subunit I ([pfam:PF00115]) and contains the HxH motif conserved in both. A DALI search suggests that this family may be related to Cox1, however, there is no evidence for the involvement of this family in any Cox1-like assembly. AlphaFold prediction suggests that these proteins contain four transmembrane alpha helices which can for a homotrimeric complex.", "domain_architectures": 2, "interpro_id": "IPR021299", "known_evidence_count": null, "matches": 914, "name": "Protein of unknown function (DUF2871)", "partial_evidence_count": null, "pfam_id": "PF11070", "proteins": 914, "proteomes": 859, "short_name": "DUF2871", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11070", "structures": 0, "taxa": 1357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to adopt a globular structure consisting of array of helices.", "domain_architectures": 64, "interpro_id": "IPR056064", "known_evidence_count": null, "matches": 924, "name": "Domain of unknown function (DUF7647)", "partial_evidence_count": null, "pfam_id": "PF24658", "proteins": 914, "proteomes": 392, "short_name": "DUF7647", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24658", "structures": 0, "taxa": 1130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 541, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 717 and 769 amino acids in length. This family appears to be related to [pfam:PF07519].", "domain_architectures": 10, "interpro_id": "IPR045556", "known_evidence_count": null, "matches": 920, "name": "Tannase-like family of unknown function (DUF6351)", "partial_evidence_count": null, "pfam_id": "PF19878", "proteins": 913, "proteomes": 746, "short_name": "DUF6351", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19878", "structures": 0, "taxa": 1162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 830, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a helical domain found in a group of uncharacterised sequences from bacteria and archaea. It is usually found in association with [pfam:PF07760].", "domain_architectures": 11, "interpro_id": "IPR061541", "known_evidence_count": null, "matches": 922, "name": "Domain of unknown function (DUF8471)", "partial_evidence_count": null, "pfam_id": "PF28863", "proteins": 913, "proteomes": 471, "short_name": "DUF8471", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28863", "structures": 0, "taxa": 902, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It shares similarity to RasGAP domains.", "domain_architectures": 15, "interpro_id": "IPR061824", "known_evidence_count": null, "matches": 943, "name": "Domain of unknown function (DUF8763)", "partial_evidence_count": null, "pfam_id": "PF30930", "proteins": 913, "proteomes": 877, "short_name": "DUF8763", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30930", "structures": 0, "taxa": 1762, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 629, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a functionally uncharacterised family of integral membrane proteins. This protein family is found in bacteria, and is approximately 60 amino acids in length. There are several conserved glycines in the first transmembrane helix that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR043723", "known_evidence_count": null, "matches": 912, "name": "Domain of unknown function (DUF5665)", "partial_evidence_count": null, "pfam_id": "PF18910", "proteins": 912, "proteomes": 787, "short_name": "DUF5665", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18910", "structures": 0, "taxa": 1313, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 758, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It contains a set of conserved cysteine residues which are predicted to form a disulfide bond.", "domain_architectures": 8, "interpro_id": "IPR056634", "known_evidence_count": null, "matches": 971, "name": "Domain of unknown function (DUF7732)", "partial_evidence_count": null, "pfam_id": "PF24866", "proteins": 912, "proteomes": 846, "short_name": "DUF7732", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24866", "structures": 0, "taxa": 1653, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 702, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised fungal sequences which have a similar structure to KH domains, according to structure predictions.", "domain_architectures": 271, "interpro_id": "IPR061519", "known_evidence_count": null, "matches": 919, "name": "Domain of unknown function (DUF8449)", "partial_evidence_count": null, "pfam_id": "PF28723", "proteins": 912, "proteomes": 486, "short_name": "DUF8449", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28723", "structures": 0, "taxa": 1138, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 671, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 190 amino acids in length. There are two completely conserved residues (L and D) that may be functionally important.", "domain_architectures": 17, "interpro_id": "IPR022552", "known_evidence_count": null, "matches": 1357, "name": "Protein of unknown function (DUF3685)", "partial_evidence_count": null, "pfam_id": "PF12452", "proteins": 911, "proteomes": 603, "short_name": "DUF3685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12452", "structures": 0, "taxa": 1687, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 718, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal proteins of unknown function.", "domain_architectures": 7, "interpro_id": "IPR008508", "known_evidence_count": null, "matches": 951, "name": "Protein of unknown function (DUF790)", "partial_evidence_count": null, "pfam_id": "PF05626", "proteins": 910, "proteomes": 794, "short_name": "DUF790", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05626", "structures": 5, "taxa": 1699, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 591, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021375", "known_evidence_count": null, "matches": 910, "name": "Protein of unknown function (DUF2997)", "partial_evidence_count": null, "pfam_id": "PF11211", "proteins": 910, "proteomes": 654, "short_name": "DUF2997", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11211", "structures": 0, "taxa": 1591, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 633, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021471", "known_evidence_count": null, "matches": 910, "name": "Protein of unknown function (DUF3124)", "partial_evidence_count": null, "pfam_id": "PF11322", "proteins": 910, "proteomes": 844, "short_name": "DUF3124", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11322", "structures": 0, "taxa": 1587, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This protein region family is found in fungi, and is typically between 384 and 430 amino acids in length. These proteins are largely disordered with small regions of high conservation that are likely acting as short linear motifs. Some members of this family contain gelsolin domains at the C-terminus.", "domain_architectures": 23, "interpro_id": "IPR025118", "known_evidence_count": null, "matches": 984, "name": "Family of unknown function (DUF4045)", "partial_evidence_count": null, "pfam_id": "PF13254", "proteins": 910, "proteomes": 864, "short_name": "DUF4045", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13254", "structures": 0, "taxa": 1730, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 759, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This fungal family has no known function. However, it is rich in paired, as CXXC, cysteines and histidines, but these do not fall in the conformation that might suggest zinc-binding.", "domain_architectures": 4, "interpro_id": "IPR027915", "known_evidence_count": null, "matches": 916, "name": "Domain of unknown function (DUF4452)", "partial_evidence_count": null, "pfam_id": "PF14618", "proteins": 910, "proteomes": 884, "short_name": "DUF4452", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14618", "structures": 0, "taxa": 1771, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 841, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 7, "interpro_id": "IPR041056", "known_evidence_count": null, "matches": 943, "name": "Family of unknown function (DUF5585)", "partial_evidence_count": null, "pfam_id": "PF17823", "proteins": 910, "proteomes": 679, "short_name": "DUF5585", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17823", "structures": 0, "taxa": 2154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 585, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is mainly found in bacteria, and is approximately 100 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046706", "known_evidence_count": null, "matches": 910, "name": "Domain of unknown function (DUF6779)", "partial_evidence_count": null, "pfam_id": "PF20570", "proteins": 910, "proteomes": 908, "short_name": "DUF6779", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20570", "structures": 0, "taxa": 1114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are approximately 50 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046134", "known_evidence_count": null, "matches": 909, "name": "Family of unknown function (DUF6131)", "partial_evidence_count": null, "pfam_id": "PF19626", "proteins": 909, "proteomes": 707, "short_name": "DUF6131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19626", "structures": 0, "taxa": 872, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 869, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a group of uncharacterised proteins from Archaea. This domain adopts alpha/beta fold consisting of a central five-stranded beta-sheet enveloped by four alpha-helices, similar to that found in profilin.", "domain_architectures": 5, "interpro_id": "IPR055944", "known_evidence_count": null, "matches": 909, "name": "Domain of unknown function (DUF7522)", "partial_evidence_count": null, "pfam_id": "PF24366", "proteins": 909, "proteomes": 270, "short_name": "DUF7522", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24366", "structures": 0, "taxa": 429, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 731, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into an open barrel-like structure. It contains two pair of conserved cysteine residues which are predicted to form disulfide bonds. It may be involve in oligomerisation given the number of conserved exposed hydrophobic residues.", "domain_architectures": 20, "interpro_id": "IPR058517", "known_evidence_count": null, "matches": 924, "name": "Domain of unknown function (DUF8204)", "partial_evidence_count": null, "pfam_id": "PF26631", "proteins": 908, "proteomes": 391, "short_name": "DUF8204", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26631", "structures": 0, "taxa": 1086, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 640, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 153 and 460 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046158", "known_evidence_count": null, "matches": 909, "name": "Family of unknown function (DUF6160)", "partial_evidence_count": null, "pfam_id": "PF19657", "proteins": 906, "proteomes": 275, "short_name": "DUF6160", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19657", "structures": 1, "taxa": 416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 372, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 110 residues found in small uncharacterized proteins in Streptomyces and related Actinomycetes. These proteins typically consist of this single domain only. The function of this domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061890", "known_evidence_count": null, "matches": 906, "name": "Domain of unknown function (DUF8829)", "partial_evidence_count": null, "pfam_id": "PF31166", "proteins": 906, "proteomes": 840, "short_name": "DUF8829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31166", "structures": 0, "taxa": 937, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 516, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and viruses, and is approximately 70 amino acids in length. There is a single completely conserved residue C that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR022193", "known_evidence_count": null, "matches": 905, "name": "Protein of unknown function (DUF3718)", "partial_evidence_count": null, "pfam_id": "PF12514", "proteins": 905, "proteomes": 348, "short_name": "DUF3718", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12514", "structures": 0, "taxa": 466, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 547, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 340 amino acids in length. This protein has a conserved LDE sequence motif.", "domain_architectures": 2, "interpro_id": "IPR021936", "known_evidence_count": null, "matches": 905, "name": "Protein of unknown function (DUF3549)", "partial_evidence_count": null, "pfam_id": "PF12069", "proteins": 904, "proteomes": 897, "short_name": "DUF3549", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12069", "structures": 0, "taxa": 1152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain is found towards the C terminus of human NEDD4 -binding protein 2 (N4BP2), which has 5'-polynucleotide kinase and nicking endonuclease activity and may play a role in DNA repair or recombination. This domain is often found N-terminal to [pfam:PF25124] and [pfam:PF08590].", "domain_architectures": 25, "interpro_id": "IPR056719", "known_evidence_count": null, "matches": 904, "name": "Domain of unknown function (DUF7817)", "partial_evidence_count": null, "pfam_id": "PF25125", "proteins": 904, "proteomes": 637, "short_name": "DUF7817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25125", "structures": 0, "taxa": 1971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 654, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This uncharacterised domain is found at the C-terminal in Uncharacterized protein MG366, Uncharacterized protein UU173 and related bacteria. UU173 is encoded next to an element that encodes UU172 [Swissprot:Q9PQX1], a phase-variable surface membrane protein paralogous to multiple-banded antigen (MBA) [[cite:PUB00159629]].", "domain_architectures": 10, "interpro_id": "IPR021301", "known_evidence_count": null, "matches": 904, "name": "Domain of unknown function (DUF2779)", "partial_evidence_count": null, "pfam_id": "PF11074", "proteins": 903, "proteomes": 847, "short_name": "DUF2779", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11074", "structures": 0, "taxa": 1818, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 107, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Fungi. It shares a weak sequence similarity to the C-terminal domain of the Escherichia Coli ProQ RNA binding protein ([pfam:PF17516]) and it is predicted to adopt a similar structure with SH3-like topology.", "domain_architectures": 14, "interpro_id": "IPR055500", "known_evidence_count": null, "matches": 903, "name": "Domain of unknown function (DUF7072)", "partial_evidence_count": null, "pfam_id": "PF23258", "proteins": 903, "proteomes": 875, "short_name": "DUF7072", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23258", "structures": 0, "taxa": 1757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 722, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised fungal sequences that also contain [pfam:PF00069]. It has a conserved I/LWG motif.", "domain_architectures": 13, "interpro_id": "IPR057213", "known_evidence_count": null, "matches": 903, "name": "Domain of unknown function (DUF7891)", "partial_evidence_count": null, "pfam_id": "PF25421", "proteins": 903, "proteomes": 868, "short_name": "DUF7891", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25421", "structures": 0, "taxa": 1703, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 705, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins and predominantly in fungi. It contains highly conserved cysteine and histidine residues which are likely to coordinate a metal ion. These residues are predicted to come close in space and assemble in a shape typical for CCHC zinc finger domains. This domain is likely to contain two of these domains.", "domain_architectures": 30, "interpro_id": "IPR059407", "known_evidence_count": null, "matches": 903, "name": "Domain of unknown function (DUF8363)", "partial_evidence_count": null, "pfam_id": "PF27939", "proteins": 903, "proteomes": 347, "short_name": "DUF8363", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27939", "structures": 0, "taxa": 904, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Several members are annotated as being LysM domain-like proteins, but these did not match any LysM domains reported in the literature.", "domain_architectures": 3, "interpro_id": "IPR021734", "known_evidence_count": null, "matches": 902, "name": "Domain of unknown function (DUF3303)", "partial_evidence_count": null, "pfam_id": "PF11746", "proteins": 902, "proteomes": 742, "short_name": "DUF3303", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11746", "structures": 0, "taxa": 1374, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It contains two pairs of conserved cysteine residues that are probably involves in metal coordination.", "domain_architectures": 43, "interpro_id": "IPR061761", "known_evidence_count": null, "matches": 903, "name": "Domain of unknown function (DUF8700)", "partial_evidence_count": null, "pfam_id": "PF30714", "proteins": 902, "proteomes": 102, "short_name": "DUF8700", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30714", "structures": 0, "taxa": 564, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 536, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in Bacilli. Family members of this family are predicted to have trans-membrane domains.", "domain_architectures": 1, "interpro_id": "IPR035211", "known_evidence_count": null, "matches": 900, "name": "Family of unknown function (DUF5325)", "partial_evidence_count": null, "pfam_id": "PF17259", "proteins": 900, "proteomes": 898, "short_name": "DUF5325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17259", "structures": 0, "taxa": 1130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 533, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in proteobacteria and sporadically in archaea, and is approximately 100 amino acids in length. There are two conserved sequence motifs: NNH and RLS. This domain is often found to the N-terminus of [pfam:PF02830].", "domain_architectures": 2, "interpro_id": "IPR045987", "known_evidence_count": null, "matches": 900, "name": "Domain of unknown function (DUF5943)", "partial_evidence_count": null, "pfam_id": "PF19367", "proteins": 900, "proteomes": 875, "short_name": "DUF5943", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19367", "structures": 0, "taxa": 1119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 650, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It contains a number of highly conserved cysteine and histidine residues that may be involved in metal coordination. Some proteins contain two copies of this domain. It probably adopt a novel fold judging by its predicted structure.", "domain_architectures": 51, "interpro_id": "IPR058519", "known_evidence_count": null, "matches": 911, "name": "Domain of unknown function (DUF8206)", "partial_evidence_count": null, "pfam_id": "PF26633", "proteins": 900, "proteomes": 362, "short_name": "DUF8206", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26633", "structures": 0, "taxa": 1018, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 516, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 26, "interpro_id": "IPR014903", "known_evidence_count": null, "matches": 918, "name": "Putative papain-like cysteine peptidase (DUF1796)", "partial_evidence_count": null, "pfam_id": "PF08795", "proteins": 899, "proteomes": 546, "short_name": "DUF1796", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08795", "structures": 0, "taxa": 1112, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 744, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical short plant proteins from Arabidopsis thaliana and Oryza sativa. The function of this family is unknown.", "domain_architectures": 22, "interpro_id": "IPR009515", "known_evidence_count": null, "matches": 905, "name": "Protein of unknown function (DUF1138)", "partial_evidence_count": null, "pfam_id": "PF06592", "proteins": 898, "proteomes": 362, "short_name": "DUF1138", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06592", "structures": 2, "taxa": 1039, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 540, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. Some members are annotated as YfeZ however this cannot be confirmed.", "domain_architectures": 3, "interpro_id": "IPR021318", "known_evidence_count": null, "matches": 898, "name": "Protein of unknown function (DUF2919)", "partial_evidence_count": null, "pfam_id": "PF11143", "proteins": 898, "proteomes": 887, "short_name": "DUF2919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11143", "structures": 0, "taxa": 1164, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 758, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal beta sheet domain of the DUF4518 family of proteins. This domain has an NTF2-like fold. The function of this domain is unknown.", "domain_architectures": 17, "interpro_id": "IPR063724", "known_evidence_count": null, "matches": 901, "name": "DUF4518 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF15008", "proteins": 897, "proteomes": 672, "short_name": "DUF4518", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15008", "structures": 0, "taxa": 2474, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 592, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 250 amino acids in length. There are two conserved sequence motifs: RPG and WRR. The proteins in this family are frequently annotated as DNA-K related proteins however there is little accompanying literature to confirm this.", "domain_architectures": 2, "interpro_id": "IPR021030", "known_evidence_count": null, "matches": 896, "name": "DNA-K related protein", "partial_evidence_count": null, "pfam_id": "PF12531", "proteins": 896, "proteomes": 888, "short_name": "DUF3731", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12531", "structures": 0, "taxa": 1362, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It has detectable similarity to winged helix HTH domains and it is predicted to adopt similar structure.", "domain_architectures": 69, "interpro_id": "IPR056063", "known_evidence_count": null, "matches": 907, "name": "Domain of unknown function (DUF7646)", "partial_evidence_count": null, "pfam_id": "PF24657", "proteins": 895, "proteomes": 399, "short_name": "DUF7646", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24657", "structures": 0, "taxa": 1181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 424, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a likely zinc binding domain that according to structural modelling may form homodimers. The domain is primarily found in actinobacteria as well as a small range of bacteriophage. The function of this domain is unknown.", "domain_architectures": 7, "interpro_id": "IPR057170", "known_evidence_count": null, "matches": 895, "name": "Domain of unknown function (DUF7848)", "partial_evidence_count": null, "pfam_id": "PF25232", "proteins": 895, "proteomes": 448, "short_name": "DUF7848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25232", "structures": 0, "taxa": 540, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 646, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR018676", "known_evidence_count": null, "matches": 894, "name": "Uncharacterized conserved protein (DUF2149)", "partial_evidence_count": null, "pfam_id": "PF09919", "proteins": 894, "proteomes": 784, "short_name": "DUF2149", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09919", "structures": 0, "taxa": 1543, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 559, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of proteins from Gammaproteobacteria spp. Many members are annotated as being like the E coli protein YbaM.", "domain_architectures": 1, "interpro_id": "IPR019630", "known_evidence_count": null, "matches": 894, "name": "Protein of unknown function (DUF2496)", "partial_evidence_count": null, "pfam_id": "PF10689", "proteins": 894, "proteomes": 894, "short_name": "DUF2496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10689", "structures": 0, "taxa": 1229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 607, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 220 and 257 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR025503", "known_evidence_count": null, "matches": 897, "name": "Domain of unknown function (DUF4391)", "partial_evidence_count": null, "pfam_id": "PF14335", "proteins": 893, "proteomes": 863, "short_name": "DUF4391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14335", "structures": 0, "taxa": 2022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 560, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046601", "known_evidence_count": null, "matches": 893, "name": "Family of unknown function (DUF6660)", "partial_evidence_count": null, "pfam_id": "PF20365", "proteins": 893, "proteomes": 763, "short_name": "DUF6660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20365", "structures": 0, "taxa": 1010, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 571, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This potential domain is functionally uncharacterised. It is found at the C-terminus of a number of ATP transporter proteins suggesting this domain may be involved in ligand binding.", "domain_architectures": 5, "interpro_id": "IPR015005", "known_evidence_count": null, "matches": 893, "name": "Domain of unknown function (DUF1854)", "partial_evidence_count": null, "pfam_id": "PF08909", "proteins": 892, "proteomes": 865, "short_name": "DUF1854", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08909", "structures": 0, "taxa": 1261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in plants and cyanobacteria has no known function. The structure of this domain has been solved by NMR for the alr2454 protein [[cite:PUB00061127]]. The structure was determined to be a novel fold composed of four alpha helices and a sheet of three anti-parallel beta-strands.", "domain_architectures": 18, "interpro_id": "IPR021420", "known_evidence_count": null, "matches": 895, "name": "Domain of unknown function (DUF3067)", "partial_evidence_count": null, "pfam_id": "PF11267", "proteins": 892, "proteomes": 674, "short_name": "DUF3067", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11267", "structures": 1, "taxa": 1903, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 433, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry includes the capsid assembly scaffolding protein Gp46 from Staphylococcus phage 80alpha, which is involved in icosaedric procapsid assembly. It coassembles with capsid proteins to form the procapsid [[cite:PUB00153369]]. The scaffolding protein is found within the capsid as a series of concentric shells. During DNA packaging, the scaffolding protein molecules are released from the procapsid.", "domain_architectures": 2, "interpro_id": "IPR025580", "known_evidence_count": null, "matches": 891, "name": "Capsid assembly scaffolding protein Gp46", "partial_evidence_count": null, "pfam_id": "PF14265", "proteins": 891, "proteomes": 784, "short_name": "DUF4355", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14265", "structures": 1, "taxa": 1631, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 610, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 5, "interpro_id": "IPR021342", "known_evidence_count": null, "matches": 890, "name": "Protein of unknown function (DUF2959)", "partial_evidence_count": null, "pfam_id": "PF11172", "proteins": 890, "proteomes": 855, "short_name": "DUF2959", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11172", "structures": 0, "taxa": 1374, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 543, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 6, "interpro_id": "IPR019283", "known_evidence_count": null, "matches": 899, "name": "Uncharacterized protein conserved in bacteria (DUF2330)", "partial_evidence_count": null, "pfam_id": "PF10092", "proteins": 889, "proteomes": 731, "short_name": "DUF2330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10092", "structures": 0, "taxa": 1391, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 560, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 284 and 326 amino acids in length. This domain is found associated with [pfam:PF01507] in some proteins, suggesting a functional link.", "domain_architectures": 3, "interpro_id": "IPR025248", "known_evidence_count": null, "matches": 890, "name": "Protein of unknown function (DUF4007)", "partial_evidence_count": null, "pfam_id": "PF13182", "proteins": 889, "proteomes": 807, "short_name": "DUF4007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13182", "structures": 2, "taxa": 1905, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 604, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_4772, a putative uncharacterized protein. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 1, "interpro_id": "IPR025415", "known_evidence_count": null, "matches": 889, "name": "Domain of unknown function (DUF4141)", "partial_evidence_count": null, "pfam_id": "PF13605", "proteins": 889, "proteomes": 545, "short_name": "DUF4141", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13605", "structures": 0, "taxa": 890, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 595, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several bacterial YihD proteins of unknown function [[cite:PUB00009964]].", "domain_architectures": 3, "interpro_id": "IPR009383", "known_evidence_count": null, "matches": 889, "name": "Protein of unknown function (DUF1040)", "partial_evidence_count": null, "pfam_id": "PF06288", "proteins": 888, "proteomes": 887, "short_name": "DUF1040", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06288", "structures": 1, "taxa": 1261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 821, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found at the C-terminal of a group of uncharacterised bacterial and archaeal proteins. It may adopt a Ig-like fold.", "domain_architectures": 10, "interpro_id": "IPR011674", "known_evidence_count": null, "matches": 890, "name": "Domain of unknown function (DUF1616)", "partial_evidence_count": null, "pfam_id": "PF07760", "proteins": 887, "proteomes": 416, "short_name": "DUF1616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07760", "structures": 0, "taxa": 760, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 803, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically 131 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR027892", "known_evidence_count": null, "matches": 926, "name": "Domain of unknown function (DUF4581)", "partial_evidence_count": null, "pfam_id": "PF15167", "proteins": 887, "proteomes": 725, "short_name": "DUF4581", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15167", "structures": 0, "taxa": 2259, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 784, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 238 and 436 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR031518", "known_evidence_count": null, "matches": 918, "name": "Domain of unknown function (DUF4693)", "partial_evidence_count": null, "pfam_id": "PF15764", "proteins": 887, "proteomes": 675, "short_name": "DUF4693", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15764", "structures": 0, "taxa": 2123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 748, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in Caenorhabditis elegans uncharacterized protein C01C4.2 and related proteins. It is predicted to adopt an alpha+beta barrel with some similarity to the dimeric alpha+beta barrel structures, in particular REDY-like protein Hapk ([pfam:PF11639]).", "domain_architectures": 14, "interpro_id": "IPR055577", "known_evidence_count": null, "matches": 894, "name": "Domain of unknown function (DUF7153)", "partial_evidence_count": null, "pfam_id": "PF23672", "proteins": 887, "proteomes": 412, "short_name": "DUF7153", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23672", "structures": 0, "taxa": 1480, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 730, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in uncharacterised fungal sequences, which is a cysteine-rich domain found at the C-terminal end of these sequences.", "domain_architectures": 31, "interpro_id": "IPR061525", "known_evidence_count": null, "matches": 888, "name": "Domain of unknown function (DUF8455)", "partial_evidence_count": null, "pfam_id": "PF28755", "proteins": 887, "proteomes": 619, "short_name": "DUF8455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28755", "structures": 0, "taxa": 1399, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 798, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. It is found in proteins from eukaryotes, and is typically between 39 and 76 amino acids in length. There are several conserved motifs, Y/FxN, KF and KPTG and a highly conserved W residue at the N-terminal. Structural predictions indicate this domain may fold into three alpha helices.", "domain_architectures": 9, "interpro_id": "IPR049203", "known_evidence_count": null, "matches": 887, "name": "Domain of unknown function (DUF6818)", "partial_evidence_count": null, "pfam_id": "PF20681", "proteins": 886, "proteomes": 172, "short_name": "DUF6818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20681", "structures": 0, "taxa": 489, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 550, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 70 amino acids in length. The family is found in association with [pfam:PF00005]. There is a conserved REP sequence motif. There is a single completely conserved residue P that may be functionally important. The proteins in this family are frequently annotated as ABC Cobalt transporters however there is little accompanying literature to confirm this.", "domain_architectures": 6, "interpro_id": "IPR022216", "known_evidence_count": null, "matches": 885, "name": "ATP-binding cassette cobalt transporter", "partial_evidence_count": null, "pfam_id": "PF12558", "proteins": 885, "proteomes": 860, "short_name": "DUF3744", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12558", "structures": 0, "taxa": 1324, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 570, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 141 and 157 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046161", "known_evidence_count": null, "matches": 884, "name": "Family of unknown function (DUF6163)", "partial_evidence_count": null, "pfam_id": "PF19660", "proteins": 884, "proteomes": 884, "short_name": "DUF6163", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19660", "structures": 0, "taxa": 1188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 542, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are remotely related to nucleotidyltransferases and share similar active site architecture.", "domain_architectures": 4, "interpro_id": "IPR053860", "known_evidence_count": null, "matches": 884, "name": "Family of unknown function (DUF6932)", "partial_evidence_count": null, "pfam_id": "PF22014", "proteins": 884, "proteomes": 799, "short_name": "DUF6932", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22014", "structures": 0, "taxa": 1673, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 397, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a membrane protein domain of approximately 70 residues found in Streptomyces and related Actinomycetes. In Streptomyces coelicolor, SCO4131 containing this domain is located in a gene cluster (SCO4126-SCO4131) that affects actinorhodin antibiotic biosynthesis [[cite:PUB00163737]]. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061888", "known_evidence_count": null, "matches": 884, "name": "Domain of unknown function (DUF8827)", "partial_evidence_count": null, "pfam_id": "PF31162", "proteins": 884, "proteomes": 832, "short_name": "DUF8827", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31162", "structures": 0, "taxa": 889, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 518, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 5, "interpro_id": "IPR020206", "known_evidence_count": null, "matches": 882, "name": "Protein of unknown function (DUF2753)", "partial_evidence_count": null, "pfam_id": "PF10952", "proteins": 882, "proteomes": 827, "short_name": "DUF2753", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10952", "structures": 0, "taxa": 1270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 477, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in the middle region of bacterial sequences, which have a [pfam:PF20103] at the N-terminal.", "domain_architectures": 8, "interpro_id": "IPR056726", "known_evidence_count": null, "matches": 887, "name": "Domain of unknown function (DUF7824)", "partial_evidence_count": null, "pfam_id": "PF25148", "proteins": 882, "proteomes": 678, "short_name": "DUF7824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25148", "structures": 0, "taxa": 968, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 720, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 11, "interpro_id": "IPR018853", "known_evidence_count": null, "matches": 927, "name": "Protein of unknown function (DUF2457)", "partial_evidence_count": null, "pfam_id": "PF10446", "proteins": 881, "proteomes": 858, "short_name": "DUF2457", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10446", "structures": 0, "taxa": 1737, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 547, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR010365", "known_evidence_count": null, "matches": 880, "name": "Bacterial protein of unknown function (DUF961)", "partial_evidence_count": null, "pfam_id": "PF06125", "proteins": 880, "proteomes": 360, "short_name": "DUF961", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06125", "structures": 1, "taxa": 694, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 407, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry contains a set of proteins that have a predicted 6-helical hairpin fold found in a wide range of glycosyl hydrolase enzymes, suggesting a potential function for these proteins. These proteins are largely found in actinobacteria and Alphaproteobacteria.", "domain_architectures": 5, "interpro_id": "IPR054190", "known_evidence_count": null, "matches": 882, "name": "Domain of unknown function (DUF6895)", "partial_evidence_count": null, "pfam_id": "PF21836", "proteins": 880, "proteomes": 569, "short_name": "DUF6895", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21836", "structures": 0, "taxa": 901, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in human Protein dispatched homolog 3 (DISP3) and related proteins mainly from vertebrates. DISP3 (PTCHD2), a sterol-sensing domain- containing protein, is highly expressed in neural tissue, promotes cell proliferation and alters expression of genes that are involved in tumourigenesis. The function of this domain is unknown.", "domain_architectures": 20, "interpro_id": "IPR053954", "known_evidence_count": null, "matches": 890, "name": "Domain of unknown function (DUF7023)", "partial_evidence_count": null, "pfam_id": "PF22894", "proteins": 880, "proteomes": 684, "short_name": "DUF7023", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22894", "structures": 0, "taxa": 2109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in multiple copies in a number of bacterial proteins. It is closely related to domains represented by DUF11 ([pfam:PF01345]). Similarly to DUF11, this domain contains a conserved N-terminal lysine and a C-terminal asparagine with central aspartate/glutamate residues suggesting that it may contain an isopeptide bond.", "domain_architectures": 376, "interpro_id": "IPR057687", "known_evidence_count": null, "matches": 3813, "name": "Domain of unknown function (DUF7927)", "partial_evidence_count": null, "pfam_id": "PF25549", "proteins": 880, "proteomes": 552, "short_name": "DUF7927", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25549", "structures": 0, "taxa": 887, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 732, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from fungi. It is predicted to adopt a UBA domain-like structure. UBA domains are often involved in ubiquitin binding. The specific function of this domain", "domain_architectures": 27, "interpro_id": "IPR059476", "known_evidence_count": null, "matches": 880, "name": "Domain of unknown function (DUF8432)", "partial_evidence_count": null, "pfam_id": "PF28536", "proteins": 880, "proteomes": 866, "short_name": "DUF8432", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28536", "structures": 0, "taxa": 1684, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 708, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. This domain is predicted to fold into a globular structure with a winged helix HTH topology.", "domain_architectures": 22, "interpro_id": "IPR056042", "known_evidence_count": null, "matches": 881, "name": "Domain of unknown function (DUF7625)", "partial_evidence_count": null, "pfam_id": "PF24620", "proteins": 879, "proteomes": 352, "short_name": "DUF7625", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24620", "structures": 0, "taxa": 951, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 592, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a domain of unknown function. It forms a central anti-parallel beta sheet with flanking alpha helical regions.", "domain_architectures": 1, "interpro_id": "IPR014904", "known_evidence_count": null, "matches": 878, "name": "Protein of unknown function (DUF1797)", "partial_evidence_count": null, "pfam_id": "PF08796", "proteins": 878, "proteomes": 877, "short_name": "DUF1797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08796", "structures": 1, "taxa": 1186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 737, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a beta-beta-alpha zinc finger found in a group of uncharacterised sequences, mainly from fungi.", "domain_architectures": 38, "interpro_id": "IPR055494", "known_evidence_count": null, "matches": 878, "name": "Domain of unknown function (DUF7066)", "partial_evidence_count": null, "pfam_id": "PF23217", "proteins": 878, "proteomes": 590, "short_name": "DUF7066", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23217", "structures": 0, "taxa": 1758, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 647, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR019235", "known_evidence_count": null, "matches": 876, "name": "Predicted membrane protein (DUF2178)", "partial_evidence_count": null, "pfam_id": "PF09946", "proteins": 876, "proteomes": 718, "short_name": "DUF2178", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09946", "structures": 0, "taxa": 1374, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 656, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in bacteria and eukaryotes.", "domain_architectures": 14, "interpro_id": "IPR021562", "known_evidence_count": null, "matches": 876, "name": "Protein of unknown function (DUF3007)", "partial_evidence_count": null, "pfam_id": "PF11460", "proteins": 876, "proteomes": 678, "short_name": "DUF3007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11460", "structures": 0, "taxa": 1930, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 696, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. These are likely membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR046739", "known_evidence_count": null, "matches": 876, "name": "Family of unknown function (DUF6789)", "partial_evidence_count": null, "pfam_id": "PF20587", "proteins": 876, "proteomes": 608, "short_name": "DUF6789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20587", "structures": 0, "taxa": 1191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 716, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in a group of uncharacterised fungal sequences.", "domain_architectures": 6, "interpro_id": "IPR057199", "known_evidence_count": null, "matches": 876, "name": "Domain of unknown function (DUF7877)", "partial_evidence_count": null, "pfam_id": "PF25289", "proteins": 876, "proteomes": 857, "short_name": "DUF7877", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25289", "structures": 0, "taxa": 1682, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 734, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised sequences from fungi. It may adopt a nucleotidyl transferase-like fold.", "domain_architectures": 8, "interpro_id": "IPR056004", "known_evidence_count": null, "matches": 885, "name": "Domain of unknown function (DUF7582)", "partial_evidence_count": null, "pfam_id": "PF24483", "proteins": 874, "proteomes": 670, "short_name": "DUF7582", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24483", "structures": 0, "taxa": 1304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 725, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 393 and 442 amino acids in length.", "domain_architectures": 14, "interpro_id": "IPR025040", "known_evidence_count": null, "matches": 974, "name": "Protein of unknown function (DUF3984)", "partial_evidence_count": null, "pfam_id": "PF13136", "proteins": 872, "proteomes": 848, "short_name": "DUF3984", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13136", "structures": 0, "taxa": 1692, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 554, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain lies C-terminal to DUF4959, [pfam:PF16323].", "domain_architectures": 7, "interpro_id": "IPR033431", "known_evidence_count": null, "matches": 872, "name": "Domain of unknown function (DUF5126)", "partial_evidence_count": null, "pfam_id": "PF17166", "proteins": 872, "proteomes": 347, "short_name": "DUF5126", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17166", "structures": 1, "taxa": 506, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 523, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of bacterial proteins with undetermined function. All bacteria in this family are from the Rhizobiales order.", "domain_architectures": 1, "interpro_id": "IPR009273", "known_evidence_count": null, "matches": 871, "name": "Domain of Unknown Function (DUF930)", "partial_evidence_count": null, "pfam_id": "PF06059", "proteins": 871, "proteomes": 503, "short_name": "DUF930", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06059", "structures": 0, "taxa": 681, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 536, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in hypothetical bacterial proteins of around 200 residues in length. The function of this domain is unknown.", "domain_architectures": 7, "interpro_id": "IPR009988", "known_evidence_count": null, "matches": 871, "name": "Domain of unknown function (DUF1510)", "partial_evidence_count": null, "pfam_id": "PF07423", "proteins": 871, "proteomes": 823, "short_name": "DUF1510", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07423", "structures": 0, "taxa": 1060, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 576, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found at the N-terminal of DUF3472, [pfam:PF00958].", "domain_architectures": 21, "interpro_id": "IPR031712", "known_evidence_count": null, "matches": 872, "name": "Domain of unknown function (DUF5077)", "partial_evidence_count": null, "pfam_id": "PF16871", "proteins": 871, "proteomes": 693, "short_name": "DUF5077", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16871", "structures": 2, "taxa": 1175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 755, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 157 and 192 amino acids in length. There is a single completely conserved residue D that may be functionally important. The family includes Protein CFAP276 and homologues. CFAP276 has been suggested to be involved in intracellular Ca2 homeostasis [[cite:PUB00093604]].", "domain_architectures": 14, "interpro_id": "IPR022179", "known_evidence_count": null, "matches": 870, "name": "Protein of unknown function (DUF3695)", "partial_evidence_count": null, "pfam_id": "PF12494", "proteins": 870, "proteomes": 649, "short_name": "DUF3695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12494", "structures": 13, "taxa": 2374, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 545, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 285 and 362 amino acids in length. This domain is sometimes associated with AAA domains.", "domain_architectures": 9, "interpro_id": "IPR029492", "known_evidence_count": null, "matches": 870, "name": "Protein of unknown function (DUF4435)", "partial_evidence_count": null, "pfam_id": "PF14491", "proteins": 870, "proteomes": 816, "short_name": "DUF4435", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14491", "structures": 0, "taxa": 1880, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 528, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Actinobacteria. The function is not known.", "domain_architectures": 11, "interpro_id": "IPR019719", "known_evidence_count": null, "matches": 888, "name": "Protein of unknown function (DUF2599)", "partial_evidence_count": null, "pfam_id": "PF10783", "proteins": 869, "proteomes": 761, "short_name": "DUF2599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10783", "structures": 0, "taxa": 1078, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 689, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes uncharacterised fungal sequences. It represents a long alpha-helix found near the C-terminal.", "domain_architectures": 11, "interpro_id": "IPR056023", "known_evidence_count": null, "matches": 869, "name": "Domain of unknown function (DUF7603)", "partial_evidence_count": null, "pfam_id": "PF24554", "proteins": 869, "proteomes": 857, "short_name": "DUF7603", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24554", "structures": 0, "taxa": 1698, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 739, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several insect specific proteins. [swissprot:Q25513] is annotated as being a haemolymph glycoprotein precursor. The function of this family is unknown [[cite:PUB00013024]].", "domain_architectures": 17, "interpro_id": "IPR009832", "known_evidence_count": null, "matches": 888, "name": "Protein of unknown function (DUF1397)", "partial_evidence_count": null, "pfam_id": "PF07165", "proteins": 868, "proteomes": 273, "short_name": "DUF1397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07165", "structures": 0, "taxa": 1101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 817, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the C-terminal of a group of uncharacterised archaeal sequences, which contain an HTH domain at the N-terminal.", "domain_architectures": 6, "interpro_id": "IPR055775", "known_evidence_count": null, "matches": 871, "name": "Domain of unknown function (DUF7351)", "partial_evidence_count": null, "pfam_id": "PF24042", "proteins": 868, "proteomes": 245, "short_name": "DUF7351", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24042", "structures": 0, "taxa": 394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 707, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 228 and 257 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR025122", "known_evidence_count": null, "matches": 872, "name": "Domain of unknown function (DUF4048)", "partial_evidence_count": null, "pfam_id": "PF13257", "proteins": 867, "proteomes": 844, "short_name": "DUF4048", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13257", "structures": 0, "taxa": 1649, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 525, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function and is mostly found in Bacilli.", "domain_architectures": 1, "interpro_id": "IPR035218", "known_evidence_count": null, "matches": 867, "name": "Family of unknown function (DUF5327)", "partial_evidence_count": null, "pfam_id": "PF17261", "proteins": 867, "proteomes": 864, "short_name": "DUF5327", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17261", "structures": 0, "taxa": 1097, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 321, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into a globular structure with ubiquitin-like topology elaborated with long loops. It is frequently found in combination with [pfam:PF23086].", "domain_architectures": 20, "interpro_id": "IPR055781", "known_evidence_count": null, "matches": 872, "name": "Domain of unknown function (DUF7357)", "partial_evidence_count": null, "pfam_id": "PF24054", "proteins": 867, "proteomes": 839, "short_name": "DUF7357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24054", "structures": 0, "taxa": 1649, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 716, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha/beta structure composed of a four-stranded antiparallel curved beta-sheet packed with two alpha-helices on one side. This domain contains three pairs of conserved cisteine residues that are predicted to form disulfide bonds.", "domain_architectures": 10, "interpro_id": "IPR061855", "known_evidence_count": null, "matches": 868, "name": "Domain of unknown function (DUF8794)", "partial_evidence_count": null, "pfam_id": "PF31055", "proteins": 867, "proteomes": 343, "short_name": "DUF8794", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31055", "structures": 0, "taxa": 751, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 552, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a subclade of DUF488 domains with degenerate C-terminal core strand. Sometimes it is observed adjacent to the DUF488-s subclade, suggesting it preserves a catalytic activity comparable to other active DUF488 subclades [[cite:PUB00153826]].", "domain_architectures": 2, "interpro_id": "IPR054495", "known_evidence_count": null, "matches": 866, "name": "Active DUF488-N3 subclade", "partial_evidence_count": null, "pfam_id": "PF22751", "proteins": 866, "proteomes": 823, "short_name": "DUF488-N3a", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22751", "structures": 0, "taxa": 1522, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 728, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found at the N-terminal of a group of uncharacterised fungal sequences which is found in association with a Cytidyltransferase-like domain ([pfam:PF01467]) at the C-terminal. This domain seems to adopt a structure similar to those in the HUP superfamily.", "domain_architectures": 9, "interpro_id": "IPR061516", "known_evidence_count": null, "matches": 867, "name": "Domain of unknown function (DUF8446)", "partial_evidence_count": null, "pfam_id": "PF28717", "proteins": 866, "proteomes": 828, "short_name": "DUF8446", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28717", "structures": 0, "taxa": 1625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 552, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR043748", "known_evidence_count": null, "matches": 869, "name": "Family of unknown function (DUF5693)", "partial_evidence_count": null, "pfam_id": "PF18949", "proteins": 865, "proteomes": 835, "short_name": "DUF5693", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18949", "structures": 0, "taxa": 1365, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 526, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function with some overlap with clan family members of CL0058.", "domain_architectures": 2, "interpro_id": "IPR043751", "known_evidence_count": null, "matches": 866, "name": "Family of unknown function (DUF5696)", "partial_evidence_count": null, "pfam_id": "PF18952", "proteins": 865, "proteomes": 437, "short_name": "DUF5696", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18952", "structures": 10, "taxa": 779, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 709, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in a group of uncharacterised fungal sequences.", "domain_architectures": 6, "interpro_id": "IPR056687", "known_evidence_count": null, "matches": 865, "name": "Domain of unknown function (DUF7785)", "partial_evidence_count": null, "pfam_id": "PF25009", "proteins": 865, "proteomes": 848, "short_name": "DUF7785", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25009", "structures": 0, "taxa": 1668, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 396, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically 89 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046648", "known_evidence_count": null, "matches": 864, "name": "Family of unknown function (DUF6760)", "partial_evidence_count": null, "pfam_id": "PF20546", "proteins": 864, "proteomes": 798, "short_name": "DUF6760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20546", "structures": 0, "taxa": 1296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 372, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 100 residues found in small uncharacterized proteins in Streptomyces and related Actinomycetes. These proteins typically consist of this single domain only. Foldseek analysis suggests weak structural similarity to DUF6204 ([pfam:PF19707]). The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061891", "known_evidence_count": null, "matches": 864, "name": "Domain of unknown function (DUF8830)", "partial_evidence_count": null, "pfam_id": "PF31169", "proteins": 864, "proteomes": 859, "short_name": "DUF8830", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31169", "structures": 0, "taxa": 940, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 662, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from animals. Many proteins in this group also contain [pfam:PF00057].", "domain_architectures": 15, "interpro_id": "IPR056707", "known_evidence_count": null, "matches": 868, "name": "Domain of unknown function (DUF7805)", "partial_evidence_count": null, "pfam_id": "PF25090", "proteins": 863, "proteomes": 289, "short_name": "DUF7805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25090", "structures": 0, "taxa": 1077, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 726, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 110 amino acids in length.", "domain_architectures": 15, "interpro_id": "IPR031600", "known_evidence_count": null, "matches": 897, "name": "Domain of unknown function (DUF4706)", "partial_evidence_count": null, "pfam_id": "PF15797", "proteins": 862, "proteomes": 687, "short_name": "DUF4706", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15797", "structures": 0, "taxa": 2571, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised fungal sequences.", "domain_architectures": 39, "interpro_id": "IPR056015", "known_evidence_count": null, "matches": 863, "name": "Domain of unknown function (DUF7593)", "partial_evidence_count": null, "pfam_id": "PF24513", "proteins": 862, "proteomes": 848, "short_name": "DUF7593", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24513", "structures": 0, "taxa": 1643, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 797, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between and 59 amino acids in length. There are two conserved sequence motifs: KET and VLP. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 10, "interpro_id": "IPR027960", "known_evidence_count": null, "matches": 861, "name": "Domain of unknown function (DUF4519)", "partial_evidence_count": null, "pfam_id": "PF15012", "proteins": 861, "proteomes": 796, "short_name": "DUF4519", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15012", "structures": 0, "taxa": 2697, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 90 residues found in S8 family serine peptidases (subtilisins). The domain is found N-terminal to the Peptidase_S8 catalytic domain ([pfam:PF00082]). In Bacteroidota members, the proteins often contain a C-terminal T9SS secretion signal ([pfam:PF18962]). This family is found in bacteria including Pseudomonadota, Actinomycetota and Bacteroidota, as well as fungi (Ascomycota). The function of this domain remains to be determined.", "domain_architectures": 122, "interpro_id": "IPR061790", "known_evidence_count": null, "matches": 861, "name": "Domain of unknown function (DUF8729)", "partial_evidence_count": null, "pfam_id": "PF30773", "proteins": 861, "proteomes": 656, "short_name": "DUF8729", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30773", "structures": 0, "taxa": 1359, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found towards the N-terminal of CHAT domain-containing protein, such as SwissProt:A0A100JVW6, from Streptomyces scabiei. This domain may adopt a A/B hydrolase fold and is often found in association with TCAD7 ([pfam:PF19973]) and CHAT ([pfam:PF12770]) domains.", "domain_architectures": 39, "interpro_id": "IPR055803", "known_evidence_count": null, "matches": 1098, "name": "Domain of unknown function (DUF7379)", "partial_evidence_count": null, "pfam_id": "PF24096", "proteins": 860, "proteomes": 789, "short_name": "DUF7379", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24096", "structures": 1, "taxa": 1637, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 818, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of domains found in Halobacteria at the C-terminus of a set of ABC transporter proteins. This suggests this may be a substrate binding domain.", "domain_architectures": 9, "interpro_id": "IPR059272", "known_evidence_count": null, "matches": 865, "name": "Domain of unknown function (DUF8228)", "partial_evidence_count": null, "pfam_id": "PF26679", "proteins": 860, "proteomes": 259, "short_name": "DUF8228", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26679", "structures": 0, "taxa": 410, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Bacillaceae.", "domain_architectures": 1, "interpro_id": "IPR024490", "known_evidence_count": null, "matches": 859, "name": "Protein of unknown function (DUF2759)", "partial_evidence_count": null, "pfam_id": "PF10958", "proteins": 859, "proteomes": 856, "short_name": "DUF2759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10958", "structures": 0, "taxa": 1073, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 529, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021382", "known_evidence_count": null, "matches": 859, "name": "Protein of unknown function (DUF3014)", "partial_evidence_count": null, "pfam_id": "PF11219", "proteins": 859, "proteomes": 830, "short_name": "DUF3014", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11219", "structures": 0, "taxa": 1225, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "A family of uncharacterised proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]]. This domain is likely to be related to the Toprim domain.", "domain_architectures": 31, "interpro_id": "IPR024385", "known_evidence_count": null, "matches": 869, "name": "Domain of unknown function (DUF3854)", "partial_evidence_count": null, "pfam_id": "PF12965", "proteins": 859, "proteomes": 412, "short_name": "DUF3854", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12965", "structures": 0, "taxa": 1132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 764, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Drosophila melanogaster proteins of unknown function.", "domain_architectures": 16, "interpro_id": "IPR007999", "known_evidence_count": null, "matches": 881, "name": "Protein of unknown function (DUF745)", "partial_evidence_count": null, "pfam_id": "PF05335", "proteins": 858, "proteomes": 218, "short_name": "DUF745", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05335", "structures": 0, "taxa": 792, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 719, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Metazoa.", "domain_architectures": 10, "interpro_id": "IPR041477", "known_evidence_count": null, "matches": 898, "name": "Family of unknown function (DUF5577)", "partial_evidence_count": null, "pfam_id": "PF17740", "proteins": 858, "proteomes": 454, "short_name": "DUF5577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17740", "structures": 0, "taxa": 1650, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 819, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble Zinc beta-ribbon domains.", "domain_architectures": 1, "interpro_id": "IPR055985", "known_evidence_count": null, "matches": 856, "name": "Family of unknown function (DUF7563)", "partial_evidence_count": null, "pfam_id": "PF24444", "proteins": 856, "proteomes": 252, "short_name": "DUF7563", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24444", "structures": 0, "taxa": 423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 756, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in mammals. This family includes two human proteins: C12orf60 and C12orf69.", "domain_architectures": 5, "interpro_id": "IPR027895", "known_evidence_count": null, "matches": 882, "name": "Protein of unknown function (DUF4533)", "partial_evidence_count": null, "pfam_id": "PF15047", "proteins": 854, "proteomes": 561, "short_name": "DUF4533", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15047", "structures": 0, "taxa": 1650, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 704, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into array of helices.", "domain_architectures": 11, "interpro_id": "IPR061822", "known_evidence_count": null, "matches": 860, "name": "Domain of unknown function (DUF8761)", "partial_evidence_count": null, "pfam_id": "PF30927", "proteins": 854, "proteomes": 841, "short_name": "DUF8761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30927", "structures": 0, "taxa": 1655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 523, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in many hypothetical proteins. The structure of one of the proteins in this family has been solved and it adopts an all alpha helical fold.", "domain_architectures": 1, "interpro_id": "IPR014913", "known_evidence_count": null, "matches": 853, "name": "Bacterial domain of unknown function (DUF1798)", "partial_evidence_count": null, "pfam_id": "PF08807", "proteins": 853, "proteomes": 851, "short_name": "DUF1798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08807", "structures": 4, "taxa": 1090, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 533, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length. There are two completely conserved residues (P and G) that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR025516", "known_evidence_count": null, "matches": 861, "name": "Domain of unknown function (DUF4404)", "partial_evidence_count": null, "pfam_id": "PF14357", "proteins": 853, "proteomes": 844, "short_name": "DUF4404", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14357", "structures": 0, "taxa": 1210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 566, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a likely bacterial Ig-like fold, suggesting it may be a family of lipoproteins.", "domain_architectures": 5, "interpro_id": "IPR027829", "known_evidence_count": null, "matches": 1005, "name": "Domain of unknown function (DUF4625)", "partial_evidence_count": null, "pfam_id": "PF15418", "proteins": 853, "proteomes": 464, "short_name": "DUF4625", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15418", "structures": 0, "taxa": 727, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 697, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 152 and 673 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR027851", "known_evidence_count": null, "matches": 872, "name": "Domain of unknown function (DUF4628)", "partial_evidence_count": null, "pfam_id": "PF15429", "proteins": 853, "proteomes": 502, "short_name": "DUF4628", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15429", "structures": 0, "taxa": 1657, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR035183", "known_evidence_count": null, "matches": 853, "name": "Family of unknown function (DUF5304)", "partial_evidence_count": null, "pfam_id": "PF17230", "proteins": 853, "proteomes": 850, "short_name": "DUF5304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17230", "structures": 0, "taxa": 915, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 710, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal sequences that also contain a Zn(2)Cys(6) DNA-binding domain ([pfam:PF00172]).", "domain_architectures": 5, "interpro_id": "IPR061514", "known_evidence_count": null, "matches": 865, "name": "Domain of unknown function (DUF8444)", "partial_evidence_count": null, "pfam_id": "PF28706", "proteins": 853, "proteomes": 834, "short_name": "DUF8444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28706", "structures": 0, "taxa": 1630, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 611, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in rhodobacteria. Proteins in this family are typically between 411 and 445 amino acids in length. The family is found to the N-terminus of [pfam:PF01551].", "domain_architectures": 5, "interpro_id": "IPR045974", "known_evidence_count": null, "matches": 859, "name": "Family of unknown function (DUF5930)", "partial_evidence_count": null, "pfam_id": "PF19353", "proteins": 852, "proteomes": 841, "short_name": "DUF5930", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19353", "structures": 0, "taxa": 1243, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 561, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short domain lies at the N-terminus of DUF2154, [pfam:PF09922], hereafter named Toast_rack from its structural resemblance. The function of both domains is unknown though DUF2154 is proposed to be a cell-adhesion protein.", "domain_architectures": 12, "interpro_id": "IPR031346", "known_evidence_count": null, "matches": 858, "name": "N-terminal domain of toast_rack, DUF2154", "partial_evidence_count": null, "pfam_id": "PF17115", "proteins": 851, "proteomes": 801, "short_name": "Toast_rack_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17115", "structures": 1, "taxa": 1320, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 692, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins.", "domain_architectures": 27, "interpro_id": "IPR061810", "known_evidence_count": null, "matches": 940, "name": "Domain of unknown function (DUF8749)", "partial_evidence_count": null, "pfam_id": "PF30847", "proteins": 851, "proteomes": 419, "short_name": "DUF8749", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30847", "structures": 0, "taxa": 1181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in Actinobacteria. Most of the family members contain one trans-membrane domain.", "domain_architectures": 2, "interpro_id": "IPR035214", "known_evidence_count": null, "matches": 850, "name": "Family of unknown function (DUF5324)", "partial_evidence_count": null, "pfam_id": "PF17258", "proteins": 850, "proteomes": 841, "short_name": "DUF5324", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17258", "structures": 0, "taxa": 919, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 659, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into an alpha/beta structure consisting of a central mixed beta-sheet and alpha-helices packed on both sides. It is usually found upstream DUF7913 ([pfam:PF25500]).", "domain_architectures": 24, "interpro_id": "IPR057237", "known_evidence_count": null, "matches": 894, "name": "Domain of unknown function (DUF7915)", "partial_evidence_count": null, "pfam_id": "PF25502", "proteins": 850, "proteomes": 341, "short_name": "DUF7915", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25502", "structures": 0, "taxa": 940, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 712, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of conserved fungal proteins of unknown function.", "domain_architectures": 7, "interpro_id": "IPR024526", "known_evidence_count": null, "matches": 849, "name": "Protein of unknown function (DUF3807)", "partial_evidence_count": null, "pfam_id": "PF12720", "proteins": 849, "proteomes": 840, "short_name": "DUF3807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12720", "structures": 0, "taxa": 1651, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 702, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a globular structure with significant structural similarity to alkaline phosphatases.", "domain_architectures": 20, "interpro_id": "IPR056696", "known_evidence_count": null, "matches": 887, "name": "Domain of unknown function (DUF7794)", "partial_evidence_count": null, "pfam_id": "PF25070", "proteins": 849, "proteomes": 381, "short_name": "DUF7794", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25070", "structures": 0, "taxa": 1064, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 559, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 5, "interpro_id": "IPR016755", "known_evidence_count": null, "matches": 849, "name": "Uncharacterized protein conserved in bacteria (DUF2322)", "partial_evidence_count": null, "pfam_id": "PF10084", "proteins": 848, "proteomes": 836, "short_name": "DUF2322", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10084", "structures": 0, "taxa": 1234, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 459, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as ybfG however currently no function is known.", "domain_architectures": 4, "interpro_id": "IPR021239", "known_evidence_count": null, "matches": 853, "name": "Protein of unknown function DUF2625", "partial_evidence_count": null, "pfam_id": "PF10946", "proteins": 848, "proteomes": 797, "short_name": "DUF2625", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10946", "structures": 0, "taxa": 1242, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 636, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is functionally uncharacterized. It is about 300-500 amino acids in length. This family is found in plants and bacteria.", "domain_architectures": 22, "interpro_id": "IPR021763", "known_evidence_count": null, "matches": 897, "name": "Protein of unknown function (DUF3326)", "partial_evidence_count": null, "pfam_id": "PF11805", "proteins": 848, "proteomes": 613, "short_name": "DUF3326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11805", "structures": 0, "taxa": 1794, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 543, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in Alphaproteobacteria. Proteins in this family are typically between 173 and 189 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046083", "known_evidence_count": null, "matches": 848, "name": "Family of unknown function (DUF6101)", "partial_evidence_count": null, "pfam_id": "PF19596", "proteins": 848, "proteomes": 846, "short_name": "DUF6101", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19596", "structures": 0, "taxa": 1128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 759, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a helical domain found in association with a G domain (also known as MMR_HSR1 or GTP-binding domain), a conserved nucleotide-binding domain that typically binds GTP. This domain is found predominantly in fungal species across both Basidiomycota and Ascomycota phyla. The function of this domain is unknown. Structure predictions suggest it may adopt a HTH fold.", "domain_architectures": 21, "interpro_id": "IPR061575", "known_evidence_count": null, "matches": 852, "name": "Domain of unknown function (DUF8505)", "partial_evidence_count": null, "pfam_id": "PF29139", "proteins": 848, "proteomes": 239, "short_name": "DUF8505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29139", "structures": 0, "taxa": 578, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 597, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised prokaryotic proteins most of which likely associated with proteins located in pilBC operon. It is frequently found inserted in [[pfam:PF23960]]. This domain is predicted to adopt a single-stranded right-handed beta-helix with similarity to ice-binding proteins and other adhesive domains.", "domain_architectures": 53, "interpro_id": "IPR055729", "known_evidence_count": null, "matches": 856, "name": "Domain of unknown function (DUF7305)", "partial_evidence_count": null, "pfam_id": "PF23981", "proteins": 846, "proteomes": 704, "short_name": "DUF7305", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23981", "structures": 0, "taxa": 1480, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 586, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of bacterial sequences with undetermined function.", "domain_architectures": 1, "interpro_id": "IPR010360", "known_evidence_count": null, "matches": 845, "name": "Domain of unknown function (DUF956)", "partial_evidence_count": null, "pfam_id": "PF06115", "proteins": 845, "proteomes": 796, "short_name": "DUF956", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06115", "structures": 0, "taxa": 1210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 490, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal and and bacterial proteins of around 300 residues in length. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR009561", "known_evidence_count": null, "matches": 844, "name": "Protein of unknown function (DUF1177)", "partial_evidence_count": null, "pfam_id": "PF06675", "proteins": 844, "proteomes": 790, "short_name": "DUF1177", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06675", "structures": 0, "taxa": 1346, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 564, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 344 and 443 amino acids in length. There are two completely conserved residues (R and L) that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR025396", "known_evidence_count": null, "matches": 844, "name": "Domain of unknown function (DUF4302)", "partial_evidence_count": null, "pfam_id": "PF14135", "proteins": 844, "proteomes": 529, "short_name": "DUF4302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14135", "structures": 0, "taxa": 736, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 735, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family represents a repeated region found in several Theileria parva proteins. The repeat is normally about 70 residues long and contains a conserved aromatic residue in the middle.", "domain_architectures": 38, "interpro_id": "IPR007480", "known_evidence_count": null, "matches": 1856, "name": "Domain of unknown function, DUF529", "partial_evidence_count": null, "pfam_id": "PF04385", "proteins": 843, "proteomes": 11, "short_name": "FAINT", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04385", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 452, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021677", "known_evidence_count": null, "matches": 843, "name": "Protein of unknown function (DUF2986)", "partial_evidence_count": null, "pfam_id": "PF11661", "proteins": 843, "proteomes": 763, "short_name": "DUF2986", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11661", "structures": 0, "taxa": 975, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 676, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain of unknown function has an enolase N-terminal domain-like fold. Its genomic context suggests that it may have a role in anaerobic vitamin B12 biosynthesis. This domain is often found at the N-terminus of proteins containing DUF364, [pfam:PF04016]. The structure of UnioProtKB:B8FUJ5, PDB:3l5o, suggests that the whole protein has this enolase N-terminal-like fold and an Rossmann-like C-terminal domain. Structural and bioinformatic analyses reveal partial similarities to Rossmann-like methyltransferases, with residues from the enolase-like fold combining to form a unique active site that is likely to be involved in the condensation or hydrolysis of molecules implicated in the synthesis of flavins, pterins or other siderophores. The protein may be playing a role in heavy-metal chelation [[cite:PUB00075371]].", "domain_architectures": 6, "interpro_id": "IPR025251", "known_evidence_count": null, "matches": 843, "name": "Putative heavy-metal chelation", "partial_evidence_count": null, "pfam_id": "PF13938", "proteins": 843, "proteomes": 695, "short_name": "DUF4213", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13938", "structures": 2, "taxa": 1584, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 650, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 16, "interpro_id": "IPR021467", "known_evidence_count": null, "matches": 842, "name": "Protein of unknown function (DUF3119)", "partial_evidence_count": null, "pfam_id": "PF11317", "proteins": 842, "proteomes": 651, "short_name": "DUF3119", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11317", "structures": 0, "taxa": 1845, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 304, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001973) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the fervenulin biosynthetic gene cluster from Streptomyces hiroshimensis [[cite:PUB00099459]]. This family appears to be predominantly found in Actinoabacteria.", "domain_architectures": 6, "interpro_id": "IPR046200", "known_evidence_count": null, "matches": 843, "name": "Family of unknown function (DUF6233)", "partial_evidence_count": null, "pfam_id": "PF19746", "proteins": 842, "proteomes": 450, "short_name": "DUF6233", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19746", "structures": 0, "taxa": 510, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 524, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 160 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045470", "known_evidence_count": null, "matches": 839, "name": "Family of unknown function (DUF6495)", "partial_evidence_count": null, "pfam_id": "PF20105", "proteins": 839, "proteomes": 835, "short_name": "DUF6495", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20105", "structures": 0, "taxa": 1066, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 511, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Members of this family are all Proteobacteria. Several are annotated as being YjjA or YjjA-like, but this protein is uncharacterised.", "domain_architectures": 4, "interpro_id": "IPR019637", "known_evidence_count": null, "matches": 847, "name": "Protein of unknown function (DUF2501)", "partial_evidence_count": null, "pfam_id": "PF10696", "proteins": 838, "proteomes": 809, "short_name": "DUF2501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10696", "structures": 0, "taxa": 1101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 497, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as lipoproteins however this cannot be confirmed. Currently this family has no known function.", "domain_architectures": 2, "interpro_id": "IPR021431", "known_evidence_count": null, "matches": 842, "name": "Protein of unknown function (DUF3080)", "partial_evidence_count": null, "pfam_id": "PF11279", "proteins": 837, "proteomes": 827, "short_name": "DUF3080", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11279", "structures": 0, "taxa": 1110, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 488, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 357 and 735 amino acids in length. The family is found in association with [pfam:PF09925]. There is a single completely conserved residue K that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR025513", "known_evidence_count": null, "matches": 841, "name": "Domain of unknown function (DUF4401)", "partial_evidence_count": null, "pfam_id": "PF14351", "proteins": 837, "proteomes": 823, "short_name": "DUF4401", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14351", "structures": 0, "taxa": 1298, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 361, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function frequently found C-terminal in proteins from Actinomycetota. This domain is distantly related to [pfam:PF19374] (DUF5949). The gene SCO1756 encoding a protein with this domain was found to be more abundant in bacterioferritin mutants during morphological differentiation [[cite:PUB00163738]], although the specific function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061903", "known_evidence_count": null, "matches": 837, "name": "Domain of unknown function (DUF8842)", "partial_evidence_count": null, "pfam_id": "PF31237", "proteins": 837, "proteomes": 826, "short_name": "DUF8842", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31237", "structures": 0, "taxa": 888, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 495, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length. There are two completely conserved L residues that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR024980", "known_evidence_count": null, "matches": 836, "name": "Protein of unknown function (DUF3886)", "partial_evidence_count": null, "pfam_id": "PF13025", "proteins": 836, "proteomes": 835, "short_name": "DUF3886", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13025", "structures": 0, "taxa": 975, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 9, "interpro_id": "IPR046300", "known_evidence_count": null, "matches": 836, "name": "Family of unknown function (DUF6415)", "partial_evidence_count": null, "pfam_id": "PF19979", "proteins": 836, "proteomes": 449, "short_name": "DUF6415", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19979", "structures": 0, "taxa": 511, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins from Actinomycetes. STRING analysis indicates functional association with His_Phos_1 ([pfam:PF00300]) and AAA ATPase domains.", "domain_architectures": 1, "interpro_id": "IPR061905", "known_evidence_count": null, "matches": 836, "name": "Domain of unknown function (DUF8844)", "partial_evidence_count": null, "pfam_id": "PF31248", "proteins": 836, "proteomes": 832, "short_name": "DUF8844", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31248", "structures": 0, "taxa": 886, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 523, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. This family includes the B. subtilis YqhV protein which is found just upstream of the SpoIIIA operon, suggesting it may play a role in sporulation or its regulation [[cite:PUB00034563]]. The protein is composed of three hydrophobic alpha helices that may form transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR020390", "known_evidence_count": null, "matches": 835, "name": "Protein of unknown function (DUF2619)", "partial_evidence_count": null, "pfam_id": "PF10942", "proteins": 835, "proteomes": 825, "short_name": "DUF2619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10942", "structures": 0, "taxa": 1101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 531, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of around 100 residues locates at the C-terminal of some glycerophosphoryl diester phosphodiesterases and uncharacterized proteins in various Bacteroides and Prevotella species. The function of this domain is not yet clear, however, it is described as a putative glycerophosphoryl diester phosphodiesterase (PDBe:3i10).", "domain_architectures": 16, "interpro_id": "IPR032160", "known_evidence_count": null, "matches": 834, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16387", "proteins": 833, "proteomes": 689, "short_name": "DUF4996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16387", "structures": 1, "taxa": 1230, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 359, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001590) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the formicamycins A-M biosynthetic gene cluster from Streptomyces sp. KY5 [[cite:PUB00098929]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046245", "known_evidence_count": null, "matches": 833, "name": "Family of unknown function (DUF6278)", "partial_evidence_count": null, "pfam_id": "PF19794", "proteins": 833, "proteomes": 820, "short_name": "DUF6278", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19794", "structures": 0, "taxa": 922, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 651, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 106 and 131 amino acids in length. There are two conserved sequence motifs: SGE and VRF.", "domain_architectures": 10, "interpro_id": "IPR032756", "known_evidence_count": null, "matches": 832, "name": "Domain of unknown function (DUF4685)", "partial_evidence_count": null, "pfam_id": "PF15737", "proteins": 832, "proteomes": 389, "short_name": "DUF4685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15737", "structures": 0, "taxa": 1312, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 694, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a beta-sandwich. It contains highly conserved cysteine residues that are predicted to form a disulfide bond.", "domain_architectures": 9, "interpro_id": "IPR056145", "known_evidence_count": null, "matches": 843, "name": "Domain of unknown function (DUF7728)", "partial_evidence_count": null, "pfam_id": "PF24854", "proteins": 832, "proteomes": 771, "short_name": "DUF7728", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24854", "structures": 0, "taxa": 1465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 671, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal of Uncharacterised sequences from plants. It is associated with [pfam:PF00004] and may represent the AAA ATPase lid domain.", "domain_architectures": 37, "interpro_id": "IPR061565", "known_evidence_count": null, "matches": 835, "name": "Domain of unknown function (DUF8495)", "partial_evidence_count": null, "pfam_id": "PF29043", "proteins": 831, "proteomes": 395, "short_name": "DUF8495", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29043", "structures": 0, "taxa": 1139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 532, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into a beta-barrel with a PH-like topology.", "domain_architectures": 19, "interpro_id": "IPR056032", "known_evidence_count": null, "matches": 833, "name": "Domain of unknown function (DUF7613)", "partial_evidence_count": null, "pfam_id": "PF24588", "proteins": 830, "proteomes": 793, "short_name": "DUF7613", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24588", "structures": 0, "taxa": 1524, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 446, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 170-200 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046551", "known_evidence_count": null, "matches": 829, "name": "Family of unknown function (DUF6705)", "partial_evidence_count": null, "pfam_id": "PF20448", "proteins": 829, "proteomes": 317, "short_name": "DUF6705", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20448", "structures": 0, "taxa": 449, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 516, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 137 and 159 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046289", "known_evidence_count": null, "matches": 828, "name": "Family of unknown function (DUF6326)", "partial_evidence_count": null, "pfam_id": "PF19851", "proteins": 828, "proteomes": 768, "short_name": "DUF6326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19851", "structures": 0, "taxa": 1369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 681, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to adopt a globular structure composed of alpha-helices. This domain has a number of conserved positively changed residues that in the predicted structure define a large positively charged patch on the surface.", "domain_architectures": 11, "interpro_id": "IPR056041", "known_evidence_count": null, "matches": 829, "name": "Domain of unknown function (DUF7624)", "partial_evidence_count": null, "pfam_id": "PF24616", "proteins": 828, "proteomes": 804, "short_name": "DUF7624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24616", "structures": 0, "taxa": 1581, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 667, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants.", "domain_architectures": 11, "interpro_id": "IPR056070", "known_evidence_count": null, "matches": 830, "name": "Domain of unknown function (DUF7653)", "partial_evidence_count": null, "pfam_id": "PF24670", "proteins": 828, "proteomes": 356, "short_name": "DUF7653", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24670", "structures": 0, "taxa": 974, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 504, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021254", "known_evidence_count": null, "matches": 830, "name": "Protein of unknown function (DUF2806)", "partial_evidence_count": null, "pfam_id": "PF10987", "proteins": 827, "proteomes": 795, "short_name": "DUF2806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10987", "structures": 0, "taxa": 1424, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 386, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus and appears to be predominantly found in actinobacteria [[cite:PUB00098882]].", "domain_architectures": 1, "interpro_id": "IPR045728", "known_evidence_count": null, "matches": 827, "name": "Family of unknown function (DUF6082)", "partial_evidence_count": null, "pfam_id": "PF19560", "proteins": 827, "proteomes": 542, "short_name": "DUF6082", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19560", "structures": 0, "taxa": 694, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 500, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are likely to be phage derived. This domain forms a five stranded beta sheet with alpha helices packed on one face. Structure prediction suggests that this domain is likely to form a homodimeric structure.", "domain_architectures": 3, "interpro_id": "IPR046025", "known_evidence_count": null, "matches": 826, "name": "Family of unknown function (DUF5983) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF19419", "proteins": 826, "proteomes": 618, "short_name": "DUF5983", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19419", "structures": 0, "taxa": 1091, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 479, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001065) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the herboxidiene biosynthetic gene cluster from Streptomyces chromofuscus and appears to be predominantly found in Actinobacteria [[cite:PUB00098901]].", "domain_architectures": 2, "interpro_id": "IPR045730", "known_evidence_count": null, "matches": 828, "name": "Family of unknown function (DUF6084)", "partial_evidence_count": null, "pfam_id": "PF19562", "proteins": 826, "proteomes": 816, "short_name": "DUF6084", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19562", "structures": 0, "taxa": 1107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 480, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001580) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the ebelactone biosynthetic gene cluster from Kitasatospora aburaviensis [[cite:PUB00098891]]. This family appears to be predominantly found in actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR045647", "known_evidence_count": null, "matches": 826, "name": "Family of unknown function (DUF6401)", "partial_evidence_count": null, "pfam_id": "PF19939", "proteins": 826, "proteomes": 678, "short_name": "DUF6401", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19939", "structures": 0, "taxa": 804, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 782, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Archaeal domain of unknown function. Predicted to be an integral membrane protein with six transmembrane regions.", "domain_architectures": 1, "interpro_id": "IPR007254", "known_evidence_count": null, "matches": 825, "name": "Domain of unknown function (DUF373)", "partial_evidence_count": null, "pfam_id": "PF04123", "proteins": 825, "proteomes": 549, "short_name": "DUF373", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04123", "structures": 0, "taxa": 999, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 514, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins.", "domain_architectures": 1, "interpro_id": "IPR015017", "known_evidence_count": null, "matches": 825, "name": "Domain of unknown function (DUF1904)", "partial_evidence_count": null, "pfam_id": "PF08921", "proteins": 825, "proteomes": 762, "short_name": "DUF1904", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08921", "structures": 2, "taxa": 1111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 686, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family is specific to the Chordates. Some members also carry Kinesin-motor domains at their N-terminus, Kinesin, [pfam:PF00225].", "domain_architectures": 10, "interpro_id": "IPR029329", "known_evidence_count": null, "matches": 826, "name": "Domain of unknown function (DUF4472)", "partial_evidence_count": null, "pfam_id": "PF14739", "proteins": 825, "proteomes": 599, "short_name": "DUF4472", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14739", "structures": 0, "taxa": 2069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 566, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length. There is a single completely conserved residue F that may be functionally important. Recent structures show this domain has an NTF2 fold.", "domain_architectures": 1, "interpro_id": "IPR031977", "known_evidence_count": null, "matches": 824, "name": "Domain of unknown function (DUF4783)", "partial_evidence_count": null, "pfam_id": "PF16022", "proteins": 824, "proteomes": 810, "short_name": "DUF4783", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16022", "structures": 3, "taxa": 1142, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 523, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into a beta-barrel with a PH-like topology.", "domain_architectures": 16, "interpro_id": "IPR056031", "known_evidence_count": null, "matches": 824, "name": "Domain of unknown function (DUF7612)", "partial_evidence_count": null, "pfam_id": "PF24587", "proteins": 824, "proteomes": 791, "short_name": "DUF7612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24587", "structures": 0, "taxa": 1521, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 525, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into a beta-barrel with a PH-like topology.", "domain_architectures": 16, "interpro_id": "IPR056033", "known_evidence_count": null, "matches": 830, "name": "Domain of unknown function (DUF7614)", "partial_evidence_count": null, "pfam_id": "PF24589", "proteins": 824, "proteomes": 793, "short_name": "DUF7614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24589", "structures": 0, "taxa": 1522, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 543, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 260 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 7, "interpro_id": "IPR032315", "known_evidence_count": null, "matches": 851, "name": "Domain of unknown function (4846)", "partial_evidence_count": null, "pfam_id": "PF16138", "proteins": 823, "proteomes": 795, "short_name": "DUF4846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16138", "structures": 0, "taxa": 1281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 711, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This protein family is a domain of unknown function, which is found in eukaryotes. Proteins in this family are typically between 82 and 137 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR027953", "known_evidence_count": null, "matches": 822, "name": "Domain of unknown function (DUF4605)", "partial_evidence_count": null, "pfam_id": "PF15378", "proteins": 822, "proteomes": 523, "short_name": "DUF4605", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15378", "structures": 0, "taxa": 1857, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 686, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 197 and 268 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046591", "known_evidence_count": null, "matches": 862, "name": "Family of unknown function (DUF6649)", "partial_evidence_count": null, "pfam_id": "PF20354", "proteins": 822, "proteomes": 807, "short_name": "DUF6649", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20354", "structures": 0, "taxa": 1616, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 699, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains highly conserved cysteine residues that are predicted to form disulfide bonds. This domain is predicted to fold into an alpha/beta structure with an unique topology.", "domain_architectures": 9, "interpro_id": "IPR057194", "known_evidence_count": null, "matches": 861, "name": "Domain of unknown function (DUF7872)", "partial_evidence_count": null, "pfam_id": "PF25278", "proteins": 822, "proteomes": 135, "short_name": "DUF7872", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25278", "structures": 0, "taxa": 296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to fold into a beta-barrel with a PH-like topology.", "domain_architectures": 15, "interpro_id": "IPR056030", "known_evidence_count": null, "matches": 821, "name": "Domain of unknown function (DUF7611)", "partial_evidence_count": null, "pfam_id": "PF24586", "proteins": 821, "proteomes": 791, "short_name": "DUF7611", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24586", "structures": 0, "taxa": 1519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 683, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 70 amino acids in length.", "domain_architectures": 21, "interpro_id": "IPR031985", "known_evidence_count": null, "matches": 820, "name": "Domain of unknown function (DUF4787)", "partial_evidence_count": null, "pfam_id": "PF16029", "proteins": 819, "proteomes": 622, "short_name": "DUF4787", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16029", "structures": 0, "taxa": 2157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 469, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR043755", "known_evidence_count": null, "matches": 819, "name": "Family of unknown function (DUF5701)", "partial_evidence_count": null, "pfam_id": "PF18959", "proteins": 819, "proteomes": 806, "short_name": "DUF5701", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18959", "structures": 0, "taxa": 1092, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 215, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in RHS (rearrangement hotspot) family proteins and related polymorphic toxin proteins. It is often associated with ADP-ribosyltransferase toxin domains ([pfam:PF03496]) and RHS repeats ([pfam:PF03527]). In Escherichia coli K12, the domain is found in YibJ, which may be a pseudogene. The family is predominantly found in Actinomycetota, particularly Pseudonocardiaceae, and also in Proteobacteria. The function of this domain remains to be determined. Shows similarity to SteB family [pfam:PF29776] and [pfam:PF14252].", "domain_architectures": 185, "interpro_id": "IPR061677", "known_evidence_count": null, "matches": 968, "name": "Domain of unknown function (DUF8616)", "partial_evidence_count": null, "pfam_id": "PF30400", "proteins": 819, "proteomes": 632, "short_name": "DUF8616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30400", "structures": 0, "taxa": 1086, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to fold into a three helical bundle.", "domain_architectures": 43, "interpro_id": "IPR056062", "known_evidence_count": null, "matches": 818, "name": "Domain of unknown function (DUF7645)", "partial_evidence_count": null, "pfam_id": "PF24655", "proteins": 818, "proteomes": 371, "short_name": "DUF7645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24655", "structures": 0, "taxa": 1017, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 482, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are predicted to adopt alpha/beta structure with a central nine-stranded antiparallel beta-sheet with helices packed on both sides. The predicted structure has some partial structural similarity to bacterial S-adenosylmethionine decarboxylases.", "domain_architectures": 2, "interpro_id": "IPR053847", "known_evidence_count": null, "matches": 824, "name": "Family of unknown function (DUF6928)", "partial_evidence_count": null, "pfam_id": "PF21997", "proteins": 817, "proteomes": 732, "short_name": "DUF6928", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21997", "structures": 0, "taxa": 1024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 481, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are typically between 139 and 579 amino acids in length. There is a conserved sequence motif GPV. Some members of this family are hypothetical ABC transporter permeases.", "domain_architectures": 2, "interpro_id": "IPR046264", "known_evidence_count": null, "matches": 827, "name": "Family of unknown function (DUF6297)", "partial_evidence_count": null, "pfam_id": "PF19814", "proteins": 816, "proteomes": 801, "short_name": "DUF6297", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19814", "structures": 0, "taxa": 1035, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 694, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 10, "interpro_id": "IPR041404", "known_evidence_count": null, "matches": 1010, "name": "Family of unknown function (DUF5588)", "partial_evidence_count": null, "pfam_id": "PF17826", "proteins": 814, "proteomes": 562, "short_name": "DUF5588", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17826", "structures": 0, "taxa": 2022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001731) is described by MIBiG as an example of the following biosynthetic class, other (unspecified).", "domain_architectures": 1, "interpro_id": "IPR045999", "known_evidence_count": null, "matches": 813, "name": "Family of unknown function (DUF5955)", "partial_evidence_count": null, "pfam_id": "PF19380", "proteins": 813, "proteomes": 764, "short_name": "DUF5955", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19380", "structures": 0, "taxa": 837, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 485, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 30 to 78 amino acids in length. This protein has two conserved sequence motifs: WVA and CGH.", "domain_architectures": 5, "interpro_id": "IPR021948", "known_evidence_count": null, "matches": 812, "name": "Protein of unknown function (DUF3565)", "partial_evidence_count": null, "pfam_id": "PF12088", "proteins": 812, "proteomes": 790, "short_name": "DUF3565", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12088", "structures": 0, "taxa": 1194, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 356, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in Actinobacteria. Many of the family members are predicted to contain two trans-membrane domains.", "domain_architectures": 1, "interpro_id": "IPR020246", "known_evidence_count": null, "matches": 812, "name": "Family of unknown function (DUF5326)", "partial_evidence_count": null, "pfam_id": "PF17260", "proteins": 812, "proteomes": 806, "short_name": "DUF5326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17260", "structures": 0, "taxa": 859, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 706, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 45 and 100 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR031389", "known_evidence_count": null, "matches": 811, "name": "Domain of unknown function (DUF4665)", "partial_evidence_count": null, "pfam_id": "PF15679", "proteins": 811, "proteomes": 500, "short_name": "DUF4665", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15679", "structures": 0, "taxa": 1892, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 528, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a likely integral membrane protein. These proteins are composed of three alpha helices followed by a short beta hairpin. This family is called DUF6867. Proteins in this family are found in Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR049201", "known_evidence_count": null, "matches": 811, "name": "Domain of unknown function (DUF6867)", "partial_evidence_count": null, "pfam_id": "PF21741", "proteins": 811, "proteomes": 791, "short_name": "DUF6867", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21741", "structures": 0, "taxa": 1134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 475, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR021813", "known_evidence_count": null, "matches": 810, "name": "Protein of unknown function (DUF3392)", "partial_evidence_count": null, "pfam_id": "PF11872", "proteins": 810, "proteomes": 807, "short_name": "DUF3392", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11872", "structures": 0, "taxa": 1017, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 661, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 167 and 308 amino acids in length. The exact function of this protein remains unknown, but it is thought to be a single-pass membrane protein. This family contains many highly conserved cysteine residues.", "domain_architectures": 11, "interpro_id": "IPR027888", "known_evidence_count": null, "matches": 913, "name": "Domain of unknown function (DUF4501)", "partial_evidence_count": null, "pfam_id": "PF14946", "proteins": 810, "proteomes": 440, "short_name": "DUF4501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14946", "structures": 0, "taxa": 1508, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 402, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001848) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the diazaquinomycin H biosynthetic gene cluster from Micromonospora sp. B006 [[cite:PUB00098974]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR045770", "known_evidence_count": null, "matches": 811, "name": "Family of unknown function (DUF6223)", "partial_evidence_count": null, "pfam_id": "PF19733", "proteins": 810, "proteomes": 738, "short_name": "DUF6223", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19733", "structures": 0, "taxa": 959, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 689, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to adopt a globular alpha/ beta structure containing several disulfide bonds made by highly conserved cysteine residues.", "domain_architectures": 16, "interpro_id": "IPR056698", "known_evidence_count": null, "matches": 837, "name": "Domain of unknown function (DUF7796)", "partial_evidence_count": null, "pfam_id": "PF25072", "proteins": 810, "proteomes": 393, "short_name": "DUF7796", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25072", "structures": 0, "taxa": 1158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 611, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 100 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR022203", "known_evidence_count": null, "matches": 811, "name": "Protein of unknown function (DUF3727)", "partial_evidence_count": null, "pfam_id": "PF12527", "proteins": 809, "proteomes": 624, "short_name": "DUF3727", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12527", "structures": 0, "taxa": 1788, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in plants and cyanobacteria. Proteins in this family are typically between 108 and 202 amino acids in length.", "domain_architectures": 16, "interpro_id": "IPR040003", "known_evidence_count": null, "matches": 811, "name": "Family of unknown function (DUF6825)", "partial_evidence_count": null, "pfam_id": "PF20711", "proteins": 809, "proteomes": 603, "short_name": "DUF6825", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20711", "structures": 0, "taxa": 1675, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 532, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a TIM-barrel structure. It shares detectable similarity with Mycobacterium tuberculosis Indole-3-glycerol phosphate synthase (TrpC).", "domain_architectures": 1, "interpro_id": "IPR057238", "known_evidence_count": null, "matches": 809, "name": "Domain of unknown function (DUF7916)", "partial_evidence_count": null, "pfam_id": "PF25509", "proteins": 809, "proteomes": 720, "short_name": "DUF7916", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25509", "structures": 0, "taxa": 1300, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in Actinobacteria, and is approximately 140 amino acids in length. The family is found in association with [pfam:PF14378].", "domain_architectures": 3, "interpro_id": "IPR045977", "known_evidence_count": null, "matches": 808, "name": "Domain of unknown function (DUF5933)", "partial_evidence_count": null, "pfam_id": "PF19356", "proteins": 808, "proteomes": 608, "short_name": "DUF5933", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19356", "structures": 0, "taxa": 685, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 532, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes. Proteins in this family are typically between 332 and 351 amino acids in length. There are several conserved Gly residues and two conserved motifs, AQ and GW.", "domain_architectures": 1, "interpro_id": "IPR046495", "known_evidence_count": null, "matches": 808, "name": "Family of unknown function (DUF6588)", "partial_evidence_count": null, "pfam_id": "PF20230", "proteins": 808, "proteomes": 737, "short_name": "DUF6588", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20230", "structures": 0, "taxa": 1098, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 720, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This family represents a domain of unknown function located between the Transcription factor IIIC subunit delta N-term ([pfam:PF12657]) and the Putative zinc-finger of transcription factor IIIC complex ([pfam:PF12660]) within the transcription Factor IIIC 90 kDa subunit (TFIIIC-delta/TFIIIC90, also known as general transcription factor 3C polypeptide 4). TFIIIC is a multisubunit complex that directly recognises promoter elements and recruits TFIIIB and RNA polymerase III, being absolutely required for RNA polymerase III transcription. TFIIIC90 has an intrinsic histone acetyltransferase activity with a substrate specificity for histone H3 [[cite:PUB00056254]]. This domain is likely to be involved in the interaction with other components of the TFIIIC complex.", "domain_architectures": 8, "interpro_id": "IPR045803", "known_evidence_count": null, "matches": 808, "name": "Domain of unknown function (DUF5921)", "partial_evidence_count": null, "pfam_id": "PF19336", "proteins": 807, "proteomes": 656, "short_name": "DUF5921", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19336", "structures": 3, "taxa": 2039, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 661, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in uncharacterised fungal proteins. This domain contains a nucleotide-binding like fold, typical of ATPases. This domain forms an alpha/beta canonical fold.", "domain_architectures": 17, "interpro_id": "IPR059384", "known_evidence_count": null, "matches": 809, "name": "Domain of unknown function (DUF8340)", "partial_evidence_count": null, "pfam_id": "PF27033", "proteins": 807, "proteomes": 327, "short_name": "DUF8340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27033", "structures": 0, "taxa": 929, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 393, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several phage and bacterial proteins of unknown function. Computational analysis involving sequence, predicted structure and genomic context suggests that these proteins may be endonucleases which function in phage genome segregation, or the repair of double-stranded breaks introduced during either this process or DNA replication [[cite:PUB00020736]].", "domain_architectures": 2, "interpro_id": "IPR009414", "known_evidence_count": null, "matches": 807, "name": "Protein of unknown function (DUF1064)", "partial_evidence_count": null, "pfam_id": "PF06356", "proteins": 806, "proteomes": 720, "short_name": "DUF1064", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06356", "structures": 0, "taxa": 1566, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 690, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 180 amino acids in length. There is a conserved EALT sequence motif.", "domain_architectures": 5, "interpro_id": "IPR027884", "known_evidence_count": null, "matches": 841, "name": "Domain of unknown function (DUF4614)", "partial_evidence_count": null, "pfam_id": "PF15391", "proteins": 806, "proteomes": 545, "short_name": "DUF4614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15391", "structures": 0, "taxa": 1949, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 358, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 115 and 135 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR045436", "known_evidence_count": null, "matches": 806, "name": "Family of unknown function (DUF6507)", "partial_evidence_count": null, "pfam_id": "PF20117", "proteins": 806, "proteomes": 490, "short_name": "DUF6507", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20117", "structures": 0, "taxa": 629, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 454, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold onto an alpha-helical bundle consisting of five alpha-helices. It is frequently found in combination with [pfam:PF13387] and [pfam:PF25222].", "domain_architectures": 3, "interpro_id": "IPR057164", "known_evidence_count": null, "matches": 806, "name": "Domain of unknown function (DUF7842)", "partial_evidence_count": null, "pfam_id": "PF25224", "proteins": 806, "proteomes": 790, "short_name": "DUF7842", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25224", "structures": 0, "taxa": 1171, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 560, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. It is found in bacteria, and is approximately 50 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025470", "known_evidence_count": null, "matches": 805, "name": "Domain of unknown function (DUF4321)", "partial_evidence_count": null, "pfam_id": "PF14209", "proteins": 805, "proteomes": 800, "short_name": "DUF4321", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14209", "structures": 0, "taxa": 1336, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 492, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is present at the N-terminal of uncharacterised proteins predominantly found in Firmicutes, which also contain a FHA (Forkhead-associated) domain. It is approximately 160 amino acids in length and contains a conserved sequence YxI/V motif and a Proline conserved residue.", "domain_architectures": 6, "interpro_id": "IPR045962", "known_evidence_count": null, "matches": 805, "name": "Domain of unknown function (DUF6382)", "partial_evidence_count": null, "pfam_id": "PF19909", "proteins": 805, "proteomes": 717, "short_name": "DUF6382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19909", "structures": 0, "taxa": 1026, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 452, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised bacterial proteins. This domain is about 60 amino acids in length and contains the conserved motifs GPY, GxxC and GCxC. These conserved cysteine residues and the fact that this domain has overlaps with families in clan CL0172 suggest that it is related to thioredoxins and it is likely in thiol-disulfide isomerases.", "domain_architectures": 1, "interpro_id": "IPR045494", "known_evidence_count": null, "matches": 805, "name": "Domain of unknown function (DUF6436)", "partial_evidence_count": null, "pfam_id": "PF20029", "proteins": 805, "proteomes": 760, "short_name": "DUF6436", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20029", "structures": 0, "taxa": 1020, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 144 and 171 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046585", "known_evidence_count": null, "matches": 820, "name": "Family of unknown function (DUF6643)", "partial_evidence_count": null, "pfam_id": "PF20348", "proteins": 805, "proteomes": 798, "short_name": "DUF6643", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20348", "structures": 0, "taxa": 848, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 654, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised plant proteins. They are predicted to adopt a non-compact structure composed of alpha-helices.", "domain_architectures": 8, "interpro_id": "IPR057196", "known_evidence_count": null, "matches": 820, "name": "Family of unknown function (DUF7874)", "partial_evidence_count": null, "pfam_id": "PF25284", "proteins": 803, "proteomes": 339, "short_name": "DUF7874", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25284", "structures": 0, "taxa": 942, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 676, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes.", "domain_architectures": 15, "interpro_id": "IPR031643", "known_evidence_count": null, "matches": 879, "name": "Domain of unknown function (DUF4708)", "partial_evidence_count": null, "pfam_id": "PF15813", "proteins": 801, "proteomes": 595, "short_name": "DUF4708", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15813", "structures": 0, "taxa": 2169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into an array of four alpha-helices.", "domain_architectures": 25, "interpro_id": "IPR057235", "known_evidence_count": null, "matches": 837, "name": "Domain of unknown function (DUF7913)", "partial_evidence_count": null, "pfam_id": "PF25500", "proteins": 801, "proteomes": 340, "short_name": "DUF7913", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25500", "structures": 0, "taxa": 942, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 68 and 82 amino acids in length. There are two conserved sequence motifs: GGP and YEHF.", "domain_architectures": 4, "interpro_id": "IPR046030", "known_evidence_count": null, "matches": 800, "name": "Family of unknown function (DUF5988)", "partial_evidence_count": null, "pfam_id": "PF19450", "proteins": 800, "proteomes": 637, "short_name": "DUF5988", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19450", "structures": 0, "taxa": 758, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 480, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045448", "known_evidence_count": null, "matches": 800, "name": "Family of unknown function (DUF6500)", "partial_evidence_count": null, "pfam_id": "PF20110", "proteins": 800, "proteomes": 790, "short_name": "DUF6500", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20110", "structures": 0, "taxa": 1221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 462, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins appear to be structurally distantly related to TraK proteins suggesting they have an important tole in a type IV secretion system likely involved in conjugation.", "domain_architectures": 4, "interpro_id": "IPR021844", "known_evidence_count": null, "matches": 800, "name": "Protein of unknown function (DUF3438)", "partial_evidence_count": null, "pfam_id": "PF11920", "proteins": 799, "proteomes": 628, "short_name": "DUF3438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11920", "structures": 0, "taxa": 1068, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 467, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains hypothetical proteins of unknown function that are approximately 120 residues long. Family members include eukaryotic and bacterial proteins. Members of this family are predicted to homodimerise by AlphaFold prediction.", "domain_architectures": 2, "interpro_id": "IPR009666", "known_evidence_count": null, "matches": 797, "name": "Protein of unknown function (DUF1257)", "partial_evidence_count": null, "pfam_id": "PF06868", "proteins": 797, "proteomes": 360, "short_name": "DUF1257", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06868", "structures": 0, "taxa": 1030, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 475, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045385", "known_evidence_count": null, "matches": 797, "name": "Family of unknown function (DUF6526)", "partial_evidence_count": null, "pfam_id": "PF20136", "proteins": 797, "proteomes": 788, "short_name": "DUF6526", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20136", "structures": 0, "taxa": 988, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 758, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in uncharacterised proteins from archaea.", "domain_architectures": 3, "interpro_id": "IPR055769", "known_evidence_count": null, "matches": 797, "name": "Domain of unknown function (DUF7345)", "partial_evidence_count": null, "pfam_id": "PF24036", "proteins": 797, "proteomes": 289, "short_name": "DUF7345", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24036", "structures": 0, "taxa": 472, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 665, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains a number of highly conserved cysteine residues some of which may be involved in metal coordination.", "domain_architectures": 7, "interpro_id": "IPR057193", "known_evidence_count": null, "matches": 820, "name": "Domain of unknown function (DUF7871)", "partial_evidence_count": null, "pfam_id": "PF25277", "proteins": 797, "proteomes": 784, "short_name": "DUF7871", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25277", "structures": 0, "taxa": 1579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 447, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length. There are two completely conserved residues (A and Y) that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR024987", "known_evidence_count": null, "matches": 802, "name": "Protein of unknown function (DUF3889)", "partial_evidence_count": null, "pfam_id": "PF13028", "proteins": 796, "proteomes": 638, "short_name": "DUF3889", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13028", "structures": 1, "taxa": 752, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 681, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 117 and 253 amino acids in length.", "domain_architectures": 11, "interpro_id": "IPR028019", "known_evidence_count": null, "matches": 804, "name": "Domain of unknown function (DUF4508)", "partial_evidence_count": null, "pfam_id": "PF14969", "proteins": 796, "proteomes": 655, "short_name": "DUF4508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14969", "structures": 0, "taxa": 2404, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 451, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]].", "domain_architectures": 2, "interpro_id": "IPR024215", "known_evidence_count": null, "matches": 793, "name": "Protein of unknown function (DUF3847)", "partial_evidence_count": null, "pfam_id": "PF12958", "proteins": 793, "proteomes": 316, "short_name": "DUF3847", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12958", "structures": 0, "taxa": 593, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 637, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain has a restriction endonuclease-like fold. The function of these proteins is unknown. Some members of the family are annotated as nucleoporins.", "domain_architectures": 16, "interpro_id": "IPR055528", "known_evidence_count": null, "matches": 794, "name": "Domain of unknown function (DUF7102)", "partial_evidence_count": null, "pfam_id": "PF23394", "proteins": 793, "proteomes": 781, "short_name": "DUF7102", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23394", "structures": 0, "taxa": 1591, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 595, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and eukaryotes, and is typically between 288 and 306 amino acids in length.", "domain_architectures": 53, "interpro_id": "IPR031962", "known_evidence_count": null, "matches": 849, "name": "Domain of unknown function (DUF4781)", "partial_evidence_count": null, "pfam_id": "PF16013", "proteins": 792, "proteomes": 356, "short_name": "DUF4781", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16013", "structures": 0, "taxa": 1142, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 534, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 370 residues in length and is mainly found in various species, such as Shewanella, Rheinheimera, Saccharophagus, Leptolyngbya and so on. It contains serveral TPR repeat-containing proteins. The function of this family is unknown.", "domain_architectures": 49, "interpro_id": "IPR017481", "known_evidence_count": null, "matches": 819, "name": "Domain of unknown function (DUF4915)", "partial_evidence_count": null, "pfam_id": "PF16261", "proteins": 792, "proteomes": 652, "short_name": "DUF4915", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16261", "structures": 0, "taxa": 1488, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 578, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 201 and 257 amino acids in length. Some proteins also contains an iron-sulfur cluster.", "domain_architectures": 6, "interpro_id": "IPR024264", "known_evidence_count": null, "matches": 791, "name": "Domain of unknown function (DUF3786)", "partial_evidence_count": null, "pfam_id": "PF12654", "proteins": 791, "proteomes": 300, "short_name": "DUF3786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12654", "structures": 0, "taxa": 652, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 598, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Protein of unknown function found in a cyanobacterium, and the chloroplasts of algae.", "domain_architectures": 25, "interpro_id": "IPR007570", "known_evidence_count": null, "matches": 808, "name": "Protein of unknown function (DUF561)", "partial_evidence_count": null, "pfam_id": "PF04481", "proteins": 790, "proteomes": 578, "short_name": "DUF561", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04481", "structures": 0, "taxa": 1709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 427, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 50 amino acids in length. The protein is likely to be of phage origin and is found as protein Gp02 [swissprot:C8CLF5] in the Xylella phage Xfas53 [[cite:PUB00109600]].", "domain_architectures": 5, "interpro_id": "IPR025319", "known_evidence_count": null, "matches": 790, "name": "Domain of unknown function (DUF4224)", "partial_evidence_count": null, "pfam_id": "PF13986", "proteins": 790, "proteomes": 653, "short_name": "DUF4224", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13986", "structures": 0, "taxa": 1116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 495, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of predicted integral membrane proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046077", "known_evidence_count": null, "matches": 790, "name": "Family of unknown function (DUF6095)", "partial_evidence_count": null, "pfam_id": "PF19589", "proteins": 790, "proteomes": 787, "short_name": "DUF6095", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19589", "structures": 0, "taxa": 998, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 459, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR021364", "known_evidence_count": null, "matches": 789, "name": "Protein of unknown function (DUF2857)", "partial_evidence_count": null, "pfam_id": "PF11198", "proteins": 789, "proteomes": 631, "short_name": "DUF2857", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11198", "structures": 0, "taxa": 1111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 752, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of uncharacterised archaeal proteins predicted to show an all-beta barrel fold, including HVO_1607 ([swissprot:D4GZ36]). They contain a highly conserved motif Y/HVxPxP.", "domain_architectures": 4, "interpro_id": "IPR061654", "known_evidence_count": null, "matches": 787, "name": "Family of unknown function (DUF8593)", "partial_evidence_count": null, "pfam_id": "PF29877", "proteins": 786, "proteomes": 203, "short_name": "DUF8593", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29877", "structures": 0, "taxa": 333, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 508, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised proteins predominantly from Alphaproteobacteria but it is also present in some sequences from eukaryotes. This domain is approximately 75 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045531", "known_evidence_count": null, "matches": 785, "name": "Domain of unknown function (DUF6468)", "partial_evidence_count": null, "pfam_id": "PF20072", "proteins": 785, "proteomes": 755, "short_name": "DUF6468", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20072", "structures": 0, "taxa": 1163, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 527, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Methanosarcinaceae.", "domain_architectures": 4, "interpro_id": "IPR020271", "known_evidence_count": null, "matches": 785, "name": "Protein of unknown function (DUF2683)", "partial_evidence_count": null, "pfam_id": "PF10884", "proteins": 784, "proteomes": 471, "short_name": "DUF2683", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10884", "structures": 0, "taxa": 612, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 482, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in flavobacteria, and is approximately 220 amino acids in length. The family is found to the C-terminus of [pfam:PF04326]. Proteins in this family vary in length from 377 to 380 amino acids.", "domain_architectures": 2, "interpro_id": "IPR045973", "known_evidence_count": null, "matches": 784, "name": "Domain of unknown function (DUF5929)", "partial_evidence_count": null, "pfam_id": "PF19351", "proteins": 784, "proteomes": 778, "short_name": "DUF5929", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19351", "structures": 0, "taxa": 953, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 515, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 120 residues found in predicted integral membrane proteins. Some members are annotated as NnrS family proteins. According to STRING, this domain co-occurs with DUF2249 ([pfam:PF10006]). This family is found predominantly in Actinomycetota and Pseudomonadota. The function of this domain remains to be determined.", "domain_architectures": 9, "interpro_id": "IPR061805", "known_evidence_count": null, "matches": 786, "name": "Domain of unknown function (DUF8744)", "partial_evidence_count": null, "pfam_id": "PF30795", "proteins": 784, "proteomes": 766, "short_name": "DUF8744", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30795", "structures": 0, "taxa": 1385, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 749, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043902", "known_evidence_count": null, "matches": 783, "name": "Family of unknown function (DUF5786)", "partial_evidence_count": null, "pfam_id": "PF19099", "proteins": 783, "proteomes": 282, "short_name": "DUF5786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19099", "structures": 0, "taxa": 440, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 499, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This is a probable HAD-like (haloalkanoate dehalogenase) domain found in bacterial phosphoserine phosphatases.", "domain_architectures": 3, "interpro_id": "IPR041449", "known_evidence_count": null, "matches": 782, "name": "Domain of unknown function (DUF5609)", "partial_evidence_count": null, "pfam_id": "PF18429", "proteins": 782, "proteomes": 782, "short_name": "DUF5609", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18429", "structures": 1, "taxa": 1069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 641, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The domain described by this entry is located towards the N-terminal in putative transmembrane and uncharacterised proteins found in plants. It is predicted to adopt a C2 fold. C2 domains are membrane-binding modules that share a common overall fold: a single compact greek-key motif organised as an eight-stranded anti-parallel beta-sandwich consisting of a pair of four-stranded beta-sheets [[cite:PUB00160608]].", "domain_architectures": 13, "interpro_id": "IPR057713", "known_evidence_count": null, "matches": 801, "name": "Domain of unknown function (DUF7953)", "partial_evidence_count": null, "pfam_id": "PF25829", "proteins": 782, "proteomes": 360, "short_name": "DUF7953", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25829", "structures": 0, "taxa": 1018, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 498, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 90 amino acids in length. This protein has a conserved EIVDK sequence motif.", "domain_architectures": 1, "interpro_id": "IPR021951", "known_evidence_count": null, "matches": 781, "name": "Protein of unknown function (DUF3567)", "partial_evidence_count": null, "pfam_id": "PF12091", "proteins": 781, "proteomes": 779, "short_name": "DUF3567", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12091", "structures": 0, "taxa": 943, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 508, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal bacterial immunoglobulin-like (Big) domain of approximately 120 residues. The domain is found C-terminal to the M14 carboxypeptidase catalytic domain ([pfam:PF00246]). This family is found predominantly in Bacteroidota, particularly Cytophagales and Sphingobacteriales. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061792", "known_evidence_count": null, "matches": 781, "name": "Domain of unknown function (DUF8731)", "partial_evidence_count": null, "pfam_id": "PF30777", "proteins": 781, "proteomes": 487, "short_name": "DUF8731", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30777", "structures": 0, "taxa": 979, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 475, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The 3cjl structure is likely a representative of a new fold with some resemblance to 3-helical bundle folds such as the serum albumin-like fold of SCOP. No significant hits reported by a Dali search. This protein is the first structural representative of a small (about 60 proteins) family of proteins that are found among proteo- and enterobacteria (REF http://www.topsan.org/Proteins/JCSG/3CJL).", "domain_architectures": 1, "interpro_id": "IPR024476", "known_evidence_count": null, "matches": 780, "name": "Domain of Unknown Function with PDB structure (DUF3861)", "partial_evidence_count": null, "pfam_id": "PF12977", "proteins": 780, "proteomes": 761, "short_name": "DUF3861", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12977", "structures": 1, "taxa": 1193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 506, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is only found in bacteria. Proteins in this family vary in length from 96 to 160 amino acids.", "domain_architectures": 3, "interpro_id": "IPR021769", "known_evidence_count": null, "matches": 785, "name": "Domain of unknown function (DUF3331)", "partial_evidence_count": null, "pfam_id": "PF11811", "proteins": 779, "proteomes": 220, "short_name": "DUF3331", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11811", "structures": 0, "taxa": 242, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 640, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Fungi. It has a detectable similarity to known galactose-binding domains, in particular to the C-terminal domain of Bacillus sp. alkaline serine protease, and is predicted to adopt similar structure.", "domain_architectures": 23, "interpro_id": "IPR056012", "known_evidence_count": null, "matches": 779, "name": "Domain of unknown function (DUF7590)", "partial_evidence_count": null, "pfam_id": "PF24503", "proteins": 778, "proteomes": 764, "short_name": "DUF7590", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24503", "structures": 0, "taxa": 1516, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 466, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR021300", "known_evidence_count": null, "matches": 777, "name": "Protein of unknown function (DUF2859)", "partial_evidence_count": null, "pfam_id": "PF11072", "proteins": 777, "proteomes": 611, "short_name": "DUF2859", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11072", "structures": 0, "taxa": 1025, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 441, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 30 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR022109", "known_evidence_count": null, "matches": 777, "name": "Protein of unknown function (DUF3649)", "partial_evidence_count": null, "pfam_id": "PF12365", "proteins": 777, "proteomes": 699, "short_name": "DUF3649", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12365", "structures": 0, "taxa": 957, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 668, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family of vertebrate proteins lies to the C-terminus of Ubiquitin-specific peptidase-like protein family peptidase_C98, [pfam:PF15499]. It might be acting as the exosite for the peptidase.", "domain_architectures": 5, "interpro_id": "IPR029388", "known_evidence_count": null, "matches": 789, "name": "Domain of unknown function (DUF4650)", "partial_evidence_count": null, "pfam_id": "PF15509", "proteins": 776, "proteomes": 567, "short_name": "DUF4650", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15509", "structures": 0, "taxa": 1715, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 574, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This domain is found in bacteria, archaea and a few lower eukaryotes species. There are two conserved sequence motifs: LDP and DHA. Many members of this family have been annotated as dihydropteroate synthases, however no experimental evidence can be found for this and [swissprot:Q57571] has been shown not to possess dihydropteroate synthase activity [[cite:PUB00057368]]. In bacteria, this domain is found in predicted conflict systems that also encode genes for an active Thymidylate synthase and a pterin-dependent one-carbon carrier (MtrA domain). This system is predicted to deplete virally generated nucleotides and replace them with a nucleotide that restricts invasive DNA or protects host DNA [[cite:PUB00155486]].", "domain_architectures": 16, "interpro_id": "IPR025595", "known_evidence_count": null, "matches": 781, "name": "PterinBD-DUF4346", "partial_evidence_count": null, "pfam_id": "PF14251", "proteins": 775, "proteomes": 668, "short_name": "PterinBD-DUF4346", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14251", "structures": 0, "taxa": 1712, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 540, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 170 residues in length and is mainly found in various Parabacteroides and Bacteroides species. The function of this family is unknown.", "domain_architectures": 11, "interpro_id": "IPR032269", "known_evidence_count": null, "matches": 788, "name": "Domain of unknown function (DUF4833)", "partial_evidence_count": null, "pfam_id": "PF16117", "proteins": 774, "proteomes": 587, "short_name": "DUF4833", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16117", "structures": 0, "taxa": 929, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 442, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of bacterial domains of unknown function.", "domain_architectures": 12, "interpro_id": "IPR054254", "known_evidence_count": null, "matches": 775, "name": "Domain of unknown function (DUF6985)", "partial_evidence_count": null, "pfam_id": "PF22481", "proteins": 774, "proteomes": 665, "short_name": "DUF6985", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22481", "structures": 0, "taxa": 1296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 468, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR046155", "known_evidence_count": null, "matches": 774, "name": "Family of unknown function (DUF6157)", "partial_evidence_count": null, "pfam_id": "PF19654", "proteins": 773, "proteomes": 764, "short_name": "DUF6157", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19654", "structures": 0, "taxa": 1231, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 525, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046735", "known_evidence_count": null, "matches": 773, "name": "Family of unknown function (DUF6627)", "partial_evidence_count": null, "pfam_id": "PF20332", "proteins": 773, "proteomes": 726, "short_name": "DUF6627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20332", "structures": 0, "taxa": 1201, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 521, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and eukaryotes, and is typically between 161 and 175 amino acids in length. There is a conserved WGE sequence motif.", "domain_architectures": 36, "interpro_id": "IPR032379", "known_evidence_count": null, "matches": 776, "name": "Domain of unknown function (DUF4874)", "partial_evidence_count": null, "pfam_id": "PF16173", "proteins": 772, "proteomes": 602, "short_name": "DUF4874", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16173", "structures": 0, "taxa": 1354, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 521, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in bacterial proteins either as a standalone domain or in combination with an HTH domain that resembles lambda C1 repressor DNA-binding domain. This family has a partial sequence similarity to the RAP1 C-terminal (RCT) domain.", "domain_architectures": 3, "interpro_id": "IPR053830", "known_evidence_count": null, "matches": 771, "name": "Family of unknown function (DUF6922)", "partial_evidence_count": null, "pfam_id": "PF21956", "proteins": 771, "proteomes": 608, "short_name": "DUF6922", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21956", "structures": 0, "taxa": 1069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 447, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR021548", "known_evidence_count": null, "matches": 770, "name": "Protein of unknown function (DUF2895)", "partial_evidence_count": null, "pfam_id": "PF11444", "proteins": 770, "proteomes": 615, "short_name": "DUF2895", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11444", "structures": 0, "taxa": 1032, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 725, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in uncharacterised plant sequences. This domain may have a beta-propeller structure.", "domain_architectures": 26, "interpro_id": "IPR056016", "known_evidence_count": null, "matches": 792, "name": "Domain of unknown function (DUF7595)", "partial_evidence_count": null, "pfam_id": "PF24523", "proteins": 770, "proteomes": 39, "short_name": "DUF7595", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24523", "structures": 0, "taxa": 135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 456, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 4, "interpro_id": "IPR025233", "known_evidence_count": null, "matches": 769, "name": "Domain of unknown function (DUF4176)", "partial_evidence_count": null, "pfam_id": "PF13780", "proteins": 768, "proteomes": 428, "short_name": "DUF4176", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13780", "structures": 2, "taxa": 745, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 416, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in the N-terminal region of a group of bacterial proteins, including Haloperoxidase from Muricauda lutaonensis. In this protein, this domain is found associated to [pfam:PF01569]. Its specific function is unknown.", "domain_architectures": 35, "interpro_id": "IPR049283", "known_evidence_count": null, "matches": 769, "name": "Domain of unknown function (DUF6851)", "partial_evidence_count": null, "pfam_id": "PF21167", "proteins": 768, "proteomes": 607, "short_name": "DUF6851", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21167", "structures": 4, "taxa": 1239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 140 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025129", "known_evidence_count": null, "matches": 767, "name": "Domain of unknown function (DUF4055)", "partial_evidence_count": null, "pfam_id": "PF13264", "proteins": 767, "proteomes": 724, "short_name": "DUF4055", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13264", "structures": 3, "taxa": 1545, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 735, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a probable zinc finger domain found in uncharacterised plant proteins. This domain shares similarity with GRF zinc fingers. It has highly conserved cysteine residues in equivalent positions but is has a large insertion located between the third and the fourth potential zinc coordinating residue.", "domain_architectures": 16, "interpro_id": "IPR061809", "known_evidence_count": null, "matches": 772, "name": "Domain of unknown function (DUF8748)", "partial_evidence_count": null, "pfam_id": "PF30834", "proteins": 767, "proteomes": 47, "short_name": "DUF8748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30834", "structures": 0, "taxa": 196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 523, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 180 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025374", "known_evidence_count": null, "matches": 766, "name": "Domain of unknown function (DUF4364)", "partial_evidence_count": null, "pfam_id": "PF14277", "proteins": 766, "proteomes": 762, "short_name": "DUF4364", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14277", "structures": 0, "taxa": 1251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 531, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, archaea and eukaryotes, and is typically between 75 and 104 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR025524", "known_evidence_count": null, "matches": 767, "name": "Domain of unknown function (DUF4412)", "partial_evidence_count": null, "pfam_id": "PF14371", "proteins": 766, "proteomes": 673, "short_name": "DUF4412", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14371", "structures": 0, "taxa": 1314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 377, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 86 and 118 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046165", "known_evidence_count": null, "matches": 765, "name": "Family of unknown function (DUF6167)", "partial_evidence_count": null, "pfam_id": "PF19664", "proteins": 765, "proteomes": 763, "short_name": "DUF6167", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19664", "structures": 0, "taxa": 896, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 656, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This cysteine-rich domain is functionally uncharacterised and is found in eukaryotes. Proteins with this domain are typically between 194 and 289 amino acids in length. AlphaFold structural models reveal a C-terminal beta-strand, usually located after the DUF4796_C domain ([pfam:PF16044]). This beta-strand (not included in this entry's seed alignment) contributes to the beta-sheet structure within this domain.", "domain_architectures": 12, "interpro_id": "IPR053922", "known_evidence_count": null, "matches": 764, "name": "DUF4796 N-terminal", "partial_evidence_count": null, "pfam_id": "PF22795", "proteins": 764, "proteomes": 687, "short_name": "DUF4796_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22795", "structures": 0, "taxa": 2543, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 468, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in bacteria is functionally uncharacterised. Proteins in this family are approximately 60 amino acids in length and they are predicted to have a coiled-coil structure. There are two conserved motifs: KxLxxxY and EA.", "domain_architectures": 1, "interpro_id": "IPR045493", "known_evidence_count": null, "matches": 763, "name": "Family of unknown function (DUF6435)", "partial_evidence_count": null, "pfam_id": "PF20027", "proteins": 763, "proteomes": 752, "short_name": "DUF6435", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20027", "structures": 0, "taxa": 1126, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 724, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058328", "known_evidence_count": null, "matches": 763, "name": "Family of unknown function (DUF8015)", "partial_evidence_count": null, "pfam_id": "PF26047", "proteins": 763, "proteomes": 278, "short_name": "DUF8015", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26047", "structures": 0, "taxa": 447, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 505, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 120 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009867", "known_evidence_count": null, "matches": 762, "name": "Protein of unknown function (DUF1422)", "partial_evidence_count": null, "pfam_id": "PF07226", "proteins": 762, "proteomes": 761, "short_name": "DUF1422", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07226", "structures": 0, "taxa": 1051, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 532, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This group of 2H-phosphodiesterases comprises a single family typified by the protein mlr3352 from M.loti. Members are also present in various alpha-proteobacteria, Synechocystis, Streptococcus and Chilo iridescent virus. The presence of a member of this predominantly bacterial group in a large eukaryotic DNA virus represents a potential case of horizontal transfer from a bacterial source into a virus. Several proteins of bacterial origin have been noticed in the insect viruses (L.M.Iyer, E.V.Koonin and L.Aravind, unpublished observations and these appear to have been acquired from endo-symbiotic or parasitic bacteria that share the same host cells with the viruses. Presence of 2H proteins in the proteomes of large DNA viruses (e.g. T4 57B protein and the Fowl-pox virus FPV025) may point to some role for these proteins in regulating the viral tRNA metabolism. Each member of this family contains an internal duplication, each of which contains an HXTX motif that defines the family.", "domain_architectures": 5, "interpro_id": "IPR015069", "known_evidence_count": null, "matches": 763, "name": "Domain of unknown function (DUF1868)", "partial_evidence_count": null, "pfam_id": "PF08975", "proteins": 762, "proteomes": 685, "short_name": "2H-phosphodiest", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08975", "structures": 1, "taxa": 1467, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 491, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021513", "known_evidence_count": null, "matches": 762, "name": "Protein of unknown function (DUF3175)", "partial_evidence_count": null, "pfam_id": "PF11373", "proteins": 762, "proteomes": 745, "short_name": "DUF3175", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11373", "structures": 0, "taxa": 1155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 478, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family is not known.", "domain_architectures": 12, "interpro_id": "IPR031339", "known_evidence_count": null, "matches": 764, "name": "Domain of unknown function (DUF4942)", "partial_evidence_count": null, "pfam_id": "PF13708", "proteins": 762, "proteomes": 561, "short_name": "DUF4942", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13708", "structures": 0, "taxa": 1134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 474, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 75 and 117 amino acids in length. There is a conserved AIN sequence motif. There are two completely conserved residues (L and Y) that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR022191", "known_evidence_count": null, "matches": 761, "name": "Protein of unknown function (DUF3717)", "partial_evidence_count": null, "pfam_id": "PF12512", "proteins": 761, "proteomes": 634, "short_name": "DUF3717", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12512", "structures": 0, "taxa": 768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 608, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins from prokaryotes. It contains two pairs of conserved cysteines that are likely involved in metal coordination. This domain is predicted to structurally resemble Zinc beta-ribbon domains.", "domain_architectures": 20, "interpro_id": "IPR055999", "known_evidence_count": null, "matches": 762, "name": "Domain of unknown function (DUF7577)", "partial_evidence_count": null, "pfam_id": "PF24463", "proteins": 761, "proteomes": 587, "short_name": "DUF7577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24463", "structures": 0, "taxa": 1184, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 558, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A role of this family in UDP-N-acetylenolpyruvoylglucosamine reductase, as MurB, could not be confirmed.", "domain_architectures": 1, "interpro_id": "IPR018919", "known_evidence_count": null, "matches": 759, "name": "Protein of unknown function (DUF2484)", "partial_evidence_count": null, "pfam_id": "PF10658", "proteins": 759, "proteomes": 534, "short_name": "DUF2484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10658", "structures": 0, "taxa": 745, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is found in bacteria. Proteins in this family are about 240 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR021974", "known_evidence_count": null, "matches": 759, "name": "Protein of unknown function (DUF3581)", "partial_evidence_count": null, "pfam_id": "PF12119", "proteins": 759, "proteomes": 750, "short_name": "DUF3581", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12119", "structures": 0, "taxa": 990, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 319, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000222) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the FD-594 biosynthetic gene cluster from Streptomyces sp. TA-0256 and it appears to be predominantly found in actinobacteria [[cite:PUB00099415]].", "domain_architectures": 2, "interpro_id": "IPR046081", "known_evidence_count": null, "matches": 760, "name": "Family of unknown function (DUF6099)", "partial_evidence_count": null, "pfam_id": "PF19594", "proteins": 759, "proteomes": 751, "short_name": "DUF6099", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19594", "structures": 0, "taxa": 796, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 623, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised plant proteins that share detectable similarity with members of the Glycosyl transferase clan GT-B.", "domain_architectures": 26, "interpro_id": "IPR056712", "known_evidence_count": null, "matches": 837, "name": "Family of unknown function (DUF7810)", "partial_evidence_count": null, "pfam_id": "PF25102", "proteins": 759, "proteomes": 363, "short_name": "DUF7810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25102", "structures": 0, "taxa": 1010, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 544, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in Uncharacterized protein MJ0754 from Methanocaldococcus jannaschii and similar proteins from bacteria and archaea. MJ0754 adopts a dimeric assembly, with each monomer consisting of six alpha-helices [[cite:PUB00100681]]. It is a member of a broad superfamily of ferritin-like diiron-carboxylate proteins whose function is unknown. The conserved residues of a diiron centre are present within the putative active site.", "domain_architectures": 9, "interpro_id": "IPR019243", "known_evidence_count": null, "matches": 762, "name": "Uncharacterized protein domain (DUF2202)", "partial_evidence_count": null, "pfam_id": "PF09968", "proteins": 758, "proteomes": 658, "short_name": "DUF2202", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09968", "structures": 4, "taxa": 1461, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in the C-terminal region of proteins carrying [pfam:PF16586] and [pfam:PF13204]. The C-terminal domain is carried by species such as Bacteroides vulgatus.", "domain_architectures": 6, "interpro_id": "IPR041239", "known_evidence_count": null, "matches": 758, "name": "Domain of unknown function (DUF5605)", "partial_evidence_count": null, "pfam_id": "PF18310", "proteins": 758, "proteomes": 571, "short_name": "DUF5605", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18310", "structures": 1, "taxa": 1029, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 616, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a short family of uncharacterised proteins from plants. AlphaFold predictions suggest that the protein contains two non-contacting alpha-helices.", "domain_architectures": 20, "interpro_id": "IPR049198", "known_evidence_count": null, "matches": 773, "name": "Family of unknown function (DUF6865)", "partial_evidence_count": null, "pfam_id": "PF21737", "proteins": 758, "proteomes": 320, "short_name": "DUF6865", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21737", "structures": 0, "taxa": 927, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 439, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Gammaproteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021316", "known_evidence_count": null, "matches": 757, "name": "Protein of unknown function (DUF2913)", "partial_evidence_count": null, "pfam_id": "PF11140", "proteins": 757, "proteomes": 444, "short_name": "DUF2913", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11140", "structures": 0, "taxa": 668, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 384, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001070) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the kirromycin biosynthetic gene cluster from Streptomyces collinus Tu 365 [[cite:PUB00098988],[cite:PUB00098989]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR045778", "known_evidence_count": null, "matches": 757, "name": "Family of unknown function (DUF6204)", "partial_evidence_count": null, "pfam_id": "PF19707", "proteins": 757, "proteomes": 744, "short_name": "DUF6204", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19707", "structures": 0, "taxa": 903, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 564 to 612 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR022562", "known_evidence_count": null, "matches": 772, "name": "Protein of unknown function (DUF3466)", "partial_evidence_count": null, "pfam_id": "PF11949", "proteins": 756, "proteomes": 698, "short_name": "DUF3466", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11949", "structures": 0, "taxa": 1085, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 458, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes the B. subtilis YjgB protein [swissprot:O34960], which is functionally uncharacterised. This is not a homologue of E. coli YjgB, Swiss: P27250. Expression of B. subtilis YjgB is regulated by the alternative transcription factor sigma-B [[cite:PUB00057342]]. This family is found in bacteria, and is approximately 140 amino acids in length.", "domain_architectures": 21, "interpro_id": "IPR025453", "known_evidence_count": null, "matches": 787, "name": "Domain of unknown function (DUF4309)", "partial_evidence_count": null, "pfam_id": "PF14172", "proteins": 755, "proteomes": 578, "short_name": "DUF4309", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14172", "structures": 1, "taxa": 787, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 514, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in bacteria which adopts a beta-barrel fold of the YmcC-like type.", "domain_architectures": 5, "interpro_id": "IPR049279", "known_evidence_count": null, "matches": 755, "name": "DUF3108-like", "partial_evidence_count": null, "pfam_id": "PF21347", "proteins": 755, "proteomes": 653, "short_name": "DUF3108_like", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21347", "structures": 2, "taxa": 1113, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 545, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 9, "interpro_id": "IPR021374", "known_evidence_count": null, "matches": 754, "name": "Protein of unknown function (DUF2996)", "partial_evidence_count": null, "pfam_id": "PF11210", "proteins": 754, "proteomes": 585, "short_name": "DUF2996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11210", "structures": 2, "taxa": 1618, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 403, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021438", "known_evidence_count": null, "matches": 755, "name": "Protein of unknown function (DUF3087)", "partial_evidence_count": null, "pfam_id": "PF11286", "proteins": 753, "proteomes": 750, "short_name": "DUF3087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11286", "structures": 0, "taxa": 930, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021488", "known_evidence_count": null, "matches": 753, "name": "Domain of unknown function (DUF3142)", "partial_evidence_count": null, "pfam_id": "PF11340", "proteins": 753, "proteomes": 718, "short_name": "DUF3142", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11340", "structures": 2, "taxa": 1050, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 473, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 6, "interpro_id": "IPR021494", "known_evidence_count": null, "matches": 753, "name": "Protein of unknown function (DUF3149)", "partial_evidence_count": null, "pfam_id": "PF11346", "proteins": 753, "proteomes": 747, "short_name": "DUF3149", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11346", "structures": 0, "taxa": 1179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 521, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found mainly in Bacteria. Members of this family have multiple trans-membrane domains with the majority typically constituted of 4 trans-membrane regions.", "domain_architectures": 5, "interpro_id": "IPR035168", "known_evidence_count": null, "matches": 752, "name": "Family of unknown function (DUF5317)", "partial_evidence_count": null, "pfam_id": "PF17248", "proteins": 751, "proteomes": 684, "short_name": "DUF5317", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17248", "structures": 0, "taxa": 1212, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 463, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. It belongs to the PD-(D/E)XK nuclease superfamily suggesting it has a nuclease function. This family of proteins is found in bacteria. Proteins in this family are typically between 278 and 290 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR046612", "known_evidence_count": null, "matches": 752, "name": "Domain of unknown function (DUF6671)", "partial_evidence_count": null, "pfam_id": "PF20376", "proteins": 751, "proteomes": 716, "short_name": "DUF6671", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20376", "structures": 0, "taxa": 1479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 330, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are about 100 amino acids in length and are uncharacterised.", "domain_architectures": 2, "interpro_id": "IPR014915", "known_evidence_count": null, "matches": 750, "name": "Phage related hypothetical protein (DUF1799)", "partial_evidence_count": null, "pfam_id": "PF08809", "proteins": 750, "proteomes": 684, "short_name": "DUF1799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08809", "structures": 0, "taxa": 1341, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 444, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 121 to 136 amino acids in length. This protein has a conserved RLN sequence motif.", "domain_architectures": 1, "interpro_id": "IPR021877", "known_evidence_count": null, "matches": 750, "name": "Protein of unknown function (DUF3487)", "partial_evidence_count": null, "pfam_id": "PF11990", "proteins": 750, "proteomes": 599, "short_name": "DUF3487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11990", "structures": 0, "taxa": 1008, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from plants. It is predicted to adopt an alpha-helical bundle with ferritin-like topology. This domain is frequently found in combination with [pfam:PF01764].", "domain_architectures": 17, "interpro_id": "IPR055782", "known_evidence_count": null, "matches": 783, "name": "Domain of unknown function (DUF7358)", "partial_evidence_count": null, "pfam_id": "PF24057", "proteins": 750, "proteomes": 324, "short_name": "DUF7358", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24057", "structures": 0, "taxa": 895, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 382, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised actinobacterial proteins.", "domain_architectures": 1, "interpro_id": "IPR057195", "known_evidence_count": null, "matches": 750, "name": "Family of unknown function (DUF7873)", "partial_evidence_count": null, "pfam_id": "PF25283", "proteins": 750, "proteomes": 739, "short_name": "DUF7873", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25283", "structures": 0, "taxa": 1059, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 632, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of a group of fungal uncharacterised proteins. This domain adopts a immunoglobulin -like fold. Its function is unknown.", "domain_architectures": 12, "interpro_id": "IPR061568", "known_evidence_count": null, "matches": 773, "name": "Domain of unknown function (DUF8498)", "partial_evidence_count": null, "pfam_id": "PF29061", "proteins": 750, "proteomes": 730, "short_name": "DUF8498", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29061", "structures": 3, "taxa": 1431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 668, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 93 and 229 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR027812", "known_evidence_count": null, "matches": 756, "name": "Domain of unknown function (DUF4653)", "partial_evidence_count": null, "pfam_id": "PF15546", "proteins": 749, "proteomes": 657, "short_name": "DUF4653", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15546", "structures": 0, "taxa": 2053, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 496, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 71 and 88 amino acids in length. There are two conserved sequence motifs: KTGS and RMV.", "domain_architectures": 2, "interpro_id": "IPR045936", "known_evidence_count": null, "matches": 747, "name": "Family of unknown function (DUF6356)", "partial_evidence_count": null, "pfam_id": "PF19883", "proteins": 747, "proteomes": 717, "short_name": "DUF6356", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19883", "structures": 0, "taxa": 1072, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 669, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a functionally uncharacterised domain that shows structural similarity to [pfam:PF14032] which is the sensor domain of the PknH protein kinase protein.", "domain_architectures": 9, "interpro_id": "IPR059274", "known_evidence_count": null, "matches": 747, "name": "Domain of unknown function (DUF8575)", "partial_evidence_count": null, "pfam_id": "PF26686", "proteins": 746, "proteomes": 420, "short_name": "DUF8575", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26686", "structures": 0, "taxa": 823, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 557, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several plant, cyanobacterial and algal proteins of unknown function. The family is exclusively found in phototrophic organisms and may therefore play a role in photosynthesis (personal obs:Moxon SJ).", "domain_architectures": 11, "interpro_id": "IPR008470", "known_evidence_count": null, "matches": 745, "name": "Protein of unknown function (DUF751)", "partial_evidence_count": null, "pfam_id": "PF05421", "proteins": 745, "proteomes": 628, "short_name": "DUF751", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05421", "structures": 0, "taxa": 1793, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 429, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 247 and 267 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045920", "known_evidence_count": null, "matches": 745, "name": "Family of unknown function (DUF6339)", "partial_evidence_count": null, "pfam_id": "PF19866", "proteins": 745, "proteomes": 710, "short_name": "DUF6339", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19866", "structures": 0, "taxa": 1344, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 456, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 119 and 132 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR045507", "known_evidence_count": null, "matches": 745, "name": "Family of unknown function (DUF6483)", "partial_evidence_count": null, "pfam_id": "PF20092", "proteins": 745, "proteomes": 677, "short_name": "DUF6483", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20092", "structures": 0, "taxa": 1006, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They share significant sequence similarity with immunity protein Imm5 and are predicted to adopt similar alpha-helical structure.", "domain_architectures": 4, "interpro_id": "IPR053855", "known_evidence_count": null, "matches": 750, "name": "Family of unknown function (DUF6931)", "partial_evidence_count": null, "pfam_id": "PF22011", "proteins": 745, "proteomes": 687, "short_name": "DUF6931", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22011", "structures": 0, "taxa": 1126, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 383, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are found in various phage proteins.", "domain_architectures": 4, "interpro_id": "IPR007731", "known_evidence_count": null, "matches": 744, "name": "Protein of unknown function (DUF669)", "partial_evidence_count": null, "pfam_id": "PF05037", "proteins": 744, "proteomes": 662, "short_name": "DUF669", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05037", "structures": 0, "taxa": 1529, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 453, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 230 residues in length. Members of this family are often referred to as YjaH and are found in the Orders Vibrionales and Enterobacteriales. The function of this family is unknown.", "domain_architectures": 5, "interpro_id": "IPR010858", "known_evidence_count": null, "matches": 747, "name": "Protein of unknown function (DUF1481)", "partial_evidence_count": null, "pfam_id": "PF07356", "proteins": 744, "proteomes": 738, "short_name": "DUF1481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07356", "structures": 0, "taxa": 1018, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 417, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function. However, given its similarity to the CHAP domain it seems likely that this is an enzyme involved in cleaving peptidoglycan.", "domain_architectures": 20, "interpro_id": "IPR019262", "known_evidence_count": null, "matches": 744, "name": "Uncharacterized protein conserved in bacteria (DUF2272)", "partial_evidence_count": null, "pfam_id": "PF10030", "proteins": 744, "proteomes": 697, "short_name": "DUF2272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10030", "structures": 0, "taxa": 1175, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 469, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are predicted to fold into five-bladed beta-propeller that has similarity to apyrase but it is circularly permuted. The C-terminal two beta-strands of this domain occupy the position of the two N-terminal beta-strands in apyrase.", "domain_architectures": 6, "interpro_id": "IPR053851", "known_evidence_count": null, "matches": 745, "name": "Family of unknown function (DUF6929)", "partial_evidence_count": null, "pfam_id": "PF22000", "proteins": 744, "proteomes": 725, "short_name": "DUF6929", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22000", "structures": 0, "taxa": 1015, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 372, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of at least 8 paralogs in Myxococcus xanthus, a member of the Deltaproteobacteria. The function is unknown.", "domain_architectures": 2, "interpro_id": "IPR011754", "known_evidence_count": null, "matches": 762, "name": "Protein of unknown function (DUF2381)", "partial_evidence_count": null, "pfam_id": "PF09544", "proteins": 743, "proteomes": 41, "short_name": "DUF2381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09544", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mainly found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR043767", "known_evidence_count": null, "matches": 742, "name": "Family of unknown function (DUF5713)", "partial_evidence_count": null, "pfam_id": "PF18977", "proteins": 742, "proteomes": 705, "short_name": "DUF5713", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18977", "structures": 0, "taxa": 1149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025464", "known_evidence_count": null, "matches": 741, "name": "Domain of unknown function (DUF4315)", "partial_evidence_count": null, "pfam_id": "PF14193", "proteins": 741, "proteomes": 313, "short_name": "DUF4315", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14193", "structures": 0, "taxa": 619, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 335, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000360) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the GE81112 biosynthetic gene cluster from Streptomyces sp. L-49973 and appears to be predominantly found in Actinobacteria [[cite:PUB00074314]].", "domain_architectures": 3, "interpro_id": "IPR046175", "known_evidence_count": null, "matches": 745, "name": "DUF6177, C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF19674", "proteins": 741, "proteomes": 531, "short_name": "DUF6177", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19674", "structures": 0, "taxa": 672, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 455, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterized bacterial proteins with a length of ~140-150 residues. They are predicted to adopt an alpha-helical structure consisting of two structural repeats.", "domain_architectures": 1, "interpro_id": "IPR054211", "known_evidence_count": null, "matches": 741, "name": "Family of unknown function (DUF6918)", "partial_evidence_count": null, "pfam_id": "PF21893", "proteins": 741, "proteomes": 728, "short_name": "DUF6918", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21893", "structures": 0, "taxa": 1139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 386, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 65 amino acids found in Actinomycetes. It is predicted to fold into a beta-sandwich structure composed of two three-stranded antiparallel beta-sheets packed on each other.", "domain_architectures": 1, "interpro_id": "IPR061897", "known_evidence_count": null, "matches": 741, "name": "Domain of unknown function (DUF8836)", "partial_evidence_count": null, "pfam_id": "PF31188", "proteins": 741, "proteomes": 738, "short_name": "DUF8836", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31188", "structures": 0, "taxa": 880, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 463, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins have no known function.", "domain_architectures": 2, "interpro_id": "IPR021292", "known_evidence_count": null, "matches": 740, "name": "Protein of unknown function (DUF2863)", "partial_evidence_count": null, "pfam_id": "PF11062", "proteins": 740, "proteomes": 697, "short_name": "DUF2863", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11062", "structures": 0, "taxa": 897, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 599, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant proteins. This domain is often found associated with [pfam:PF00628] and is predicted to have an all-alpha helical configuration.", "domain_architectures": 22, "interpro_id": "IPR056699", "known_evidence_count": null, "matches": 741, "name": "Domain of unknown function (DUF7797)", "partial_evidence_count": null, "pfam_id": "PF25073", "proteins": 740, "proteomes": 356, "short_name": "DUF7797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25073", "structures": 0, "taxa": 1002, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 482, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a four helical bundle domain found at the C-terminus of Aquifex aeolicus aq_1824 protein ([swissprot:O67685]). The function of these proteins is not known. This domain is often associated with proteins containing kinase domains.", "domain_architectures": 30, "interpro_id": "IPR058395", "known_evidence_count": null, "matches": 996, "name": "Domain of unknown function (DUF8082)", "partial_evidence_count": null, "pfam_id": "PF26309", "proteins": 740, "proteomes": 568, "short_name": "DUF8082", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26309", "structures": 0, "taxa": 1158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 699, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Family of uncharacterised, hypothetical archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR007564", "known_evidence_count": null, "matches": 739, "name": "Protein of unknown function (DUF555)", "partial_evidence_count": null, "pfam_id": "PF04475", "proteins": 739, "proteomes": 437, "short_name": "DUF555", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04475", "structures": 0, "taxa": 730, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR019621", "known_evidence_count": null, "matches": 739, "name": "Protein of unknown function (DUF2491)", "partial_evidence_count": null, "pfam_id": "PF10679", "proteins": 739, "proteomes": 736, "short_name": "DUF2491", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10679", "structures": 0, "taxa": 1090, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 482, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR024244", "known_evidence_count": null, "matches": 739, "name": "Protein of unknown function (DUF2537)", "partial_evidence_count": null, "pfam_id": "PF10801", "proteins": 739, "proteomes": 737, "short_name": "DUF2537", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10801", "structures": 0, "taxa": 899, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 458, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 110 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR025648", "known_evidence_count": null, "matches": 739, "name": "Domain of unknown function (DUF4358)", "partial_evidence_count": null, "pfam_id": "PF14270", "proteins": 739, "proteomes": 522, "short_name": "DUF4358", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14270", "structures": 0, "taxa": 812, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 451, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised alpha helical domain found in bacteria, archaea and viruses. Proteins in this family are typically between 147 and 190 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031876", "known_evidence_count": null, "matches": 738, "name": "Domain of unknown function (DUF4760)", "partial_evidence_count": null, "pfam_id": "PF15956", "proteins": 738, "proteomes": 681, "short_name": "DUF4760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15956", "structures": 0, "taxa": 1430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 463, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045447", "known_evidence_count": null, "matches": 738, "name": "Family of unknown function (DUF6501)", "partial_evidence_count": null, "pfam_id": "PF20111", "proteins": 738, "proteomes": 737, "short_name": "DUF6501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20111", "structures": 0, "taxa": 940, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family represents the carboxy terminus of a protein of unknown function, found in dsDNA viruses with no RNA stage, including bacteriophages lambda and P22, and also in some Escherichia coli prophages.", "domain_architectures": 15, "interpro_id": "IPR007539", "known_evidence_count": null, "matches": 738, "name": "Protein of unknown function (DUF551)", "partial_evidence_count": null, "pfam_id": "PF04448", "proteins": 737, "proteomes": 624, "short_name": "DUF551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04448", "structures": 0, "taxa": 1408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 477, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR021213", "known_evidence_count": null, "matches": 737, "name": "Protein of unknown function (DUF2567)", "partial_evidence_count": null, "pfam_id": "PF10821", "proteins": 737, "proteomes": 736, "short_name": "DUF2567", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10821", "structures": 0, "taxa": 909, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 600, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found at the C-terminal of fungal sequences. It may adopt a ubiquitin-like fold.", "domain_architectures": 21, "interpro_id": "IPR056669", "known_evidence_count": null, "matches": 737, "name": "Domain of unknown function (DUF7767)", "partial_evidence_count": null, "pfam_id": "PF24962", "proteins": 737, "proteomes": 728, "short_name": "DUF7767", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24962", "structures": 0, "taxa": 1400, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 640, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 35, "interpro_id": "IPR004951", "known_evidence_count": null, "matches": 748, "name": "Caenorhabditis protein of unknown function, DUF268", "partial_evidence_count": null, "pfam_id": "PF03269", "proteins": 733, "proteomes": 311, "short_name": "DUF268", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03269", "structures": 0, "taxa": 986, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 433, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR021549", "known_evidence_count": null, "matches": 737, "name": "Protein of unknown function (DUF2894)", "partial_evidence_count": null, "pfam_id": "PF11445", "proteins": 733, "proteomes": 726, "short_name": "DUF2894", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11445", "structures": 0, "taxa": 900, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 476, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 100 amino acids in length. The family is found in association with [pfam:PF00589].", "domain_architectures": 5, "interpro_id": "IPR022169", "known_evidence_count": null, "matches": 733, "name": "Phage integrase protein", "partial_evidence_count": null, "pfam_id": "PF12482", "proteins": 733, "proteomes": 351, "short_name": "DUF3701", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12482", "structures": 0, "taxa": 521, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the istamycin biosynthetic gene cluster from Streptomyces tenjimariensis [[cite:PUB00098957]]. This family appears to be predominantly found in Actinoabactteria.", "domain_architectures": 2, "interpro_id": "IPR046251", "known_evidence_count": null, "matches": 733, "name": "Family of unknown function (DUF6284)", "partial_evidence_count": null, "pfam_id": "PF19801", "proteins": 733, "proteomes": 502, "short_name": "DUF6284", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19801", "structures": 0, "taxa": 615, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 430, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function", "domain_architectures": 3, "interpro_id": "IPR022555", "known_evidence_count": null, "matches": 771, "name": "Protein of unknown function (DUF2577)", "partial_evidence_count": null, "pfam_id": "PF10844", "proteins": 732, "proteomes": 575, "short_name": "DUF2577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10844", "structures": 1, "taxa": 957, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 429, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR025441", "known_evidence_count": null, "matches": 732, "name": "Domain of unknown function (DUF4181)", "partial_evidence_count": null, "pfam_id": "PF13789", "proteins": 732, "proteomes": 433, "short_name": "DUF4181", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13789", "structures": 0, "taxa": 609, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 563, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into alpha-beta-beta sandwich. It has two pairs of conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 13, "interpro_id": "IPR057210", "known_evidence_count": null, "matches": 734, "name": "Domain of unknown function (DUF7888)", "partial_evidence_count": null, "pfam_id": "PF25411", "proteins": 731, "proteomes": 370, "short_name": "DUF7888", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25411", "structures": 0, "taxa": 767, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 95 residues in length. The function of this family is unknown.", "domain_architectures": 10, "interpro_id": "IPR010781", "known_evidence_count": null, "matches": 730, "name": "Protein of unknown function (DUF1376)", "partial_evidence_count": null, "pfam_id": "PF07120", "proteins": 730, "proteomes": 596, "short_name": "DUF1376", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07120", "structures": 0, "taxa": 1123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 464, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is frequently found in combination with [pfam:PF21818] and [pfam:PF20815] which suggests that it may be involved in DNA binding and recognition. It is predicted to adopt a globular structure consisting of a three-stranded antiparallel beta-sheet and alpha-helices packed on one side of it.", "domain_architectures": 38, "interpro_id": "IPR056079", "known_evidence_count": null, "matches": 730, "name": "Domain of unknown function (DUF7662)", "partial_evidence_count": null, "pfam_id": "PF24698", "proteins": 730, "proteomes": 663, "short_name": "DUF7662", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24698", "structures": 0, "taxa": 1264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 434, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 244 to 323 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR021783", "known_evidence_count": null, "matches": 774, "name": "Protein of unknown function (DUF3348)", "partial_evidence_count": null, "pfam_id": "PF11828", "proteins": 729, "proteomes": 725, "short_name": "DUF3348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11828", "structures": 0, "taxa": 911, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 425, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in bacterial proteins.", "domain_architectures": 3, "interpro_id": "IPR041651", "known_evidence_count": null, "matches": 726, "name": "Domain of unknown function (DUF5610)", "partial_evidence_count": null, "pfam_id": "PF18433", "proteins": 726, "proteomes": 701, "short_name": "DUF5610", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18433", "structures": 1, "taxa": 1031, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 517, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR043747", "known_evidence_count": null, "matches": 758, "name": "Family of unknown function (DUF5692)", "partial_evidence_count": null, "pfam_id": "PF18948", "proteins": 726, "proteomes": 552, "short_name": "DUF5692", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18948", "structures": 0, "taxa": 1021, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 652, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a short region of ccdc82_homologues that is conserved from Schizo. pombe up to humans. The function is not known.", "domain_architectures": 5, "interpro_id": "IPR025244", "known_evidence_count": null, "matches": 729, "name": "Domain of unknown function (DUF4196)", "partial_evidence_count": null, "pfam_id": "PF13846", "proteins": 725, "proteomes": 537, "short_name": "DUF4196", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13846", "structures": 0, "taxa": 1573, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 579, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found N-terminal in a group of uncharacterised proteins mainly from plants. It shares a significant sequence similarity with the N-terminal domain of bHLH-MYC and R2R3-MYB transcription factors ([pfam:PF14215]) and it is predicted to adopt similar structure.", "domain_architectures": 11, "interpro_id": "IPR055478", "known_evidence_count": null, "matches": 754, "name": "Domain of unknown function (DUF7050)", "partial_evidence_count": null, "pfam_id": "PF23133", "proteins": 724, "proteomes": 332, "short_name": "DUF7050", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23133", "structures": 0, "taxa": 948, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in probable transcriptional regulators from Actinomycetota predominantly in the genus Streptomyces. These proteins contain an N-terminal helix-turn-helix DNA-binding domain followed by this domain. The function of this domain is unknown.", "domain_architectures": 6, "interpro_id": "IPR061902", "known_evidence_count": null, "matches": 725, "name": "Domain of unknown function (DUF8841)", "partial_evidence_count": null, "pfam_id": "PF31225", "proteins": 724, "proteomes": 562, "short_name": "DUF8841", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31225", "structures": 0, "taxa": 645, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 475, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 400 residues in length and is mainly found in various Bacteroides and Prevotella species. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR032331", "known_evidence_count": null, "matches": 724, "name": "Domain of unknown function (DUF4856)", "partial_evidence_count": null, "pfam_id": "PF16148", "proteins": 723, "proteomes": 701, "short_name": "DUF4856", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16148", "structures": 0, "taxa": 1126, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 491, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 50 amino acids in length. This protein has conserved AYL and DLE sequence motifs.", "domain_architectures": 2, "interpro_id": "IPR021946", "known_evidence_count": null, "matches": 722, "name": "Protein of unknown function (DUF3563)", "partial_evidence_count": null, "pfam_id": "PF12086", "proteins": 722, "proteomes": 428, "short_name": "DUF3563", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12086", "structures": 0, "taxa": 554, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 578, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a repeating domain found in fungal proteins. It is proline-rich, and the function is not known.", "domain_architectures": 22, "interpro_id": "IPR024436", "known_evidence_count": null, "matches": 1457, "name": "Domain of unknwon function (DUF3824)", "partial_evidence_count": null, "pfam_id": "PF12868", "proteins": 722, "proteomes": 668, "short_name": "DUF3824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12868", "structures": 0, "taxa": 1585, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 50 residues found in Actinomycetes, predominantly in Streptomyces. The function of this family remains to be determined. Members are predicted to fold into a simple structure composed of a small three stranded antiparallel beta-sheet and an alpha-helix connecting the first and the second beta-strand.", "domain_architectures": 1, "interpro_id": "IPR061900", "known_evidence_count": null, "matches": 721, "name": "Domain of unknown function (DUF8839)", "partial_evidence_count": null, "pfam_id": "PF31205", "proteins": 721, "proteomes": 464, "short_name": "DUF8839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31205", "structures": 0, "taxa": 505, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 284, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000413) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This family includes a protein encoded by the pyoverdin biosynthetic gene cluster from Pseudomonas protegens Pf-5 [[cite:PUB00010150],[cite:PUB00007220]].", "domain_architectures": 9, "interpro_id": "IPR046053", "known_evidence_count": null, "matches": 720, "name": "Family of unknown function (DUF6011)", "partial_evidence_count": null, "pfam_id": "PF19474", "proteins": 720, "proteomes": 656, "short_name": "DUF6011", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19474", "structures": 0, "taxa": 1226, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 442, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 146 and 251 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046282", "known_evidence_count": null, "matches": 720, "name": "Family of unknown function (DUF6319)", "partial_evidence_count": null, "pfam_id": "PF19844", "proteins": 720, "proteomes": 593, "short_name": "DUF6319", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19844", "structures": 0, "taxa": 717, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 625, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is predicted to fold into a four-helical up-and-down bundle. It is usually found in two tandem copies. This domain is likely associated with the membrane.", "domain_architectures": 10, "interpro_id": "IPR056691", "known_evidence_count": null, "matches": 1245, "name": "Domain of unknown function (DUF7789)", "partial_evidence_count": null, "pfam_id": "PF25044", "proteins": 719, "proteomes": 446, "short_name": "DUF7789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25044", "structures": 0, "taxa": 1752, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found mostly in fungal proteins. This domain contains a coiled coil hairpin domain similar to that of [[pfam:PF24481]].", "domain_architectures": 19, "interpro_id": "IPR059319", "known_evidence_count": null, "matches": 722, "name": "Domain of unknown function (DUF8275)", "partial_evidence_count": null, "pfam_id": "PF26916", "proteins": 719, "proteomes": 709, "short_name": "DUF8275", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26916", "structures": 0, "taxa": 1423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 396, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR014547", "known_evidence_count": null, "matches": 719, "name": "Uncharacterized protein conserved in bacteria (DUF2145)", "partial_evidence_count": null, "pfam_id": "PF09916", "proteins": 718, "proteomes": 598, "short_name": "DUF2145", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09916", "structures": 0, "taxa": 929, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 480, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of putative small secreted proteins expressed by Actinobacteria. The function is not known.", "domain_architectures": 5, "interpro_id": "IPR022566", "known_evidence_count": null, "matches": 718, "name": "Protein of unknown function (DUF2613)", "partial_evidence_count": null, "pfam_id": "PF11021", "proteins": 718, "proteomes": 645, "short_name": "DUF2613", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11021", "structures": 0, "taxa": 847, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 459, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found in gamma- and beta-proteobacteria. They are predicted to adopt an alpha-helical structure with a complex topology.", "domain_architectures": 1, "interpro_id": "IPR058511", "known_evidence_count": null, "matches": 718, "name": "Domain of unknown function (DUF8198)", "partial_evidence_count": null, "pfam_id": "PF26621", "proteins": 718, "proteomes": 668, "short_name": "DUF8198", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26621", "structures": 0, "taxa": 984, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 476, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins from Bacteroidetes. This domain has a beta-sandwich prealbumin-like fold.", "domain_architectures": 5, "interpro_id": "IPR024278", "known_evidence_count": null, "matches": 717, "name": "Protein of unknown function (DUF3823) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF12866", "proteins": 717, "proteomes": 418, "short_name": "DUF3823", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12866", "structures": 4, "taxa": 619, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 619, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 93 and 189 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR029089", "known_evidence_count": null, "matches": 717, "name": "Domain of unknown function (DUF4660)", "partial_evidence_count": null, "pfam_id": "PF15559", "proteins": 716, "proteomes": 585, "short_name": "DUF4660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15559", "structures": 0, "taxa": 1921, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 480, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 89 and 103 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045391", "known_evidence_count": null, "matches": 716, "name": "Family of unknown function (DUF6520)", "partial_evidence_count": null, "pfam_id": "PF20130", "proteins": 716, "proteomes": 460, "short_name": "DUF6520", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20130", "structures": 0, "taxa": 608, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 456, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR021230", "known_evidence_count": null, "matches": 715, "name": "Protein of unknown function (DUF2810)", "partial_evidence_count": null, "pfam_id": "PF10928", "proteins": 715, "proteomes": 713, "short_name": "DUF2810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10928", "structures": 1, "taxa": 948, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 490, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal beta propeller domain of this family.", "domain_architectures": 83, "interpro_id": "IPR058667", "known_evidence_count": null, "matches": 745, "name": "DUF6242 beta propeller domain", "partial_evidence_count": null, "pfam_id": "PF25852", "proteins": 715, "proteomes": 666, "short_name": "DUF6242_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25852", "structures": 4, "taxa": 1468, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 536, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 5, "interpro_id": "IPR021489", "known_evidence_count": null, "matches": 725, "name": "Protein of unknown function (DUF3143)", "partial_evidence_count": null, "pfam_id": "PF11341", "proteins": 714, "proteomes": 584, "short_name": "DUF3143", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11341", "structures": 0, "taxa": 1632, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 110 amino acids in length. The family is found in association with [pfam:PF05860].", "domain_architectures": 10, "interpro_id": "IPR021026", "known_evidence_count": null, "matches": 714, "name": "Filamentous haemagglutinin family outer membrane protein", "partial_evidence_count": null, "pfam_id": "PF12545", "proteins": 714, "proteomes": 504, "short_name": "DUF3739", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12545", "structures": 0, "taxa": 805, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 465, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 320 residues in length. Members of this family are mainly found in Rhizobium and Agrobacterium species. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR009843", "known_evidence_count": null, "matches": 720, "name": "Protein of unknown function (DUF1403)", "partial_evidence_count": null, "pfam_id": "PF07183", "proteins": 712, "proteomes": 448, "short_name": "DUF1403", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07183", "structures": 0, "taxa": 683, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in a wide range of bacterial cell surface proteins. It is predicted to adopt a beta-sandwich with Ig-like topology. Many members contain a pair of conserved cysteine residues that are predicted to form disulfide bond.", "domain_architectures": 141, "interpro_id": "IPR046524", "known_evidence_count": null, "matches": 712, "name": "Domain of unknown function (DUF6701), first Ig-like domain", "partial_evidence_count": null, "pfam_id": "PF20419", "proteins": 712, "proteomes": 670, "short_name": "DUF6701", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20419", "structures": 0, "taxa": 1009, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 323, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000360) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the GE81112 biosynthetic gene cluster from Streptomyces sp. L-49973 and appears to be predominantly found in Actinobacteria [[cite:PUB00074314]].", "domain_architectures": 3, "interpro_id": "IPR062939", "known_evidence_count": null, "matches": 712, "name": "DUF6177, N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF30002", "proteins": 712, "proteomes": 518, "short_name": "DUF6177_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30002", "structures": 0, "taxa": 651, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 404, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length. This family appears to be related to [pfam:PF03729].", "domain_architectures": 7, "interpro_id": "IPR045590", "known_evidence_count": null, "matches": 723, "name": "Family of unknown function (DUF6463)", "partial_evidence_count": null, "pfam_id": "PF20064", "proteins": 710, "proteomes": 582, "short_name": "DUF6463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20064", "structures": 0, "taxa": 1051, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 538, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 133 and 156 amino acids in length.", "domain_architectures": 15, "interpro_id": "IPR046580", "known_evidence_count": null, "matches": 740, "name": "Family of unknown function (DUF6640)", "partial_evidence_count": null, "pfam_id": "PF20345", "proteins": 709, "proteomes": 642, "short_name": "DUF6640", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20345", "structures": 0, "taxa": 1345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 511, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045519", "known_evidence_count": null, "matches": 707, "name": "Family of unknown function (DUF6476)", "partial_evidence_count": null, "pfam_id": "PF20082", "proteins": 707, "proteomes": 707, "short_name": "DUF6476", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20082", "structures": 0, "taxa": 1031, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 474, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain has no known function.", "domain_architectures": 7, "interpro_id": "IPR021503", "known_evidence_count": null, "matches": 708, "name": "Domain of unknown function (DUF3110)", "partial_evidence_count": null, "pfam_id": "PF11360", "proteins": 706, "proteomes": 577, "short_name": "DUF3110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11360", "structures": 0, "taxa": 1710, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 419, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 120 amino acids in length. It is likely to contain 2 to 3 copies of a PD40-like repeat.", "domain_architectures": 5, "interpro_id": "IPR022223", "known_evidence_count": null, "matches": 707, "name": "Protein of unknown function (DUF3748)", "partial_evidence_count": null, "pfam_id": "PF12566", "proteins": 706, "proteomes": 700, "short_name": "DUF3748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12566", "structures": 0, "taxa": 1041, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 618, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain covering the whole length in Uncharacterized protein C6orf62 from metazoa. C6orf62 is ubiquitously expressed, including in brain tissue, which led to its inclusion in neurogenetic linkage studies, particularly in the region associated with developmental dyslexia. Though C6orf62 itself was not confirmed as causal, it lies adjacent to dyslexia-associated genes such as KIAA0319 and DCDC2, both of which are involved in neuronal migration and axonal growth [[cite:PUB00162470]]. This domain covers other regions in related proteins.", "domain_architectures": 4, "interpro_id": "IPR027903", "known_evidence_count": null, "matches": 726, "name": "Domain of unknown function (DUF4566)", "partial_evidence_count": null, "pfam_id": "PF15130", "proteins": 706, "proteomes": 525, "short_name": "DUF4566", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15130", "structures": 0, "taxa": 1819, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 593, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 229 and 247 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR045466", "known_evidence_count": null, "matches": 706, "name": "Family of unknown function (DUF6498)", "partial_evidence_count": null, "pfam_id": "PF20108", "proteins": 706, "proteomes": 500, "short_name": "DUF6498", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20108", "structures": 0, "taxa": 977, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 523, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is typically between 75 and 86 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR045406", "known_evidence_count": null, "matches": 706, "name": "Family of unknown function (DUF6513)", "partial_evidence_count": null, "pfam_id": "PF20123", "proteins": 706, "proteomes": 685, "short_name": "DUF6513", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20123", "structures": 0, "taxa": 1132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in multiple copies in a number of bacterial proteins. It is closely related to domains represented by DUF11 ([pfam:PF01345]). Some members, similarly to DUF11, contains a conserved N-terminal lysine and a C-terminal asparagine with central aspartate/glutamate residues suggesting that they may contain an isopeptide bond.", "domain_architectures": 344, "interpro_id": "IPR057693", "known_evidence_count": null, "matches": 1854, "name": "Domain of unknown function (DUF7933)", "partial_evidence_count": null, "pfam_id": "PF25564", "proteins": 706, "proteomes": 570, "short_name": "DUF7933", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25564", "structures": 0, "taxa": 1090, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 415, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function at the N-terminal in uncharacterised proteins mostly found in bacteria. This domain belongs to proteins with a conserved four or five-helix up-and-down bundle structure. This structure is typical of focal adhesion targeting (FAT) domains and is responsible for dimerisation. These proteins are also present in transcriptional regulators where the bundle structure is important for their dynamic conformational equilibrium to control target specificity. The conserved helical bundle architecture enables these proteins to function in protein-protein interactions and regulatory processes [[cite:PUB00075415],[cite:PUB00004911],[cite:PUB00161916]].", "domain_architectures": 4, "interpro_id": "IPR059364", "known_evidence_count": null, "matches": 706, "name": "Domain of unknown function (DUF8320)", "partial_evidence_count": null, "pfam_id": "PF26994", "proteins": 706, "proteomes": 491, "short_name": "DUF8320", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26994", "structures": 0, "taxa": 637, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 446, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in a wide variety of bacteria such as proteobacteria, spirochaetes, firmicutes and actinobacteria, and is approximately 280 amino acids in length. The family is found in to the N-terminus of [pfam:PF00211].", "domain_architectures": 8, "interpro_id": "IPR045983", "known_evidence_count": null, "matches": 707, "name": "Family of unknown function (DUF5939)", "partial_evidence_count": null, "pfam_id": "PF19363", "proteins": 705, "proteomes": 556, "short_name": "DUF5939", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19363", "structures": 0, "taxa": 887, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 403, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is predominantly found in Firmicute bacterial proteins and is functionally uncharacterised. It is found in proteins that are likely to be surface exposed. It is predicted to fold into a globular structure with C-type lectin topology. This domain is frequently found in combination with other carbohydrate-binding domains implying that it may be involved in carbohydrate recognition/binding.", "domain_architectures": 110, "interpro_id": "IPR046240", "known_evidence_count": null, "matches": 734, "name": "Domain of unknown function (DUF6273)", "partial_evidence_count": null, "pfam_id": "PF19789", "proteins": 704, "proteomes": 436, "short_name": "DUF6273", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19789", "structures": 1, "taxa": 892, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 436, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical bacterial proteins of around 80 residues in length. Members of this family are found in Rhizobium, Agrobacterium and Brucella species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009780", "known_evidence_count": null, "matches": 703, "name": "Protein of unknown function (DUF1344)", "partial_evidence_count": null, "pfam_id": "PF07076", "proteins": 703, "proteomes": 476, "short_name": "DUF1344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07076", "structures": 0, "taxa": 655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 443, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 8, "interpro_id": "IPR021256", "known_evidence_count": null, "matches": 703, "name": "Protein of unknown function (DUF2808)", "partial_evidence_count": null, "pfam_id": "PF10989", "proteins": 703, "proteomes": 270, "short_name": "DUF2808", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10989", "structures": 0, "taxa": 713, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 602, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins largely from fungi. The function is not known.", "domain_architectures": 17, "interpro_id": "IPR028018", "known_evidence_count": null, "matches": 707, "name": "Domain of unknown function (DUF4646)", "partial_evidence_count": null, "pfam_id": "PF15496", "proteins": 703, "proteomes": 438, "short_name": "DUF4646", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15496", "structures": 0, "taxa": 1005, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 476, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR020503", "known_evidence_count": null, "matches": 702, "name": "Protein of unknown function (DUF2652)", "partial_evidence_count": null, "pfam_id": "PF10851", "proteins": 702, "proteomes": 635, "short_name": "DUF2652", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10851", "structures": 0, "taxa": 926, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a coiled-coil region found at the C-terminal of a group of uncharacterised sequences from fungi.", "domain_architectures": 15, "interpro_id": "IPR055914", "known_evidence_count": null, "matches": 702, "name": "Coiled-coil region of unknown function (DUF7491)", "partial_evidence_count": null, "pfam_id": "PF24319", "proteins": 702, "proteomes": 690, "short_name": "DUF7491", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24319", "structures": 0, "taxa": 1438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 310, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in tandem in a number of bacterial proteins which are likely associated with the bacterial cell surface. It is predicted to fold into a beta-sandwich. Some members of this entry are likely to contain an intramolecular isopeptide bond connecting their N- and C-terminal strands. This family is closely related to [pfam:PF19407].", "domain_architectures": 252, "interpro_id": "IPR055382", "known_evidence_count": null, "matches": 1351, "name": "Domain of unknown function (DUF7601)", "partial_evidence_count": null, "pfam_id": "PF24547", "proteins": 702, "proteomes": 390, "short_name": "DUF7601", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24547", "structures": 18, "taxa": 679, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 468, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Members of this family are Gammaproteobacteria. Many are annotated as like E coli protein YciN. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019633", "known_evidence_count": null, "matches": 701, "name": "Protein of unknown function (DUF2498)", "partial_evidence_count": null, "pfam_id": "PF10692", "proteins": 701, "proteomes": 701, "short_name": "DUF2498", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10692", "structures": 1, "taxa": 959, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 431, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 156 and 167 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046586", "known_evidence_count": null, "matches": 701, "name": "Family of unknown function (DUF6644)", "partial_evidence_count": null, "pfam_id": "PF20349", "proteins": 701, "proteomes": 533, "short_name": "DUF6644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20349", "structures": 0, "taxa": 913, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 483, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Solution of the structure of the Lactobacillus plantarum protein from this family has indicated a potential new fold with remote similarities to TBP-like (TATA-binding protein) structures. This similarity, in combination with genomic context analysis, leads us to propose an involvement in amino-acid metabolism. The potentially novel fold is an alpha + beta fold comprising two beta sheets packed against a single helix. The enzyme is present in the cytosol.", "domain_architectures": 1, "interpro_id": "IPR014965", "known_evidence_count": null, "matches": 699, "name": "Putative amino acid metabolism", "partial_evidence_count": null, "pfam_id": "PF08866", "proteins": 699, "proteomes": 699, "short_name": "DUF1831", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08866", "structures": 1, "taxa": 999, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000118) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the pactamycin biosynthetic gene cluster from Streptomyces pactum [[cite:PUB00099419]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR046195", "known_evidence_count": null, "matches": 702, "name": "Family of unknown function (DUF6227)", "partial_evidence_count": null, "pfam_id": "PF19738", "proteins": 699, "proteomes": 693, "short_name": "DUF6227", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19738", "structures": 0, "taxa": 738, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 143 to 307 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR021960", "known_evidence_count": null, "matches": 843, "name": "Protein of unknown function (DUF3577)", "partial_evidence_count": null, "pfam_id": "PF12101", "proteins": 698, "proteomes": 568, "short_name": "DUF3577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12101", "structures": 0, "taxa": 994, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 586, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to fold into four helices that form two helical hairpins arranged in V-shape.", "domain_architectures": 23, "interpro_id": "IPR056705", "known_evidence_count": null, "matches": 711, "name": "Domain of unknown function (DUF7803)", "partial_evidence_count": null, "pfam_id": "PF25086", "proteins": 698, "proteomes": 364, "short_name": "DUF7803", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25086", "structures": 0, "taxa": 1027, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 572, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found in plants. They are predicted to adopt structures similar to choline-like transporters.", "domain_architectures": 13, "interpro_id": "IPR056715", "known_evidence_count": null, "matches": 798, "name": "Family of unknown function (DUF7813)", "partial_evidence_count": null, "pfam_id": "PF25105", "proteins": 698, "proteomes": 345, "short_name": "DUF7813", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25105", "structures": 0, "taxa": 946, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 387, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function. Some members are annotated as membrane proteins however this cannot be confirmed.", "domain_architectures": 1, "interpro_id": "IPR021356", "known_evidence_count": null, "matches": 697, "name": "Protein of unknown function (DUF2976)", "partial_evidence_count": null, "pfam_id": "PF11190", "proteins": 697, "proteomes": 567, "short_name": "DUF2976", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11190", "structures": 0, "taxa": 966, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 419, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as lipoproteins however this cannot be confirmed.", "domain_architectures": 1, "interpro_id": "IPR021534", "known_evidence_count": null, "matches": 697, "name": "Protein of unknown function (DUF3192)", "partial_evidence_count": null, "pfam_id": "PF11399", "proteins": 697, "proteomes": 391, "short_name": "DUF3192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11399", "structures": 0, "taxa": 588, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 443, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 79 to 104 amino acids in length. This protein has a single completely conserved residue C that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR021937", "known_evidence_count": null, "matches": 696, "name": "Protein of unknown function (DUF3551)", "partial_evidence_count": null, "pfam_id": "PF12071", "proteins": 696, "proteomes": 105, "short_name": "DUF3551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12071", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 152 and 283 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR028013", "known_evidence_count": null, "matches": 695, "name": "Domain of unknown function (DUF4437)", "partial_evidence_count": null, "pfam_id": "PF14499", "proteins": 695, "proteomes": 631, "short_name": "DUF4437", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14499", "structures": 1, "taxa": 1275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 455, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 269 and 295 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045445", "known_evidence_count": null, "matches": 695, "name": "Family of unknown function (DUF6502)", "partial_evidence_count": null, "pfam_id": "PF20112", "proteins": 695, "proteomes": 604, "short_name": "DUF6502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20112", "structures": 0, "taxa": 964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram-negative bacteria. It is predicted to fold into small alpha/beta domain consisting of three-stranded beta-sheet and two alpha-helices packed on it. It is frequently found in combination with helicase domains.", "domain_architectures": 17, "interpro_id": "IPR059482", "known_evidence_count": null, "matches": 695, "name": "Domain of unknown function (DUF8438)", "partial_evidence_count": null, "pfam_id": "PF28556", "proteins": 695, "proteomes": 421, "short_name": "DUF8438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28556", "structures": 0, "taxa": 629, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 682, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative proteins are found in Trichomonas vaginalis in large numbers. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR025181", "known_evidence_count": null, "matches": 694, "name": "Protein of unknown function (DUF4108)", "partial_evidence_count": null, "pfam_id": "PF13390", "proteins": 694, "proteomes": 2, "short_name": "DUF4108", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13390", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 379, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins whose function is unknown. They may be distantly related to ADP-ribosylating toxins.", "domain_architectures": 2, "interpro_id": "IPR049253", "known_evidence_count": null, "matches": 698, "name": "Family of unknown function (DUF6886)", "partial_evidence_count": null, "pfam_id": "PF21820", "proteins": 694, "proteomes": 685, "short_name": "DUF6886", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21820", "structures": 0, "taxa": 982, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 382, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 94 and 126 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR022053", "known_evidence_count": null, "matches": 693, "name": "Protein of unknown function (DUF3613)", "partial_evidence_count": null, "pfam_id": "PF12266", "proteins": 693, "proteomes": 693, "short_name": "DUF3613", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12266", "structures": 0, "taxa": 873, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 453, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short domain is functionally uncharacterised.", "domain_architectures": 4, "interpro_id": "IPR024331", "known_evidence_count": null, "matches": 693, "name": "Domain of unknown function (DUF3859)", "partial_evidence_count": null, "pfam_id": "PF12975", "proteins": 693, "proteomes": 663, "short_name": "DUF3859", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12975", "structures": 1, "taxa": 1033, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 419, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharcaterised bacterial proteins. It is predicted to fold into a four helical bundle.", "domain_architectures": 1, "interpro_id": "IPR061772", "known_evidence_count": null, "matches": 692, "name": "Domain of unknown function (DUF8711)", "partial_evidence_count": null, "pfam_id": "PF30729", "proteins": 692, "proteomes": 505, "short_name": "DUF8711", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30729", "structures": 0, "taxa": 634, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry contains a domain that is found as tandem repeats in a number of bacterial proteins. The domain is rich in negatively charged amino acids and contains multiple potential calcium binding sites.", "domain_architectures": 349, "interpro_id": "IPR043824", "known_evidence_count": null, "matches": 2360, "name": "Domain of unknown function (DUF5801)", "partial_evidence_count": null, "pfam_id": "PF19116", "proteins": 691, "proteomes": 495, "short_name": "DUF5801", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19116", "structures": 1, "taxa": 840, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 329, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 60 residues. The domain is typically found following AAA_16 domains ([pfam:PF13191]) in multidomain proteins that often also contain guanylate cyclase domains ([pfam:PF00211]). Proteins containing this domain include adenylate and guanylate cyclases. This family is found in bacteria (Actinomycetota, Myxococcota, Pseudomonadota) and eukaryotes. The function of this domain remains to be determined.", "domain_architectures": 78, "interpro_id": "IPR061800", "known_evidence_count": null, "matches": 691, "name": "Domain of unknown function (DUF8739)", "partial_evidence_count": null, "pfam_id": "PF30788", "proteins": 691, "proteomes": 517, "short_name": "DUF8739", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30788", "structures": 0, "taxa": 1190, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 439, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is found in bacteria. The function is not known.", "domain_architectures": 3, "interpro_id": "IPR019650", "known_evidence_count": null, "matches": 691, "name": "Hypothetical protein (DUF2513)", "partial_evidence_count": null, "pfam_id": "PF10711", "proteins": 690, "proteomes": 649, "short_name": "DUF2513", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10711", "structures": 0, "taxa": 1473, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 599, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 171 and 270 amino acids in length. There is a conserved STLGG sequence motif.", "domain_architectures": 23, "interpro_id": "IPR032072", "known_evidence_count": null, "matches": 693, "name": "Domain of unknown function (DUF4807)", "partial_evidence_count": null, "pfam_id": "PF16065", "proteins": 690, "proteomes": 583, "short_name": "DUF4807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16065", "structures": 0, "taxa": 1967, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 500, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in bacteria is functionally uncharacterised. Proteins in this family are typically between 113 and 127 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045655", "known_evidence_count": null, "matches": 690, "name": "Family of unknown function (DUF6394)", "partial_evidence_count": null, "pfam_id": "PF19931", "proteins": 690, "proteomes": 650, "short_name": "DUF6394", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19931", "structures": 0, "taxa": 1114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 387, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised proteins mainly from bacteria, but it is also found in eukaryotes. Some proteins containing this domain also contain zinc finger C2H2-type domains. There are three conserved motifs: TxI/V, RxFF and FxF, and a conserved W/Y residue at the C-terminal.", "domain_architectures": 4, "interpro_id": "IPR045492", "known_evidence_count": null, "matches": 690, "name": "Domain of unknown function (DUF6434)", "partial_evidence_count": null, "pfam_id": "PF20026", "proteins": 690, "proteomes": 679, "short_name": "DUF6434", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20026", "structures": 0, "taxa": 1147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 437, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to adopt an alpha-helical structure consisting of four helices. This domain contains several conserved aromatic hydrophobic residues that may have a functional role.", "domain_architectures": 95, "interpro_id": "IPR056010", "known_evidence_count": null, "matches": 695, "name": "Domain of unknown function (DUF7588)", "partial_evidence_count": null, "pfam_id": "PF24496", "proteins": 689, "proteomes": 56, "short_name": "DUF7588", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24496", "structures": 0, "taxa": 243, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 348, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Metazoa. It is predicted to fold into an alpha/beta stricture composed of mixed beta-sheet and helices packed on one side of it.", "domain_architectures": 25, "interpro_id": "IPR059425", "known_evidence_count": null, "matches": 703, "name": "Domain of unknown function (DUF8381)", "partial_evidence_count": null, "pfam_id": "PF28323", "proteins": 689, "proteomes": 9, "short_name": "DUF8381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28323", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 392, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021676", "known_evidence_count": null, "matches": 688, "name": "Protein of unknown function (DUF3262)", "partial_evidence_count": null, "pfam_id": "PF11660", "proteins": 688, "proteomes": 558, "short_name": "DUF3262", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11660", "structures": 0, "taxa": 958, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 357, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 340 residues in length and is mainly found in various Burkholderia and Brucella species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032581", "known_evidence_count": null, "matches": 690, "name": "Domain of unknown function (DUF4917)", "partial_evidence_count": null, "pfam_id": "PF16263", "proteins": 688, "proteomes": 653, "short_name": "DUF4917", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16263", "structures": 0, "taxa": 1284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 466, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 210 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR045622", "known_evidence_count": null, "matches": 694, "name": "Family of unknown function (DUF6441)", "partial_evidence_count": null, "pfam_id": "PF20039", "proteins": 688, "proteomes": 421, "short_name": "DUF6441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20039", "structures": 0, "taxa": 826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001931) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the carrimycin biosynthetic gene cluster from unidentified unclassified sequences. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046210", "known_evidence_count": null, "matches": 687, "name": "Family of unknown function (DUF6243)", "partial_evidence_count": null, "pfam_id": "PF19756", "proteins": 687, "proteomes": 534, "short_name": "DUF6243", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19756", "structures": 0, "taxa": 603, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 655, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised archaeal proteins. It is predicted to fold into a three-stranded antiparallel beta-sheet. It contains a highly conserved tryptophan residue located at the beginning of the third beta-strand.", "domain_architectures": 1, "interpro_id": "IPR055933", "known_evidence_count": null, "matches": 687, "name": "Domain of unknown function (DUF7511)", "partial_evidence_count": null, "pfam_id": "PF24351", "proteins": 687, "proteomes": 261, "short_name": "DUF7511", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24351", "structures": 0, "taxa": 410, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 14, "interpro_id": "IPR021451", "known_evidence_count": null, "matches": 687, "name": "Protein of unknown function (DUF3102)", "partial_evidence_count": null, "pfam_id": "PF11300", "proteins": 686, "proteomes": 427, "short_name": "DUF3102", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11300", "structures": 0, "taxa": 1009, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 456, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is only found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR021768", "known_evidence_count": null, "matches": 686, "name": "Domain of unknown function (DUF3332)", "partial_evidence_count": null, "pfam_id": "PF11810", "proteins": 686, "proteomes": 609, "short_name": "DUF3332", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11810", "structures": 0, "taxa": 930, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 590, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 464 and 550 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR031526", "known_evidence_count": null, "matches": 795, "name": "Domain of unknown function (DUF4698)", "partial_evidence_count": null, "pfam_id": "PF15769", "proteins": 686, "proteomes": 485, "short_name": "DUF4698", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15769", "structures": 0, "taxa": 1694, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Fungi. These proteins are likely involved in chromatin remodelling. The domain represented by this entry is predicted to fold into a globular structure with significant similarity to chromo domain ([pfam:PF00385]).", "domain_architectures": 16, "interpro_id": "IPR055565", "known_evidence_count": null, "matches": 687, "name": "Domain of unknown function (DUF7141)", "partial_evidence_count": null, "pfam_id": "PF23614", "proteins": 686, "proteomes": 671, "short_name": "DUF7141", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23614", "structures": 0, "taxa": 1318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 423, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 165 residues found in DEAD/DEAH box helicases. The domain is found C-terminal to Helicase_C ([pfam:PF00271]) and SNF2-rel_dom ([pfam:PF00176]) domains. These proteins include HepA-like helicases. This family is found in bacteria, predominantly Actinomycetota and Pseudomonadota. The function of this domain remains to be determined.", "domain_architectures": 10, "interpro_id": "IPR061802", "known_evidence_count": null, "matches": 687, "name": "Domain of unknown function (DUF8741)", "partial_evidence_count": null, "pfam_id": "PF30790", "proteins": 686, "proteomes": 670, "short_name": "DUF8741", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30790", "structures": 0, "taxa": 1517, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 417, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Bacillales lineage.", "domain_architectures": 3, "interpro_id": "IPR020139", "known_evidence_count": null, "matches": 685, "name": "Domain of unknown function (DUF2642)", "partial_evidence_count": null, "pfam_id": "PF10842", "proteins": 685, "proteomes": 570, "short_name": "DUF2642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10842", "structures": 0, "taxa": 798, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 380, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 3, "interpro_id": "IPR019276", "known_evidence_count": null, "matches": 685, "name": "Uncharacterized conserved protein (DUF2303)", "partial_evidence_count": null, "pfam_id": "PF10065", "proteins": 684, "proteomes": 614, "short_name": "DUF2303", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10065", "structures": 0, "taxa": 1241, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 392 and 433 amino acids in length. There is a conserved NNS sequence motif.", "domain_architectures": 7, "interpro_id": "IPR032627", "known_evidence_count": null, "matches": 684, "name": "Protein of unknown function (DUF4876)", "partial_evidence_count": null, "pfam_id": "PF16215", "proteins": 684, "proteomes": 476, "short_name": "DUF4876", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16215", "structures": 1, "taxa": 727, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This domain is found in the Telomerase protein component 1 (TEP1) and it contains an homology region to the telomerase associated protein from Tetrahymena p80 [[cite:PUB00099027]]. TEP1 is a component of the telomerase ribonucleoprotein complex and is thought to be responsible for catalysing the addition of new telomeres to chromosomes. TEP1 is also a component of the vault particle, a cytoplasmic ribonucleoprotein complex, in which it is required for vault RNA stability and its association with the vault particle [[cite:PUB00035328]]. This domain is localised between the TROVE ([pfam:PF05731]) and DUF4062 ([pfam:PF13271]) domains.", "domain_architectures": 244, "interpro_id": "IPR045804", "known_evidence_count": null, "matches": 699, "name": "Domain of unknown function (DUF5920)", "partial_evidence_count": null, "pfam_id": "PF19334", "proteins": 684, "proteomes": 387, "short_name": "DUF5920", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19334", "structures": 0, "taxa": 1447, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 426, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family includes sequences of largely unknown function but which share a number of features in common. They are expressed by bacterial species, and in many cases these bacteria are known to associate symbiotically with plants. Moreover, the majority are coded for by plasmids, which in many cases are known to confer on the organism the ability to interact symbiotically with leguminous plants. An example of such a plasmid is NGR234, which encodes Y4CF, a protein of unknown function that is a member of this family [[cite:PUB00004254]]. Other members of this family are expressed by organisms with a documented genomic similarity to plant symbionts [[cite:PUB00015202]].", "domain_architectures": 2, "interpro_id": "IPR011670", "known_evidence_count": null, "matches": 683, "name": "Protein of unknown function (DUF1612)", "partial_evidence_count": null, "pfam_id": "PF07756", "proteins": 683, "proteomes": 385, "short_name": "DUF1612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07756", "structures": 0, "taxa": 553, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 625, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 5, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 9 } }, "demotion_reasons": [], "description": "This domain is a CTP-dependent riboflavin kinase (RFK), found in archaea, that catalyses the phosphorylation of riboflavin to form flavin mononucleotide in riboflavin biosynthesis [ec:2.7.1.26]. Its structure resembles a RIFT barrel, structurally similar to but topologically distinct from bacterial and eukaryotic examples. The N-terminal is a winged helix-turn-helix DNA-binding domain, and the C-terminal half is most similar in sequence to a group of cradle-loop barrels. [swissprot:O28174] has this domain attached to [pfam:PF00325].", "domain_architectures": 18, "interpro_id": "IPR023602", "known_evidence_count": null, "matches": 683, "name": "Domain of unknown function DUF120", "partial_evidence_count": null, "pfam_id": "PF01982", "proteins": 682, "proteomes": 657, "short_name": "CTP-dep_RFKase", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01982", "structures": 8, "taxa": 1274, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain found in bacterial family of proteins which is a component of a contractile injection system related to phage sheath proteins [[cite:PUB00097484]].", "domain_architectures": 6, "interpro_id": "IPR019694", "known_evidence_count": null, "matches": 683, "name": "DUF2586, N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF10758", "proteins": 682, "proteomes": 578, "short_name": "DUF2586", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10758", "structures": 0, "taxa": 1112, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 405, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000387) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the mangotoxin biosynthetic gene cluster from Pseudomonas syringae pv. syringae [[cite:PUB00099371],[cite:PUB00099470]]. This family appears to be predominantly found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR046199", "known_evidence_count": null, "matches": 682, "name": "Family of unknown function (DUF6231)", "partial_evidence_count": null, "pfam_id": "PF19742", "proteins": 682, "proteomes": 680, "short_name": "DUF6231", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19742", "structures": 0, "taxa": 866, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 613, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes and include SNORC, a cartilage specific small membrane proteoglycan that plays a role in the regulation of chondrocyte maturation and postnatal endochondral ossification [[cite:PUB00088166],[cite:PUB00088164]]. There are two conserved sequence motifs: LGPGAI and LRKF.", "domain_architectures": 5, "interpro_id": "IPR031500", "known_evidence_count": null, "matches": 684, "name": "Small Novel Rich in Cartilage", "partial_evidence_count": null, "pfam_id": "PF15756", "proteins": 681, "proteomes": 636, "short_name": "DUF4690", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15756", "structures": 0, "taxa": 1981, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 458, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 8, "interpro_id": "IPR031989", "known_evidence_count": null, "matches": 705, "name": "Domain of unknown function (DUF5067)", "partial_evidence_count": null, "pfam_id": "PF16729", "proteins": 681, "proteomes": 500, "short_name": "DUF5067", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16729", "structures": 2, "taxa": 874, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 510, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 101 residues found in uncharacterized proteins in plants (Viridiplantae) and cyanobacteria. In plants, it is found predominantly in eudicotyledons and monocots. These are small single-domain proteins whose function is unknown.", "domain_architectures": 20, "interpro_id": "IPR061883", "known_evidence_count": null, "matches": 681, "name": "Domain of unknown function (DUF8822)", "partial_evidence_count": null, "pfam_id": "PF31137", "proteins": 681, "proteomes": 597, "short_name": "DUF8822", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31137", "structures": 0, "taxa": 1700, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in viruses, and is approximately 20 amino acids in length. The family is found in association with [pfam:PF00073]. There is a single completely conserved residue Y that may be functionally important.", "domain_architectures": 7, "interpro_id": "IPR022539", "known_evidence_count": null, "matches": 680, "name": "Protein of unknown function (DUF3724)", "partial_evidence_count": null, "pfam_id": "PF12521", "proteins": 680, "proteomes": 3, "short_name": "DUF3724", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12521", "structures": 15, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 486, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 100 amino acids in length. This domain contains an N-terminal HXE motif.", "domain_architectures": 12, "interpro_id": "IPR027876", "known_evidence_count": null, "matches": 700, "name": "Domain of unknown function (DUF4550)", "partial_evidence_count": null, "pfam_id": "PF15084", "proteins": 680, "proteomes": 437, "short_name": "DUF4550", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15084", "structures": 0, "taxa": 1650, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 400, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised.", "domain_architectures": 5, "interpro_id": "IPR014990", "known_evidence_count": null, "matches": 683, "name": "Protein of unknown function (DUF1838)", "partial_evidence_count": null, "pfam_id": "PF08894", "proteins": 679, "proteomes": 493, "short_name": "DUF1838", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08894", "structures": 0, "taxa": 1087, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 470, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chordata.", "domain_architectures": 7, "interpro_id": "IPR037656", "known_evidence_count": null, "matches": 890, "name": "Family of unknown function (DUF5525)", "partial_evidence_count": null, "pfam_id": "PF17663", "proteins": 678, "proteomes": 436, "short_name": "DUF5525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17663", "structures": 0, "taxa": 1478, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 379, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the domain of unknown function found in bacterial and fungal sequences, including some F5/8 type C domain-containing proteins such as Swissprot:A0A4V0YDU8. This domain may adopt a galactose-binding domain-like fold. This domain is found in several copies, predominantly between two and six times, and it is found in association with PIG-L ([pfam:PF02585]) domain.", "domain_architectures": 164, "interpro_id": "IPR055826", "known_evidence_count": null, "matches": 878, "name": "Domain of unknown function (DUF7402)", "partial_evidence_count": null, "pfam_id": "PF24135", "proteins": 677, "proteomes": 525, "short_name": "DUF7402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24135", "structures": 0, "taxa": 1077, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 379, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of phage related proteins whose function is uncharacterised.", "domain_architectures": 2, "interpro_id": "IPR019670", "known_evidence_count": null, "matches": 676, "name": "Protein of unknown function (DUF2523)", "partial_evidence_count": null, "pfam_id": "PF10734", "proteins": 676, "proteomes": 557, "short_name": "DUF2523", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10734", "structures": 0, "taxa": 1056, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 169 and 192 amino acids in length.", "domain_architectures": 16, "interpro_id": "IPR025409", "known_evidence_count": null, "matches": 679, "name": "Domain of unknown function (DUF4303)", "partial_evidence_count": null, "pfam_id": "PF14136", "proteins": 676, "proteomes": 596, "short_name": "DUF4303", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14136", "structures": 0, "taxa": 1125, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 416, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, eukaryotes and viruses. Proteins in this family are typically between 129 and 147 amino acids in length.", "domain_architectures": 16, "interpro_id": "IPR046163", "known_evidence_count": null, "matches": 675, "name": "Family of unknown function (DUF6165)", "partial_evidence_count": null, "pfam_id": "PF19662", "proteins": 675, "proteomes": 620, "short_name": "DUF6165", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19662", "structures": 0, "taxa": 1069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a middle domain found in DoxX family proteins from Bacteroidota. The domain is composed of three beta-strands forming a small beta-sheet and is around 40 residues in length. The domain is located between the N-terminal MauE domain ([pfam:PF07291]) and a C-terminal region. DoxX family proteins are found primarily in Bacteroidales, Chitinophagales and Cytophagales within the Bacteroidota phylum. The function of this domain remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061533", "known_evidence_count": null, "matches": 675, "name": "Domain of unknown function (DUF8463)", "partial_evidence_count": null, "pfam_id": "PF28800", "proteins": 675, "proteomes": 674, "short_name": "DUF8463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28800", "structures": 0, "taxa": 961, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 476, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of paralogous proteins in Rhodopirellula baltica.", "domain_architectures": 6, "interpro_id": "IPR011465", "known_evidence_count": null, "matches": 682, "name": "Protein of unknown function (DUF1571)", "partial_evidence_count": null, "pfam_id": "PF07608", "proteins": 673, "proteomes": 481, "short_name": "DUF1571", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07608", "structures": 0, "taxa": 669, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 480, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria and archaea. Proteins in this family are about 200 amino acids in length. The structure of protein [swissprot:Q63J81] from B. pseudomallei has been solved. This protein contains two domains, domain I (1:31, 46:81) is a helical domain, domain II (32:45,82-193) is a mainly beta protein with a beta barrel. According to crystal contacts the proteins probably functions as a dimer. The gene neighbourhood analysis suggests that this protein may be functionally related to rubrerythrin and ferredoxin. The wedge surface between the two domains might be functionally important. The fold of this protein could best be described as a circularly permuted C2-like fold (details derived from TOPSAN).", "domain_architectures": 2, "interpro_id": "IPR021890", "known_evidence_count": null, "matches": 673, "name": "Protein of unknown function (DUF3501)", "partial_evidence_count": null, "pfam_id": "PF12007", "proteins": 673, "proteomes": 663, "short_name": "DUF3501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12007", "structures": 1, "taxa": 1241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 486, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025373", "known_evidence_count": null, "matches": 673, "name": "Domain of unknown function (DUF4363)", "partial_evidence_count": null, "pfam_id": "PF14276", "proteins": 673, "proteomes": 581, "short_name": "DUF4363", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14276", "structures": 0, "taxa": 1038, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 621, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in archaeal tRNA-guanine transglycosylase ([ec:2.4.2.48]) and in archaeosine synthase ([ec:2.6.1.97]) proteins.", "domain_architectures": 11, "interpro_id": "IPR040777", "known_evidence_count": null, "matches": 673, "name": "Domain of unknown function (DUF5591)", "partial_evidence_count": null, "pfam_id": "PF17884", "proteins": 673, "proteomes": 532, "short_name": "DUF5591", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17884", "structures": 1, "taxa": 999, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 149 and 172 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046595", "known_evidence_count": null, "matches": 673, "name": "Family of unknown function (DUF6653)", "partial_evidence_count": null, "pfam_id": "PF20358", "proteins": 673, "proteomes": 632, "short_name": "DUF6653", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20358", "structures": 0, "taxa": 1200, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 453, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 400 to 434 amino acids in length. This protein has two conserved sequence motifs: NPV and DNNG.", "domain_architectures": 4, "interpro_id": "IPR021847", "known_evidence_count": null, "matches": 672, "name": "Protein of unknown function (DUF3443)", "partial_evidence_count": null, "pfam_id": "PF11925", "proteins": 672, "proteomes": 314, "short_name": "DUF3443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11925", "structures": 0, "taxa": 484, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 520, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 40 amino acids in length. The family is found in association with [pfam:PF00954], [pfam:PF01453], [pfam:PF00069], [pfam:PF08276]. There is a conserved ELPL sequence motif.", "domain_architectures": 68, "interpro_id": "IPR022126", "known_evidence_count": null, "matches": 684, "name": "Receptor serine/threonine kinase", "partial_evidence_count": null, "pfam_id": "PF12398", "proteins": 672, "proteomes": 196, "short_name": "DUF3660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12398", "structures": 0, "taxa": 551, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 408, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short protein of unknown function is found within the operon of a contractile injection system of Photorhabdus asymbiotica [swissprot:B6VNN9].", "domain_architectures": 2, "interpro_id": "IPR045459", "known_evidence_count": null, "matches": 672, "name": "Family of unknown function (DUF5908)", "partial_evidence_count": null, "pfam_id": "PF19265", "proteins": 672, "proteomes": 568, "short_name": "DUF5908", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19265", "structures": 3, "taxa": 1021, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 585, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are about 150 amino acids in length and have no known function.", "domain_architectures": 27, "interpro_id": "IPR013869", "known_evidence_count": null, "matches": 686, "name": "Protein of unknown function (DUF1757)", "partial_evidence_count": null, "pfam_id": "PF08560", "proteins": 671, "proteomes": 489, "short_name": "DUF1757", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08560", "structures": 1, "taxa": 1338, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 447, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR012190", "known_evidence_count": null, "matches": 671, "name": "Protein of unknown function (DUF4264)", "partial_evidence_count": null, "pfam_id": "PF14084", "proteins": 671, "proteomes": 670, "short_name": "DUF4264", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14084", "structures": 0, "taxa": 1001, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 560, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a four helical bundle domain found in a range of uncharacterised proteins. This domain is sometimes found in proteins that also contain [pfam:PF07762]. Shows similarity to the PsbQ superfamily.", "domain_architectures": 20, "interpro_id": "IPR057202", "known_evidence_count": null, "matches": 688, "name": "Domain of unknown function (DUF7880)", "partial_evidence_count": null, "pfam_id": "PF25306", "proteins": 671, "proteomes": 387, "short_name": "DUF7880", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25306", "structures": 0, "taxa": 1091, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 635, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised C. elegans proteins. The region represented by this family can is found to be repeated up to four time in some proteins.", "domain_architectures": 27, "interpro_id": "IPR006570", "known_evidence_count": null, "matches": 1023, "name": "Domain of unknown function (DUF545)", "partial_evidence_count": null, "pfam_id": "PF04435", "proteins": 670, "proteomes": 12, "short_name": "SPK", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04435", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 137 and 149 amino acids in length. This family may be distantly related to RelE proteins.", "domain_architectures": 9, "interpro_id": "IPR024265", "known_evidence_count": null, "matches": 670, "name": "Protein of unknown function (DUF3788)", "partial_evidence_count": null, "pfam_id": "PF12663", "proteins": 670, "proteomes": 498, "short_name": "DUF3788", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12663", "structures": 0, "taxa": 1094, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 404, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in bacteria.", "domain_architectures": 7, "interpro_id": "IPR043743", "known_evidence_count": null, "matches": 677, "name": "Family of unknown function (DUF5688)", "partial_evidence_count": null, "pfam_id": "PF18941", "proteins": 670, "proteomes": 274, "short_name": "DUF5688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18941", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 389, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. Proteins in this family are found in bacteria, are typically around 85 amino acids in length and have a conserved motif FxxGF.", "domain_architectures": 2, "interpro_id": "IPR049215", "known_evidence_count": null, "matches": 669, "name": "Family of unknown function (DUF6809)", "partial_evidence_count": null, "pfam_id": "PF20648", "proteins": 669, "proteomes": 288, "short_name": "DUF6809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20648", "structures": 0, "taxa": 493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region found in a bacterial protein which may be a hemagglutinin or hemolysin.", "domain_architectures": 229, "interpro_id": "IPR006915", "known_evidence_count": null, "matches": 676, "name": "Possible hemagglutinin (DUF637)", "partial_evidence_count": null, "pfam_id": "PF04830", "proteins": 668, "proteomes": 423, "short_name": "DUF637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04830", "structures": 0, "taxa": 751, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 554, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various putative metal binding prokaryotic proteins, has no known function.", "domain_architectures": 4, "interpro_id": "IPR018664", "known_evidence_count": null, "matches": 668, "name": "Predicted metal-binding protein (DUF2103)", "partial_evidence_count": null, "pfam_id": "PF09876", "proteins": 668, "proteomes": 662, "short_name": "DUF2103", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09876", "structures": 0, "taxa": 1430, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 401, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are approximately 170 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046730", "known_evidence_count": null, "matches": 668, "name": "Family of unknown function (DUF6622)", "partial_evidence_count": null, "pfam_id": "PF20327", "proteins": 668, "proteomes": 652, "short_name": "DUF6622", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20327", "structures": 0, "taxa": 986, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 392, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein domain that is often found in single domain proteins. It is also sometimes found in larger multi-domain proteins. The function of this domain is unknown.", "domain_architectures": 36, "interpro_id": "IPR049250", "known_evidence_count": null, "matches": 668, "name": "Domain of unknown function (DUF6883)", "partial_evidence_count": null, "pfam_id": "PF21814", "proteins": 668, "proteomes": 483, "short_name": "DUF6883", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21814", "structures": 0, "taxa": 1279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 426, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 56 and 93 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR025463", "known_evidence_count": null, "matches": 667, "name": "Domain of unknown function (DUF4314)", "partial_evidence_count": null, "pfam_id": "PF14192", "proteins": 667, "proteomes": 489, "short_name": "DUF4314", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14192", "structures": 0, "taxa": 1035, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 403, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is conserved in the Bacillales. The function is not known, but given this domain's relationship to the SIS domain it may carry out a sugar isomerase reaction. Several members are annotated as being YWJG, a protein expressed downstream of pyrG, a gene encoding for cytidine triphosphate synthetase.", "domain_architectures": 2, "interpro_id": "IPR019676", "known_evidence_count": null, "matches": 667, "name": "Domain of unknown function (DUF2529)", "partial_evidence_count": null, "pfam_id": "PF10740", "proteins": 666, "proteomes": 664, "short_name": "DUF2529", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10740", "structures": 1, "taxa": 849, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 430, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021490", "known_evidence_count": null, "matches": 666, "name": "Protein of unknown function (DUF3144)", "partial_evidence_count": null, "pfam_id": "PF11342", "proteins": 666, "proteomes": 585, "short_name": "DUF3144", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11342", "structures": 1, "taxa": 949, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 403, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in bacteria. These proteins share a conserved beta barrel domain with extensive variable insertions. The N and C-terminus of these proteins are the most conserved regions and interact with each other.", "domain_architectures": 2, "interpro_id": "IPR045633", "known_evidence_count": null, "matches": 666, "name": "Domain of unknown function (DUF6414)", "partial_evidence_count": null, "pfam_id": "PF19952", "proteins": 666, "proteomes": 627, "short_name": "DUF6414", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19952", "structures": 0, "taxa": 1423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 442, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 110 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025079", "known_evidence_count": null, "matches": 665, "name": "Domain of unknown function (DUF3943)", "partial_evidence_count": null, "pfam_id": "PF13084", "proteins": 665, "proteomes": 591, "short_name": "DUF3943", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13084", "structures": 0, "taxa": 993, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 400, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in a set of bacterial sequences, whose function is unknown.", "domain_architectures": 6, "interpro_id": "IPR055507", "known_evidence_count": null, "matches": 667, "name": "Domain of unknown function (DUF7079)", "partial_evidence_count": null, "pfam_id": "PF23296", "proteins": 665, "proteomes": 614, "short_name": "DUF7079", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23296", "structures": 0, "taxa": 1111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 523 and 1105 amino acids in length.", "domain_architectures": 32, "interpro_id": "IPR045392", "known_evidence_count": null, "matches": 1268, "name": "Family of unknown function (DUF6519)", "partial_evidence_count": null, "pfam_id": "PF20129", "proteins": 664, "proteomes": 641, "short_name": "DUF6519", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20129", "structures": 0, "taxa": 1250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 404, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a group of hypothetical bacterial proteins that contain three conserved cysteine residues towards the N-terminal. The function of these proteins is unknown.", "domain_architectures": 3, "interpro_id": "IPR009553", "known_evidence_count": null, "matches": 673, "name": "Protein of unknown function (DUF1173)", "partial_evidence_count": null, "pfam_id": "PF06666", "proteins": 663, "proteomes": 552, "short_name": "DUF1173", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06666", "structures": 0, "taxa": 924, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000406) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the phosphinothricintripeptide biosynthetic gene cluster from Streptomyces viridochromogenes [[cite:PUB00098894]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR045652", "known_evidence_count": null, "matches": 665, "name": "Family of unknown function (DUF6397)", "partial_evidence_count": null, "pfam_id": "PF19934", "proteins": 662, "proteomes": 655, "short_name": "DUF6397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19934", "structures": 0, "taxa": 719, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 357, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a set of uncharacterised bacterial proteins. Structure prediction shows them to be composed of three alpha helices.", "domain_architectures": 4, "interpro_id": "IPR056077", "known_evidence_count": null, "matches": 662, "name": "Family of unknown function (DUF7660)", "partial_evidence_count": null, "pfam_id": "PF24693", "proteins": 662, "proteomes": 631, "short_name": "DUF7660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24693", "structures": 0, "taxa": 1178, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 533, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from plants. It is predicted to adopt a structure consisting of a mixed beta-sheet and alpha-helices packed on both sides with unique topology. It contains a highly conserved sequence motif RxKxRKG that contributes to the formation of a highly basic surface patch.", "domain_architectures": 8, "interpro_id": "IPR057173", "known_evidence_count": null, "matches": 668, "name": "Domain of unknown function (DUF7851)", "partial_evidence_count": null, "pfam_id": "PF25236", "proteins": 662, "proteomes": 341, "short_name": "DUF7851", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25236", "structures": 0, "taxa": 955, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 226, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in a wide range of bacterial cell surface proteins. It is predicted to adopt a beta-sandwich with Ig-like topology.", "domain_architectures": 93, "interpro_id": "", "known_evidence_count": null, "matches": 662, "name": "DUF6701, second domain", "partial_evidence_count": null, "pfam_id": "PF28243", "proteins": 662, "proteomes": 616, "short_name": "DUF6701_2nd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28243", "structures": 0, "taxa": 932, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 332, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This predicted winged helix domain is found in a group of uncharacterised fungal proteins. It is often found associated with [pfam:PF00145].", "domain_architectures": 14, "interpro_id": "IPR057215", "known_evidence_count": null, "matches": 661, "name": "Domain of unknown function (DUF7893)", "partial_evidence_count": null, "pfam_id": "PF25423", "proteins": 661, "proteomes": 632, "short_name": "DUF7893", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25423", "structures": 3, "taxa": 1339, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 420, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a globular structure composed of array of alpha-helices. It contains several highly conserved negatively charged residues that cluster in space and may be important for function.", "domain_architectures": 8, "interpro_id": "IPR059414", "known_evidence_count": null, "matches": 662, "name": "Domain of unknown function (DUF8370)", "partial_evidence_count": null, "pfam_id": "PF28123", "proteins": 661, "proteomes": 633, "short_name": "DUF8370", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28123", "structures": 0, "taxa": 1481, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in bacteria. This entry represents a likely integral membrane region with six transmembrane helices. The family is found in association with [pfam:PF11141].", "domain_architectures": 2, "interpro_id": "IPR045968", "known_evidence_count": null, "matches": 660, "name": "Family of unknown function (DUF5924)", "partial_evidence_count": null, "pfam_id": "PF19346", "proteins": 660, "proteomes": 653, "short_name": "DUF5924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19346", "structures": 0, "taxa": 820, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 536, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a globular structure consisting of a antiparallel beta-sheet curved around a central alpha-helix.", "domain_architectures": 13, "interpro_id": "IPR056706", "known_evidence_count": null, "matches": 661, "name": "Domain of unknown function (DUF7804)", "partial_evidence_count": null, "pfam_id": "PF25089", "proteins": 660, "proteomes": 354, "short_name": "DUF7804", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25089", "structures": 0, "taxa": 992, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 448, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021267", "known_evidence_count": null, "matches": 659, "name": "Protein of unknown function (DUF2844)", "partial_evidence_count": null, "pfam_id": "PF11005", "proteins": 659, "proteomes": 303, "short_name": "DUF2844", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11005", "structures": 0, "taxa": 447, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 348, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 111 and 149 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR024984", "known_evidence_count": null, "matches": 659, "name": "Protein of unknown function (DUF3888)", "partial_evidence_count": null, "pfam_id": "PF13027", "proteins": 659, "proteomes": 468, "short_name": "DUF3888", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13027", "structures": 0, "taxa": 659, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 393, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 3, "interpro_id": "IPR011090", "known_evidence_count": null, "matches": 658, "name": "Protein of unknown function (DUF1525)", "partial_evidence_count": null, "pfam_id": "PF07511", "proteins": 658, "proteomes": 525, "short_name": "DUF1525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07511", "structures": 0, "taxa": 941, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Proteobacteria. Proteins in this family are typically between 80 and 101 amino acids in length and contain four conserved cysteine residues at the C-terminal.", "domain_architectures": 1, "interpro_id": "IPR046494", "known_evidence_count": null, "matches": 658, "name": "Family of unknown function (DUF6587)", "partial_evidence_count": null, "pfam_id": "PF20228", "proteins": 658, "proteomes": 658, "short_name": "DUF6587", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20228", "structures": 0, "taxa": 842, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 536, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to fold into an alpha-helical bundle.", "domain_architectures": 30, "interpro_id": "IPR056700", "known_evidence_count": null, "matches": 679, "name": "Domain of unknown function (DUF7798)", "partial_evidence_count": null, "pfam_id": "PF25074", "proteins": 658, "proteomes": 383, "short_name": "DUF7798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25074", "structures": 0, "taxa": 1066, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 220 residues found in bacteria, predominantly Proteobacteria. This domain is typically located N-terminal to HNH nuclease domains ([pfam:PF13395]). Some proteins containing this domain also possess methyltransferase domains, suggesting a role in restriction-modification systems. The function of this domain remains to be determined.", "domain_architectures": 16, "interpro_id": "IPR061869", "known_evidence_count": null, "matches": 658, "name": "Domain of unknown function (DUF8808)", "partial_evidence_count": null, "pfam_id": "PF31103", "proteins": 658, "proteomes": 628, "short_name": "DUF8808", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31103", "structures": 0, "taxa": 1188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 361, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 2, "interpro_id": "IPR035242", "known_evidence_count": null, "matches": 657, "name": "Family of unknown function (DUF5329)", "partial_evidence_count": null, "pfam_id": "PF17263", "proteins": 657, "proteomes": 645, "short_name": "DUF5329", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17263", "structures": 0, "taxa": 1050, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 455, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Bacillales.", "domain_architectures": 6, "interpro_id": "IPR035272", "known_evidence_count": null, "matches": 657, "name": "Family of unknown function (DUF5351)", "partial_evidence_count": null, "pfam_id": "PF17302", "proteins": 657, "proteomes": 560, "short_name": "DUF5351", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17302", "structures": 0, "taxa": 1296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 399, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised bacterial proteins. This domain is about 70 amino acids in length and contains the conserved sequence motifs WK, RS and TxxG.", "domain_architectures": 7, "interpro_id": "IPR045489", "known_evidence_count": null, "matches": 656, "name": "Domain of unknown function (DUF6429)", "partial_evidence_count": null, "pfam_id": "PF20008", "proteins": 656, "proteomes": 588, "short_name": "DUF6429", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20008", "structures": 0, "taxa": 1170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 487, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is approximately 57 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR046625", "known_evidence_count": null, "matches": 655, "name": "Domain of unknown function (DUF6737)", "partial_evidence_count": null, "pfam_id": "PF20522", "proteins": 655, "proteomes": 549, "short_name": "DUF6737", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20522", "structures": 0, "taxa": 1559, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 468, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. There is a conserved SQREIE sequence motif.", "domain_architectures": 1, "interpro_id": "IPR045471", "known_evidence_count": null, "matches": 654, "name": "Family of unknown function (DUF6494)", "partial_evidence_count": null, "pfam_id": "PF20104", "proteins": 654, "proteomes": 642, "short_name": "DUF6494", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20104", "structures": 0, "taxa": 1039, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 526, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is fund in uncharacterised plant proteins. It is predicted to fold into alpha- helical bundle.", "domain_architectures": 25, "interpro_id": "IPR056697", "known_evidence_count": null, "matches": 671, "name": "Domain of unknown function (DUF7795)", "partial_evidence_count": null, "pfam_id": "PF25071", "proteins": 654, "proteomes": 349, "short_name": "DUF7795", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25071", "structures": 0, "taxa": 970, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 545, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins conserved in fungi. The function is not known.", "domain_architectures": 10, "interpro_id": "IPR018830", "known_evidence_count": null, "matches": 659, "name": "Protein of unknown function (DUF2434)", "partial_evidence_count": null, "pfam_id": "PF10361", "proteins": 653, "proteomes": 643, "short_name": "DUF2434", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10361", "structures": 0, "taxa": 1299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 624, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Caenorhabditis elegans.", "domain_architectures": 16, "interpro_id": "IPR022559", "known_evidence_count": null, "matches": 659, "name": "Protein of unknown function (DUF2650)", "partial_evidence_count": null, "pfam_id": "PF10853", "proteins": 653, "proteomes": 95, "short_name": "DUF2650", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10853", "structures": 0, "taxa": 225, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 397, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 90 residues in length. Members of this family seem to be found exclusively in the Orders Vibrionales and Enterobacteriales. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009971", "known_evidence_count": null, "matches": 652, "name": "Protein of unknown function (DUF1496)", "partial_evidence_count": null, "pfam_id": "PF07383", "proteins": 652, "proteomes": 636, "short_name": "DUF1496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07383", "structures": 0, "taxa": 960, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 540, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in metazoa. This family includes human protein C12orf56.", "domain_architectures": 12, "interpro_id": "IPR027878", "known_evidence_count": null, "matches": 816, "name": "Protein of unknown function (DUF4551)", "partial_evidence_count": null, "pfam_id": "PF15087", "proteins": 652, "proteomes": 416, "short_name": "DUF4551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15087", "structures": 0, "taxa": 1532, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function which is mostly found in Bacteria.", "domain_architectures": 1, "interpro_id": "IPR035220", "known_evidence_count": null, "matches": 652, "name": "Family of unknown function (DUF5330)", "partial_evidence_count": null, "pfam_id": "PF17264", "proteins": 652, "proteomes": 651, "short_name": "DUF5330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17264", "structures": 0, "taxa": 861, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 175 and 193 amino acids in length. Many proteins in this family are annotated as catalase, but this could not be verified.", "domain_architectures": 6, "interpro_id": "IPR043721", "known_evidence_count": null, "matches": 653, "name": "Family of unknown function (DUF5662)", "partial_evidence_count": null, "pfam_id": "PF18907", "proteins": 652, "proteomes": 587, "short_name": "DUF5662", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18907", "structures": 0, "taxa": 1355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an NTF2-like domain found in a family of uncharacterised proteins predominantly found in the Nocardiaceae family within the Actinomycetota phylum. The proteins in this family are typically found in bacteria, with a notable presence in genera such as Nocardia and Rhodococcus. The proteins are generally around 200 to 300 amino acids in length. Many of these proteins are predicted to be membrane-associated, as indicated by the presence of transmembrane helices. The exact function of this family remains unknown.", "domain_architectures": 2, "interpro_id": "IPR058489", "known_evidence_count": null, "matches": 652, "name": "Domain of unknown function (DUF8176)", "partial_evidence_count": null, "pfam_id": "PF26527", "proteins": 652, "proteomes": 201, "short_name": "DUF8176", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26527", "structures": 0, "taxa": 255, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 461, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR019206", "known_evidence_count": null, "matches": 651, "name": "Predicted membrane protein (DUF2085)", "partial_evidence_count": null, "pfam_id": "PF09858", "proteins": 651, "proteomes": 567, "short_name": "DUF2085", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09858", "structures": 0, "taxa": 1259, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 525, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 161 and 601 amino acids in length.", "domain_architectures": 16, "interpro_id": "IPR028042", "known_evidence_count": null, "matches": 711, "name": "Domain of unknown function (DUF4639)", "partial_evidence_count": null, "pfam_id": "PF15479", "proteins": 651, "proteomes": 483, "short_name": "DUF4639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15479", "structures": 0, "taxa": 1856, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 392, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001612) is described by MIBiG as an example of the following biosynthetic class, alkaloid. It includes a member from the ambiguine H isonitrile biosynthetic gene cluster from Fischerella ambigua UTEX 1903 [[cite:PUB00099402]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR046192", "known_evidence_count": null, "matches": 651, "name": "Family of unknown function (DUF6220)", "partial_evidence_count": null, "pfam_id": "PF19728", "proteins": 651, "proteomes": 546, "short_name": "DUF6220", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19728", "structures": 0, "taxa": 988, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 530, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to adopt a globular structure with similarity to members of the Kinetochore globular domain-like superfamily.", "domain_architectures": 26, "interpro_id": "IPR056708", "known_evidence_count": null, "matches": 657, "name": "Domain of unknown function (DUF7806)", "partial_evidence_count": null, "pfam_id": "PF25091", "proteins": 651, "proteomes": 345, "short_name": "DUF7806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25091", "structures": 0, "taxa": 971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised sequences from bacteria, mainly from Streptomyces. It may constitute transmembrane helices.", "domain_architectures": 4, "interpro_id": "IPR061531", "known_evidence_count": null, "matches": 651, "name": "Domain of unknown function (DUF8461)", "partial_evidence_count": null, "pfam_id": "PF28792", "proteins": 651, "proteomes": 533, "short_name": "DUF8461", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28792", "structures": 0, "taxa": 755, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 43 residues found in uncharacterized proteins in Streptomycetaceae. The STRING analysis indicates functional association with hydrolase domains ([pfam:PF00561], PF12146, PF12697). This domain is predicted to adopt a simple structure composed of three-stranded beta-sheet and an alpha-helix. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061895", "known_evidence_count": null, "matches": 651, "name": "Domain of unknown function (DUF8834)", "partial_evidence_count": null, "pfam_id": "PF31185", "proteins": 651, "proteomes": 641, "short_name": "DUF8834", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31185", "structures": 0, "taxa": 696, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 375, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus spp.", "domain_architectures": 2, "interpro_id": "IPR020516", "known_evidence_count": null, "matches": 664, "name": "Protein of unknown function (DUF2653)", "partial_evidence_count": null, "pfam_id": "PF10850", "proteins": 650, "proteomes": 620, "short_name": "DUF2653", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10850", "structures": 0, "taxa": 733, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 367, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 212 and 228 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046737", "known_evidence_count": null, "matches": 651, "name": "Family of unknown function (DUF6629)", "partial_evidence_count": null, "pfam_id": "PF20334", "proteins": 650, "proteomes": 628, "short_name": "DUF6629", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20334", "structures": 0, "taxa": 1107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 449, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is primarily found in proteobacteria. Proteins in this family are typically between 124 and 153 amino acids in length. Proteins in this family has several conserved histidine residues that may form zinc binding sites.", "domain_architectures": 4, "interpro_id": "IPR054061", "known_evidence_count": null, "matches": 667, "name": "Domain of unknown function (DUF6915)", "partial_evidence_count": null, "pfam_id": "PF21866", "proteins": 650, "proteomes": 496, "short_name": "DUF6915", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21866", "structures": 0, "taxa": 987, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 617, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised halobacterial proteins. The domain adopts a compact domain structure composed of a twisted 5 stranded sheet with a C-terminal alpha helix.", "domain_architectures": 2, "interpro_id": "IPR058273", "known_evidence_count": null, "matches": 650, "name": "Family of unknown function (DUF7967)", "partial_evidence_count": null, "pfam_id": "PF25921", "proteins": 650, "proteomes": 277, "short_name": "DUF7967", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25921", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins.", "domain_architectures": 2, "interpro_id": "IPR015082", "known_evidence_count": null, "matches": 650, "name": "Domain of unknown function (DUF1896)", "partial_evidence_count": null, "pfam_id": "PF08989", "proteins": 649, "proteomes": 351, "short_name": "DUF1896", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08989", "structures": 1, "taxa": 539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 442, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Lactobacillales.", "domain_architectures": 2, "interpro_id": "IPR021351", "known_evidence_count": null, "matches": 649, "name": "Protein of unknown function (DUF2969)", "partial_evidence_count": null, "pfam_id": "PF11184", "proteins": 649, "proteomes": 649, "short_name": "DUF2969", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11184", "structures": 0, "taxa": 921, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 376, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 183 and 197 amino acids in length. Based on similarity to [pfam:PF03188] these proteins may be cytochromes.", "domain_architectures": 4, "interpro_id": "IPR045382", "known_evidence_count": null, "matches": 649, "name": "Family of unknown function (DUF6529)", "partial_evidence_count": null, "pfam_id": "PF20139", "proteins": 649, "proteomes": 614, "short_name": "DUF6529", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20139", "structures": 0, "taxa": 807, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 504, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to fold into a six-stranded beta-barrel. Inserted in this barrel is an alpha-helix that packs on the barrel side and it is enriched with positively charged residues which may have a functional importance.", "domain_architectures": 34, "interpro_id": "IPR056011", "known_evidence_count": null, "matches": 657, "name": "Domain of unknown function (DUF7589)", "partial_evidence_count": null, "pfam_id": "PF24500", "proteins": 649, "proteomes": 365, "short_name": "DUF7589", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24500", "structures": 0, "taxa": 1013, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 416, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes the B. subtilis YdiK protein [swissprot:O05524], which is functionally uncharacterised. This is not a homologue of E. coli YdiK, which belongs to [pfam:PF01594]. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025426", "known_evidence_count": null, "matches": 648, "name": "Domain of unknown function (DUF4305)", "partial_evidence_count": null, "pfam_id": "PF14146", "proteins": 648, "proteomes": 647, "short_name": "DUF4305", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14146", "structures": 0, "taxa": 840, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 386, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a small family of proteins from several bacterial species, whose function is not known. It may, however, be related to the GvpL_GvpF family of proteins, [pfam:PF06386].", "domain_architectures": 5, "interpro_id": "IPR024291", "known_evidence_count": null, "matches": 648, "name": "Protein of unknown function (DUF3829)", "partial_evidence_count": null, "pfam_id": "PF12889", "proteins": 647, "proteomes": 543, "short_name": "DUF3829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12889", "structures": 0, "taxa": 931, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 352, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several bacteriophage proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR007927", "known_evidence_count": null, "matches": 647, "name": "Protein of unknown function (DUF722)", "partial_evidence_count": null, "pfam_id": "PF05263", "proteins": 646, "proteomes": 530, "short_name": "DUF722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05263", "structures": 0, "taxa": 1075, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial immunoglobulin-like (Big) domain of approximately 150 residues. The domain is found in multi-domain proteins that also contain the DUF7408 domain ([pfam:PF24157]). This family is restricted to Bacillota, particularly Bacillales (including Paenibacillus and Bacillaceae) and Clostridia. The function of this domain remains to be determined.", "domain_architectures": 9, "interpro_id": "IPR061786", "known_evidence_count": null, "matches": 645, "name": "Domain of unknown function (DUF8725)", "partial_evidence_count": null, "pfam_id": "PF30766", "proteins": 645, "proteomes": 595, "short_name": "DUF8725", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30766", "structures": 0, "taxa": 991, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 438, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 159 and 176 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046740", "known_evidence_count": null, "matches": 644, "name": "Family of unknown function (DUF6790)", "partial_evidence_count": null, "pfam_id": "PF20589", "proteins": 644, "proteomes": 582, "short_name": "DUF6790", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20589", "structures": 0, "taxa": 1108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 308, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a set of uncharacterised bacterial and phage proteins that are annotated as putative holins.", "domain_architectures": 4, "interpro_id": "IPR057700", "known_evidence_count": null, "matches": 644, "name": "Family of unknown function (DUF7940)", "partial_evidence_count": null, "pfam_id": "PF25612", "proteins": 644, "proteomes": 540, "short_name": "DUF7940", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25612", "structures": 0, "taxa": 986, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 322, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 98 and 145 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR025518", "known_evidence_count": null, "matches": 643, "name": "Domain of unknown function (DUF4406)", "partial_evidence_count": null, "pfam_id": "PF14359", "proteins": 643, "proteomes": 576, "short_name": "DUF4406", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14359", "structures": 0, "taxa": 1293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 387, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain forms the N-terminal, extracellular domain of some homologs of Staph BlaR1 proteases, where it replaces the penicillin-binding domain of BlaR1. It is also found in many uncharacterised proteins in a broad range of bacteria. Its association with BlaR1 homologues suggests it may be involved in substrate-, possibly antibiotic-binding, but this prediction has not been verified experimentally.", "domain_architectures": 16, "interpro_id": "IPR032250", "known_evidence_count": null, "matches": 643, "name": "Domain of unknown function (DUF4825)", "partial_evidence_count": null, "pfam_id": "PF16107", "proteins": 643, "proteomes": 613, "short_name": "DUF4825", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16107", "structures": 0, "taxa": 1000, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are all Gammaproteobacteria. The function is not known.", "domain_architectures": 2, "interpro_id": "IPR019638", "known_evidence_count": null, "matches": 643, "name": "Protein of unknown function (DUF2502)", "partial_evidence_count": null, "pfam_id": "PF10697", "proteins": 642, "proteomes": 406, "short_name": "DUF2502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10697", "structures": 0, "taxa": 563, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 428, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminus of a family of uncharacterised proteins from Pseudomonadati bacteria. Structure prediction suggests that this domain mediates homodimerisation.", "domain_architectures": 1, "interpro_id": "IPR061746", "known_evidence_count": null, "matches": 642, "name": "Domain of unknown function (DUF8685)", "partial_evidence_count": null, "pfam_id": "PF30640", "proteins": 642, "proteomes": 641, "short_name": "DUF8685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30640", "structures": 0, "taxa": 917, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 404, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domainfound in proteins that are functionally uncharacterised. It is likely to adopt papain-like fold.", "domain_architectures": 3, "interpro_id": "IPR014989", "known_evidence_count": null, "matches": 642, "name": "DUF1839 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF08893", "proteins": 641, "proteomes": 582, "short_name": "DUF1839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08893", "structures": 0, "taxa": 834, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 404, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It usually follows domain with papain-like fold.", "domain_architectures": 3, "interpro_id": "IPR062933", "known_evidence_count": null, "matches": 641, "name": "DUF1839 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF30709", "proteins": 641, "proteomes": 582, "short_name": "DUF1839_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30709", "structures": 0, "taxa": 834, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 375, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is found in bacteria and eukaryotes. Proteins in this family are typically between 943 to 1234 amino acids in length. This family contains a P-loop motif suggesting it is a nucleotide binding protein. It may be involved in replication.", "domain_architectures": 2, "interpro_id": "IPR021979", "known_evidence_count": null, "matches": 645, "name": "Protein of unknown function (DUF3584)", "partial_evidence_count": null, "pfam_id": "PF12128", "proteins": 640, "proteomes": 605, "short_name": "DUF3584", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12128", "structures": 0, "taxa": 1051, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 393, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045441", "known_evidence_count": null, "matches": 723, "name": "Family of unknown function (DUF6506)", "partial_evidence_count": null, "pfam_id": "PF20116", "proteins": 640, "proteomes": 613, "short_name": "DUF6506", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20116", "structures": 0, "taxa": 1248, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 322, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains a number of highly conserved positively charged residues that may have functional role.", "domain_architectures": 5, "interpro_id": "IPR054277", "known_evidence_count": null, "matches": 641, "name": "Domain of unknown function (DUF7008)", "partial_evidence_count": null, "pfam_id": "PF22654", "proteins": 640, "proteomes": 571, "short_name": "DUF7008", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22654", "structures": 0, "taxa": 961, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 530, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a beta-meander that coils to form an open barrel-like structure.", "domain_architectures": 15, "interpro_id": "IPR056683", "known_evidence_count": null, "matches": 649, "name": "Domain of unknown function (DUF7781)", "partial_evidence_count": null, "pfam_id": "PF25003", "proteins": 640, "proteomes": 402, "short_name": "DUF7781", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25003", "structures": 0, "taxa": 1114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 437, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial immunoglobulin-like (Big) domain of approximately 100 residues. The domain is found at the N-terminus of multi-domain proteins that also contain the DUF7408 domain ([pfam:PF24157]). Structural similarity searches identify this as a member of the E-set Ig-like superfamily. This family is restricted to Bacillota, particularly Bacillales (including Paenibacillus and Bacillaceae) and Clostridia. The function of this domain remains to be determined.", "domain_architectures": 10, "interpro_id": "IPR061787", "known_evidence_count": null, "matches": 640, "name": "Domain of unknown function (DUF8726)", "partial_evidence_count": null, "pfam_id": "PF30767", "proteins": 640, "proteomes": 586, "short_name": "DUF8726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30767", "structures": 0, "taxa": 1022, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 389, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 200 residues in length and is mainly found in various Pseudomonas species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032609", "known_evidence_count": null, "matches": 639, "name": "Domain of unknown function (DUF4893)", "partial_evidence_count": null, "pfam_id": "PF16233", "proteins": 639, "proteomes": 542, "short_name": "DUF4893", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16233", "structures": 0, "taxa": 762, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 408, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 412 and 454 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046578", "known_evidence_count": null, "matches": 677, "name": "Family of unknown function (DUF6638)", "partial_evidence_count": null, "pfam_id": "PF20343", "proteins": 639, "proteomes": 634, "short_name": "DUF6638", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20343", "structures": 0, "taxa": 937, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised bacterial protein domain. This domain is found in single domain proteins as well as in large multidomain proteins that contain immunity related domains. This suggests that this family may play a role in a toxin/antitoxin system. The domain contains two structural sites that contain two conserved histidines and an aspartate that may be functionally important.", "domain_architectures": 23, "interpro_id": "IPR057154", "known_evidence_count": null, "matches": 639, "name": "Domain of unknown function (DUF7832)", "partial_evidence_count": null, "pfam_id": "PF25191", "proteins": 639, "proteomes": 594, "short_name": "DUF7832", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25191", "structures": 0, "taxa": 1108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 441, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 281 and 297 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR022208", "known_evidence_count": null, "matches": 639, "name": "Protein of unknown function (DUF3737)", "partial_evidence_count": null, "pfam_id": "PF12541", "proteins": 638, "proteomes": 581, "short_name": "DUF3737", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12541", "structures": 0, "taxa": 1076, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 425, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised and is found in bacteria and eukaryotes. It may contain an ATP-grasp-like fold which suggest an ATP-binding function. There are several conserved motifs: EGxxR, PxxWxxDF and ExNCSCV.", "domain_architectures": 23, "interpro_id": "IPR049212", "known_evidence_count": null, "matches": 748, "name": "Domain of unknown function (DUF6815)", "partial_evidence_count": null, "pfam_id": "PF20668", "proteins": 638, "proteomes": 456, "short_name": "DUF6815", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20668", "structures": 0, "taxa": 821, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 417, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial protein forms a likely integral membrane beta barrel domain.", "domain_architectures": 1, "interpro_id": "IPR049236", "known_evidence_count": null, "matches": 638, "name": "Family of unknown function (DUF6850)", "partial_evidence_count": null, "pfam_id": "PF21012", "proteins": 638, "proteomes": 472, "short_name": "DUF6850", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21012", "structures": 0, "taxa": 715, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 385, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain found central in a family of proteobacterial zinc ribbon proteins. Their exact function has not as yet been defined. This domain shares significant similarity with some CdiI immunity proteins.", "domain_architectures": 5, "interpro_id": "IPR016908", "known_evidence_count": null, "matches": 637, "name": "Domain of unknown function (DUF2310)", "partial_evidence_count": null, "pfam_id": "PF10071", "proteins": 637, "proteomes": 634, "short_name": "DUF2310", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10071", "structures": 0, "taxa": 953, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 411, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021350", "known_evidence_count": null, "matches": 637, "name": "Protein of unknown function (DUF2968)", "partial_evidence_count": null, "pfam_id": "PF11180", "proteins": 637, "proteomes": 362, "short_name": "DUF2968", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11180", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 590, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are found in various Trypanosomatida hypothetical proteins, as well as in the cysteine protease calpain. Their exact function has not, as yet, been defined. This domain adopts a jelly-roll fold.", "domain_architectures": 11, "interpro_id": "IPR015232", "known_evidence_count": null, "matches": 775, "name": "Domain of unknown function (DUF1935)", "partial_evidence_count": null, "pfam_id": "PF09149", "proteins": 636, "proteomes": 29, "short_name": "DUF1935", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09149", "structures": 2, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 536, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of sequences coming from hypothetical proteins found in both bacterial and archaeal species.", "domain_architectures": 3, "interpro_id": "IPR011672", "known_evidence_count": null, "matches": 635, "name": "Protein of unknown function (DUF1614)", "partial_evidence_count": null, "pfam_id": "PF07758", "proteins": 635, "proteomes": 559, "short_name": "DUF1614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07758", "structures": 0, "taxa": 1340, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 424, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR019620", "known_evidence_count": null, "matches": 635, "name": "Protein of unknown function (DUF2492)", "partial_evidence_count": null, "pfam_id": "PF10678", "proteins": 635, "proteomes": 634, "short_name": "DUF2492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10678", "structures": 0, "taxa": 981, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 461, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a ubiquitin-like fold domain found in a range of bacterial proteins. These proteins usually have an adjacent HNH domain to the C-terminus ([pfam:PF13391]). The function of this domain is unknown.", "domain_architectures": 11, "interpro_id": "IPR057203", "known_evidence_count": null, "matches": 636, "name": "Domain of unknown function (DUF8573)", "partial_evidence_count": null, "pfam_id": "PF25324", "proteins": 635, "proteomes": 146, "short_name": "DUF8573", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25324", "structures": 0, "taxa": 398, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 365, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of phage proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR024400", "known_evidence_count": null, "matches": 634, "name": "Protein of unknown function (DUF2635)", "partial_evidence_count": null, "pfam_id": "PF10948", "proteins": 634, "proteomes": 563, "short_name": "DUF2635", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10948", "structures": 0, "taxa": 990, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 496, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of hypothetical proteins in Rhodopirellula baltica. This family carries a highly conserved HExxH sequence motif characteristic of members of the Peptidase clan MA.", "domain_architectures": 15, "interpro_id": "IPR011464", "known_evidence_count": null, "matches": 633, "name": "Protein of unknown function (DUF1570)", "partial_evidence_count": null, "pfam_id": "PF07607", "proteins": 633, "proteomes": 319, "short_name": "DUF1570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07607", "structures": 0, "taxa": 625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 334, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function. The domain is found in bacteria, primarily in cyanobacteria and their phage. It is typically around 80-90 amino acids in length. AlphaFold prediction suggests this protein is composed of two longer paired alpha helices followed by a shorter third helix.", "domain_architectures": 3, "interpro_id": "IPR055643", "known_evidence_count": null, "matches": 633, "name": "Family of unknown function (DUF7219)", "partial_evidence_count": null, "pfam_id": "PF23856", "proteins": 633, "proteomes": 276, "short_name": "DUF7219", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23856", "structures": 0, "taxa": 780, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 394, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is found in bacteria and eukaryotes. Proteins in this family are about 250 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR020909", "known_evidence_count": null, "matches": 631, "name": "Protein of unknown function (DUF3603)", "partial_evidence_count": null, "pfam_id": "PF12227", "proteins": 631, "proteomes": 612, "short_name": "DUF3603", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12227", "structures": 1, "taxa": 833, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 380, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a zinc ribbon domain found in a family of proteobacterial proteins. Their exact function has not yet been defined.", "domain_architectures": 4, "interpro_id": "IPR061655", "known_evidence_count": null, "matches": 631, "name": "Domain of unknown function (DUF8594)", "partial_evidence_count": null, "pfam_id": "PF29880", "proteins": 630, "proteomes": 627, "short_name": "DUF8594", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29880", "structures": 0, "taxa": 943, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents family of uncharacterised proteins. They share an N-terminal CPF/Y motif that is characteristic of the NCPF superfamily of proteins.", "domain_architectures": 13, "interpro_id": "IPR049240", "known_evidence_count": null, "matches": 630, "name": "Domain of unknown function (DUF6875)", "partial_evidence_count": null, "pfam_id": "PF21780", "proteins": 629, "proteomes": 535, "short_name": "DUF6875", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21780", "structures": 0, "taxa": 908, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 384, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is only found in bacteria. Proteins in this family are typically between 227 to 238 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR024513", "known_evidence_count": null, "matches": 628, "name": "Protein of unknown function (DUF3334)", "partial_evidence_count": null, "pfam_id": "PF11813", "proteins": 628, "proteomes": 627, "short_name": "DUF3334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11813", "structures": 0, "taxa": 857, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 416, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a HEPN-like domain found in bacterial proteins. The AlphaFold structures show this entry is a part of the Nucleotidyltransferase substrate binding domain superfamily.", "domain_architectures": 5, "interpro_id": "IPR022104", "known_evidence_count": null, "matches": 628, "name": "Domain of unknown function (DUF3644)", "partial_evidence_count": null, "pfam_id": "PF12358", "proteins": 628, "proteomes": 598, "short_name": "DUF3644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12358", "structures": 0, "taxa": 1458, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 431, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an N-terminal domain of unknown function mostly found in bacteria. It is possible that this domain might be a putative glycoside hydrolase. This family belongs to the Galactose Mutarotase-like superfamily.", "domain_architectures": 22, "interpro_id": "IPR043757", "known_evidence_count": null, "matches": 649, "name": "Domain of unknown function (DUF5703)", "partial_evidence_count": null, "pfam_id": "PF18961", "proteins": 628, "proteomes": 552, "short_name": "DUF5703_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18961", "structures": 2, "taxa": 977, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 205 and 220 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045393", "known_evidence_count": null, "matches": 633, "name": "Family of unknown function (DUF6518)", "partial_evidence_count": null, "pfam_id": "PF20128", "proteins": 628, "proteomes": 567, "short_name": "DUF6518", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20128", "structures": 0, "taxa": 862, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 364, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This region is found as two or more repeats in a small number of hypothetical proteins.", "domain_architectures": 14, "interpro_id": "IPR008520", "known_evidence_count": null, "matches": 1550, "name": "Domain of unknown function (DUF802)", "partial_evidence_count": null, "pfam_id": "PF05650", "proteins": 627, "proteomes": 623, "short_name": "DUF802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05650", "structures": 0, "taxa": 783, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 428, "candidate_reasons": [ "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins from Bacteroidetes. This domain has an Ig-like fold.", "domain_architectures": 4, "interpro_id": "IPR041186", "known_evidence_count": null, "matches": 627, "name": "Domain of unknown function (DUF3823_C)", "partial_evidence_count": null, "pfam_id": "PF18003", "proteins": 627, "proteomes": 389, "short_name": "DUF3823_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18003", "structures": 4, "taxa": 576, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 514, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in plant proteins that are probably related to NOMO family of proteins. The latter are components of the multi-pass translocon (MPT) complex which mediates insertion of multi-pass membrane proteins into the lipid bilayer of membranes [[cite:PUB00155613]]. The domain represented by this entry is predicted to adopt a globular beta-sandwich structure with a prealbumin-like topology.", "domain_architectures": 100, "interpro_id": "IPR055576", "known_evidence_count": null, "matches": 627, "name": "Domain of unknown function (DUF7152)", "partial_evidence_count": null, "pfam_id": "PF23662", "proteins": 627, "proteomes": 343, "short_name": "DUF7152", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23662", "structures": 0, "taxa": 1096, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 389, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 489 to 517 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR021794", "known_evidence_count": null, "matches": 626, "name": "Protein of unknown function (DUF3360)", "partial_evidence_count": null, "pfam_id": "PF11840", "proteins": 626, "proteomes": 489, "short_name": "DUF3360", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11840", "structures": 0, "taxa": 720, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in plant sequences. It may adopt a three-helical bundle fold.", "domain_architectures": 13, "interpro_id": "IPR056652", "known_evidence_count": null, "matches": 640, "name": "Domain of unknown function (DUF7750)", "partial_evidence_count": null, "pfam_id": "PF24930", "proteins": 626, "proteomes": 355, "short_name": "DUF7750", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24930", "structures": 0, "taxa": 984, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 445, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 2, "interpro_id": "IPR021521", "known_evidence_count": null, "matches": 625, "name": "Protein of unknown function (DUF3185)", "partial_evidence_count": null, "pfam_id": "PF11381", "proteins": 625, "proteomes": 600, "short_name": "DUF3185", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11381", "structures": 0, "taxa": 992, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 507, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 238 and 363 amino acids in length. There are two conserved sequence motifs: EYP and KCTPD.", "domain_architectures": 8, "interpro_id": "IPR029236", "known_evidence_count": null, "matches": 658, "name": "Domain of unknown function (DUF4618)", "partial_evidence_count": null, "pfam_id": "PF15397", "proteins": 625, "proteomes": 360, "short_name": "DUF4618", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15397", "structures": 0, "taxa": 1337, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 390, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 98 and 195 amino acids in length and adopt a helix-rich bundle structure and share a similar fold with a flagellin homologue, hook-associated protein.", "domain_architectures": 4, "interpro_id": "IPR046548", "known_evidence_count": null, "matches": 625, "name": "Family of unknown function (DUF6804)", "partial_evidence_count": null, "pfam_id": "PF20619", "proteins": 625, "proteomes": 579, "short_name": "DUF6804", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20619", "structures": 0, "taxa": 918, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 486, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to adopt a globular structure consisting of array of helices.", "domain_architectures": 12, "interpro_id": "IPR056065", "known_evidence_count": null, "matches": 626, "name": "Domain of unknown function (DUF7648)", "partial_evidence_count": null, "pfam_id": "PF24659", "proteins": 625, "proteomes": 354, "short_name": "DUF7648", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24659", "structures": 0, "taxa": 973, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 586, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of archaebacterial proteins are about 170 amino acids in length. They have no known function. The most conserved portion of the protein contains the sequence GEEDL that may be important for its function.", "domain_architectures": 3, "interpro_id": "IPR007164", "known_evidence_count": null, "matches": 624, "name": "Protein of unknown function (DUF359)", "partial_evidence_count": null, "pfam_id": "PF04019", "proteins": 624, "proteomes": 609, "short_name": "DUF359", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04019", "structures": 3, "taxa": 1110, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 589, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family includes several uncharacterised archaeal proteins. This protein appears to contain two HHH motifs.", "domain_architectures": 3, "interpro_id": "IPR007003", "known_evidence_count": null, "matches": 624, "name": "Protein of unknown function (DUF655)", "partial_evidence_count": null, "pfam_id": "PF04919", "proteins": 624, "proteomes": 618, "short_name": "DUF655", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04919", "structures": 3, "taxa": 1177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 405, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several bacterial putative membrane proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR009328", "known_evidence_count": null, "matches": 624, "name": "Protein of unknown function (DUF986)", "partial_evidence_count": null, "pfam_id": "PF06173", "proteins": 624, "proteomes": 581, "short_name": "DUF986", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06173", "structures": 0, "taxa": 918, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 323, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical, highly conserved Streptococcal and related phage proteins of around 100 residues in length. The function of this family is unknown. It appears to be distantly related to [pfam:PF08281].", "domain_architectures": 6, "interpro_id": "IPR010861", "known_evidence_count": null, "matches": 624, "name": "Protein of unknown function (DUF1492)", "partial_evidence_count": null, "pfam_id": "PF07374", "proteins": 624, "proteomes": 524, "short_name": "DUF1492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07374", "structures": 0, "taxa": 1123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of Actinobacterial proteins of unknown function. AlphaFold predicts a confident dimeric arrangement. This family appears to be distantly related to [pfam:PF19887].", "domain_architectures": 7, "interpro_id": "IPR054202", "known_evidence_count": null, "matches": 638, "name": "Domain of unknown function (DUF6907)", "partial_evidence_count": null, "pfam_id": "PF21848", "proteins": 624, "proteomes": 430, "short_name": "DUF6907", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21848", "structures": 0, "taxa": 611, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 502, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to adopt an alpha/beta structure with a central four-stranded antiparallel beta-sheet and alpha helices packed on it. It has weak sequence and structural similarity to NIL domains. It is usually found N-terminal to protein kinase domains.", "domain_architectures": 17, "interpro_id": "IPR055801", "known_evidence_count": null, "matches": 627, "name": "Domain of unknown function (DUF7377)", "partial_evidence_count": null, "pfam_id": "PF24093", "proteins": 624, "proteomes": 351, "short_name": "DUF7377", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24093", "structures": 0, "taxa": 961, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 430, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from several species of Staphylococcus. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009303", "known_evidence_count": null, "matches": 623, "name": "Staphylococcal protein of unknown function (DUF960)", "partial_evidence_count": null, "pfam_id": "PF06124", "proteins": 623, "proteomes": 476, "short_name": "DUF960", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06124", "structures": 1, "taxa": 782, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 372, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR046179", "known_evidence_count": null, "matches": 622, "name": "Family of unknown function (DUF6188)", "partial_evidence_count": null, "pfam_id": "PF19686", "proteins": 622, "proteomes": 521, "short_name": "DUF6188", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19686", "structures": 0, "taxa": 804, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 511, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. This domain is predicted to fold into an alpha-helical hairpin.", "domain_architectures": 20, "interpro_id": "IPR056034", "known_evidence_count": null, "matches": 626, "name": "Domain of unknown function (DUF7615)", "partial_evidence_count": null, "pfam_id": "PF24590", "proteins": 621, "proteomes": 337, "short_name": "DUF7615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24590", "structures": 0, "taxa": 947, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 417, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in Bacteroidetes proteins, is frequently associated with a putative thiol-disulfide oxidoreductase domain, [pfam:PF13905]. The function of this domain is not known.", "domain_architectures": 11, "interpro_id": "IPR033395", "known_evidence_count": null, "matches": 621, "name": "Domain of unknown function (DUF5106)", "partial_evidence_count": null, "pfam_id": "PF17127", "proteins": 620, "proteomes": 527, "short_name": "DUF5106", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17127", "structures": 1, "taxa": 830, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 170 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046588", "known_evidence_count": null, "matches": 621, "name": "Family of unknown function (DUF6646)", "partial_evidence_count": null, "pfam_id": "PF20351", "proteins": 620, "proteomes": 604, "short_name": "DUF6646", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20351", "structures": 0, "taxa": 726, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 400, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised cyanobacterial proteins.", "domain_architectures": 4, "interpro_id": "IPR054053", "known_evidence_count": null, "matches": 620, "name": "Family of unknown function (DUF6887)", "partial_evidence_count": null, "pfam_id": "PF21826", "proteins": 620, "proteomes": 151, "short_name": "DUF6887", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21826", "structures": 0, "taxa": 438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 391, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 188 and 241 amino acids in length. There is a single completely conserved residue Y that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR032083", "known_evidence_count": null, "matches": 620, "name": "Domain of unknown function (DUF4811)", "partial_evidence_count": null, "pfam_id": "PF16069", "proteins": 619, "proteomes": 433, "short_name": "DUF4811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16069", "structures": 0, "taxa": 645, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal to the NTPase domain [pfam:PF05729] in a group of fungal proteins, including [swissprot:U7Q5X2] from Sporothrix schenckii. It is predicted to adopt an alpha-helical configuration.", "domain_architectures": 119, "interpro_id": "IPR055496", "known_evidence_count": null, "matches": 619, "name": "Domain of unknown function (DUF7068)", "partial_evidence_count": null, "pfam_id": "PF23238", "proteins": 619, "proteomes": 299, "short_name": "DUF7068", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23238", "structures": 0, "taxa": 626, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 534, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes uncharacterised archaeal sequences.", "domain_architectures": 4, "interpro_id": "IPR055811", "known_evidence_count": null, "matches": 620, "name": "Family of unknown function (DUF7387)", "partial_evidence_count": null, "pfam_id": "PF24113", "proteins": 619, "proteomes": 402, "short_name": "DUF7387", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24113", "structures": 0, "taxa": 825, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 582, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Proteins in this family range from 80 to 90 residues in length and may have a C-terminal transmembrane alpha helix.", "domain_architectures": 1, "interpro_id": "IPR058341", "known_evidence_count": null, "matches": 619, "name": "Family of unknown function (DUF8028)", "partial_evidence_count": null, "pfam_id": "PF26071", "proteins": 619, "proteomes": 272, "short_name": "DUF8028", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26071", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025630", "known_evidence_count": null, "matches": 617, "name": "Domain of unknown function (DUF4288)", "partial_evidence_count": null, "pfam_id": "PF14119", "proteins": 617, "proteomes": 589, "short_name": "DUF4288", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14119", "structures": 0, "taxa": 1086, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of proteins from the Pseudomonadaceae.", "domain_architectures": 1, "interpro_id": "IPR012449", "known_evidence_count": null, "matches": 616, "name": "Protein of unknown function (DUF1654)", "partial_evidence_count": null, "pfam_id": "PF07867", "proteins": 616, "proteomes": 372, "short_name": "DUF1654", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07867", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 160 amino acids in length. There is a conserved AYTG sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025013", "known_evidence_count": null, "matches": 616, "name": "Protein of unknown function (DUF3907)", "partial_evidence_count": null, "pfam_id": "PF13047", "proteins": 616, "proteomes": 614, "short_name": "DUF3907", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13047", "structures": 0, "taxa": 733, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria, and is typically between 56 and 95 amino acids in length.", "domain_architectures": 71, "interpro_id": "IPR025465", "known_evidence_count": null, "matches": 616, "name": "Domain of unknown function (DUF4316)", "partial_evidence_count": null, "pfam_id": "PF14195", "proteins": 616, "proteomes": 291, "short_name": "DUF4316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14195", "structures": 0, "taxa": 561, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 445, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to adopt globular structure consisting of a curved beta-sheet and alpha-helices packed on one side of it. It contains a semi-conserved FKGFSS sequence motif.", "domain_architectures": 6, "interpro_id": "IPR056636", "known_evidence_count": null, "matches": 618, "name": "Domain of unknown function (DUF7734)", "partial_evidence_count": null, "pfam_id": "PF24869", "proteins": 616, "proteomes": 548, "short_name": "DUF7734", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24869", "structures": 0, "taxa": 1543, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 546, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This predicted RNA recognition domain (RRM) is found in a group of uncharacterised plant proteins. It is predicted to show an alpha/beta configuration. It has conserved residues P, H, C and Y. Its specific function is unknown.", "domain_architectures": 30, "interpro_id": "IPR061553", "known_evidence_count": null, "matches": 617, "name": "Domain of unknown function (DUF8483)", "partial_evidence_count": null, "pfam_id": "PF28947", "proteins": 616, "proteomes": 36, "short_name": "DUF8483", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28947", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 366, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021430", "known_evidence_count": null, "matches": 615, "name": "Protein of unknown function (DUF3079)", "partial_evidence_count": null, "pfam_id": "PF11278", "proteins": 615, "proteomes": 605, "short_name": "DUF3079", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11278", "structures": 0, "taxa": 819, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 234 to 251 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR021806", "known_evidence_count": null, "matches": 615, "name": "Protein of unknown function (DUF3379)", "partial_evidence_count": null, "pfam_id": "PF11859", "proteins": 615, "proteomes": 608, "short_name": "DUF3379", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11859", "structures": 0, "taxa": 843, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 377, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR010938", "known_evidence_count": null, "matches": 614, "name": "Protein of unknown function (DUF1131)", "partial_evidence_count": null, "pfam_id": "PF06572", "proteins": 614, "proteomes": 610, "short_name": "DUF1131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06572", "structures": 1, "taxa": 919, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 396, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 60 to 77 amino acids in length. This protein has two completely conserved residues (R and L) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR021932", "known_evidence_count": null, "matches": 613, "name": "Protein of unknown function (DUF3545)", "partial_evidence_count": null, "pfam_id": "PF12065", "proteins": 613, "proteomes": 600, "short_name": "DUF3545", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12065", "structures": 0, "taxa": 773, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 370, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 327 and 345 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025062", "known_evidence_count": null, "matches": 613, "name": "Protein of unknown function (DUF4003)", "partial_evidence_count": null, "pfam_id": "PF13170", "proteins": 613, "proteomes": 543, "short_name": "DUF4003", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13170", "structures": 0, "taxa": 800, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 362, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in the Uncharacterized protein HI_1292 from Haemophilus influenzae and related sequences from Bacteria. It is found at the N-terminal, associated with [pfam:PF10071].", "domain_architectures": 4, "interpro_id": "IPR061650", "known_evidence_count": null, "matches": 613, "name": "Domain of unknown function (DUF8589)", "partial_evidence_count": null, "pfam_id": "PF29828", "proteins": 613, "proteomes": 609, "short_name": "DUF8589", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29828", "structures": 0, "taxa": 884, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 581, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family represents a short repeat region found a number of C. elegans proteins of unknown function.", "domain_architectures": 36, "interpro_id": "IPR004296", "known_evidence_count": null, "matches": 2221, "name": "DUF236 repeat", "partial_evidence_count": null, "pfam_id": "PF03057", "proteins": 612, "proteomes": 84, "short_name": "DUF236", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03057", "structures": 0, "taxa": 191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 467, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. There are two conserved sequence motifs: QIGPT and GMVR.", "domain_architectures": 1, "interpro_id": "IPR046287", "known_evidence_count": null, "matches": 612, "name": "Family of unknown function (DUF6324)", "partial_evidence_count": null, "pfam_id": "PF19849", "proteins": 612, "proteomes": 611, "short_name": "DUF6324", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19849", "structures": 0, "taxa": 847, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as the membrane protein YiaF. No function is currently known.", "domain_architectures": 1, "interpro_id": "IPR021413", "known_evidence_count": null, "matches": 611, "name": "Protein of unknown function (DUF3053)", "partial_evidence_count": null, "pfam_id": "PF11254", "proteins": 611, "proteomes": 542, "short_name": "DUF3053", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11254", "structures": 0, "taxa": 798, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 411, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is mainly found in Firmicute bacteria. Proteins in this family are typically between 220 and 604 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR046283", "known_evidence_count": null, "matches": 610, "name": "Family of unknown function (DUF6320)", "partial_evidence_count": null, "pfam_id": "PF19845", "proteins": 610, "proteomes": 576, "short_name": "DUF6320", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19845", "structures": 0, "taxa": 1027, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 110 residues found predominantly in Bacteroidota, particularly Flavobacteriaceae. The function of this family remains to be determined. Members are predicted to adopt a structure with significant similarity to members of the PDDEXK superfamily and in particular to [pfam:PF02021].", "domain_architectures": 3, "interpro_id": "IPR061901", "known_evidence_count": null, "matches": 609, "name": "Domain of unknown function (DUF8840)", "partial_evidence_count": null, "pfam_id": "PF31210", "proteins": 609, "proteomes": 606, "short_name": "DUF8840", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31210", "structures": 0, "taxa": 869, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 574, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "Members of this family are short (less than 100 amino acid) proteins found in archaebacteria. The function of these proteins is unknown.", "domain_architectures": 4, "interpro_id": "IPR023140", "known_evidence_count": null, "matches": 639, "name": "Protein of unknown function (DUF357)", "partial_evidence_count": null, "pfam_id": "PF04010", "proteins": 608, "proteomes": 602, "short_name": "DUF357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04010", "structures": 4, "taxa": 1088, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised bacterial proteins is found mainly in Actinomycetes. Members of this family are predicted to contain three transmembrane helices. A member of this family, SCO4225, is a putative integral membrane protein found in Streptomyces coelicolor, [swissprot:Q9FCE5]. The gene encoding SCO4225 is part of a cluster of genes (phoU to sco4225) that are involved in phosphate regulation and metabolism. This gene cluster is regulated by the two-component system PhoR-PhoP, which responds to phosphate availability in the environment [[cite:PUB00159567]]. The expression of SCO4225 is directly regulated by MacR, a response regulator that binds to a specific sequence in the promoter region of SCO4225. This regulation links SCO4225 to other genes in the MacR regulon, many of which are also membrane proteins [[cite:PUB00159414]].", "domain_architectures": 2, "interpro_id": "IPR057702", "known_evidence_count": null, "matches": 654, "name": "Family of unknown function (DUF7942)", "partial_evidence_count": null, "pfam_id": "PF25637", "proteins": 608, "proteomes": 487, "short_name": "DUF7942", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25637", "structures": 0, "taxa": 641, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of bacterial and plasmid sequences that carry at least one zinc-finger towards the N-terminus and a possible second at the C-terminus.", "domain_architectures": 8, "interpro_id": "IPR021686", "known_evidence_count": null, "matches": 610, "name": "zinc-finger-containing domain", "partial_evidence_count": null, "pfam_id": "PF11672", "proteins": 607, "proteomes": 543, "short_name": "DUF3268", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11672", "structures": 0, "taxa": 1170, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 427, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR041313", "known_evidence_count": null, "matches": 611, "name": "Domain of unknown function (DUF5642)", "partial_evidence_count": null, "pfam_id": "PF18702", "proteins": 607, "proteomes": 299, "short_name": "DUF5642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18702", "structures": 1, "taxa": 347, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 310 and 361 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR025538", "known_evidence_count": null, "matches": 622, "name": "Domain of unknown function (DUF4424)", "partial_evidence_count": null, "pfam_id": "PF14415", "proteins": 606, "proteomes": 568, "short_name": "DUF4424", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14415", "structures": 1, "taxa": 953, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 313, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000847) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the thienamycin biosynthetic gene cluster from Streptomyces cattleya and it appears to be predominantly found in actinobacteria [[cite:PUB00083660]].", "domain_architectures": 3, "interpro_id": "IPR046080", "known_evidence_count": null, "matches": 606, "name": "Family of unknown function (DUF6098)", "partial_evidence_count": null, "pfam_id": "PF19593", "proteins": 606, "proteomes": 584, "short_name": "DUF6098", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19593", "structures": 0, "taxa": 787, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacterial proteins which are functionally uncharacterised. Proteins in this family are typically between 225 and 1025 amino acids in length. There is a conserved Tryptophan residue at the N-terminal and a highly conserved SDLN sequence.", "domain_architectures": 21, "interpro_id": "IPR046217", "known_evidence_count": null, "matches": 606, "name": "Domain of unknown function (DUF6250)", "partial_evidence_count": null, "pfam_id": "PF19763", "proteins": 606, "proteomes": 574, "short_name": "DUF6250", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19763", "structures": 0, "taxa": 977, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 511, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a five-stranded antiparallel beta-sheet and two alpha-helices packed on it.", "domain_architectures": 6, "interpro_id": "IPR056713", "known_evidence_count": null, "matches": 615, "name": "Domain of unknown function (DUF7811)", "partial_evidence_count": null, "pfam_id": "PF25103", "proteins": 606, "proteomes": 393, "short_name": "DUF7811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25103", "structures": 0, "taxa": 1077, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 508, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region approximately 200 residues long within a number of proteins of unknown function that seem to be specific to C. elegans.", "domain_architectures": 35, "interpro_id": "IPR009689", "known_evidence_count": null, "matches": 609, "name": "Protein of unknown function (DUF1280)", "partial_evidence_count": null, "pfam_id": "PF06918", "proteins": 605, "proteomes": 65, "short_name": "DUF1280", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06918", "structures": 0, "taxa": 226, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 572, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The function of this family of proteins, has not, as yet, been determined. Members of this family are as yet uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically 128 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR028099", "known_evidence_count": null, "matches": 611, "name": "Domain of unknown function (DUF4577)", "partial_evidence_count": null, "pfam_id": "PF15145", "proteins": 605, "proteomes": 545, "short_name": "DUF4577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15145", "structures": 0, "taxa": 1606, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 332, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001048) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide), polyketide, and saccharide. This family includes a protein in the tallysomycin A biosynthetic gene cluster from Streptoalloteichus hindustanus [[cite:PUB00083679]]. Some members of this family have been annotated as monooxygenase, but this could not be confirmed.", "domain_architectures": 6, "interpro_id": "IPR046032", "known_evidence_count": null, "matches": 606, "name": "Family of unknown function (DUF5990)", "partial_evidence_count": null, "pfam_id": "PF19452", "proteins": 605, "proteomes": 592, "short_name": "DUF5990", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19452", "structures": 0, "taxa": 977, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 464, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Alphaproteobacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046247", "known_evidence_count": null, "matches": 605, "name": "Family of unknown function (DUF6280)", "partial_evidence_count": null, "pfam_id": "PF19796", "proteins": 605, "proteomes": 603, "short_name": "DUF6280", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19796", "structures": 0, "taxa": 834, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 372, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 131 and 449 amino acids in length.", "domain_architectures": 20, "interpro_id": "IPR045425", "known_evidence_count": null, "matches": 605, "name": "Family of unknown function (DUF6508)", "partial_evidence_count": null, "pfam_id": "PF20118", "proteins": 605, "proteomes": 578, "short_name": "DUF6508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20118", "structures": 0, "taxa": 1214, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The search results from NCBI sequence alignment indicates a conserved domain belonging to ASCH superfamily [[cite:PUB00044668]]. Dali searching results show that the protein is a structurally similar to the PUA domain, suggesting it may be involved in RNA recognition. It has been reported that the deletion of PUA genes results in impaired growth (RluD) and competitive disadvantage (TruB) in Escherichia coli. Suggestions have been put forward that, apart from their usual catalytic role, certain PUS enzymes (e.g. TruB) may also act as chaperones for RNA folding. The interface interaction indicates that the biomolecule of protein NP_809782.1 should be a dimer.", "domain_architectures": 5, "interpro_id": "IPR039440", "known_evidence_count": null, "matches": 604, "name": "Domain of unknown function (DUF3850)", "partial_evidence_count": null, "pfam_id": "PF12961", "proteins": 604, "proteomes": 544, "short_name": "DUF3850", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12961", "structures": 1, "taxa": 1185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 447, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 165 and 177 amino acids in length. There is a single completely conserved residue G that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR025480", "known_evidence_count": null, "matches": 694, "name": "Domain of unknown function (DUF4330)", "partial_evidence_count": null, "pfam_id": "PF14221", "proteins": 604, "proteomes": 539, "short_name": "DUF4330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14221", "structures": 0, "taxa": 1241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 51, "interpro_id": "IPR031866", "known_evidence_count": null, "matches": 1595, "name": "Putative sperm flagellar membrane protein", "partial_evidence_count": null, "pfam_id": "PF15950", "proteins": 604, "proteomes": 282, "short_name": "DUF4758", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15950", "structures": 0, "taxa": 1117, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 559, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Some members of this protein have an N-terminal lipoprotein attachment motif.", "domain_architectures": 3, "interpro_id": "IPR058285", "known_evidence_count": null, "matches": 626, "name": "Family of unknown function (DUF7979)", "partial_evidence_count": null, "pfam_id": "PF25934", "proteins": 604, "proteomes": 238, "short_name": "DUF7979", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25934", "structures": 0, "taxa": 382, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 319, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain found in bacterial family of proteins which is is a component of a contractile injection system related to phage sheath proteins [[cite:PUB00097484]].", "domain_architectures": 3, "interpro_id": "IPR062236", "known_evidence_count": null, "matches": 604, "name": "DUF2586, C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF29510", "proteins": 604, "proteomes": 527, "short_name": "DUF2586_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29510", "structures": 0, "taxa": 998, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 505, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This a is family of uncharacterised proteins.", "domain_architectures": 4, "interpro_id": "IPR018858", "known_evidence_count": null, "matches": 613, "name": "Protein of unknown function (DUF2458)", "partial_evidence_count": null, "pfam_id": "PF10454", "proteins": 603, "proteomes": 593, "short_name": "DUF2458", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10454", "structures": 0, "taxa": 1331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 383, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 169 and 185 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046153", "known_evidence_count": null, "matches": 603, "name": "Family of unknown function (DUF6155)", "partial_evidence_count": null, "pfam_id": "PF19652", "proteins": 603, "proteomes": 589, "short_name": "DUF6155", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19652", "structures": 0, "taxa": 923, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 244, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000119) is described by MIBiG as an example of the following biosynthetic classes, polyketide and saccharide, in particular the 7-deoxypactamycin biosynthetic gene cluster from Streptomyces pactum [[cite:PUB00099419],[cite:PUB00099449],[cite:PUB00099466]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046241", "known_evidence_count": null, "matches": 603, "name": "Family of unknown function (DUF6274)", "partial_evidence_count": null, "pfam_id": "PF19790", "proteins": 603, "proteomes": 600, "short_name": "DUF6274", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19790", "structures": 0, "taxa": 659, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 175 residues found in putative signal transduction proteins. Some members are annotated as histidine kinases or HSP90-like ATPases, and one example contains a HATPase_c domain ([pfam:PF02518]) suggesting these proteins function in two-component signalling systems. This domain may represent a sensor input domain. This family is found almost exclusively in Actinomycetota, particularly Streptomyces. The function of this domain remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061806", "known_evidence_count": null, "matches": 604, "name": "Domain of unknown function (DUF8745)", "partial_evidence_count": null, "pfam_id": "PF30796", "proteins": 603, "proteomes": 581, "short_name": "DUF8745", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30796", "structures": 0, "taxa": 706, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 311, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021519", "known_evidence_count": null, "matches": 602, "name": "Protein of unknown function (DUF3182)", "partial_evidence_count": null, "pfam_id": "PF11379", "proteins": 602, "proteomes": 591, "short_name": "DUF3182", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11379", "structures": 0, "taxa": 828, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 488, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into an alpha-helical structure with similarity to alpha-solenoid domains.", "domain_architectures": 16, "interpro_id": "IPR056714", "known_evidence_count": null, "matches": 636, "name": "Domain of unknown function (DUF7812)", "partial_evidence_count": null, "pfam_id": "PF25104", "proteins": 602, "proteomes": 351, "short_name": "DUF7812", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25104", "structures": 0, "taxa": 960, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 311 and 340 amino acids in length.", "domain_architectures": 14, "interpro_id": "IPR045383", "known_evidence_count": null, "matches": 601, "name": "Family of unknown function (DUF6528)", "partial_evidence_count": null, "pfam_id": "PF20138", "proteins": 601, "proteomes": 472, "short_name": "DUF6528", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20138", "structures": 0, "taxa": 779, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in the Bacillaceae family. Several members are named as YqfT. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR020277", "known_evidence_count": null, "matches": 600, "name": "Protein of unknown function (DUF2624)", "partial_evidence_count": null, "pfam_id": "PF11116", "proteins": 600, "proteomes": 599, "short_name": "DUF2624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11116", "structures": 0, "taxa": 768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This predicted domain is found in a group of uncharacterised fungal proteins that also contain an F-box domain. This domain is predicted to adopt a winged helix fold.", "domain_architectures": 13, "interpro_id": "IPR057214", "known_evidence_count": null, "matches": 602, "name": "Domain of unknown function (DUF7892)", "partial_evidence_count": null, "pfam_id": "PF25422", "proteins": 600, "proteomes": 580, "short_name": "DUF7892", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25422", "structures": 0, "taxa": 1254, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 423, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 261 and 345 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR017496", "known_evidence_count": null, "matches": 599, "name": "Protein of unknown function (DUF3623)", "partial_evidence_count": null, "pfam_id": "PF12291", "proteins": 599, "proteomes": 586, "short_name": "DUF3623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12291", "structures": 0, "taxa": 1013, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 559, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in Uncharacterized protein T05H10.3 from C.elegans and related nematode proteins. It is predicted to adopt a beta-sandwich with similarity to domains members of H-lectin-like superfamily. This domain contains several highly conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 18, "interpro_id": "IPR056710", "known_evidence_count": null, "matches": 608, "name": "Domain of unknown function (DUF7808)", "partial_evidence_count": null, "pfam_id": "PF25096", "proteins": 599, "proteomes": 89, "short_name": "DUF7808", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25096", "structures": 0, "taxa": 211, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 451, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in uncharcaterised proteins from Alphaproteobacteria, predominantly in Rhodobacterales (including Roseobacteraceae and Paracoccaceae). The domain is approximately 100 residues in length and is predicted to adopt an alpha/beta structure containing a four stranded antiparallel beta-sheet. STRING analysis shows these proteins are consistently associated with cell division and secretion system proteins, including DivIB ([pfam:PF03799]), RodZ ([pfam:PF13464]) and SPOR domain proteins ([pfam:PF05036]). The specific function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061907", "known_evidence_count": null, "matches": 599, "name": "Domain of unknown function (DUF8846)", "partial_evidence_count": null, "pfam_id": "PF31256", "proteins": 599, "proteomes": 598, "short_name": "DUF8846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31256", "structures": 0, "taxa": 827, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 467, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. THey contain 4 N-terminal cysteines that may form a zinc binding domain.", "domain_architectures": 3, "interpro_id": "IPR014997", "known_evidence_count": null, "matches": 599, "name": "Protein of unknown function (DUF1847)", "partial_evidence_count": null, "pfam_id": "PF08901", "proteins": 598, "proteomes": 533, "short_name": "DUF1847", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08901", "structures": 0, "taxa": 1210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 566, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins predominantly found in Halobacteria. They are thought to be GNAT (Gcn5-related N-acetyltransferases) family acetyltransferases.", "domain_architectures": 4, "interpro_id": "IPR043854", "known_evidence_count": null, "matches": 598, "name": "Family of unknown function (DUF5816)", "partial_evidence_count": null, "pfam_id": "PF19133", "proteins": 598, "proteomes": 279, "short_name": "DUF5816", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19133", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 357, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 246 and 268 amino acids in length. There are seven highly conserved Gly residues. It is predicted to contain tandem of PH-like domains.", "domain_architectures": 8, "interpro_id": "IPR046492", "known_evidence_count": null, "matches": 612, "name": "Family of unknown function (DUF6585)", "partial_evidence_count": null, "pfam_id": "PF20226", "proteins": 598, "proteomes": 436, "short_name": "DUF6585", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20226", "structures": 0, "taxa": 716, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 558, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins mainly from halobacteria. Members are predicted to show an alpha-helical configuration forming an intramolecular coiled-coil structure.", "domain_architectures": 3, "interpro_id": "IPR055545", "known_evidence_count": null, "matches": 598, "name": "Family of unknown function (DUF7121)", "partial_evidence_count": null, "pfam_id": "PF23435", "proteins": 598, "proteomes": 549, "short_name": "DUF7121", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23435", "structures": 0, "taxa": 1000, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 364, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta globular structure with topology similar to NADH-quinone oxidoreductase subunit 16.", "domain_architectures": 1, "interpro_id": "IPR055571", "known_evidence_count": null, "matches": 598, "name": "Domain of unknown function (DUF7147)", "partial_evidence_count": null, "pfam_id": "PF23648", "proteins": 598, "proteomes": 596, "short_name": "DUF7147", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23648", "structures": 0, "taxa": 748, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 563, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR007355", "known_evidence_count": null, "matches": 597, "name": "Protein of unknown function (DUF424)", "partial_evidence_count": null, "pfam_id": "PF04242", "proteins": 597, "proteomes": 595, "short_name": "DUF424", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04242", "structures": 1, "taxa": 1091, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000843) is described by MIBiG as an example of the following biosynthetic class, other (unspecified), in particular the alanylclavam biosynthetic gene cluster from Streptomyces clavuligerus ATCC 27064 [[cite:PUB00099389],[cite:PUB00099390]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR045925", "known_evidence_count": null, "matches": 597, "name": "Family of unknown function (DUF6344)", "partial_evidence_count": null, "pfam_id": "PF19871", "proteins": 597, "proteomes": 592, "short_name": "DUF6344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19871", "structures": 0, "taxa": 635, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001859) is described by MIBiG as an example of the following biosynthetic class, other (unspecified), in particular fosfomycin biosynthetic gene cluster from Pseudomonas syringae [[cite:PUB00098902],[cite:PUB00143563]]. This family is predominantly found in proteobacteria. Some members of this family have been putatively identified as DNA repair proteins.", "domain_architectures": 1, "interpro_id": "IPR045662", "known_evidence_count": null, "matches": 597, "name": "Family of unknown function (DUF6388)", "partial_evidence_count": null, "pfam_id": "PF19925", "proteins": 597, "proteomes": 390, "short_name": "DUF6388", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19925", "structures": 0, "taxa": 439, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 352, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000699) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the hygromycin A biosynthetic gene cluster from Streptomyces hygroscopicus subsp. hygroscopicus [[cite:PUB00098957]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR046275", "known_evidence_count": null, "matches": 603, "name": "Family of unknown function (DUF6308)", "partial_evidence_count": null, "pfam_id": "PF19827", "proteins": 596, "proteomes": 511, "short_name": "DUF6308", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19827", "structures": 0, "taxa": 774, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the domain of unknown function found towards the C-terminal of some MACPF domain-containing proteins from fungi, such as SwissProt:A0A2P4PCT2. It is found associated with MACPF_1 ([pfam:PF22693]) domain.", "domain_architectures": 17, "interpro_id": "IPR055854", "known_evidence_count": null, "matches": 624, "name": "Domain of unknown function (DUF7431)", "partial_evidence_count": null, "pfam_id": "PF24209", "proteins": 596, "proteomes": 23, "short_name": "DUF7431", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24209", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 377, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 260 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR020042", "known_evidence_count": null, "matches": 595, "name": "Domain of unknown function (DUF4311)", "partial_evidence_count": null, "pfam_id": "PF14188", "proteins": 595, "proteomes": 588, "short_name": "DUF4311", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14188", "structures": 0, "taxa": 930, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 393, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal SH3-like barrel domain of approximately 60 residues. The domain is found at the N-terminus of DEAD/DEAH box helicases, preceding ResIII ([pfam:PF04851]), SNF2-rel_dom ([pfam:PF00176]), DEAD ([pfam:PF00270]), Helicase_C ([pfam:PF00271]) and NOV_C ([pfam:PF13020]) domains. This family is found in bacteria, predominantly Actinomycetota and Pseudomonadota. The function of this domain remains to be determined.", "domain_architectures": 12, "interpro_id": "IPR061803", "known_evidence_count": null, "matches": 595, "name": "Domain of unknown function (DUF8742)", "partial_evidence_count": null, "pfam_id": "PF30791", "proteins": 595, "proteomes": 572, "short_name": "DUF8742", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30791", "structures": 0, "taxa": 1414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 398, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 130 residues. The domain is found C-terminal to DUF2357 ([pfam:PF09823]) and PDDEXK_7 ([pfam:PF04411]) domains in proteins annotated as restriction endonucleases, including 5-methylcytosine-specific restriction enzymes. This family is found in bacteria (predominantly Bacillota) and archaea (Methanobacteriota). The function of this domain remains to be determined.", "domain_architectures": 13, "interpro_id": "IPR061804", "known_evidence_count": null, "matches": 595, "name": "Domain of unknown function (DUF8743)", "partial_evidence_count": null, "pfam_id": "PF30793", "proteins": 595, "proteomes": 567, "short_name": "DUF8743", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30793", "structures": 0, "taxa": 1238, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 396, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are found in a set of hypothetical bacterial proteins. Their exact function has not, as yet, been determined.", "domain_architectures": 13, "interpro_id": "IPR015305", "known_evidence_count": null, "matches": 595, "name": "Domain of unknown function (DUF1961)", "partial_evidence_count": null, "pfam_id": "PF09224", "proteins": 594, "proteomes": 564, "short_name": "DUF1961", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09224", "structures": 1, "taxa": 1018, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 485, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial and eukaryotic proteins. It is predicted to contain nine transmembrane helices arranged in a bundle. This domain has similarity to domains members of the INSIG-like superfamily.", "domain_architectures": 26, "interpro_id": "IPR056704", "known_evidence_count": null, "matches": 635, "name": "Domain of unknown function (DUF7802)", "partial_evidence_count": null, "pfam_id": "PF25085", "proteins": 594, "proteomes": 453, "short_name": "DUF7802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25085", "structures": 0, "taxa": 1458, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 214 and 231 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025456", "known_evidence_count": null, "matches": 593, "name": "Domain of unknown function (DUF4310)", "partial_evidence_count": null, "pfam_id": "PF14187", "proteins": 593, "proteomes": 590, "short_name": "DUF4310", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14187", "structures": 0, "taxa": 927, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 341, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 250 residues in length and is mainly found in various Firmicutes species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032479", "known_evidence_count": null, "matches": 593, "name": "Domain of unknown function (DUF5058)", "partial_evidence_count": null, "pfam_id": "PF16481", "proteins": 593, "proteomes": 482, "short_name": "DUF5058", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16481", "structures": 0, "taxa": 902, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 444, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is predominantly found in Rhodobacterales. Proteins in this family are typically between 160 and 175 amino acids in length. There are some conserved motifs: IDA/S, SSPxRxRACF and DG. Many members in this family are thought to be histidine kinases.", "domain_architectures": 3, "interpro_id": "IPR045616", "known_evidence_count": null, "matches": 596, "name": "Family of unknown function (DUF6446)", "partial_evidence_count": null, "pfam_id": "PF20044", "proteins": 592, "proteomes": 592, "short_name": "DUF6446", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20044", "structures": 0, "taxa": 829, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 418, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria and archaea. This domain is typically between 274 to 285 amino acids in length. This domain is found associated with [pfam:PF03065].", "domain_architectures": 4, "interpro_id": "IPR021923", "known_evidence_count": null, "matches": 593, "name": "Domain of unknown function (DUF3536)", "partial_evidence_count": null, "pfam_id": "PF12055", "proteins": 591, "proteomes": 581, "short_name": "DUF3536", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12055", "structures": 0, "taxa": 1492, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 420, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised bacterial proteins. This domain is about 150 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR045951", "known_evidence_count": null, "matches": 591, "name": "Domain of unknown function (DUF6371)", "partial_evidence_count": null, "pfam_id": "PF19898", "proteins": 591, "proteomes": 471, "short_name": "DUF6371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19898", "structures": 0, "taxa": 858, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 487, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a group of uncharacterised plant proteins. It is predicted to fold into an array of alpha-helices.", "domain_architectures": 11, "interpro_id": "IPR057198", "known_evidence_count": null, "matches": 606, "name": "Domain of unknown function (DUF7876)", "partial_evidence_count": null, "pfam_id": "PF25286", "proteins": 591, "proteomes": 368, "short_name": "DUF7876", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25286", "structures": 0, "taxa": 1015, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 441, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 62 residues found in small uncharacterized proteins in Alphaproteobacteria, particularly Rhodobacterales (Roseobacteraceae, Paracoccaceae). These proteins typically consist of this single domain only. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061892", "known_evidence_count": null, "matches": 590, "name": "Domain of unknown function (DUF8831)", "partial_evidence_count": null, "pfam_id": "PF31171", "proteins": 590, "proteomes": 590, "short_name": "DUF8831", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31171", "structures": 0, "taxa": 833, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 362, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to adopt a beta-sandwich with similarity to galactose-binding domains.", "domain_architectures": 13, "interpro_id": "IPR055795", "known_evidence_count": null, "matches": 593, "name": "Domain of unknown function (DUF7371)", "partial_evidence_count": null, "pfam_id": "PF24086", "proteins": 589, "proteomes": 576, "short_name": "DUF7371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24086", "structures": 0, "taxa": 1189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 501, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several Drosophila proteins of unknown function.", "domain_architectures": 6, "interpro_id": "IPR007931", "known_evidence_count": null, "matches": 599, "name": "Protein of unknown function (DUF725)", "partial_evidence_count": null, "pfam_id": "PF05267", "proteins": 588, "proteomes": 86, "short_name": "DUF725", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05267", "structures": 0, "taxa": 353, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 367, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 99 and 118 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR020037", "known_evidence_count": null, "matches": 588, "name": "Domain of unknown function (DUF4312)", "partial_evidence_count": null, "pfam_id": "PF14189", "proteins": 588, "proteomes": 586, "short_name": "DUF4312", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14189", "structures": 0, "taxa": 930, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are predicted to adopt an alpha/beta structure consisting of a central mixed beta-sheet packed on both sides with alpha-helices that is reminiscent to the common structural core of N-acetyltransferases (NAT).", "domain_architectures": 2, "interpro_id": "IPR053865", "known_evidence_count": null, "matches": 589, "name": "Family of unknown function (DUF6934)", "partial_evidence_count": null, "pfam_id": "PF22028", "proteins": 588, "proteomes": 266, "short_name": "DUF6934", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22028", "structures": 0, "taxa": 373, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 397, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised.", "domain_architectures": 3, "interpro_id": "IPR014960", "known_evidence_count": null, "matches": 587, "name": "Domain of unknown function DUF1828", "partial_evidence_count": null, "pfam_id": "PF08861", "proteins": 587, "proteomes": 543, "short_name": "DUF1828", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08861", "structures": 0, "taxa": 1347, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 434, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 96 and 116 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045516", "known_evidence_count": null, "matches": 587, "name": "Family of unknown function (DUF6477)", "partial_evidence_count": null, "pfam_id": "PF20083", "proteins": 587, "proteomes": 586, "short_name": "DUF6477", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20083", "structures": 0, "taxa": 849, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length. There are two conserved sequence motifs: DPTGI and ILA.", "domain_architectures": 1, "interpro_id": "IPR045424", "known_evidence_count": null, "matches": 587, "name": "Family of unknown function (DUF6509)", "partial_evidence_count": null, "pfam_id": "PF20119", "proteins": 587, "proteomes": 586, "short_name": "DUF6509", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20119", "structures": 0, "taxa": 669, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 382, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins. Many of the sequences in this family are annotated as putative DNA binding proteins but the function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010434", "known_evidence_count": null, "matches": 586, "name": "Protein of unknown function (DUF1033)", "partial_evidence_count": null, "pfam_id": "PF06279", "proteins": 586, "proteomes": 584, "short_name": "DUF1033", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06279", "structures": 0, "taxa": 790, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 187, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is centrally located in a group of uncharacterised plant proteins. It is often found associated to [pfam:PF12371]", "domain_architectures": 17, "interpro_id": "IPR056001", "known_evidence_count": null, "matches": 587, "name": "Domain of unknown function (DUF7579)", "partial_evidence_count": null, "pfam_id": "PF24474", "proteins": 586, "proteomes": 320, "short_name": "DUF7579", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24474", "structures": 0, "taxa": 897, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 439, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short protein is found mainly in firmicute bacteria. It is functionally uncharacterised.", "domain_architectures": 2, "interpro_id": "IPR024208", "known_evidence_count": null, "matches": 585, "name": "Domain of unknown function (DUF3842)", "partial_evidence_count": null, "pfam_id": "PF12953", "proteins": 585, "proteomes": 527, "short_name": "DUF3842", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12953", "structures": 0, "taxa": 1056, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 351, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a beta-sandwich structure with long twisted strands.", "domain_architectures": 5, "interpro_id": "", "known_evidence_count": null, "matches": 737, "name": "Domain of unknown function (DUF7852)", "partial_evidence_count": null, "pfam_id": "PF25250", "proteins": 585, "proteomes": 274, "short_name": "DUF7852", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25250", "structures": 0, "taxa": 445, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 545, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Proteins in this family are predicted to adopt a series of four alpha helices that do not form a compact domain. There is weak evidence for a homodimer from structure prediction.", "domain_architectures": 3, "interpro_id": "IPR058276", "known_evidence_count": null, "matches": 585, "name": "Family of unknown function (DUF7970)", "partial_evidence_count": null, "pfam_id": "PF25925", "proteins": 585, "proteomes": 238, "short_name": "DUF7970", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25925", "structures": 0, "taxa": 394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 485, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria.", "domain_architectures": 3, "interpro_id": "IPR058279", "known_evidence_count": null, "matches": 842, "name": "Family of unknown function (DUF7973)", "partial_evidence_count": null, "pfam_id": "PF25928", "proteins": 585, "proteomes": 498, "short_name": "DUF7973", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25928", "structures": 0, "taxa": 1011, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 392, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is usually found in tandem in uncharacterised proteins mainly from Leptospira lineage. This domain closely resembles the Salmonella typhoid toxin PltB subunit.", "domain_architectures": 2, "interpro_id": "IPR061846", "known_evidence_count": null, "matches": 646, "name": "Domain of unknown function (DUF8785)", "partial_evidence_count": null, "pfam_id": "PF31045", "proteins": 585, "proteomes": 565, "short_name": "DUF8785", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31045", "structures": 0, "taxa": 864, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 362, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. Proteins in this family are predominantly found in Bacteroidetes and are approximately 80 amino acids in length. There are several conserved motifs: IxxGL, FGxY and GEY.", "domain_architectures": 3, "interpro_id": "IPR049211", "known_evidence_count": null, "matches": 584, "name": "Family of unknown function (DUF6814)", "partial_evidence_count": null, "pfam_id": "PF20664", "proteins": 584, "proteomes": 583, "short_name": "DUF6814", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20664", "structures": 0, "taxa": 717, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in bacteria. It may to adopt a beta-sandwich fold with an Ig-like topology.", "domain_architectures": 104, "interpro_id": "IPR061674", "known_evidence_count": null, "matches": 592, "name": "Domain of unknown function (DUF8613)", "partial_evidence_count": null, "pfam_id": "PF30219", "proteins": 584, "proteomes": 552, "short_name": "DUF8613", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30219", "structures": 0, "taxa": 825, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 348, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 85 and 118 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046549", "known_evidence_count": null, "matches": 583, "name": "Family of unknown function (DUF6703)", "partial_evidence_count": null, "pfam_id": "PF20444", "proteins": 583, "proteomes": 582, "short_name": "DUF6703", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20444", "structures": 0, "taxa": 767, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 462, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised plant proteins. It is predicted to fold into unique alpha/beta structure consisting of a meander curved beta-sheet and alpha-helices packed on one face of the sheet and sandwiched with another four-stranded small beta-sheet.", "domain_architectures": 13, "interpro_id": "IPR059267", "known_evidence_count": null, "matches": 597, "name": "Domain of unknown function (DUF8223)", "partial_evidence_count": null, "pfam_id": "PF26668", "proteins": 583, "proteomes": 352, "short_name": "DUF8223", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26668", "structures": 0, "taxa": 978, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 544, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR031742", "known_evidence_count": null, "matches": 582, "name": "Domain of unknown function (DUF4730)", "partial_evidence_count": null, "pfam_id": "PF15873", "proteins": 582, "proteomes": 540, "short_name": "DUF4730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15873", "structures": 0, "taxa": 1851, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 549, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the central alpha+beta domain of this family of proteins. The function of these proteins is unknown.", "domain_architectures": 7, "interpro_id": "IPR058775", "known_evidence_count": null, "matches": 588, "name": "Family of unknown function (DUF8054) central domain", "partial_evidence_count": null, "pfam_id": "PF26238", "proteins": 582, "proteomes": 259, "short_name": "DUF8054_M", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26238", "structures": 0, "taxa": 406, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 572, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative proteins are found in Trichomonas vaginalis in large numbers. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR025180", "known_evidence_count": null, "matches": 581, "name": "Protein of unknown function (DUF4107)", "partial_evidence_count": null, "pfam_id": "PF13389", "proteins": 581, "proteomes": 1, "short_name": "DUF4107", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13389", "structures": 0, "taxa": 10, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 419, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry consists of an uncharacterised domain found in proteins of around 660 residues in length and is mainly found in various Bacteroides species. The function of these proteins is unknown. This domain consists of repeated strands.", "domain_architectures": 4, "interpro_id": "IPR032533", "known_evidence_count": null, "matches": 581, "name": "Domain of unknown function (DUF4954)", "partial_evidence_count": null, "pfam_id": "PF16314", "proteins": 581, "proteomes": 562, "short_name": "DUF4954", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16314", "structures": 0, "taxa": 960, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 396, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in Firmicutes and Actinobacteria. Proteins in this family are typically between 587 and 710 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046062", "known_evidence_count": null, "matches": 593, "name": "Family of unknown function (DUF6020)", "partial_evidence_count": null, "pfam_id": "PF19484", "proteins": 581, "proteomes": 392, "short_name": "DUF6020", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19484", "structures": 0, "taxa": 695, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 398, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from alphaproteobacteria. It is predicted to fold into an alpha-helical hairpin structure.", "domain_architectures": 1, "interpro_id": "IPR061837", "known_evidence_count": null, "matches": 581, "name": "Domain of unknown function (DUF8776)", "partial_evidence_count": null, "pfam_id": "PF31035", "proteins": 581, "proteomes": 557, "short_name": "DUF8776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31035", "structures": 0, "taxa": 805, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes.", "domain_architectures": 1, "interpro_id": "IPR021402", "known_evidence_count": null, "matches": 580, "name": "Protein of unknown function (DUF3042)", "partial_evidence_count": null, "pfam_id": "PF11240", "proteins": 580, "proteomes": 569, "short_name": "DUF3042", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11240", "structures": 0, "taxa": 808, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 120 amino acids in length. This domain has a conserved GHHSE sequence motif.", "domain_architectures": 16, "interpro_id": "IPR021944", "known_evidence_count": null, "matches": 579, "name": "Domain of unknown function (DUF3560)", "partial_evidence_count": null, "pfam_id": "PF12083", "proteins": 579, "proteomes": 507, "short_name": "DUF3560", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12083", "structures": 0, "taxa": 1077, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 498, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in insects. This region contains a repeat rich in tryptophan and lysine. Structure prediction suggests that these repeats for extended helical twisting pairs of antiparallel beta strands.", "domain_architectures": 20, "interpro_id": "IPR032134", "known_evidence_count": null, "matches": 2022, "name": "Domain of unknown function (DUF4816)", "partial_evidence_count": null, "pfam_id": "PF16086", "proteins": 579, "proteomes": 235, "short_name": "DUF4816", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16086", "structures": 0, "taxa": 842, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046130", "known_evidence_count": null, "matches": 579, "name": "Family of unknown function (DUF6127)", "partial_evidence_count": null, "pfam_id": "PF19622", "proteins": 579, "proteomes": 502, "short_name": "DUF6127", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19622", "structures": 0, "taxa": 866, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold onto a structure with significant similarity to Glucose-regulated metallo-peptidase M90. This domain is frequently found in combination with [pfam:PF13387].", "domain_architectures": 4, "interpro_id": "IPR057166", "known_evidence_count": null, "matches": 710, "name": "Domain of unknown function (DUF7844)", "partial_evidence_count": null, "pfam_id": "PF25226", "proteins": 579, "proteomes": 573, "short_name": "DUF7844", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25226", "structures": 0, "taxa": 663, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 234, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000087) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the lasalocid biosynthetic gene cluster from Streptomyces lasaliensis [[cite:PUB00098916]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 8, "interpro_id": "IPR045682", "known_evidence_count": null, "matches": 579, "name": "Family of unknown function (DUF6193)", "partial_evidence_count": null, "pfam_id": "PF19692", "proteins": 578, "proteomes": 426, "short_name": "DUF6193", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19692", "structures": 0, "taxa": 594, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in a group of fungal uncharacterised proteins that also contain [pfam:PF12906] and [pfam:PF23113]. It has highly conserved E and L residues.", "domain_architectures": 12, "interpro_id": "IPR057211", "known_evidence_count": null, "matches": 578, "name": "Family of unknown function (DUF7889)", "partial_evidence_count": null, "pfam_id": "PF25417", "proteins": 578, "proteomes": 567, "short_name": "DUF7889", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25417", "structures": 0, "taxa": 1005, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 338, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021367", "known_evidence_count": null, "matches": 579, "name": "Protein of unknown function (DUF2982)", "partial_evidence_count": null, "pfam_id": "PF11201", "proteins": 577, "proteomes": 573, "short_name": "DUF2982", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11201", "structures": 0, "taxa": 733, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 397, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 244 and 264 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025132", "known_evidence_count": null, "matches": 596, "name": "Protein of unknown function (DUF4058)", "partial_evidence_count": null, "pfam_id": "PF13267", "proteins": 576, "proteomes": 157, "short_name": "DUF4058", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13267", "structures": 0, "taxa": 495, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 502, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 109 and 206 amino acids in length. There is a conserved RFKTQP sequence motif.", "domain_architectures": 8, "interpro_id": "IPR031521", "known_evidence_count": null, "matches": 577, "name": "Domain of unknown function (DUF4695)", "partial_evidence_count": null, "pfam_id": "PF15766", "proteins": 576, "proteomes": 447, "short_name": "DUF4695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15766", "structures": 0, "taxa": 1737, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 404, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in bacteria and archaea. The function is not known. The structure of two proteins in this family were solved using NMR and shown to adopt a winged helix-turn-helix fold [[cite:PUB00075673]]. Structural analysis shows that these proteins form an unusual dimeric conformation. This dimer was shown to be similar to that found in the FadR and TubR wHTH domains. It was suggested [[cite:PUB00075673]] that these proteins are not very likely to bind to DNA.", "domain_architectures": 4, "interpro_id": "IPR019707", "known_evidence_count": null, "matches": 575, "name": "Winged helix-turn-helix domain (DUF2582)", "partial_evidence_count": null, "pfam_id": "PF10771", "proteins": 575, "proteomes": 323, "short_name": "DUF2582", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10771", "structures": 2, "taxa": 576, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 352, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family is found in various Bacteroides and Prevotella species. Proteins in this family are around 350 amino acids in length.", "domain_architectures": 27, "interpro_id": "IPR032185", "known_evidence_count": null, "matches": 590, "name": "Domain of unknown function (DUF5017)", "partial_evidence_count": null, "pfam_id": "PF16409", "proteins": 575, "proteomes": 378, "short_name": "DUF5017", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16409", "structures": 0, "taxa": 636, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 349, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001593) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the ficellomycin biosynthetic gene cluster from Streptomyces ficellus [[cite:PUB00099388]].", "domain_architectures": 1, "interpro_id": "IPR045919", "known_evidence_count": null, "matches": 575, "name": "Family of unknown function (DUF6338)", "partial_evidence_count": null, "pfam_id": "PF19865", "proteins": 575, "proteomes": 538, "short_name": "DUF6338", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19865", "structures": 0, "taxa": 1098, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is typically between 53 to 190 amino acids in length. This domain is found associated with [pfam:PF01507]. This domain has a conserved KND sequence motif.", "domain_architectures": 7, "interpro_id": "IPR021845", "known_evidence_count": null, "matches": 792, "name": "Domain of unknown function (DUF3440)", "partial_evidence_count": null, "pfam_id": "PF11922", "proteins": 574, "proteomes": 512, "short_name": "DUF3440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11922", "structures": 0, "taxa": 1016, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 510, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a family of membrane and transmembrane proteins from mycobacterial and related species. This domain has similarity to the ligand-binding domains of neurotransmitter ligand-gated ion channels and sensory receptors and it is likely to have similar function.", "domain_architectures": 17, "interpro_id": "IPR061748", "known_evidence_count": null, "matches": 581, "name": "Domain of unknown function (DUF8687)", "partial_evidence_count": null, "pfam_id": "PF30642", "proteins": 573, "proteomes": 169, "short_name": "DUF8687", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30642", "structures": 0, "taxa": 477, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 392, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mainly found in bacteria.", "domain_architectures": 6, "interpro_id": "IPR043769", "known_evidence_count": null, "matches": 572, "name": "Family of unknown function (DUF5715)", "partial_evidence_count": null, "pfam_id": "PF18979", "proteins": 572, "proteomes": 541, "short_name": "DUF5715", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18979", "structures": 0, "taxa": 802, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 299, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a number of hypothetical putative membrane proteins which seem to be specific to Photorhabdus and Yersinia species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR010665", "known_evidence_count": null, "matches": 571, "name": "Protein of unknown function (DUF1240)", "partial_evidence_count": null, "pfam_id": "PF06836", "proteins": 571, "proteomes": 232, "short_name": "DUF1240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06836", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 348, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised proteins from bacteria (predominantly Proteobacteria) and eukaryotes. This domain is approximately 60 amino acids in length. There is a conserved motif KxxRG and a highly conserved L residue. It may be a DNA-binding domain.", "domain_architectures": 3, "interpro_id": "IPR045526", "known_evidence_count": null, "matches": 609, "name": "Domain of unknown function (DUF6471)", "partial_evidence_count": null, "pfam_id": "PF20075", "proteins": 571, "proteomes": 513, "short_name": "DUF6471", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20075", "structures": 0, "taxa": 1012, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 349, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021439", "known_evidence_count": null, "matches": 570, "name": "Protein of unknown function (DUF3088)", "partial_evidence_count": null, "pfam_id": "PF11287", "proteins": 570, "proteomes": 524, "short_name": "DUF3088", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11287", "structures": 0, "taxa": 837, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025477", "known_evidence_count": null, "matches": 570, "name": "Domain of unknown function (DUF4327)", "partial_evidence_count": null, "pfam_id": "PF14217", "proteins": 570, "proteomes": 223, "short_name": "DUF4327", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14217", "structures": 0, "taxa": 619, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins found in Eukaryota, has no known function.", "domain_architectures": 8, "interpro_id": "IPR020526", "known_evidence_count": null, "matches": 570, "name": "Family of unknown function (DUF5323)", "partial_evidence_count": null, "pfam_id": "PF17257", "proteins": 570, "proteomes": 388, "short_name": "DUF5323", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17257", "structures": 10, "taxa": 1171, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 427, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Rhodobacterales. Most members are predicted to have 2 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR020308", "known_evidence_count": null, "matches": 570, "name": "Family of unknown function (DUF5337)", "partial_evidence_count": null, "pfam_id": "PF17272", "proteins": 570, "proteomes": 569, "short_name": "DUF5337", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17272", "structures": 0, "taxa": 793, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in Halobacteria. They are likely composed mainly of alpha-helices. These proteins contain a semi-conserved GxWTDDxxAA sequence motif toward their C terminus.", "domain_architectures": 7, "interpro_id": "IPR055693", "known_evidence_count": null, "matches": 571, "name": "Family of unknown function (DUF7269)", "partial_evidence_count": null, "pfam_id": "PF23933", "proteins": 570, "proteomes": 239, "short_name": "DUF7269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23933", "structures": 0, "taxa": 404, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 334, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta structure composed of a central five-stranded mixed beta-sheet and alpha-helices packed on both sides. This domain has a significant structural similarity to domains members of PD-(D/E)XK nuclease superfamily that extends to the active site architecture suggesting that this domain may possess endonuclease activity. This domain is frequently found in combination with [pfam:PF28123] (DUF8370).", "domain_architectures": 12, "interpro_id": "IPR059415", "known_evidence_count": null, "matches": 570, "name": "Domain of unknown function (DUF8371)", "partial_evidence_count": null, "pfam_id": "PF28130", "proteins": 570, "proteomes": 504, "short_name": "DUF8371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28130", "structures": 0, "taxa": 1264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 303, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 140 residues found in secreted proteins in Actinomycetota, particularly Pseudonocardiaceae. This domain adopts a double psi beta barrel fold. The function of this domain remains to be determined.", "domain_architectures": 13, "interpro_id": "IPR061875", "known_evidence_count": null, "matches": 572, "name": "Domain of unknown function (DUF8814)", "partial_evidence_count": null, "pfam_id": "PF31114", "proteins": 570, "proteomes": 508, "short_name": "DUF8814", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31114", "structures": 0, "taxa": 717, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes", "domain_architectures": 2, "interpro_id": "IPR021525", "known_evidence_count": null, "matches": 575, "name": "Protein of unknown function (DUF3189)", "partial_evidence_count": null, "pfam_id": "PF11385", "proteins": 569, "proteomes": 432, "short_name": "DUF3189", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11385", "structures": 0, "taxa": 759, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 450, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins. Some members have an aspartic peptidase domain at the C-terminal ([pfam:PF13650]).", "domain_architectures": 29, "interpro_id": "IPR025165", "known_evidence_count": null, "matches": 572, "name": "Protein of unknown function (DUF4100)", "partial_evidence_count": null, "pfam_id": "PF13352", "proteins": 569, "proteomes": 132, "short_name": "DUF4100", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13352", "structures": 0, "taxa": 394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 230 residues in length and is mainly found in various Bacteroides and Prevotella species. The function of this family is unknown.", "domain_architectures": 8, "interpro_id": "IPR032578", "known_evidence_count": null, "matches": 570, "name": "Domain of unknown function (DUF4919)", "partial_evidence_count": null, "pfam_id": "PF16266", "proteins": 569, "proteomes": 455, "short_name": "DUF4919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16266", "structures": 0, "taxa": 773, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 386, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They share sequence similarity to Ig-like domains found in a number of proteins such as xylosyltransferase, alkylpurine DNA glycosylase, cycloisomaltooligosaccharide glucanotransferase and are predicted to adopt the same structure.", "domain_architectures": 3, "interpro_id": "IPR054221", "known_evidence_count": null, "matches": 569, "name": "Family of unknown function (DUF6941)", "partial_evidence_count": null, "pfam_id": "PF22091", "proteins": 568, "proteomes": 541, "short_name": "DUF6941", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22091", "structures": 0, "taxa": 1235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 332, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR021751", "known_evidence_count": null, "matches": 567, "name": "Protein of unknown function (DUF3318)", "partial_evidence_count": null, "pfam_id": "PF11780", "proteins": 567, "proteomes": 370, "short_name": "DUF3318", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11780", "structures": 0, "taxa": 795, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Members of this family, which are found in a set of hypothetical bacterial proteins, contain a core of six alpha-helices, where one central helix is surrounded by the other five. The exact function of this family has not, as yet, been determined [[cite:PUB00035390]]. The known structure shows this domain contains two copies of the histone fold [[cite:PUB00035390]].", "domain_architectures": 2, "interpro_id": "IPR015207", "known_evidence_count": null, "matches": 566, "name": "Domain of unknown function (DUF1931)", "partial_evidence_count": null, "pfam_id": "PF09123", "proteins": 566, "proteomes": 528, "short_name": "DUF1931", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09123", "structures": 3, "taxa": 919, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 343, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 557 and 582 amino acids in length. There is a conserved YNG sequence motif.", "domain_architectures": 3, "interpro_id": "IPR046107", "known_evidence_count": null, "matches": 569, "name": "Protein of unknown function (DUF6044)", "partial_evidence_count": null, "pfam_id": "PF19510", "proteins": 566, "proteomes": 490, "short_name": "DUF6044", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19510", "structures": 0, "taxa": 774, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 349, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001418) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from the myxochromide D biosynthetic gene cluster from Hyalangium minutum [[cite:PUB00098945]].", "domain_architectures": 4, "interpro_id": "IPR045709", "known_evidence_count": null, "matches": 566, "name": "Family of unknown function (DUF6065)", "partial_evidence_count": null, "pfam_id": "PF19541", "proteins": 566, "proteomes": 493, "short_name": "DUF6065", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19541", "structures": 0, "taxa": 912, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised bacterial proteins. It has a conserved WP motif and it may contain a helix-turn-helix motif as it overlaps with members in clan CL0123.", "domain_architectures": 1, "interpro_id": "IPR045942", "known_evidence_count": null, "matches": 566, "name": "Domain of unknown function (DUF6362)", "partial_evidence_count": null, "pfam_id": "PF19889", "proteins": 566, "proteomes": 402, "short_name": "DUF6362", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19889", "structures": 0, "taxa": 826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length and contain three transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR046027", "known_evidence_count": null, "matches": 565, "name": "Family of unknown function (DUF5985)", "partial_evidence_count": null, "pfam_id": "PF19447", "proteins": 565, "proteomes": 267, "short_name": "DUF5985", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19447", "structures": 0, "taxa": 490, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 520, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Archaeal domain of unknown function.", "domain_architectures": 2, "interpro_id": "IPR007171", "known_evidence_count": null, "matches": 564, "name": "Domain of unknown function (DUF371)", "partial_evidence_count": null, "pfam_id": "PF04027", "proteins": 564, "proteomes": 563, "short_name": "DUF371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04027", "structures": 2, "taxa": 1019, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 510, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Caenorhabditis elegans specific proteins of unknown function. Members of this family have an alpha/beta hydrolase fold.", "domain_architectures": 22, "interpro_id": "IPR010463", "known_evidence_count": null, "matches": 598, "name": "Alpha/beta hydrolase of unknown function (DUF1057)", "partial_evidence_count": null, "pfam_id": "PF06342", "proteins": 564, "proteomes": 204, "short_name": "DUF1057", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06342", "structures": 0, "taxa": 664, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 488, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "A number of this family members have a coiled coil domain at the C terminal.", "domain_architectures": 4, "interpro_id": "IPR035205", "known_evidence_count": null, "matches": 564, "name": "Family of unknown function (DUF5320)", "partial_evidence_count": null, "pfam_id": "PF17253", "proteins": 564, "proteomes": 471, "short_name": "DUF5320", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17253", "structures": 0, "taxa": 1269, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 377, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in bacteria. It is predicted to adopt a globular structure consisting of two nearly orthogonal beta-sheets and two helices that connect them. Toward the C terminus these proteins contain a highly conserved enriched with negatively charged residues region having nearly invariant EKDFxC sequence motif.", "domain_architectures": 1, "interpro_id": "IPR053825", "known_evidence_count": null, "matches": 564, "name": "Family of unknown function (DUF7009)", "partial_evidence_count": null, "pfam_id": "PF22668", "proteins": 564, "proteomes": 521, "short_name": "DUF7009", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22668", "structures": 0, "taxa": 768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 131 to 151 amino acids in length. This protein has a conserved HWTH sequence motif. These proteins are predicted to adopt a globular structure with OB-fold topology.", "domain_architectures": 2, "interpro_id": "IPR021856", "known_evidence_count": null, "matches": 563, "name": "Protein of unknown function (DUF3465)", "partial_evidence_count": null, "pfam_id": "PF11948", "proteins": 563, "proteomes": 533, "short_name": "DUF3465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11948", "structures": 0, "taxa": 967, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 356, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 212 to 238 amino acids in length. This protein has a conserved SCL sequence motif.", "domain_architectures": 3, "interpro_id": "IPR021927", "known_evidence_count": null, "matches": 608, "name": "Protein of unknown function (DUF3540)", "partial_evidence_count": null, "pfam_id": "PF12059", "proteins": 563, "proteomes": 404, "short_name": "DUF3540", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12059", "structures": 0, "taxa": 762, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 343, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 151 and 236 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR046172", "known_evidence_count": null, "matches": 615, "name": "Family of unknown function (DUF6174)", "partial_evidence_count": null, "pfam_id": "PF19671", "proteins": 563, "proteomes": 449, "short_name": "DUF6174", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19671", "structures": 0, "taxa": 892, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 449, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It has a detectable similarity to known glycosyltransferases clan GT-A and is predicted to adopt similar structure.", "domain_architectures": 8, "interpro_id": "IPR056682", "known_evidence_count": null, "matches": 624, "name": "Domain of unknown function (DUF7780)", "partial_evidence_count": null, "pfam_id": "PF25002", "proteins": 563, "proteomes": 291, "short_name": "DUF7780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25002", "structures": 0, "taxa": 789, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 401, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045442", "known_evidence_count": null, "matches": 562, "name": "Family of unknown function (DUF6505)", "partial_evidence_count": null, "pfam_id": "PF20115", "proteins": 562, "proteomes": 560, "short_name": "DUF6505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20115", "structures": 0, "taxa": 835, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This hypothetical protein, found in bacteria and in the eukaryote Leishmania, has no known function.", "domain_architectures": 1, "interpro_id": "IPR015045", "known_evidence_count": null, "matches": 561, "name": "Protein of unknown function (DUF1861)", "partial_evidence_count": null, "pfam_id": "PF08950", "proteins": 561, "proteomes": 368, "short_name": "DUF1861", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08950", "structures": 6, "taxa": 589, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 71 and 125 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR024269", "known_evidence_count": null, "matches": 560, "name": "Protein of unknown function (DUF3791)", "partial_evidence_count": null, "pfam_id": "PF12668", "proteins": 560, "proteomes": 363, "short_name": "DUF3791", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12668", "structures": 0, "taxa": 712, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length. There is a single completely conserved residue D that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR022080", "known_evidence_count": null, "matches": 559, "name": "Protein of unknown function (DUF3630)", "partial_evidence_count": null, "pfam_id": "PF12305", "proteins": 559, "proteomes": 558, "short_name": "DUF3630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12305", "structures": 0, "taxa": 774, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 495, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry corresponds to a protein precursor of a peptide from the edible fungi Cordyceps militaris is said to induce apoptosis in mammalian cell lines in vitro [[cite:PUB00098843]].", "domain_architectures": 18, "interpro_id": "IPR045564", "known_evidence_count": null, "matches": 560, "name": "Family of unknown function (DUF5910)", "partial_evidence_count": null, "pfam_id": "PF19287", "proteins": 559, "proteomes": 219, "short_name": "DUF5910", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19287", "structures": 0, "taxa": 521, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 333, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A predicted immunity protein with an alpha+beta fold and conserved tryptophan,tyrosine and an acidic residues. Proteins containing this domain are present in bacterial polymorphic toxin systems as an immediate gene neighbor of the toxin gene, which usually contains toxin domains of the ColD/E5, Tox-REase-4, Ntox49 or Ntox14 families [[cite:PUB00066726]]. The domain is also found in heterogeneous polyimmunity loci.", "domain_architectures": 5, "interpro_id": "IPR025560", "known_evidence_count": null, "matches": 564, "name": "Immunity protein 22", "partial_evidence_count": null, "pfam_id": "PF14112", "proteins": 558, "proteomes": 502, "short_name": "DUF4284", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14112", "structures": 0, "taxa": 869, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a presumed domain that is functionally uncharacterised. This domain family is primarily found in Rhodobacteria, and is approximately 300 amino acids in length. The family is found to the C-terminus of [pfam:PF02485] and so is likely to have a role in carbohydrate modification.", "domain_architectures": 3, "interpro_id": "IPR045971", "known_evidence_count": null, "matches": 559, "name": "Family of unknown function (DUF5927)", "partial_evidence_count": null, "pfam_id": "PF19349", "proteins": 558, "proteomes": 557, "short_name": "DUF5927", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19349", "structures": 0, "taxa": 767, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 473, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised prokaryotic proteins. They are likely associated with the membrane and consists of several transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR055966", "known_evidence_count": null, "matches": 558, "name": "Family of unknown function (DUF7544)", "partial_evidence_count": null, "pfam_id": "PF24400", "proteins": 558, "proteomes": 449, "short_name": "DUF7544", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24400", "structures": 0, "taxa": 822, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 359, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 100 residues found in bacteria. This domain is typically located at the C-terminus of proteins containing DUF1156 ([pfam:PF06634]). These proteins are often associated with mobile genetic elements, including transposases and site-specific DNA methyltransferases. The function of this domain remains to be determined.", "domain_architectures": 8, "interpro_id": "IPR061868", "known_evidence_count": null, "matches": 558, "name": "Domain of unknown function (DUF8807)", "partial_evidence_count": null, "pfam_id": "PF31094", "proteins": 558, "proteomes": 532, "short_name": "DUF8807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31094", "structures": 0, "taxa": 1340, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of proteins identified in Leptospira interrogans.", "domain_architectures": 24, "interpro_id": "IPR011448", "known_evidence_count": null, "matches": 594, "name": "Protein of unknown function (DUF1554)", "partial_evidence_count": null, "pfam_id": "PF07588", "proteins": 557, "proteomes": 112, "short_name": "DUF1554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07588", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 346, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR021336", "known_evidence_count": null, "matches": 557, "name": "Protein of unknown function (DUF2949)", "partial_evidence_count": null, "pfam_id": "PF11165", "proteins": 557, "proteomes": 240, "short_name": "DUF2949", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11165", "structures": 0, "taxa": 661, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 349, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 186 and 200 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046584", "known_evidence_count": null, "matches": 557, "name": "Family of unknown function (DUF6642)", "partial_evidence_count": null, "pfam_id": "PF20347", "proteins": 557, "proteomes": 539, "short_name": "DUF6642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20347", "structures": 0, "taxa": 720, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 312, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial domain of unknown function.", "domain_architectures": 1, "interpro_id": "IPR054262", "known_evidence_count": null, "matches": 557, "name": "Domain of unknown function (DUF6993)", "partial_evidence_count": null, "pfam_id": "PF22504", "proteins": 557, "proteomes": 550, "short_name": "DUF6993", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22504", "structures": 0, "taxa": 614, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 13, "interpro_id": "IPR032096", "known_evidence_count": null, "matches": 896, "name": "Domain of unknown function (DUF4815)", "partial_evidence_count": null, "pfam_id": "PF16075", "proteins": 556, "proteomes": 491, "short_name": "DUF4815", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16075", "structures": 15, "taxa": 1262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria. Several members are annotated as being protein YbfA. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019663", "known_evidence_count": null, "matches": 555, "name": "Protein of unknown function (DUF2517)", "partial_evidence_count": null, "pfam_id": "PF10725", "proteins": 555, "proteomes": 555, "short_name": "DUF2517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10725", "structures": 0, "taxa": 756, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 297, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria. Recently, it was proposed that members of this family along with members of DUF943 ([pfam:PF06092]) should be recognised as a putative toxin-antitoxin pair in which DUF3289 is a homolog of Colicin M and DUF943 ([pfam:PF06092]) acts as its cognate immunity protein [[cite:PUB00154362]].", "domain_architectures": 21, "interpro_id": "IPR017483", "known_evidence_count": null, "matches": 576, "name": "Protein of unknown function (DUF3289)", "partial_evidence_count": null, "pfam_id": "PF11692", "proteins": 555, "proteomes": 270, "short_name": "DUF3289", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11692", "structures": 3, "taxa": 501, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 330, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteria. Members of this family have one or two predicted trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035406", "known_evidence_count": null, "matches": 555, "name": "Family of unknown function (DUF5412)", "partial_evidence_count": null, "pfam_id": "PF17428", "proteins": 555, "proteomes": 452, "short_name": "DUF5412", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17428", "structures": 0, "taxa": 742, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 349, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain family is functionally uncharacterised. This domain is found in bacteria and is typically 100 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046647", "known_evidence_count": null, "matches": 555, "name": "Domain of unknown function (DUF6759)", "partial_evidence_count": null, "pfam_id": "PF20545", "proteins": 555, "proteomes": 173, "short_name": "DUF6759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20545", "structures": 0, "taxa": 220, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 330, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is found in Lactobacillae prophages.", "domain_architectures": 1, "interpro_id": "IPR012455", "known_evidence_count": null, "matches": 554, "name": "Prophage protein (DUF1660)", "partial_evidence_count": null, "pfam_id": "PF07874", "proteins": 554, "proteomes": 455, "short_name": "DUF1660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07874", "structures": 0, "taxa": 632, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 287, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised and it is found in bacteria and viruses. Proteins in this family are typically between 161 and 200 amino acids in length. There are some conserved sequences: HQK and KWG at the N-terminal, and HNxxW near the C-terminal.", "domain_architectures": 4, "interpro_id": "IPR046208", "known_evidence_count": null, "matches": 554, "name": "Family of unknown function (DUF6241)", "partial_evidence_count": null, "pfam_id": "PF19754", "proteins": 554, "proteomes": 414, "short_name": "DUF6241", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19754", "structures": 0, "taxa": 552, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in functionally uncharacterised proteins from Burkholderiaceae. This domain is approximately 60 amino acids in length and it has a conserved tryptophan residue at the N-terminal, the conserved motifs PxW and AxRxxxE and an aspartate conserved residue at the C-terminal. Some members containing this domain are hypothetical transposases.", "domain_architectures": 2, "interpro_id": "IPR046696", "known_evidence_count": null, "matches": 554, "name": "Domain of unknown function (DUF6566)", "partial_evidence_count": null, "pfam_id": "PF20204", "proteins": 554, "proteomes": 248, "short_name": "DUF6566", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20204", "structures": 0, "taxa": 335, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 452, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to contain two short alpha-helices. At the N-terminus, it contains a number of highly conserved positively charged residues.", "domain_architectures": 6, "interpro_id": "IPR057212", "known_evidence_count": null, "matches": 558, "name": "Domain of unknown function (DUF7890)", "partial_evidence_count": null, "pfam_id": "PF25418", "proteins": 554, "proteomes": 256, "short_name": "DUF7890", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25418", "structures": 0, "taxa": 678, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 314, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in both bacteria and archaea. The proteins are predominantly found in Actinomycetes and Halobacteria. The proteins in this family are approximately 300 to 400 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR058441", "known_evidence_count": null, "matches": 554, "name": "Domain of unknown function (DUF8128)", "partial_evidence_count": null, "pfam_id": "PF26449", "proteins": 554, "proteomes": 415, "short_name": "DUF8128", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26449", "structures": 0, "taxa": 687, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 295, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical putative membrane proteins from Escherichia coli, Yersinia pestis and Salmonella typhi. Recently, it was proposed that members of this family along with members of DUF3289 ([pfam:PF11692]) should be recognised as a putative toxin-antitoxin pair in which DUF3289 ([pfam:PF11692]) is a homolog of Colicin M and DUF943 acts as its cognate immunity protein [[cite:PUB00154362]].", "domain_architectures": 2, "interpro_id": "IPR010351", "known_evidence_count": null, "matches": 553, "name": "Enterobacterial putative membrane protein (DUF943)", "partial_evidence_count": null, "pfam_id": "PF06092", "proteins": 553, "proteomes": 141, "short_name": "DUF943", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06092", "structures": 0, "taxa": 239, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 417, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of uncharacterized proteins is mostly found in Alphaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR020349", "known_evidence_count": null, "matches": 553, "name": "Family of unknown function (DUF5333)", "partial_evidence_count": null, "pfam_id": "PF17267", "proteins": 553, "proteomes": 509, "short_name": "DUF5333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17267", "structures": 0, "taxa": 704, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 407, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in bacteria. Proteins in this family are typically between 294 and 372 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR046312", "known_evidence_count": null, "matches": 576, "name": "Family of unknown function (DUF6454)", "partial_evidence_count": null, "pfam_id": "PF20055", "proteins": 553, "proteomes": 537, "short_name": "DUF6454", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20055", "structures": 0, "taxa": 1076, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 383, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of bacterial proteins. The predicted structure shows a 5 stranded beta barrel elaborated with many alpha helical elements.", "domain_architectures": 13, "interpro_id": "IPR058292", "known_evidence_count": null, "matches": 553, "name": "Family of unknown function (DUF7986)", "partial_evidence_count": null, "pfam_id": "PF25948", "proteins": 553, "proteomes": 479, "short_name": "DUF7986", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25948", "structures": 0, "taxa": 1070, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 328, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This set of hypothetical proteins is produced by prokaryotes pertaining to the Bacillus genus.", "domain_architectures": 5, "interpro_id": "IPR015053", "known_evidence_count": null, "matches": 554, "name": "Domain of unknown function (DUF1871)", "partial_evidence_count": null, "pfam_id": "PF08958", "proteins": 552, "proteomes": 517, "short_name": "DUF1871", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08958", "structures": 2, "taxa": 741, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of bacterial proteins assume a beta-sandwich structure consisting of two antiparallel beta-sheets similar to an immunoglobulin-like fold, with an additional small, antiparallel beta-sheet. The longer-stranded beta-sheet is made up of four antiparallel beta-strands. The shorter-stranded beta-sheet consists of five beta-strands, four of these beta-strands form an antiparallel beta-sheet. The exact function of this family of proteins is unknown, though a putative role includes involvement in host-bacterial interactions involved in endocytosis or phagocytosis, possibly during bacterial internalisation [[cite:PUB00028893]].", "domain_architectures": 2, "interpro_id": "IPR015250", "known_evidence_count": null, "matches": 554, "name": "Domain of unknown function (DUF1942)", "partial_evidence_count": null, "pfam_id": "PF09167", "proteins": 552, "proteomes": 249, "short_name": "DUF1942", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09167", "structures": 1, "taxa": 292, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 393, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is functionally uncharacterised. This domain family is found in eukaryotes, and is around 420 amino acids in length. Structurally, this family is made of alpha helices.", "domain_architectures": 45, "interpro_id": "IPR049232", "known_evidence_count": null, "matches": 602, "name": "Family of unknown function (DUF6829)", "partial_evidence_count": null, "pfam_id": "PF20717", "proteins": 552, "proteomes": 249, "short_name": "DUF6829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20717", "structures": 0, "taxa": 523, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 523, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the second domain in a family of uncharacterised proteins from halophilic archaea that contain four domains. The proteins in this family are predominantly found in the class Halobacteria, which includes families such as Haloferacaceae, Natrialbaceae, and Haloarculaceae. These proteins are typically around 400 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR058603", "known_evidence_count": null, "matches": 552, "name": "Domain of unknown function (DUF8167) 2nd domain", "partial_evidence_count": null, "pfam_id": "PF26502", "proteins": 552, "proteomes": 246, "short_name": "DUF8167_2nd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26502", "structures": 0, "taxa": 381, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes.", "domain_architectures": 3, "interpro_id": "IPR021707", "known_evidence_count": null, "matches": 551, "name": "Protein of unknown function (DUF3290)", "partial_evidence_count": null, "pfam_id": "PF11694", "proteins": 551, "proteomes": 534, "short_name": "DUF3290", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11694", "structures": 0, "taxa": 868, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 460, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a three helical up-and-down bundle.", "domain_architectures": 22, "interpro_id": "IPR061811", "known_evidence_count": null, "matches": 557, "name": "Domain of unknown function (DUF8750)", "partial_evidence_count": null, "pfam_id": "PF30850", "proteins": 551, "proteomes": 359, "short_name": "DUF8750", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30850", "structures": 3, "taxa": 996, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 353, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR019242", "known_evidence_count": null, "matches": 550, "name": "Uncharacterized protein conserved in bacteria (DUF2198)", "partial_evidence_count": null, "pfam_id": "PF09964", "proteins": 550, "proteomes": 549, "short_name": "DUF2198", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09964", "structures": 0, "taxa": 702, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 348, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 185 and 201 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046149", "known_evidence_count": null, "matches": 551, "name": "Family of unknown function (DUF6151)", "partial_evidence_count": null, "pfam_id": "PF19648", "proteins": 550, "proteomes": 531, "short_name": "DUF6151", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19648", "structures": 0, "taxa": 971, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000198) is described by MIBiG as an example of the following biosynthetic classes, polyketide and saccharide. It includes a member from the arenimycin A biosynthetic gene cluster from Salinispora arenicola CNB527 [[cite:PUB00099432],[cite:PUB00099413]].", "domain_architectures": 3, "interpro_id": "IPR046174", "known_evidence_count": null, "matches": 550, "name": "Family of unknown function (DUF6176)", "partial_evidence_count": null, "pfam_id": "PF19673", "proteins": 550, "proteomes": 505, "short_name": "DUF6176", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19673", "structures": 0, "taxa": 995, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 407, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 260 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045514", "known_evidence_count": null, "matches": 549, "name": "Family of unknown function (DUF6478)", "partial_evidence_count": null, "pfam_id": "PF20086", "proteins": 549, "proteomes": 549, "short_name": "DUF6478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20086", "structures": 0, "taxa": 753, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 334, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 100 residues. The domain can occur once or twice within a protein, sometimes in tandem. Some members are predicted lipoproteins. This family is found predominantly in Cyanobacteriota and Actinomycetota. The function of this domain remains to be determined.", "domain_architectures": 21, "interpro_id": "IPR061799", "known_evidence_count": null, "matches": 765, "name": "Domain of unknown function (DUF8738)", "partial_evidence_count": null, "pfam_id": "PF30787", "proteins": 549, "proteomes": 409, "short_name": "DUF8738", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30787", "structures": 0, "taxa": 960, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 366, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of mycobacterial proteins are uncharacterised. This family has partial similarity to EspA related proteins.", "domain_architectures": 9, "interpro_id": "IPR019710", "known_evidence_count": null, "matches": 548, "name": "Domain of unknown function (DUF4226)", "partial_evidence_count": null, "pfam_id": "PF10774", "proteins": 548, "proteomes": 218, "short_name": "DUF4226", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10774", "structures": 0, "taxa": 245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 522, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 2, "interpro_id": "IPR043901", "known_evidence_count": null, "matches": 564, "name": "Family of unknown function (DUF5787)", "partial_evidence_count": null, "pfam_id": "PF19100", "proteins": 548, "proteomes": 277, "short_name": "DUF5787", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19100", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 432, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt an alpha-helical structure consisting of four helices.", "domain_architectures": 20, "interpro_id": "IPR056027", "known_evidence_count": null, "matches": 548, "name": "Domain of unknown function (DUF7608)", "partial_evidence_count": null, "pfam_id": "PF24581", "proteins": 548, "proteomes": 538, "short_name": "DUF7608", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24581", "structures": 0, "taxa": 1132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 435, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in plants. This domain is structurally related to Lipase/lipooxygenase domain (PLAT/LH2 domain).", "domain_architectures": 13, "interpro_id": "IPR056657", "known_evidence_count": null, "matches": 571, "name": "Domain of unknown function (DUF7755)", "partial_evidence_count": null, "pfam_id": "PF24938", "proteins": 548, "proteomes": 386, "short_name": "DUF7755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24938", "structures": 0, "taxa": 1056, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 520, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain three predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058349", "known_evidence_count": null, "matches": 548, "name": "Family of unknown function (DUF8036)", "partial_evidence_count": null, "pfam_id": "PF26119", "proteins": 548, "proteomes": 273, "short_name": "DUF8036", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26119", "structures": 0, "taxa": 473, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 327, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins found predominantly in Bacilli. The domain is approximately 120 amino acids in length. Proteins containing this domain are primarily found in the order Bacillales, including genera such as Bacillus, Brevibacillus, and Thermoactinomyces. The domain contains predicted transmembrane regions.", "domain_architectures": 2, "interpro_id": "IPR020534", "known_evidence_count": null, "matches": 551, "name": "Domain of unknown function (DUF3679)", "partial_evidence_count": null, "pfam_id": "PF12438", "proteins": 547, "proteomes": 547, "short_name": "DUF3679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12438", "structures": 0, "taxa": 700, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 404, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 260 amino acids in length. The family is found to the C-terminus of [pfam:PF02485] and so is likely to have a role in carbohydrate modification.", "domain_architectures": 2, "interpro_id": "IPR045972", "known_evidence_count": null, "matches": 547, "name": "Family of unknown function (DUF5928)", "partial_evidence_count": null, "pfam_id": "PF19350", "proteins": 547, "proteomes": 547, "short_name": "DUF5928", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19350", "structures": 0, "taxa": 742, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 343, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 136 and 200 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR046576", "known_evidence_count": null, "matches": 544, "name": "Family of unknown function (DUF6636)", "partial_evidence_count": null, "pfam_id": "PF20341", "proteins": 544, "proteomes": 499, "short_name": "DUF6636", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20341", "structures": 0, "taxa": 813, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 456, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 15, "interpro_id": "IPR038776", "known_evidence_count": null, "matches": 566, "name": "Family of unknown function (DUF5563)", "partial_evidence_count": null, "pfam_id": "PF17718", "proteins": 543, "proteomes": 332, "short_name": "DUF5563", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17718", "structures": 0, "taxa": 1159, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 319, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is mainly found in Firmicutes but also in viruses. Proteins in this family are approximately 60 amino acids in length and they contain three conserved motifs: RF, TGxxY and TPLLD. Some members of this family are probably Xylan 1,4-beta-xylosidases.", "domain_architectures": 2, "interpro_id": "IPR045515", "known_evidence_count": null, "matches": 544, "name": "Family of unknown function (DUF6440)", "partial_evidence_count": null, "pfam_id": "PF20037", "proteins": 543, "proteomes": 494, "short_name": "DUF6440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20037", "structures": 0, "taxa": 924, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 513, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal integral membrane domain of a family of uncharacterised proteins from halophilic archaea that contain four domains. The proteins in this family are predominantly found in the class Halobacteria, which includes families such as Haloferacaceae, Natrialbaceae, and Haloarculaceae. These proteins are typically around 400 amino acids in length. This domain contains three predicted transmembrane helices.", "domain_architectures": 4, "interpro_id": "IPR058480", "known_evidence_count": null, "matches": 543, "name": "Domain of unknown function (DUF8167) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26501", "proteins": 543, "proteomes": 247, "short_name": "DUF8167", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26501", "structures": 0, "taxa": 388, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 515, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the third domain from a family of uncharacterised proteins from halophilic archaea that contain four domains. The proteins in this family are predominantly found in the class Halobacteria, which includes families such as Haloferacaceae, Natrialbaceae, and Haloarculaceae. These proteins are typically around 400 amino acids in length. This domain adopts a five stranded beta barrel structure.", "domain_architectures": 6, "interpro_id": "IPR058604", "known_evidence_count": null, "matches": 543, "name": "Domain of unknown function (DUF8167) 3rd domain", "partial_evidence_count": null, "pfam_id": "PF26503", "proteins": 543, "proteomes": 243, "short_name": "DUF8167_3rd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26503", "structures": 0, "taxa": 372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of bacterial proteins of unknown function. The domain structure includes a four stranded beta sheet which has two conserved aspartates in a DXDXG motif close to a highly conserved histidine. These three residues may for the potential active site.", "domain_architectures": 2, "interpro_id": "IPR054191", "known_evidence_count": null, "matches": 542, "name": "Domain of unknown function (DUF6896)", "partial_evidence_count": null, "pfam_id": "PF21837", "proteins": 542, "proteomes": 494, "short_name": "DUF6896", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21837", "structures": 0, "taxa": 929, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly found in actinomycetes. This domain, which contains highly conserved W, D, G residues and a conserved motif FxHRHR, is predicted to form an antiparallel beta sheet and alpha helices. Bet_v_1 domains contain a hydrophobic ligand-binding pocket [[cite:PUB00053295]]. The specific function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR059454", "known_evidence_count": null, "matches": 542, "name": "Domain of unknown function (DUF8410)", "partial_evidence_count": null, "pfam_id": "PF28469", "proteins": 542, "proteomes": 519, "short_name": "DUF8410", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28469", "structures": 0, "taxa": 1024, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 445, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. This family represents an approximately 200 residue long globular alpha/beta domain. The domain contains a conserved Glutamic acid, Aspartic acid and Histidine residue that may contribute to an enzymatic active site.", "domain_architectures": 1, "interpro_id": "IPR058365", "known_evidence_count": null, "matches": 541, "name": "Domain of unknown function (DUF8052)", "partial_evidence_count": null, "pfam_id": "PF26226", "proteins": 541, "proteomes": 529, "short_name": "DUF8052", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26226", "structures": 0, "taxa": 1003, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001740) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the phthoxazolin biosynthetic gene cluster from Streptomyces avermitilis [[cite:PUB00098835]]. Shows some similarity to secretion system proteins.", "domain_architectures": 1, "interpro_id": "IPR045558", "known_evidence_count": null, "matches": 540, "name": "Domain of unknown function (DUF6317)", "partial_evidence_count": null, "pfam_id": "PF19840", "proteins": 540, "proteomes": 413, "short_name": "DUF6317", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19840", "structures": 0, "taxa": 548, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 502, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 112 and 212 amino acids in length. There is a single completely conserved residue G that may be functionally important.", "domain_architectures": 15, "interpro_id": "IPR022149", "known_evidence_count": null, "matches": 552, "name": "Protein of unknown function (DUF3681)", "partial_evidence_count": null, "pfam_id": "PF12442", "proteins": 539, "proteomes": 41, "short_name": "DUF3681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12442", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 446, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised domains that show similarities to members of the colipase superfamily/", "domain_architectures": 47, "interpro_id": "IPR055531", "known_evidence_count": null, "matches": 1494, "name": "Domain of unknown function (DUF7107)", "partial_evidence_count": null, "pfam_id": "PF23416", "proteins": 539, "proteomes": 112, "short_name": "DUF7107", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23416", "structures": 0, "taxa": 369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 389, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain contains is found in many copies in a variety of uncharacterised fly proteins. This domain has a Ly6/uPAR/alpha-neurotoxin-like domain structure.", "domain_architectures": 41, "interpro_id": "IPR008472", "known_evidence_count": null, "matches": 2881, "name": "Domain of unknown function (DUF753)", "partial_evidence_count": null, "pfam_id": "PF05444", "proteins": 538, "proteomes": 96, "short_name": "DUF753", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05444", "structures": 0, "taxa": 425, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a putative sugar-binding family.", "domain_architectures": 3, "interpro_id": "IPR024284", "known_evidence_count": null, "matches": 553, "name": "Protein of unknown function (DUF3826)", "partial_evidence_count": null, "pfam_id": "PF12875", "proteins": 538, "proteomes": 353, "short_name": "DUF3826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12875", "structures": 3, "taxa": 519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 328, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 210 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025063", "known_evidence_count": null, "matches": 537, "name": "Protein of unknown function (DUF4004)", "partial_evidence_count": null, "pfam_id": "PF13171", "proteins": 537, "proteomes": 531, "short_name": "DUF4004", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13171", "structures": 0, "taxa": 768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 301, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001011) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from the meridamycin biosynthetic gene cluster from Streptomyces sp. NRRL 30748 [[cite:PUB00099405]].", "domain_architectures": 2, "interpro_id": "IPR046052", "known_evidence_count": null, "matches": 537, "name": "Family of unknown function (DUF6010)", "partial_evidence_count": null, "pfam_id": "PF19473", "proteins": 537, "proteomes": 529, "short_name": "DUF6010", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19473", "structures": 0, "taxa": 908, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 296, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 179 and 218 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046231", "known_evidence_count": null, "matches": 537, "name": "Family of unknown function (DUF6264)", "partial_evidence_count": null, "pfam_id": "PF19779", "proteins": 537, "proteomes": 460, "short_name": "DUF6264", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19779", "structures": 0, "taxa": 543, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 357, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small N-terminal domain of approximately 40 residues found in bacterial signal transduction histidine kinases and diguanylate cyclases. The domain is composed of an alpha helix and beta hairpin. It is located N-terminal to PAS domains ([pfam:PF00989]) and ultimately HisKA ([pfam:PF00512]) and HATPase_c ([pfam:PF02518]) domains. This family is found in bacteria, predominantly Pseudomonadota and Bacteroidota. The function of this domain remains to be determined.", "domain_architectures": 136, "interpro_id": "IPR061816", "known_evidence_count": null, "matches": 537, "name": "Domain of unknown function (DUF8755)", "partial_evidence_count": null, "pfam_id": "PF30886", "proteins": 537, "proteomes": 527, "short_name": "DUF8755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30886", "structures": 0, "taxa": 993, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 327, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 7, "interpro_id": "IPR035255", "known_evidence_count": null, "matches": 536, "name": "Domain of unknown function (DUF5348)", "partial_evidence_count": null, "pfam_id": "PF17295", "proteins": 536, "proteomes": 368, "short_name": "DUF5348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17295", "structures": 1, "taxa": 709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001598) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the foxicins A-D biosynthetic gene cluster from Streptomyces diastatochromogenes [[cite:PUB00099472]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046295", "known_evidence_count": null, "matches": 536, "name": "Family of unknown function (DUF6332)", "partial_evidence_count": null, "pfam_id": "PF19857", "proteins": 536, "proteomes": 520, "short_name": "DUF6332", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19857", "structures": 0, "taxa": 563, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterized proteins found in bacteriophages. The function of this protein family is currently unknown. The family appears to be conserved across various phage species that infect Escherichia coli and related bacteria. The family includes members from Phage T2, T4 and T6. Members of this family are typically short proteins of around 60-67 amino acids in length. Bacteriophage T4 contains four proteins that belong to this family. The structure of these proteins is predicted to be composed of two alpha helices that pack together. Structure prediction suggests these proteins may homodimerise (iPTM=0.83).", "domain_architectures": 1, "interpro_id": "IPR055861", "known_evidence_count": null, "matches": 536, "name": "Family of unknown function (DUF7438)", "partial_evidence_count": null, "pfam_id": "PF24219", "proteins": 536, "proteomes": 185, "short_name": "DUF7438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24219", "structures": 0, "taxa": 414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 318, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 165 residues predicted to adopt an OB-fold. This family is found in bacteria, predominantly Actinomycetota, Pseudomonadota, and Bacteroidota. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061818", "known_evidence_count": null, "matches": 536, "name": "Domain of unknown function (DUF8757)", "partial_evidence_count": null, "pfam_id": "PF30888", "proteins": 536, "proteomes": 523, "short_name": "DUF8757", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30888", "structures": 0, "taxa": 1219, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 255, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001973) is described by MIBiG as an example of the following biosynthetic class, other (unspecified).", "domain_architectures": 2, "interpro_id": "IPR045998", "known_evidence_count": null, "matches": 541, "name": "Family of unknown function (DUF5954)", "partial_evidence_count": null, "pfam_id": "PF19379", "proteins": 535, "proteomes": 415, "short_name": "DUF5954", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19379", "structures": 0, "taxa": 468, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in Burkholderia.", "domain_architectures": 3, "interpro_id": "IPR021234", "known_evidence_count": null, "matches": 538, "name": "Protein of unknown function (DUF2827)", "partial_evidence_count": null, "pfam_id": "PF10933", "proteins": 534, "proteomes": 161, "short_name": "DUF2827", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10933", "structures": 0, "taxa": 280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Proteobacteria. Proteins in this family are typically between 76 and 94 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046685", "known_evidence_count": null, "matches": 534, "name": "Family of unknown function (DUF6555)", "partial_evidence_count": null, "pfam_id": "PF20192", "proteins": 534, "proteomes": 273, "short_name": "DUF6555", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20192", "structures": 0, "taxa": 298, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 361, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mostly found in bacteria and archea. Some members contain WD repeats.", "domain_architectures": 13, "interpro_id": "IPR043765", "known_evidence_count": null, "matches": 536, "name": "Family of unknown function (DUF5711)", "partial_evidence_count": null, "pfam_id": "PF18975", "proteins": 533, "proteomes": 524, "short_name": "DUF5711", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18975", "structures": 0, "taxa": 950, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 367, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found at the C-terminal of a group of uncharacterised sequences from bacteria and it is functionally uncharacterised. It may adopt a TPR fold.", "domain_architectures": 16, "interpro_id": "IPR045921", "known_evidence_count": null, "matches": 532, "name": "Domain of unknown function (DUF6340)", "partial_evidence_count": null, "pfam_id": "PF19867", "proteins": 532, "proteomes": 485, "short_name": "DUF6340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19867", "structures": 0, "taxa": 850, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 458, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Fungi. Proteins in this family are approximately 300 amino acids in length. There are some conserved motifs, HxFF, HPD and FHLLI.", "domain_architectures": 11, "interpro_id": "IPR046486", "known_evidence_count": null, "matches": 532, "name": "Family of unknown function (DUF6579)", "partial_evidence_count": null, "pfam_id": "PF20219", "proteins": 532, "proteomes": 340, "short_name": "DUF6579", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20219", "structures": 0, "taxa": 678, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria and eukaryotes and it is approximately 50 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR046478", "known_evidence_count": null, "matches": 618, "name": "Domain of unknown function (DUF6799)", "partial_evidence_count": null, "pfam_id": "PF20606", "proteins": 532, "proteomes": 269, "short_name": "DUF6799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20606", "structures": 0, "taxa": 392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 333, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "In most members this domain covers almost the whole sequence, but a few member-sequences also carry a TonB_C domain, PF03544. This domain has a lipocalin fold.", "domain_architectures": 7, "interpro_id": "IPR027991", "known_evidence_count": null, "matches": 535, "name": "Domain of unknown function (DUF4488)", "partial_evidence_count": null, "pfam_id": "PF14869", "proteins": 531, "proteomes": 473, "short_name": "DUF4488", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14869", "structures": 3, "taxa": 705, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length. Several proteins in this family are annotated as toxin-antitoxin system proteins.", "domain_architectures": 1, "interpro_id": "IPR045705", "known_evidence_count": null, "matches": 531, "name": "Family of unknown function (DUF6061)", "partial_evidence_count": null, "pfam_id": "PF19537", "proteins": 531, "proteomes": 202, "short_name": "DUF6061", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19537", "structures": 0, "taxa": 369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 343, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of around 115 residues in length which seem to be specific to Enterobacteria. The function of the family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009700", "known_evidence_count": null, "matches": 533, "name": "Protein of unknown function (DUF1283)", "partial_evidence_count": null, "pfam_id": "PF06932", "proteins": 530, "proteomes": 488, "short_name": "DUF1283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06932", "structures": 0, "taxa": 716, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 182 and 282 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR025320", "known_evidence_count": null, "matches": 530, "name": "Protein of unknown function (DUF4225)", "partial_evidence_count": null, "pfam_id": "PF13988", "proteins": 530, "proteomes": 294, "short_name": "DUF4225", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13988", "structures": 0, "taxa": 479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 352, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is primarily found in bacteria. Proteins in this family are integral membrane proteins that are approximately 50 amino acids in length. There is a C-terminal conserved APFIY sequence motif. This family may have distant partial similarity to [pfam:PF02694] suggesting this may be a transporter protein.", "domain_architectures": 3, "interpro_id": "IPR046031", "known_evidence_count": null, "matches": 530, "name": "Family of unknown function (DUF5989)", "partial_evidence_count": null, "pfam_id": "PF19451", "proteins": 530, "proteomes": 499, "short_name": "DUF5989", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19451", "structures": 0, "taxa": 1226, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 329, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in uncharacterised bacterial proteins. It is remotely related to the integrase core domain with a partly conserved active site architecture.", "domain_architectures": 16, "interpro_id": "IPR054216", "known_evidence_count": null, "matches": 530, "name": "Domain of unknown function (DUF6930)", "partial_evidence_count": null, "pfam_id": "PF22007", "proteins": 530, "proteomes": 510, "short_name": "DUF6930", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22007", "structures": 0, "taxa": 1235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 436, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into an alpha/beta structure that is topologically similar to BRSK1/2 KA1 domain ([pfam:PF21122]).", "domain_architectures": 24, "interpro_id": "IPR055572", "known_evidence_count": null, "matches": 539, "name": "Domain of unknown function (DUF7148)", "partial_evidence_count": null, "pfam_id": "PF23650", "proteins": 530, "proteomes": 389, "short_name": "DUF7148", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23650", "structures": 0, "taxa": 1087, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 2, "interpro_id": "IPR018725", "known_evidence_count": null, "matches": 530, "name": "Predicted secreted protein (DUF2259)", "partial_evidence_count": null, "pfam_id": "PF10016", "proteins": 529, "proteomes": 500, "short_name": "DUF2259", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10016", "structures": 0, "taxa": 764, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 425, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This immunoglobulin-like (Ig-like) domain is found in a group of uncharacterised plant proteins. It is usually found associated with [pfam:PF11817].", "domain_architectures": 20, "interpro_id": "IPR059431", "known_evidence_count": null, "matches": 531, "name": "Domain of unknown function (DUF8387)", "partial_evidence_count": null, "pfam_id": "PF28382", "proteins": 529, "proteomes": 357, "short_name": "DUF8387", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28382", "structures": 0, "taxa": 986, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 370, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins includes the Phage Mu releasin protein which is important in the phage lysis process [[cite:PUB00101887]]. Structure predictions suggest that this protein might form a homomeric coiled-coil.", "domain_architectures": 1, "interpro_id": "IPR020269", "known_evidence_count": null, "matches": 528, "name": "Phage Mu-like releasin family", "partial_evidence_count": null, "pfam_id": "PF10805", "proteins": 528, "proteomes": 466, "short_name": "DUF2730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10805", "structures": 0, "taxa": 1021, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 341, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 102 and 118 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046508", "known_evidence_count": null, "matches": 528, "name": "Family of unknown function (DUF6686)", "partial_evidence_count": null, "pfam_id": "PF20391", "proteins": 528, "proteomes": 499, "short_name": "DUF6686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20391", "structures": 0, "taxa": 741, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 443, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in fungi, and is approximately 130 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR046624", "known_evidence_count": null, "matches": 546, "name": "Family of unknown function (DUF6736)", "partial_evidence_count": null, "pfam_id": "PF20521", "proteins": 527, "proteomes": 273, "short_name": "DUF6736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20521", "structures": 0, "taxa": 538, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 309, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021436", "known_evidence_count": null, "matches": 526, "name": "Protein of unknown function (DUF3085)", "partial_evidence_count": null, "pfam_id": "PF11284", "proteins": 526, "proteomes": 439, "short_name": "DUF3085", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11284", "structures": 0, "taxa": 812, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046162", "known_evidence_count": null, "matches": 526, "name": "Family of unknown function (DUF6164)", "partial_evidence_count": null, "pfam_id": "PF19661", "proteins": 526, "proteomes": 524, "short_name": "DUF6164", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19661", "structures": 0, "taxa": 731, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 483, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. They may be part of toxin/antitoxin system.", "domain_architectures": 2, "interpro_id": "IPR055979", "known_evidence_count": null, "matches": 526, "name": "Family of unknown function (DUF7557)", "partial_evidence_count": null, "pfam_id": "PF24434", "proteins": 526, "proteomes": 319, "short_name": "DUF7557", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24434", "structures": 0, "taxa": 588, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 168 and 208 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046609", "known_evidence_count": null, "matches": 525, "name": "Family of unknown function (DUF6668)", "partial_evidence_count": null, "pfam_id": "PF20373", "proteins": 525, "proteomes": 464, "short_name": "DUF6668", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20373", "structures": 0, "taxa": 646, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 242, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised and are predicted to adopt an all-beta fold [[cite:PUB00034476]]. They are often found in gene neighborhoods containing genes for an NlpC peptidase and a Ubiquitin domain predicted to be involved in tail assembly [[cite:PUB00034476]].", "domain_architectures": 7, "interpro_id": "IPR014974", "known_evidence_count": null, "matches": 524, "name": "Domain of unknown function (DUF1833)", "partial_evidence_count": null, "pfam_id": "PF08875", "proteins": 524, "proteomes": 456, "short_name": "DUF1833", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08875", "structures": 0, "taxa": 993, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 327, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 7, "interpro_id": "IPR019260", "known_evidence_count": null, "matches": 524, "name": "Uncharacterized protein conserved in bacteria (DUF2262)", "partial_evidence_count": null, "pfam_id": "PF10020", "proteins": 524, "proteomes": 418, "short_name": "DUF2262", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10020", "structures": 0, "taxa": 926, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 437, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in eukaryotes, and is typically between 247 and 324 amino acids in length. The family is found in association with [pfam:PF00085].", "domain_architectures": 11, "interpro_id": "IPR031827", "known_evidence_count": null, "matches": 562, "name": "Domain of unknown function (DUF4746)", "partial_evidence_count": null, "pfam_id": "PF15928", "proteins": 524, "proteomes": 239, "short_name": "DUF4746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15928", "structures": 0, "taxa": 872, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 495, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal alpha helical domain of this family of proteins.", "domain_architectures": 6, "interpro_id": "IPR058674", "known_evidence_count": null, "matches": 524, "name": "Family of unknown function (DUF8054) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26236", "proteins": 524, "proteomes": 256, "short_name": "DUF8054_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26236", "structures": 0, "taxa": 400, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 338, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 80 amino acids in length. There is a single completely conserved residue E that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR022201", "known_evidence_count": null, "matches": 523, "name": "Protein of unknown function (DUF3726)", "partial_evidence_count": null, "pfam_id": "PF12525", "proteins": 523, "proteomes": 515, "short_name": "DUF3726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12525", "structures": 0, "taxa": 826, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 280, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of hypothetical lipoproteins around 210 residues of length and is mainly found in various Pseudomonas species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032248", "known_evidence_count": null, "matches": 523, "name": "Domain of unknown function (DUF4823)", "partial_evidence_count": null, "pfam_id": "PF16105", "proteins": 523, "proteomes": 506, "short_name": "DUF4823", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16105", "structures": 0, "taxa": 666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in a number of prokaryotic proteins. It is mostly found fused with the N-terminal domain [pfam:PF04256]. This C-terminal domain is suggested to be a PIN like domain [[cite:PUB00091006]].", "domain_architectures": 3, "interpro_id": "IPR041652", "known_evidence_count": null, "matches": 524, "name": "Domain of unknown function (DUF5616)", "partial_evidence_count": null, "pfam_id": "PF18481", "proteins": 523, "proteomes": 518, "short_name": "DUF5616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18481", "structures": 0, "taxa": 981, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 303, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised, but The C-terminus appears to be related to methyltransferases. This family of proteins is found in bacteria. Proteins in this family are typically between 362 and 396 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046076", "known_evidence_count": null, "matches": 522, "name": "Uncharacterised methyltransferase family (DUF6094)", "partial_evidence_count": null, "pfam_id": "PF19587", "proteins": 522, "proteomes": 437, "short_name": "DUF6094", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19587", "structures": 0, "taxa": 936, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in uncharacterised proteins from bacteria, as well as in some plasmid pRiA4b ORF-3 family of proteins.", "domain_architectures": 15, "interpro_id": "IPR055733", "known_evidence_count": null, "matches": 522, "name": "Domain of unknown function (DUF7309)", "partial_evidence_count": null, "pfam_id": "PF23988", "proteins": 522, "proteomes": 497, "short_name": "DUF7309", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23988", "structures": 0, "taxa": 1173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 351, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This archaeal family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR024508", "known_evidence_count": null, "matches": 522, "name": "Protein of unknown function (DUF3226)", "partial_evidence_count": null, "pfam_id": "PF11536", "proteins": 521, "proteomes": 428, "short_name": "DUF3226", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11536", "structures": 1, "taxa": 1169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 433, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised fungal proteins. It is predicted to adopt a globular alpha-helical structure.", "domain_architectures": 7, "interpro_id": "IPR055567", "known_evidence_count": null, "matches": 522, "name": "Domain of unknown function (DUF7143)", "partial_evidence_count": null, "pfam_id": "PF23631", "proteins": 521, "proteomes": 407, "short_name": "DUF7143", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23631", "structures": 0, "taxa": 865, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 304, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria. The function is not known but many of the members are annotated as protein YgdB.", "domain_architectures": 2, "interpro_id": "IPR019652", "known_evidence_count": null, "matches": 520, "name": "Protein of unknown function (DUF2509)", "partial_evidence_count": null, "pfam_id": "PF10713", "proteins": 520, "proteomes": 506, "short_name": "DUF2509", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10713", "structures": 0, "taxa": 701, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 445, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 209 and 353 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR031983", "known_evidence_count": null, "matches": 539, "name": "Domain of unknown function (DUF4786)", "partial_evidence_count": null, "pfam_id": "PF16027", "proteins": 519, "proteomes": 241, "short_name": "DUF4786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16027", "structures": 0, "taxa": 907, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 324, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Enterobacterial sequences of around 200 residues in length which are often known as YiiQ proteins. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009918", "known_evidence_count": null, "matches": 521, "name": "Protein of unknown function (DUF1454)", "partial_evidence_count": null, "pfam_id": "PF07305", "proteins": 518, "proteomes": 514, "short_name": "DUF1454", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07305", "structures": 0, "taxa": 737, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 386, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in some vertebrates. This family includes human protein C11orf80.", "domain_architectures": 15, "interpro_id": "IPR028040", "known_evidence_count": null, "matches": 577, "name": "Domain of unknown function (DUF4554)", "partial_evidence_count": null, "pfam_id": "PF15091", "proteins": 518, "proteomes": 287, "short_name": "DUF4554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15091", "structures": 0, "taxa": 1033, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised bacterial proteins. These proteins are highly hydrophobic and contain a conserved DxxxY sequence motif. Some proteins have a sequence similarity to members of the Glycosyl transferase GT-C superfamily and are predicted to fold into similar structures, suggesting they may be glycosyltransferases.", "domain_architectures": 4, "interpro_id": "IPR058514", "known_evidence_count": null, "matches": 523, "name": "Domain of unknown function (DUF8201)", "partial_evidence_count": null, "pfam_id": "PF26626", "proteins": 518, "proteomes": 464, "short_name": "DUF8201", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26626", "structures": 0, "taxa": 833, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021370", "known_evidence_count": null, "matches": 517, "name": "Protein of unknown function (DUF2987)", "partial_evidence_count": null, "pfam_id": "PF11205", "proteins": 517, "proteomes": 506, "short_name": "DUF2987", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11205", "structures": 0, "taxa": 686, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in bacteria. This region is formed of a slightly irregular alpha solenoid related to HEAT repeats.", "domain_architectures": 11, "interpro_id": "IPR043782", "known_evidence_count": null, "matches": 544, "name": "Family of unknown function (DUF5724)", "partial_evidence_count": null, "pfam_id": "PF18991", "proteins": 517, "proteomes": 479, "short_name": "DUF5724", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18991", "structures": 0, "taxa": 868, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 326, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 187 and 238 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025522", "known_evidence_count": null, "matches": 515, "name": "Domain of unknown function (DUF4410)", "partial_evidence_count": null, "pfam_id": "PF14366", "proteins": 515, "proteomes": 403, "short_name": "DUF4410", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14366", "structures": 0, "taxa": 757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This eukaryotic family of proteins are annotated as ycf68 but have no known function.", "domain_architectures": 10, "interpro_id": "IPR022546", "known_evidence_count": null, "matches": 516, "name": "Protein of unknown function (DUF2647)", "partial_evidence_count": null, "pfam_id": "PF10839", "proteins": 514, "proteomes": 139, "short_name": "DUF2647", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10839", "structures": 0, "taxa": 632, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 475, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt a mainly alpha-helical structure.", "domain_architectures": 2, "interpro_id": "IPR055941", "known_evidence_count": null, "matches": 513, "name": "Family of unknown function (DUF7519)", "partial_evidence_count": null, "pfam_id": "PF24363", "proteins": 513, "proteomes": 227, "short_name": "DUF7519", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24363", "structures": 0, "taxa": 366, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 338, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 73 and 86 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025342", "known_evidence_count": null, "matches": 512, "name": "Domain of unknown function (DUF4248)", "partial_evidence_count": null, "pfam_id": "PF14053", "proteins": 512, "proteomes": 132, "short_name": "DUF4248", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14053", "structures": 0, "taxa": 215, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 368, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in Proteobacteria and Bacteroidetes. Proteins in this family are typically between 215 and 242 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR045708", "known_evidence_count": null, "matches": 512, "name": "Family of unknown function (DUF6064)", "partial_evidence_count": null, "pfam_id": "PF19540", "proteins": 512, "proteomes": 489, "short_name": "DUF6064", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19540", "structures": 0, "taxa": 977, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 361, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 170 amino acids in length and adopt a bacterial PH-like domain that has two transmembrane alpha helices inserted between the first and second strands of the PH domain. This protein is distantly related to [pfam:PF14256].", "domain_architectures": 1, "interpro_id": "IPR046088", "known_evidence_count": null, "matches": 512, "name": "Bacterial PH-like domain (DUF6106)", "partial_evidence_count": null, "pfam_id": "PF19601", "proteins": 512, "proteomes": 454, "short_name": "DUF6106", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19601", "structures": 0, "taxa": 785, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 327, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of proteins, which are typically between 100 and 122 amino acids in length. This protein is often found to be plasmid borne and in a few cases is associated with ParBc domains that are critical for plasmid segregation. This suggests that this domain may play a role in chromosome segregation or plasmid partitioning. Structural modelling suggests this domain will form a homodimeric complex.", "domain_architectures": 4, "interpro_id": "IPR056090", "known_evidence_count": null, "matches": 513, "name": "Family of unknown function (DUF7673)", "partial_evidence_count": null, "pfam_id": "PF24720", "proteins": 512, "proteomes": 421, "short_name": "DUF7673", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24720", "structures": 0, "taxa": 769, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 385, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "", "domain_architectures": 3, "interpro_id": "IPR007368", "known_evidence_count": null, "matches": 510, "name": "Protein of unknown function (DUF434)", "partial_evidence_count": null, "pfam_id": "PF04256", "proteins": 510, "proteomes": 508, "short_name": "DUF434", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04256", "structures": 0, "taxa": 946, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 12, "interpro_id": "IPR018746", "known_evidence_count": null, "matches": 558, "name": "Uncharacterized membrane protein (DUF2298)", "partial_evidence_count": null, "pfam_id": "PF10060", "proteins": 509, "proteomes": 369, "short_name": "DUF2298", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10060", "structures": 0, "taxa": 766, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as YchH however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR019698", "known_evidence_count": null, "matches": 509, "name": "Protein of unknown function (DUF2583)", "partial_evidence_count": null, "pfam_id": "PF10762", "proteins": 509, "proteomes": 508, "short_name": "DUF2583", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10762", "structures": 0, "taxa": 700, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 311, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021334", "known_evidence_count": null, "matches": 509, "name": "Protein of unknown function (DUF2947)", "partial_evidence_count": null, "pfam_id": "PF11163", "proteins": 509, "proteomes": 502, "short_name": "DUF2947", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11163", "structures": 0, "taxa": 716, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 426, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It contains the so-called HeH motif (helix-extended loop-helix). This motif is known to engage in protein-protein and/or nucleic acid interactions. Some proteins contain two copies of this domain.", "domain_architectures": 7, "interpro_id": "IPR056689", "known_evidence_count": null, "matches": 510, "name": "Domain of unknown function (DUF7787)", "partial_evidence_count": null, "pfam_id": "PF25042", "proteins": 508, "proteomes": 300, "short_name": "DUF7787", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25042", "structures": 0, "taxa": 833, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 408, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised plant proteins. They are predicted to adopt a helical hairpin structure.", "domain_architectures": 15, "interpro_id": "IPR057197", "known_evidence_count": null, "matches": 514, "name": "Domain of unknown function (DUF7875)", "partial_evidence_count": null, "pfam_id": "PF25285", "proteins": 508, "proteomes": 327, "short_name": "DUF7875", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25285", "structures": 0, "taxa": 915, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 308, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "", "domain_architectures": 35, "interpro_id": "IPR005048", "known_evidence_count": null, "matches": 509, "name": "Drosophila protein of unknown function, DUF287", "partial_evidence_count": null, "pfam_id": "PF03384", "proteins": 506, "proteomes": 24, "short_name": "DUF287", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03384", "structures": 2, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The sequences making up this family are derived from various hypothetical phage and prophage proteins. The region in question is approximately 140 amino acids long.", "domain_architectures": 6, "interpro_id": "IPR012865", "known_evidence_count": null, "matches": 506, "name": "Protein of unknown function (DUF1642)", "partial_evidence_count": null, "pfam_id": "PF07852", "proteins": 506, "proteomes": 385, "short_name": "DUF1642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07852", "structures": 0, "taxa": 835, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in a set of bacterial proteins, including Cytochrome c-type protein. It is functionally uncharacterised.", "domain_architectures": 3, "interpro_id": "IPR015170", "known_evidence_count": null, "matches": 506, "name": "Domain of unknown function (DUF1924)", "partial_evidence_count": null, "pfam_id": "PF09086", "proteins": 506, "proteomes": 483, "short_name": "DUF1924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09086", "structures": 7, "taxa": 891, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 419, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata. Family members carry a zinc finger family on the N-terminal [pfam:PF15663].", "domain_architectures": 10, "interpro_id": "IPR040943", "known_evidence_count": null, "matches": 656, "name": "Family of unknown function (DUF5571)", "partial_evidence_count": null, "pfam_id": "PF17732", "proteins": 506, "proteomes": 245, "short_name": "DUF5571", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17732", "structures": 0, "taxa": 830, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 474, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Archaeal protein of unknown function.", "domain_architectures": 3, "interpro_id": "IPR007408", "known_evidence_count": null, "matches": 505, "name": "Protein of unknown function (DUF460)", "partial_evidence_count": null, "pfam_id": "PF04312", "proteins": 505, "proteomes": 505, "short_name": "DUF460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04312", "structures": 0, "taxa": 906, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 2, "interpro_id": "IPR021238", "known_evidence_count": null, "matches": 505, "name": "Protein of unknown function DUF2620", "partial_evidence_count": null, "pfam_id": "PF10941", "proteins": 505, "proteomes": 489, "short_name": "DUF2620", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10941", "structures": 0, "taxa": 845, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 289, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. The conserved hypothetical protein VC1805 from Vibrio cholerae belongs to this group. It adopts a monomeric assembly, showing an unusual topology with a flat seven-stranded anti-parallel beta-sheet and two helices located on the same side of the sheet. It has some structural homology with the human protein p32 and binds to the complement protein C1q, which suggests a possible role in the adherence of the bacteria to the intestinal wall [[cite:PUB00049533]].", "domain_architectures": 1, "interpro_id": "IPR021248", "known_evidence_count": null, "matches": 505, "name": "Protein of unknown function (DUF2787)", "partial_evidence_count": null, "pfam_id": "PF10980", "proteins": 505, "proteomes": 259, "short_name": "DUF2787", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10980", "structures": 2, "taxa": 433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, and is approximately 470 amino acids in length. This domain may consist of TPRs.", "domain_architectures": 9, "interpro_id": "IPR045472", "known_evidence_count": null, "matches": 507, "name": "Domain of unknown function (DUF6493)", "partial_evidence_count": null, "pfam_id": "PF20103", "proteins": 505, "proteomes": 388, "short_name": "DUF6493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20103", "structures": 0, "taxa": 635, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 293, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 85 residues predicted to adopt an OB-fold. This family is found in bacteria, predominantly Actinomycetota, Pseudomonadota, and Bacteroidota. The function of this domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061819", "known_evidence_count": null, "matches": 505, "name": "Domain of unknown function (DUF8758)", "partial_evidence_count": null, "pfam_id": "PF30889", "proteins": 505, "proteomes": 493, "short_name": "DUF8758", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30889", "structures": 0, "taxa": 1158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 373 and 763 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR031440", "known_evidence_count": null, "matches": 523, "name": "Domain of unknown function (DUF4670)", "partial_evidence_count": null, "pfam_id": "PF15709", "proteins": 504, "proteomes": 300, "short_name": "DUF4670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15709", "structures": 0, "taxa": 1150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 391, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 110 amino acids in length. There is a conserved QQL sequence motif.", "domain_architectures": 4, "interpro_id": "IPR031651", "known_evidence_count": null, "matches": 511, "name": "Domain of unknown function (DUF4709)", "partial_evidence_count": null, "pfam_id": "PF15821", "proteins": 504, "proteomes": 283, "short_name": "DUF4709", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15821", "structures": 0, "taxa": 1149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 359, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 450 residues in length and is mainly found in various Corynebacterium species. Several proteins are predicted as galactose-1-phosphate uridylytransferases. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032576", "known_evidence_count": null, "matches": 505, "name": "Domain of unknown function (DUF4921)", "partial_evidence_count": null, "pfam_id": "PF16268", "proteins": 504, "proteomes": 499, "short_name": "DUF4921", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16268", "structures": 0, "taxa": 918, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 289, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They share significant sequence similarity with PvuII endonucleases and are predicted to adopt similar structure. The predicted structures, however, do not suggest similarity in the active site architecture.", "domain_architectures": 5, "interpro_id": "IPR054267", "known_evidence_count": null, "matches": 509, "name": "Family of unknown function (DUF6998)", "partial_evidence_count": null, "pfam_id": "PF22522", "proteins": 504, "proteomes": 486, "short_name": "DUF6998", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22522", "structures": 2, "taxa": 1108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 313, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021432", "known_evidence_count": null, "matches": 503, "name": "Protein of unknown function (DUF3081)", "partial_evidence_count": null, "pfam_id": "PF11280", "proteins": 503, "proteomes": 495, "short_name": "DUF3081", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11280", "structures": 0, "taxa": 644, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 322, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 292 and 338 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR046733", "known_evidence_count": null, "matches": 505, "name": "Family of unknown function (DUF6625)", "partial_evidence_count": null, "pfam_id": "PF20330", "proteins": 503, "proteomes": 409, "short_name": "DUF6625", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20330", "structures": 0, "taxa": 908, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 220, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from Dictyostelia. It is predicted to adopt Ig-like fold with the fibronectin type III-like topology.", "domain_architectures": 82, "interpro_id": "IPR055463", "known_evidence_count": null, "matches": 523, "name": "Domain of unknown function (DUF7035)", "partial_evidence_count": null, "pfam_id": "PF23034", "proteins": 503, "proteomes": 16, "short_name": "DUF7035", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23034", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 365, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 277 and 315 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR046157", "known_evidence_count": null, "matches": 502, "name": "Family of unknown function (DUF6159)", "partial_evidence_count": null, "pfam_id": "PF19656", "proteins": 502, "proteomes": 480, "short_name": "DUF6159", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19656", "structures": 0, "taxa": 951, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 481, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of small proteins mainly from Halobacteria. It contains highly conserved cysteine residues arranged in two CxxC motifs that likely coordinate zinc. The first motif could be more broadly defined as YECxxCG. This domain is predicted to adopt zinc ribbon fold.", "domain_architectures": 2, "interpro_id": "IPR055553", "known_evidence_count": null, "matches": 502, "name": "Domain of unknown function (DUF7129)", "partial_evidence_count": null, "pfam_id": "PF23455", "proteins": 502, "proteomes": 235, "short_name": "DUF7129", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23455", "structures": 0, "taxa": 370, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 281, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in bacterial proteins. Some of the members of this family might contain an EF-hand calcium binding site. The predicted structure of this domain consists of three beta sheets.", "domain_architectures": 80, "interpro_id": "IPR055575", "known_evidence_count": null, "matches": 961, "name": "Domain of unknown function (DUF7151)", "partial_evidence_count": null, "pfam_id": "PF23657", "proteins": 502, "proteomes": 371, "short_name": "DUF7151", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23657", "structures": 0, "taxa": 675, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 474, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in the Archaea. The domain is predominantly found in members of the Methanobacteriota phylum, specifically within the Halobacteria class. Proteins containing this domain are typically integral membrane proteins with two transmembrane helices. The domain is approximately 60-70 amino acids in length. This domain is sometimes associated with [pfam:PF09997].", "domain_architectures": 3, "interpro_id": "IPR059312", "known_evidence_count": null, "matches": 501, "name": "Domain of unknown function (DUF8268)", "partial_evidence_count": null, "pfam_id": "PF26799", "proteins": 501, "proteomes": 286, "short_name": "DUF8268", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26799", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 302, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry rerpesents uncharacterised proteins found mainly in Cyanobacteria. They contain a ribbon-helix-helix (RHH) motif and may interact with DNA.", "domain_architectures": 3, "interpro_id": "IPR061839", "known_evidence_count": null, "matches": 501, "name": "Family of unknown function (DUF8778)", "partial_evidence_count": null, "pfam_id": "PF31038", "proteins": 501, "proteomes": 439, "short_name": "DUF8778", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31038", "structures": 0, "taxa": 1017, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 314, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 110 residues found in Type IIG restriction-modification enzymes in bacteria. This domain is located C-terminal to the TaqI_C domain ([pfam:PF12950]). The function of this domain remains to be determined.", "domain_architectures": 14, "interpro_id": "IPR061871", "known_evidence_count": null, "matches": 501, "name": "Domain of unknown function (DUF8810)", "partial_evidence_count": null, "pfam_id": "PF31106", "proteins": 501, "proteomes": 440, "short_name": "DUF8810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31106", "structures": 0, "taxa": 995, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 321, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unkown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021482", "known_evidence_count": null, "matches": 500, "name": "Protein of unknown function (DUF3135)", "partial_evidence_count": null, "pfam_id": "PF11333", "proteins": 500, "proteomes": 485, "short_name": "DUF3135", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11333", "structures": 0, "taxa": 796, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 400, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 254 and 462 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR028004", "known_evidence_count": null, "matches": 508, "name": "Domain of unknown function (DUF4643)", "partial_evidence_count": null, "pfam_id": "PF15485", "proteins": 500, "proteomes": 377, "short_name": "DUF4643", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15485", "structures": 0, "taxa": 1342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 416, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It has sequence similarity to PB1 domain and it is predicted to adopt similar structure with typical ubiquitin-like topology.", "domain_architectures": 9, "interpro_id": "IPR055562", "known_evidence_count": null, "matches": 506, "name": "Domain of unknown function (DUF7138)", "partial_evidence_count": null, "pfam_id": "PF23596", "proteins": 500, "proteomes": 283, "short_name": "DUF7138", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23596", "structures": 0, "taxa": 859, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 311, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 310 residues in length. Members of this family seem to be found exclusively in Agrobacterium, Rhizobium and Brucella species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009842", "known_evidence_count": null, "matches": 499, "name": "Protein of unknown function (DUF1402)", "partial_evidence_count": null, "pfam_id": "PF07182", "proteins": 499, "proteomes": 457, "short_name": "DUF1402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07182", "structures": 0, "taxa": 616, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of paralogous proteins in Leptospira interrogans. Several (e.g. [swissprot:Q8F4V2]) have been annotated as possible CopG-like transcriptional regulators (see [pfam:PF01402]).", "domain_architectures": 2, "interpro_id": "IPR011458", "known_evidence_count": null, "matches": 500, "name": "Protein of unknown function (DUF1564)", "partial_evidence_count": null, "pfam_id": "PF07600", "proteins": 499, "proteomes": 47, "short_name": "DUF1564", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07600", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 312, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021435", "known_evidence_count": null, "matches": 499, "name": "Protein of unknown function (DUF3084)", "partial_evidence_count": null, "pfam_id": "PF11283", "proteins": 499, "proteomes": 494, "short_name": "DUF3084", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11283", "structures": 0, "taxa": 1127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 389, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It contains two pairs of conserved cysteines that may be involved in metal coordination. It is predicted to adopt a structure typical for zinc ribbon domains.", "domain_architectures": 9, "interpro_id": "IPR056717", "known_evidence_count": null, "matches": 500, "name": "Domain of unknown function (DUF7815)", "partial_evidence_count": null, "pfam_id": "PF25122", "proteins": 499, "proteomes": 323, "short_name": "DUF7815", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25122", "structures": 0, "taxa": 897, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 448, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in a group of uncharacterised archaeal proteins. It is predicted to adopt an all-beta structure.", "domain_architectures": 27, "interpro_id": "IPR057149", "known_evidence_count": null, "matches": 538, "name": "Domain of unknown function (DUF7827)", "partial_evidence_count": null, "pfam_id": "PF25162", "proteins": 499, "proteomes": 223, "short_name": "DUF7827", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25162", "structures": 0, "taxa": 356, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 340, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain has no known function.", "domain_architectures": 1, "interpro_id": "IPR014959", "known_evidence_count": null, "matches": 498, "name": "Domain of unknown function (DUF1827)", "partial_evidence_count": null, "pfam_id": "PF08860", "proteins": 498, "proteomes": 405, "short_name": "DUF1827", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08860", "structures": 1, "taxa": 601, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 190 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046160", "known_evidence_count": null, "matches": 499, "name": "Family of unknown function (DUF6162)", "partial_evidence_count": null, "pfam_id": "PF19659", "proteins": 498, "proteomes": 477, "short_name": "DUF6162", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19659", "structures": 0, "taxa": 641, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 88 and 99 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR045389", "known_evidence_count": null, "matches": 498, "name": "Family of unknown function (DUF6522)", "partial_evidence_count": null, "pfam_id": "PF20132", "proteins": 498, "proteomes": 418, "short_name": "DUF6522", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20132", "structures": 0, "taxa": 670, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0002011) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the ansacarbamitocin A biosynthetic gene cluster from Amycolatopsis alba DSM 44262. This family appears to be predominantly found in bacteria.", "domain_architectures": 5, "interpro_id": "IPR045929", "known_evidence_count": null, "matches": 497, "name": "Family of unknown function (DUF6348)", "partial_evidence_count": null, "pfam_id": "PF19875", "proteins": 497, "proteomes": 454, "short_name": "DUF6348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19875", "structures": 0, "taxa": 796, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 141 and 178 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045524", "known_evidence_count": null, "matches": 515, "name": "Domain of unknown function (DUF6473)", "partial_evidence_count": null, "pfam_id": "PF20078", "proteins": 497, "proteomes": 486, "short_name": "DUF6473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20078", "structures": 0, "taxa": 757, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as lipoproteins however this cannot be confirmed.", "domain_architectures": 1, "interpro_id": "IPR021372", "known_evidence_count": null, "matches": 496, "name": "Protein of unknown function (DUF2989)", "partial_evidence_count": null, "pfam_id": "PF11207", "proteins": 496, "proteomes": 491, "short_name": "DUF2989", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11207", "structures": 0, "taxa": 625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 315, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 71 and 82 amino acids in length. There are two conserved sequence motifs: KKY and YQK.", "domain_architectures": 1, "interpro_id": "IPR046290", "known_evidence_count": null, "matches": 496, "name": "Family of unknown function (DUF6327)", "partial_evidence_count": null, "pfam_id": "PF19852", "proteins": 496, "proteomes": 474, "short_name": "DUF6327", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19852", "structures": 0, "taxa": 581, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 332, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 270 residues in length and is mainly found in various Bacillus cereus species. Some members of this family are annotated as Galactose-1-phosphate uridylyltransferases, but the specific function of this family is unknown.", "domain_architectures": 5, "interpro_id": "IPR046322", "known_evidence_count": null, "matches": 495, "name": "Domain of unknown function (DUF4931) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF16285", "proteins": 495, "proteomes": 475, "short_name": "DUF4931_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16285", "structures": 1, "taxa": 768, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 418, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in bacteria and viruses, and is approximately 90 amino acids in length. The family is found in association with [pfam:PF02498].", "domain_architectures": 14, "interpro_id": "IPR022549", "known_evidence_count": null, "matches": 497, "name": "Protein of unknown function (DUF3627)", "partial_evidence_count": null, "pfam_id": "PF12299", "proteins": 494, "proteomes": 131, "short_name": "DUF3627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12299", "structures": 0, "taxa": 408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000376) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular JBIR-34 biosynthetic gene cluster from Streptomyces sp. Sp080513GE-23 [[cite:PUB00099434]]. This family appears to be predominantly found in actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR046266", "known_evidence_count": null, "matches": 499, "name": "Family of unknown function (DUF6299)", "partial_evidence_count": null, "pfam_id": "PF19816", "proteins": 494, "proteomes": 481, "short_name": "DUF6299", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19816", "structures": 0, "taxa": 556, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 350, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 87 and 141 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045422", "known_evidence_count": null, "matches": 494, "name": "Family of unknown function (DUF6511)", "partial_evidence_count": null, "pfam_id": "PF20121", "proteins": 494, "proteomes": 342, "short_name": "DUF6511", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20121", "structures": 0, "taxa": 718, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from Dictyostelia. It is predicted to adopt Ig-like fold with the fibronectin type III-like topology.", "domain_architectures": 84, "interpro_id": "IPR055462", "known_evidence_count": null, "matches": 512, "name": "Domain of unknown function (DUF7034)", "partial_evidence_count": null, "pfam_id": "PF23033", "proteins": 494, "proteomes": 9, "short_name": "DUF7034", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23033", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 471, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a small family of uncharacterised archaeal proteins. They are predicted to fold into a helical hairpin.", "domain_architectures": 2, "interpro_id": "IPR055975", "known_evidence_count": null, "matches": 494, "name": "Family of unknown function (DUF7553)", "partial_evidence_count": null, "pfam_id": "PF24430", "proteins": 494, "proteomes": 260, "short_name": "DUF7553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24430", "structures": 0, "taxa": 455, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 410, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 8, "interpro_id": "IPR018852", "known_evidence_count": null, "matches": 491, "name": "Protein of unknown function (DUF2456)", "partial_evidence_count": null, "pfam_id": "PF10445", "proteins": 491, "proteomes": 454, "short_name": "DUF2456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10445", "structures": 0, "taxa": 917, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 254, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021452", "known_evidence_count": null, "matches": 491, "name": "Protein of unknown function (DUF3103)", "partial_evidence_count": null, "pfam_id": "PF11301", "proteins": 491, "proteomes": 468, "short_name": "DUF3103", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11301", "structures": 0, "taxa": 703, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 396, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharcaterised metazoan proteins. It shares similarity with Tetraspannin-like four transmembrane helical domains.", "domain_architectures": 7, "interpro_id": "IPR061851", "known_evidence_count": null, "matches": 501, "name": "Domain of unknown function (DUF8790)", "partial_evidence_count": null, "pfam_id": "PF31051", "proteins": 491, "proteomes": 307, "short_name": "DUF8790", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31051", "structures": 0, "taxa": 1211, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021634", "known_evidence_count": null, "matches": 490, "name": "Protein of unknown function (DUF3240)", "partial_evidence_count": null, "pfam_id": "PF11582", "proteins": 490, "proteomes": 477, "short_name": "DUF3240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11582", "structures": 1, "taxa": 864, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 457, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins. They share a semi-conserved YDxxNPXAW sequence motif.", "domain_architectures": 1, "interpro_id": "IPR055755", "known_evidence_count": null, "matches": 490, "name": "Family of unknown function (DUF7331)", "partial_evidence_count": null, "pfam_id": "PF24018", "proteins": 490, "proteomes": 266, "short_name": "DUF7331", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24018", "structures": 0, "taxa": 436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 243, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR021559", "known_evidence_count": null, "matches": 489, "name": "Protein of unknown function (DUF3019)", "partial_evidence_count": null, "pfam_id": "PF11456", "proteins": 489, "proteomes": 284, "short_name": "DUF3019", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11456", "structures": 0, "taxa": 410, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 407, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 305 and 370 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR027958", "known_evidence_count": null, "matches": 542, "name": "Domain of unknown function (DUF4657)", "partial_evidence_count": null, "pfam_id": "PF15552", "proteins": 489, "proteomes": 270, "short_name": "DUF4657", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15552", "structures": 0, "taxa": 978, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 301, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 98 and 116 amino acids in length. There is a conserved KRER sequence motif.", "domain_architectures": 1, "interpro_id": "IPR046170", "known_evidence_count": null, "matches": 489, "name": "Family of unknown function (DUF6172)", "partial_evidence_count": null, "pfam_id": "PF19669", "proteins": 489, "proteomes": 471, "short_name": "DUF6172", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19669", "structures": 0, "taxa": 723, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 364, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into unusual alpha/beta structure composed of a four-stranded antiparallel beta-sheet capped with alpha-helices.", "domain_architectures": 4, "interpro_id": "IPR058524", "known_evidence_count": null, "matches": 494, "name": "Domain of unknown function (DUF8211)", "partial_evidence_count": null, "pfam_id": "PF26638", "proteins": 489, "proteomes": 6, "short_name": "DUF8211", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26638", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several uncharacterised proteins from Neisseria meningitidis. These proteins may have a role in DNA-binding.", "domain_architectures": 46, "interpro_id": "IPR007929", "known_evidence_count": null, "matches": 984, "name": "Protein of unknown function (DUF723)", "partial_evidence_count": null, "pfam_id": "PF05265", "proteins": 488, "proteomes": 415, "short_name": "DUF723", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05265", "structures": 0, "taxa": 1074, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 403, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein family is found in eukaryotes. Proteins in this family are typically between 166 and 538 amino acids in length.", "domain_architectures": 18, "interpro_id": "IPR028101", "known_evidence_count": null, "matches": 570, "name": "Domain of unknown function (DUF4616)", "partial_evidence_count": null, "pfam_id": "PF15394", "proteins": 488, "proteomes": 262, "short_name": "DUF4616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15394", "structures": 0, "taxa": 955, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein that adopts a beta-grasp fold.", "domain_architectures": 5, "interpro_id": "IPR049243", "known_evidence_count": null, "matches": 612, "name": "Family of unknown function (DUF6878)", "partial_evidence_count": null, "pfam_id": "PF21798", "proteins": 488, "proteomes": 343, "short_name": "DUF6878", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21798", "structures": 0, "taxa": 634, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the C-terminal of a group of uncharacterised sequences from bacteria. It may adopt a TPR-like fold. It is found associated with [pfam:PF20103] at the N-terminal and [pfam:PF25148] in the middle.", "domain_architectures": 8, "interpro_id": "IPR056727", "known_evidence_count": null, "matches": 488, "name": "Domain of unknown function (DUF7825)", "partial_evidence_count": null, "pfam_id": "PF25149", "proteins": 488, "proteomes": 383, "short_name": "DUF7825", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25149", "structures": 0, "taxa": 593, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 246, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 220 residues found in subtilisin-like serine peptidases in Actinomycetota. This domain is typically located C-terminal to the Peptidase_S8 catalytic domain ([pfam:PF00082]) and PA domain ([pfam:PF02225]). The function of this domain remains to be determined.", "domain_architectures": 32, "interpro_id": "IPR061872", "known_evidence_count": null, "matches": 488, "name": "Domain of unknown function (DUF8811)", "partial_evidence_count": null, "pfam_id": "PF31107", "proteins": 488, "proteomes": 443, "short_name": "DUF8811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31107", "structures": 0, "taxa": 730, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 93 and 146 amino acids in length. There is a conserved IRIV sequence motif.", "domain_architectures": 12, "interpro_id": "IPR025372", "known_evidence_count": null, "matches": 488, "name": "Domain of unknown function (DUF4362)", "partial_evidence_count": null, "pfam_id": "PF14275", "proteins": 487, "proteomes": 406, "short_name": "DUF4362", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14275", "structures": 0, "taxa": 578, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 121 and 153 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045467", "known_evidence_count": null, "matches": 520, "name": "Family of unknown function (DUF6497)", "partial_evidence_count": null, "pfam_id": "PF20107", "proteins": 487, "proteomes": 487, "short_name": "DUF6497", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20107", "structures": 0, "taxa": 684, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 45 and 78 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046615", "known_evidence_count": null, "matches": 487, "name": "Family of unknown function (DUF6728)", "partial_evidence_count": null, "pfam_id": "PF20498", "proteins": 487, "proteomes": 487, "short_name": "DUF6728", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20498", "structures": 0, "taxa": 678, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes.", "domain_architectures": 2, "interpro_id": "IPR021486", "known_evidence_count": null, "matches": 486, "name": "Protein of unknown function (DUF3139)", "partial_evidence_count": null, "pfam_id": "PF11337", "proteins": 486, "proteomes": 367, "short_name": "DUF3139", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11337", "structures": 0, "taxa": 561, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 279, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in proteobacteria and actinobacteria, and is approximately 240 amino acids in length. The family is found in association with [pfam:PF03435].", "domain_architectures": 4, "interpro_id": "IPR045982", "known_evidence_count": null, "matches": 486, "name": "Family of unknown function (DUF5938)", "partial_evidence_count": null, "pfam_id": "PF19362", "proteins": 486, "proteomes": 455, "short_name": "DUF5938", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19362", "structures": 0, "taxa": 703, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain of unknown function is found in uncharacterised proteins mainly from Proteobacteria, and is about 100 amino acids in length. It has the conserved sequences RxxRY and PLPPAxLPxWDG.", "domain_architectures": 10, "interpro_id": "IPR045653", "known_evidence_count": null, "matches": 488, "name": "Domain of unknown function (DUF6396)", "partial_evidence_count": null, "pfam_id": "PF19933", "proteins": 486, "proteomes": 219, "short_name": "DUF6396", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19933", "structures": 0, "taxa": 356, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 453, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eu- and prokaryotic proteins. It contains four invariant cysteines and it is predicted to adopt a Zn-ribbon fold.", "domain_architectures": 11, "interpro_id": "IPR055997", "known_evidence_count": null, "matches": 486, "name": "Domain of unknown function (DUF7575)", "partial_evidence_count": null, "pfam_id": "PF24460", "proteins": 486, "proteomes": 306, "short_name": "DUF7575", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24460", "structures": 0, "taxa": 576, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in metazoan proteins. It is predicted to fold into two meander beta-sheets that pack on each other.", "domain_architectures": 17, "interpro_id": "IPR061857", "known_evidence_count": null, "matches": 505, "name": "Domain of unknown function (DUF8796)", "partial_evidence_count": null, "pfam_id": "PF31062", "proteins": 486, "proteomes": 337, "short_name": "DUF8796", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31062", "structures": 0, "taxa": 1207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 9, "interpro_id": "IPR021610", "known_evidence_count": null, "matches": 494, "name": "Protein of unknown function (DUF3228)", "partial_evidence_count": null, "pfam_id": "PF11539", "proteins": 485, "proteomes": 448, "short_name": "DUF3228", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11539", "structures": 2, "taxa": 929, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 280, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 42 and 56 amino acids in length. There is a single completely conserved residue M that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025270", "known_evidence_count": null, "matches": 485, "name": "Protein of unknown function (DUF4044)", "partial_evidence_count": null, "pfam_id": "PF13253", "proteins": 485, "proteomes": 483, "short_name": "DUF4044", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13253", "structures": 0, "taxa": 660, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 308, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001707) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 3, "interpro_id": "IPR045990", "known_evidence_count": null, "matches": 491, "name": "Family of unknown function (DUF5946)", "partial_evidence_count": null, "pfam_id": "PF19371", "proteins": 485, "proteomes": 427, "short_name": "DUF5946", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19371", "structures": 0, "taxa": 844, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found at the C-terminus of proteins contains a [pfam:PF03235] domain at the N-terminus. This domain is composed of multiple alpha helices.", "domain_architectures": 4, "interpro_id": "IPR057156", "known_evidence_count": null, "matches": 484, "name": "Family of unknown function (DUF7834)", "partial_evidence_count": null, "pfam_id": "PF25202", "proteins": 484, "proteomes": 466, "short_name": "DUF7834", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25202", "structures": 0, "taxa": 988, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 406, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 128 and 299 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR029235", "known_evidence_count": null, "matches": 519, "name": "Domain of unknown function (DUF4619)", "partial_evidence_count": null, "pfam_id": "PF15398", "proteins": 483, "proteomes": 310, "short_name": "DUF4619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15398", "structures": 0, "taxa": 1197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain found in a variety of uncharacterised phage proteins.", "domain_architectures": 7, "interpro_id": "IPR055634", "known_evidence_count": null, "matches": 483, "name": "Domain of unknown function (DUF7210)", "partial_evidence_count": null, "pfam_id": "PF23843", "proteins": 483, "proteomes": 428, "short_name": "DUF7210", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23843", "structures": 0, "taxa": 964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 323, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of hypothetical proteins in Leptospira interrogans.", "domain_architectures": 1, "interpro_id": "IPR011468", "known_evidence_count": null, "matches": 482, "name": "Protein of unknown function (DUF1574)", "partial_evidence_count": null, "pfam_id": "PF07611", "proteins": 482, "proteomes": 181, "short_name": "DUF1574", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07611", "structures": 0, "taxa": 433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 395, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. There is a conserved HRYQNPW sequence motif. This family includes the human protein C4orf45.", "domain_architectures": 5, "interpro_id": "IPR027814", "known_evidence_count": null, "matches": 486, "name": "Domain of unknown function (DUF4562)", "partial_evidence_count": null, "pfam_id": "PF15123", "proteins": 482, "proteomes": 355, "short_name": "DUF4562", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15123", "structures": 4, "taxa": 1348, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 297, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 11, "interpro_id": "IPR031837", "known_evidence_count": null, "matches": 483, "name": "Domain of unknown function (DUF5071)", "partial_evidence_count": null, "pfam_id": "PF16804", "proteins": 482, "proteomes": 443, "short_name": "DUF5071", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16804", "structures": 3, "taxa": 874, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 357, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial domain with an unknown function. It folds into a Y-shaped alpha-helical structure, comprising an anti- parallel 4-helix bundle at the base and two helical arms [[cite:PUB00153915]].", "domain_architectures": 1, "interpro_id": "IPR007463", "known_evidence_count": null, "matches": 480, "name": "Protein of unknown function (DUF507)", "partial_evidence_count": null, "pfam_id": "PF04368", "proteins": 480, "proteomes": 381, "short_name": "DUF507", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04368", "structures": 2, "taxa": 694, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Family of uncharacterised prophage proteins found in Gammaproteobacteria. These may be HNH-nucleases, as there are several conserved cysteines and histidines.", "domain_architectures": 4, "interpro_id": "IPR010373", "known_evidence_count": null, "matches": 480, "name": "Protein of unknown function (DUF968)", "partial_evidence_count": null, "pfam_id": "PF06147", "proteins": 480, "proteomes": 384, "short_name": "DUF968", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06147", "structures": 0, "taxa": 720, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 298, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 58 and 136 amino acids in length. There is a single completely conserved residue R that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR025458", "known_evidence_count": null, "matches": 480, "name": "Domain of unknown function (DUF4278)", "partial_evidence_count": null, "pfam_id": "PF14105", "proteins": 480, "proteomes": 186, "short_name": "DUF4278", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14105", "structures": 0, "taxa": 564, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 456, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. Members are predicted to adopt an alpha-helical configuration. This family belongs to the ribbon-helix-helix clan.", "domain_architectures": 2, "interpro_id": "IPR055544", "known_evidence_count": null, "matches": 479, "name": "Family of unknown function (DUF7120)", "partial_evidence_count": null, "pfam_id": "PF23434", "proteins": 479, "proteomes": 285, "short_name": "DUF7120", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23434", "structures": 0, "taxa": 465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 303 and 319 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR031528", "known_evidence_count": null, "matches": 494, "name": "Domain of unknown function (DUF4699)", "partial_evidence_count": null, "pfam_id": "PF15770", "proteins": 478, "proteomes": 395, "short_name": "DUF4699", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15770", "structures": 0, "taxa": 1345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 279, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046146", "known_evidence_count": null, "matches": 478, "name": "Family of unknown function (DUF6148)", "partial_evidence_count": null, "pfam_id": "PF19645", "proteins": 478, "proteomes": 438, "short_name": "DUF6148", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19645", "structures": 0, "taxa": 938, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This domain has a structure that resembles the galactose-binding domain. This domain is often associated with a [pfam:PF00884] sulfatase like domain. Suggesting that this domain may be part of an enzyme that modifies some kind of carbohydrate.", "domain_architectures": 21, "interpro_id": "IPR054288", "known_evidence_count": null, "matches": 480, "name": "Domain of unknown function (DUF7024)", "partial_evidence_count": null, "pfam_id": "PF22895", "proteins": 478, "proteomes": 424, "short_name": "DUF7024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22895", "structures": 0, "taxa": 688, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein domain found in Actinomycetes, predominantly in Mycobacteriales and Micrococcales. The domain is approximately 230-236 amino acids in length and typically occurs as part of multi-domain proteins.", "domain_architectures": 4, "interpro_id": "IPR061618", "known_evidence_count": null, "matches": 481, "name": "Domain of unknown function (DUF8548)", "partial_evidence_count": null, "pfam_id": "PF29425", "proteins": 478, "proteomes": 414, "short_name": "DUF8548", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29425", "structures": 0, "taxa": 756, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 328, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 90 residues in length. Members of the family seem to be found exclusively in Mycobacterium species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009963", "known_evidence_count": null, "matches": 477, "name": "Protein of unknown function (DUF1490)", "partial_evidence_count": null, "pfam_id": "PF07371", "proteins": 477, "proteomes": 322, "short_name": "DUF1490", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07371", "structures": 0, "taxa": 407, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 441, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of a group of uncharacterised archaeal proteins. This domain is predicted to adopt an alpha-helical structure. Members of this family have an HTH domain at the N terminus.", "domain_architectures": 7, "interpro_id": "IPR057161", "known_evidence_count": null, "matches": 477, "name": "Domain of unknown function (DUF7839)", "partial_evidence_count": null, "pfam_id": "PF25211", "proteins": 477, "proteomes": 448, "short_name": "DUF7839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25211", "structures": 0, "taxa": 775, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 340, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family is found in several undescribed proteins. The alignment is distinguished by the frequent occurrence of conserved glycine and aromatic residues.", "domain_architectures": 4, "interpro_id": "IPR011470", "known_evidence_count": null, "matches": 939, "name": "Protein of unknown function (DUF1576)", "partial_evidence_count": null, "pfam_id": "PF07613", "proteins": 476, "proteomes": 448, "short_name": "DUF1576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07613", "structures": 0, "taxa": 835, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are typically between 258 and 528 amino acids in length. There is a conserved GSC sequence motif.", "domain_architectures": 28, "interpro_id": "IPR046237", "known_evidence_count": null, "matches": 485, "name": "Family of unknown function (DUF6270)", "partial_evidence_count": null, "pfam_id": "PF19786", "proteins": 476, "proteomes": 411, "short_name": "DUF6270", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19786", "structures": 0, "taxa": 783, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 449, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family represents the C-terminus (approximately 200 residues) of a number of archaeal proteins of unknown function. One member is annotated as being a possible carboligase enzyme.", "domain_architectures": 3, "interpro_id": "IPR009720", "known_evidence_count": null, "matches": 475, "name": "Domain of unknown function (DUF1297)", "partial_evidence_count": null, "pfam_id": "PF06973", "proteins": 475, "proteomes": 251, "short_name": "DUF1297", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06973", "structures": 9, "taxa": 521, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 349, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as yckD however currently no function is known.", "domain_architectures": 6, "interpro_id": "IPR024485", "known_evidence_count": null, "matches": 502, "name": "Protein of unknown function (DUF2680)", "partial_evidence_count": null, "pfam_id": "PF10925", "proteins": 475, "proteomes": 357, "short_name": "DUF2680", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10925", "structures": 0, "taxa": 709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021339", "known_evidence_count": null, "matches": 475, "name": "Protein of unknown function (DUF2956)", "partial_evidence_count": null, "pfam_id": "PF11169", "proteins": 475, "proteomes": 474, "short_name": "DUF2956", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11169", "structures": 0, "taxa": 672, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 323, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. There is a conserved LTKVV sequence motif.", "domain_architectures": 1, "interpro_id": "IPR046613", "known_evidence_count": null, "matches": 475, "name": "Family of unknown function (DUF6726)", "partial_evidence_count": null, "pfam_id": "PF20487", "proteins": 475, "proteomes": 403, "short_name": "DUF6726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20487", "structures": 0, "taxa": 596, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 275, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins either standalone or C-terminal to HTH winged helix domains. It has a partial sequence similarity to ribosome associated factors that are members of [pfam:PF02482].", "domain_architectures": 7, "interpro_id": "IPR054241", "known_evidence_count": null, "matches": 494, "name": "Domain of unknown function (DUF6968)", "partial_evidence_count": null, "pfam_id": "PF22302", "proteins": 475, "proteomes": 389, "short_name": "DUF6968", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22302", "structures": 0, "taxa": 732, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 349, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 90 residues found in proteins annotated as quinate 5-dehydrogenase. This domain is structurally distinct from the C-terminal catalytic region. This family is found in bacteria, predominantly Bacillota (especially Clostridia) and Pseudomonadota. The function of this domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061814", "known_evidence_count": null, "matches": 475, "name": "Domain of unknown function (DUF8753)", "partial_evidence_count": null, "pfam_id": "PF30884", "proteins": 475, "proteomes": 447, "short_name": "DUF8753", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30884", "structures": 0, "taxa": 965, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Archaeal protein of unknown function.", "domain_architectures": 2, "interpro_id": "IPR007366", "known_evidence_count": null, "matches": 474, "name": "Protein of unknown function (DUF432)", "partial_evidence_count": null, "pfam_id": "PF04254", "proteins": 474, "proteomes": 454, "short_name": "DUF432", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04254", "structures": 0, "taxa": 881, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 139 and 154 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046171", "known_evidence_count": null, "matches": 474, "name": "Family of unknown function (DUF6173)", "partial_evidence_count": null, "pfam_id": "PF19670", "proteins": 474, "proteomes": 471, "short_name": "DUF6173", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19670", "structures": 0, "taxa": 807, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 441, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins.", "domain_architectures": 8, "interpro_id": "IPR055690", "known_evidence_count": null, "matches": 474, "name": "Family of unknown function (DUF7266)", "partial_evidence_count": null, "pfam_id": "PF23928", "proteins": 474, "proteomes": 298, "short_name": "DUF7266", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23928", "structures": 0, "taxa": 480, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 451, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the small C-terminal beta domain of this family of proteins. This domain contains 6 highly conserved cysteines. These form two putative zinc binding sites.", "domain_architectures": 4, "interpro_id": "IPR058675", "known_evidence_count": null, "matches": 474, "name": "Family of unknown function (DUF8054) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26237", "proteins": 474, "proteomes": 242, "short_name": "DUF8054_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26237", "structures": 0, "taxa": 387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 336, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes.", "domain_architectures": 1, "interpro_id": "IPR021701", "known_evidence_count": null, "matches": 473, "name": "Domain of unknown function (DUF3284)", "partial_evidence_count": null, "pfam_id": "PF11687", "proteins": 473, "proteomes": 384, "short_name": "DUF3284", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11687", "structures": 0, "taxa": 649, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 300, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is an uncharacterised family of Bacillus proteins.", "domain_architectures": 1, "interpro_id": "IPR024217", "known_evidence_count": null, "matches": 473, "name": "Protein of unknown function (DUF3813)", "partial_evidence_count": null, "pfam_id": "PF12758", "proteins": 473, "proteomes": 473, "short_name": "DUF3813", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12758", "structures": 0, "taxa": 601, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046606", "known_evidence_count": null, "matches": 473, "name": "Family of unknown function (DUF6665)", "partial_evidence_count": null, "pfam_id": "PF20370", "proteins": 473, "proteomes": 471, "short_name": "DUF6665", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20370", "structures": 0, "taxa": 652, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 200 residues found in proteins annotated as quinate 5-dehydrogenase. Structure prediction suggests a Rossmann-like fold. This family is found in bacteria, predominantly Bacillota (especially Clostridia) and Pseudomonadota. The function of this domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061815", "known_evidence_count": null, "matches": 473, "name": "Domain of unknown function (DUF8754)", "partial_evidence_count": null, "pfam_id": "PF30885", "proteins": 473, "proteomes": 445, "short_name": "DUF8754", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30885", "structures": 0, "taxa": 959, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of probable enzymes found in a range of bacteria. Shows structural similarity to Mannosyl-oligosaccharide alpha-1,2-mannosidase.", "domain_architectures": 4, "interpro_id": "IPR058347", "known_evidence_count": null, "matches": 571, "name": "Domain of unknown function (DUF8034)", "partial_evidence_count": null, "pfam_id": "PF26099", "proteins": 472, "proteomes": 380, "short_name": "DUF8034", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26099", "structures": 0, "taxa": 628, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 446, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This family represents the N-terminus of a number of hypothetical archaeal proteins of unknown function. This family is structurally related to the PreATP-grasp domain.", "domain_architectures": 2, "interpro_id": "IPR010672", "known_evidence_count": null, "matches": 471, "name": "Protein of unknown function (DUF1246)", "partial_evidence_count": null, "pfam_id": "PF06849", "proteins": 471, "proteomes": 251, "short_name": "DUF1246", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06849", "structures": 9, "taxa": 514, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 290, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 150 residues in length and is mainly found in various Bacteroides and Prevotella species. The function of this protein is unknown.", "domain_architectures": 17, "interpro_id": "IPR032530", "known_evidence_count": null, "matches": 471, "name": "Domain of unknown function (DUF4957)", "partial_evidence_count": null, "pfam_id": "PF16318", "proteins": 471, "proteomes": 404, "short_name": "DUF4957", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16318", "structures": 0, "taxa": 625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 315, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 270 residues in length and is mainly found in various Bacillus cereus species. Some members of this family are annotated as Galactose-1-phosphate uridylyltransferases, but the specific function of this family is unknown.", "domain_architectures": 5, "interpro_id": "IPR049285", "known_evidence_count": null, "matches": 473, "name": "Domain of unknown function (DUF4931) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20956", "proteins": 471, "proteomes": 450, "short_name": "DUF4931_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20956", "structures": 1, "taxa": 693, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised bacterial proteins.", "domain_architectures": 15, "interpro_id": "IPR054187", "known_evidence_count": null, "matches": 472, "name": "Family of unknown function (DUF6892)", "partial_evidence_count": null, "pfam_id": "PF21832", "proteins": 471, "proteomes": 432, "short_name": "DUF6892", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21832", "structures": 0, "taxa": 801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical proteins produced by bacteria of the Bacillus genus.", "domain_architectures": 1, "interpro_id": "IPR015062", "known_evidence_count": null, "matches": 469, "name": "Domain of unknown function (DUF1885)", "partial_evidence_count": null, "pfam_id": "PF08968", "proteins": 469, "proteomes": 467, "short_name": "DUF1885", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08968", "structures": 1, "taxa": 573, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 354, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001035) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide), polyketide and other (Aminocoumarin). This family includes a protein from the pneumocandin B0 biosynthetic gene cluster from Glarea lozoyensis ATCC 20868 and appear to be predominantly found in fungi [[cite:PUB00098936],[cite:PUB00098937]].", "domain_architectures": 3, "interpro_id": "IPR045702", "known_evidence_count": null, "matches": 469, "name": "Family of unknown function (DUF6060)", "partial_evidence_count": null, "pfam_id": "PF19535", "proteins": 469, "proteomes": 292, "short_name": "DUF6060", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19535", "structures": 0, "taxa": 673, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 320, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins that show structural similarity to [pfam:PF06124].", "domain_architectures": 2, "interpro_id": "IPR049241", "known_evidence_count": null, "matches": 469, "name": "Family of unknown function (DUF6876)", "partial_evidence_count": null, "pfam_id": "PF21781", "proteins": 469, "proteomes": 337, "short_name": "DUF6876", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21781", "structures": 0, "taxa": 688, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in bacteria and some viruses. The function is not known.", "domain_architectures": 2, "interpro_id": "IPR019659", "known_evidence_count": null, "matches": 468, "name": "Protein of unknown function (DUF2514)", "partial_evidence_count": null, "pfam_id": "PF10721", "proteins": 468, "proteomes": 386, "short_name": "DUF2514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10721", "structures": 0, "taxa": 767, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 311, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 86 and 106 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046093", "known_evidence_count": null, "matches": 468, "name": "Family of unknown function (DUF6111)", "partial_evidence_count": null, "pfam_id": "PF19606", "proteins": 468, "proteomes": 468, "short_name": "DUF6111", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19606", "structures": 0, "taxa": 676, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 304, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are enriched with hydrophobic residues and are likely associated with the membrane. These proteins contain two conserved motifs GLDxxYxxxG and FLxxFD.", "domain_architectures": 2, "interpro_id": "IPR054261", "known_evidence_count": null, "matches": 468, "name": "Family of unknown function (DUF6992)", "partial_evidence_count": null, "pfam_id": "PF22503", "proteins": 468, "proteomes": 436, "short_name": "DUF6992", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22503", "structures": 0, "taxa": 731, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between and 90 amino acids in length. The human member of this family is C17orf67.", "domain_architectures": 2, "interpro_id": "IPR027870", "known_evidence_count": null, "matches": 469, "name": "Domain of unknown function (DUF4543)", "partial_evidence_count": null, "pfam_id": "PF15076", "proteins": 467, "proteomes": 402, "short_name": "DUF4543", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15076", "structures": 0, "taxa": 1376, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 275, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in uncharacterised bacterial proteins. It shares some similarity to the C-terminal domain of JetD [[pfam:PF09983]].", "domain_architectures": 2, "interpro_id": "IPR055705", "known_evidence_count": null, "matches": 467, "name": "Domain of unknown function (DUF7281)", "partial_evidence_count": null, "pfam_id": "PF23947", "proteins": 467, "proteomes": 460, "short_name": "DUF7281", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23947", "structures": 0, "taxa": 837, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function at the N-terminal in putative histidine kinases mostly found in bacteria. This domain belongs to proteins with a conserved four or five- helix up-and-down bundle structure. This structure is typical of focal adhesion targeting (FAT) domains and is responsible for dimerisation. It could also be present in transcriptional regulators where the bundle structure is important for their dynamic conformational equilibrium to control target specificity. The conserved helical bundle architecture enables these proteins to function in protein- protein interactions and regulatory processes [[cite:PUB00075415],[cite:PUB00004911],[cite:PUB00161916]].", "domain_architectures": 4, "interpro_id": "IPR059360", "known_evidence_count": null, "matches": 468, "name": "Domain of unknown function (DUF8316)", "partial_evidence_count": null, "pfam_id": "PF26990", "proteins": 467, "proteomes": 338, "short_name": "DUF8316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26990", "structures": 0, "taxa": 391, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 302, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR019705", "known_evidence_count": null, "matches": 466, "name": "Protein of unknown function (DUF2594)", "partial_evidence_count": null, "pfam_id": "PF10769", "proteins": 466, "proteomes": 466, "short_name": "DUF2594", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10769", "structures": 0, "taxa": 638, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR016896", "known_evidence_count": null, "matches": 466, "name": "Protein of unknown function (DUF2860)", "partial_evidence_count": null, "pfam_id": "PF11059", "proteins": 466, "proteomes": 331, "short_name": "DUF2860", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11059", "structures": 0, "taxa": 560, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 47 and 76 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025018", "known_evidence_count": null, "matches": 466, "name": "Protein of unknown function (DUF3953)", "partial_evidence_count": null, "pfam_id": "PF13129", "proteins": 466, "proteomes": 333, "short_name": "DUF3953", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13129", "structures": 0, "taxa": 466, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 343, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised and it is found in bacterial (predominantly in cyanobacteria) and eukaryotic (mainly from plants) sequences. Structure prediction using AlphaFold resource, suggest that this domain may have a START-like (StAR-related lipid-transfer) fold consisting of an alpha/beta structure of a helix-grip fold, that forms cavities for hydrophobic substrates or ligands which may indicate a possible function for this domain.", "domain_architectures": 15, "interpro_id": "IPR049213", "known_evidence_count": null, "matches": 469, "name": "Domain of unknown function (DUF6816)", "partial_evidence_count": null, "pfam_id": "PF20670", "proteins": 466, "proteomes": 305, "short_name": "DUF6816", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20670", "structures": 0, "taxa": 879, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 297, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised proteins from bacteria. This domain is about 90 amino acids in length. It contains the conserved sequences CxxC, RxxCxxxxC and a conserved LP motif.", "domain_architectures": 4, "interpro_id": "IPR045536", "known_evidence_count": null, "matches": 465, "name": "Domain of unknown function (DUF6431)", "partial_evidence_count": null, "pfam_id": "PF20020", "proteins": 465, "proteomes": 318, "short_name": "DUF6431", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20020", "structures": 0, "taxa": 716, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Enterobacterial proteins of around 160 residues in length. The function of this family is unknown. However, it appears to be distantly related to other HTH families so may act as a transcriptional regulator.", "domain_architectures": 2, "interpro_id": "IPR009901", "known_evidence_count": null, "matches": 464, "name": "Protein of unknown function (DUF1441)", "partial_evidence_count": null, "pfam_id": "PF07278", "proteins": 464, "proteomes": 418, "short_name": "DUF1441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07278", "structures": 0, "taxa": 940, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 320, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in bacteria.", "domain_architectures": 4, "interpro_id": "IPR043776", "known_evidence_count": null, "matches": 465, "name": "Family of unknown function (DUF5718)", "partial_evidence_count": null, "pfam_id": "PF18985", "proteins": 464, "proteomes": 446, "short_name": "DUF5718", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18985", "structures": 0, "taxa": 692, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 306, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short protein is found among some phage. It is possibly distantly related to the small terminase family [pfam:PF05119].", "domain_architectures": 3, "interpro_id": "IPR055644", "known_evidence_count": null, "matches": 464, "name": "Family of unknown function (DUF7220)", "partial_evidence_count": null, "pfam_id": "PF23858", "proteins": 464, "proteomes": 329, "short_name": "DUF7220", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23858", "structures": 0, "taxa": 726, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 312, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins around 110 residues in length and found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032593", "known_evidence_count": null, "matches": 463, "name": "Domain of unknown function (DUF4907)", "partial_evidence_count": null, "pfam_id": "PF16250", "proteins": 463, "proteomes": 450, "short_name": "DUF4907", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16250", "structures": 0, "taxa": 644, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 298, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of Glycosyl hydrolase family 38 proteins around 700 residues in length and is mainly found in various Clostridium and Rhizobium species. The function of this family is unknown.", "domain_architectures": 16, "interpro_id": "IPR032482", "known_evidence_count": null, "matches": 486, "name": "Domain of unknown function (DUF5054)", "partial_evidence_count": null, "pfam_id": "PF16477", "proteins": 463, "proteomes": 326, "short_name": "DUF5054", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16477", "structures": 0, "taxa": 798, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 448, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins containing this domain are found predominantly in the class Halobacteria, which includes families such as Natrialbaceae, Haloferacaceae, and Haloarculaceae. The domain is approximately 100-120 amino acids in length. The domain adopts an alpha/beta plait architecture.", "domain_architectures": 3, "interpro_id": "IPR058473", "known_evidence_count": null, "matches": 465, "name": "Domain of unknown function (DUF8159)", "partial_evidence_count": null, "pfam_id": "PF26490", "proteins": 463, "proteomes": 236, "short_name": "DUF8159", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26490", "structures": 0, "taxa": 373, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 283, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins possess metal binding properties; however, their exact function has not, as yet, been determined.", "domain_architectures": 1, "interpro_id": "IPR019250", "known_evidence_count": null, "matches": 462, "name": "Uncharacterized metal-binding protein (DUF2227)", "partial_evidence_count": null, "pfam_id": "PF09988", "proteins": 462, "proteomes": 441, "short_name": "DUF2227", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09988", "structures": 0, "taxa": 1005, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 380, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It contains several conserved aromatic residues.", "domain_architectures": 9, "interpro_id": "IPR061859", "known_evidence_count": null, "matches": 464, "name": "Domain of unknown function (DUF8798)", "partial_evidence_count": null, "pfam_id": "PF31065", "proteins": 462, "proteomes": 320, "short_name": "DUF8798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31065", "structures": 0, "taxa": 884, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 354, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in metazoa. This entry represents the central globular domain of the protein related to the calmodulin domain.", "domain_architectures": 24, "interpro_id": "IPR049246", "known_evidence_count": null, "matches": 464, "name": "Family of unknown function (DUF5580) middle domain", "partial_evidence_count": null, "pfam_id": "PF20742", "proteins": 461, "proteomes": 266, "short_name": "DUF5580_M", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20742", "structures": 0, "taxa": 1053, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021444", "known_evidence_count": null, "matches": 460, "name": "Protein of unknown function (DUF3094)", "partial_evidence_count": null, "pfam_id": "PF11293", "proteins": 460, "proteomes": 457, "short_name": "DUF3094", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11293", "structures": 0, "taxa": 541, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 306, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 160 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045352", "known_evidence_count": null, "matches": 460, "name": "Family of unknown function (DUF6530)", "partial_evidence_count": null, "pfam_id": "PF20140", "proteins": 460, "proteomes": 428, "short_name": "DUF6530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20140", "structures": 0, "taxa": 777, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It contains four pairs of highly conserved cysteine residues that may be involved in metal coordination. It also contains a highly conserved CxxCxGxG sequence motif.", "domain_architectures": 8, "interpro_id": "IPR057217", "known_evidence_count": null, "matches": 461, "name": "Domain of unknown function (DUF7895)", "partial_evidence_count": null, "pfam_id": "PF25433", "proteins": 460, "proteomes": 338, "short_name": "DUF7895", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25433", "structures": 0, "taxa": 969, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal beta sandwich domain of approximately 110 residues found in Pvc16 proteins. The domain is located C-terminal to the Pvc16_N domain ([pfam:PF14065]). These proteins are components of extracellular contractile injection systems (eCIS), which are phage tail-like structures used by bacteria to deliver effector proteins. This family is found in bacteria, predominantly Cyanobacteriota, Pseudomonadota, and Actinomycetota. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061817", "known_evidence_count": null, "matches": 460, "name": "Domain of unknown function (DUF8756)", "partial_evidence_count": null, "pfam_id": "PF30887", "proteins": 460, "proteomes": 434, "short_name": "DUF8756", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30887", "structures": 0, "taxa": 1018, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 362, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 75 residues in length and is mainly found in various Thermotogav species. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032587", "known_evidence_count": null, "matches": 458, "name": "Domain of unknown function (DUF4911)", "partial_evidence_count": null, "pfam_id": "PF16256", "proteins": 458, "proteomes": 431, "short_name": "DUF4911", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16256", "structures": 0, "taxa": 940, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 427, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins that are thought to have helicase activity, predominantly found in Halobacteria and Methanomicrobia.", "domain_architectures": 2, "interpro_id": "IPR043852", "known_evidence_count": null, "matches": 458, "name": "Family of unknown function (DUF5814)", "partial_evidence_count": null, "pfam_id": "PF19131", "proteins": 458, "proteomes": 458, "short_name": "DUF5814", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19131", "structures": 1, "taxa": 753, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 323, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein of 86 residues is expressed in bacteria. It consists of four alpha helices and two beta strands. Its function is unknown. One UniProt entry gives the gene name as Traf5.", "domain_architectures": 1, "interpro_id": "IPR018592", "known_evidence_count": null, "matches": 457, "name": "Domain of unknown function (DUF2024)", "partial_evidence_count": null, "pfam_id": "PF09630", "proteins": 457, "proteomes": 426, "short_name": "DUF2024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09630", "structures": 1, "taxa": 708, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 301, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short domain is normally found at the very N-terminus of Hyrdrolases [pfam:PF00702].", "domain_architectures": 4, "interpro_id": "IPR025138", "known_evidence_count": null, "matches": 457, "name": "Domain of unknown function (DUF4072)", "partial_evidence_count": null, "pfam_id": "PF13284", "proteins": 457, "proteomes": 457, "short_name": "DUF4072", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13284", "structures": 0, "taxa": 597, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of presumed integral membrane proteins is found in bacteria and archaea. Proteins in this family are approximately 90 amino acids in length and contain two predicted transmembrane helices.", "domain_architectures": 4, "interpro_id": "IPR044020", "known_evidence_count": null, "matches": 457, "name": "2TM family of unknown function (DUF5676)", "partial_evidence_count": null, "pfam_id": "PF18926", "proteins": 457, "proteomes": 413, "short_name": "DUF5676", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18926", "structures": 0, "taxa": 900, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 421, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised proteins mainly found in worms. This is likely a transmembrane segment.", "domain_architectures": 10, "interpro_id": "IPR054291", "known_evidence_count": null, "matches": 457, "name": "Domain of unknown function (DUF7027)", "partial_evidence_count": null, "pfam_id": "PF22954", "proteins": 457, "proteomes": 220, "short_name": "DUF7027", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22954", "structures": 0, "taxa": 857, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry rerepsents uncharacterised bacterial proteins. It shares similarity to Inclusion body protein PixA and other structurally related domains.", "domain_architectures": 1, "interpro_id": "IPR061849", "known_evidence_count": null, "matches": 457, "name": "Domain of unknown function (DUF8788)", "partial_evidence_count": null, "pfam_id": "PF31048", "proteins": 457, "proteomes": 176, "short_name": "DUF8788", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31048", "structures": 2, "taxa": 369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in proteins from bacteria and phages which are functionally uncharacterised. This domain is about 100 amino acids in length. It contains two conserved sequence motifs, KxxR and DxxxDxxGY.", "domain_architectures": 5, "interpro_id": "IPR045958", "known_evidence_count": null, "matches": 456, "name": "Domain of unknown function (DUF6378)", "partial_evidence_count": null, "pfam_id": "PF19905", "proteins": 456, "proteomes": 441, "short_name": "DUF6378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19905", "structures": 0, "taxa": 1128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a phage protein which contains a C1q and TNF superfamily domain. Structure prediction suggests that this domain forms a confident homotrimeric interaction.", "domain_architectures": 7, "interpro_id": "IPR055681", "known_evidence_count": null, "matches": 462, "name": "Domain of unknown function (DUF7257)", "partial_evidence_count": null, "pfam_id": "PF23918", "proteins": 456, "proteomes": 404, "short_name": "DUF7257", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23918", "structures": 1, "taxa": 934, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 150 residues in length. Some family members are described as putative lipoproteins but the function of the family is unknown.", "domain_architectures": 6, "interpro_id": "IPR009736", "known_evidence_count": null, "matches": 459, "name": "Protein of unknown function (DUF1307)", "partial_evidence_count": null, "pfam_id": "PF06998", "proteins": 454, "proteomes": 329, "short_name": "DUF1307", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06998", "structures": 1, "taxa": 546, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 400 residues in length and is mainly found in various Bacteroides species. Several proteins are annotated as glycerophosphodiester phosphodiesterases, but the origin of this annotation is not clear.", "domain_architectures": 44, "interpro_id": "IPR032329", "known_evidence_count": null, "matches": 464, "name": "Domain of unknown function (DUF4855)", "partial_evidence_count": null, "pfam_id": "PF16147", "proteins": 454, "proteomes": 269, "short_name": "DUF4855", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16147", "structures": 0, "taxa": 504, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 170 residues in length and is mainly found in various Bacillus species (B. cereus, B. thuringiensis and B. anthracis). The solved structure of B. anthracis homologs has a variant of the Greek-key beta barrel fold, making the DUF4870 family a member of a large group of bacterial immunoglobulin like domains, but the functional consequences of this classification remain unknown.", "domain_architectures": 4, "interpro_id": "IPR032366", "known_evidence_count": null, "matches": 457, "name": "Domain of unknown function (DUF4871)", "partial_evidence_count": null, "pfam_id": "PF16167", "proteins": 454, "proteomes": 373, "short_name": "DUF4871", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16167", "structures": 1, "taxa": 496, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 434, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. Members adopt a beta configuration with high similarity to the CS domain ([pfam:PF04969]).", "domain_architectures": 1, "interpro_id": "IPR055551", "known_evidence_count": null, "matches": 454, "name": "Family of unknown function (DUF7127)", "partial_evidence_count": null, "pfam_id": "PF23444", "proteins": 454, "proteomes": 281, "short_name": "DUF7127", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23444", "structures": 0, "taxa": 440, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 287, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small helical hairpin domain found at the C-terminus of bacterial signalling proteins. It may form homodimers to make a four helical bundle structure.", "domain_architectures": 4, "interpro_id": "IPR061870", "known_evidence_count": null, "matches": 454, "name": "Domain of unknown function (DUF8809)", "partial_evidence_count": null, "pfam_id": "PF31105", "proteins": 454, "proteomes": 450, "short_name": "DUF8809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31105", "structures": 0, "taxa": 812, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is around 190 amino acids in length. As yet no function has been given to any member of the family.", "domain_architectures": 5, "interpro_id": "IPR024211", "known_evidence_count": null, "matches": 453, "name": "Domain of unknown function (DUF3841)", "partial_evidence_count": null, "pfam_id": "PF12952", "proteins": 453, "proteomes": 339, "short_name": "DUF3841", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12952", "structures": 0, "taxa": 751, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 377, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 8, "interpro_id": "IPR037691", "known_evidence_count": null, "matches": 453, "name": "Family of unknown function (DUF5564)", "partial_evidence_count": null, "pfam_id": "PF17719", "proteins": 453, "proteomes": 361, "short_name": "DUF5564", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17719", "structures": 1, "taxa": 1324, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 360, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to contain two transmembrane helices.", "domain_architectures": 11, "interpro_id": "IPR057209", "known_evidence_count": null, "matches": 454, "name": "Domain of unknown function (DUF7887)", "partial_evidence_count": null, "pfam_id": "PF25397", "proteins": 453, "proteomes": 350, "short_name": "DUF7887", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25397", "structures": 0, "taxa": 1005, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 404, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "", "domain_architectures": 2, "interpro_id": "IPR003831", "known_evidence_count": null, "matches": 452, "name": "Uncharacterized ArCR, COG1888", "partial_evidence_count": null, "pfam_id": "PF02680", "proteins": 452, "proteomes": 448, "short_name": "DUF211", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02680", "structures": 3, "taxa": 980, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Enterobacterial proteins of around 80 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009885", "known_evidence_count": null, "matches": 452, "name": "Protein of unknown function (DUF1435)", "partial_evidence_count": null, "pfam_id": "PF07256", "proteins": 452, "proteomes": 451, "short_name": "DUF1435", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07256", "structures": 0, "taxa": 606, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 295, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represent the C-terminal domain of the structure. In two related Bacteroides species the gene lies immediately upstream from a putative ATP binding component of an ATP transporter and a putative histidinol phosphatase. The structure of this domain is strikingly similar to the N-terminal structure of 1ma7 whose C-terminal domain is a phage integrase, [pfam:PF00589].", "domain_architectures": 5, "interpro_id": "IPR024266", "known_evidence_count": null, "matches": 452, "name": "Domain of unknown function (DUF3806)", "partial_evidence_count": null, "pfam_id": "PF12713", "proteins": 452, "proteomes": 437, "short_name": "DUF3806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12713", "structures": 1, "taxa": 790, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 306, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 220 residues in length and is mainly found in various human gut Firmicutes and a few eubacteria species. It is also amply represented in human gut metagenomic datasets. Distant homology analysis and marginal HMM overlaps suggest this family is a distant homologue of Ureidoglycolate hydrolase [pfam:PF04115], but this prediction is not verified by experiment, therefore the function of this family is still unknown.", "domain_architectures": 2, "interpro_id": "IPR032358", "known_evidence_count": null, "matches": 452, "name": "Domain of unknown function (DUF4867)", "partial_evidence_count": null, "pfam_id": "PF16161", "proteins": 452, "proteomes": 424, "short_name": "DUF4867", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16161", "structures": 2, "taxa": 771, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 420, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Halobacteria. It is predicted to adopt a globular structure composed mainly of alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR055684", "known_evidence_count": null, "matches": 452, "name": "Domain of unknown function (DUF7260)", "partial_evidence_count": null, "pfam_id": "PF23921", "proteins": 452, "proteomes": 238, "short_name": "DUF7260", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23921", "structures": 0, "taxa": 380, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 370, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a alpha/beta structure with a central mixed beta-sheet and alpha-helices packed on both sides. The predicted structure has a topological similarity to PACT family domains members of [pfam:PF09754].", "domain_architectures": 13, "interpro_id": "IPR057216", "known_evidence_count": null, "matches": 472, "name": "Domain of unknown function (DUF7894)", "partial_evidence_count": null, "pfam_id": "PF25428", "proteins": 452, "proteomes": 318, "short_name": "DUF7894", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25428", "structures": 0, "taxa": 894, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family consists of several putative phage excisionase proteins of around 80 residues in length.", "domain_architectures": 1, "interpro_id": "IPR009634", "known_evidence_count": null, "matches": 450, "name": "Putative excisionase (DUF1233)", "partial_evidence_count": null, "pfam_id": "PF06806", "proteins": 450, "proteomes": 394, "short_name": "DUF1233", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06806", "structures": 1, "taxa": 765, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 272, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. There is a conserved EGT sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025100", "known_evidence_count": null, "matches": 450, "name": "Protein of unknown function (DUF4025)", "partial_evidence_count": null, "pfam_id": "PF13217", "proteins": 450, "proteomes": 430, "short_name": "DUF4025", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13217", "structures": 0, "taxa": 561, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 299, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 397 and 433 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046713", "known_evidence_count": null, "matches": 451, "name": "Family of unknown function (DUF6786)", "partial_evidence_count": null, "pfam_id": "PF20583", "proteins": 450, "proteomes": 404, "short_name": "DUF6786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20583", "structures": 0, "taxa": 725, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into array of helices. It has similarity to helical domain found in MmeI restriction-modification enzymes.", "domain_architectures": 25, "interpro_id": "IPR056716", "known_evidence_count": null, "matches": 450, "name": "Domain of unknown function (DUF7814)", "partial_evidence_count": null, "pfam_id": "PF25120", "proteins": 450, "proteomes": 385, "short_name": "DUF7814", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25120", "structures": 0, "taxa": 820, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021399", "known_evidence_count": null, "matches": 449, "name": "Protein of unknown function (DUF3038)", "partial_evidence_count": null, "pfam_id": "PF11237", "proteins": 449, "proteomes": 240, "short_name": "DUF3038", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11237", "structures": 0, "taxa": 658, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 244, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is found in Pseudomonas species. Several members are annotated as being acetyl-CoA carboxylase alpha subunit, but his could not be confirmed.", "domain_architectures": 2, "interpro_id": "IPR032024", "known_evidence_count": null, "matches": 451, "name": "Domain of unknown function (DUF5064)", "partial_evidence_count": null, "pfam_id": "PF16703", "proteins": 449, "proteomes": 395, "short_name": "DUF5064", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16703", "structures": 1, "taxa": 433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 316, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found mainly in firmicutes, and is approximately 170 amino acids in length. The family is found in association with [pfam:PF08545].", "domain_architectures": 5, "interpro_id": "IPR045984", "known_evidence_count": null, "matches": 449, "name": "Family of unknown function (DUF5940)", "partial_evidence_count": null, "pfam_id": "PF19364", "proteins": 449, "proteomes": 398, "short_name": "DUF5940", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19364", "structures": 0, "taxa": 874, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 416, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in archaea but also in some bacterial species. They may have a Rossmann-like alpha/beta/alpha fold.", "domain_architectures": 3, "interpro_id": "IPR055834", "known_evidence_count": null, "matches": 449, "name": "Family of unknown function (DUF7411)", "partial_evidence_count": null, "pfam_id": "PF24167", "proteins": 449, "proteomes": 440, "short_name": "DUF7411", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24167", "structures": 1, "taxa": 728, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 406, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a number of Drosophila melanogaster proteins of unknown function. These contain several conserved cysteine residues.", "domain_architectures": 8, "interpro_id": "IPR006611", "known_evidence_count": null, "matches": 458, "name": "Protein of unknown function (DUF1431)", "partial_evidence_count": null, "pfam_id": "PF07248", "proteins": 448, "proteomes": 86, "short_name": "DUF1431", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07248", "structures": 0, "taxa": 357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function is restricted to Gammaproteobacteria.", "domain_architectures": 4, "interpro_id": "IPR021379", "known_evidence_count": null, "matches": 523, "name": "Protein of unknown function (DUF3012)", "partial_evidence_count": null, "pfam_id": "PF11216", "proteins": 448, "proteomes": 424, "short_name": "DUF3012", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11216", "structures": 0, "taxa": 641, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 272, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 114 and 143 amino acids in length. There is a conserved KNLFD sequence motif.", "domain_architectures": 1, "interpro_id": "IPR020979", "known_evidence_count": null, "matches": 448, "name": "Protein of unknown function (DUF3802)", "partial_evidence_count": null, "pfam_id": "PF12290", "proteins": 448, "proteomes": 448, "short_name": "DUF3802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12290", "structures": 0, "taxa": 564, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 309, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_2984, a putative uncharacterized protein As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231). It appears to be upregulated in the presence of host or other bacterial species vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 2, "interpro_id": "IPR024353", "known_evidence_count": null, "matches": 448, "name": "Domain of unknown function, B. Theta Gene description (DUF3871)", "partial_evidence_count": null, "pfam_id": "PF12987", "proteins": 448, "proteomes": 340, "short_name": "DUF3871", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12987", "structures": 0, "taxa": 522, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 289, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in Vibrio spp. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR032036", "known_evidence_count": null, "matches": 448, "name": "Domain of unknown function (DUF5062)", "partial_evidence_count": null, "pfam_id": "PF16691", "proteins": 448, "proteomes": 446, "short_name": "DUF5062", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16691", "structures": 1, "taxa": 665, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 293, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 7, "interpro_id": "IPR043856", "known_evidence_count": null, "matches": 453, "name": "Protein of unknown function (DUF5818)", "partial_evidence_count": null, "pfam_id": "PF19135", "proteins": 448, "proteomes": 321, "short_name": "DUF5818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19135", "structures": 0, "taxa": 531, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 421, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins.", "domain_architectures": 17, "interpro_id": "IPR056018", "known_evidence_count": null, "matches": 449, "name": "Domain of unknown function (DUF7597)", "partial_evidence_count": null, "pfam_id": "PF24530", "proteins": 447, "proteomes": 34, "short_name": "DUF7597", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24530", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 310, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. However, this family was identified as belonging to the nucleotidyltransferase superfamily [[cite:PUB00066751]].", "domain_architectures": 3, "interpro_id": "IPR018700", "known_evidence_count": null, "matches": 446, "name": "Nucleotidyl transferase of unknown function (DUF2204)", "partial_evidence_count": null, "pfam_id": "PF09970", "proteins": 446, "proteomes": 431, "short_name": "DUF2204", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09970", "structures": 0, "taxa": 935, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 385, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This small family contains human, mouse and fish members but the function is not known.", "domain_architectures": 7, "interpro_id": "IPR021748", "known_evidence_count": null, "matches": 457, "name": "Protein of unknown function (DUF3314)", "partial_evidence_count": null, "pfam_id": "PF11771", "proteins": 446, "proteomes": 342, "short_name": "DUF3314", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11771", "structures": 0, "taxa": 1146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 430, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of trypsin-6-like proteins found in nematodes that are part of the chymotrypsin family S1, ie a serine peptidase. The C. elegans sequence UniProt:O01566 is trypsin-6: all the active site residues are present (His90, Asp168, Ser267).", "domain_architectures": 17, "interpro_id": "IPR005514", "known_evidence_count": null, "matches": 523, "name": "Nematode trypsin-6-like family", "partial_evidence_count": null, "pfam_id": "PF03761", "proteins": 445, "proteomes": 50, "short_name": "DUF316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03761", "structures": 0, "taxa": 162, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 277, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as glutamine synthetase translation inhibitor however this function can not be confirmed.", "domain_architectures": 1, "interpro_id": "IPR021232", "known_evidence_count": null, "matches": 445, "name": "Protein of unknown function (DUF2735)", "partial_evidence_count": null, "pfam_id": "PF10931", "proteins": 445, "proteomes": 443, "short_name": "DUF2735", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10931", "structures": 0, "taxa": 554, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 425, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-beta structure.", "domain_architectures": 3, "interpro_id": "IPR055951", "known_evidence_count": null, "matches": 447, "name": "Family of unknown function (DUF7529)", "partial_evidence_count": null, "pfam_id": "PF24373", "proteins": 445, "proteomes": 228, "short_name": "DUF7529", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24373", "structures": 0, "taxa": 373, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised bacterial proteins. They share detectable similarity to proteins members of [pfam:PF08974] whose function is unknown. Their predicted structures resemble the structure of DNA mimic protein DMP12 but elaborated with additional alpha helices.", "domain_architectures": 3, "interpro_id": "IPR056108", "known_evidence_count": null, "matches": 447, "name": "Domain of unknown function (DUF7691)", "partial_evidence_count": null, "pfam_id": "PF24740", "proteins": 445, "proteomes": 400, "short_name": "DUF7691", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24740", "structures": 0, "taxa": 656, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a globular structure consisting of segregated alpha-helices and a five-stranded antiparallel beta-sheet. This domain contains two highly conserved sequence motifs TxxHGG and YEED that may be of a functional importance.", "domain_architectures": 4, "interpro_id": "IPR054276", "known_evidence_count": null, "matches": 445, "name": "Domain of unknown function (DUF7007)", "partial_evidence_count": null, "pfam_id": "PF22653", "proteins": 444, "proteomes": 358, "short_name": "DUF7007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22653", "structures": 0, "taxa": 699, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 430, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a short conserved region (approximately 50 residues long), sometimes repeated, within a number of hypothetical Oryza sativa proteins of unknown function.", "domain_architectures": 21, "interpro_id": "IPR010811", "known_evidence_count": null, "matches": 443, "name": "Protein of unknown function (DUF1409)", "partial_evidence_count": null, "pfam_id": "PF07197", "proteins": 443, "proteomes": 23, "short_name": "DUF1409", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07197", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 247, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 100 residues in length and is mainly found in various Burkholderiales species, such as Herbaspirillum, Cupriavidus, Ralstonia and so on. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032556", "known_evidence_count": null, "matches": 443, "name": "Domain of unknown function (DUF4936)", "partial_evidence_count": null, "pfam_id": "PF16290", "proteins": 443, "proteomes": 443, "short_name": "DUF4936", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16290", "structures": 0, "taxa": 564, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 151 and 172 amino acids in length. This family has a conserved sequence motif DER and two conserved residues, a Tyr and a Gly.", "domain_architectures": 4, "interpro_id": "IPR046664", "known_evidence_count": null, "matches": 444, "name": "Family of unknown function (DUF6773)", "partial_evidence_count": null, "pfam_id": "PF20563", "proteins": 443, "proteomes": 395, "short_name": "DUF6773", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20563", "structures": 0, "taxa": 677, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 279, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small C-terminal helical domain of approximately 40 residues found in bacterial ImmA/IrrE family metallopeptidases. This domain is located C-terminal to the Peptidase_M78 catalytic domain ([pfam:PF06114]). The function of this domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061874", "known_evidence_count": null, "matches": 443, "name": "Domain of unknown function (DUF8813)", "partial_evidence_count": null, "pfam_id": "PF31113", "proteins": 443, "proteomes": 437, "short_name": "DUF8813", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31113", "structures": 0, "taxa": 1133, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 440, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 57 residues found in aspartic peptidases in Arachis (peanut). This domain is located C-terminal to the Asp_protease_2 domain ([pfam:PF13650]). These proteins may be associated with transposable elements. The function of this C-terminal domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061887", "known_evidence_count": null, "matches": 443, "name": "Domain of unknown function (DUF8826)", "partial_evidence_count": null, "pfam_id": "PF31160", "proteins": 443, "proteomes": 4, "short_name": "DUF8826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31160", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents the Uncharacterized protein YtmB and related proteins. Its structure was determined (PDB:2nwa) and shows significant similarity to PUA domains. Its function is unknown.", "domain_architectures": 2, "interpro_id": "IPR019699", "known_evidence_count": null, "matches": 441, "name": "Domain of unknown function (DUF2584)", "partial_evidence_count": null, "pfam_id": "PF10763", "proteins": 441, "proteomes": 439, "short_name": "DUF2584", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10763", "structures": 1, "taxa": 614, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae. All proteins are annotated as YaaI precursor however currently no function is known.", "domain_architectures": 5, "interpro_id": "IPR020240", "known_evidence_count": null, "matches": 460, "name": "Domain of unknown function (DUF2541)", "partial_evidence_count": null, "pfam_id": "PF10807", "proteins": 441, "proteomes": 367, "short_name": "DUF2541", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10807", "structures": 0, "taxa": 688, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 267, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021343", "known_evidence_count": null, "matches": 441, "name": "Protein of unknown function (DUF2960)", "partial_evidence_count": null, "pfam_id": "PF11173", "proteins": 441, "proteomes": 441, "short_name": "DUF2960", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11173", "structures": 0, "taxa": 576, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 360 amino acids in length. They share global similarity with the Nucleoid-associated protein YejK and are predicted to fold into similar structure.", "domain_architectures": 2, "interpro_id": "IPR025006", "known_evidence_count": null, "matches": 454, "name": "Protein of unknown function (DUF3900)", "partial_evidence_count": null, "pfam_id": "PF13039", "proteins": 441, "proteomes": 421, "short_name": "DUF3900", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13039", "structures": 0, "taxa": 515, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 409, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to adopt Ig-like fold.", "domain_architectures": 5, "interpro_id": "IPR055774", "known_evidence_count": null, "matches": 483, "name": "Domain of unknown function (DUF7350)", "partial_evidence_count": null, "pfam_id": "PF24041", "proteins": 441, "proteomes": 240, "short_name": "DUF7350", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24041", "structures": 0, "taxa": 383, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 304, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal of a group of uncharacterised sequences from bacteria, found associated with [pfam:PF19867] at the C-terminal. This domain may adopt a TolB_N-like fold.", "domain_architectures": 2, "interpro_id": "IPR061664", "known_evidence_count": null, "matches": 441, "name": "Domain of unknown function (DUF8603)", "partial_evidence_count": null, "pfam_id": "PF29981", "proteins": 441, "proteomes": 398, "short_name": "DUF8603", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29981", "structures": 0, "taxa": 618, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide.", "domain_architectures": 2, "interpro_id": "IPR045993", "known_evidence_count": null, "matches": 441, "name": "Domain of unknown function (DUF5949)", "partial_evidence_count": null, "pfam_id": "PF19374", "proteins": 440, "proteomes": 430, "short_name": "DUF5949", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19374", "structures": 0, "taxa": 458, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are predicted to adopt alpha-helical structure. These proteins contain several invariant histidines and aspartates that may have a functional role.", "domain_architectures": 1, "interpro_id": "IPR054268", "known_evidence_count": null, "matches": 440, "name": "Family of unknown function (DUF6999)", "partial_evidence_count": null, "pfam_id": "PF22523", "proteins": 440, "proteomes": 435, "short_name": "DUF6999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22523", "structures": 0, "taxa": 772, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 412, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This entry represents a domain found at the C-terminus of archaebacterial proteins that have an N-terminal radical SAM domain. This domain is structurally similar to the C-terminal domain of the UreE urease accessory protein [pfam:PF05194].", "domain_architectures": 3, "interpro_id": "IPR058374", "known_evidence_count": null, "matches": 440, "name": "Domain of unknown function (DUF8061)", "partial_evidence_count": null, "pfam_id": "PF26257", "proteins": 440, "proteomes": 438, "short_name": "DUF8061", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26257", "structures": 0, "taxa": 742, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 273, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised Proteobacteria proteins.", "domain_architectures": 3, "interpro_id": "IPR009337", "known_evidence_count": null, "matches": 442, "name": "Protein of unknown function (DUF995)", "partial_evidence_count": null, "pfam_id": "PF06191", "proteins": 439, "proteomes": 301, "short_name": "DUF995", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06191", "structures": 0, "taxa": 464, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 287, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of prokaryotic proteins adopt a fold consisting of one alpha-helix and four beta-strands. Their function has not, as yet, been elucidated [[cite:PUB00035388]].", "domain_architectures": 1, "interpro_id": "IPR015066", "known_evidence_count": null, "matches": 439, "name": "Domain of unknown function (DUF1902)", "partial_evidence_count": null, "pfam_id": "PF08972", "proteins": 439, "proteomes": 402, "short_name": "DUF1902", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08972", "structures": 1, "taxa": 946, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is mainly found in uncharacterized proteins around 290 residues in length and is mainly found in various Bacteroides species. It has a curved central beta sheet flanked by helices. Distant homolog analysis showed it has a similarity with GDSL-like Lipase/Acylhydrolase family. The function of this domain is still unknown.", "domain_architectures": 20, "interpro_id": "IPR032616", "known_evidence_count": null, "matches": 442, "name": "Domain of unknown function (DUF4886)", "partial_evidence_count": null, "pfam_id": "PF16227", "proteins": 438, "proteomes": 347, "short_name": "DUF4886", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16227", "structures": 1, "taxa": 632, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacterial proteins, functionally uncharacterised. It is approximately 50-70 amino acids in length and it has the conserved sequence TRExxxxGPF/Y.", "domain_architectures": 3, "interpro_id": "IPR045630", "known_evidence_count": null, "matches": 438, "name": "Domain of unknown function (DUF6316)", "partial_evidence_count": null, "pfam_id": "PF19837", "proteins": 438, "proteomes": 335, "short_name": "DUF6316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19837", "structures": 0, "taxa": 477, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 301, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 69 and 100 amino acids in length. There are two conserved sequence motifs: AALPWSP and RAE.", "domain_architectures": 2, "interpro_id": "IPR045386", "known_evidence_count": null, "matches": 438, "name": "Family of unknown function (DUF6525)", "partial_evidence_count": null, "pfam_id": "PF20135", "proteins": 438, "proteomes": 417, "short_name": "DUF6525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20135", "structures": 0, "taxa": 641, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 270 and 340 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR046558", "known_evidence_count": null, "matches": 652, "name": "Family of unknown function (DUF6712)", "partial_evidence_count": null, "pfam_id": "PF20459", "proteins": 438, "proteomes": 345, "short_name": "DUF6712", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20459", "structures": 0, "taxa": 613, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 413, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. Members are predicted to show an alpha-beta configuration with similarity to the KaiC domain ([pfam:PF06745]).", "domain_architectures": 5, "interpro_id": "IPR055549", "known_evidence_count": null, "matches": 443, "name": "Family of unknown function (DUF7125)", "partial_evidence_count": null, "pfam_id": "PF23442", "proteins": 438, "proteomes": 326, "short_name": "DUF7125", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23442", "structures": 0, "taxa": 551, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 321, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins includes SPy_2034 from Streptococcus pyogenes, which is though to play an important role in the virulence of the bacteria. This protein shows a unique tetrameric organisation composed of four helix-loop- helix motifs [[cite:PUB00101005]].", "domain_architectures": 4, "interpro_id": "IPR025384", "known_evidence_count": null, "matches": 436, "name": "Domain of unknown function (DUF4298)", "partial_evidence_count": null, "pfam_id": "PF14131", "proteins": 436, "proteomes": 414, "short_name": "DUF4298", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14131", "structures": 2, "taxa": 771, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 255, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins.", "domain_architectures": 1, "interpro_id": "IPR015058", "known_evidence_count": null, "matches": 435, "name": "Protein of unknown function (DUF1878)", "partial_evidence_count": null, "pfam_id": "PF08963", "proteins": 435, "proteomes": 419, "short_name": "DUF1878", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08963", "structures": 1, "taxa": 548, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 406, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 7, "interpro_id": "IPR018716", "known_evidence_count": null, "matches": 435, "name": "Uncharacterized protein conserved in archaea (DUF2240)", "partial_evidence_count": null, "pfam_id": "PF09999", "proteins": 435, "proteomes": 435, "short_name": "DUF2240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09999", "structures": 0, "taxa": 736, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 291, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of presumed domains is found in bacteria and archaea. Proteins in this family are typically between 152 and 220 amino acids in length. In some of the proteins this domain is associated with an N-terminal HTH domain, suggesting that they are transcriptional regulators. This suggests that this may be a previously unidentified ligand binding domain.", "domain_architectures": 2, "interpro_id": "IPR043735", "known_evidence_count": null, "matches": 435, "name": "Domain of unknown function (DUF5680)", "partial_evidence_count": null, "pfam_id": "PF18931", "proteins": 435, "proteomes": 422, "short_name": "DUF5680", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18931", "structures": 0, "taxa": 792, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Actinomycetota lineage. It is predicted to adopt a complex alpha/beta structure resembling the shape of 'stalk and head'. Structurally it is similar to the so-called choice-of-anchor G proteins, which are sortase and exosortase targets, and are likely to be found on the cell surface.", "domain_architectures": 56, "interpro_id": "IPR059438", "known_evidence_count": null, "matches": 485, "name": "Domain of unknown function (DUF8394)", "partial_evidence_count": null, "pfam_id": "PF28433", "proteins": 435, "proteomes": 329, "short_name": "DUF8394", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28433", "structures": 0, "taxa": 471, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 290, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 160 residues found in uncharcaterised proteins from Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR061896", "known_evidence_count": null, "matches": 435, "name": "Domain of unknown function (DUF8835)", "partial_evidence_count": null, "pfam_id": "PF31187", "proteins": 435, "proteomes": 336, "short_name": "DUF8835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31187", "structures": 0, "taxa": 675, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 255, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 204 and 480 amino acids in length. There are two completely conserved residues (G and D) that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR025569", "known_evidence_count": null, "matches": 435, "name": "Domain of unknown function (DUF4335)", "partial_evidence_count": null, "pfam_id": "PF14233", "proteins": 434, "proteomes": 238, "short_name": "DUF4335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14233", "structures": 0, "taxa": 659, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 378, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family or archaeal proteins whose function is unknown. They may adopt a dimeric alpha/beta barrel fold.", "domain_architectures": 4, "interpro_id": "IPR055828", "known_evidence_count": null, "matches": 452, "name": "Family of unknown function (DUF7405)", "partial_evidence_count": null, "pfam_id": "PF24152", "proteins": 434, "proteomes": 303, "short_name": "DUF7405", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24152", "structures": 0, "taxa": 522, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 240, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length. There is a conserved KLP sequence motif.", "domain_architectures": 2, "interpro_id": "IPR025097", "known_evidence_count": null, "matches": 433, "name": "Protein of unknown function (DUF4023)", "partial_evidence_count": null, "pfam_id": "PF13215", "proteins": 433, "proteomes": 431, "short_name": "DUF4023", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13215", "structures": 0, "taxa": 509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 298, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 560 and 931 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR022244", "known_evidence_count": null, "matches": 435, "name": "Protein of unknown function (DUF3769)", "partial_evidence_count": null, "pfam_id": "PF12600", "proteins": 432, "proteomes": 378, "short_name": "DUF3769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12600", "structures": 0, "taxa": 1141, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 247, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of no known function is found in Bacilli.", "domain_architectures": 3, "interpro_id": "IPR017263", "known_evidence_count": null, "matches": 440, "name": "Family of unknown function (DUF5342)", "partial_evidence_count": null, "pfam_id": "PF17277", "proteins": 432, "proteomes": 410, "short_name": "DUF5342", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17277", "structures": 0, "taxa": 527, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 101 and 135 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046543", "known_evidence_count": null, "matches": 441, "name": "Family of unknown function (DUF6802)", "partial_evidence_count": null, "pfam_id": "PF20615", "proteins": 432, "proteomes": 424, "short_name": "DUF6802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20615", "structures": 0, "taxa": 545, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as integrase regulator R however this cannot be confirmed. This family of proteins with unknown function appear to be restricted to Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021502", "known_evidence_count": null, "matches": 431, "name": "Protein of unknown function (DUF3158)", "partial_evidence_count": null, "pfam_id": "PF11358", "proteins": 431, "proteomes": 348, "short_name": "DUF3158", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11358", "structures": 0, "taxa": 618, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 369, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in insects. Proteins in this family are typically between 238 and 666 amino acids in length. This domain has been identified as structurally similar to TRAF-like domains ([pfam:PF03145]) [[cite:PUB00152793]].", "domain_architectures": 9, "interpro_id": "IPR031732", "known_evidence_count": null, "matches": 431, "name": "Domain of unknown function (DUF4729)", "partial_evidence_count": null, "pfam_id": "PF15866", "proteins": 430, "proteomes": 149, "short_name": "DUF4729", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15866", "structures": 0, "taxa": 526, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 444 and 485 amino acids in length. There is a conserved TLR sequence motif.", "domain_architectures": 16, "interpro_id": "IPR031949", "known_evidence_count": null, "matches": 517, "name": "Domain of unknown function (DUF4776)", "partial_evidence_count": null, "pfam_id": "PF16003", "proteins": 430, "proteomes": 198, "short_name": "DUF4776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16003", "structures": 0, "taxa": 738, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 168 and 339 amino acids in length. These proteins are likely to be integral membrane proteins.", "domain_architectures": 3, "interpro_id": "IPR043728", "known_evidence_count": null, "matches": 653, "name": "Domain of unknown function (DUF5671)", "partial_evidence_count": null, "pfam_id": "PF18920", "proteins": 430, "proteomes": 425, "short_name": "DUF5671", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18920", "structures": 0, "taxa": 758, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of short proteins is functionally uncharacterised.", "domain_architectures": 3, "interpro_id": "IPR014964", "known_evidence_count": null, "matches": 429, "name": "Domain of unknown function (DUF1830)", "partial_evidence_count": null, "pfam_id": "PF08865", "proteins": 429, "proteomes": 239, "short_name": "DUF1830", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08865", "structures": 0, "taxa": 652, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 275, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently no function is known.", "domain_architectures": 2, "interpro_id": "IPR021493", "known_evidence_count": null, "matches": 430, "name": "Protein of unknown function (DUF3147)", "partial_evidence_count": null, "pfam_id": "PF11345", "proteins": 429, "proteomes": 228, "short_name": "DUF3147", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11345", "structures": 0, "taxa": 407, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 374, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 251 and 457 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR017801", "known_evidence_count": null, "matches": 436, "name": "Protein of unknown function (DUF3738)", "partial_evidence_count": null, "pfam_id": "PF12543", "proteins": 429, "proteomes": 157, "short_name": "DUF3738", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12543", "structures": 0, "taxa": 285, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 3, "interpro_id": "IPR031796", "known_evidence_count": null, "matches": 431, "name": "Domain of unknown function (DUF5076)", "partial_evidence_count": null, "pfam_id": "PF16826", "proteins": 429, "proteomes": 419, "short_name": "DUF5076", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16826", "structures": 1, "taxa": 655, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001807) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the totopotensamide A biosynthetic gene cluster from Streptomyces pactum [[cite:PUB00099468]]. This family appears to be predominantly present in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR045935", "known_evidence_count": null, "matches": 429, "name": "Family of unknown function (DUF6355)", "partial_evidence_count": null, "pfam_id": "PF19882", "proteins": 429, "proteomes": 312, "short_name": "DUF6355", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19882", "structures": 0, "taxa": 420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represent the domain of unknown function found in Drosophila. According to structure predictions, it may adopt fybronectin type I module (FN1) fold.", "domain_architectures": 18, "interpro_id": "IPR057681", "known_evidence_count": null, "matches": 433, "name": "Domain of unknown function (DUF7921)", "partial_evidence_count": null, "pfam_id": "PF25537", "proteins": 429, "proteomes": 255, "short_name": "DUF7921", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25537", "structures": 0, "taxa": 961, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 410, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of proteins from halobacteria. It has several W and R conserved residues. This domain is predicted to show an alpha-beta configuration.", "domain_architectures": 1, "interpro_id": "IPR055548", "known_evidence_count": null, "matches": 428, "name": "Domain of unknown function (DUF7124)", "partial_evidence_count": null, "pfam_id": "PF23439", "proteins": 428, "proteomes": 282, "short_name": "DUF7124", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23439", "structures": 0, "taxa": 447, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 379, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from animals. It is predicted to adopt a mainly alpha-helical configuration.", "domain_architectures": 19, "interpro_id": "IPR056711", "known_evidence_count": null, "matches": 455, "name": "Domain of unknown function (DUF7809)", "partial_evidence_count": null, "pfam_id": "PF25100", "proteins": 428, "proteomes": 11, "short_name": "DUF7809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25100", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 354, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from animals and plants. It is predicted to adopt an unique complex alpha/beta structure.", "domain_architectures": 19, "interpro_id": "IPR057208", "known_evidence_count": null, "matches": 431, "name": "Domain of unknown function (DUF7886)", "partial_evidence_count": null, "pfam_id": "PF25377", "proteins": 428, "proteomes": 362, "short_name": "DUF7886", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25377", "structures": 0, "taxa": 1237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 295, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to adopt an unique complex alpha/ beta structure. IT contains a number of conserved negatively charged residues that may be essential for function.", "domain_architectures": 5, "interpro_id": "IPR059269", "known_evidence_count": null, "matches": 435, "name": "Domain of unknown function (DUF8225)", "partial_evidence_count": null, "pfam_id": "PF26676", "proteins": 428, "proteomes": 400, "short_name": "DUF8225", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26676", "structures": 0, "taxa": 987, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 346, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins containing a ferredoxin domain, has no known function.", "domain_architectures": 2, "interpro_id": "IPR019224", "known_evidence_count": null, "matches": 427, "name": "Uncharacterized protein containing a ferredoxin domain (DUF2148)", "partial_evidence_count": null, "pfam_id": "PF09918", "proteins": 427, "proteomes": 386, "short_name": "DUF2148", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09918", "structures": 0, "taxa": 874, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 293, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in the conserved fungal proteins SPP41 (suppressor of PrP4, there are four members, 1 to 4). In S. cerevisiae it is conserved towards the C-terminus of HMG domains. The function is not known. However, it has been shown that SPP41 is involved in negative regulation of expression of spliceosome components PRP4 and PRP3 and that it relocalizes to the cytosol in response to hypoxia [[cite:PUB00098543],[cite:PUB00098542]].", "domain_architectures": 10, "interpro_id": "IPR021386", "known_evidence_count": null, "matches": 432, "name": "SPP41, DUF3020", "partial_evidence_count": null, "pfam_id": "PF11223", "proteins": 427, "proteomes": 253, "short_name": "DUF3020", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11223", "structures": 0, "taxa": 580, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, mainly Actinobacteria and Firmicutes. Many members are thought to contain TPR regions There are two conserved motifs, AxRL and LxxY.", "domain_architectures": 6, "interpro_id": "IPR046491", "known_evidence_count": null, "matches": 427, "name": "Family of unknown function (DUF6584)", "partial_evidence_count": null, "pfam_id": "PF20225", "proteins": 427, "proteomes": 405, "short_name": "DUF6584", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20225", "structures": 0, "taxa": 638, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is found in uncharacterised sequences from Plasmodium falciparum and similar sequences from Apicomplexa. This domain may adopt a TNF receptor-like fold.", "domain_architectures": 112, "interpro_id": "IPR056047", "known_evidence_count": null, "matches": 428, "name": "Domain of unknown function (DUF7630)", "partial_evidence_count": null, "pfam_id": "PF24633", "proteins": 427, "proteomes": 99, "short_name": "DUF7630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24633", "structures": 0, "taxa": 313, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 80 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR025369", "known_evidence_count": null, "matches": 430, "name": "Domain of unknown function (DUF4274)", "partial_evidence_count": null, "pfam_id": "PF14096", "proteins": 426, "proteomes": 404, "short_name": "DUF4274", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14096", "structures": 0, "taxa": 806, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterized proteins found in phage and bacterial species, particularly in the Gammaproteobacteria class. Members of this family are typically short proteins, ranging from 32 to 85 amino acids in length. Many members are predicted to contain disordered regions and AlphaFold predictions show a non-globular structure.", "domain_architectures": 2, "interpro_id": "IPR055654", "known_evidence_count": null, "matches": 426, "name": "Family of unknown function (DUF7230)", "partial_evidence_count": null, "pfam_id": "PF23876", "proteins": 426, "proteomes": 425, "short_name": "DUF7230", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23876", "structures": 0, "taxa": 907, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as YpbF however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR020210", "known_evidence_count": null, "matches": 425, "name": "Protein of unknown function (DUF2663)", "partial_evidence_count": null, "pfam_id": "PF10864", "proteins": 425, "proteomes": 424, "short_name": "DUF2663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10864", "structures": 0, "taxa": 549, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 382, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of unknown function.", "domain_architectures": 7, "interpro_id": "IPR035185", "known_evidence_count": null, "matches": 430, "name": "Family of unknown function (DUF5305)", "partial_evidence_count": null, "pfam_id": "PF17231", "proteins": 425, "proteomes": 345, "short_name": "DUF5305", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17231", "structures": 0, "taxa": 661, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 366, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised insect proteins mainly from clade Diptera. It is predicted to fold into a four helical bundle which shares detectable similarity to Marvel-like domains. Some proteins contain two copies of this domain. It is likely to be associated with membrane.", "domain_architectures": 4, "interpro_id": "IPR056677", "known_evidence_count": null, "matches": 429, "name": "Domain of unknown function (DUF7775)", "partial_evidence_count": null, "pfam_id": "PF24985", "proteins": 425, "proteomes": 172, "short_name": "DUF7775", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24985", "structures": 0, "taxa": 678, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 333, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are approximately 190 amino acids in length.", "domain_architectures": 7, "interpro_id": "", "known_evidence_count": null, "matches": 426, "name": "Domain of unknown function (DUF4675)", "partial_evidence_count": null, "pfam_id": "PF15720", "proteins": 424, "proteomes": 324, "short_name": "DUF4675", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15720", "structures": 0, "taxa": 1147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 292, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 80 amino acids in length. There is a conserved sequence motif SG.", "domain_architectures": 5, "interpro_id": "IPR045965", "known_evidence_count": null, "matches": 424, "name": "Domain of unknown function (DUF6385)", "partial_evidence_count": null, "pfam_id": "PF19912", "proteins": 424, "proteomes": 239, "short_name": "DUF6385", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19912", "structures": 0, "taxa": 440, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found, and is approximately 160 amino acids in length. The domain is found in sequences that belong to the Thif family and is in association with [pfam:PF00899], located at its N-terminal.", "domain_architectures": 2, "interpro_id": "IPR046741", "known_evidence_count": null, "matches": 424, "name": "Domain of unknown function (DUF6791)", "partial_evidence_count": null, "pfam_id": "PF20590", "proteins": 424, "proteomes": 409, "short_name": "DUF6791", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20590", "structures": 0, "taxa": 941, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 398, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of a group of archaeal sequences that contain [pfam:PF01978] at the N-terminal. It is predicted to adopt a Phospholipase D-like fold.", "domain_architectures": 3, "interpro_id": "IPR055859", "known_evidence_count": null, "matches": 424, "name": "Domain of unknown function (DUF7436)", "partial_evidence_count": null, "pfam_id": "PF24217", "proteins": 424, "proteomes": 312, "short_name": "DUF7436", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24217", "structures": 0, "taxa": 534, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillaceae bacteria.", "domain_architectures": 1, "interpro_id": "IPR019668", "known_evidence_count": null, "matches": 423, "name": "Protein of unknown function (DUF2524)", "partial_evidence_count": null, "pfam_id": "PF10732", "proteins": 423, "proteomes": 404, "short_name": "DUF2524", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10732", "structures": 0, "taxa": 544, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 272, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in bacterial proteins, functionally uncharacterised. Proteins in this family are typically between 664 and 1043 amino acids in length. Some members of this family are thought to be pectin/pectate lyases.", "domain_architectures": 6, "interpro_id": "IPR046265", "known_evidence_count": null, "matches": 423, "name": "Domain of unknown function (DUF6298)", "partial_evidence_count": null, "pfam_id": "PF19815", "proteins": 423, "proteomes": 400, "short_name": "DUF6298", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19815", "structures": 0, "taxa": 687, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 194, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial and phage proteins of around 230 residues in length. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR009785", "known_evidence_count": null, "matches": 422, "name": "Protein of unknown function (DUF1351)", "partial_evidence_count": null, "pfam_id": "PF07083", "proteins": 422, "proteomes": 385, "short_name": "DUF1351", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07083", "structures": 0, "taxa": 823, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 353, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. It is predicted to form a globular structure consisting of alpha-helices. It contains a set of conserved cysteine residues which are predicted to form disulfide bridges.", "domain_architectures": 12, "interpro_id": "IPR056637", "known_evidence_count": null, "matches": 427, "name": "Domain of unknown function (DUF7735)", "partial_evidence_count": null, "pfam_id": "PF24870", "proteins": 422, "proteomes": 254, "short_name": "DUF7735", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24870", "structures": 0, "taxa": 530, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 267, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 3, "interpro_id": "IPR019284", "known_evidence_count": null, "matches": 421, "name": "Predicted membrane protein (DUF2335)", "partial_evidence_count": null, "pfam_id": "PF10097", "proteins": 421, "proteomes": 408, "short_name": "DUF2335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10097", "structures": 0, "taxa": 1036, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus spp. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 1, "interpro_id": "IPR019686", "known_evidence_count": null, "matches": 421, "name": "Protein of unknown function (DUF2536)", "partial_evidence_count": null, "pfam_id": "PF10750", "proteins": 421, "proteomes": 419, "short_name": "DUF2536", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10750", "structures": 0, "taxa": 513, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 379, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 36, "interpro_id": "IPR021704", "known_evidence_count": null, "matches": 586, "name": "Protein of unknown function (DUF3287)", "partial_evidence_count": null, "pfam_id": "PF11690", "proteins": 421, "proteomes": 8, "short_name": "DUF3287", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11690", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of unknown function specific to Bacillus.", "domain_architectures": 2, "interpro_id": "IPR019667", "known_evidence_count": null, "matches": 420, "name": "Protein of unknown function (DUF2521)", "partial_evidence_count": null, "pfam_id": "PF10730", "proteins": 420, "proteomes": 417, "short_name": "DUF2521", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10730", "structures": 0, "taxa": 558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 357, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, eukaryotes and viruses, and is approximately 50 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR031942", "known_evidence_count": null, "matches": 537, "name": "Domain of unknown function (DUF4774)", "partial_evidence_count": null, "pfam_id": "PF15999", "proteins": 420, "proteomes": 177, "short_name": "DUF4774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15999", "structures": 0, "taxa": 714, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain that is found in tandem repeats in Bacteroidota bacterial surface proteins, commonly associated with PA14 adhesive domain. This domain is composed of a beta hairpin followed by an alpha helix. There is a conserved pair of cysteine residues in each domain that form a disulphide bridge that presumably stabilises this small domain.", "domain_architectures": 39, "interpro_id": "IPR046020", "known_evidence_count": null, "matches": 838, "name": "Family of unknown function (DUF5977)", "partial_evidence_count": null, "pfam_id": "PF19404", "proteins": 420, "proteomes": 255, "short_name": "DUF5977", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19404", "structures": 0, "taxa": 376, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found in gamma- and beta-proteobacteria. A member of this family, STM2901, is a putative cytoplasmic protein from many but not all forms of SPI-1 (Salmonella Pathogenicity Island 1).", "domain_architectures": 7, "interpro_id": "IPR058522", "known_evidence_count": null, "matches": 420, "name": "Family of unknown function (DUF8209)", "partial_evidence_count": null, "pfam_id": "PF26636", "proteins": 420, "proteomes": 263, "short_name": "DUF8209", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26636", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 224, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of at least 9 paralogs in Myxococcus xanthus, a member of the Deltaproteobacteria. One appears truncated toward the N-terminus; the others are predicted lipoproteins. The function is unknown.", "domain_architectures": 12, "interpro_id": "IPR011755", "known_evidence_count": null, "matches": 419, "name": "Predicted lipoprotein of unknown function (DUF2380)", "partial_evidence_count": null, "pfam_id": "PF09533", "proteins": 419, "proteomes": 77, "short_name": "DUF2380", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09533", "structures": 0, "taxa": 225, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 14, "interpro_id": "IPR033427", "known_evidence_count": null, "matches": 420, "name": "Domain of unknown function (DUF5123)", "partial_evidence_count": null, "pfam_id": "PF17161", "proteins": 419, "proteomes": 338, "short_name": "DUF5123", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17161", "structures": 0, "taxa": 509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 254, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised proteins from Proteobacteria. This domain is approximately 80 amino acids in length and exhibits overlaps with [pfam:PF04717], which suggests that it has an OB fold and, thus, it belongs to the same clan. Many proteins containing this domain are related to the Type VI secretion system and to Phage-related baseplate proteins.", "domain_architectures": 2, "interpro_id": "IPR045506", "known_evidence_count": null, "matches": 419, "name": "Domain of unknown function (DUF6484)", "partial_evidence_count": null, "pfam_id": "PF20093", "proteins": 419, "proteomes": 347, "short_name": "DUF6484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20093", "structures": 0, "taxa": 625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 267, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins appear to come from the Trb operon however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR024475", "known_evidence_count": null, "matches": 418, "name": "Protein of unknown function (DUF2749)", "partial_evidence_count": null, "pfam_id": "PF10907", "proteins": 418, "proteomes": 178, "short_name": "DUF2749", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10907", "structures": 0, "taxa": 280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 398, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 2, "interpro_id": "IPR043900", "known_evidence_count": null, "matches": 419, "name": "Family of unknown function (DUF5788)", "partial_evidence_count": null, "pfam_id": "PF19101", "proteins": 418, "proteomes": 316, "short_name": "DUF5788", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19101", "structures": 0, "taxa": 515, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in related bacterial proteins. It is predicted to adopt an alpha/beta globular structure and shares significant sequence and structural similarity to members of PD-(D/E)XK nuclease superfamily, in particular, BpuSI N-terminal nuclease domain ([pfam:PF15516]).", "domain_architectures": 17, "interpro_id": "IPR055573", "known_evidence_count": null, "matches": 421, "name": "Domain of unknown function (DUF7149)", "partial_evidence_count": null, "pfam_id": "PF23653", "proteins": 418, "proteomes": 357, "short_name": "DUF7149", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23653", "structures": 0, "taxa": 724, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 5, "interpro_id": "IPR021216", "known_evidence_count": null, "matches": 429, "name": "Protein of unknown function (DUF2722)", "partial_evidence_count": null, "pfam_id": "PF10846", "proteins": 417, "proteomes": 347, "short_name": "DUF2722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10846", "structures": 0, "taxa": 760, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC00001735) is described by MIBiG as an example of the following biosynthetic class, other. This family includes a protein from the pentostatine biosynthetic gene cluster from Streptomyces antibioticus and appears to be predominantly found in Streptomyces [[cite:PUB00098953]].", "domain_architectures": 3, "interpro_id": "IPR045729", "known_evidence_count": null, "matches": 417, "name": "Family of unknown function (DUF6083)", "partial_evidence_count": null, "pfam_id": "PF19561", "proteins": 417, "proteomes": 332, "short_name": "DUF6083", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19561", "structures": 0, "taxa": 402, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 315, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function mostly found in arthropods. This domain may adopt a three helical bundle fold. These sequences might be related to reverse transcriptase polymerases.", "domain_architectures": 61, "interpro_id": "IPR055475", "known_evidence_count": null, "matches": 420, "name": "Domain of unknown function (DUF7047)", "partial_evidence_count": null, "pfam_id": "PF23088", "proteins": 417, "proteomes": 28, "short_name": "DUF7047", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23088", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 238, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 452 to 532 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR021801", "known_evidence_count": null, "matches": 420, "name": "Protein of unknown function (DUF3370)", "partial_evidence_count": null, "pfam_id": "PF11850", "proteins": 416, "proteomes": 233, "short_name": "DUF3370", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11850", "structures": 0, "taxa": 649, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 324, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 15, "interpro_id": "IPR022601", "known_evidence_count": null, "matches": 450, "name": "Protein of unknown function (DUF3160)", "partial_evidence_count": null, "pfam_id": "PF11369", "proteins": 415, "proteomes": 314, "short_name": "DUF3160", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11369", "structures": 0, "taxa": 829, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 244, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001055) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the yersiniabactin biosynthetic gene cluster from Escherichia coli [[cite:PUB00098903]]. This family appears to be predominantly found in Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR045644", "known_evidence_count": null, "matches": 415, "name": "Family of unknown function (DUF6404)", "partial_evidence_count": null, "pfam_id": "PF19942", "proteins": 415, "proteomes": 357, "short_name": "DUF6404", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19942", "structures": 0, "taxa": 593, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 300, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found at the C-terminal of [pfam:PF16314] and it may have an alpha-helical fold.", "domain_architectures": 2, "interpro_id": "IPR049208", "known_evidence_count": null, "matches": 415, "name": "Domain of unknown function (DUF6819)", "partial_evidence_count": null, "pfam_id": "PF20683", "proteins": 415, "proteomes": 410, "short_name": "DUF6819", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20683", "structures": 0, "taxa": 709, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR022721", "known_evidence_count": null, "matches": 414, "name": "Protein of unknown function (DUF3561)", "partial_evidence_count": null, "pfam_id": "PF12084", "proteins": 414, "proteomes": 413, "short_name": "DUF3561", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12084", "structures": 0, "taxa": 575, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000026) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the avilamycin A biosynthetic gene cluster from Streptomyces viridochromogenes Tue57 and appears to be predominantly found in bacteria [[cite:PUB00099435]].", "domain_architectures": 2, "interpro_id": "IPR046042", "known_evidence_count": null, "matches": 414, "name": "Family of unknown function (DUF6000)", "partial_evidence_count": null, "pfam_id": "PF19463", "proteins": 414, "proteomes": 382, "short_name": "DUF6000", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19463", "structures": 0, "taxa": 598, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 277, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in bacteria. Proteins in this family are typically between 237 and 249 amino acids in length. They contain a central predicted transmembrane helix.", "domain_architectures": 1, "interpro_id": "IPR045707", "known_evidence_count": null, "matches": 414, "name": "Family of unknown function (DUF6063)", "partial_evidence_count": null, "pfam_id": "PF19539", "proteins": 414, "proteomes": 389, "short_name": "DUF6063", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19539", "structures": 0, "taxa": 727, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 241, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in Firmicutes. Might contain multiple trans-membrane sequences.", "domain_architectures": 1, "interpro_id": "IPR035167", "known_evidence_count": null, "matches": 413, "name": "Family of unknown function (DUF5316)", "partial_evidence_count": null, "pfam_id": "PF17247", "proteins": 413, "proteomes": 379, "short_name": "DUF5316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17247", "structures": 0, "taxa": 554, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteria. Most of the family members are predicted to have 2 trans-membrane regions.", "domain_architectures": 3, "interpro_id": "IPR035287", "known_evidence_count": null, "matches": 413, "name": "Family of unknown function (DUF5362)", "partial_evidence_count": null, "pfam_id": "PF17319", "proteins": 413, "proteomes": 384, "short_name": "DUF5362", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17319", "structures": 0, "taxa": 769, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 296, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 222 and 245 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046121", "known_evidence_count": null, "matches": 413, "name": "Family of unknown function (DUF6118)", "partial_evidence_count": null, "pfam_id": "PF19613", "proteins": 413, "proteomes": 276, "short_name": "DUF6118", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19613", "structures": 0, "taxa": 483, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised eukaryotic proteins. It shares detectable similarity to the Thioredoxin-like SNTX domain ([pfam:PF18078]) and it is predicted to adopt similar structure.", "domain_architectures": 33, "interpro_id": "IPR056073", "known_evidence_count": null, "matches": 419, "name": "Domain of unknown function (DUF7656)", "partial_evidence_count": null, "pfam_id": "PF24676", "proteins": 413, "proteomes": 259, "short_name": "DUF7656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24676", "structures": 0, "taxa": 675, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This uncharacterised family of proteins are principally found in cyanobacteria.", "domain_architectures": 8, "interpro_id": "IPR014954", "known_evidence_count": null, "matches": 413, "name": "Domain of unknown function (DUF1825)", "partial_evidence_count": null, "pfam_id": "PF08855", "proteins": 412, "proteomes": 365, "short_name": "DUF1825", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08855", "structures": 0, "taxa": 1026, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR020126", "known_evidence_count": null, "matches": 412, "name": "Protein of unknown function (DUF2732)", "partial_evidence_count": null, "pfam_id": "PF10809", "proteins": 412, "proteomes": 322, "short_name": "DUF2732", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10809", "structures": 0, "taxa": 504, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 384, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR055712", "known_evidence_count": null, "matches": 412, "name": "Family of unknown function (DUF7288)", "partial_evidence_count": null, "pfam_id": "PF23959", "proteins": 412, "proteomes": 334, "short_name": "DUF7288", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23959", "structures": 0, "taxa": 538, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 391, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are often found in genomic contexts with a ThiS family protein suggesting they may functionally interact. These proteins contain a highly conserved histidine towards the C-terminus that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR058361", "known_evidence_count": null, "matches": 412, "name": "Domain of unknown function (DUF8048)", "partial_evidence_count": null, "pfam_id": "PF26222", "proteins": 412, "proteomes": 246, "short_name": "DUF8048", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26222", "structures": 0, "taxa": 382, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "family of short proteins of bacterial proteins of phage origin, exemplified by protein SPBc2p013 from Bacillus phage SPBc2, found in various Bacillus and Pseudomonas species. Structure show unexpected structural similarity to greek key beta barrels from the E-set domain, especially to domains involved in carbohydrate and protein- protein binding. However functional consequences of this similarity are not confirmed.", "domain_architectures": 2, "interpro_id": "IPR032624", "known_evidence_count": null, "matches": 411, "name": "Domain of unknown function (DUF4879)", "partial_evidence_count": null, "pfam_id": "PF16219", "proteins": 411, "proteomes": 371, "short_name": "DUF4879", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16219", "structures": 1, "taxa": 635, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 295, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A C-terminal domain in a large family of (predicted) secreted proteins with unknown functions from human gut bacteroides", "domain_architectures": 5, "interpro_id": "IPR027824", "known_evidence_count": null, "matches": 410, "name": "Domain of unknown function (DUF4469) with IG-like fold", "partial_evidence_count": null, "pfam_id": "PF14734", "proteins": 410, "proteomes": 130, "short_name": "DUF4469", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14734", "structures": 1, "taxa": 265, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function mainly found in bacteria.", "domain_architectures": 30, "interpro_id": "IPR043780", "known_evidence_count": null, "matches": 410, "name": "Family of unknown function (DUF5722)", "partial_evidence_count": null, "pfam_id": "PF18989", "proteins": 410, "proteomes": 310, "short_name": "DUF5722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18989", "structures": 0, "taxa": 646, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in Firmicute bacteria. Proteins in this family are typically between 88 and 109 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046092", "known_evidence_count": null, "matches": 410, "name": "Family of unknown function (DUF6110)", "partial_evidence_count": null, "pfam_id": "PF19605", "proteins": 410, "proteomes": 400, "short_name": "DUF6110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19605", "structures": 0, "taxa": 714, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 228 and 260 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046505", "known_evidence_count": null, "matches": 411, "name": "Family of unknown function (DUF6683)", "partial_evidence_count": null, "pfam_id": "PF20388", "proteins": 410, "proteomes": 265, "short_name": "DUF6683", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20388", "structures": 0, "taxa": 519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 225, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised ORFs found in Bacteriophage and Lactococcus lactis.", "domain_architectures": 2, "interpro_id": "IPR008489", "known_evidence_count": null, "matches": 409, "name": "Domain of unknown function (DUF771)", "partial_evidence_count": null, "pfam_id": "PF05595", "proteins": 409, "proteomes": 357, "short_name": "DUF771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05595", "structures": 0, "taxa": 642, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. These proteins are enriched with hydrophobic residues and it is quite likely to be associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR053803", "known_evidence_count": null, "matches": 409, "name": "Family of unknown function (DUF6949)", "partial_evidence_count": null, "pfam_id": "PF22258", "proteins": 409, "proteomes": 409, "short_name": "DUF6949", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22258", "structures": 0, "taxa": 536, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is largely made up of uncharacterised proteins from the Ciliophora. The function is not known.", "domain_architectures": 4, "interpro_id": "IPR028008", "known_evidence_count": null, "matches": 412, "name": "Domain of unknown function (DUF4441)", "partial_evidence_count": null, "pfam_id": "PF14536", "proteins": 408, "proteomes": 10, "short_name": "DUF4441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14536", "structures": 1, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 363, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordates. This entry represents a C-terminal fibronectin type III domain.", "domain_architectures": 2, "interpro_id": "IPR048317", "known_evidence_count": null, "matches": 408, "name": "Family of unknown function (DUF5581) Fn3-like domain", "partial_evidence_count": null, "pfam_id": "PF17744", "proteins": 408, "proteomes": 373, "short_name": "DUF5581", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17744", "structures": 0, "taxa": 1247, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 332, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 104 and 215 amino acids in length. There are two conserved sequence motifs: GDRTIDG and VVANF.", "domain_architectures": 5, "interpro_id": "IPR046164", "known_evidence_count": null, "matches": 408, "name": "Family of unknown function (DUF6166)", "partial_evidence_count": null, "pfam_id": "PF19663", "proteins": 408, "proteomes": 287, "short_name": "DUF6166", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19663", "structures": 0, "taxa": 653, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, mainly found in bacteria and eukaryotes, is functionally uncharacterised. This domain is approximately 100 amino acids in length and, based on structure prediction and overlaps with other families, belongs to the transthyretin superfamily. It is likely to have a seven stranded beta sandwich fold.", "domain_architectures": 3, "interpro_id": "IPR046474", "known_evidence_count": null, "matches": 408, "name": "Domain of unknown function (DUF6795)", "partial_evidence_count": null, "pfam_id": "PF20598", "proteins": 408, "proteomes": 223, "short_name": "DUF6795", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20598", "structures": 0, "taxa": 427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised domains found in a variety of phage and bacterial genomes. Structure prediction suggests the domain is composed of a small beta sheet of three strands and an alpha helix. There is some evidence from prediction that these domains might form a dimeric arrangement.", "domain_architectures": 3, "interpro_id": "IPR055760", "known_evidence_count": null, "matches": 408, "name": "Domain of unknown function (DUF7336)", "partial_evidence_count": null, "pfam_id": "PF24024", "proteins": 408, "proteomes": 360, "short_name": "DUF7336", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24024", "structures": 0, "taxa": 873, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of functionally uncharacterised bacterial sequences. This domain is found associated with a GIY-YIG domain at the N-terminal or an endonuclease domain.", "domain_architectures": 6, "interpro_id": "IPR061667", "known_evidence_count": null, "matches": 408, "name": "Domain of unknown function (DUF8606)", "partial_evidence_count": null, "pfam_id": "PF30087", "proteins": 408, "proteomes": 400, "short_name": "DUF8606", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30087", "structures": 0, "taxa": 983, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 386, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of Archaeal 7-TM proteins. There are 6 closely assembled TM-regions at the N-terminus followed by a long intracellular, from residues 220-590, highly conserved region, of unknown function, terminating with one more TM-region. The short 25 residue section between TMs 5 and 6 might lie on the outer surface of the membrane and be acting as a receptor (from TMHMM).", "domain_architectures": 3, "interpro_id": "IPR019204", "known_evidence_count": null, "matches": 430, "name": "Predicted membrane protein (DUF2070)", "partial_evidence_count": null, "pfam_id": "PF09843", "proteins": 407, "proteomes": 397, "short_name": "DUF2070", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09843", "structures": 0, "taxa": 735, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 143 and 1871 amino acids in length. The human member of this family is C6orf183.", "domain_architectures": 25, "interpro_id": "IPR029376", "known_evidence_count": null, "matches": 413, "name": "Domain of unknown function (DUF4549)", "partial_evidence_count": null, "pfam_id": "PF15082", "proteins": 407, "proteomes": 329, "short_name": "DUF4549", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15082", "structures": 0, "taxa": 1332, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 388 and 411 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045941", "known_evidence_count": null, "matches": 417, "name": "Family of unknown function (DUF6361)", "partial_evidence_count": null, "pfam_id": "PF19888", "proteins": 407, "proteomes": 396, "short_name": "DUF6361", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19888", "structures": 0, "taxa": 960, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 67 and 240 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR031696", "known_evidence_count": null, "matches": 444, "name": "Domain of unknown function (DUF4719)", "partial_evidence_count": null, "pfam_id": "PF15843", "proteins": 406, "proteomes": 308, "short_name": "DUF4719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15843", "structures": 0, "taxa": 1069, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and it is functionally uncharacterised. Proteins in this family are approximately 110 amino acids in length. Some of the members included in this family are thought to be glutaminyl-tRNA synthetases. There are some conserved sequence motifs: CGxC, YFVD/EG and GDAH.", "domain_architectures": 1, "interpro_id": "IPR045950", "known_evidence_count": null, "matches": 406, "name": "Family of unknown function (DUF6370)", "partial_evidence_count": null, "pfam_id": "PF19897", "proteins": 406, "proteomes": 402, "short_name": "DUF6370", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19897", "structures": 0, "taxa": 512, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 380, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of a group of archaeal sequences that contain [pfam:PF01978] at the N-terminal. It is predicted to adopt an all-alpha configuration.", "domain_architectures": 6, "interpro_id": "IPR055860", "known_evidence_count": null, "matches": 406, "name": "Family of unknown function (DUF7437)", "partial_evidence_count": null, "pfam_id": "PF24218", "proteins": 406, "proteomes": 192, "short_name": "DUF7437", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24218", "structures": 0, "taxa": 317, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 296, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 180 residues in length and is mainly found in various Parabacteroides and Bacteroides species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032574", "known_evidence_count": null, "matches": 417, "name": "Domain of unknown function (DUF4924)", "partial_evidence_count": null, "pfam_id": "PF16271", "proteins": 405, "proteomes": 404, "short_name": "DUF4924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16271", "structures": 0, "taxa": 650, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 281, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Proteobacteria. It is predicted to adopt an alpha/beta globular structure. It has three highly conserved histidines that are predicted to cluster together in space and are likely involved in metal coordination.", "domain_architectures": 3, "interpro_id": "IPR054242", "known_evidence_count": null, "matches": 406, "name": "Domain of unknown function (DUF6969)", "partial_evidence_count": null, "pfam_id": "PF22308", "proteins": 405, "proteomes": 385, "short_name": "DUF6969", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22308", "structures": 0, "taxa": 725, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a non-compact structure consisting of four highly hydrophobic alpha-helices that could potentially dimerise.", "domain_architectures": 2, "interpro_id": "IPR056066", "known_evidence_count": null, "matches": 405, "name": "Domain of unknown function (DUF7649)", "partial_evidence_count": null, "pfam_id": "PF24661", "proteins": 405, "proteomes": 402, "short_name": "DUF7649", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24661", "structures": 0, "taxa": 582, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 330, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 7, "interpro_id": "IPR040505", "known_evidence_count": null, "matches": 465, "name": "Family of unknown function (DUF5537)", "partial_evidence_count": null, "pfam_id": "PF17690", "proteins": 404, "proteomes": 250, "short_name": "DUF5537", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17690", "structures": 0, "taxa": 974, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 279, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009530", "known_evidence_count": null, "matches": 403, "name": "Protein of unknown function (DUF1149)", "partial_evidence_count": null, "pfam_id": "PF06619", "proteins": 403, "proteomes": 391, "short_name": "DUF1149", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06619", "structures": 2, "taxa": 563, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 253, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021496", "known_evidence_count": null, "matches": 403, "name": "Protein of unknown function (DUF3150)", "partial_evidence_count": null, "pfam_id": "PF11348", "proteins": 403, "proteomes": 303, "short_name": "DUF3150", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11348", "structures": 0, "taxa": 644, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins which are predicted to form a small three helical bundle containing a beta hairpin between helices 1 and 2.", "domain_architectures": 3, "interpro_id": "IPR054238", "known_evidence_count": null, "matches": 403, "name": "Domain of unknown function (DUF6965)", "partial_evidence_count": null, "pfam_id": "PF22292", "proteins": 403, "proteomes": 309, "short_name": "DUF6965", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22292", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 242, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised bacterial protein domains. The structure of these proteins shows some structural similarity to the PePSy domain.", "domain_architectures": 10, "interpro_id": "IPR056640", "known_evidence_count": null, "matches": 414, "name": "Domain of unknown function (DUF7738)", "partial_evidence_count": null, "pfam_id": "PF24880", "proteins": 403, "proteomes": 314, "short_name": "DUF7738", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24880", "structures": 0, "taxa": 599, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 221, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR020323", "known_evidence_count": null, "matches": 405, "name": "Protein of unknown function (DUF2716)", "partial_evidence_count": null, "pfam_id": "PF10898", "proteins": 402, "proteomes": 368, "short_name": "DUF2716", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10898", "structures": 0, "taxa": 640, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 100 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR027932", "known_evidence_count": null, "matches": 404, "name": "Domain of unknown function (DUF4606)", "partial_evidence_count": null, "pfam_id": "PF15379", "proteins": 402, "proteomes": 335, "short_name": "DUF4606", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15379", "structures": 0, "taxa": 1311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 353, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 74 and 92 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR032011", "known_evidence_count": null, "matches": 468, "name": "Domain of unknown function (DUF4794)", "partial_evidence_count": null, "pfam_id": "PF16042", "proteins": 402, "proteomes": 142, "short_name": "DUF4794", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16042", "structures": 0, "taxa": 531, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 238, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain, found in bacteria, is functionally uncharacterised. It is around 50 amino acids in length and contains a conserved GTW sequence motif.", "domain_architectures": 13, "interpro_id": "IPR046254", "known_evidence_count": null, "matches": 405, "name": "Domain of unknown function (DUF6287)", "partial_evidence_count": null, "pfam_id": "PF19804", "proteins": 402, "proteomes": 208, "short_name": "DUF6287", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19804", "structures": 0, "taxa": 327, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 315, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 150 amino acids in length. There are two conserved sequence motifs: MHML and LGKK.", "domain_architectures": 5, "interpro_id": "IPR027898", "known_evidence_count": null, "matches": 406, "name": "Domain of unknown function (DUF4629)", "partial_evidence_count": null, "pfam_id": "PF15442", "proteins": 401, "proteomes": 158, "short_name": "DUF4629", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15442", "structures": 0, "taxa": 550, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A large family of uncharacterized proteins mostly from human gut bacteroides, but also some environmental and water bacteria (Planctomycetes) as well as metagenomic samples Most proteins from this family are secreted or located on the outer surface and may participate in cell-cell interactions or cell-nutrient interactions This function is supported by a solved structure of a Bacteroides ovatus homolog, which adapts a galactose binding (jelly-roll) beta barrel structure", "domain_architectures": 26, "interpro_id": "IPR027828", "known_evidence_count": null, "matches": 451, "name": "Domain of unknown function (DUF4465)", "partial_evidence_count": null, "pfam_id": "PF14717", "proteins": 400, "proteomes": 323, "short_name": "DUF4465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14717", "structures": 7, "taxa": 608, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 374, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function. Studies of the TA0095 gene product indicate that this 96-residue hypothetical protein from Thermoplasma acidophilum is a member of the COG4004 orthologous group of unknown function found in Archaea bacteria. The structure displays an alpha/beta two-layer sandwich architecture formed by three alpha-helices and five beta-strands. Furthermore, structural homologs indicate that the TA0095 structure belongs to the TBP-like fold [[cite:PUB00047999]].", "domain_architectures": 1, "interpro_id": "IPR040713", "known_evidence_count": null, "matches": 400, "name": "Domain of unknown function (DUF5611)", "partial_evidence_count": null, "pfam_id": "PF18446", "proteins": 400, "proteomes": 400, "short_name": "DUF5611", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18446", "structures": 1, "taxa": 674, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 370, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in a group of proteins mainly from animals.", "domain_architectures": 9, "interpro_id": "IPR059336", "known_evidence_count": null, "matches": 408, "name": "Domain of unknown function (DUF8292)", "partial_evidence_count": null, "pfam_id": "PF26941", "proteins": 400, "proteomes": 193, "short_name": "DUF8292", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26941", "structures": 0, "taxa": 673, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members annotate the proteins to be putative lipoproteins however this cannot be confirmed. Currently no function is known for this family of proteins.", "domain_architectures": 1, "interpro_id": "IPR021340", "known_evidence_count": null, "matches": 399, "name": "Protein of unknown function (DUF2957)", "partial_evidence_count": null, "pfam_id": "PF11170", "proteins": 399, "proteomes": 159, "short_name": "DUF2957", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11170", "structures": 0, "taxa": 185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045620", "known_evidence_count": null, "matches": 399, "name": "Family of unknown function (DUF6442)", "partial_evidence_count": null, "pfam_id": "PF20040", "proteins": 399, "proteomes": 324, "short_name": "DUF6442", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20040", "structures": 0, "taxa": 619, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 281, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a set of uncharacterised proteins found in prokaryotes. They share remote similarity to LolA and LolB outer-membrane lipoproteins. Similar to LolA and LolB these proteins are predicted to have a hydrophobic cavity consisting of an unclosed beta-barrel and an alpha-helical lid.", "domain_architectures": 6, "interpro_id": "IPR054213", "known_evidence_count": null, "matches": 399, "name": "Family of unknown function (DUF6920)", "partial_evidence_count": null, "pfam_id": "PF21900", "proteins": 399, "proteomes": 388, "short_name": "DUF6920", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21900", "structures": 0, "taxa": 1015, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 388, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is sometimes found in tandem. This domain is predicted to adopt a globular structure consisting of alpha helices with some similarity to SAM domains.", "domain_architectures": 15, "interpro_id": "IPR056000", "known_evidence_count": null, "matches": 520, "name": "Domain of unknown function (DUF7578)", "partial_evidence_count": null, "pfam_id": "PF24466", "proteins": 399, "proteomes": 9, "short_name": "DUF7578", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24466", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family aligns the C-terminal region from several bacterial proteins of unknown function that may be involved in a theta-type replication mechanism [[cite:PUB00019474],[cite:PUB00099934],[cite:PUB00099935]].", "domain_architectures": 7, "interpro_id": "IPR007489", "known_evidence_count": null, "matches": 398, "name": "Protein of unknown function, DUF536", "partial_evidence_count": null, "pfam_id": "PF04394", "proteins": 398, "proteomes": 318, "short_name": "DUF536", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04394", "structures": 1, "taxa": 534, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 238, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 300 residues in length and is mainly found in various high GC Gram+ bacteria, but also in several pathogenic and non-pathogenic enterobacteria (Salmonella, E. coli). Distant homology analysis suggests this could be a branch of Xylose isomerase-like TIM barrel family, but this prediction is currently not confirmed by experiment", "domain_architectures": 1, "interpro_id": "IPR032344", "known_evidence_count": null, "matches": 398, "name": "Domain of unknown function (DUF4862)", "partial_evidence_count": null, "pfam_id": "PF16154", "proteins": 398, "proteomes": 387, "short_name": "DUF4862", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16154", "structures": 0, "taxa": 629, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The domain is predominantly found in members of the Halobacteria class, including families such as Haloferacaceae and Haloarculaceae. Proteins containing this domain are typically between 90 and 110 amino acids in length. The C-terminus of this domain is predicted by AlphaFold 3 to form a trimeric coiled-coil structure [swissprot:Q5V7B6] (ipTM=0.89 pTM=0.89).", "domain_architectures": 1, "interpro_id": "IPR058469", "known_evidence_count": null, "matches": 398, "name": "Domain of unknown function (DUF8156)", "partial_evidence_count": null, "pfam_id": "PF26485", "proteins": 398, "proteomes": 278, "short_name": "DUF8156", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26485", "structures": 0, "taxa": 509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. It is frequently found in combination with [pfam:PF27162]. This domain share similarity to domains that are members of the Mog1p/PsbP-like superfamily.", "domain_architectures": 7, "interpro_id": "IPR061641", "known_evidence_count": null, "matches": 400, "name": "Domain of unknown function (DUF8580)", "partial_evidence_count": null, "pfam_id": "PF29711", "proteins": 398, "proteomes": 346, "short_name": "DUF8580", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29711", "structures": 0, "taxa": 436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 125 residues found in multi-domain proteins that contain the DUF7408 domain ([pfam:PF24157]). Structural similarity searches identify this as a member of the galactose-binding domain-like superfamily. This family is found in Bacillota, particularly Bacillales (including Paenibacillus and Bacillaceae) and Clostridia, as well as some Chloroflexota. The function of this domain remains to be determined.", "domain_architectures": 8, "interpro_id": "IPR061876", "known_evidence_count": null, "matches": 398, "name": "Domain of unknown function (DUF8815)", "partial_evidence_count": null, "pfam_id": "PF31117", "proteins": 398, "proteomes": 365, "short_name": "DUF8815", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31117", "structures": 0, "taxa": 576, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 231, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR024248", "known_evidence_count": null, "matches": 397, "name": "Protein of unknown function (DUF2695)", "partial_evidence_count": null, "pfam_id": "PF10905", "proteins": 397, "proteomes": 388, "short_name": "DUF2695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10905", "structures": 0, "taxa": 738, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A lipocain-like domain found in functionally uncharacterised bacterial proteins, often as a repeat of two domains. Proteins with this domain are found in a wide range of bacteria and are often annotated as S-layer proteins, but the origin of this annotation is not clear", "domain_architectures": 8, "interpro_id": "IPR032247", "known_evidence_count": null, "matches": 589, "name": "Domain of unknown function (DUF4822)", "partial_evidence_count": null, "pfam_id": "PF16103", "proteins": 397, "proteomes": 365, "short_name": "DUF4822", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16103", "structures": 2, "taxa": 552, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is mostly found in bacteria.", "domain_architectures": 5, "interpro_id": "IPR043756", "known_evidence_count": null, "matches": 420, "name": "Family of unknown function (DUF5702)", "partial_evidence_count": null, "pfam_id": "PF18960", "proteins": 397, "proteomes": 358, "short_name": "DUF5702", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18960", "structures": 0, "taxa": 618, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 354, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal helical domain found in C20orf195 and its homologues found in chordates.", "domain_architectures": 3, "interpro_id": "IPR049231", "known_evidence_count": null, "matches": 397, "name": "Family of unknown function (DUF5581) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20996", "proteins": 397, "proteomes": 362, "short_name": "DUF5581_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20996", "structures": 0, "taxa": 1216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a Bacterial family of unknown function. Family members are predicted to belong to Type VII secretion (T7S) system. There is a conserved YxxxD/E sequence. It is a general secretion signal that is present in all known mycobacterial T7S substrates or substrate complexes [[cite:PUB00099431]].", "domain_architectures": 1, "interpro_id": "IPR046318", "known_evidence_count": null, "matches": 396, "name": "Family of unknown function (DUF5344)", "partial_evidence_count": null, "pfam_id": "PF17279", "proteins": 396, "proteomes": 221, "short_name": "DUF5344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17279", "structures": 0, "taxa": 343, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 2, "interpro_id": "IPR043753", "known_evidence_count": null, "matches": 396, "name": "Family of unknown function (DUF5699)", "partial_evidence_count": null, "pfam_id": "PF18956", "proteins": 396, "proteomes": 259, "short_name": "DUF5699", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18956", "structures": 0, "taxa": 525, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 337, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into array of alpha-helices some of which connected by extended loops.", "domain_architectures": 9, "interpro_id": "IPR059441", "known_evidence_count": null, "matches": 396, "name": "Domain of unknown function (DUF8397)", "partial_evidence_count": null, "pfam_id": "PF28437", "proteins": 396, "proteomes": 71, "short_name": "DUF8397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28437", "structures": 0, "taxa": 211, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 242, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Firmicutes. These proteins appear to be distantly related to HHH domains and are therefore likely to be DNA-binding. Genomic environment-visualisation confirms the likely function as being DNA-binding, as this short protein lies very closely between an integrase and a replication protein (http://www.microbesonline.org/).", "domain_architectures": 2, "interpro_id": "IPR021512", "known_evidence_count": null, "matches": 398, "name": "Domain of unknown function (DUF3173)", "partial_evidence_count": null, "pfam_id": "PF11372", "proteins": 395, "proteomes": 285, "short_name": "DUF3173", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11372", "structures": 0, "taxa": 487, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 359, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region approximately 260 residues long within a number of hypothetical proteins of unknown function that seem to be specific to C. elegans. Note that this family contains a number of conserved cysteine and histidine residues.This family corresponds to the Mirage group of putative transposases and family members are relatively close homologs of Transposase_21 ([pfam:PF02992]) proteins (1).", "domain_architectures": 15, "interpro_id": "IPR009667", "known_evidence_count": null, "matches": 394, "name": "Protein of unknown function (DUF1258)", "partial_evidence_count": null, "pfam_id": "PF06869", "proteins": 394, "proteomes": 68, "short_name": "DUF1258", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06869", "structures": 0, "taxa": 273, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 225, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently there is no known function.", "domain_architectures": 1, "interpro_id": "IPR021509", "known_evidence_count": null, "matches": 394, "name": "Protein of unknown function (DUF3169)", "partial_evidence_count": null, "pfam_id": "PF11368", "proteins": 394, "proteomes": 381, "short_name": "DUF3169", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11368", "structures": 0, "taxa": 596, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. It is found in bacteria and eukaryotes, and is approximately 130 amino acids in length. It is often found in association with [pfam:PF05593] and [pfam:PF03527]. There is a single completely conserved residue D and a highly conserved HTH motif which may be functionally important.", "domain_architectures": 49, "interpro_id": "IPR025479", "known_evidence_count": null, "matches": 399, "name": "Domain of unknown function (DUF4329)", "partial_evidence_count": null, "pfam_id": "PF14220", "proteins": 394, "proteomes": 347, "short_name": "DUF4329", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14220", "structures": 0, "taxa": 727, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of bacterial proteins of unknown function.", "domain_architectures": 5, "interpro_id": "IPR028028", "known_evidence_count": null, "matches": 394, "name": "Domain of unknown function (DUF4450)", "partial_evidence_count": null, "pfam_id": "PF14614", "proteins": 394, "proteomes": 365, "short_name": "DUF4450", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14614", "structures": 0, "taxa": 568, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 231, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001765) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the salecan biosynthetic gene cluster from Agrobacterium tumefaciens and appears to be predominantly found in Rhizobiales [[cite:PUB00098950]].", "domain_architectures": 1, "interpro_id": "IPR045720", "known_evidence_count": null, "matches": 394, "name": "Family of unknown function (DUF6074)", "partial_evidence_count": null, "pfam_id": "PF19551", "proteins": 394, "proteomes": 323, "short_name": "DUF6074", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19551", "structures": 0, "taxa": 445, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in several cell surface proteins, such as extracellular matrix-binding protein ebh [[cite:PUB00014728]]. Some members are involved in antibiotic resistance (e.g [swissprot:Q9RL69] and [swissprot:Q9LCJ9]) [[cite:PUB00014727]] and/or cellular adhesion (e.g. [swissprot:Q931R6]) [[cite:PUB00014728]]. In some proteins it is repeated more than fifteen times, being the most repeated domain in streptococci [[cite:PUB00097824]]. This is a predominantly alpha-helical domain that form a long, thin, fibre-like structure and it has been proposed to function as a stalk that helps the adhesive non-repeat region (NRR) of proteins protrude beyond the cell surface [[cite:PUB00097823],[cite:PUB00065268]].", "domain_architectures": 192, "interpro_id": "IPR011439", "known_evidence_count": null, "matches": 2712, "name": "Domain of Unknown Function (DUF1542)", "partial_evidence_count": null, "pfam_id": "PF07564", "proteins": 393, "proteomes": 153, "short_name": "DUF1542", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07564", "structures": 0, "taxa": 310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus spp.", "domain_architectures": 4, "interpro_id": "IPR020258", "known_evidence_count": null, "matches": 393, "name": "Protein of unknown function (DUF2651)", "partial_evidence_count": null, "pfam_id": "PF10852", "proteins": 393, "proteomes": 331, "short_name": "DUF2651", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10852", "structures": 0, "taxa": 594, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins may be membrane proteins however this cannot be confirmed. Currently there is no known function.", "domain_architectures": 4, "interpro_id": "IPR021632", "known_evidence_count": null, "matches": 396, "name": "Protein of unknown function (DUF3239)", "partial_evidence_count": null, "pfam_id": "PF11580", "proteins": 393, "proteomes": 387, "short_name": "DUF3239", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11580", "structures": 1, "taxa": 600, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 284, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein domain is of unknown function. though putatively involved in DNA mismatch repair. It is associated with [pfam:PF01713].", "domain_architectures": 3, "interpro_id": "IPR018598", "known_evidence_count": null, "matches": 392, "name": "Domain of unknown function (DUF2027)", "partial_evidence_count": null, "pfam_id": "PF09640", "proteins": 392, "proteomes": 392, "short_name": "DUF2027", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09640", "structures": 1, "taxa": 616, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are probably distantly related to uracil-DNA glycosylases and other related DNA glycosylases given their predicted structure.", "domain_architectures": 2, "interpro_id": "IPR054222", "known_evidence_count": null, "matches": 394, "name": "Family of unknown function (DUF6942)", "partial_evidence_count": null, "pfam_id": "PF22098", "proteins": 392, "proteomes": 390, "short_name": "DUF6942", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22098", "structures": 0, "taxa": 545, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 140 amino acids in length. There is a single completely conserved residue Q that may be functionally important.", "domain_architectures": 17, "interpro_id": "IPR031927", "known_evidence_count": null, "matches": 395, "name": "Domain of unknown function (DUF4767)", "partial_evidence_count": null, "pfam_id": "PF15983", "proteins": 391, "proteomes": 275, "short_name": "DUF4767", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15983", "structures": 0, "taxa": 433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are approximately 150 amino acids in length. Probably, this family correspond to lipoproteins.", "domain_architectures": 2, "interpro_id": "IPR045956", "known_evidence_count": null, "matches": 391, "name": "Family of unknown function (DUF6376)", "partial_evidence_count": null, "pfam_id": "PF19903", "proteins": 391, "proteomes": 380, "short_name": "DUF6376", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19903", "structures": 0, "taxa": 495, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 374, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral proteins found in halobacteria.", "domain_architectures": 4, "interpro_id": "IPR058284", "known_evidence_count": null, "matches": 394, "name": "Family of unknown function (DUF7978)", "partial_evidence_count": null, "pfam_id": "PF25933", "proteins": 391, "proteomes": 236, "short_name": "DUF7978", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25933", "structures": 0, "taxa": 379, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 240, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 103 and 114 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR022090", "known_evidence_count": null, "matches": 390, "name": "Protein of unknown function (DUF3634)", "partial_evidence_count": null, "pfam_id": "PF12321", "proteins": 390, "proteomes": 384, "short_name": "DUF3634", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12321", "structures": 0, "taxa": 544, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 281, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are related to HlyIII family [pfam:PF03006] and are predicted to adopt the same structure consisting of seven transmembrane helices. Their predicted structure, suggests that, similarly to HlyIII, they may contain a Zn-binding site, albeit slightly rearranged as only two of the Zn-coordinating residues are in conserved positions.", "domain_architectures": 6, "interpro_id": "IPR054235", "known_evidence_count": null, "matches": 392, "name": "Family of unknown function (DUF6962)", "partial_evidence_count": null, "pfam_id": "PF22285", "proteins": 390, "proteomes": 366, "short_name": "DUF6962", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22285", "structures": 0, "taxa": 769, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins either standalone or in combination with other domains. It is predicted to adopt a globular structure consisting of an antiparallel three-stranded beta-sheet and alpha-helices packed on one side of it.", "domain_architectures": 5, "interpro_id": "IPR056133", "known_evidence_count": null, "matches": 390, "name": "Domain of unknown function (DUF7716)", "partial_evidence_count": null, "pfam_id": "PF24832", "proteins": 390, "proteomes": 335, "short_name": "DUF7716", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24832", "structures": 0, "taxa": 676, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several highly conserved, hypothetical phage proteins of around 200 residues in length. The function of this family is unknown. Some proteins are annotated as IrsA (intracellular response to stress).", "domain_architectures": 3, "interpro_id": "IPR009797", "known_evidence_count": null, "matches": 499, "name": "Protein of unknown function (DUF1367)", "partial_evidence_count": null, "pfam_id": "PF07105", "proteins": 389, "proteomes": 335, "short_name": "DUF1367", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07105", "structures": 0, "taxa": 684, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR018738", "known_evidence_count": null, "matches": 388, "name": "Uncharacterized conserved protein (DUF2280)", "partial_evidence_count": null, "pfam_id": "PF10045", "proteins": 388, "proteomes": 334, "short_name": "DUF2280", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10045", "structures": 0, "taxa": 620, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in hypothetical proteins from Pseudomonas aeruginosa [[cite:PUB00091431]].", "domain_architectures": 2, "interpro_id": "IPR041081", "known_evidence_count": null, "matches": 426, "name": "Family of unknown function (DUF5629)", "partial_evidence_count": null, "pfam_id": "PF18629", "proteins": 388, "proteomes": 387, "short_name": "DUF5629", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18629", "structures": 1, "taxa": 409, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 276, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small bacterial integral membrane protein of unknown function that is composed of two transmembrane helices. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR049220", "known_evidence_count": null, "matches": 388, "name": "Family of unknown function (DUF6868)", "partial_evidence_count": null, "pfam_id": "PF21742", "proteins": 388, "proteomes": 384, "short_name": "DUF6868", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21742", "structures": 0, "taxa": 824, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 203, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR018695", "known_evidence_count": null, "matches": 508, "name": "Uncharacterised protein conserved in bacteria (DUF2194)", "partial_evidence_count": null, "pfam_id": "PF09960", "proteins": 387, "proteomes": 368, "short_name": "DUF2194", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09960", "structures": 1, "taxa": 668, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 219, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000223) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the rabelomycin biosynthetic gene cluster from uncultured bacterium BAC AB649/1850 [[cite:PUB00098876]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 4, "interpro_id": "IPR045773", "known_evidence_count": null, "matches": 389, "name": "Family of unknown function (DUF6226)", "partial_evidence_count": null, "pfam_id": "PF19736", "proteins": 387, "proteomes": 376, "short_name": "DUF6226", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19736", "structures": 0, "taxa": 577, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in a group of uncharacterised proteins. Some members are annotated as related to antimicrobial activity. It contains two highly conserved motifs RGYD and RGDY.", "domain_architectures": 26, "interpro_id": "IPR061873", "known_evidence_count": null, "matches": 393, "name": "Domain of unknown function (DUF8812)", "partial_evidence_count": null, "pfam_id": "PF31111", "proteins": 387, "proteomes": 279, "short_name": "DUF8812", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31111", "structures": 0, "taxa": 640, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins. The structure of a hypothetical protein from Pseudomonas aeruginosa has shown it to adopt an alpha/beta fold, placing it in the Endonuclease superfamily/clan of restriction endonucleases.", "domain_architectures": 2, "interpro_id": "IPR014796", "known_evidence_count": null, "matches": 386, "name": "Putative endonuclease, protein of unknown function (DUF1780)", "partial_evidence_count": null, "pfam_id": "PF08682", "proteins": 386, "proteomes": 382, "short_name": "DUF1780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08682", "structures": 1, "taxa": 471, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 359, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR014518", "known_evidence_count": null, "matches": 386, "name": "Uncharacterized protein conserved in archaea (DUF2150)", "partial_evidence_count": null, "pfam_id": "PF09920", "proteins": 386, "proteomes": 383, "short_name": "DUF2150", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09920", "structures": 0, "taxa": 629, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 101 and 122 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045589", "known_evidence_count": null, "matches": 386, "name": "Family of unknown function (DUF6464)", "partial_evidence_count": null, "pfam_id": "PF20065", "proteins": 386, "proteomes": 214, "short_name": "DUF6464", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20065", "structures": 0, "taxa": 598, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins that have a five fold symmetric alpha/beta propeller fold belonging to the GME (guanidino-group modifying enzymes) superfamily [[cite:PUB00009967],[cite:PUB00151878]].", "domain_architectures": 2, "interpro_id": "IPR049238", "known_evidence_count": null, "matches": 386, "name": "Family of unknown function (DUF6873)", "partial_evidence_count": null, "pfam_id": "PF21778", "proteins": 386, "proteomes": 380, "short_name": "DUF6873", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21778", "structures": 0, "taxa": 690, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found mainly in Gram-positive bacteria. They are predicted to be associated with the membrane and to adopt structure that has topological similarity to the common structural core of Succinate-acetate permease (SatP) superfamily proteins.", "domain_architectures": 6, "interpro_id": "IPR054224", "known_evidence_count": null, "matches": 393, "name": "Family of unknown function (DUF6944)", "partial_evidence_count": null, "pfam_id": "PF22116", "proteins": 386, "proteomes": 283, "short_name": "DUF6944", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22116", "structures": 0, "taxa": 609, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 330, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised metazoan proteins. It is predicted to adopt a globular structure with lipocalin fold. It also contains several highly conserved cysteine residues that are likely involved in the formation of intra-domain disulfide bridges.", "domain_architectures": 19, "interpro_id": "IPR055473", "known_evidence_count": null, "matches": 405, "name": "Domain of unknown function (DUF7045)", "partial_evidence_count": null, "pfam_id": "PF23073", "proteins": 386, "proteomes": 256, "short_name": "DUF7045", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23073", "structures": 0, "taxa": 985, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 234, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in a presumed integral membrane domain is functionally uncharacterised.", "domain_architectures": 8, "interpro_id": "IPR058671", "known_evidence_count": null, "matches": 386, "name": "DUF6311 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF25853", "proteins": 386, "proteomes": 307, "short_name": "DUF6311_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25853", "structures": 0, "taxa": 624, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae. This domain is found in a group of bacterial lipoproteins such as YajI from E.coli and SadB from Salmonella typhimurium. SadB is required for proper surface expression of the autotransporter adhesin SadA [[cite:PUB00086613]].", "domain_architectures": 1, "interpro_id": "IPR021658", "known_evidence_count": null, "matches": 385, "name": "Protein of unknown function (DUF3251)", "partial_evidence_count": null, "pfam_id": "PF11622", "proteins": 385, "proteomes": 384, "short_name": "DUF3251", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11622", "structures": 1, "taxa": 570, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage domains. This domain is found in one to two copies per proteins. It seems likely that the proteins with a single copy of the domain form homodimers.", "domain_architectures": 4, "interpro_id": "IPR055838", "known_evidence_count": null, "matches": 684, "name": "Domain of unknown function (DUF7415)", "partial_evidence_count": null, "pfam_id": "PF24187", "proteins": 385, "proteomes": 226, "short_name": "DUF7415", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24187", "structures": 0, "taxa": 517, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found mainly in Alphaproteobacteria. These are predicted to fold into a alpha/beta structure, composed of a five-stranded antiparallel beta-sheet that curves around a single helix, which partly resemble TATA-box binding protein individual repeats. These proteins contain two pairs of conserved cysteine residues that are predicted to form disulfide bonds suggesting that they may be secreted.", "domain_architectures": 4, "interpro_id": "IPR058513", "known_evidence_count": null, "matches": 385, "name": "Family of unknown function (DUF8200)", "partial_evidence_count": null, "pfam_id": "PF26624", "proteins": 384, "proteomes": 346, "short_name": "DUF8200", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26624", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 200, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is mainly found in Actinobacteria. Proteins in this family are typically between 132 and 185 amino acids in length. There are three conserved motifs, WQ, CCG and GxV.", "domain_architectures": 4, "interpro_id": "IPR046485", "known_evidence_count": null, "matches": 383, "name": "Family of unknown function (DUF6578)", "partial_evidence_count": null, "pfam_id": "PF20218", "proteins": 383, "proteomes": 359, "short_name": "DUF6578", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20218", "structures": 0, "taxa": 527, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 355, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Halobacteria. It contains highly conserved cysteine residues arranged in two CxxC motifs that likely coordinate zinc. The first motif could be more broadly defined as a semi-conserved MWRCxxCGEM sequence motif. This domain is predicted to adopt a zinc ribbon fold with similarity to rubredoxin-like domains.", "domain_architectures": 3, "interpro_id": "IPR055554", "known_evidence_count": null, "matches": 383, "name": "Domain of unknown function (DUF7130)", "partial_evidence_count": null, "pfam_id": "PF23458", "proteins": 383, "proteomes": 247, "short_name": "DUF7130", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23458", "structures": 0, "taxa": 402, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Enterobacterial proteins of around 80 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009950", "known_evidence_count": null, "matches": 382, "name": "Protein of unknown function (DUF1480)", "partial_evidence_count": null, "pfam_id": "PF07351", "proteins": 382, "proteomes": 380, "short_name": "DUF1480", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07351", "structures": 1, "taxa": 520, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000721) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the tobramycin biosynthetic gene cluster from Streptoalloteichus tenebrarius and appears to be predominantly found in Actinobacteria [[cite:PUB00098957]].", "domain_architectures": 3, "interpro_id": "IPR045732", "known_evidence_count": null, "matches": 382, "name": "Family of unknown function (DUF6086)", "partial_evidence_count": null, "pfam_id": "PF19564", "proteins": 382, "proteomes": 356, "short_name": "DUF6086", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19564", "structures": 0, "taxa": 471, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 246, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of proteobacteria proteins of unknown function. This family is unrelated to [pfam:PF03960] which contains a set of transcription factors that are also named YjbD.", "domain_architectures": 1, "interpro_id": "IPR020317", "known_evidence_count": null, "matches": 381, "name": "YjbD family (DUF3811)", "partial_evidence_count": null, "pfam_id": "PF11656", "proteins": 381, "proteomes": 380, "short_name": "DUF3811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11656", "structures": 0, "taxa": 541, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 308, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from plants. It has sequence and structural similarity to domains members of Dimeric alpha/beta barrel superfamily.", "domain_architectures": 8, "interpro_id": "IPR055816", "known_evidence_count": null, "matches": 382, "name": "Domain of unknown function (DUF7392)", "partial_evidence_count": null, "pfam_id": "PF24118", "proteins": 381, "proteomes": 236, "short_name": "DUF7392", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24118", "structures": 0, "taxa": 661, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "[swissprot:Q4C9H3] is associated with the [pfam:PF01383] domain suggesting this presumed domain could have a role in phycobilisomes.", "domain_architectures": 4, "interpro_id": "IPR014945", "known_evidence_count": null, "matches": 380, "name": "Domain of unknown function (DUF1816)", "partial_evidence_count": null, "pfam_id": "PF08846", "proteins": 380, "proteomes": 239, "short_name": "DUF1816", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08846", "structures": 0, "taxa": 659, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminus of proteins that are functionally uncharacterised.", "domain_architectures": 2, "interpro_id": "IPR014992", "known_evidence_count": null, "matches": 380, "name": "Domain of unknown function (DUF1842)", "partial_evidence_count": null, "pfam_id": "PF08896", "proteins": 380, "proteomes": 275, "short_name": "DUF1842", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08896", "structures": 3, "taxa": 468, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins with unknown function appear to be restricted to Firmicutes.", "domain_architectures": 2, "interpro_id": "IPR021380", "known_evidence_count": null, "matches": 380, "name": "Protein of unknown function (DUF3013)", "partial_evidence_count": null, "pfam_id": "PF11217", "proteins": 380, "proteomes": 380, "short_name": "DUF3013", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11217", "structures": 1, "taxa": 567, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 206, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 112 and 148 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046500", "known_evidence_count": null, "matches": 380, "name": "Family of unknown function (DUF6678)", "partial_evidence_count": null, "pfam_id": "PF20383", "proteins": 380, "proteomes": 359, "short_name": "DUF6678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20383", "structures": 0, "taxa": 767, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 317, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found at the C-terminal of fungal sequences, and is typically between 48 and 62 amino acids in length. The domain is found in association with [pfam:PF00735]. There is a conserved sequence motif WxRHxAAxK that may be functionally important.", "domain_architectures": 9, "interpro_id": "IPR046707", "known_evidence_count": null, "matches": 383, "name": "Domain of unknown function (DUF6780)", "partial_evidence_count": null, "pfam_id": "PF20571", "proteins": 380, "proteomes": 377, "short_name": "DUF6780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20571", "structures": 0, "taxa": 831, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 307, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 176 and 187 amino acids in length. There is a conserved DPG sequence motif.", "domain_architectures": 3, "interpro_id": "IPR025529", "known_evidence_count": null, "matches": 379, "name": "Domain of unknown function (DUF4416)", "partial_evidence_count": null, "pfam_id": "PF14385", "proteins": 379, "proteomes": 367, "short_name": "DUF4416", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14385", "structures": 0, "taxa": 832, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 221, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR024999", "known_evidence_count": null, "matches": 378, "name": "Protein of unknown function (DUF3905)", "partial_evidence_count": null, "pfam_id": "PF13045", "proteins": 378, "proteomes": 378, "short_name": "DUF3905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13045", "structures": 0, "taxa": 459, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 344, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in proteins related to the Archaea-specific chemotaxis proteins. It shares significant sequence and structural similarity to three-helical HTH domains.", "domain_architectures": 3, "interpro_id": "IPR061640", "known_evidence_count": null, "matches": 378, "name": "Domain of unknown function (DUF8579)", "partial_evidence_count": null, "pfam_id": "PF29648", "proteins": 378, "proteomes": 276, "short_name": "DUF8579", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29648", "structures": 2, "taxa": 495, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Proteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021693", "known_evidence_count": null, "matches": 393, "name": "Protein of unknown function (DUF3275)", "partial_evidence_count": null, "pfam_id": "PF11679", "proteins": 377, "proteomes": 308, "short_name": "DUF3275", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11679", "structures": 0, "taxa": 579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised bacterial proteins that adopts a compact domain composed of 5 beta strands and a single alpha helix.", "domain_architectures": 2, "interpro_id": "IPR056078", "known_evidence_count": null, "matches": 377, "name": "Domain of unknown function (DUF7661)", "partial_evidence_count": null, "pfam_id": "PF24697", "proteins": 377, "proteomes": 372, "short_name": "DUF7661", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24697", "structures": 0, "taxa": 547, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 255, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins found in bacteria and archaea.", "domain_architectures": 1, "interpro_id": "IPR009324", "known_evidence_count": null, "matches": 376, "name": "Protein of unknown function (DUF981)", "partial_evidence_count": null, "pfam_id": "PF06168", "proteins": 376, "proteomes": 345, "short_name": "DUF981", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06168", "structures": 0, "taxa": 781, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 332, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 37 and 78 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR031744", "known_evidence_count": null, "matches": 376, "name": "Domain of unknown function (DUF4731)", "partial_evidence_count": null, "pfam_id": "PF15875", "proteins": 376, "proteomes": 301, "short_name": "DUF4731", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15875", "structures": 0, "taxa": 1068, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001964) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the alkylpyrone-407 biosynthetic gene cluster from Cystobacterineae bacterium [[cite:PUB00098951]].", "domain_architectures": 8, "interpro_id": "IPR045727", "known_evidence_count": null, "matches": 379, "name": "Family of unknown function (DUF6081)", "partial_evidence_count": null, "pfam_id": "PF19559", "proteins": 376, "proteomes": 325, "short_name": "DUF6081", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19559", "structures": 0, "taxa": 577, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 276, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Alphaproteobacteria. Proteins in this family are typically between 161 and 194 amino acids in length. This family is related to [pfam:PF03713] and is therefore part of the ferritin superfamily.", "domain_architectures": 3, "interpro_id": "IPR046514", "known_evidence_count": null, "matches": 376, "name": "Domain of unknown function (DUF6692)", "partial_evidence_count": null, "pfam_id": "PF20402", "proteins": 376, "proteomes": 292, "short_name": "DUF6692", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20402", "structures": 0, "taxa": 514, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 352, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry includes uncharacterised archaeal proteins including Uncharacterized protein AF_0763 from Archaeoglobus fulgidus [[swissprot:O29495]].", "domain_architectures": 2, "interpro_id": "IPR056613", "known_evidence_count": null, "matches": 376, "name": "Family of unknown function (DUF7287)", "partial_evidence_count": null, "pfam_id": "PF23958", "proteins": 376, "proteomes": 300, "short_name": "DUF7287", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23958", "structures": 0, "taxa": 499, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents uncharacterised proteins found in bacteria. These proteins are related to members of [pfam:PF03513] which are described as immunity proteins. They are predicted to adopt similar structure composed of a four-stranded antiparallel beta-sheet with alpha-helices packed on one side of it.", "domain_architectures": 4, "interpro_id": "IPR056100", "known_evidence_count": null, "matches": 379, "name": "Domain of unknown function (DUF7683)", "partial_evidence_count": null, "pfam_id": "PF24731", "proteins": 376, "proteomes": 334, "short_name": "DUF7683", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24731", "structures": 0, "taxa": 662, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 327, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 70 amino acids in length. There are two conserved sequence motifs: CRC and YFDC.", "domain_architectures": 4, "interpro_id": "IPR032061", "known_evidence_count": null, "matches": 376, "name": "Domain of unknown function (DUF4802)", "partial_evidence_count": null, "pfam_id": "PF16060", "proteins": 375, "proteomes": 196, "short_name": "DUF4802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16060", "structures": 0, "taxa": 703, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this family are uncharacterised, but have been identified as members of a gene cluster for the synthesis of Ansamitocin [[cite:PUB00078767]].", "domain_architectures": 1, "interpro_id": "IPR033456", "known_evidence_count": null, "matches": 375, "name": "Protein of unknown function (DUF5132)", "partial_evidence_count": null, "pfam_id": "PF17195", "proteins": 375, "proteomes": 255, "short_name": "DUF5132", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17195", "structures": 0, "taxa": 665, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function. It is found mostly in Bacteria. Members of this family are predicted to contain 2 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035238", "known_evidence_count": null, "matches": 374, "name": "Family of unknown function (DUF5345)", "partial_evidence_count": null, "pfam_id": "PF17280", "proteins": 374, "proteomes": 372, "short_name": "DUF5345", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17280", "structures": 0, "taxa": 466, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is made up of members from various Burkholderia spp. The function is unknown.", "domain_architectures": 1, "interpro_id": "IPR018924", "known_evidence_count": null, "matches": 373, "name": "Protein of unknown function (DUF2486)", "partial_evidence_count": null, "pfam_id": "PF10667", "proteins": 373, "proteomes": 373, "short_name": "DUF2486", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10667", "structures": 0, "taxa": 436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 305, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 91 and 186 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR024271", "known_evidence_count": null, "matches": 373, "name": "Protein of unknown function (DUF3782)", "partial_evidence_count": null, "pfam_id": "PF12644", "proteins": 373, "proteomes": 138, "short_name": "DUF3782", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12644", "structures": 0, "taxa": 438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 277, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function is found in Mycobacterium spp.", "domain_architectures": 1, "interpro_id": "IPR031702", "known_evidence_count": null, "matches": 373, "name": "Domain of unknown function (DUF5078)", "partial_evidence_count": null, "pfam_id": "PF16877", "proteins": 373, "proteomes": 248, "short_name": "DUF5078", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16877", "structures": 6, "taxa": 281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 309, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 71 and 100 amino acids in length. There is a conserved AKR sequence motif.", "domain_architectures": 5, "interpro_id": "IPR027893", "known_evidence_count": null, "matches": 373, "name": "Domain of unknown function (DUF4611)", "partial_evidence_count": null, "pfam_id": "PF15387", "proteins": 372, "proteomes": 314, "short_name": "DUF4611", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15387", "structures": 2, "taxa": 1181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001590) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the formicamycins A-M biosynthetic gene cluster from Streptomyces sp. KY5 [[cite:PUB00098929]].", "domain_architectures": 4, "interpro_id": "IPR045694", "known_evidence_count": null, "matches": 374, "name": "Family of unknown function (DUF6058)", "partial_evidence_count": null, "pfam_id": "PF19531", "proteins": 372, "proteomes": 350, "short_name": "DUF6058", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19531", "structures": 0, "taxa": 559, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 237, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They share significant sequence similarity with each of the specificity subunit target recognition domains of type I restriction-modification enzymes and are predicted to adopt the same structure.", "domain_architectures": 1, "interpro_id": "IPR054223", "known_evidence_count": null, "matches": 372, "name": "Family of unknown function (DUF6943)", "partial_evidence_count": null, "pfam_id": "PF22105", "proteins": 372, "proteomes": 260, "short_name": "DUF6943", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22105", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 353, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of a group of proteins from eubacteria. It is predicted to show a mainly alpha-configuration. This entry is found associated with [pfam:PF23375] and [pfam:PF23374]", "domain_architectures": 3, "interpro_id": "IPR055522", "known_evidence_count": null, "matches": 372, "name": "Domain of unknown function (DUF7096)", "partial_evidence_count": null, "pfam_id": "PF23379", "proteins": 372, "proteomes": 278, "short_name": "DUF7096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23379", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 353, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small group of archaeal sequences whose function is unknown.", "domain_architectures": 2, "interpro_id": "IPR055809", "known_evidence_count": null, "matches": 372, "name": "Family of unknown function (DUF7385)", "partial_evidence_count": null, "pfam_id": "PF24110", "proteins": 372, "proteomes": 229, "short_name": "DUF7385", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24110", "structures": 0, "taxa": 356, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 306, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in human Ras-related protein Rab-34, isoform NARR and related proteins. It contains several RP motifs.", "domain_architectures": 50, "interpro_id": "IPR059393", "known_evidence_count": null, "matches": 500, "name": "Domain of unknown function (DUF8349)", "partial_evidence_count": null, "pfam_id": "PF27509", "proteins": 372, "proteomes": 177, "short_name": "DUF8349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27509", "structures": 0, "taxa": 920, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001916) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the lavendiol biosynthetic gene cluster from Streptomyces lavendulae [[cite:PUB00098885]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046185", "known_evidence_count": null, "matches": 371, "name": "Family of unknown function (DUF6213)", "partial_evidence_count": null, "pfam_id": "PF19719", "proteins": 371, "proteomes": 367, "short_name": "DUF6213", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19719", "structures": 0, "taxa": 403, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram negative bacteria. It has similarity to known AspS Pilotin-like domains and it is predicted to fold into a similar structure.", "domain_architectures": 2, "interpro_id": "IPR061549", "known_evidence_count": null, "matches": 371, "name": "Domain of unknown function (DUF8479)", "partial_evidence_count": null, "pfam_id": "PF28901", "proteins": 371, "proteomes": 350, "short_name": "DUF8479", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28901", "structures": 0, "taxa": 588, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This is a family of putative cytoplasmic proteins. The structure of these proteins form an antiparallel beta and sheet and contain some alpha helical regions.", "domain_architectures": 2, "interpro_id": "IPR018994", "known_evidence_count": null, "matches": 370, "name": "Protein of unknown function (DUF2002)", "partial_evidence_count": null, "pfam_id": "PF09400", "proteins": 370, "proteomes": 369, "short_name": "DUF2002", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09400", "structures": 1, "taxa": 539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family is conserved largely in Gammaproteobacteria. Several members are named as YfgG. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR022576", "known_evidence_count": null, "matches": 370, "name": "Protein of unknown function (DUF2633)", "partial_evidence_count": null, "pfam_id": "PF11119", "proteins": 370, "proteomes": 370, "short_name": "DUF2633", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11119", "structures": 0, "taxa": 523, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001782) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the spiroindimicin A biosynthetic gene cluster from Streptomyces sp. SCSIO 03032 [[cite:PUB00099387]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR046186", "known_evidence_count": null, "matches": 401, "name": "Family of unknown function (DUF6214)", "partial_evidence_count": null, "pfam_id": "PF19720", "proteins": 370, "proteomes": 365, "short_name": "DUF6214", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19720", "structures": 0, "taxa": 404, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001381) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the brasilinolide A biosynthetic gene cluster from Nocardia terpenica [[cite:PUB00098914]]. This family appears to be predominantly found in actinobacteria.", "domain_architectures": 7, "interpro_id": "IPR046268", "known_evidence_count": null, "matches": 381, "name": "Family of unknown function (DUF6301)", "partial_evidence_count": null, "pfam_id": "PF19818", "proteins": 370, "proteomes": 212, "short_name": "DUF6301", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19818", "structures": 0, "taxa": 351, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 240, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Proteobacteria. These proteins are likely to be outer membrane proteins.", "domain_architectures": 1, "interpro_id": "IPR021523", "known_evidence_count": null, "matches": 369, "name": "Protein of unknown function (DUF3187)", "partial_evidence_count": null, "pfam_id": "PF11383", "proteins": 369, "proteomes": 320, "short_name": "DUF3187", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11383", "structures": 0, "taxa": 631, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 200, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 50 amino acids in length. There is a single completely conserved residue Y that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR022213", "known_evidence_count": null, "matches": 368, "name": "Protein of unknown function (DUF3742)", "partial_evidence_count": null, "pfam_id": "PF12553", "proteins": 368, "proteomes": 283, "short_name": "DUF3742", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12553", "structures": 0, "taxa": 528, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. Proteins in this family are found in bacteria and they are approximately 70 amino acids in length. It contains the RE/K and GW conserved motifs.", "domain_architectures": 1, "interpro_id": "IPR045946", "known_evidence_count": null, "matches": 368, "name": "Family of unknown function (DUF6366)", "partial_evidence_count": null, "pfam_id": "PF19893", "proteins": 368, "proteomes": 348, "short_name": "DUF6366", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19893", "structures": 0, "taxa": 496, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain from a family of Chordate proteins that includes C19orf68. These proteins appear to be transposon related.", "domain_architectures": 34, "interpro_id": "IPR049218", "known_evidence_count": null, "matches": 436, "name": "DUF5575 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20784", "proteins": 368, "proteomes": 193, "short_name": "DUF5575_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20784", "structures": 0, "taxa": 792, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function. The family is rich in proline residues.", "domain_architectures": 4, "interpro_id": "IPR018903", "known_evidence_count": null, "matches": 394, "name": "Protein of unknown function (DUF2476)", "partial_evidence_count": null, "pfam_id": "PF10630", "proteins": 367, "proteomes": 139, "short_name": "DUF2476", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10630", "structures": 0, "taxa": 447, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are approximately 290 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR028970", "known_evidence_count": null, "matches": 374, "name": "Domain of unknown function (DUF4662)", "partial_evidence_count": null, "pfam_id": "PF15578", "proteins": 367, "proteomes": 193, "short_name": "DUF4662", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15578", "structures": 0, "taxa": 688, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 460 residues in length and is mainly found in various Bacteroides species, such as Bacteroides fragilis, Bacteroides sp. and so on. Several members are annotated as putative metalloproteases, but the specific function of this family is unknown.", "domain_architectures": 8, "interpro_id": "IPR032560", "known_evidence_count": null, "matches": 367, "name": "Domain of unknown function (DUF4932)", "partial_evidence_count": null, "pfam_id": "PF16286", "proteins": 367, "proteomes": 321, "short_name": "DUF4932", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16286", "structures": 0, "taxa": 607, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small bacterial protein of unknown function. Its predicted structure shows a 6 stranded beta sheet with a C-terminal helix packed on one side. In a few proteins this domain is associated with [pfam:PF15595] a presumed immunity protein, which could suggest this domain may have a toxin function or be involved in a toxin/antitoxin system or in phage defence.", "domain_architectures": 4, "interpro_id": "IPR049248", "known_evidence_count": null, "matches": 367, "name": "Domain of unknown function (DUF6881)", "partial_evidence_count": null, "pfam_id": "PF21812", "proteins": 367, "proteomes": 349, "short_name": "DUF6881", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21812", "structures": 0, "taxa": 698, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised bacterial proteins. This domain likely contains a zinc binding site.", "domain_architectures": 10, "interpro_id": "IPR057679", "known_evidence_count": null, "matches": 368, "name": "Domain of unknown function (DUF7919)", "partial_evidence_count": null, "pfam_id": "PF25535", "proteins": 367, "proteomes": 315, "short_name": "DUF7919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25535", "structures": 0, "taxa": 610, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 351, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this archaebacterial protein family are around 250-300 amino acid residues in length. The function of these proteins is not known.", "domain_architectures": 25, "interpro_id": "IPR008553", "known_evidence_count": null, "matches": 371, "name": "Protein of unknown function (DUF835)", "partial_evidence_count": null, "pfam_id": "PF05763", "proteins": 366, "proteomes": 68, "short_name": "DUF835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05763", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus cereus.", "domain_architectures": 1, "interpro_id": "IPR024488", "known_evidence_count": null, "matches": 366, "name": "Protein of unknown function (DUF2777)", "partial_evidence_count": null, "pfam_id": "PF10949", "proteins": 366, "proteomes": 365, "short_name": "DUF2777", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10949", "structures": 0, "taxa": 471, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 313, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised fungal proteins are primarily found in ascomycota.", "domain_architectures": 3, "interpro_id": "IPR035186", "known_evidence_count": null, "matches": 387, "name": "Family of unknown function (DUF5308)", "partial_evidence_count": null, "pfam_id": "PF17233", "proteins": 366, "proteomes": 363, "short_name": "DUF5308", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17233", "structures": 0, "taxa": 704, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 323, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chordata.", "domain_architectures": 1, "interpro_id": "IPR039954", "known_evidence_count": null, "matches": 366, "name": "Family of unknown function (DUF5527)", "partial_evidence_count": null, "pfam_id": "PF17665", "proteins": 366, "proteomes": 319, "short_name": "DUF5527", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17665", "structures": 0, "taxa": 1195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000187) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the asukamycin biosynthetic gene cluster from Streptomyces nodosus subsp. asukaensis [[cite:PUB00099427]]. This family appears to be predominantly found in actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR046263", "known_evidence_count": null, "matches": 366, "name": "Family of unknown function (DUF6296)", "partial_evidence_count": null, "pfam_id": "PF19813", "proteins": 366, "proteomes": 304, "short_name": "DUF6296", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19813", "structures": 0, "taxa": 336, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 290, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 60 amino acids found at the N-terminal of 20.7 kDa protein in NOF-FB from Drosophila melanogaster and as tandem arrays of 10-11 copies in other members of this entry, from insects. The function of this domain remains to be determined.", "domain_architectures": 22, "interpro_id": "IPR061894", "known_evidence_count": null, "matches": 455, "name": "Domain of unknown function (DUF8833)", "partial_evidence_count": null, "pfam_id": "PF31175", "proteins": 366, "proteomes": 62, "short_name": "DUF8833", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31175", "structures": 0, "taxa": 364, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 339, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043826", "known_evidence_count": null, "matches": 365, "name": "Family of unknown function (DUF5803)", "partial_evidence_count": null, "pfam_id": "PF19119", "proteins": 365, "proteomes": 365, "short_name": "DUF5803", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19119", "structures": 0, "taxa": 579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000452) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the tyrocidine biosynthetic gene cluster from Brevibacillus brevis NBRC 100599 and appears to be predominantly found in bacteria [[cite:PUB00099473]].", "domain_architectures": 3, "interpro_id": "IPR046136", "known_evidence_count": null, "matches": 367, "name": "Family of unknown function (DUF6138)", "partial_evidence_count": null, "pfam_id": "PF19635", "proteins": 365, "proteomes": 304, "short_name": "DUF6138", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19635", "structures": 0, "taxa": 481, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram-negative bacteria. It contains six highly conserved histidine that cluster in space and probably represent two metal coordinating sites.", "domain_architectures": 1, "interpro_id": "IPR061548", "known_evidence_count": null, "matches": 365, "name": "Domain of unknown function (DUF8478)", "partial_evidence_count": null, "pfam_id": "PF28899", "proteins": 365, "proteomes": 288, "short_name": "DUF8478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28899", "structures": 0, "taxa": 459, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001042) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the sanglifehrin A biosynthetic gene cluster from Streptomyces flaveolus [[cite:PUB00099463]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 4, "interpro_id": "IPR046196", "known_evidence_count": null, "matches": 366, "name": "Family of unknown function (DUF6228)", "partial_evidence_count": null, "pfam_id": "PF19739", "proteins": 364, "proteomes": 348, "short_name": "DUF6228", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19739", "structures": 0, "taxa": 616, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 348, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. This domain is the middle of three domains found in the DUF2110 family proteins. It has an OB-like fold.", "domain_architectures": 4, "interpro_id": "IPR056756", "known_evidence_count": null, "matches": 364, "name": "DUF2110 central domain", "partial_evidence_count": null, "pfam_id": "PF09883", "proteins": 363, "proteomes": 362, "short_name": "DUF2110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09883", "structures": 0, "taxa": 583, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 349, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. It is found at the N-terminus of the DUF2110 family proteins.", "domain_architectures": 4, "interpro_id": "IPR056758", "known_evidence_count": null, "matches": 363, "name": "DUF2110 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF24872", "proteins": 363, "proteomes": 361, "short_name": "DUF2110_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24872", "structures": 0, "taxa": 575, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 348, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. It is found at the C-terminus of DUF2110 family proteins.", "domain_architectures": 4, "interpro_id": "IPR056757", "known_evidence_count": null, "matches": 363, "name": "DUF2110 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF24873", "proteins": 363, "proteomes": 362, "short_name": "DUF2110_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24873", "structures": 0, "taxa": 583, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised animal proteins that also contain [pfam:PF05183]. This domain is predicted to adopt a mainly alpha helical structure. Its specific function is unknown.", "domain_architectures": 36, "interpro_id": "IPR056654", "known_evidence_count": null, "matches": 364, "name": "Domain of unknown function (DUF7752)", "partial_evidence_count": null, "pfam_id": "PF24934", "proteins": 363, "proteomes": 95, "short_name": "DUF7752", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24934", "structures": 0, "taxa": 228, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 241, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 250 residues in length and is found in several Chlamydia and Anabaena species. The function of this family is unknown.", "domain_architectures": 8, "interpro_id": "IPR010602", "known_evidence_count": null, "matches": 364, "name": "Protein of unknown function (DUF1186)", "partial_evidence_count": null, "pfam_id": "PF06685", "proteins": 362, "proteomes": 339, "short_name": "DUF1186", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06685", "structures": 0, "taxa": 829, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 234, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. A few of the family members contain a zinc finger domain.", "domain_architectures": 3, "interpro_id": "IPR017211", "known_evidence_count": null, "matches": 362, "name": "Uncharacterized protein conserved in archaea (DUF2180)", "partial_evidence_count": null, "pfam_id": "PF09947", "proteins": 362, "proteomes": 304, "short_name": "DUF2180", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09947", "structures": 0, "taxa": 498, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 326, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are found in large numbers in the Trichomonas vaginalis proteome. The function of this protein is unknown.", "domain_architectures": 4, "interpro_id": "IPR025179", "known_evidence_count": null, "matches": 364, "name": "Protein of unknown function (DUF4106)", "partial_evidence_count": null, "pfam_id": "PF13388", "proteins": 362, "proteomes": 2, "short_name": "DUF4106", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13388", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 273, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR027853", "known_evidence_count": null, "matches": 362, "name": "Domain of unknown function (DUF4492)", "partial_evidence_count": null, "pfam_id": "PF14899", "proteins": 362, "proteomes": 358, "short_name": "DUF4492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14899", "structures": 0, "taxa": 625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 219, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in Firmicute bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046117", "known_evidence_count": null, "matches": 362, "name": "Family of unknown function (DUF6054)", "partial_evidence_count": null, "pfam_id": "PF19524", "proteins": 362, "proteomes": 334, "short_name": "DUF6054", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19524", "structures": 0, "taxa": 603, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001215) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the conglobatin biosynthetic gene cluster from Streptomyces conglobatus [[cite:PUB00099436]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR046177", "known_evidence_count": null, "matches": 362, "name": "Family of unknown function (DUF6186)", "partial_evidence_count": null, "pfam_id": "PF19684", "proteins": 362, "proteomes": 353, "short_name": "DUF6186", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19684", "structures": 0, "taxa": 469, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000093) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the meilingmycin biosynthetic gene cluster from Streptomyces nanchangensis [[cite:PUB00099370],[cite:PUB00099380]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 4, "interpro_id": "IPR046238", "known_evidence_count": null, "matches": 374, "name": "Family of unknown function (DUF6271)", "partial_evidence_count": null, "pfam_id": "PF19787", "proteins": 362, "proteomes": 338, "short_name": "DUF6271", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19787", "structures": 0, "taxa": 466, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 247, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 340 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045932", "known_evidence_count": null, "matches": 366, "name": "Family of unknown function (DUF6352)", "partial_evidence_count": null, "pfam_id": "PF19879", "proteins": 362, "proteomes": 356, "short_name": "DUF6352", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19879", "structures": 0, "taxa": 568, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They share significant sequence similarity to HTH winged helix domains, in particular to the N-terminal domain of transcriptional regulator BrxR and RNA polymerase III subunit RPC82.", "domain_architectures": 2, "interpro_id": "IPR054228", "known_evidence_count": null, "matches": 362, "name": "Family of unknown function (DUF6953)", "partial_evidence_count": null, "pfam_id": "PF22266", "proteins": 362, "proteomes": 350, "short_name": "DUF6953", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22266", "structures": 0, "taxa": 550, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 330, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This entry represents a ferredoxin-like fold domain found at the C-terminus of a range of proteins that contain LolA-like domains suggesting these proteins may act as lipoprotein chaperones. The function of this domain is uncertain.", "domain_architectures": 22, "interpro_id": "IPR058265", "known_evidence_count": null, "matches": 368, "name": "Domain of unknown function (DUF7959)", "partial_evidence_count": null, "pfam_id": "PF25899", "proteins": 362, "proteomes": 175, "short_name": "DUF7959", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25899", "structures": 0, "taxa": 629, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 345, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 1, "interpro_id": "IPR058305", "known_evidence_count": null, "matches": 362, "name": "Family of unknown function (DUF7992)", "partial_evidence_count": null, "pfam_id": "PF25955", "proteins": 362, "proteomes": 270, "short_name": "DUF7992", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25955", "structures": 0, "taxa": 419, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of hypothetical proteins in Leptospira interrogans.", "domain_architectures": 4, "interpro_id": "IPR011471", "known_evidence_count": null, "matches": 361, "name": "Protein of unknown function (DUF1577)", "partial_evidence_count": null, "pfam_id": "PF07614", "proteins": 361, "proteomes": 89, "short_name": "DUF1577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07614", "structures": 0, "taxa": 153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 94 and 107 amino acids in length. There is a conserved EYY sequence motif.", "domain_architectures": 2, "interpro_id": "IPR027890", "known_evidence_count": null, "matches": 361, "name": "Domain of unknown function (DUF4491)", "partial_evidence_count": null, "pfam_id": "PF14898", "proteins": 361, "proteomes": 348, "short_name": "DUF4491", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14898", "structures": 0, "taxa": 670, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001065) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the herboxidiene biosynthetic gene cluster from Streptomyces chromofuscus [[cite:PUB00098901]]. This family appears to be predominantly found in actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR045660", "known_evidence_count": null, "matches": 377, "name": "Family of unknown function (DUF6390)", "partial_evidence_count": null, "pfam_id": "PF19927", "proteins": 361, "proteomes": 353, "short_name": "DUF6390", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19927", "structures": 0, "taxa": 507, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 347, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in the Caenorhabditis elegans uncharacterised protein Clec-72 and related eukaryotic proteins. It is predicted to adopt a globular structure with similarity to Galactose-binding domains.", "domain_architectures": 18, "interpro_id": "IPR055578", "known_evidence_count": null, "matches": 419, "name": "Domain of unknown function (DUF7154)", "partial_evidence_count": null, "pfam_id": "PF23673", "proteins": 361, "proteomes": 9, "short_name": "DUF7154", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23673", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001920) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 4, "interpro_id": "IPR046002", "known_evidence_count": null, "matches": 362, "name": "Family of unknown function (DUF5958)", "partial_evidence_count": null, "pfam_id": "PF19383", "proteins": 360, "proteomes": 326, "short_name": "DUF5958", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19383", "structures": 0, "taxa": 490, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is found primarily in proteobacteria. Proteins in this family are approximately 50 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046035", "known_evidence_count": null, "matches": 360, "name": "Family of unknown function (DUF5993)", "partial_evidence_count": null, "pfam_id": "PF19455", "proteins": 360, "proteomes": 357, "short_name": "DUF5993", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19455", "structures": 0, "taxa": 594, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of small phage proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR059316", "known_evidence_count": null, "matches": 360, "name": "Family of unknown function (DUF8272)", "partial_evidence_count": null, "pfam_id": "PF26839", "proteins": 360, "proteomes": 357, "short_name": "DUF8272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26839", "structures": 0, "taxa": 846, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 303, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. The proteins contain a conserved VLPPLK sequence motif.", "domain_architectures": 2, "interpro_id": "IPR027836", "known_evidence_count": null, "matches": 381, "name": "Protein of unknown function (DUF4529)", "partial_evidence_count": null, "pfam_id": "PF15032", "proteins": 359, "proteomes": 285, "short_name": "DUF4529", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15032", "structures": 0, "taxa": 1013, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 160 amino acids in length. There is a conserved RYGK sequence motif.", "domain_architectures": 9, "interpro_id": "IPR031936", "known_evidence_count": null, "matches": 360, "name": "Domain of unknown function (DUF4771)", "partial_evidence_count": null, "pfam_id": "PF15995", "proteins": 358, "proteomes": 188, "short_name": "DUF4771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15995", "structures": 0, "taxa": 667, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 267, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in uncharacterised bacterial proteins. It is probably remotely related to PemK-like, MazF-like toxins and is predicted to adopt SH3-like fold.", "domain_architectures": 1, "interpro_id": "IPR053845", "known_evidence_count": null, "matches": 358, "name": "Domain of unknown function (DUF6927)", "partial_evidence_count": null, "pfam_id": "PF21992", "proteins": 358, "proteomes": 289, "short_name": "DUF6927", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21992", "structures": 0, "taxa": 532, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is a presumed domain found towards the C-terminal of a group of uncharacterised sequences from C. elegans and similar proteins from nematodes.", "domain_architectures": 39, "interpro_id": "IPR056075", "known_evidence_count": null, "matches": 367, "name": "Domain of unknown function (DUF7658)", "partial_evidence_count": null, "pfam_id": "PF24678", "proteins": 358, "proteomes": 107, "short_name": "DUF7658", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24678", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 248, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in gram negative bacteria. They are predicted to adopt non-globular structure composed of two helices.", "domain_architectures": 1, "interpro_id": "IPR061577", "known_evidence_count": null, "matches": 358, "name": "Family of unknown function (DUF8507)", "partial_evidence_count": null, "pfam_id": "PF29170", "proteins": 358, "proteomes": 201, "short_name": "DUF8507", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29170", "structures": 0, "taxa": 346, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are found in Borrelia. The proteins are about 190 amino acids long and have no known function.", "domain_architectures": 2, "interpro_id": "IPR004180", "known_evidence_count": null, "matches": 357, "name": "Borrelia family of unknown function DUF226", "partial_evidence_count": null, "pfam_id": "PF02890", "proteins": 357, "proteomes": 32, "short_name": "DUF226", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02890", "structures": 0, "taxa": 56, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 338, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is present in a family of proteins predominantly found in Halobacteria. These proteins are thought to be the replication protein H.", "domain_architectures": 5, "interpro_id": "IPR043855", "known_evidence_count": null, "matches": 357, "name": "Domain of unknown function (DUF5817)", "partial_evidence_count": null, "pfam_id": "PF19134", "proteins": 357, "proteomes": 331, "short_name": "DUF5817", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19134", "structures": 0, "taxa": 546, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 200, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046169", "known_evidence_count": null, "matches": 357, "name": "Family of unknown function (DUF6171)", "partial_evidence_count": null, "pfam_id": "PF19668", "proteins": 357, "proteomes": 347, "short_name": "DUF6171", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19668", "structures": 0, "taxa": 557, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mainly found in bacteria. It is distantly related to Pfam family [pfam:PF09719], which is a heme binding cytochrome. This domain is found associated with other domains such as the Radical SAM domain and a methyltransferase.", "domain_architectures": 10, "interpro_id": "IPR043768", "known_evidence_count": null, "matches": 356, "name": "Family of unknown function (DUF5714)", "partial_evidence_count": null, "pfam_id": "PF18978", "proteins": 356, "proteomes": 319, "short_name": "DUF5714", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18978", "structures": 0, "taxa": 755, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 117 and 173 amino acids in length. These proteins have a highly charged N-terminus.", "domain_architectures": 2, "interpro_id": "IPR046313", "known_evidence_count": null, "matches": 356, "name": "Family of unknown function (DUF6465)", "partial_evidence_count": null, "pfam_id": "PF20069", "proteins": 356, "proteomes": 285, "short_name": "DUF6465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20069", "structures": 0, "taxa": 488, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 223, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in bacterial proteins, mainly from Firmicutes. Proteins in this family are typically between 116 and 320 amino acids in length. Many members are thought to contain a zinc ribbon domain at the N-terminal. This entry includes Uncharacterized protein YebC from Bacillus subtilis which contains transmembrane helices. This entry shows structural similarity to the Yip1 domain [pfam:PF04893].", "domain_architectures": 3, "interpro_id": "IPR046481", "known_evidence_count": null, "matches": 356, "name": "Domain of unknown function (DUF6574)", "partial_evidence_count": null, "pfam_id": "PF20214", "proteins": 356, "proteomes": 337, "short_name": "DUF6574", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20214", "structures": 0, "taxa": 557, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 229, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046659", "known_evidence_count": null, "matches": 356, "name": "Family of unknown function (DUF6768)", "partial_evidence_count": null, "pfam_id": "PF20556", "proteins": 356, "proteomes": 353, "short_name": "DUF6768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20556", "structures": 0, "taxa": 664, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 297, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of uncharacterised proteins are found in mammals.", "domain_architectures": 3, "interpro_id": "IPR029395", "known_evidence_count": null, "matches": 355, "name": "Domain of unknown function (DUF4514)", "partial_evidence_count": null, "pfam_id": "PF14986", "proteins": 355, "proteomes": 215, "short_name": "DUF4514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14986", "structures": 0, "taxa": 786, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 299, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 21 } }, "demotion_reasons": [], "description": "This region is found in some SIR2 family proteins ([pfam:PF02146]).", "domain_architectures": 8, "interpro_id": "IPR007654", "known_evidence_count": null, "matches": 393, "name": "Protein of unknown function (DUF592)", "partial_evidence_count": null, "pfam_id": "PF04574", "proteins": 354, "proteomes": 302, "short_name": "DUF592", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04574", "structures": 2, "taxa": 760, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus and appears to be predominantly found in Actinobacteria [[cite:PUB00098882]].", "domain_architectures": 1, "interpro_id": "IPR046075", "known_evidence_count": null, "matches": 354, "name": "Family of unknown function (DUF6093)", "partial_evidence_count": null, "pfam_id": "PF19586", "proteins": 354, "proteomes": 301, "short_name": "DUF6093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19586", "structures": 0, "taxa": 514, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 296 and 311 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046603", "known_evidence_count": null, "matches": 354, "name": "Family of unknown function (DUF6662)", "partial_evidence_count": null, "pfam_id": "PF20367", "proteins": 354, "proteomes": 295, "short_name": "DUF6662", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20367", "structures": 0, "taxa": 520, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in uncharacterised bacterial proteins. They share sequence similarity with several HTH winged helix domains, one of which Zinc uptake regulation protein FurB.", "domain_architectures": 3, "interpro_id": "IPR054233", "known_evidence_count": null, "matches": 354, "name": "Family of unknown function (DUF6958)", "partial_evidence_count": null, "pfam_id": "PF22278", "proteins": 354, "proteomes": 325, "short_name": "DUF6958", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22278", "structures": 0, "taxa": 666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 329, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to be organised into two domains, an N-terminal with an all-beta configuration and a C-terminal with a mainly alpha-structure.", "domain_architectures": 1, "interpro_id": "IPR055946", "known_evidence_count": null, "matches": 354, "name": "Family of unknown function (DUF7524)", "partial_evidence_count": null, "pfam_id": "PF24368", "proteins": 354, "proteomes": 352, "short_name": "DUF7524", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24368", "structures": 0, "taxa": 570, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR024492", "known_evidence_count": null, "matches": 355, "name": "Protein of unknown function (DUF2764)", "partial_evidence_count": null, "pfam_id": "PF10962", "proteins": 353, "proteomes": 347, "short_name": "DUF2764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10962", "structures": 0, "taxa": 738, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000144) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the salinomycin biosynthetic gene cluster from Streptomyces albus [[cite:PUB00098892]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR045649", "known_evidence_count": null, "matches": 353, "name": "Family of unknown function (DUF6400)", "partial_evidence_count": null, "pfam_id": "PF19938", "proteins": 353, "proteomes": 352, "short_name": "DUF6400", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19938", "structures": 0, "taxa": 415, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 228, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised membrane proteins found in Actinomycetes. These proteins contain 12 putative transmembrane helices.", "domain_architectures": 9, "interpro_id": "IPR057697", "known_evidence_count": null, "matches": 355, "name": "Domain of unknown function (DUF7937)", "partial_evidence_count": null, "pfam_id": "PF25592", "proteins": 353, "proteomes": 336, "short_name": "DUF7937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25592", "structures": 0, "taxa": 473, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 312, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from metazoan. This domain is composed of seven alpha-helices predicted as transmembrane.", "domain_architectures": 6, "interpro_id": "IPR061862", "known_evidence_count": null, "matches": 361, "name": "Family of unknown function (DUF8801)", "partial_evidence_count": null, "pfam_id": "PF31070", "proteins": 353, "proteomes": 242, "short_name": "DUF8801", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31070", "structures": 0, "taxa": 988, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Protein of unknown function found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR018567", "known_evidence_count": null, "matches": 355, "name": "Domain of unknown function (DUF2020)", "partial_evidence_count": null, "pfam_id": "PF09449", "proteins": 352, "proteomes": 349, "short_name": "DUF2020", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09449", "structures": 1, "taxa": 452, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Bacteroidetes and its function is unknown. It is approximately 60 amino acids in length. It contains a conserved motif DxxxW and a highly conserved tyrosine residue.", "domain_architectures": 1, "interpro_id": "IPR046695", "known_evidence_count": null, "matches": 352, "name": "Domain of unknown function (DUF6565)", "partial_evidence_count": null, "pfam_id": "PF20203", "proteins": 352, "proteomes": 310, "short_name": "DUF6565", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20203", "structures": 0, "taxa": 387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and eukaryotes. Proteins in this family are about 220 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR021809", "known_evidence_count": null, "matches": 351, "name": "Protein of unknown function (DUF3386)", "partial_evidence_count": null, "pfam_id": "PF11866", "proteins": 351, "proteomes": 306, "short_name": "DUF3386", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11866", "structures": 0, "taxa": 795, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 231, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterized. This family is found in bacteroides. Proteins in this family are typically around 150 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR032168", "known_evidence_count": null, "matches": 351, "name": "Domain of unknown function (DUF5004)", "partial_evidence_count": null, "pfam_id": "PF16395", "proteins": 351, "proteomes": 329, "short_name": "DUF5004", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16395", "structures": 0, "taxa": 478, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 330, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria and Methanomicrobia.", "domain_architectures": 1, "interpro_id": "IPR043829", "known_evidence_count": null, "matches": 351, "name": "Family of unknown function (DUF5806)", "partial_evidence_count": null, "pfam_id": "PF19122", "proteins": 351, "proteomes": 337, "short_name": "DUF5806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19122", "structures": 0, "taxa": 544, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001634) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046015", "known_evidence_count": null, "matches": 351, "name": "Family of unknown function (DUF5972)", "partial_evidence_count": null, "pfam_id": "PF19397", "proteins": 351, "proteomes": 274, "short_name": "DUF5972", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19397", "structures": 1, "taxa": 369, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 107 and 214 amino acids in length. These proteins may have a threefold symmetric beta-trefoil fold, a symmetric protein structure thought to be conserved in protein evolution [[cite:PUB00101220]].", "domain_architectures": 5, "interpro_id": "IPR046702", "known_evidence_count": null, "matches": 351, "name": "Family of unknown function (DUF6572)", "partial_evidence_count": null, "pfam_id": "PF20212", "proteins": 351, "proteomes": 310, "short_name": "DUF6572", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20212", "structures": 0, "taxa": 720, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Actinomycetes. It is predicted to fold into an array of alpha-helices. Some members have a small three-helical bundle inserted into it.", "domain_architectures": 5, "interpro_id": "IPR059394", "known_evidence_count": null, "matches": 356, "name": "Domain of unknown function (DUF8350)", "partial_evidence_count": null, "pfam_id": "PF27615", "proteins": 351, "proteomes": 311, "short_name": "DUF8350", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27615", "structures": 0, "taxa": 408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001922) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the isoindolinomycin biosynthetic gene cluster from Streptomyces sp. SoC090715LN-16 [[cite:PUB00098935]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR046262", "known_evidence_count": null, "matches": 350, "name": "Family of unknown function (DUF6295)", "partial_evidence_count": null, "pfam_id": "PF19812", "proteins": 350, "proteomes": 348, "short_name": "DUF6295", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19812", "structures": 0, "taxa": 522, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Actinobacteria. Proteins in this family are typically between 547 and 730 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR046701", "known_evidence_count": null, "matches": 356, "name": "Family of unknown function (DUF6571)", "partial_evidence_count": null, "pfam_id": "PF20211", "proteins": 350, "proteomes": 247, "short_name": "DUF6571", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20211", "structures": 0, "taxa": 333, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins of unknown function is predicted to contain 3 or 4 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR020509", "known_evidence_count": null, "matches": 349, "name": "Family of unknown function (DUF5367)", "partial_evidence_count": null, "pfam_id": "PF17329", "proteins": 349, "proteomes": 339, "short_name": "DUF5367", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17329", "structures": 0, "taxa": 613, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 335, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043952", "known_evidence_count": null, "matches": 349, "name": "Family of unknown function (DUF5783)", "partial_evidence_count": null, "pfam_id": "PF19095", "proteins": 349, "proteomes": 276, "short_name": "DUF5783", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19095", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 210, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046087", "known_evidence_count": null, "matches": 349, "name": "Family of unknown function (DUF6105)", "partial_evidence_count": null, "pfam_id": "PF19600", "proteins": 349, "proteomes": 349, "short_name": "DUF6105", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19600", "structures": 0, "taxa": 449, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 249, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR021294", "known_evidence_count": null, "matches": 348, "name": "Protein of unknown function (DUF2866)", "partial_evidence_count": null, "pfam_id": "PF11065", "proteins": 348, "proteomes": 176, "short_name": "DUF2866", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11065", "structures": 0, "taxa": 197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. This domain is likely to be a zinc-binding domain.", "domain_architectures": 1, "interpro_id": "IPR045504", "known_evidence_count": null, "matches": 348, "name": "Domain of unknown function (DUF6487)", "partial_evidence_count": null, "pfam_id": "PF20097", "proteins": 348, "proteomes": 276, "short_name": "DUF6487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20097", "structures": 0, "taxa": 602, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria. This domain is about 230 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR021928", "known_evidence_count": null, "matches": 347, "name": "Domain of unknown function (DUF3541)", "partial_evidence_count": null, "pfam_id": "PF12060", "proteins": 347, "proteomes": 330, "short_name": "DUF3541", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12060", "structures": 0, "taxa": 442, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 303, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in mammals. Proteins in this family are typically between 170 and 190 amino acids in length. The protein includes the human integral membrane TMEM217 protein.", "domain_architectures": 3, "interpro_id": "IPR027862", "known_evidence_count": null, "matches": 352, "name": "Protein of unknown function (DUF4534)", "partial_evidence_count": null, "pfam_id": "PF15049", "proteins": 347, "proteomes": 198, "short_name": "DUF4534", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15049", "structures": 0, "taxa": 681, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 281 and 302 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR029073", "known_evidence_count": null, "matches": 349, "name": "Domain of unknown function (DUF4661)", "partial_evidence_count": null, "pfam_id": "PF15576", "proteins": 347, "proteomes": 316, "short_name": "DUF4661", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15576", "structures": 0, "taxa": 1098, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in bacteria. It may adopt a beta-barrel structure.", "domain_architectures": 2, "interpro_id": "IPR040580", "known_evidence_count": null, "matches": 347, "name": "Domain of unknown function (DUF5627)", "partial_evidence_count": null, "pfam_id": "PF18620", "proteins": 347, "proteomes": 319, "short_name": "DUF5627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18620", "structures": 1, "taxa": 523, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 131 and 142 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045387", "known_evidence_count": null, "matches": 347, "name": "Family of unknown function (DUF6524)", "partial_evidence_count": null, "pfam_id": "PF20134", "proteins": 347, "proteomes": 323, "short_name": "DUF6524", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20134", "structures": 0, "taxa": 570, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 162, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a domain of unknown function in putative EGF-like domain-containing proteins found in eukaryotes, mainly ameobas. According to structure predictions it adopts an EGF-like fold which contain six conserved cysteine residues. The EGF-like fold has two-stranded beta-sheets followed by a loop to a short C-termini. It usually occurs in tandem repeats [[cite:PUB00001555]]. The domain described by this entry has the 6 conserved cysteine residues. It also acquires a similar structure to the EGF-like fold and it is 40 amino acids long.", "domain_architectures": 53, "interpro_id": "IPR057709", "known_evidence_count": null, "matches": 358, "name": "Domain of unknown function (DUF7949)", "partial_evidence_count": null, "pfam_id": "PF25820", "proteins": 347, "proteomes": 12, "short_name": "DUF7949", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25820", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001431) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide.", "domain_architectures": 3, "interpro_id": "IPR045997", "known_evidence_count": null, "matches": 347, "name": "Domain of unknown function (DUF5953)", "partial_evidence_count": null, "pfam_id": "PF19378", "proteins": 346, "proteomes": 42, "short_name": "DUF5953", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19378", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 322, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt a mainly beta structure.", "domain_architectures": 1, "interpro_id": "IPR055959", "known_evidence_count": null, "matches": 346, "name": "Family of unknown function (DUF7537)", "partial_evidence_count": null, "pfam_id": "PF24381", "proteins": 346, "proteomes": 177, "short_name": "DUF7537", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24381", "structures": 0, "taxa": 307, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 290, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain found at the N-terminus of an archaeal family of proteins called DUF1699.", "domain_architectures": 3, "interpro_id": "IPR059826", "known_evidence_count": null, "matches": 346, "name": "Family of unknown function (DUF1699) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF28505", "proteins": 346, "proteomes": 138, "short_name": "DUF1699_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28505", "structures": 0, "taxa": 261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 248, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 82 and 98 amino acids in length. There are two conserved sequence motifs: GKNWY and ITA.", "domain_architectures": 12, "interpro_id": "IPR024229", "known_evidence_count": null, "matches": 347, "name": "Protein of unknown function (DUF3781)", "partial_evidence_count": null, "pfam_id": "PF12636", "proteins": 345, "proteomes": 325, "short_name": "DUF3781", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12636", "structures": 0, "taxa": 680, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in vertebrates.", "domain_architectures": 14, "interpro_id": "IPR032771", "known_evidence_count": null, "matches": 352, "name": "Protein of unknown function (DUF4527)", "partial_evidence_count": null, "pfam_id": "PF15030", "proteins": 345, "proteomes": 252, "short_name": "DUF4527", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15030", "structures": 0, "taxa": 909, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 283, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 44 and 137 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR028106", "known_evidence_count": null, "matches": 346, "name": "Domain of unknown function (DUF4578)", "partial_evidence_count": null, "pfam_id": "PF15147", "proteins": 345, "proteomes": 269, "short_name": "DUF4578", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15147", "structures": 0, "taxa": 943, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 201 and 519 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR027822", "known_evidence_count": null, "matches": 363, "name": "Domain of unknown function (DUF4641)", "partial_evidence_count": null, "pfam_id": "PF15483", "proteins": 345, "proteomes": 127, "short_name": "DUF4641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15483", "structures": 0, "taxa": 406, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 439 and 479 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045726", "known_evidence_count": null, "matches": 525, "name": "Family of unknown function (DUF6080)", "partial_evidence_count": null, "pfam_id": "PF19558", "proteins": 345, "proteomes": 281, "short_name": "DUF6080", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19558", "structures": 0, "taxa": 379, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 225, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046152", "known_evidence_count": null, "matches": 345, "name": "Family of unknown function (DUF6154)", "partial_evidence_count": null, "pfam_id": "PF19651", "proteins": 345, "proteomes": 341, "short_name": "DUF6154", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19651", "structures": 0, "taxa": 459, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001558) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the cosmomycin C biosynthetic gene cluster from Streptomyces sp. CNT302 [[cite:PUB00099411]]. This family appears to be predominantly found in actinobacteria.", "domain_architectures": 4, "interpro_id": "IPR045961", "known_evidence_count": null, "matches": 345, "name": "Family of unknown function (DUF6381)", "partial_evidence_count": null, "pfam_id": "PF19908", "proteins": 345, "proteomes": 230, "short_name": "DUF6381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19908", "structures": 0, "taxa": 283, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 200, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus spp.", "domain_architectures": 1, "interpro_id": "IPR019688", "known_evidence_count": null, "matches": 344, "name": "Protein of unknown function (DUF2533)", "partial_evidence_count": null, "pfam_id": "PF10752", "proteins": 344, "proteomes": 342, "short_name": "DUF2533", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10752", "structures": 0, "taxa": 463, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 4, "interpro_id": "IPR021511", "known_evidence_count": null, "matches": 345, "name": "Protein of unknown function (DUF3172)", "partial_evidence_count": null, "pfam_id": "PF11371", "proteins": 344, "proteomes": 306, "short_name": "DUF3172", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11371", "structures": 0, "taxa": 861, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length. There are two conserved sequence motifs: GTG and SKG.", "domain_architectures": 3, "interpro_id": "IPR025175", "known_evidence_count": null, "matches": 344, "name": "Protein of unknown function (DUF3934)", "partial_evidence_count": null, "pfam_id": "PF13070", "proteins": 344, "proteomes": 339, "short_name": "DUF3934", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13070", "structures": 0, "taxa": 378, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000385) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the lysobactin biosynthetic gene cluster from Lysobacter sp. ATCC 53042 [[cite:PUB00098898]].", "domain_architectures": 1, "interpro_id": "IPR046256", "known_evidence_count": null, "matches": 344, "name": "Family of unknown function (DUF6289)", "partial_evidence_count": null, "pfam_id": "PF19806", "proteins": 344, "proteomes": 187, "short_name": "DUF6289", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19806", "structures": 0, "taxa": 307, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 244, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR017016", "known_evidence_count": null, "matches": 344, "name": "Family of unknown function (DUF6514)", "partial_evidence_count": null, "pfam_id": "PF20124", "proteins": 344, "proteomes": 291, "short_name": "DUF6514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20124", "structures": 0, "taxa": 481, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several uncharacterised proteins which seem to be found exclusively in Rhizobium loti.", "domain_architectures": 1, "interpro_id": "IPR007771", "known_evidence_count": null, "matches": 343, "name": "Protein of unknown function (DUF680)", "partial_evidence_count": null, "pfam_id": "PF05079", "proteins": 343, "proteomes": 55, "short_name": "DUF680", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05079", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 284, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 331 and 596 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031496", "known_evidence_count": null, "matches": 412, "name": "Domain of unknown function (DUF4688)", "partial_evidence_count": null, "pfam_id": "PF15752", "proteins": 343, "proteomes": 249, "short_name": "DUF4688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15752", "structures": 0, "taxa": 863, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillales. Most of the family members are predicted to have one trans-membrane region.", "domain_architectures": 1, "interpro_id": "IPR035281", "known_evidence_count": null, "matches": 343, "name": "Family of unknown function (DUF5359)", "partial_evidence_count": null, "pfam_id": "PF17313", "proteins": 343, "proteomes": 343, "short_name": "DUF5359", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17313", "structures": 0, "taxa": 450, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain from a family of Chordate proteins that includes C19orf68. These proteins appear to be transposon related. This domain appears to be related to the WRKY-like DNA-binding domains.", "domain_architectures": 25, "interpro_id": "IPR049217", "known_evidence_count": null, "matches": 426, "name": "DUF5575 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20783", "proteins": 343, "proteomes": 200, "short_name": "DUF5575_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20783", "structures": 0, "taxa": 735, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 217, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small bacterial protein o unknown function. Proteins in this family are primarily found in Firmicutes.", "domain_architectures": 2, "interpro_id": "IPR049222", "known_evidence_count": null, "matches": 343, "name": "Family of unknown function (DUF6870)", "partial_evidence_count": null, "pfam_id": "PF21757", "proteins": 343, "proteomes": 210, "short_name": "DUF6870", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21757", "structures": 0, "taxa": 427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of a group of uncharacterised sequences from actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR055582", "known_evidence_count": null, "matches": 343, "name": "Family of unknown function (DUF7158)", "partial_evidence_count": null, "pfam_id": "PF23716", "proteins": 343, "proteomes": 331, "short_name": "DUF7158", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23716", "structures": 0, "taxa": 408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of phage proteins that adopt a small beta barrel-like domain. The family is found in phages infecting members of the Enterobacteriaceae, such as Escherichia, Salmonella, Klebsiella, Cronobacter, Citrobacter, Erwinia, and Pectobacterium. The exact function of this protein within the phage tail is unknown. The family shows a highly conserved length of around 60-75 amino acids, with a few members having N- or C-terminal extensions.", "domain_architectures": 4, "interpro_id": "IPR055629", "known_evidence_count": null, "matches": 343, "name": "Domain of unknown function (DUF7205)", "partial_evidence_count": null, "pfam_id": "PF23835", "proteins": 343, "proteomes": 318, "short_name": "DUF7205", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23835", "structures": 0, "taxa": 806, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 325, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea and eukaryotes. These proteins contain two pairs of conserved cysteines and two pairs of conserved histidines that are probably involved in zinc coordination. These proteins likely resemble two classical C2H2 zinc fingers that pack on each other and form a compact globular structure.", "domain_architectures": 10, "interpro_id": "IPR055987", "known_evidence_count": null, "matches": 344, "name": "Family of unknown function (DUF7565)", "partial_evidence_count": null, "pfam_id": "PF24446", "proteins": 343, "proteomes": 317, "short_name": "DUF7565", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24446", "structures": 0, "taxa": 623, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 9, "interpro_id": "IPR031849", "known_evidence_count": null, "matches": 345, "name": "Domain of unknown function (DUF5069)", "partial_evidence_count": null, "pfam_id": "PF16798", "proteins": 342, "proteomes": 95, "short_name": "DUF5069", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16798", "structures": 1, "taxa": 220, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 234, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001520) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the aurantinin B biosynthetic gene cluster from Bacillus subtilis [[cite:PUB00098962]]. This family appears to be predominantly present in Firmicutes.", "domain_architectures": 2, "interpro_id": "IPR046286", "known_evidence_count": null, "matches": 342, "name": "Family of unknown function (DUF6323)", "partial_evidence_count": null, "pfam_id": "PF19848", "proteins": 342, "proteomes": 331, "short_name": "DUF6323", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19848", "structures": 0, "taxa": 601, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in metazoa. This entry represents the C-terminal domain.", "domain_architectures": 7, "interpro_id": "IPR049247", "known_evidence_count": null, "matches": 342, "name": "Family of unknown function (DUF5580) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20743", "proteins": 342, "proteomes": 234, "short_name": "DUF5580_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20743", "structures": 0, "taxa": 887, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 234, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry consists of several uncharacterized proteins mainly found in Bacteroides. This entry represents the C-terminal domain which adopts a Ig-like fold.", "domain_architectures": 26, "interpro_id": "IPR061639", "known_evidence_count": null, "matches": 348, "name": "Domain of unknown function (DUF8578)", "partial_evidence_count": null, "pfam_id": "PF29641", "proteins": 342, "proteomes": 322, "short_name": "DUF8578", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29641", "structures": 0, "taxa": 493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 242, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins which seem to be specific to firmicute species. Members of this family are typically around 100 residues in length. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR010813", "known_evidence_count": null, "matches": 341, "name": "Domain of unknown function (DUF1413)", "partial_evidence_count": null, "pfam_id": "PF07205", "proteins": 341, "proteomes": 293, "short_name": "DUF1413", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07205", "structures": 0, "taxa": 641, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 180 amino acids in length. The family is found in association with [pfam:PF01381].", "domain_architectures": 6, "interpro_id": "IPR022055", "known_evidence_count": null, "matches": 341, "name": "Protein of unknown function (DUF3612)", "partial_evidence_count": null, "pfam_id": "PF12268", "proteins": 341, "proteomes": 340, "short_name": "DUF3612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12268", "structures": 0, "taxa": 474, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins. The possess a beta sheet packed against an alpha helical subdomain. This alignment contains three fully conserved cysteines that look like they form an Fe-S cluster or zinc binding site in the predicted structures.", "domain_architectures": 1, "interpro_id": "IPR054196", "known_evidence_count": null, "matches": 340, "name": "Domain of unknown function (DUF6901)", "partial_evidence_count": null, "pfam_id": "PF21842", "proteins": 340, "proteomes": 289, "short_name": "DUF6901", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21842", "structures": 0, "taxa": 558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents OB-fold domains found in uncharacterised metazoan proteins where they are often found in multiple copies.", "domain_architectures": 26, "interpro_id": "IPR061599", "known_evidence_count": null, "matches": 569, "name": "Domain of unknown function (DUF8529)", "partial_evidence_count": null, "pfam_id": "PF29292", "proteins": 340, "proteomes": 131, "short_name": "DUF8529", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29292", "structures": 0, "taxa": 558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 280, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members if this family are predicted to have 10 transmembrane regions.", "domain_architectures": 2, "interpro_id": "IPR007294", "known_evidence_count": null, "matches": 357, "name": "Protein of unknown function (DUF401)", "partial_evidence_count": null, "pfam_id": "PF04165", "proteins": 339, "proteomes": 302, "short_name": "DUF401", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04165", "structures": 0, "taxa": 816, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the C-terminus (approximately 120 residues) of a number of hypothetical bacterial proteins of unknown function. These are possibly membrane proteins involved in immunity.", "domain_architectures": 3, "interpro_id": "IPR006541", "known_evidence_count": null, "matches": 339, "name": "Protein of unknown function (DUF1430)", "partial_evidence_count": null, "pfam_id": "PF07242", "proteins": 339, "proteomes": 273, "short_name": "DUF1430", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07242", "structures": 0, "taxa": 516, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several Enterobacterial proteins of around 60 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009954", "known_evidence_count": null, "matches": 339, "name": "Protein of unknown function (DUF1482)", "partial_evidence_count": null, "pfam_id": "PF07358", "proteins": 339, "proteomes": 268, "short_name": "DUF1482", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07358", "structures": 0, "taxa": 398, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised found in ABC transporter permeases. This domain family is found in bacteria and is approximately 300 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045611", "known_evidence_count": null, "matches": 339, "name": "Domain of unknown function (DUF6449)", "partial_evidence_count": null, "pfam_id": "PF20047", "proteins": 339, "proteomes": 333, "short_name": "DUF6449", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20047", "structures": 0, "taxa": 538, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 194, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, and is around 100 amino acids in length. This domain is found in association with [pfam:PF13442]. There is a conserved sequence motif GPLP.", "domain_architectures": 36, "interpro_id": "IPR046476", "known_evidence_count": null, "matches": 339, "name": "Domain of unknown function (DUF6797)", "partial_evidence_count": null, "pfam_id": "PF20601", "proteins": 339, "proteomes": 216, "short_name": "DUF6797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20601", "structures": 0, "taxa": 403, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Mollicutes.", "domain_architectures": 20, "interpro_id": "IPR021348", "known_evidence_count": null, "matches": 706, "name": "Protein of unknown function (DUF2963)", "partial_evidence_count": null, "pfam_id": "PF11178", "proteins": 338, "proteomes": 33, "short_name": "DUF2963", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11178", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 247 and 417 amino acids in length. Most of the proteins in this family have an N-terminal lipoprotein attachment site. These proteins have distant similarity to periplasmic ligand binding families such as [pfam:PF02608], which suggests that this family have a similar role.", "domain_architectures": 3, "interpro_id": "IPR024258", "known_evidence_count": null, "matches": 339, "name": "Protein of unknown function (DUF3798)", "partial_evidence_count": null, "pfam_id": "PF12683", "proteins": 338, "proteomes": 257, "short_name": "DUF3798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12683", "structures": 1, "taxa": 568, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length. There are two completely conserved residues (P and S) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025578", "known_evidence_count": null, "matches": 338, "name": "Domain of unknown function (DUF4359)", "partial_evidence_count": null, "pfam_id": "PF14271", "proteins": 338, "proteomes": 306, "short_name": "DUF4359", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14271", "structures": 0, "taxa": 782, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 133 and 164 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046124", "known_evidence_count": null, "matches": 344, "name": "Family of unknown function (DUF6121)", "partial_evidence_count": null, "pfam_id": "PF19616", "proteins": 338, "proteomes": 336, "short_name": "DUF6121", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19616", "structures": 0, "taxa": 361, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 228, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001520) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the aurantinin B biosynthetic gene cluster from Bacillus subtilis [[cite:PUB00098962]]. This family appears to be predominantly found in firmicutes.", "domain_architectures": 4, "interpro_id": "IPR045751", "known_evidence_count": null, "matches": 339, "name": "Family of unknown function (DUF6179)", "partial_evidence_count": null, "pfam_id": "PF19677", "proteins": 338, "proteomes": 332, "short_name": "DUF6179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19677", "structures": 0, "taxa": 613, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 191, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this bacterial family of proteins are annotated as YusU however no function is currently known. This family of proteins appears to be restricted to Bacillus spp.", "domain_architectures": 2, "interpro_id": "IPR020393", "known_evidence_count": null, "matches": 337, "name": "Protein of unknown function (DUF2573)", "partial_evidence_count": null, "pfam_id": "PF10835", "proteins": 337, "proteomes": 337, "short_name": "DUF2573", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10835", "structures": 0, "taxa": 417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 240, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Bacteria. The function is not known.", "domain_architectures": 6, "interpro_id": "IPR022565", "known_evidence_count": null, "matches": 339, "name": "Protein of unknown function (DUF2608)", "partial_evidence_count": null, "pfam_id": "PF11019", "proteins": 337, "proteomes": 199, "short_name": "DUF2608", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11019", "structures": 0, "taxa": 524, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 11, "interpro_id": "IPR025191", "known_evidence_count": null, "matches": 337, "name": "Protein of unknown function (DUF4125)", "partial_evidence_count": null, "pfam_id": "PF13526", "proteins": 337, "proteomes": 319, "short_name": "DUF4125", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13526", "structures": 0, "taxa": 611, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001707) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 3, "interpro_id": "IPR046003", "known_evidence_count": null, "matches": 337, "name": "Family of unknown function (DUF5959)", "partial_evidence_count": null, "pfam_id": "PF19384", "proteins": 337, "proteomes": 283, "short_name": "DUF5959", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19384", "structures": 0, "taxa": 360, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 106 and 169 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046574", "known_evidence_count": null, "matches": 337, "name": "Family of unknown function (DUF6634)", "partial_evidence_count": null, "pfam_id": "PF20339", "proteins": 337, "proteomes": 245, "short_name": "DUF6634", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20339", "structures": 0, "taxa": 410, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 298, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in uncharacterised sequences from nematodes. It may have a helix-turn-helix structure.", "domain_architectures": 16, "interpro_id": "IPR061522", "known_evidence_count": null, "matches": 349, "name": "Domain of unknown function (DUF8452)", "partial_evidence_count": null, "pfam_id": "PF28730", "proteins": 337, "proteomes": 59, "short_name": "DUF8452", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28730", "structures": 0, "taxa": 216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 220 and 340 amino acids in length. There is a single completely conserved residue G that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR025530", "known_evidence_count": null, "matches": 335, "name": "Domain of unknown function (DUF4417)", "partial_evidence_count": null, "pfam_id": "PF14386", "proteins": 335, "proteomes": 268, "short_name": "DUF4417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14386", "structures": 0, "taxa": 706, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 282 and 480 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR029134", "known_evidence_count": null, "matches": 385, "name": "Domain of unknown function (DUF4647)", "partial_evidence_count": null, "pfam_id": "PF15504", "proteins": 335, "proteomes": 200, "short_name": "DUF4647", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15504", "structures": 0, "taxa": 750, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 352 and 375 amino acids in length. It contains the conserved motifs FHFxxxP, GH and PD, and a conserved Phe residue at the C-terminal.", "domain_architectures": 14, "interpro_id": "IPR046653", "known_evidence_count": null, "matches": 335, "name": "Family of unknown function (DUF6765)", "partial_evidence_count": null, "pfam_id": "PF20551", "proteins": 335, "proteomes": 315, "short_name": "DUF6765", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20551", "structures": 0, "taxa": 762, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain of unknown function found in uncharacterised proteins from Dictyosteliales. It may adopt a Ig-like fold.", "domain_architectures": 67, "interpro_id": "IPR056645", "known_evidence_count": null, "matches": 348, "name": "Domain of unknown function (DUF7743)", "partial_evidence_count": null, "pfam_id": "PF24893", "proteins": 335, "proteomes": 25, "short_name": "DUF7743", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24893", "structures": 0, "taxa": 106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small protein of approximately 80 to 130 residues found in cyanobacteria and photosynthetic eukaryotes. The family is present in Cyanobacteria (Oscillatoriales, Nostocales) and in photosynthetic eukaryotes including Chlorophyta (green algae) and Stramenopiles (Ochrophyta). The distribution across cyanobacteria and algae with secondary plastids suggests these proteins may be plastid-associated. The function of this family remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061681", "known_evidence_count": null, "matches": 335, "name": "Family of unknown function (DUF8620)", "partial_evidence_count": null, "pfam_id": "PF30508", "proteins": 335, "proteomes": 326, "short_name": "DUF8620", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30508", "structures": 0, "taxa": 940, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]]. This family appears to be predominantly found in bacteria and archaea.", "domain_architectures": 3, "interpro_id": "IPR045926", "known_evidence_count": null, "matches": 334, "name": "Domain of unknown function (DUF6345)", "partial_evidence_count": null, "pfam_id": "PF19872", "proteins": 334, "proteomes": 300, "short_name": "DUF6345", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19872", "structures": 0, "taxa": 725, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 255, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It contains two pairs of highly conserved cysteine residues that may coordinate a metal ion. This domain is predicted to fold into a structure that is probably distantly related to domains with beta-tent fold (CL0080). The zinc ribbon in this domain is grafted into alpha/beta core.", "domain_architectures": 4, "interpro_id": "IPR059287", "known_evidence_count": null, "matches": 334, "name": "Domain of unknown function (DUF8243)", "partial_evidence_count": null, "pfam_id": "PF26731", "proteins": 334, "proteomes": 267, "short_name": "DUF8243", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26731", "structures": 0, "taxa": 646, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal helical hairpin domain found in DUF3084-containing membrane proteins. It follows the N-terminal DUF3084 domain ([pfam:PF11283]) and one or more intervening domains. The proteins contain an N-terminal signal peptide and a transmembrane helix, suggesting membrane localisation. In Nostoc sp. PCC 7120, the protein Alr4393 is predicted to be a single-pass membrane protein. In Synechococcus sp. WH 8102, the homologue SYNW0274 has been computationally linked to the nitrogen assimilation regulatory network controlled by NtcA. The family is found predominantly in Cyanobacteria (Nostocales, Oscillatoriales) and in Negativicutes (Veillonellaceae). The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR062273", "known_evidence_count": null, "matches": 334, "name": "DUF3084-associated C-terminal helical hairpin", "partial_evidence_count": null, "pfam_id": "PF30500", "proteins": 334, "proteomes": 330, "short_name": "DUF3084_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30500", "structures": 0, "taxa": 873, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 221, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family is unknown. Members all come from Burkholderia spp. [swissprot:A2WH83] is annotated as Serine/threonine-protein kinase, but this could not be confirmed.", "domain_architectures": 1, "interpro_id": "IPR018894", "known_evidence_count": null, "matches": 333, "name": "Protein of unknown function (DUF2471)", "partial_evidence_count": null, "pfam_id": "PF10616", "proteins": 333, "proteomes": 221, "short_name": "DUF2471", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10616", "structures": 0, "taxa": 268, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 324, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short family is largely confined to Caenorhabditis proteins. The function is not known. There are two well-conserved aspartate residues.", "domain_architectures": 9, "interpro_id": "IPR027913", "known_evidence_count": null, "matches": 348, "name": "Domain of unknown function (DUF4473)", "partial_evidence_count": null, "pfam_id": "PF14747", "proteins": 333, "proteomes": 15, "short_name": "DUF4473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14747", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR043761", "known_evidence_count": null, "matches": 333, "name": "Family of unknown function (DUF5707)", "partial_evidence_count": null, "pfam_id": "PF18968", "proteins": 333, "proteomes": 252, "short_name": "DUF5707", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18968", "structures": 0, "taxa": 282, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 171, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 4, "interpro_id": "IPR043863", "known_evidence_count": null, "matches": 334, "name": "Family of unknown function (DUF5825)", "partial_evidence_count": null, "pfam_id": "PF19142", "proteins": 333, "proteomes": 293, "short_name": "DUF5825", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19142", "structures": 0, "taxa": 413, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046126", "known_evidence_count": null, "matches": 333, "name": "Family of unknown function (DUF6123)", "partial_evidence_count": null, "pfam_id": "PF19618", "proteins": 333, "proteomes": 332, "short_name": "DUF6123", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19618", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 314, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in Halobacteria.", "domain_architectures": 3, "interpro_id": "IPR055685", "known_evidence_count": null, "matches": 333, "name": "Family of unknown function (DUF7261)", "partial_evidence_count": null, "pfam_id": "PF23922", "proteins": 333, "proteomes": 218, "short_name": "DUF7261", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23922", "structures": 0, "taxa": 346, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Enterobacterial proteins of around 100 residues in length. Members of this family are often described as YbjC. In E. coli the ybjC gene is located downstream of nfsA (which encodes the major oxygen-insensitive nitroreductase). It is thought that nfsA and ybjC form an operon an its promoter is a class I SoxS-dependent promoter [[cite:PUB00013045]]. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR010815", "known_evidence_count": null, "matches": 331, "name": "Protein of unknown function (DUF1418)", "partial_evidence_count": null, "pfam_id": "PF07214", "proteins": 331, "proteomes": 330, "short_name": "DUF1418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07214", "structures": 0, "taxa": 522, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 203, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains a semi-conserved sequence motif TxYPGxR. It is likely that this domain is a transmembrane domain composed of alpha-helices.", "domain_architectures": 5, "interpro_id": "IPR056074", "known_evidence_count": null, "matches": 332, "name": "Domain of unknown function (DUF7657)", "partial_evidence_count": null, "pfam_id": "PF24677", "proteins": 331, "proteomes": 309, "short_name": "DUF7657", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24677", "structures": 0, "taxa": 578, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 308, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of a family of uncharacterised proteins from archaea. The proteins in this family are predominantly found in halophilic archaea, including members of the Halobacteria class. The proteins typically range from 450 to 550 amino acids in length. The central domain is a methyltransferase.", "domain_architectures": 10, "interpro_id": "IPR058959", "known_evidence_count": null, "matches": 331, "name": "Domain of unknown function (DUF8157) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26487", "proteins": 331, "proteomes": 330, "short_name": "DUF8157_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26487", "structures": 0, "taxa": 524, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 50 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046132", "known_evidence_count": null, "matches": 330, "name": "Family of unknown function (DUF6129)", "partial_evidence_count": null, "pfam_id": "PF19624", "proteins": 330, "proteomes": 326, "short_name": "DUF6129", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19624", "structures": 0, "taxa": 580, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000464) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the xenoamicin A biosynthetic gene cluster from Xenorhabdus doucetiae [[cite:PUB00098890]]. This family appears to be predominantly found in proteobacteria.", "domain_architectures": 9, "interpro_id": "IPR045646", "known_evidence_count": null, "matches": 343, "name": "Family of unknown function (DUF6402)", "partial_evidence_count": null, "pfam_id": "PF19940", "proteins": 330, "proteomes": 217, "short_name": "DUF6402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19940", "structures": 0, "taxa": 475, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 127 and 139 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046572", "known_evidence_count": null, "matches": 330, "name": "Family of unknown function (DUF6632)", "partial_evidence_count": null, "pfam_id": "PF20337", "proteins": 330, "proteomes": 316, "short_name": "DUF6632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20337", "structures": 0, "taxa": 615, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_1065, a putative uncharacterized protein As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), It appears to be upregulated in the presence of host or other bacterial species vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 12, "interpro_id": "IPR024480", "known_evidence_count": null, "matches": 329, "name": "Domain of unknown function (DUF3868)", "partial_evidence_count": null, "pfam_id": "PF12984", "proteins": 329, "proteomes": 129, "short_name": "DUF3868", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12984", "structures": 0, "taxa": 206, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 150 residues in length and is mainly found in various Shewanella species. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR032251", "known_evidence_count": null, "matches": 329, "name": "Domain of unknown function (DUF4826)", "partial_evidence_count": null, "pfam_id": "PF16108", "proteins": 329, "proteomes": 316, "short_name": "DUF4826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16108", "structures": 0, "taxa": 482, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 302, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain three predicted transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR058357", "known_evidence_count": null, "matches": 328, "name": "Family of unknown function (DUF8044)", "partial_evidence_count": null, "pfam_id": "PF26161", "proteins": 328, "proteomes": 242, "short_name": "DUF8044", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26161", "structures": 0, "taxa": 437, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillaceae. Some members in this family of proteins are annotated as YkvR however this cannot be confirmed.", "domain_architectures": 1, "interpro_id": "IPR021596", "known_evidence_count": null, "matches": 327, "name": "Protein of unknown function (DUF3219)", "partial_evidence_count": null, "pfam_id": "PF11514", "proteins": 327, "proteomes": 321, "short_name": "DUF3219", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11514", "structures": 1, "taxa": 426, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 193, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 355 and 380 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025130", "known_evidence_count": null, "matches": 328, "name": "Protein of unknown function (DUF4056)", "partial_evidence_count": null, "pfam_id": "PF13265", "proteins": 327, "proteomes": 316, "short_name": "DUF4056", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13265", "structures": 0, "taxa": 556, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins. Although apparently having a bacterial origin these proteins appear in genomic contexts suggesting they are part of an integrated phage genome. Structurally these proteins are composed of a beta hairpin followed by a pair of alpha helices.", "domain_architectures": 2, "interpro_id": "IPR056114", "known_evidence_count": null, "matches": 327, "name": "Family of unknown function (DUF7697)", "partial_evidence_count": null, "pfam_id": "PF24752", "proteins": 327, "proteomes": 211, "short_name": "DUF7697", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24752", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region, within Arabidopsis thaliana proteins, of unknown function. Family members sometimes contain more than one copy.It has been reported that this domain will be found in other Brassicaceae.", "domain_architectures": 10, "interpro_id": "IPR009605", "known_evidence_count": null, "matches": 425, "name": "Protein of unknown function (DUF1216)", "partial_evidence_count": null, "pfam_id": "PF06746", "proteins": 326, "proteomes": 33, "short_name": "DUF1216", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06746", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial protein is uncharacterised.", "domain_architectures": 3, "interpro_id": "IPR014926", "known_evidence_count": null, "matches": 326, "name": "Protein of unknown function (DUF1804)", "partial_evidence_count": null, "pfam_id": "PF08822", "proteins": 326, "proteomes": 302, "short_name": "DUF1804", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08822", "structures": 0, "taxa": 727, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 313, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function however the structure has been determined. The protein consists of two alpha-helices packed on the same side of a central beta-hairpin [[cite:PUB00029976]].", "domain_architectures": 1, "interpro_id": "IPR024502", "known_evidence_count": null, "matches": 326, "name": "Protein of unknown function (DUF3194)", "partial_evidence_count": null, "pfam_id": "PF11419", "proteins": 326, "proteomes": 326, "short_name": "DUF3194", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11419", "structures": 2, "taxa": 521, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 240, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This entry represents the central domain from a family of Chordate proteins that includes C19orf68. These proteins appear to be transposon related. This domain appears to be closely related to the MULE RNaseH domain [pfam:PF10551].", "domain_architectures": 25, "interpro_id": "IPR048315", "known_evidence_count": null, "matches": 431, "name": "DUF5575 central RNaseH like domain", "partial_evidence_count": null, "pfam_id": "PF17738", "proteins": 326, "proteomes": 183, "short_name": "DUF5575", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17738", "structures": 0, "taxa": 633, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001709) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the nystatin biosynthetic gene cluster from Streptomyces albulus [[cite:PUB00098984]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 6, "interpro_id": "IPR045775", "known_evidence_count": null, "matches": 326, "name": "Family of unknown function (DUF6207)", "partial_evidence_count": null, "pfam_id": "PF19711", "proteins": 326, "proteomes": 221, "short_name": "DUF6207", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19711", "structures": 0, "taxa": 255, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 275, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from filamentous fungi. It contains ten highly conserved cysteine residues which are predicted to form disulfide bonds.", "domain_architectures": 9, "interpro_id": "IPR058526", "known_evidence_count": null, "matches": 329, "name": "Domain of unknown function (DUF8213)", "partial_evidence_count": null, "pfam_id": "PF26641", "proteins": 326, "proteomes": 312, "short_name": "DUF8213", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26641", "structures": 0, "taxa": 666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A member of the deaminase fold that binds an unknown ligand in the crystal structure. The protein is ADP-ribosylated at a conserved aspartate [[cite:PUB00046766]]. Contextual analysis suggests that the domain is likely to bind NAD or ADP ribose either to sense redox states or to function as a regulatory ADP ribosyltransferase [[cite:PUB00057473]].", "domain_architectures": 7, "interpro_id": "IPR015067", "known_evidence_count": null, "matches": 325, "name": "Domain of unknown function (DUF1893)", "partial_evidence_count": null, "pfam_id": "PF08973", "proteins": 325, "proteomes": 320, "short_name": "TM1506", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08973", "structures": 2, "taxa": 673, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR022704", "known_evidence_count": null, "matches": 325, "name": "Protein of unknown function (DUF2746)", "partial_evidence_count": null, "pfam_id": "PF10874", "proteins": 325, "proteomes": 322, "short_name": "DUF2746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10874", "structures": 0, "taxa": 761, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 136, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000965) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the C-1027 biosynthetic gene cluster from Streptomyces globisporus [[cite:PUB00099378],[cite:PUB00099425]].", "domain_architectures": 1, "interpro_id": "IPR046051", "known_evidence_count": null, "matches": 325, "name": "Family of unknown function (DUF6009)", "partial_evidence_count": null, "pfam_id": "PF19472", "proteins": 325, "proteomes": 220, "short_name": "DUF6009", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19472", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found mainly in Proteobacteria. These proteins are predicted to adopt an alpha-helical structure. They contain a highly conserved RXXXE-motif and an invariant histidine that may have a functional role.", "domain_architectures": 1, "interpro_id": "IPR054257", "known_evidence_count": null, "matches": 325, "name": "Family of unknown function (DUF6988)", "partial_evidence_count": null, "pfam_id": "PF22491", "proteins": 325, "proteomes": 300, "short_name": "DUF6988", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22491", "structures": 0, "taxa": 611, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a region of tetratricopeptide (TPR)-like repeats found in a group of uncharacterised proteins from proteobacteria. Its function is unknown.", "domain_architectures": 32, "interpro_id": "IPR059418", "known_evidence_count": null, "matches": 332, "name": "Domain of unknown function (DUF8374)", "partial_evidence_count": null, "pfam_id": "PF28160", "proteins": 325, "proteomes": 96, "short_name": "DUF8374", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28160", "structures": 0, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 88, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from the Siphoviruses and other bacterial viruses. Some members of this family are described as putative minor structural proteins.", "domain_architectures": 14, "interpro_id": "IPR008577", "known_evidence_count": null, "matches": 374, "name": "Siphovirus protein of unknown function (DUF859)", "partial_evidence_count": null, "pfam_id": "PF05895", "proteins": 324, "proteomes": 290, "short_name": "DUF859", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05895", "structures": 0, "taxa": 666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of presumed domains is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 196 and 222 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046109", "known_evidence_count": null, "matches": 325, "name": "Domain of unknown function (DUF6046)", "partial_evidence_count": null, "pfam_id": "PF19512", "proteins": 324, "proteomes": 266, "short_name": "DUF6046", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19512", "structures": 0, "taxa": 515, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in proteobacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046634", "known_evidence_count": null, "matches": 324, "name": "Family of unknown function (DUF6746)", "partial_evidence_count": null, "pfam_id": "PF20531", "proteins": 324, "proteomes": 309, "short_name": "DUF6746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20531", "structures": 0, "taxa": 509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They share sequence similarity with DarT toxin and are likely to adopt the same structure.", "domain_architectures": 1, "interpro_id": "IPR054271", "known_evidence_count": null, "matches": 324, "name": "Family of unknown function (DUF7002)", "partial_evidence_count": null, "pfam_id": "PF22531", "proteins": 324, "proteomes": 315, "short_name": "DUF7002", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22531", "structures": 0, "taxa": 631, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 302, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is probably distantly related to CcmS and [pfam:PF26617] and it is predicted to adopt topologically similar structure. It is found frequently in combination with zf-MYND [pfam:PF01753] and in multiple copies.", "domain_architectures": 21, "interpro_id": "IPR058518", "known_evidence_count": null, "matches": 354, "name": "Domain of unknown function (DUF8205)", "partial_evidence_count": null, "pfam_id": "PF26632", "proteins": 324, "proteomes": 63, "short_name": "DUF8205", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26632", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 230, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 118 to 142 amino acids in length. This protein has a conserved WSRE sequence motif.", "domain_architectures": 2, "interpro_id": "IPR021947", "known_evidence_count": null, "matches": 323, "name": "Protein of unknown function (DUF3564)", "partial_evidence_count": null, "pfam_id": "PF12087", "proteins": 323, "proteomes": 174, "short_name": "DUF3564", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12087", "structures": 0, "taxa": 195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small protein that has a domain with a structure resembling a double stranded RNA-binding domain such as [pfam:PF00035]. Thus suggesting this protein may also have a dsRNA binding function. This is supported by the presence of several conserved positively charged residues.", "domain_architectures": 1, "interpro_id": "IPR054193", "known_evidence_count": null, "matches": 323, "name": "Domain of unknown function (DUF6898)", "partial_evidence_count": null, "pfam_id": "PF21839", "proteins": 323, "proteomes": 322, "short_name": "DUF6898", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21839", "structures": 0, "taxa": 533, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a helical domain found in plant proteins. The function of these proteins is unknown.", "domain_architectures": 14, "interpro_id": "IPR054290", "known_evidence_count": null, "matches": 323, "name": "Domain of unknown function (DUF7026)", "partial_evidence_count": null, "pfam_id": "PF22950", "proteins": 323, "proteomes": 252, "short_name": "DUF7026", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22950", "structures": 0, "taxa": 684, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 306, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised archaeal proteins. They contain two pairs of conserved cysteine residues and are predicted to adopt a fold typical for Treble-clef zinc fingers.", "domain_architectures": 1, "interpro_id": "IPR055998", "known_evidence_count": null, "matches": 323, "name": "Family of unknown function (DUF7576)", "partial_evidence_count": null, "pfam_id": "PF24461", "proteins": 323, "proteomes": 219, "short_name": "DUF7576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24461", "structures": 0, "taxa": 352, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 228, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in Bacteroidetes. Proteins in this family are typically between 531 and 570 amino acids in length. There is a conserved GGVCR sequence motif.", "domain_architectures": 2, "interpro_id": "IPR046070", "known_evidence_count": null, "matches": 328, "name": "Family of unknown function (DUF6029)", "partial_evidence_count": null, "pfam_id": "PF19494", "proteins": 322, "proteomes": 315, "short_name": "DUF6029", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19494", "structures": 0, "taxa": 562, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021376", "known_evidence_count": null, "matches": 321, "name": "Protein of unknown function (DUF2999)", "partial_evidence_count": null, "pfam_id": "PF11212", "proteins": 321, "proteomes": 320, "short_name": "DUF2999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11212", "structures": 0, "taxa": 396, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021500", "known_evidence_count": null, "matches": 321, "name": "Protein of unknown function (DUF3156)", "partial_evidence_count": null, "pfam_id": "PF11354", "proteins": 321, "proteomes": 310, "short_name": "DUF3156", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11354", "structures": 0, "taxa": 465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 296, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of an uncharacterised putative enzyme. It shows structural similarity to the N-terminal domain of enolase.", "domain_architectures": 2, "interpro_id": "IPR060062", "known_evidence_count": null, "matches": 321, "name": "Domain of unknown function (DUF8230) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26684", "proteins": 321, "proteomes": 277, "short_name": "DUF8230_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26684", "structures": 0, "taxa": 456, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short protein is likely to be of phage origin. For example it is found in the [swissprot:B6DZ51] Enterobacteria phage YYZ-2008. It is largely found in enteric bacteria. The molecular function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR025317", "known_evidence_count": null, "matches": 320, "name": "Domain of unknown function (DUF4222)", "partial_evidence_count": null, "pfam_id": "PF13973", "proteins": 320, "proteomes": 216, "short_name": "DUF4222", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13973", "structures": 0, "taxa": 350, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046166", "known_evidence_count": null, "matches": 320, "name": "Family of unknown function (DUF6168)", "partial_evidence_count": null, "pfam_id": "PF19665", "proteins": 320, "proteomes": 320, "short_name": "DUF6168", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19665", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 301, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised halobacterial proteins.", "domain_architectures": 2, "interpro_id": "IPR058289", "known_evidence_count": null, "matches": 323, "name": "Family of unknown function (DUF7983)", "partial_evidence_count": null, "pfam_id": "PF25943", "proteins": 320, "proteomes": 163, "short_name": "DUF7983", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25943", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 236, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021347", "known_evidence_count": null, "matches": 319, "name": "Protein of unknown function (DUF2964)", "partial_evidence_count": null, "pfam_id": "PF11177", "proteins": 319, "proteomes": 173, "short_name": "DUF2964", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11177", "structures": 0, "taxa": 196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 243, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is the C-terminal domain of TM_1086 which consists of a 3-layer sandwich.", "domain_architectures": 2, "interpro_id": "IPR048399", "known_evidence_count": null, "matches": 319, "name": "Domain of unknown function (DUF4438), C-terminal", "partial_evidence_count": null, "pfam_id": "PF20999", "proteins": 319, "proteomes": 266, "short_name": "DUF4438_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20999", "structures": 2, "taxa": 629, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 306, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found mainly in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination.", "domain_architectures": 3, "interpro_id": "IPR055995", "known_evidence_count": null, "matches": 319, "name": "Domain of unknown function (DUF7573)", "partial_evidence_count": null, "pfam_id": "PF24458", "proteins": 319, "proteomes": 261, "short_name": "DUF7573", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24458", "structures": 0, "taxa": 411, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 293, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of an uncharacterised putative enzyme. It shows structural similarity to the C-terminal domain of enolase and has a TIM barrel fold.", "domain_architectures": 2, "interpro_id": "IPR060063", "known_evidence_count": null, "matches": 319, "name": "Domain of unknown function (DUF8230) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26685", "proteins": 319, "proteomes": 277, "short_name": "DUF8230_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26685", "structures": 0, "taxa": 456, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some of the members of this family are hypothetical bacterial and archaeal proteins, but others are annotated as being cation transporters expressed by the archaebacterium Methanosarcina mazei ([swissprot:Q8PXG5], [swissprot:Q8PXG7] and [swissprot:Q8PXG8]).", "domain_architectures": 2, "interpro_id": "IPR012443", "known_evidence_count": null, "matches": 318, "name": "Protein of unknown function (DUF1646)", "partial_evidence_count": null, "pfam_id": "PF07854", "proteins": 318, "proteomes": 245, "short_name": "DUF1646", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07854", "structures": 0, "taxa": 427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR018757", "known_evidence_count": null, "matches": 318, "name": "Uncharacterized protein conserved in bacteria (DUF2316)", "partial_evidence_count": null, "pfam_id": "PF10078", "proteins": 318, "proteomes": 307, "short_name": "DUF2316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10078", "structures": 0, "taxa": 549, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of bacterial proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR020140", "known_evidence_count": null, "matches": 318, "name": "Protein of unknown function (DUF2553)", "partial_evidence_count": null, "pfam_id": "PF10830", "proteins": 318, "proteomes": 297, "short_name": "DUF2553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10830", "structures": 0, "taxa": 403, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 162, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus cereus.", "domain_architectures": 6, "interpro_id": "IPR021631", "known_evidence_count": null, "matches": 318, "name": "Protein of unknown function (DUF3238)", "partial_evidence_count": null, "pfam_id": "PF11579", "proteins": 318, "proteomes": 263, "short_name": "DUF3238", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11579", "structures": 1, "taxa": 477, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 210, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]].", "domain_architectures": 2, "interpro_id": "IPR024363", "known_evidence_count": null, "matches": 319, "name": "Protein of unknown function (DUF3853)", "partial_evidence_count": null, "pfam_id": "PF12964", "proteins": 318, "proteomes": 222, "short_name": "DUF3853", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12964", "structures": 0, "taxa": 358, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function, found in Bacillales. Members of the family are predicted to have between 4 and 5 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035289", "known_evidence_count": null, "matches": 318, "name": "Family of unknown function (DUF5366)", "partial_evidence_count": null, "pfam_id": "PF17328", "proteins": 318, "proteomes": 316, "short_name": "DUF5366", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17328", "structures": 0, "taxa": 413, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 299, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found C-terminal in functionally uncharacterised archaeal proteins. This domain is predicted to adopt winged helix domain structure. It is usually located upstream [pfam:PF19810] and this domain organisation as well as the predicted structure are reminiscent of CRISPR-associated protein, Csa3.", "domain_architectures": 6, "interpro_id": "IPR054162", "known_evidence_count": null, "matches": 318, "name": "DUF6293 C-terminal winged helix domain", "partial_evidence_count": null, "pfam_id": "PF22665", "proteins": 318, "proteomes": 250, "short_name": "WHD_DUF6293", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22665", "structures": 0, "taxa": 506, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 296, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria and Methanomicrobia.", "domain_architectures": 1, "interpro_id": "IPR043827", "known_evidence_count": null, "matches": 317, "name": "Family of unknown function (DUF5804)", "partial_evidence_count": null, "pfam_id": "PF19120", "proteins": 317, "proteomes": 316, "short_name": "DUF5804", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19120", "structures": 0, "taxa": 500, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 234 and 254 amino acids in length. This family contains two repeated domains that each contain a conserved CXXC and GXCXXH sequence motif. This suggests that these proteins are likely to be metal binding.", "domain_architectures": 3, "interpro_id": "IPR045706", "known_evidence_count": null, "matches": 328, "name": "Family of unknown function (DUF6062)", "partial_evidence_count": null, "pfam_id": "PF19538", "proteins": 317, "proteomes": 294, "short_name": "DUF6062", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19538", "structures": 0, "taxa": 676, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 303, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. These proteins are predicted to be largely disordered. They contain a semi-conserved VIADxx[DE]xAW sequence motif.", "domain_architectures": 1, "interpro_id": "IPR055978", "known_evidence_count": null, "matches": 317, "name": "Family of unknown function (DUF7556)", "partial_evidence_count": null, "pfam_id": "PF24433", "proteins": 317, "proteomes": 235, "short_name": "DUF7556", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24433", "structures": 0, "taxa": 381, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is the N-terminal domain of TM_1086 and related proteins.", "domain_architectures": 2, "interpro_id": "IPR029433", "known_evidence_count": null, "matches": 316, "name": "Domain of unknown function (DUF4438), N-terminal", "partial_evidence_count": null, "pfam_id": "PF14505", "proteins": 316, "proteomes": 264, "short_name": "DUF4438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14505", "structures": 2, "taxa": 625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 287, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 176 and 214 amino acids in length. There is a single completely conserved residue W that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR032145", "known_evidence_count": null, "matches": 318, "name": "Domain of unknown function (DUF4818)", "partial_evidence_count": null, "pfam_id": "PF16089", "proteins": 316, "proteomes": 125, "short_name": "DUF4818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16089", "structures": 0, "taxa": 481, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 58 and 74 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR045764", "known_evidence_count": null, "matches": 316, "name": "Family of unknown function (DUF6132)", "partial_evidence_count": null, "pfam_id": "PF19628", "proteins": 316, "proteomes": 305, "short_name": "DUF6132", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19628", "structures": 0, "taxa": 578, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from bacteria and protostome animals. It is predicted to fold into a curved meander beta-sheet. It contains four highly conserved cysteine residues, two of which are predicted to cluster together in space and are likely involved in disulfide bond formation.", "domain_architectures": 1, "interpro_id": "IPR054243", "known_evidence_count": null, "matches": 316, "name": "Domain of unknown function (DUF6970)", "partial_evidence_count": null, "pfam_id": "PF22311", "proteins": 316, "proteomes": 249, "short_name": "DUF6970", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22311", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 297, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble Zinc beta-ribbon domains.", "domain_architectures": 2, "interpro_id": "IPR057157", "known_evidence_count": null, "matches": 316, "name": "Domain of unknown function (DUF7835)", "partial_evidence_count": null, "pfam_id": "PF25205", "proteins": 316, "proteomes": 218, "short_name": "DUF7835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25205", "structures": 0, "taxa": 348, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 299, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble Zinc beta-ribbon domains.", "domain_architectures": 4, "interpro_id": "IPR057158", "known_evidence_count": null, "matches": 316, "name": "Domain of unknown function (DUF7836)", "partial_evidence_count": null, "pfam_id": "PF25206", "proteins": 316, "proteomes": 269, "short_name": "DUF7836", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25206", "structures": 0, "taxa": 474, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein family related to [pfam:PF11580] (DUF3239). The family is found in Cyanobacteria (Oscillatoriales, Nostocales, Chroococcales) and in photosynthetic eukaryotes including Chlorophyta (green algae) and Stramenopiles (Ochrophyta). The presence in eukaryotic algae likely reflects plastid-encoded or plastid-targeted proteins derived from the cyanobacterial endosymbiont ancestor. The function of this family remains to be determined.", "domain_architectures": 7, "interpro_id": "IPR061680", "known_evidence_count": null, "matches": 319, "name": "Family of unknown function (DUF8619)", "partial_evidence_count": null, "pfam_id": "PF30501", "proteins": 316, "proteomes": 304, "short_name": "DUF8619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30501", "structures": 0, "taxa": 871, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is produced from gene PA1123 in Pseudomonas. It contains three alpha helices and six beta strands and is thought to be monomeric. It appears to be present in the biofilm layer and may be a lipoprotein.", "domain_architectures": 1, "interpro_id": "IPR023117", "known_evidence_count": null, "matches": 315, "name": "Protein of unknown function (DUF2025)", "partial_evidence_count": null, "pfam_id": "PF09634", "proteins": 315, "proteomes": 314, "short_name": "DUF2025", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09634", "structures": 1, "taxa": 326, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain family is found in viruses, and is approximately 40 amino acids in length. There is a conserved MFNLKF sequence motif. There are two completely conserved residues (E and P) that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR024378", "known_evidence_count": null, "matches": 315, "name": "RNA dependent RNA polymerase", "partial_evidence_count": null, "pfam_id": "PF12426", "proteins": 315, "proteomes": 56, "short_name": "DUF3674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12426", "structures": 15, "taxa": 116, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small protein that has a likely signal peptide that takes up most of the sequence. Thus a small peptide might be released from these proteins.", "domain_architectures": 1, "interpro_id": "IPR054188", "known_evidence_count": null, "matches": 315, "name": "Family of unknown function (DUF6893)", "partial_evidence_count": null, "pfam_id": "PF21833", "proteins": 315, "proteomes": 310, "short_name": "DUF6893", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21833", "structures": 0, "taxa": 492, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain found in a range of bacterial and phage proteins. In a few proteins it is associated with [pfam:PF11994]. This region is composed of two alpha helices.", "domain_architectures": 3, "interpro_id": "IPR054195", "known_evidence_count": null, "matches": 317, "name": "Family of unknown function (DUF6900)", "partial_evidence_count": null, "pfam_id": "PF21841", "proteins": 315, "proteomes": 252, "short_name": "DUF6900", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21841", "structures": 0, "taxa": 553, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 139, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. These proteins contain a highly conserved lipoprotein-type signal peptide sequence at the N terminus and two invariant cysteine residues within this domain suggesting their extracytoplasmic localisation.", "domain_architectures": 1, "interpro_id": "IPR055903", "known_evidence_count": null, "matches": 315, "name": "Domain of unknown function (DUF7480)", "partial_evidence_count": null, "pfam_id": "PF24295", "proteins": 315, "proteomes": 147, "short_name": "DUF7480", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24295", "structures": 0, "taxa": 228, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain from a family of uncharacterised proteins from halophilic archaea. The family is predominantly found in the class Halobacteria, which includes members from the families Natrialbaceae and Haloferacaceae. Proteins in this family are typically between 150 and 350 amino acids in length. They are predicted to be membrane-associated, as suggested by the presence of two transmembrane helices in the central domain.", "domain_architectures": 19, "interpro_id": "IPR058962", "known_evidence_count": null, "matches": 315, "name": "Domain of unknown function (DUF8108) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26438", "proteins": 315, "proteomes": 272, "short_name": "DUF8108_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26438", "structures": 0, "taxa": 506, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 219, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is an alpha helical domain found at the C-terminal region of the hypothetical protein Rv3899c from Mycobacterium tuberculosis which is conserved across mycobacteria [[cite:PUB00091180]].", "domain_architectures": 2, "interpro_id": "IPR040833", "known_evidence_count": null, "matches": 314, "name": "Family of unknown function (DUF5631)", "partial_evidence_count": null, "pfam_id": "PF18645", "proteins": 314, "proteomes": 146, "short_name": "DUF5631", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18645", "structures": 1, "taxa": 168, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 110 residues in length. Members of this family seem to be specific to Agrobacterium species and to Rhizobium loti. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009862", "known_evidence_count": null, "matches": 313, "name": "Protein of unknown function (DUF1419)", "partial_evidence_count": null, "pfam_id": "PF07215", "proteins": 313, "proteomes": 223, "short_name": "DUF1419", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07215", "structures": 0, "taxa": 392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in various Bacteroides and Parabacteroides species. Proteins in this family are around 400 amino acids in length.", "domain_architectures": 17, "interpro_id": "IPR032181", "known_evidence_count": null, "matches": 319, "name": "Domain of unknown function (DUF5013)", "partial_evidence_count": null, "pfam_id": "PF16405", "proteins": 313, "proteomes": 204, "short_name": "DUF5013", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16405", "structures": 0, "taxa": 310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 258 and 288 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046503", "known_evidence_count": null, "matches": 313, "name": "Family of unknown function (DUF6681)", "partial_evidence_count": null, "pfam_id": "PF20386", "proteins": 313, "proteomes": 309, "short_name": "DUF6681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20386", "structures": 0, "taxa": 470, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 264 and 710 amino acids in length. Many of these proteins have a lipid attachment site suggesting they are lipoproteins.", "domain_architectures": 16, "interpro_id": "IPR027840", "known_evidence_count": null, "matches": 312, "name": "Domain of unknown function (DUF4493)", "partial_evidence_count": null, "pfam_id": "PF14900", "proteins": 312, "proteomes": 89, "short_name": "DUF4493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14900", "structures": 0, "taxa": 162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found primarily in Firmicute bacteria. Proteins in this family are typically between 130 and 155 amino acids in length. There is a conserved AFNL sequence motif.", "domain_architectures": 3, "interpro_id": "IPR045721", "known_evidence_count": null, "matches": 312, "name": "Family of unknown function (DUF6075)", "partial_evidence_count": null, "pfam_id": "PF19552", "proteins": 312, "proteomes": 235, "short_name": "DUF6075", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19552", "structures": 0, "taxa": 440, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 217, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 35 and 59 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045407", "known_evidence_count": null, "matches": 314, "name": "Family of unknown function (DUF6512)", "partial_evidence_count": null, "pfam_id": "PF20122", "proteins": 312, "proteomes": 303, "short_name": "DUF6512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20122", "structures": 0, "taxa": 641, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in uncharacterised bacterial proteins. This domain occurs either standalone or in combination with other domains. It contains conserved cysteines and histidine that may be involved in Zn2+ coordination.", "domain_architectures": 2, "interpro_id": "IPR053918", "known_evidence_count": null, "matches": 312, "name": "Domain of unknown function (DUF6980)", "partial_evidence_count": null, "pfam_id": "PF22400", "proteins": 312, "proteomes": 285, "short_name": "DUF6980", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22400", "structures": 0, "taxa": 595, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 293, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short proteins from archaea. Members are predicted to adopt an alpha-helical structure at the N terminus and show a disordered C-terminal region. In some lineages of archaea, the gene encoding these proteins is found upstream of SMC (chromosome segregation protein).", "domain_architectures": 1, "interpro_id": "IPR055940", "known_evidence_count": null, "matches": 312, "name": "Family of unknown function (DUF7518)", "partial_evidence_count": null, "pfam_id": "PF24362", "proteins": 312, "proteomes": 309, "short_name": "DUF7518", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24362", "structures": 0, "taxa": 495, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 12 } }, "demotion_reasons": [], "description": "This family consists of several repeats of around 29 residues in length. Members of this family are found in the variable surface lipoproteins in Mycoplasma bovis and in mammalian neurofilament triplet H (NefH or NF-H) proteins. This repeat contains several Lys-Ser-Pro (KSP) motifs and in NefH these are thought to function as the main target for neurofilament directed protein kinases in vivo [[cite:PUB00013013]].", "domain_architectures": 37, "interpro_id": "IPR010790", "known_evidence_count": null, "matches": 746, "name": "Repeat of unknown function (DUF1388)", "partial_evidence_count": null, "pfam_id": "PF07142", "proteins": 311, "proteomes": 189, "short_name": "DUF1388", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07142", "structures": 0, "taxa": 748, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 219, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of putative lipoproteins from bacteria. The family is probably related to the NTF2-like transpeptidase family.", "domain_architectures": 3, "interpro_id": "IPR024267", "known_evidence_count": null, "matches": 311, "name": "Domain of unknown function (DUF4878)", "partial_evidence_count": null, "pfam_id": "PF12870", "proteins": 311, "proteomes": 294, "short_name": "DUF4878", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12870", "structures": 1, "taxa": 622, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 270, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 63 and 76 amino acids in length. There is a conserved TPPTPT sequence motif.", "domain_architectures": 3, "interpro_id": "IPR027864", "known_evidence_count": null, "matches": 311, "name": "Domain of unknown function (DUF4597)", "partial_evidence_count": null, "pfam_id": "PF15366", "proteins": 311, "proteomes": 195, "short_name": "DUF4597", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15366", "structures": 0, "taxa": 683, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterobacteria phage T7.", "domain_architectures": 1, "interpro_id": "IPR035156", "known_evidence_count": null, "matches": 311, "name": "Family of unknown function (DUF5471)", "partial_evidence_count": null, "pfam_id": "PF17565", "proteins": 311, "proteomes": 308, "short_name": "DUF5471", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17565", "structures": 0, "taxa": 663, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 345 and 372 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046611", "known_evidence_count": null, "matches": 311, "name": "Family of unknown function (DUF6670)", "partial_evidence_count": null, "pfam_id": "PF20375", "proteins": 311, "proteomes": 226, "short_name": "DUF6670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20375", "structures": 0, "taxa": 368, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 107, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised domain found in phage proteins.", "domain_architectures": 2, "interpro_id": "IPR055849", "known_evidence_count": null, "matches": 313, "name": "Domain of unknown function (DUF7426)", "partial_evidence_count": null, "pfam_id": "PF24201", "proteins": 311, "proteomes": 246, "short_name": "DUF7426", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24201", "structures": 0, "taxa": 472, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 155, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt an alpha/beta structure consisting of curved beta-sheet and alpha-helices packed on the concave side of it.", "domain_architectures": 6, "interpro_id": "IPR056055", "known_evidence_count": null, "matches": 390, "name": "Domain of unknown function (DUF7638)", "partial_evidence_count": null, "pfam_id": "PF24644", "proteins": 311, "proteomes": 300, "short_name": "DUF7638", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24644", "structures": 0, "taxa": 522, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 179, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It has similarity to the C-terminal domain of Haemocyanin and it is predicted to adopt similar beta-sandwich fold.", "domain_architectures": 20, "interpro_id": "IPR057190", "known_evidence_count": null, "matches": 311, "name": "Domain of unknown function (DUF7868)", "partial_evidence_count": null, "pfam_id": "PF25271", "proteins": 311, "proteomes": 281, "short_name": "DUF7868", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25271", "structures": 1, "taxa": 602, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This N-terminal domain is not expressed in the 'Short' isoform of Collagen A [[cite:PUB00012268]].", "domain_architectures": 36, "interpro_id": "IPR010363", "known_evidence_count": null, "matches": 314, "name": "Domain of Unknown Function (DUF959)", "partial_evidence_count": null, "pfam_id": "PF06121", "proteins": 310, "proteomes": 164, "short_name": "DUF959", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06121", "structures": 0, "taxa": 621, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 241, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of protein has no known function, but it may be distantly related to the thioredoxin fold. It contains the CXXC motif that is characteristic of thioredoxins.", "domain_architectures": 11, "interpro_id": "IPR021219", "known_evidence_count": null, "matches": 310, "name": "Domain of unknown function (DUF2703)", "partial_evidence_count": null, "pfam_id": "PF10865", "proteins": 310, "proteomes": 278, "short_name": "DUF2703", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10865", "structures": 0, "taxa": 760, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 294, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 9, "interpro_id": "IPR021470", "known_evidence_count": null, "matches": 334, "name": "Protein of unknown function (DUF3123)", "partial_evidence_count": null, "pfam_id": "PF11321", "proteins": 310, "proteomes": 35, "short_name": "DUF3123", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11321", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from plants. It is predicted to adopt three-helical bundle.", "domain_architectures": 10, "interpro_id": "IPR056029", "known_evidence_count": null, "matches": 313, "name": "Domain of unknown function (DUF7610)", "partial_evidence_count": null, "pfam_id": "PF24583", "proteins": 310, "proteomes": 235, "short_name": "DUF7610", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24583", "structures": 0, "taxa": 694, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 138, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found at the C-terminal of a group of uncharacterised proteins from bacteria. It may adopt a beta-sandwich fold related to CBMs (carbohydrate binding modules). It is usually associated with [pfam:PF11340].", "domain_architectures": 1, "interpro_id": "IPR061526", "known_evidence_count": null, "matches": 310, "name": "Domain of unknown function (DUF8456)", "partial_evidence_count": null, "pfam_id": "PF28772", "proteins": 310, "proteomes": 308, "short_name": "DUF8456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28772", "structures": 0, "taxa": 435, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 224, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in bacterial proteins containing at the N terminus a methyltransferase domain.", "domain_architectures": 11, "interpro_id": "IPR061899", "known_evidence_count": null, "matches": 319, "name": "Domain of unknown function (DUF8838)", "partial_evidence_count": null, "pfam_id": "PF31198", "proteins": 310, "proteomes": 281, "short_name": "DUF8838", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31198", "structures": 0, "taxa": 776, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021481", "known_evidence_count": null, "matches": 309, "name": "Protein of unknown function (DUF3134)", "partial_evidence_count": null, "pfam_id": "PF11332", "proteins": 309, "proteomes": 245, "short_name": "DUF3134", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11332", "structures": 0, "taxa": 675, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021697", "known_evidence_count": null, "matches": 314, "name": "Protein of unknown function (DUF3278)", "partial_evidence_count": null, "pfam_id": "PF11683", "proteins": 309, "proteomes": 232, "short_name": "DUF3278", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11683", "structures": 0, "taxa": 377, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. This domain is found in bacteria. This presumed domain is about 260 amino acids in length. This domain is found associated with [pfam:PF02518], [pfam:PF00512].", "domain_architectures": 4, "interpro_id": "IPR021821", "known_evidence_count": null, "matches": 308, "name": "Domain of unknown function (DUF3404)", "partial_evidence_count": null, "pfam_id": "PF11884", "proteins": 308, "proteomes": 243, "short_name": "DUF3404", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11884", "structures": 9, "taxa": 342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 295, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 2, "interpro_id": "IPR043868", "known_evidence_count": null, "matches": 311, "name": "Family of unknown function (DUF5828)", "partial_evidence_count": null, "pfam_id": "PF19146", "proteins": 308, "proteomes": 289, "short_name": "DUF5828", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19146", "structures": 0, "taxa": 457, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several bacteriophage proteins. Some of the proteins in this family have been labeled putative cro repressor proteins.", "domain_architectures": 1, "interpro_id": "IPR008003", "known_evidence_count": null, "matches": 307, "name": "Protein of unknown function (DUF739)", "partial_evidence_count": null, "pfam_id": "PF05339", "proteins": 307, "proteomes": 277, "short_name": "DUF739", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05339", "structures": 2, "taxa": 602, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from nematodes. It is predicted to adopt a globular structure consisting of a three-stranded antiparallel beta-sheet and three alpha-helices packed on one side of it.", "domain_architectures": 28, "interpro_id": "IPR056053", "known_evidence_count": null, "matches": 308, "name": "Domain of unknown function (DUF7636)", "partial_evidence_count": null, "pfam_id": "PF24642", "proteins": 307, "proteomes": 99, "short_name": "DUF7636", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24642", "structures": 0, "taxa": 231, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 150 residues in length which are specific to Escherichia coli, Salmonella species and Yersinia pestis. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009587", "known_evidence_count": null, "matches": 306, "name": "Protein of unknown function (DUF1198)", "partial_evidence_count": null, "pfam_id": "PF06711", "proteins": 306, "proteomes": 305, "short_name": "DUF1198", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06711", "structures": 1, "taxa": 442, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Vibrionaceae.", "domain_architectures": 1, "interpro_id": "IPR021271", "known_evidence_count": null, "matches": 306, "name": "Protein of unknown function (DUF2850)", "partial_evidence_count": null, "pfam_id": "PF11012", "proteins": 306, "proteomes": 189, "short_name": "DUF2850", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11012", "structures": 0, "taxa": 240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 254, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found at the N-terminal of fungal proteins, such as SwissProt:O74728 from S.pombe, a protein thought to be localised in the ER. From AlphaFold structure prediction, it can be inferred that this domain may adopt an alpha/beta structure consisting of six antiparallel beta-strands surrounded by three or four alpha-helices.", "domain_architectures": 6, "interpro_id": "IPR049205", "known_evidence_count": null, "matches": 308, "name": "Domain of unknown function (DUF6859)", "partial_evidence_count": null, "pfam_id": "PF21656", "proteins": 306, "proteomes": 302, "short_name": "DUF6859", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21656", "structures": 0, "taxa": 801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR043778", "known_evidence_count": null, "matches": 305, "name": "Family of unknown function (DUF5720)", "partial_evidence_count": null, "pfam_id": "PF18987", "proteins": 305, "proteomes": 152, "short_name": "DUF5720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18987", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a globular structure composed of a three helical bundle.", "domain_architectures": 5, "interpro_id": "IPR056056", "known_evidence_count": null, "matches": 305, "name": "Domain of unknown function (DUF7639)", "partial_evidence_count": null, "pfam_id": "PF24645", "proteins": 305, "proteomes": 297, "short_name": "DUF7639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24645", "structures": 0, "taxa": 518, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes bacteria. Proteins in this family are approximately 150 amino acids in length. This family contains 4 conserved cysteines towards the N-terminus which may form a zinc-binding motif.", "domain_architectures": 2, "interpro_id": "IPR045724", "known_evidence_count": null, "matches": 304, "name": "Family of unknown function (DUF6078)", "partial_evidence_count": null, "pfam_id": "PF19555", "proteins": 304, "proteomes": 126, "short_name": "DUF6078", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19555", "structures": 0, "taxa": 213, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 109 and 273 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046516", "known_evidence_count": null, "matches": 304, "name": "Family of unknown function (DUF6694)", "partial_evidence_count": null, "pfam_id": "PF20404", "proteins": 304, "proteomes": 282, "short_name": "DUF6694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20404", "structures": 0, "taxa": 566, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 150 and 185 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR046560", "known_evidence_count": null, "matches": 308, "name": "Family of unknown function (DUF6714)", "partial_evidence_count": null, "pfam_id": "PF20461", "proteins": 304, "proteomes": 271, "short_name": "DUF6714", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20461", "structures": 0, "taxa": 713, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha-helical structure with similarity to 8-oxoguanine DNA glycosylase-like domains such as [pfam:PF22175] and [pfam:PF21790]. The structural similarity extends to the active site architecture with some of the active site residues conserved.", "domain_architectures": 28, "interpro_id": "IPR059469", "known_evidence_count": null, "matches": 304, "name": "Domain of unknown function (DUF8425)", "partial_evidence_count": null, "pfam_id": "PF28527", "proteins": 304, "proteomes": 295, "short_name": "DUF8425", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28527", "structures": 0, "taxa": 824, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 171, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021501", "known_evidence_count": null, "matches": 310, "name": "Protein of unknown function (DUF3157)", "partial_evidence_count": null, "pfam_id": "PF11355", "proteins": 303, "proteomes": 301, "short_name": "DUF3157", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11355", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001077) is described by MIBiG as an example of the following biosynthetic classes, polyketide and terpene. This family includes a protein from the alkyl-O-dihydrogeranyl- methoxyhydroquinones biosynthetic gene cluster from Actinoplanes missouriensis 431 and appears to be predominantly found in Actinobacteria [[cite:PUB00099454]].", "domain_architectures": 1, "interpro_id": "IPR046065", "known_evidence_count": null, "matches": 303, "name": "Family of unknown function (DUF6023)", "partial_evidence_count": null, "pfam_id": "PF19487", "proteins": 303, "proteomes": 242, "short_name": "DUF6023", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19487", "structures": 0, "taxa": 292, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain from a family of uncharacterised proteins from halophilic archaea. The proteins in this family are predominantly found in the class Halobacteria, which includes families such as Natrialbaceae, Haloferacaceae, and Haloarculaceae. The proteins in this family are generally around 270-330 amino acids in length. This domain show similarity to the Peptidase M23 family suggesting this domain may act as an endopeptidase.", "domain_architectures": 4, "interpro_id": "IPR058468", "known_evidence_count": null, "matches": 303, "name": "Domain of unknown function (DUF8155) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26482", "proteins": 303, "proteomes": 303, "short_name": "DUF8155", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26482", "structures": 0, "taxa": 514, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021290", "known_evidence_count": null, "matches": 302, "name": "Protein of unknown function (DUF2861)", "partial_evidence_count": null, "pfam_id": "PF11060", "proteins": 302, "proteomes": 239, "short_name": "DUF2861", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11060", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently they have no known function.", "domain_architectures": 1, "interpro_id": "IPR021355", "known_evidence_count": null, "matches": 302, "name": "Protein of unknown function (DUF2973)", "partial_evidence_count": null, "pfam_id": "PF11189", "proteins": 302, "proteomes": 301, "short_name": "DUF2973", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11189", "structures": 0, "taxa": 832, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 285, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 9, "interpro_id": "IPR043815", "known_evidence_count": null, "matches": 302, "name": "Family of unknown function (DUF5797)", "partial_evidence_count": null, "pfam_id": "PF19110", "proteins": 302, "proteomes": 275, "short_name": "DUF5797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19110", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 247, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Ascomycota lineage. It is predicted to fold into array of alpha-helices capped with a small three-stranded beta-sheet.", "domain_architectures": 14, "interpro_id": "IPR059400", "known_evidence_count": null, "matches": 331, "name": "Domain of unknown function (DUF8356)", "partial_evidence_count": null, "pfam_id": "PF27622", "proteins": 302, "proteomes": 158, "short_name": "DUF8356", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27622", "structures": 0, "taxa": 321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR019697", "known_evidence_count": null, "matches": 301, "name": "Protein of unknown function (DUF2590)", "partial_evidence_count": null, "pfam_id": "PF10761", "proteins": 301, "proteomes": 273, "short_name": "DUF2590", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10761", "structures": 0, "taxa": 498, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 210, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This an alpha-beta-alpha domain found at the N-terminal region of Rv3899c, a hypothetical protein from Mycobacterium tuberculosis which is conserved across mycobacteria [[cite:PUB00091180]].", "domain_architectures": 3, "interpro_id": "IPR040604", "known_evidence_count": null, "matches": 301, "name": "Family of unknown function (DUF5632)", "partial_evidence_count": null, "pfam_id": "PF18646", "proteins": 301, "proteomes": 146, "short_name": "DUF5632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18646", "structures": 1, "taxa": 170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 171, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are probably distantly related to heme-binding proteins PhuS, ChuS, HmuS.", "domain_architectures": 4, "interpro_id": "IPR053838", "known_evidence_count": null, "matches": 303, "name": "Family of unknown function (DUF6925)", "partial_evidence_count": null, "pfam_id": "PF21973", "proteins": 301, "proteomes": 272, "short_name": "DUF6925", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21973", "structures": 0, "taxa": 442, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 288, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to fold into an alpha-helical hairpin and it is likely associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR055746", "known_evidence_count": null, "matches": 301, "name": "Domain of unknown function (DUF7322)", "partial_evidence_count": null, "pfam_id": "PF24008", "proteins": 301, "proteomes": 270, "short_name": "DUF7322", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24008", "structures": 0, "taxa": 423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 284, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins found in the class Halobacteria. The proteins containing this domain are predominantly found in archaea, specifically within the order Halobacteriales. The domain is typically found in proteins ranging from 150 to 220 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR058415", "known_evidence_count": null, "matches": 302, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF26404", "proteins": 301, "proteomes": 190, "short_name": "DUF8102", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26404", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR021485", "known_evidence_count": null, "matches": 346, "name": "Protein of unknown function (DUF3138)", "partial_evidence_count": null, "pfam_id": "PF11336", "proteins": 300, "proteomes": 203, "short_name": "DUF3138", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11336", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 392 and 442 amino acids in length. This entry represents the C-terminal immunoglobulin-like domain.", "domain_architectures": 8, "interpro_id": "IPR048295", "known_evidence_count": null, "matches": 300, "name": "Domain of unknown function (DUF4785) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20943", "proteins": 300, "proteomes": 298, "short_name": "DUF4785_3rd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20943", "structures": 1, "taxa": 486, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Gram-negative bacteria. It has a detectable similarity to OmpA-like transmembrane domains and it is predicted to adopt a similar beta-barrel structure.", "domain_architectures": 3, "interpro_id": "IPR057171", "known_evidence_count": null, "matches": 300, "name": "Domain of unknown function (DUF7849)", "partial_evidence_count": null, "pfam_id": "PF25233", "proteins": 300, "proteomes": 300, "short_name": "DUF7849", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25233", "structures": 0, "taxa": 392, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal helical domain found in a family of secreted halobacterial proteins.", "domain_architectures": 2, "interpro_id": "IPR059306", "known_evidence_count": null, "matches": 300, "name": "Domain of unknown function (DUF8262)", "partial_evidence_count": null, "pfam_id": "PF26790", "proteins": 300, "proteomes": 180, "short_name": "DUF8262", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26790", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of bacterial proteins. Members of the family are about 250 residues in length.", "domain_architectures": 2, "interpro_id": "IPR054199", "known_evidence_count": null, "matches": 301, "name": "Domain of unknown function (DUF6904)", "partial_evidence_count": null, "pfam_id": "PF21845", "proteins": 299, "proteomes": 268, "short_name": "DUF6904", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21845", "structures": 0, "taxa": 564, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short proteins from archaea.", "domain_architectures": 3, "interpro_id": "IPR055894", "known_evidence_count": null, "matches": 299, "name": "Family of unknown function (DUF7471)", "partial_evidence_count": null, "pfam_id": "PF24283", "proteins": 299, "proteomes": 243, "short_name": "DUF7471", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24283", "structures": 0, "taxa": 383, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 4, "interpro_id": "IPR058288", "known_evidence_count": null, "matches": 312, "name": "Domain of unknown function (DUF7982)", "partial_evidence_count": null, "pfam_id": "PF25939", "proteins": 299, "proteomes": 244, "short_name": "DUF7982", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25939", "structures": 0, "taxa": 460, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to fold into a globular structure consisting mainly of alpha-helices. It contains one histidine and two cysteine residues which are highly conserved and may be essential for function.", "domain_architectures": 2, "interpro_id": "IPR059268", "known_evidence_count": null, "matches": 299, "name": "Domain of unknown function (DUF8224)", "partial_evidence_count": null, "pfam_id": "PF26675", "proteins": 299, "proteomes": 290, "short_name": "DUF8224", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26675", "structures": 0, "taxa": 677, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal helical domain found in a family of secreted halobacterial proteins. This domain is found C-terminal to [pfam:PF26790].", "domain_architectures": 2, "interpro_id": "IPR059308", "known_evidence_count": null, "matches": 299, "name": "Domain of unknown function (DUF8264)", "partial_evidence_count": null, "pfam_id": "PF26793", "proteins": 299, "proteomes": 180, "short_name": "DUF8264", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26793", "structures": 0, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 246, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha/beta structure composed of a meander beta-sheet packed with helices on both sides.", "domain_architectures": 9, "interpro_id": "IPR059417", "known_evidence_count": null, "matches": 299, "name": "Domain of unknown function (DUF8373)", "partial_evidence_count": null, "pfam_id": "PF28154", "proteins": 299, "proteomes": 205, "short_name": "DUF8373", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28154", "structures": 0, "taxa": 465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 472 to 574 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR021803", "known_evidence_count": null, "matches": 300, "name": "Protein of unknown function (DUF3373)", "partial_evidence_count": null, "pfam_id": "PF11853", "proteins": 298, "proteomes": 253, "short_name": "DUF3373", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11853", "structures": 0, "taxa": 505, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Potential uncharacterized enzymatic domain associated with bacterial [pfam:PF12872] domains. Has conserved residues suggestive of an enzymatic role probably related to RNA metabolism.", "domain_architectures": 7, "interpro_id": "IPR024437", "known_evidence_count": null, "matches": 299, "name": "Domain of unknown function (DUF3825)", "partial_evidence_count": null, "pfam_id": "PF12873", "proteins": 298, "proteomes": 266, "short_name": "DUF3825", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12873", "structures": 0, "taxa": 803, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes Putative lipoprotein BA_2398 from Bacillus anthracis and similar proteins from bacteria, predominantly Firmicutes and Bacteroidetes.", "domain_architectures": 4, "interpro_id": "IPR049293", "known_evidence_count": null, "matches": 302, "name": "Family of unknown function (DUF6843)", "partial_evidence_count": null, "pfam_id": "PF20862", "proteins": 298, "proteomes": 269, "short_name": "DUF6843", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20862", "structures": 1, "taxa": 468, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 135 and 154 amino acids in length. These proteins share significant sequence similarity to the central part of mammalian cell entry (MCE) protein MlaD.", "domain_architectures": 6, "interpro_id": "IPR054210", "known_evidence_count": null, "matches": 298, "name": "Family of unknown function (DUF6917)", "partial_evidence_count": null, "pfam_id": "PF21891", "proteins": 298, "proteomes": 284, "short_name": "DUF6917", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21891", "structures": 0, "taxa": 468, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 282, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain from a family of uncharacterised proteins from archaea. The proteins in this family are predominantly found in halophilic archaea, including members of the Halobacteria class. The proteins typically range from 450 to 550 amino acids in length. The central domain is a methyltransferase.", "domain_architectures": 6, "interpro_id": "IPR058470", "known_evidence_count": null, "matches": 298, "name": "Domain of unknown function (DUF8157) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26486", "proteins": 298, "proteomes": 297, "short_name": "DUF8157", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26486", "structures": 0, "taxa": 477, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated yhhA however currently no function is known. The family appears to be restricted to Enterobacteriaceae.", "domain_architectures": 2, "interpro_id": "IPR020158", "known_evidence_count": null, "matches": 297, "name": "Protein of unknown function (DUF2756)", "partial_evidence_count": null, "pfam_id": "PF10956", "proteins": 297, "proteomes": 297, "short_name": "DUF2756", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10956", "structures": 0, "taxa": 434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins includes the outer membrane lipoprotein Flpp3 from Francisella tularensis ([swissprot:Q5NF33]). Flpp3, a virulence determinant of tularemia, shows a six stranded beta-sheet supported with two crossing alpha-helices. It has a hydrophobic internal cavity that has been suggested to bind a small organic molecule. However, its specific function is still unknown [[cite:PUB00100865],[cite:PUB00100866]].", "domain_architectures": 3, "interpro_id": "IPR021952", "known_evidence_count": null, "matches": 298, "name": "Protein of unknown function (DUF3568)", "partial_evidence_count": null, "pfam_id": "PF12092", "proteins": 297, "proteomes": 158, "short_name": "DUF3568", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12092", "structures": 3, "taxa": 414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family based on the three-dimensional structure of YP_926445.1 (PDB:2L6O)", "domain_architectures": 1, "interpro_id": "IPR025284", "known_evidence_count": null, "matches": 297, "name": "protein structure with unknown function", "partial_evidence_count": null, "pfam_id": "PF13642", "proteins": 297, "proteomes": 294, "short_name": "DUF4144", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13642", "structures": 1, "taxa": 395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 40 amino acids in length. There is a conserved SGLPT sequence motif. There are two completely conserved residues (P and G) that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR032050", "known_evidence_count": null, "matches": 298, "name": "Domain of unknown function (DUF4797)", "partial_evidence_count": null, "pfam_id": "PF16051", "proteins": 297, "proteomes": 188, "short_name": "DUF4797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16051", "structures": 0, "taxa": 724, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised bacterial proteins. It is predicted to adopt a globular structure composed mainly of alpha helices.", "domain_architectures": 5, "interpro_id": "IPR055804", "known_evidence_count": null, "matches": 298, "name": "Domain of unknown function (DUF7380)", "partial_evidence_count": null, "pfam_id": "PF24098", "proteins": 297, "proteomes": 291, "short_name": "DUF7380", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24098", "structures": 0, "taxa": 855, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is ubiquitously found in uncharacterised proteins. It is found in combination with different domains and give the AlphaFold prediction either associates with another part of th polypeptide chain or with another molecule.", "domain_architectures": 12, "interpro_id": "IPR059330", "known_evidence_count": null, "matches": 298, "name": "Domain of unknown function (DUF8286)", "partial_evidence_count": null, "pfam_id": "PF26935", "proteins": 297, "proteomes": 51, "short_name": "DUF8286", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26935", "structures": 11, "taxa": 183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 203, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as cytosolic proteins. This cannot be confirmed.", "domain_architectures": 3, "interpro_id": "IPR021462", "known_evidence_count": null, "matches": 296, "name": "Protein of unknown function (DUF3114)", "partial_evidence_count": null, "pfam_id": "PF11311", "proteins": 296, "proteomes": 225, "short_name": "DUF3114", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11311", "structures": 0, "taxa": 341, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function which can be found mostly in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR035225", "known_evidence_count": null, "matches": 296, "name": "Family of unknown function (DUF5338)", "partial_evidence_count": null, "pfam_id": "PF17273", "proteins": 296, "proteomes": 230, "short_name": "DUF5338", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17273", "structures": 0, "taxa": 511, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in uncharacterised proteins from spirochaetes, predominantly from Treponema and Leptospira species, and some members of Lachnospiraceae. The domain is approximately 90 residues in length. The function of this domain remains", "domain_architectures": 4, "interpro_id": "IPR061579", "known_evidence_count": null, "matches": 296, "name": "Domain of unknown function (DUF8509)", "partial_evidence_count": null, "pfam_id": "PF29207", "proteins": 296, "proteomes": 249, "short_name": "DUF8509", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29207", "structures": 0, "taxa": 430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021422", "known_evidence_count": null, "matches": 295, "name": "Protein of unknown function (DUF3069)", "partial_evidence_count": null, "pfam_id": "PF11269", "proteins": 295, "proteomes": 295, "short_name": "DUF3069", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11269", "structures": 1, "taxa": 366, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR046205", "known_evidence_count": null, "matches": 295, "name": "Family of unknown function (DUF6238)", "partial_evidence_count": null, "pfam_id": "PF19751", "proteins": 295, "proteomes": 240, "short_name": "DUF6238", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19751", "structures": 0, "taxa": 282, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 200 amino acids in length. Many sequences are related to ParB proteins, annotated as ParB-like or ParB domain-containing proteins. It contains the conserved motifs YQR, DGQH and EAxxF.", "domain_architectures": 2, "interpro_id": "IPR046681", "known_evidence_count": null, "matches": 295, "name": "Family of unknown function (DUF6551)", "partial_evidence_count": null, "pfam_id": "PF20188", "proteins": 295, "proteomes": 255, "short_name": "DUF6551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20188", "structures": 0, "taxa": 536, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 281, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins are predominantly found in the Halobacteria class, including genera such as Natrinema and Haloferax. The domain is approximately 70-90 amino acids in length and is characterized by the presence of two predicted transmembrane helices, suggesting a potential role in membrane-associated processes.", "domain_architectures": 1, "interpro_id": "IPR058432", "known_evidence_count": null, "matches": 295, "name": "Domain of unknown function (DUF8119)", "partial_evidence_count": null, "pfam_id": "PF26436", "proteins": 295, "proteomes": 202, "short_name": "DUF8119", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26436", "structures": 0, "taxa": 334, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 254, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a conserved domain found in uncharacterised fungal sequences, an it may adopt a tri-helical bundle fold.", "domain_architectures": 4, "interpro_id": "IPR061567", "known_evidence_count": null, "matches": 296, "name": "Domain of unknown function (DUF8497)", "partial_evidence_count": null, "pfam_id": "PF29055", "proteins": 295, "proteomes": 205, "short_name": "DUF8497", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29055", "structures": 0, "taxa": 420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_4228, a putative uncharacterized protein As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), It appears to be upregulated in the presence of host or other bacterial species vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 3, "interpro_id": "IPR024450", "known_evidence_count": null, "matches": 294, "name": "Domain of unknonw function from B. Theta Gene description (DUF3874)", "partial_evidence_count": null, "pfam_id": "PF12990", "proteins": 294, "proteomes": 80, "short_name": "DUF3874", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12990", "structures": 0, "taxa": 128, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025059", "known_evidence_count": null, "matches": 296, "name": "Protein of unknown function (DUF3997)", "partial_evidence_count": null, "pfam_id": "PF13162", "proteins": 294, "proteomes": 269, "short_name": "DUF3997", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13162", "structures": 0, "taxa": 542, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 175, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillaceae.", "domain_architectures": 1, "interpro_id": "IPR020355", "known_evidence_count": null, "matches": 294, "name": "Family of unknown function (DUF5365)", "partial_evidence_count": null, "pfam_id": "PF17326", "proteins": 294, "proteomes": 292, "short_name": "DUF5365", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17326", "structures": 0, "taxa": 363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, predominantly in Rhodobacteria. Proteins in this family are typically between 203 and 225 amino acids in length. This family contains the conserved sequence motifs DIVW, RFH and GGxH.", "domain_architectures": 1, "interpro_id": "IPR046705", "known_evidence_count": null, "matches": 294, "name": "Family of unknown function (DUF6778)", "partial_evidence_count": null, "pfam_id": "PF20569", "proteins": 294, "proteomes": 280, "short_name": "DUF6778", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20569", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 281, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins. They are predicted to fold into an alpha-helical hairpin.", "domain_architectures": 1, "interpro_id": "IPR055757", "known_evidence_count": null, "matches": 294, "name": "Family of unknown function (DUF7333)", "partial_evidence_count": null, "pfam_id": "PF24020", "proteins": 294, "proteomes": 258, "short_name": "DUF7333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24020", "structures": 0, "taxa": 403, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage domains. These domains adopt a beta sandwich structure.", "domain_architectures": 3, "interpro_id": "IPR055776", "known_evidence_count": null, "matches": 294, "name": "Domain of unknown function (DUF7352)", "partial_evidence_count": null, "pfam_id": "PF24043", "proteins": 294, "proteomes": 285, "short_name": "DUF7352", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24043", "structures": 0, "taxa": 665, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Drosophila melanogaster proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR007970", "known_evidence_count": null, "matches": 296, "name": "Protein of unknown function (DUF733)", "partial_evidence_count": null, "pfam_id": "PF05306", "proteins": 293, "proteomes": 37, "short_name": "DUF733", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05306", "structures": 0, "taxa": 142, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Protein of unknown function found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR018568", "known_evidence_count": null, "matches": 294, "name": "Domain of unknown function (DUF2019)", "partial_evidence_count": null, "pfam_id": "PF09450", "proteins": 293, "proteomes": 95, "short_name": "DUF2019", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09450", "structures": 1, "taxa": 199, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 224, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 124 and 286 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR027868", "known_evidence_count": null, "matches": 297, "name": "Domain of unknown function (DUF4630)", "partial_evidence_count": null, "pfam_id": "PF15443", "proteins": 293, "proteomes": 213, "short_name": "DUF4630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15443", "structures": 0, "taxa": 767, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 242, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 320 and 483 amino acids in length. There are two conserved sequence motifs: WSLP and RPLPW.", "domain_architectures": 5, "interpro_id": "IPR032150", "known_evidence_count": null, "matches": 295, "name": "Domain of unknown function (DUF4820)", "partial_evidence_count": null, "pfam_id": "PF16091", "proteins": 293, "proteomes": 152, "short_name": "DUF4820", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16091", "structures": 0, "taxa": 540, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 120 residues in length and is mainly found in various Enterococcus and Lactobacillus species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032254", "known_evidence_count": null, "matches": 293, "name": "Domain of unknown function (DUF4828)", "partial_evidence_count": null, "pfam_id": "PF16110", "proteins": 293, "proteomes": 292, "short_name": "DUF4828", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16110", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 630 residues in length and is mainly found in various Thermotoga, Thermoanaerobacter and Carboxydibrachium species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032583", "known_evidence_count": null, "matches": 293, "name": "Domain of unknown function (DUF4914)", "partial_evidence_count": null, "pfam_id": "PF16260", "proteins": 293, "proteomes": 283, "short_name": "DUF4914", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16260", "structures": 0, "taxa": 654, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 168, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in actinobacteria. Proteins in this family are approximately 190 amino acids in length. Many protein in this family are annotated as regulator, but the source of this annotation is uncertain.", "domain_architectures": 2, "interpro_id": "IPR046029", "known_evidence_count": null, "matches": 293, "name": "Family of unknown function (DUF5987)", "partial_evidence_count": null, "pfam_id": "PF19449", "proteins": 293, "proteomes": 282, "short_name": "DUF5987", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19449", "structures": 0, "taxa": 399, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is usually found in combination with [[pfam:PF22515]] and [[pfam:PF22518]]. It is predicted to contain a winged helix (WH) domain that is flanked at the C terminus with a small helical subdomain. The latter packs on the WH domain to form a compact globular structure.", "domain_architectures": 13, "interpro_id": "IPR055650", "known_evidence_count": null, "matches": 300, "name": "Domain of unknown function (DUF7226)", "partial_evidence_count": null, "pfam_id": "PF23871", "proteins": 293, "proteomes": 282, "short_name": "DUF7226", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23871", "structures": 0, "taxa": 803, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are about 160 amino acids in length. The proteins contain small beta sheet which has two adjacent strands contributed by the N and C-terminus of the protein.", "domain_architectures": 2, "interpro_id": "IPR058308", "known_evidence_count": null, "matches": 302, "name": "Domain of unknown function (DUF7995)", "partial_evidence_count": null, "pfam_id": "PF25958", "proteins": 293, "proteomes": 135, "short_name": "DUF7995", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25958", "structures": 0, "taxa": 227, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 246, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha/beta structure with unique topology.", "domain_architectures": 4, "interpro_id": "IPR061821", "known_evidence_count": null, "matches": 300, "name": "Domain of unknown function (DUF8760)", "partial_evidence_count": null, "pfam_id": "PF30923", "proteins": 293, "proteomes": 216, "short_name": "DUF8760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30923", "structures": 0, "taxa": 510, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of highly conserved, predicted, proteins from Bacillus species. The structure forms a homo-dimer. The function is unknown.", "domain_architectures": 3, "interpro_id": "IPR018840", "known_evidence_count": null, "matches": 292, "name": "Protein of unknown function (DUF2441)", "partial_evidence_count": null, "pfam_id": "PF10386", "proteins": 292, "proteomes": 279, "short_name": "DUF2441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10386", "structures": 1, "taxa": 659, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 155, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]]. This domain frequently seen with DUF3848.", "domain_architectures": 24, "interpro_id": "IPR024383", "known_evidence_count": null, "matches": 292, "name": "Protein of unknown function (DUF3849)", "partial_evidence_count": null, "pfam_id": "PF12960", "proteins": 292, "proteomes": 176, "short_name": "DUF3849", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12960", "structures": 0, "taxa": 355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterized proteins found in CFB group of bacteria, mostly from Bacteroides and Prevotella genera present in human gut and oral cavity, respectively. JCSG target SP13584B, the experimentally determined structure consists of two WD40-like beta sheet repeats forming a beta sandwich", "domain_architectures": 1, "interpro_id": "IPR031762", "known_evidence_count": null, "matches": 292, "name": "Domain of unknown function (DUF4738)", "partial_evidence_count": null, "pfam_id": "PF15889", "proteins": 292, "proteomes": 173, "short_name": "DUF4738", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15889", "structures": 1, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically around 100 amino acids in length. It includes two conserved motifs, FA and HVRxA.", "domain_architectures": 10, "interpro_id": "IPR046489", "known_evidence_count": null, "matches": 292, "name": "Family of unknown function (DUF6582)", "partial_evidence_count": null, "pfam_id": "PF20223", "proteins": 292, "proteomes": 280, "short_name": "DUF6582", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20223", "structures": 0, "taxa": 529, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It shows two conserved motifs WP and several conserved D and R residues. Members are predicted to show beta-sheets at the N- and C-terminal ends.", "domain_architectures": 2, "interpro_id": "IPR055519", "known_evidence_count": null, "matches": 303, "name": "Family of unknown function (DUF7093)", "partial_evidence_count": null, "pfam_id": "PF23373", "proteins": 292, "proteomes": 280, "short_name": "DUF7093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23373", "structures": 0, "taxa": 438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised domain in the Halobacteria class of Archaea. The proteins in this family are predominantly found in various families within the Halobacteriales order, including Natrialbaceae, Haloferacaceae, and Haloarculaceae. The domain is typically found in proteins ranging from 58 to 130 amino acids in length. A reviewed protein containing this domain is found in Haloferax volcanii ([swissprot:D4GSN3]). This domain contains two CXXC motifs suggesting it is likely to be zinc binding.", "domain_architectures": 3, "interpro_id": "IPR058419", "known_evidence_count": null, "matches": 292, "name": "Domain of unknown function (DUF8106)", "partial_evidence_count": null, "pfam_id": "PF26408", "proteins": 292, "proteomes": 222, "short_name": "DUF8106", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26408", "structures": 0, "taxa": 354, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 234, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents putative zinc-binding domain found in a family of small uncharacterised proteins of approximately 50 to 70 residues. The family is found in cyanobacteria, chlorophyte algae, stramenopiles (including diatoms), and ascomycete fungi (primarily Dothideomycetes). The presence in both cyanobacteria and photosynthetic eukaryotes suggests possible plastid-associated function or horizontal gene transfer. The function of this family remains to be determined.", "domain_architectures": 12, "interpro_id": "IPR061683", "known_evidence_count": null, "matches": 292, "name": "Domain of unknown function (DUF8622)", "partial_evidence_count": null, "pfam_id": "PF30544", "proteins": 292, "proteomes": 279, "short_name": "DUF8622", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30544", "structures": 0, "taxa": 816, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a series of potential beta-helix repeats found in a variety of putative bacterial adhesin proteins.", "domain_architectures": 149, "interpro_id": "IPR043709", "known_evidence_count": null, "matches": 2057, "name": "Repeats of unknown function (DUF5649)", "partial_evidence_count": null, "pfam_id": "PF18886", "proteins": 291, "proteomes": 228, "short_name": "DUF5649", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18886", "structures": 0, "taxa": 551, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 277, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble treble-clef zinc fingers.", "domain_architectures": 1, "interpro_id": "IPR055984", "known_evidence_count": null, "matches": 291, "name": "Family of unknown function (DUF7562)", "partial_evidence_count": null, "pfam_id": "PF24443", "proteins": 291, "proteomes": 251, "short_name": "DUF7562", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24443", "structures": 0, "taxa": 396, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a globular alpha/beta structure.", "domain_architectures": 3, "interpro_id": "IPR056071", "known_evidence_count": null, "matches": 291, "name": "Domain of unknown function (DUF7654)", "partial_evidence_count": null, "pfam_id": "PF24672", "proteins": 291, "proteomes": 277, "short_name": "DUF7654", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24672", "structures": 0, "taxa": 506, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 35-65 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, with members found predominantly in the family Demerecviridae, particularly the genera Tequintavirus and Epseptimavirus. Additional members are found in the subfamily Ounavirinae. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061607", "known_evidence_count": null, "matches": 291, "name": "Family of unknown function (DUF8537)", "partial_evidence_count": null, "pfam_id": "PF29387", "proteins": 291, "proteomes": 289, "short_name": "DUF8537", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29387", "structures": 0, "taxa": 617, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 276, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of short uncharacterised archaeal proteins, including HVO_1785 ([swissprot:D4GSA9]). They have a highly conserved motif EIWE.", "domain_architectures": 2, "interpro_id": "IPR061656", "known_evidence_count": null, "matches": 291, "name": "Family of unknown function (DUF8595)", "partial_evidence_count": null, "pfam_id": "PF29881", "proteins": 291, "proteomes": 216, "short_name": "DUF8595", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29881", "structures": 0, "taxa": 359, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 193, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain has no known function. It is found in various hypothetical and putative bacterial proteins. The structure of this domain is known (PDB:2g6t).", "domain_architectures": 3, "interpro_id": "IPR015037", "known_evidence_count": null, "matches": 290, "name": "Domain of unknown function (DUF1919)", "partial_evidence_count": null, "pfam_id": "PF08942", "proteins": 290, "proteomes": 264, "short_name": "DUF1919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08942", "structures": 1, "taxa": 586, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 200, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain adopts an immunoglobulin-like beta-sandwich fold and structurally is most similar to fibronectin. This domain is found at the C-terminus of the Listeria monocytogenes InlP protein. This domain shares some similarity with the secretion signal domain of type X secretion systems [pfam:PF18962]. This domain is also found at the C-terminus of likely cell surface proteins suggesting this domain has a similar function.", "domain_architectures": 6, "interpro_id": "IPR021638", "known_evidence_count": null, "matches": 290, "name": "Domain of unknown function (DUF3244)", "partial_evidence_count": null, "pfam_id": "PF11589", "proteins": 290, "proteomes": 156, "short_name": "DUF3244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11589", "structures": 4, "taxa": 281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function that can be found mostly in Proteobacteria. Some of the family members are predicted to contain a coiled coil region.", "domain_architectures": 1, "interpro_id": "IPR020493", "known_evidence_count": null, "matches": 290, "name": "Family of unknown function (DUF5339)", "partial_evidence_count": null, "pfam_id": "PF17274", "proteins": 290, "proteomes": 211, "short_name": "DUF5339", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17274", "structures": 0, "taxa": 343, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in metazoa. This entry represents the N-terminal calmodulin-like domain.", "domain_architectures": 9, "interpro_id": "IPR048316", "known_evidence_count": null, "matches": 290, "name": "Family of unknown function (DUF5580) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF17743", "proteins": 290, "proteomes": 223, "short_name": "DUF5580", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17743", "structures": 0, "taxa": 870, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 279, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 3, "interpro_id": "IPR043828", "known_evidence_count": null, "matches": 290, "name": "Family of unknown function (DUF5805)", "partial_evidence_count": null, "pfam_id": "PF19121", "proteins": 290, "proteomes": 275, "short_name": "DUF5805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19121", "structures": 0, "taxa": 436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 187, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a domain of unknown function located at the N-terminal of proteins mostly found in fungi. According to structure predictions it might adopt an immunoglobulin, fibronectin type III fold. It is formed of two antiparallel beta-sheets stacked against each other, forming a beta-sandwich [[cite:PUB00158558]].", "domain_architectures": 9, "interpro_id": "IPR057692", "known_evidence_count": null, "matches": 318, "name": "Domain of unknown function (DUF7932)", "partial_evidence_count": null, "pfam_id": "PF25560", "proteins": 290, "proteomes": 187, "short_name": "DUF7932", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25560", "structures": 0, "taxa": 578, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from halobacteria. These proteins contains a conserved LPXXXP motif towards the N-terminus.", "domain_architectures": 3, "interpro_id": "IPR058270", "known_evidence_count": null, "matches": 291, "name": "Domain of unknown function (DUF7964)", "partial_evidence_count": null, "pfam_id": "PF25912", "proteins": 290, "proteomes": 164, "short_name": "DUF7964", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25912", "structures": 0, "taxa": 267, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a number of hypothetical bacterial proteins of around 410 residues in length which seem to be specific to Chlamydia species. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR009599", "known_evidence_count": null, "matches": 290, "name": "Protein of unknown function (DUF1207)", "partial_evidence_count": null, "pfam_id": "PF06727", "proteins": 289, "proteomes": 257, "short_name": "DUF1207", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06727", "structures": 0, "taxa": 524, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR021231", "known_evidence_count": null, "matches": 289, "name": "Protein of unknown function (DUF2811)", "partial_evidence_count": null, "pfam_id": "PF10929", "proteins": 289, "proteomes": 214, "short_name": "DUF2811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10929", "structures": 0, "taxa": 598, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 220, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family is found in various Bacteroides species. Proteins in this family are around 235 amino acids in length.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 289, "name": "Domain of unknown function (DUF5020)", "partial_evidence_count": null, "pfam_id": "PF16412", "proteins": 289, "proteomes": 285, "short_name": "DUF5020", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16412", "structures": 0, "taxa": 511, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 274, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins predominantly found in Halobacteria. Some members includes the MarR family transcriptional regulator.", "domain_architectures": 1, "interpro_id": "IPR043870", "known_evidence_count": null, "matches": 289, "name": "Family of unknown function (DUF5830)", "partial_evidence_count": null, "pfam_id": "PF19148", "proteins": 289, "proteomes": 288, "short_name": "DUF5830", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19148", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, mainly in Firmicutes. Proteins in this family are typically between 62 and 78 amino acids in length. Some of the members are probably transcriptional regulators. This family has overlaps with families in clan CL0123, which suggests that they share the helix-turn-helix motif.", "domain_architectures": 3, "interpro_id": "IPR045591", "known_evidence_count": null, "matches": 300, "name": "Family of unknown function (DUF6462)", "partial_evidence_count": null, "pfam_id": "PF20063", "proteins": 289, "proteomes": 114, "short_name": "DUF6462", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20063", "structures": 0, "taxa": 227, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 251, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function. In some proteins the is a C-terminal HTH domain that presumably binds to DNA. This domain may bind to an as unyet identified ligand to enable regulation of bacterial genes. This domain contains a large beta sheet composed of 11 beta strands with helices packed on the convex face. There is some evidence from structure prediction that this domain may dimerise and form a large structure that has a large hole through it that might accommodate DNA.", "domain_architectures": 5, "interpro_id": "IPR057167", "known_evidence_count": null, "matches": 291, "name": "Domain of unknown function (DUF7845)", "partial_evidence_count": null, "pfam_id": "PF25227", "proteins": 289, "proteomes": 194, "short_name": "DUF7845", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25227", "structures": 0, "taxa": 350, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 272, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a pair of domains from a family of uncharacterised proteins in halophilic archaea. The proteins are predominantly found in the class Halobacteria, which includes genera such as Halorubrum, Natrialbaceae, and Haloferacaceae. The proteins in this family typically range from 180 to 270 amino acids in length. The family contains one domain nested withing another. The outer domain shows structural similarity to [pfam:PF05014] a family of Nucleoside 2-deoxyribosyltransferases.", "domain_architectures": 1, "interpro_id": "IPR058483", "known_evidence_count": null, "matches": 289, "name": "Family of unknown function (DUF8170)", "partial_evidence_count": null, "pfam_id": "PF26508", "proteins": 289, "proteomes": 183, "short_name": "DUF8170", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26508", "structures": 0, "taxa": 307, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 149, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain, found in various bacterial hypothetical and putative signal peptide proteins, has no known function.", "domain_architectures": 5, "interpro_id": "IPR018748", "known_evidence_count": null, "matches": 559, "name": "Predicted secreted protein (DUF2300)", "partial_evidence_count": null, "pfam_id": "PF10062", "proteins": 288, "proteomes": 286, "short_name": "DUF2300", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10062", "structures": 0, "taxa": 412, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 162, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 173 and 249 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025052", "known_evidence_count": null, "matches": 288, "name": "Protein of unknown function (DUF3967)", "partial_evidence_count": null, "pfam_id": "PF13152", "proteins": 288, "proteomes": 159, "short_name": "DUF3967", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13152", "structures": 0, "taxa": 302, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 132 and 150 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025531", "known_evidence_count": null, "matches": 288, "name": "Domain of unknown function (DUF4418)", "partial_evidence_count": null, "pfam_id": "PF14387", "proteins": 288, "proteomes": 269, "short_name": "DUF4418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14387", "structures": 0, "taxa": 556, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a likely zinc-binding domain that is a putative toxin immunity protein.", "domain_architectures": 4, "interpro_id": "IPR061678", "known_evidence_count": null, "matches": 289, "name": "Domain of unknown function (DUF8617)", "partial_evidence_count": null, "pfam_id": "PF30462", "proteins": 288, "proteomes": 268, "short_name": "DUF8617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30462", "structures": 0, "taxa": 613, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 98 and 133 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR027957", "known_evidence_count": null, "matches": 301, "name": "Domain of unknown function (DUF4634)", "partial_evidence_count": null, "pfam_id": "PF15465", "proteins": 287, "proteomes": 141, "short_name": "DUF4634", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15465", "structures": 0, "taxa": 443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 134 and 191 amino acids in length. There is a single completely conserved residue C that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR032004", "known_evidence_count": null, "matches": 291, "name": "Domain of unknown function (DUF4790)", "partial_evidence_count": null, "pfam_id": "PF16037", "proteins": 287, "proteomes": 173, "short_name": "DUF4790", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16037", "structures": 0, "taxa": 625, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This is a family of Firmicutes proteins of unknown function. There is one structure, PDB:4r4g, a lipoprotein, whose N-terminus is represented by DUF4352, [pfam:PF11611].", "domain_architectures": 5, "interpro_id": "IPR031343", "known_evidence_count": null, "matches": 291, "name": "Domain of unknown function (DUF5105)", "partial_evidence_count": null, "pfam_id": "PF17118", "proteins": 287, "proteomes": 237, "short_name": "DUF5105", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17118", "structures": 1, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found primarily in Bacteroidetes bacteria. Proteins in this family are typically between 379 and 586 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045692", "known_evidence_count": null, "matches": 338, "name": "Family of unknown function (DUF6057)", "partial_evidence_count": null, "pfam_id": "PF19529", "proteins": 287, "proteomes": 135, "short_name": "DUF6057", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19529", "structures": 0, "taxa": 251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. Proteins in this family are typically between 306 and 346 amino acids in length and they are predominantly found in Proteobacteria. There is a conserved sequence MDXXdTLRH at the N-terminal and a conserved sequence YxxVEA at the C-terminal.", "domain_architectures": 2, "interpro_id": "IPR045964", "known_evidence_count": null, "matches": 338, "name": "Family of unknown function (DUF6384)", "partial_evidence_count": null, "pfam_id": "PF19911", "proteins": 287, "proteomes": 271, "short_name": "DUF6384", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19911", "structures": 0, "taxa": 497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in a group of uncharacterised proteins. It usually follows winged helix domain [pfam:PF22515]. This domain is related to PD-(D/E)XK nucleases and it is predicted to adopt the same structure with similar active site architecture.", "domain_architectures": 8, "interpro_id": "IPR054266", "known_evidence_count": null, "matches": 288, "name": "Domain of unknown function (DUF6997)", "partial_evidence_count": null, "pfam_id": "PF22518", "proteins": 287, "proteomes": 281, "short_name": "DUF6997", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22518", "structures": 0, "taxa": 758, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains four invariant cysteines and it is predicted to adopt a Zn-ribbon fold.", "domain_architectures": 3, "interpro_id": "IPR055902", "known_evidence_count": null, "matches": 287, "name": "Domain of unknown function (DUF7479)", "partial_evidence_count": null, "pfam_id": "PF24292", "proteins": 287, "proteomes": 245, "short_name": "DUF7479", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24292", "structures": 0, "taxa": 549, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal beta sandwich domain found in a family of likely halobacterial carbohydrate phosphorylase enzymes.", "domain_architectures": 7, "interpro_id": "IPR058310", "known_evidence_count": null, "matches": 288, "name": "Domain of unknown function (DUF7997)", "partial_evidence_count": null, "pfam_id": "PF25978", "proteins": 287, "proteomes": 183, "short_name": "DUF7997", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25978", "structures": 0, "taxa": 294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 278, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from worms. This domain has highly conserved motifs YRF and HLRxRK and is predicted to show high structural similarity with UBA domains, which are often involved in ubiquitin binding. It is often found associated with [pfam:PF00650].", "domain_architectures": 12, "interpro_id": "IPR059479", "known_evidence_count": null, "matches": 287, "name": "Domain of unknown function (DUF8435)", "partial_evidence_count": null, "pfam_id": "PF28543", "proteins": 287, "proteomes": 106, "short_name": "DUF8435", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28543", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry includes uncharacterised protein YfaA from Escherichia coli (strain K12). This protein has a fold that seems to be a a fusion of membrane permeability and extracellular sensor domains according to DALI pairwise alignment of PDBe:eszA, PDBe:3k8hA and PDBe:4esqA structures [[cite:PUB00152793]]. This suggests that the protein could serve as a signaling device.", "domain_architectures": 2, "interpro_id": "IPR018671", "known_evidence_count": null, "matches": 292, "name": "Uncharacterized protein conserved in bacteria (DUF2138)", "partial_evidence_count": null, "pfam_id": "PF09909", "proteins": 286, "proteomes": 286, "short_name": "DUF2138", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09909", "structures": 0, "taxa": 385, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 272, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 2, "interpro_id": "IPR043825", "known_evidence_count": null, "matches": 287, "name": "Family of unknown function (DUF5802)", "partial_evidence_count": null, "pfam_id": "PF19118", "proteins": 286, "proteomes": 277, "short_name": "DUF5802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19118", "structures": 0, "taxa": 448, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in functionally uncharacterised bacterial proteins. This domain is usually associated with a cysteine proteinase-like domain. It is predicted to fold into a partly open beta-barrel.", "domain_architectures": 2, "interpro_id": "IPR046517", "known_evidence_count": null, "matches": 286, "name": "DUF6695 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20405", "proteins": 286, "proteomes": 249, "short_name": "DUF6695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20405", "structures": 0, "taxa": 367, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria. Proteins in this family are about 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR021811", "known_evidence_count": null, "matches": 285, "name": "Protein of unknown function (DUF3389)", "partial_evidence_count": null, "pfam_id": "PF11869", "proteins": 285, "proteomes": 285, "short_name": "DUF3389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11869", "structures": 0, "taxa": 355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043812", "known_evidence_count": null, "matches": 285, "name": "Family of unknown function (DUF5794)", "partial_evidence_count": null, "pfam_id": "PF19107", "proteins": 285, "proteomes": 280, "short_name": "DUF5794", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19107", "structures": 0, "taxa": 444, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 238, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found in Euryarchaeota.", "domain_architectures": 4, "interpro_id": "IPR055710", "known_evidence_count": null, "matches": 368, "name": "Family of unknown function (DUF7286)", "partial_evidence_count": null, "pfam_id": "PF23957", "proteins": 285, "proteomes": 243, "short_name": "DUF7286", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23957", "structures": 0, "taxa": 386, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised metazoan sequences.", "domain_architectures": 11, "interpro_id": "IPR061835", "known_evidence_count": null, "matches": 294, "name": "Family of unknown function (DUF8774)", "partial_evidence_count": null, "pfam_id": "PF30976", "proteins": 285, "proteomes": 109, "short_name": "DUF8774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30976", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 273, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 4, "interpro_id": "IPR043816", "known_evidence_count": null, "matches": 284, "name": "Family of unknown function (DUF5798)", "partial_evidence_count": null, "pfam_id": "PF19111", "proteins": 284, "proteomes": 281, "short_name": "DUF5798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19111", "structures": 0, "taxa": 502, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised, it is present in proteins from bacteria and archaea. This domain is approximately typically 100 amino acids in length and contains a conserved WA sequence motif.", "domain_architectures": 11, "interpro_id": "IPR045651", "known_evidence_count": null, "matches": 284, "name": "Domain of unknown function (DUF6398)", "partial_evidence_count": null, "pfam_id": "PF19935", "proteins": 284, "proteomes": 265, "short_name": "DUF6398", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19935", "structures": 0, "taxa": 662, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 175, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 430 and 555 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046621", "known_evidence_count": null, "matches": 288, "name": "Family of unknown function (DUF6734)", "partial_evidence_count": null, "pfam_id": "PF20508", "proteins": 284, "proteomes": 229, "short_name": "DUF6734", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20508", "structures": 0, "taxa": 442, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved motifs LAGV/IVDLFG, DxPHI and LxDVxYD/ExExW and five highly conserved R residues. Members are predicted to show a mainly alpha-helical structure with a small beta-sheet.", "domain_architectures": 3, "interpro_id": "IPR055533", "known_evidence_count": null, "matches": 287, "name": "Family of unknown function (DUF7109)", "partial_evidence_count": null, "pfam_id": "PF23421", "proteins": 284, "proteomes": 284, "short_name": "DUF7109", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23421", "structures": 0, "taxa": 446, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 275, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of a number of hypothetical proteins which seem to be specific to Caenorhabditis elegans. The function of this family is unknown.", "domain_architectures": 6, "interpro_id": "IPR008588", "known_evidence_count": null, "matches": 288, "name": "Caenorhabditis elegans protein of unknown function (DUF870)", "partial_evidence_count": null, "pfam_id": "PF05912", "proteins": 283, "proteomes": 12, "short_name": "DUF870", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05912", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of unknown function appear to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021262", "known_evidence_count": null, "matches": 283, "name": "Protein of unknown function (DUF2839)", "partial_evidence_count": null, "pfam_id": "PF10999", "proteins": 283, "proteomes": 270, "short_name": "DUF2839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10999", "structures": 0, "taxa": 797, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in the Bacillaceae family. Several members are named as being YflJ, but the function is not known.", "domain_architectures": 1, "interpro_id": "IPR022580", "known_evidence_count": null, "matches": 283, "name": "Protein of unknown function (DUF2639)", "partial_evidence_count": null, "pfam_id": "PF11121", "proteins": 283, "proteomes": 252, "short_name": "DUF2639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11121", "structures": 0, "taxa": 351, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 273, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043903", "known_evidence_count": null, "matches": 283, "name": "Family of unknown function (DUF5785)", "partial_evidence_count": null, "pfam_id": "PF19098", "proteins": 283, "proteomes": 280, "short_name": "DUF5785", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19098", "structures": 0, "taxa": 437, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043811", "known_evidence_count": null, "matches": 283, "name": "Family of unknown function (DUF5793)", "partial_evidence_count": null, "pfam_id": "PF19106", "proteins": 283, "proteomes": 278, "short_name": "DUF5793", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19106", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 187 and 219 amino acids in length and may contain a LysM domain.", "domain_architectures": 2, "interpro_id": "IPR045613", "known_evidence_count": null, "matches": 283, "name": "Family of unknown function (DUF6448)", "partial_evidence_count": null, "pfam_id": "PF20046", "proteins": 283, "proteomes": 258, "short_name": "DUF6448", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20046", "structures": 0, "taxa": 652, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. The proteins contain 4 conserved cysteines.", "domain_architectures": 1, "interpro_id": "IPR045525", "known_evidence_count": null, "matches": 283, "name": "Domain of unknown function (DUF6472)", "partial_evidence_count": null, "pfam_id": "PF20076", "proteins": 283, "proteomes": 281, "short_name": "DUF6472", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20076", "structures": 0, "taxa": 455, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and fungi. Proteins in this family are typically between 220 and 250 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046475", "known_evidence_count": null, "matches": 283, "name": "Family of unknown function (DUF6796)", "partial_evidence_count": null, "pfam_id": "PF20599", "proteins": 283, "proteomes": 244, "short_name": "DUF6796", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20599", "structures": 0, "taxa": 586, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in a group of proteins predominantly from proteobacteria. It has a LxHDGK/RRL motif and a highly conserved W residue.", "domain_architectures": 3, "interpro_id": "IPR053895", "known_evidence_count": null, "matches": 283, "name": "Domain of unknown function (DUF7011)", "partial_evidence_count": null, "pfam_id": "PF22791", "proteins": 283, "proteomes": 216, "short_name": "DUF7011", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22791", "structures": 0, "taxa": 415, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of proteins from halobacteria. Members of this family, often annotated as ATPases, are predicted to show a central beta-sheet with alpha-helices in both sides.", "domain_architectures": 1, "interpro_id": "IPR055516", "known_evidence_count": null, "matches": 283, "name": "Family of unknown function (DUF7090)", "partial_evidence_count": null, "pfam_id": "PF23365", "proteins": 283, "proteomes": 282, "short_name": "DUF7090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23365", "structures": 0, "taxa": 443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins found mainly in Halobacteria. These proteins are likely associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR055968", "known_evidence_count": null, "matches": 283, "name": "Family of unknown function (DUF7546)", "partial_evidence_count": null, "pfam_id": "PF24412", "proteins": 283, "proteomes": 189, "short_name": "DUF7546", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24412", "structures": 0, "taxa": 294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an unique alpha/beta structure consisting of a mixed five-stranded beta-sheet in which the last beta-strand is antiparallel to the rest, and an alpha-helix which packs nearly orthogonal to the beta-sheet.", "domain_architectures": 11, "interpro_id": "IPR058504", "known_evidence_count": null, "matches": 285, "name": "Domain of unknown function (DUF8191)", "partial_evidence_count": null, "pfam_id": "PF26609", "proteins": 283, "proteomes": 171, "short_name": "DUF8191", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26609", "structures": 0, "taxa": 441, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 200, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of unknown function. It includes Porphyromonas gingivalis protein PGN_1290 [swissprot:B2RGS5] which was found to be down-regulated in a GppX mutant [[cite:PUB00163732]]. This domain is composed of a four stranded beta sheet (strand order 1-4-3-2) with two alpha helices packed on one side. AlphaFold3 suggests these proteins form confident homodimers ([swissprot:R9HNH3] ipTM=0.9 pTM=0.92).", "domain_architectures": 1, "interpro_id": "IPR061536", "known_evidence_count": null, "matches": 283, "name": "Domain of unknown function (DUF8466)", "partial_evidence_count": null, "pfam_id": "PF28811", "proteins": 283, "proteomes": 137, "short_name": "DUF8466", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28811", "structures": 0, "taxa": 237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021518", "known_evidence_count": null, "matches": 282, "name": "Protein of unknown function (DUF3181)", "partial_evidence_count": null, "pfam_id": "PF11378", "proteins": 282, "proteomes": 277, "short_name": "DUF3181", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11378", "structures": 0, "taxa": 760, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 187, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021700", "known_evidence_count": null, "matches": 282, "name": "Protein of unknown function (DUF3283)", "partial_evidence_count": null, "pfam_id": "PF11686", "proteins": 282, "proteomes": 278, "short_name": "DUF3283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11686", "structures": 0, "taxa": 349, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 168, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025454", "known_evidence_count": null, "matches": 282, "name": "Domain of unknown function (DUF4275)", "partial_evidence_count": null, "pfam_id": "PF14101", "proteins": 282, "proteomes": 271, "short_name": "DUF4275", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14101", "structures": 0, "taxa": 516, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 271, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043823", "known_evidence_count": null, "matches": 282, "name": "Family of unknown function (DUF5800)", "partial_evidence_count": null, "pfam_id": "PF19115", "proteins": 282, "proteomes": 282, "short_name": "DUF5800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19115", "structures": 0, "taxa": 440, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. There is a conserved N-terminal MPT sequence motif. AlphaFold predicts that this protein is composed of an N-terminal alpha helix followed by a four stranded beta sheet. AlphaFold also predicts the protein forms a strong dimer interface. It shows some weak structural similarity to the N-terminal domain of RnlA toxin.", "domain_architectures": 3, "interpro_id": "IPR054181", "known_evidence_count": null, "matches": 282, "name": "Domain of unknown function (DUF6888)", "partial_evidence_count": null, "pfam_id": "PF21828", "proteins": 282, "proteomes": 113, "short_name": "DUF6888", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21828", "structures": 0, "taxa": 347, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of proteins from halobacteria. It shows several Y and Q conserved residues and is predicted to show an antiparallel beta-sheet and an alpha-helix.", "domain_architectures": 4, "interpro_id": "IPR055520", "known_evidence_count": null, "matches": 282, "name": "Family of unknown function (DUF7094)", "partial_evidence_count": null, "pfam_id": "PF23375", "proteins": 282, "proteomes": 277, "short_name": "DUF7094", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23375", "structures": 0, "taxa": 429, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 272, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR055955", "known_evidence_count": null, "matches": 282, "name": "Family of unknown function (DUF7533)", "partial_evidence_count": null, "pfam_id": "PF24377", "proteins": 282, "proteomes": 269, "short_name": "DUF7533", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24377", "structures": 0, "taxa": 416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in HFX_2341 from Haloferax mediterranei and similar archaeal proteins. HFX_2341 is a global regulator involved in cas gene regulation. This domain is often found associated with [pfam:PF19810].", "domain_architectures": 4, "interpro_id": "IPR056678", "known_evidence_count": null, "matches": 282, "name": "Domain of unknown function (DUF7776)", "partial_evidence_count": null, "pfam_id": "PF24989", "proteins": 282, "proteomes": 274, "short_name": "DUF7776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24989", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of around 125 residues in length. Members of this family seem to be specific to Listeria and Streptococcus species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR010738", "known_evidence_count": null, "matches": 281, "name": "Protein of unknown function (DUF1310)", "partial_evidence_count": null, "pfam_id": "PF07006", "proteins": 281, "proteomes": 95, "short_name": "DUF1310", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07006", "structures": 0, "taxa": 177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found in a small family of cyanobacterial protein. These proteins are functionally uncharacterised.", "domain_architectures": 3, "interpro_id": "IPR014947", "known_evidence_count": null, "matches": 286, "name": "Domain of unknown function (DUF1818)", "partial_evidence_count": null, "pfam_id": "PF08848", "proteins": 281, "proteomes": 270, "short_name": "DUF1818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08848", "structures": 2, "taxa": 765, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised.", "domain_architectures": 5, "interpro_id": "IPR014952", "known_evidence_count": null, "matches": 281, "name": "Domain of unknown function (DUF1823)", "partial_evidence_count": null, "pfam_id": "PF08853", "proteins": 281, "proteomes": 275, "short_name": "DUF1823", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08853", "structures": 1, "taxa": 802, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in viruses. Proteins in this family are typically between 145 and 1707 amino acids in length. The family is found in association with [pfam:PF01443], [pfam:PF01661], [pfam:PF05417], [pfam:PF01660], [pfam:PF00978]. There is a single completely conserved residue L that may be functionally important.", "domain_architectures": 12, "interpro_id": "IPR022202", "known_evidence_count": null, "matches": 289, "name": "Protein of unknown function (DUF3729)", "partial_evidence_count": null, "pfam_id": "PF12526", "proteins": 281, "proteomes": 12, "short_name": "DUF3729", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12526", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are typically between 191 and 204 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046147", "known_evidence_count": null, "matches": 281, "name": "Family of unknown function (DUF6149)", "partial_evidence_count": null, "pfam_id": "PF19646", "proteins": 281, "proteomes": 270, "short_name": "DUF6149", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19646", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved motifs AxYxET, ERxL/VxF and GYAMLK/RVR. Members are predicted to show a beta-sheet and an alpha-helix.", "domain_architectures": 1, "interpro_id": "IPR055535", "known_evidence_count": null, "matches": 281, "name": "Family of unknown function (DUF7111)", "partial_evidence_count": null, "pfam_id": "PF23423", "proteins": 281, "proteomes": 280, "short_name": "DUF7111", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23423", "structures": 0, "taxa": 444, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of proteins from halobacteria. Members are predicted to show an alpha-beta configuration.", "domain_architectures": 3, "interpro_id": "IPR055546", "known_evidence_count": null, "matches": 281, "name": "Family of unknown function (DUF7122)", "partial_evidence_count": null, "pfam_id": "PF23437", "proteins": 281, "proteomes": 281, "short_name": "DUF7122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23437", "structures": 0, "taxa": 457, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 248, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an Ig-like domain found in a group of uncharacterised sequences from nematodes. The function of this domain is unknown.", "domain_architectures": 33, "interpro_id": "IPR056005", "known_evidence_count": null, "matches": 353, "name": "Domain of unknown function (DUF7583)", "partial_evidence_count": null, "pfam_id": "PF24486", "proteins": 281, "proteomes": 6, "short_name": "DUF7583", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24486", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain found in a family of uncharacterised proteins from archaea. The proteins are predominantly found in the Halobacteria class, which includes members of the Haloferacaceae, Haloarculaceae, and Natrialbaceae families. The proteins in this family are typically around 550-580 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR058499", "known_evidence_count": null, "matches": 281, "name": "Domain of unknown function (DUF8186) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26589", "proteins": 281, "proteomes": 165, "short_name": "DUF8186", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26589", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an immunoglobulin-like domain found in proteins that contain a C-terminal LruC domain. These proteins are found in pseudomonadati bacteria.", "domain_architectures": 4, "interpro_id": "IPR061539", "known_evidence_count": null, "matches": 281, "name": "Domain of unknown function (DUF8469)", "partial_evidence_count": null, "pfam_id": "PF28815", "proteins": 281, "proteomes": 186, "short_name": "DUF8469", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28815", "structures": 0, "taxa": 351, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR035223", "known_evidence_count": null, "matches": 280, "name": "Family of unknown function (DUF5335)", "partial_evidence_count": null, "pfam_id": "PF17269", "proteins": 280, "proteomes": 252, "short_name": "DUF5335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17269", "structures": 0, "taxa": 579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 267, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043953", "known_evidence_count": null, "matches": 280, "name": "Family of unknown function (DUF5784)", "partial_evidence_count": null, "pfam_id": "PF19096", "proteins": 280, "proteomes": 275, "short_name": "DUF5784", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19096", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 268, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function found predominantly in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043808", "known_evidence_count": null, "matches": 280, "name": "Family of unknown function (DUF5790)", "partial_evidence_count": null, "pfam_id": "PF19103", "proteins": 280, "proteomes": 278, "short_name": "DUF5790", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19103", "structures": 0, "taxa": 467, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function found in Halobacteria.", "domain_architectures": 3, "interpro_id": "IPR043830", "known_evidence_count": null, "matches": 286, "name": "Family of unknown function (DUF5807)", "partial_evidence_count": null, "pfam_id": "PF19123", "proteins": 280, "proteomes": 280, "short_name": "DUF5807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19123", "structures": 0, "taxa": 435, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in uncharacterised bacterial proteins that is predicted to be helical. It contains a nearly invariant tryptophan toward the N terminus and a highly conserved motif [F/Y]GGMGSx(2)D toward the C-terminus.", "domain_architectures": 3, "interpro_id": "IPR054239", "known_evidence_count": null, "matches": 280, "name": "Domain of unknown function (DUF6966)", "partial_evidence_count": null, "pfam_id": "PF22294", "proteins": 280, "proteomes": 268, "short_name": "DUF6966", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22294", "structures": 0, "taxa": 597, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 266, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a helix-turn-helix (HTH) domain found in a group of functionally uncharacterized prokaryotic proteins, typically associated with the Domain of Unknown Function (DUF5817) (Pfam: PF19134).", "domain_architectures": 2, "interpro_id": "IPR053849", "known_evidence_count": null, "matches": 280, "name": "DUF5817, C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF22798", "proteins": 280, "proteomes": 279, "short_name": "DUF5817_CT", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22798", "structures": 0, "taxa": 437, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 203, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins predominantly found in the class Clostridia. The proteins containing this domain are typically between 60 and 130 amino acids in length. The domain is highly conserved across various species within the Bacillota and Thermodesulfobacteriota phyla. Structure prediction suggests this protein is composed of two alpha helices and forms a head to tail dimer conformation. The sequences contain a set of histidines in helix one that according to AlphaFold 3 confidently binds to a zinc ion.", "domain_architectures": 3, "interpro_id": "IPR058493", "known_evidence_count": null, "matches": 280, "name": "Domain of unknown function (DUF8180)", "partial_evidence_count": null, "pfam_id": "PF26551", "proteins": 280, "proteomes": 256, "short_name": "DUF8180", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26551", "structures": 0, "taxa": 541, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 194, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021389", "known_evidence_count": null, "matches": 279, "name": "Protein of unknown function (DUF3022)", "partial_evidence_count": null, "pfam_id": "PF11226", "proteins": 279, "proteomes": 176, "short_name": "DUF3022", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11226", "structures": 0, "taxa": 196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043835", "known_evidence_count": null, "matches": 279, "name": "Family of unknown function (DUF5811)", "partial_evidence_count": null, "pfam_id": "PF19128", "proteins": 279, "proteomes": 276, "short_name": "DUF5811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19128", "structures": 0, "taxa": 430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001417) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the myxochromide D biosynthetic gene cluster from Cystobacterineae bacterium [[cite:PUB00098945]]. This family appears to be predominantly found in Cystobacterineae.", "domain_architectures": 4, "interpro_id": "IPR046277", "known_evidence_count": null, "matches": 279, "name": "Family of unknown function (DUF6310)", "partial_evidence_count": null, "pfam_id": "PF19829", "proteins": 279, "proteomes": 44, "short_name": "DUF6310", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19829", "structures": 0, "taxa": 106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are approximately 100 amino acids in length. Members in this family are thought to belong to the MarR family of transcriptional regulators.", "domain_architectures": 1, "interpro_id": "IPR045490", "known_evidence_count": null, "matches": 279, "name": "Family of unknown function (DUF6432)", "partial_evidence_count": null, "pfam_id": "PF20024", "proteins": 279, "proteomes": 279, "short_name": "DUF6432", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20024", "structures": 0, "taxa": 433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 267, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved motifs WSYY, RxYxR and HxK/RR. Members are predicted to show a predominantly alpha configuration.", "domain_architectures": 2, "interpro_id": "IPR055541", "known_evidence_count": null, "matches": 316, "name": "Family of unknown function (DUF7117)", "partial_evidence_count": null, "pfam_id": "PF23430", "proteins": 279, "proteomes": 277, "short_name": "DUF7117", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23430", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 228, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found either standalone or in tandem in uncharacterised eukaryotic proteins. It has a weak sequence similarity to Nucleotide-diphospho-sugar transferases, in particular to Glycolipid 2-alpha-mannosyltransferases ([pfam:PF01793]) and is predicted to adopt similar structure.", "domain_architectures": 15, "interpro_id": "IPR055588", "known_evidence_count": null, "matches": 358, "name": "Domain of unknown function (DUF7164)", "partial_evidence_count": null, "pfam_id": "PF23741", "proteins": 279, "proteomes": 98, "short_name": "DUF7164", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23741", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain in large, membrane-embedded proteins of mobile elements such as the Bacillus subtilis natto plasmid pLS20. It is predicted to contain five transmembrane alpha-helices.", "domain_architectures": 3, "interpro_id": "IPR058066", "known_evidence_count": null, "matches": 285, "name": "Domain of unknown function (DUF8208)", "partial_evidence_count": null, "pfam_id": "PF26635", "proteins": 279, "proteomes": 224, "short_name": "DUF8208", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26635", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This predicted RNA recognition domain (RRM) is found in a group of uncharacterised proteins from lower eukaryotes.", "domain_architectures": 7, "interpro_id": "IPR061559", "known_evidence_count": null, "matches": 280, "name": "Domain of unknown function (DUF8489)", "partial_evidence_count": null, "pfam_id": "PF28977", "proteins": 279, "proteomes": 260, "short_name": "DUF8489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28977", "structures": 0, "taxa": 774, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043809", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF5791)", "partial_evidence_count": null, "pfam_id": "PF19104", "proteins": 278, "proteomes": 278, "short_name": "DUF5791", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19104", "structures": 0, "taxa": 433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 267, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043853", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF5815)", "partial_evidence_count": null, "pfam_id": "PF19132", "proteins": 278, "proteomes": 277, "short_name": "DUF5815", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19132", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043858", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF5820)", "partial_evidence_count": null, "pfam_id": "PF19137", "proteins": 278, "proteomes": 278, "short_name": "DUF5820", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19137", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 269, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved motifs WHGP, QLWC and RxYxP. It is predicted to adopt a predominantly beta structure with a short alpha-helix.", "domain_architectures": 1, "interpro_id": "IPR054623", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF7098)", "partial_evidence_count": null, "pfam_id": "PF23384", "proteins": 278, "proteomes": 278, "short_name": "DUF7098", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23384", "structures": 0, "taxa": 430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. Members are predicted to show an alpha-beta configuration with similarity to the Rossmann fold of the TrkA-N domain ([pfam:PF02254]).", "domain_architectures": 1, "interpro_id": "IPR055550", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF7126)", "partial_evidence_count": null, "pfam_id": "PF23443", "proteins": 278, "proteomes": 277, "short_name": "DUF7126", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23443", "structures": 0, "taxa": 434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short proteins from archaea. Members are predicted to adopt an alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR055895", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF7472)", "partial_evidence_count": null, "pfam_id": "PF24284", "proteins": 278, "proteomes": 278, "short_name": "DUF7472", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24284", "structures": 0, "taxa": 437, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal region from a family of uncharacterised proteins from halophilic archaea. The proteins in this family are predominantly found in the class Halobacteria, which includes families such as Haloferacaceae, Natrialbaceae, and Haloarculaceae. The proteins in this family are approximately 130-150 amino acids in length. This region is often associated with an N-terminal RHH domain.", "domain_architectures": 2, "interpro_id": "IPR058459", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF8146)", "partial_evidence_count": null, "pfam_id": "PF26471", "proteins": 278, "proteomes": 278, "short_name": "DUF8146", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26471", "structures": 0, "taxa": 434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 183, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from the Bacillota phylum. The family is predominantly found in bacteria such as Paenibacillus and Bacillus species. Proteins in this family are typically around 280-300 amino acids in length. The proteins are predicted integral membrane proteins containing eight transmembrane domains. These proteins show structural similarity to [pfam:PF12822] suggesting this family is likely to be a transporter for an as yet unidentified substrate.", "domain_architectures": 1, "interpro_id": "IPR058484", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF8171)", "partial_evidence_count": null, "pfam_id": "PF26509", "proteins": 278, "proteomes": 276, "short_name": "DUF8171", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26509", "structures": 0, "taxa": 513, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This protein is found in bacteria and archaea. Proteins in this family are typically between 367 to 1857 amino acids in length.", "domain_architectures": 90, "interpro_id": "IPR021779", "known_evidence_count": null, "matches": 388, "name": "Protein of unknown function (DUF3344)", "partial_evidence_count": null, "pfam_id": "PF11824", "proteins": 277, "proteomes": 114, "short_name": "DUF3344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11824", "structures": 0, "taxa": 255, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 62 to 84 amino acids in length. This protein has two completely conserved residues (A and Y) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR021945", "known_evidence_count": null, "matches": 277, "name": "Protein of unknown function (DUF3562)", "partial_evidence_count": null, "pfam_id": "PF12085", "proteins": 277, "proteomes": 220, "short_name": "DUF3562", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12085", "structures": 0, "taxa": 298, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 198, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 120 and 131 amino acids in length. There are two completely conserved residues (G and Y) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025469", "known_evidence_count": null, "matches": 277, "name": "Domain of unknown function (DUF4320)", "partial_evidence_count": null, "pfam_id": "PF14208", "proteins": 277, "proteomes": 200, "short_name": "DUF4320", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14208", "structures": 0, "taxa": 403, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 221, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes.", "domain_architectures": 5, "interpro_id": "IPR029206", "known_evidence_count": null, "matches": 278, "name": "Protein of unknown function (DUF4532)", "partial_evidence_count": null, "pfam_id": "PF15046", "proteins": 277, "proteomes": 240, "short_name": "DUF4532", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15046", "structures": 0, "taxa": 920, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 600 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 15, "interpro_id": "IPR032309", "known_evidence_count": null, "matches": 277, "name": "Domain of unknown function (DUF4983)", "partial_evidence_count": null, "pfam_id": "PF16356", "proteins": 277, "proteomes": 212, "short_name": "DUF4983", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16356", "structures": 0, "taxa": 274, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function. It is present in Bacteria and most of the family members are predicted to have 4 trans-membrane regions.", "domain_architectures": 3, "interpro_id": "IPR020348", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF5360)", "partial_evidence_count": null, "pfam_id": "PF17314", "proteins": 277, "proteomes": 276, "short_name": "DUF5360", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17314", "structures": 0, "taxa": 492, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 126, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry is mainly found in Firmicutes and has a notable number of highly conserved aromatic amino acids. The entry is found towards the C-terminus of PFAM:PF02368 in some of the members and there are members that present two copies.", "domain_architectures": 10, "interpro_id": "IPR043759", "known_evidence_count": null, "matches": 283, "name": "Family of unknown function (DUF5704)", "partial_evidence_count": null, "pfam_id": "PF18964", "proteins": 277, "proteomes": 188, "short_name": "DUF5704", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18964", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043927", "known_evidence_count": null, "matches": 277, "name": "Family of unknown function (DUF5778)", "partial_evidence_count": null, "pfam_id": "PF19090", "proteins": 277, "proteomes": 277, "short_name": "DUF5778", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19090", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short domain of unknown function is found at the N-terminus of [pfam:PF01103].", "domain_architectures": 2, "interpro_id": "IPR046024", "known_evidence_count": null, "matches": 277, "name": "Domain of unknown function (DUF5982)", "partial_evidence_count": null, "pfam_id": "PF19412", "proteins": 277, "proteomes": 133, "short_name": "DUF5982", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19412", "structures": 0, "taxa": 224, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial immunoglobulin-like domain of approximately 65 residues. This domain is found predominantly in Planctomycetota and Bacillota. These domains are typically found in large secreted or surface-associated proteins, often with multiple tandem repeats. The function of this domain remains to be determined.", "domain_architectures": 14, "interpro_id": "IPR061877", "known_evidence_count": null, "matches": 277, "name": "Domain of unknown function (DUF8816)", "partial_evidence_count": null, "pfam_id": "PF31119", "proteins": 277, "proteomes": 238, "short_name": "DUF8816", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31119", "structures": 0, "taxa": 536, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This uncharacterised family of proteins are principally found in cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR014953", "known_evidence_count": null, "matches": 276, "name": "Domain of unknown function (DUF1824)", "partial_evidence_count": null, "pfam_id": "PF08854", "proteins": 276, "proteomes": 266, "short_name": "DUF1824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08854", "structures": 1, "taxa": 759, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 56 and 71 amino acids in length. There is a conserved YTP sequence motif.", "domain_architectures": 3, "interpro_id": "IPR025028", "known_evidence_count": null, "matches": 276, "name": "Protein of unknown function (DUF3951)", "partial_evidence_count": null, "pfam_id": "PF13131", "proteins": 276, "proteomes": 241, "short_name": "DUF3951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13131", "structures": 0, "taxa": 318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 233, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 289 and 334 amino acids in length. There are two completely conserved residues (W and G) that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR031366", "known_evidence_count": null, "matches": 288, "name": "Domain of unknown function (DUF4663)", "partial_evidence_count": null, "pfam_id": "PF15668", "proteins": 276, "proteomes": 229, "short_name": "DUF4663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15668", "structures": 0, "taxa": 839, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 2, "interpro_id": "IPR043832", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF5809)", "partial_evidence_count": null, "pfam_id": "PF19125", "proteins": 276, "proteomes": 276, "short_name": "DUF5809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19125", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043867", "known_evidence_count": null, "matches": 276, "name": "Family of unknown function (DUF5827)", "partial_evidence_count": null, "pfam_id": "PF19145", "proteins": 276, "proteomes": 275, "short_name": "DUF5827", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19145", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 110 and 124 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046143", "known_evidence_count": null, "matches": 276, "name": "Family of unknown function (DUF6145)", "partial_evidence_count": null, "pfam_id": "PF19642", "proteins": 276, "proteomes": 275, "short_name": "DUF6145", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19642", "structures": 0, "taxa": 445, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically 165 and 195 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046652", "known_evidence_count": null, "matches": 276, "name": "Family of unknown function (DUF6764)", "partial_evidence_count": null, "pfam_id": "PF20550", "proteins": 276, "proteomes": 179, "short_name": "DUF6764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20550", "structures": 0, "taxa": 263, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from archaea. It is predicted to adopt an all-helical configuration.", "domain_architectures": 2, "interpro_id": "IPR055543", "known_evidence_count": null, "matches": 277, "name": "Family of unknown function (DUF7119)", "partial_evidence_count": null, "pfam_id": "PF23433", "proteins": 276, "proteomes": 275, "short_name": "DUF7119", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23433", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved integral membrane domain of approximately 100-120 amino acids found exclusively in halophilic archaea. The family is restricted to the order Halobacteriales, particularly the families Natrialbaceae, Haloferacaceae and Haloarculaceae.", "domain_architectures": 1, "interpro_id": "IPR061596", "known_evidence_count": null, "matches": 276, "name": "Domain of unknown function (DUF8526)", "partial_evidence_count": null, "pfam_id": "PF29286", "proteins": 276, "proteomes": 268, "short_name": "DUF8526", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29286", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins with unknown function.", "domain_architectures": 2, "interpro_id": "IPR022538", "known_evidence_count": null, "matches": 275, "name": "Protein of unknown function (DUF2570)", "partial_evidence_count": null, "pfam_id": "PF10828", "proteins": 275, "proteomes": 215, "short_name": "DUF2570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10828", "structures": 0, "taxa": 395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. There is a conserved EKK sequence motif.", "domain_architectures": 1, "interpro_id": "IPR024998", "known_evidence_count": null, "matches": 275, "name": "Protein of unknown function (DUF3906)", "partial_evidence_count": null, "pfam_id": "PF13046", "proteins": 275, "proteomes": 274, "short_name": "DUF3906", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13046", "structures": 0, "taxa": 360, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterised proteins around 300 residues in length and found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 15, "interpro_id": "IPR032594", "known_evidence_count": null, "matches": 275, "name": "Domain of unknown function (DUF4906)", "partial_evidence_count": null, "pfam_id": "PF16249", "proteins": 275, "proteomes": 94, "short_name": "DUF4906", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16249", "structures": 0, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 168, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in Bacteroides and Sphingobacterium. The members in this family are around 350 residues in length.", "domain_architectures": 2, "interpro_id": "IPR032173", "known_evidence_count": null, "matches": 279, "name": "Domain of unknown function (DUF5007)", "partial_evidence_count": null, "pfam_id": "PF16398", "proteins": 275, "proteomes": 171, "short_name": "DUF5007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16398", "structures": 0, "taxa": 217, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043814", "known_evidence_count": null, "matches": 275, "name": "Family of unknown function (DUF5796)", "partial_evidence_count": null, "pfam_id": "PF19109", "proteins": 275, "proteomes": 274, "short_name": "DUF5796", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19109", "structures": 0, "taxa": 427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria, but also in Eukaryotes. This family contains some members that are predicted as C2H2-type domain-containing proteins.", "domain_architectures": 1, "interpro_id": "IPR043833", "known_evidence_count": null, "matches": 275, "name": "Family of unknown function (DUF5810)", "partial_evidence_count": null, "pfam_id": "PF19126", "proteins": 275, "proteomes": 275, "short_name": "DUF5810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19126", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 263, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found predominantly in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043851", "known_evidence_count": null, "matches": 275, "name": "Family of unknown function (DUF5813)", "partial_evidence_count": null, "pfam_id": "PF19130", "proteins": 275, "proteomes": 275, "short_name": "DUF5813", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19130", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of the uncharacterised protein HVO_0731 from Haloferax volcanii ([swissprot:D4GTA0]) and similar proteins from halobacteria. It is predicted to adopt an all-alpha structure. The function of this domain is unknown.", "domain_architectures": 2, "interpro_id": "IPR056494", "known_evidence_count": null, "matches": 275, "name": "DUF7108, C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF23420", "proteins": 275, "proteomes": 275, "short_name": "DUF7108_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23420", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved motifs YVWVCD, RGF and RTQFxR. Members are predicted to show an alpha-beta configuration.", "domain_architectures": 1, "interpro_id": "IPR055537", "known_evidence_count": null, "matches": 275, "name": "Family of unknown function (DUF7113)", "partial_evidence_count": null, "pfam_id": "PF23425", "proteins": 275, "proteomes": 273, "short_name": "DUF7113", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23425", "structures": 0, "taxa": 426, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial protein domain of unknown function.", "domain_architectures": 2, "interpro_id": "IPR056085", "known_evidence_count": null, "matches": 275, "name": "Domain of unknown function (DUF7668)", "partial_evidence_count": null, "pfam_id": "PF24705", "proteins": 275, "proteomes": 261, "short_name": "DUF7668", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24705", "structures": 0, "taxa": 574, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain a pair of likely transmembrane helices at the C-terminal end.", "domain_architectures": 2, "interpro_id": "IPR058283", "known_evidence_count": null, "matches": 275, "name": "Family of unknown function (DUF7977)", "partial_evidence_count": null, "pfam_id": "PF25932", "proteins": 275, "proteomes": 274, "short_name": "DUF7977", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25932", "structures": 0, "taxa": 434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 2, "interpro_id": "IPR058306", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF7993)", "partial_evidence_count": null, "pfam_id": "PF25956", "proteins": 275, "proteomes": 269, "short_name": "DUF7993", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25956", "structures": 0, "taxa": 415, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 169 and 182 amino acids in length. There is a single completely conserved residue L that may be functionally important.", "domain_architectures": 8, "interpro_id": "IPR031935", "known_evidence_count": null, "matches": 284, "name": "Domain of unknown function (DUF4770)", "partial_evidence_count": null, "pfam_id": "PF15994", "proteins": 274, "proteomes": 138, "short_name": "DUF4770", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15994", "structures": 0, "taxa": 551, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins mainly found in Proteobacteria includes RsaM from Burkholderia cenocepacia. RsaM is a transcriptional regulator involved in quorum sensing (QS). This protein folds into a unique domain with a five-stranded antiparallel beta-sheet that wraps around two alpha-helices [[cite:PUB00100860],[cite:PUB00100861]].", "domain_architectures": 2, "interpro_id": "IPR032598", "known_evidence_count": null, "matches": 274, "name": "Domain of unknown function (DUF4902)", "partial_evidence_count": null, "pfam_id": "PF16245", "proteins": 274, "proteomes": 222, "short_name": "DUF4902", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16245", "structures": 1, "taxa": 348, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043821", "known_evidence_count": null, "matches": 274, "name": "Family of unknown function (DUF5799)", "partial_evidence_count": null, "pfam_id": "PF19113", "proteins": 274, "proteomes": 274, "short_name": "DUF5799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19113", "structures": 0, "taxa": 425, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of the uncharacterised protein HVO_0731 from Haloferax volcanii ([swissprot:D4GTA0]) and similar proteins from halobacteria. It has several conserved motifs RLTR/KLxR and LVxHPxEW. It is predicted to adopt an alpha-beta structure. The function of this domain is unknown.", "domain_architectures": 1, "interpro_id": "IPR055532", "known_evidence_count": null, "matches": 274, "name": "Domain of unknown function (DUF7108)", "partial_evidence_count": null, "pfam_id": "PF23418", "proteins": 274, "proteomes": 274, "short_name": "DUF7108", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23418", "structures": 0, "taxa": 427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. They contain two pairs of conserved cysteines that are likely involved in metal coordination. It is predicted they may structurally resemble Zinc-beta ribbon domains.", "domain_architectures": 1, "interpro_id": "IPR055982", "known_evidence_count": null, "matches": 274, "name": "Family of unknown function (DUF7560)", "partial_evidence_count": null, "pfam_id": "PF24441", "proteins": 274, "proteomes": 166, "short_name": "DUF7560", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24441", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 2, "interpro_id": "IPR043940", "known_evidence_count": null, "matches": 275, "name": "Family of unknown function (DUF5781)", "partial_evidence_count": null, "pfam_id": "PF19093", "proteins": 273, "proteomes": 272, "short_name": "DUF5781", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19093", "structures": 0, "taxa": 422, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000762) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the exopolysaccharide biosynthetic gene cluster from Rhizobium leguminosarum bv. viciae and appears to be predominantly found in proteobacteria [[cite:PUB00099421]].", "domain_architectures": 1, "interpro_id": "IPR046071", "known_evidence_count": null, "matches": 273, "name": "Family of unknown function (DUF6030)", "partial_evidence_count": null, "pfam_id": "PF19495", "proteins": 273, "proteomes": 233, "short_name": "DUF6030", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19495", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in bacterial proteins and it is functionally uncharacterised. However, some proteins are putative glycoside hydrolases and this domain has some overlaps with clan family members of CL0058. Proteins containing this domain are typically between 678 and 749 amino acids in length.", "domain_architectures": 12, "interpro_id": "IPR046226", "known_evidence_count": null, "matches": 277, "name": "Domain of unknown function (DUF6259)", "partial_evidence_count": null, "pfam_id": "PF19773", "proteins": 273, "proteomes": 194, "short_name": "DUF6259", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19773", "structures": 0, "taxa": 486, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001055) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the yersiniabactin biosynthetic gene cluster from Escherichia coli [[cite:PUB00098903]]. This family appears to be predominantly found in proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR045664", "known_evidence_count": null, "matches": 274, "name": "Family of unknown function (DUF6387)", "partial_evidence_count": null, "pfam_id": "PF19924", "proteins": 273, "proteomes": 240, "short_name": "DUF6387", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19924", "structures": 0, "taxa": 458, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 81 and 125 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046569", "known_evidence_count": null, "matches": 273, "name": "Family of unknown function (DUF6723)", "partial_evidence_count": null, "pfam_id": "PF20484", "proteins": 273, "proteomes": 119, "short_name": "DUF6723", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20484", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved motifs GVQLIYEGLR, EPW and GR/K/QxQT/S. Members are predicted to show an all-alpha configuration.", "domain_architectures": 3, "interpro_id": "IPR055538", "known_evidence_count": null, "matches": 316, "name": "Family of unknown function (DUF7114)", "partial_evidence_count": null, "pfam_id": "PF23426", "proteins": 273, "proteomes": 271, "short_name": "DUF7114", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23426", "structures": 0, "taxa": 425, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. Members are predicted to adopt an all-alpha structure.", "domain_architectures": 2, "interpro_id": "IPR055542", "known_evidence_count": null, "matches": 274, "name": "Domain of unknown function (DUF7118)", "partial_evidence_count": null, "pfam_id": "PF23432", "proteins": 273, "proteomes": 272, "short_name": "DUF7118", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23432", "structures": 0, "taxa": 426, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 262, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to be organised into two domains, an N-terminal with an all-alpha configuration and a C-terminal with an alpha-beta structure.", "domain_architectures": 4, "interpro_id": "IPR055945", "known_evidence_count": null, "matches": 280, "name": "Family of unknown function (DUF7523)", "partial_evidence_count": null, "pfam_id": "PF24367", "proteins": 273, "proteomes": 273, "short_name": "DUF7523", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24367", "structures": 0, "taxa": 450, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 264, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found mainly in Halobacteria. These proteins are likely to form a dimer structure as predicted by AlphaFold with significant ipTM score.", "domain_architectures": 2, "interpro_id": "IPR055967", "known_evidence_count": null, "matches": 273, "name": "Family of unknown function (DUF7545)", "partial_evidence_count": null, "pfam_id": "PF24411", "proteins": 273, "proteomes": 271, "short_name": "DUF7545", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24411", "structures": 0, "taxa": 419, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 260, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain from a family of uncharacterised proteins from halophilic archaea. The proteins in this family are predominantly found in the class Halobacteria, which includes families such as Natrialbaceae, Haloferacaceae, and Haloarculaceae. The proteins in this family are generally around 270-330 amino acids in length. This domain is found associated with a peptidase M23 family like domain at the N-terminus.", "domain_architectures": 3, "interpro_id": "IPR058817", "known_evidence_count": null, "matches": 274, "name": "Domain of unknown function (DUF8155) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26483", "proteins": 273, "proteomes": 272, "short_name": "DUF8155_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26483", "structures": 0, "taxa": 450, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 261, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function predominantly found in Halobacteria.", "domain_architectures": 2, "interpro_id": "IPR043850", "known_evidence_count": null, "matches": 273, "name": "Family of unknown function (DUF5812)", "partial_evidence_count": null, "pfam_id": "PF19129", "proteins": 272, "proteomes": 272, "short_name": "DUF5812", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19129", "structures": 0, "taxa": 422, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function predominantly found in Halobacteria. This family includes some members which are thought to be peptidoglycan binding proteins.", "domain_architectures": 1, "interpro_id": "IPR043860", "known_evidence_count": null, "matches": 272, "name": "Family of unknown function (DUF5822)", "partial_evidence_count": null, "pfam_id": "PF19139", "proteins": 272, "proteomes": 272, "short_name": "DUF5822", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19139", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001432) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the myxochromide D biosynthetic gene cluster from Stigmatella erecta [[cite:PUB00098945]].", "domain_architectures": 1, "interpro_id": "IPR046203", "known_evidence_count": null, "matches": 272, "name": "Family of unknown function (DUF6236)", "partial_evidence_count": null, "pfam_id": "PF19749", "proteins": 272, "proteomes": 267, "short_name": "DUF6236", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19749", "structures": 0, "taxa": 586, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 30 amino acids in length. There is a conserved IAVASA sequence motif.", "domain_architectures": 1, "interpro_id": "IPR045505", "known_evidence_count": null, "matches": 272, "name": "Family of unknown function (DUF6486)", "partial_evidence_count": null, "pfam_id": "PF20096", "proteins": 272, "proteomes": 75, "short_name": "DUF6486", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20096", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, mainly Bacteroidetes and Firmicutes. Proteins in this family are typically between 239 and 255 amino acids in length. There are some conserved sequences, GxY, EKxxVD and YAxxRR and a conserved His.", "domain_architectures": 2, "interpro_id": "IPR046484", "known_evidence_count": null, "matches": 272, "name": "Family of unknown function (DUF6577)", "partial_evidence_count": null, "pfam_id": "PF20217", "proteins": 272, "proteomes": 245, "short_name": "DUF6577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20217", "structures": 0, "taxa": 539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal of HVO_2519 from Haloferax volcanii ([swissprot:D4GTV1]) and similar proteins mainly found in halobacteria. It has several conserved motifs RTxxYR, Y/FxHxxxR an RRK. It is predicted to show an alpha-beta configuration.", "domain_architectures": 2, "interpro_id": "IPR055539", "known_evidence_count": null, "matches": 272, "name": "Domain of unknown function (DUF7115)", "partial_evidence_count": null, "pfam_id": "PF23428", "proteins": 272, "proteomes": 271, "short_name": "DUF7115", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23428", "structures": 0, "taxa": 422, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found at the C-terminal end of a group of archaeal proteins. It is predicted to adopt an alpha-beta structure.", "domain_architectures": 1, "interpro_id": "IPR055949", "known_evidence_count": null, "matches": 272, "name": "Domain of unknown function (DUF7527)", "partial_evidence_count": null, "pfam_id": "PF24371", "proteins": 272, "proteomes": 269, "short_name": "DUF7527", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24371", "structures": 0, "taxa": 413, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains sequences derived from a group of hypothetical proteins expressed by Arabidopsis thaliana. These sequences are highly similar and the region concerned is about 100 residues long.", "domain_architectures": 22, "interpro_id": "IPR012436", "known_evidence_count": null, "matches": 298, "name": "Protein of unknown function (DUF1633)", "partial_evidence_count": null, "pfam_id": "PF07794", "proteins": 271, "proteomes": 14, "short_name": "DUF1633", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07794", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043813", "known_evidence_count": null, "matches": 271, "name": "Family of unknown function (DUF5795)", "partial_evidence_count": null, "pfam_id": "PF19108", "proteins": 271, "proteomes": 270, "short_name": "DUF5795", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19108", "structures": 0, "taxa": 417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses. This family was also found in Bacteria.", "domain_architectures": 1, "interpro_id": "IPR043876", "known_evidence_count": null, "matches": 271, "name": "Family of unknown function (DUF5856)", "partial_evidence_count": null, "pfam_id": "PF19174", "proteins": 271, "proteomes": 268, "short_name": "DUF5856", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19174", "structures": 0, "taxa": 622, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 301 and 317 amino acids in length. These proteins contain a conserved sequence motif FREE that may be functionally important.", "domain_architectures": 5, "interpro_id": "IPR046723", "known_evidence_count": null, "matches": 272, "name": "Family of unknown function (DUF6615)", "partial_evidence_count": null, "pfam_id": "PF20320", "proteins": 271, "proteomes": 263, "short_name": "DUF6615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20320", "structures": 0, "taxa": 664, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 280 amino acids in length. There is a conserved PRW sequence motif.", "domain_architectures": 22, "interpro_id": "IPR025115", "known_evidence_count": null, "matches": 272, "name": "Domain of unknown function (DUF4034)", "partial_evidence_count": null, "pfam_id": "PF13226", "proteins": 270, "proteomes": 253, "short_name": "DUF4034", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13226", "structures": 0, "taxa": 510, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 347 and 622 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045723", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF6077)", "partial_evidence_count": null, "pfam_id": "PF19554", "proteins": 270, "proteomes": 249, "short_name": "DUF6077", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19554", "structures": 0, "taxa": 477, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are approximately 130 amino acids in length. They contain an N-terminal zinc binding domain.", "domain_architectures": 2, "interpro_id": "IPR046243", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF6276)", "partial_evidence_count": null, "pfam_id": "PF19792", "proteins": 270, "proteomes": 270, "short_name": "DUF6276", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19792", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from halobacteria. Members are predicted to adopt an alpha-beta configuration.", "domain_architectures": 2, "interpro_id": "IPR055515", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF7089)", "partial_evidence_count": null, "pfam_id": "PF23363", "proteins": 270, "proteomes": 269, "short_name": "DUF7089", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23363", "structures": 0, "taxa": 415, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. They show several highly conserved motifs PVPV, LGL/MDP, AxWA, and PV/IHLEVC. Many members are annotated as nucleotidyltransferases.", "domain_architectures": 1, "interpro_id": "IPR055521", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF7095)", "partial_evidence_count": null, "pfam_id": "PF23378", "proteins": 270, "proteomes": 270, "short_name": "DUF7095", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23378", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family represents a family of uncharacterised proteins from T even phage.", "domain_architectures": 1, "interpro_id": "IPR055703", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF7279)", "partial_evidence_count": null, "pfam_id": "PF23945", "proteins": 270, "proteomes": 199, "short_name": "DUF7279", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23945", "structures": 0, "taxa": 488, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to fold into a single helix.", "domain_architectures": 1, "interpro_id": "IPR055736", "known_evidence_count": null, "matches": 270, "name": "Domain of unknown function (DUF7312)", "partial_evidence_count": null, "pfam_id": "PF23994", "proteins": 270, "proteomes": 270, "short_name": "DUF7312", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23994", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal sequences containing a presumed HTH domain.", "domain_architectures": 1, "interpro_id": "IPR055770", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF7346)", "partial_evidence_count": null, "pfam_id": "PF24037", "proteins": 270, "proteomes": 269, "short_name": "DUF7346", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24037", "structures": 0, "taxa": 417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 258, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-helical structure.", "domain_architectures": 2, "interpro_id": "IPR055898", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF7475)", "partial_evidence_count": null, "pfam_id": "PF24287", "proteins": 270, "proteomes": 190, "short_name": "DUF7475", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24287", "structures": 0, "taxa": 333, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a presumed domain found towards the N-terminal of a group of uncharacterised sequences from C. elegans and related proteins from nematodes. This domain may consist of spectrin repeats.", "domain_architectures": 124, "interpro_id": "IPR056701", "known_evidence_count": null, "matches": 270, "name": "Domain of unknown function (DUF7799)", "partial_evidence_count": null, "pfam_id": "PF25075", "proteins": 270, "proteomes": 162, "short_name": "DUF7799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25075", "structures": 0, "taxa": 568, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised protein from Halogeometricum borinquense (Hbor_38910) and related archaeal proteins. This protein is found next to a toxic gene Hbor_38900 and is likely a immunity protein which is able to prevent self-intoxication [[cite:PUB00160456]]. This protein is predicted to adopt a complex alpha/beta structure with an unique topology.", "domain_architectures": 4, "interpro_id": "IPR058264", "known_evidence_count": null, "matches": 336, "name": "Family of unknown function (DUF7958)", "partial_evidence_count": null, "pfam_id": "PF25858", "proteins": 270, "proteomes": 39, "short_name": "DUF7958", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25858", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 239, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The domain is found in proteins from various archaeal species, including members of the Haloferacaceae, Haloarculaceae, and Natrialbaceae families. The proteins containing this domain are typically found in halophilic archaea, which are adapted to high-salt environments. The proteins are most conserved towards their C-terminus where they contain the motif RHFYPL which may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR058474", "known_evidence_count": null, "matches": 272, "name": "Domain of unknown function (DUF8160)", "partial_evidence_count": null, "pfam_id": "PF26492", "proteins": 270, "proteomes": 161, "short_name": "DUF8160", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26492", "structures": 0, "taxa": 288, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in Arabidopsis thaliana proteins, which are specifically expressed during meiosis [[cite:PUB00097819]]. Many of these members contain a repeated region.", "domain_architectures": 13, "interpro_id": "IPR007598", "known_evidence_count": null, "matches": 463, "name": "Repeat of unknown function (DUF577)", "partial_evidence_count": null, "pfam_id": "PF04510", "proteins": 269, "proteomes": 28, "short_name": "DUF577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04510", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of proteins from the archaeon Sulfolobus, with undetermined function. According to structure prediction this protein has a thioredoxin fold.", "domain_architectures": 5, "interpro_id": "IPR009272", "known_evidence_count": null, "matches": 280, "name": "Domain of unknown function (DUF929)", "partial_evidence_count": null, "pfam_id": "PF06053", "proteins": 269, "proteomes": 161, "short_name": "DUF929", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06053", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 171, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several enterobacterial YbdJ proteins. The function of this family is unknown", "domain_architectures": 1, "interpro_id": "IPR010590", "known_evidence_count": null, "matches": 269, "name": "Protein of unknown function (DUF1158)", "partial_evidence_count": null, "pfam_id": "PF06643", "proteins": 269, "proteomes": 264, "short_name": "DUF1158", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06643", "structures": 0, "taxa": 367, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 242, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Members of this family are found in mammalian T-cell antigen receptor, and adopt an immunoglobulin-like beta-sandwich fold, with seven strands in two beta-sheets in a Greek-key topology. Their exact function has not, as yet, been determined.", "domain_architectures": 8, "interpro_id": "IPR015370", "known_evidence_count": null, "matches": 269, "name": "Domain of unknown function (DUF1968)", "partial_evidence_count": null, "pfam_id": "PF09291", "proteins": 269, "proteomes": 125, "short_name": "DUF1968", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09291", "structures": 661, "taxa": 493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 240, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in species of Drosophila, and is approximately 90 amino acids in length. The family is found in association with [pfam:PF07707].", "domain_architectures": 10, "interpro_id": "IPR031750", "known_evidence_count": null, "matches": 269, "name": "Domain of unknown function (DUF4734)", "partial_evidence_count": null, "pfam_id": "PF15881", "proteins": 269, "proteomes": 36, "short_name": "DUF4734", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15881", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 137 and 161 amino acids in length. There are two conserved sequence motifs: NLRI and HVTVDD.", "domain_architectures": 3, "interpro_id": "IPR046133", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF6130)", "partial_evidence_count": null, "pfam_id": "PF19625", "proteins": 269, "proteomes": 253, "short_name": "DUF6130", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19625", "structures": 0, "taxa": 483, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of proteins from halobacteria. It shows several conserved motifs DCPH, RGCL and RPLL/VEEHHLSxY. Members are predicted to show an alpha-beta configuration.", "domain_architectures": 2, "interpro_id": "IPR055523", "known_evidence_count": null, "matches": 278, "name": "Family of unknown function (DUF7097)", "partial_evidence_count": null, "pfam_id": "PF23382", "proteins": 269, "proteomes": 269, "short_name": "DUF7097", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23382", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved R, D W and Y residues. Members are predicted to show a mainly beta configuration.", "domain_architectures": 1, "interpro_id": "IPR055536", "known_evidence_count": null, "matches": 269, "name": "Family of unknown function (DUF7112)", "partial_evidence_count": null, "pfam_id": "PF23424", "proteins": 269, "proteomes": 267, "short_name": "DUF7112", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23424", "structures": 0, "taxa": 413, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a group of uncharacterised sequences from archaea which are related to VapC (virulence-associated protein C) family of proteins. Members of this entry may adopt a PIN-like fold.", "domain_architectures": 2, "interpro_id": "IPR055808", "known_evidence_count": null, "matches": 269, "name": "Family of unknown function (DUF7384)", "partial_evidence_count": null, "pfam_id": "PF24109", "proteins": 269, "proteomes": 268, "short_name": "DUF7384", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24109", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These small proteins are composed of two transmembrane alpha helices.", "domain_architectures": 1, "interpro_id": "IPR058287", "known_evidence_count": null, "matches": 269, "name": "Domain of unknown function (DUF7981)", "partial_evidence_count": null, "pfam_id": "PF25938", "proteins": 269, "proteomes": 269, "short_name": "DUF7981", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25938", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 175, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this functionally uncharacterised family are found in prokaryotic penicillin-binding protein 4.", "domain_architectures": 3, "interpro_id": "IPR015294", "known_evidence_count": null, "matches": 268, "name": "Domain of unknown function (DUF1958)", "partial_evidence_count": null, "pfam_id": "PF09211", "proteins": 268, "proteomes": 192, "short_name": "DUF1958", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09211", "structures": 16, "taxa": 261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein of approx.120 residues consists of three beta strands and five alpha helices, thought to fold into a homo-dimer. It is expressed in bacteria.", "domain_architectures": 1, "interpro_id": "IPR018594", "known_evidence_count": null, "matches": 268, "name": "Protein of unknown function (DUF2023)", "partial_evidence_count": null, "pfam_id": "PF09633", "proteins": 268, "proteomes": 266, "short_name": "DUF2023", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09633", "structures": 1, "taxa": 554, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 140 and 280 amino acids in length. There is a conserved RCGW sequence motif.", "domain_architectures": 2, "interpro_id": "IPR025145", "known_evidence_count": null, "matches": 268, "name": "Protein of unknown function (DUF4087)", "partial_evidence_count": null, "pfam_id": "PF13316", "proteins": 268, "proteomes": 256, "short_name": "DUF4087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13316", "structures": 0, "taxa": 473, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR033435", "known_evidence_count": null, "matches": 268, "name": "Domain of unknown function (DUF5129)", "partial_evidence_count": null, "pfam_id": "PF17173", "proteins": 268, "proteomes": 241, "short_name": "DUF5129", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17173", "structures": 0, "taxa": 325, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of putative zinc dependent peptidases that have the characteristic HEXXH motif. This family is most related to [pfam:PF10026].", "domain_architectures": 3, "interpro_id": "IPR043754", "known_evidence_count": null, "matches": 268, "name": "Putative zinc dependent peptidase (DUF5700)", "partial_evidence_count": null, "pfam_id": "PF18958", "proteins": 268, "proteomes": 245, "short_name": "DUF5700", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18958", "structures": 0, "taxa": 571, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of unknown function predominantly found in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR043931", "known_evidence_count": null, "matches": 268, "name": "Family of unknown function (DUF5779)", "partial_evidence_count": null, "pfam_id": "PF19091", "proteins": 268, "proteomes": 268, "short_name": "DUF5779", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19091", "structures": 0, "taxa": 420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000713) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from from the ribostamycin biosynthetic gene cluster from Streptomyces ribosidificus [[cite:PUB00098919]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR045683", "known_evidence_count": null, "matches": 277, "name": "Family of unknown function (DUF6192)", "partial_evidence_count": null, "pfam_id": "PF19691", "proteins": 268, "proteomes": 212, "short_name": "DUF6192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19691", "structures": 0, "taxa": 278, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 257, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. Members are predicted to show an alpha-beta configuration.", "domain_architectures": 1, "interpro_id": "IPR055534", "known_evidence_count": null, "matches": 268, "name": "Family of unknown function (DUF7110)", "partial_evidence_count": null, "pfam_id": "PF23422", "proteins": 268, "proteomes": 268, "short_name": "DUF7110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23422", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 256, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble treble-clef zinc fingers.", "domain_architectures": 2, "interpro_id": "IPR055983", "known_evidence_count": null, "matches": 269, "name": "Family of unknown function (DUF7561)", "partial_evidence_count": null, "pfam_id": "PF24442", "proteins": 268, "proteomes": 268, "short_name": "DUF7561", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24442", "structures": 0, "taxa": 416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised bacterial proteins found in bacteria. They are predicted to adopt a globular alpha/beta structure that has some similarity to MurD C-terminal domain.", "domain_architectures": 2, "interpro_id": "IPR056101", "known_evidence_count": null, "matches": 269, "name": "Domain of unknown function (DUF7684)", "partial_evidence_count": null, "pfam_id": "PF24733", "proteins": 268, "proteomes": 260, "short_name": "DUF7684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24733", "structures": 0, "taxa": 593, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 241, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family catalyses the synthesis of thymidine monophosphate (dTMP) from deoxyuridine monophosphate (dUMP). The physiological co-substrate has not yet been identified. Previous designation of this family as being thymidylate synthase from one paper, [cite:PUB00075419], has been shown to be erroneous [[cite:PUB00057368]]. The proteins are uncharacterised.", "domain_architectures": 6, "interpro_id": "IPR003745", "known_evidence_count": null, "matches": 268, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF02593", "proteins": 267, "proteomes": 149, "short_name": "DUF166", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02593", "structures": 0, "taxa": 354, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 265, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several uncharacterised proteins from Caenorhabditis elegans. The GO annotation suggests that the protein is involved in nematode larval development and has a positive regulation on growth rate.", "domain_architectures": 9, "interpro_id": "IPR007767", "known_evidence_count": null, "matches": 301, "name": "Protein of unknown function (DUF684)", "partial_evidence_count": null, "pfam_id": "PF05075", "proteins": 267, "proteomes": 20, "short_name": "DUF684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05075", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR016630", "known_evidence_count": null, "matches": 267, "name": "Uncharacterized protein conserved in bacteria (DUF2247)", "partial_evidence_count": null, "pfam_id": "PF10004", "proteins": 267, "proteomes": 245, "short_name": "DUF2247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10004", "structures": 0, "taxa": 582, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of unknown function can be found in Cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR020346", "known_evidence_count": null, "matches": 270, "name": "Family of unknown function (DUF5331)", "partial_evidence_count": null, "pfam_id": "PF17265", "proteins": 267, "proteomes": 177, "short_name": "DUF5331", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17265", "structures": 0, "taxa": 489, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in Firmicutes.", "domain_architectures": 2, "interpro_id": "IPR043779", "known_evidence_count": null, "matches": 271, "name": "Family of unknown function (DUF5721)", "partial_evidence_count": null, "pfam_id": "PF18988", "proteins": 267, "proteomes": 265, "short_name": "DUF5721", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18988", "structures": 0, "taxa": 430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 138, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 3, "interpro_id": "IPR043869", "known_evidence_count": null, "matches": 267, "name": "Family of unknown function (DUF5829)", "partial_evidence_count": null, "pfam_id": "PF19147", "proteins": 267, "proteomes": 253, "short_name": "DUF5829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19147", "structures": 0, "taxa": 451, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001922) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the isoindolinomycin biosynthetic gene cluster from Streptomyces sp. SoC090715LN-16 and appears to be predominantly found in Actinobacteria [[cite:PUB00098935]].", "domain_architectures": 1, "interpro_id": "IPR045701", "known_evidence_count": null, "matches": 267, "name": "Family of unknown function (DUF6059)", "partial_evidence_count": null, "pfam_id": "PF19534", "proteins": 267, "proteomes": 240, "short_name": "DUF6059", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19534", "structures": 0, "taxa": 298, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are typically between 39 and 59 amino acids in length. This family contains a highly conserved sequence HGKV/IKS/T.", "domain_architectures": 1, "interpro_id": "IPR046221", "known_evidence_count": null, "matches": 267, "name": "Family of unknown function (DUF6254)", "partial_evidence_count": null, "pfam_id": "PF19767", "proteins": 267, "proteomes": 265, "short_name": "DUF6254", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19767", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 259, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has a conserved motif VCRRH/YAE and conserved R, Y and W residues. Members are predicted to show an alpha-beta configuration.", "domain_architectures": 1, "interpro_id": "IPR055517", "known_evidence_count": null, "matches": 267, "name": "Family of unknown function (DUF7091)", "partial_evidence_count": null, "pfam_id": "PF23367", "proteins": 267, "proteomes": 267, "short_name": "DUF7091", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23367", "structures": 0, "taxa": 416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the second domain found in DUF6079 family proteins. DUF6079 proteins are likely to be BREX (bacteriophage exclusion) system proteins.", "domain_architectures": 13, "interpro_id": "IPR058569", "known_evidence_count": null, "matches": 267, "name": "DUF6079 second domain", "partial_evidence_count": null, "pfam_id": "PF26383", "proteins": 267, "proteomes": 256, "short_name": "DUF6079_2nd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26383", "structures": 0, "taxa": 799, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of Rhodopirellula baltica hypothetical proteins of about 500 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR011487", "known_evidence_count": null, "matches": 266, "name": "Protein of unknown function (DUF1598)", "partial_evidence_count": null, "pfam_id": "PF07643", "proteins": 266, "proteomes": 105, "short_name": "DUF1598", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07643", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR024493", "known_evidence_count": null, "matches": 266, "name": "Protein of unknown function (DUF2767)", "partial_evidence_count": null, "pfam_id": "PF10965", "proteins": 266, "proteomes": 225, "short_name": "DUF2767", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10965", "structures": 0, "taxa": 344, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 46 and 64 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR022235", "known_evidence_count": null, "matches": 274, "name": "Protein of unknown function (DUF3760)", "partial_evidence_count": null, "pfam_id": "PF12586", "proteins": 266, "proteomes": 25, "short_name": "DUF3760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12586", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 150 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025071", "known_evidence_count": null, "matches": 266, "name": "Protein of unknown function (DUF3939)", "partial_evidence_count": null, "pfam_id": "PF13075", "proteins": 266, "proteomes": 263, "short_name": "DUF3939", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13075", "structures": 0, "taxa": 326, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in bacteria.", "domain_architectures": 4, "interpro_id": "IPR040549", "known_evidence_count": null, "matches": 266, "name": "Domain of unknown function (DUF5613)", "partial_evidence_count": null, "pfam_id": "PF18467", "proteins": 266, "proteomes": 262, "short_name": "DUF5613", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18467", "structures": 1, "taxa": 363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 111, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000709) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the neomycin biosynthetic gene cluster from Streptomyces fradiae ATCC 10745 = DSM 40063 [[cite:PUB00098957]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046201", "known_evidence_count": null, "matches": 266, "name": "Family of unknown function (DUF6234)", "partial_evidence_count": null, "pfam_id": "PF19747", "proteins": 266, "proteomes": 238, "short_name": "DUF6234", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19747", "structures": 0, "taxa": 318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised sequences from archaea. It may adopt an amidotransferase-like fold.", "domain_architectures": 10, "interpro_id": "IPR055831", "known_evidence_count": null, "matches": 266, "name": "Domain of unknown function (DUF7408)", "partial_evidence_count": null, "pfam_id": "PF24157", "proteins": 266, "proteomes": 255, "short_name": "DUF7408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24157", "structures": 0, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR005915", "known_evidence_count": null, "matches": 265, "name": "Protein of unknown function (DUF443)", "partial_evidence_count": null, "pfam_id": "PF04276", "proteins": 265, "proteomes": 93, "short_name": "DUF443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04276", "structures": 0, "taxa": 162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This short domain is usually associated with [pfam:PF08861].", "domain_architectures": 2, "interpro_id": "IPR014961", "known_evidence_count": null, "matches": 265, "name": "Domain of unknown function DUF1829", "partial_evidence_count": null, "pfam_id": "PF08862", "proteins": 265, "proteomes": 257, "short_name": "DUF1829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08862", "structures": 0, "taxa": 692, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function. The family includes HI_0931 from Haemophilus influenzae ([swissprot:P44078]). Structure prediction shows this protein is composed of a single all beta sandwich domain.", "domain_architectures": 1, "interpro_id": "IPR014449", "known_evidence_count": null, "matches": 265, "name": "Uncharacterized protein conserved in bacteria (DUF2251)", "partial_evidence_count": null, "pfam_id": "PF10008", "proteins": 265, "proteomes": 264, "short_name": "DUF2251", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10008", "structures": 0, "taxa": 519, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 362 and 1493 amino acids in length.", "domain_architectures": 15, "interpro_id": "IPR032057", "known_evidence_count": null, "matches": 270, "name": "Domain of unknown function (DUF4799)", "partial_evidence_count": null, "pfam_id": "PF16056", "proteins": 265, "proteomes": 107, "short_name": "DUF4799", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16056", "structures": 0, "taxa": 409, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial family of unknown function.", "domain_architectures": 1, "interpro_id": "IPR054253", "known_evidence_count": null, "matches": 265, "name": "Domain of unknown function (DUF6984)", "partial_evidence_count": null, "pfam_id": "PF22480", "proteins": 265, "proteomes": 248, "short_name": "DUF6984", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22480", "structures": 0, "taxa": 519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins. These proteins probably do not adopt a globular structure.", "domain_architectures": 1, "interpro_id": "IPR055969", "known_evidence_count": null, "matches": 265, "name": "Family of unknown function (DUF7547)", "partial_evidence_count": null, "pfam_id": "PF24414", "proteins": 265, "proteomes": 265, "short_name": "DUF7547", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24414", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 246, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins in archaea. The proteins containing this domain are predominantly found in the class Halobacteria, which are known for their adaptation to high-salt environments. The proteins in this family are typically around 100 to 300 amino acids in length. Many of these proteins are predicted to be integral membrane proteins, as suggested by the presence of multiple transmembrane helices. The family contains a C-terminal zinc ribbon domain.", "domain_architectures": 10, "interpro_id": "IPR058421", "known_evidence_count": null, "matches": 265, "name": "Family of unknown function (DUF8108)", "partial_evidence_count": null, "pfam_id": "PF26413", "proteins": 265, "proteomes": 170, "short_name": "DUF8108", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26413", "structures": 0, "taxa": 283, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminus of a family of proteins that are functionally uncharacterised. The presumed domain is about 60 amino acid residues in length and is found independently in some proteins.", "domain_architectures": 3, "interpro_id": "IPR014994", "known_evidence_count": null, "matches": 268, "name": "Domain of unknown function (DUF1843)", "partial_evidence_count": null, "pfam_id": "PF08898", "proteins": 264, "proteomes": 105, "short_name": "DUF1843", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08898", "structures": 3, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 175, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Eubacterium rectale gene EUBREC_3695. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14737), it appears to be upregulated in the presence of Bacteroides thetaiotaomicron vs when isolated in culture [[cite:PUB00056060]].", "domain_architectures": 4, "interpro_id": "IPR024541", "known_evidence_count": null, "matches": 266, "name": "Domain of unknown function, E. rectale Gene description (DUF3881)", "partial_evidence_count": null, "pfam_id": "PF12997", "proteins": 264, "proteomes": 261, "short_name": "DUF3881", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12997", "structures": 0, "taxa": 479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised plant sequences. It is predicted to have an all-alpha configuration. It has a highly conserved PxGDW motif.", "domain_architectures": 29, "interpro_id": "IPR058331", "known_evidence_count": null, "matches": 264, "name": "Domain of unknown function (DUF8018)", "partial_evidence_count": null, "pfam_id": "PF26057", "proteins": 264, "proteomes": 108, "short_name": "DUF8018", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26057", "structures": 1, "taxa": 368, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 254, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058337", "known_evidence_count": null, "matches": 264, "name": "Family of unknown function (DUF8024)", "partial_evidence_count": null, "pfam_id": "PF26067", "proteins": 264, "proteomes": 262, "short_name": "DUF8024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26067", "structures": 0, "taxa": 411, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised metazoan sequences. It is predicted to fold into array of alpha-helices.", "domain_architectures": 10, "interpro_id": "IPR061812", "known_evidence_count": null, "matches": 267, "name": "Domain of unknown function (DUF8751)", "partial_evidence_count": null, "pfam_id": "PF30851", "proteins": 264, "proteomes": 24, "short_name": "DUF8751", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30851", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 30 amino acids in length. There is a conserved YSK sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025077", "known_evidence_count": null, "matches": 263, "name": "Domain of unknown function (DUF3941)", "partial_evidence_count": null, "pfam_id": "PF13081", "proteins": 263, "proteomes": 263, "short_name": "DUF3941", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13081", "structures": 0, "taxa": 337, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function which is found in Bacteria and Archaea.", "domain_architectures": 3, "interpro_id": "IPR035235", "known_evidence_count": null, "matches": 263, "name": "Family of unknown function (DUF5343)", "partial_evidence_count": null, "pfam_id": "PF17278", "proteins": 263, "proteomes": 259, "short_name": "DUF5343", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17278", "structures": 0, "taxa": 710, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are typically between 178 and 220 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046622", "known_evidence_count": null, "matches": 322, "name": "Family of unknown function (DUF6735)", "partial_evidence_count": null, "pfam_id": "PF20509", "proteins": 263, "proteomes": 183, "short_name": "DUF6735", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20509", "structures": 0, "taxa": 310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Cyanobacteria. Some members are annotated as membrane proteins however this cannot be confirmed.", "domain_architectures": 3, "interpro_id": "IPR021499", "known_evidence_count": null, "matches": 263, "name": "Protein of unknown function (DUF3153)", "partial_evidence_count": null, "pfam_id": "PF11353", "proteins": 262, "proteomes": 260, "short_name": "DUF3153", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11353", "structures": 0, "taxa": 682, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 217, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between and 417 amino acids in length. The human member of this family is C1orf141.", "domain_architectures": 4, "interpro_id": "IPR027847", "known_evidence_count": null, "matches": 300, "name": "Domain of unknown function (DUF4545)", "partial_evidence_count": null, "pfam_id": "PF15078", "proteins": 262, "proteomes": 149, "short_name": "DUF4545", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15078", "structures": 0, "taxa": 508, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 240 and 272 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR029171", "known_evidence_count": null, "matches": 273, "name": "Domain of unknown function (DUF4638)", "partial_evidence_count": null, "pfam_id": "PF15472", "proteins": 262, "proteomes": 203, "short_name": "DUF4638", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15472", "structures": 0, "taxa": 758, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 163, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 392 and 442 amino acids in length. This entry represents the N-terminal jelly roll domain.", "domain_architectures": 4, "interpro_id": "IPR031979", "known_evidence_count": null, "matches": 263, "name": "Domain of unknown function (DUF4785) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF16024", "proteins": 262, "proteomes": 262, "short_name": "DUF4785_1st", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16024", "structures": 1, "taxa": 405, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 163, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is the N-terminal domain found in sequences of unknown function in bacteria.", "domain_architectures": 5, "interpro_id": "IPR043775", "known_evidence_count": null, "matches": 281, "name": "Family of unknown function (DUF5717)N-terminal", "partial_evidence_count": null, "pfam_id": "PF18984", "proteins": 262, "proteomes": 260, "short_name": "DUF5717_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18984", "structures": 0, "taxa": 427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function found in viruses, which are thought to be membrane proteins.", "domain_architectures": 7, "interpro_id": "IPR043912", "known_evidence_count": null, "matches": 264, "name": "Family of unknown function (DUF5765)", "partial_evidence_count": null, "pfam_id": "PF19069", "proteins": 262, "proteomes": 167, "short_name": "DUF5765", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19069", "structures": 0, "taxa": 433, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 155, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed integral membrane domain is functionally uncharacterised. This domain family is found mainly in cyanobacteria, and is approximately 190 amino acids in length. The family is found to the C-terminus of [pfam:PF00082].", "domain_architectures": 3, "interpro_id": "IPR045986", "known_evidence_count": null, "matches": 262, "name": "Domain of unknown function (DUF5942)", "partial_evidence_count": null, "pfam_id": "PF19366", "proteins": 262, "proteomes": 256, "short_name": "DUF5942", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19366", "structures": 0, "taxa": 667, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 228, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised metazoan proteins. It is predicted to fold into an alpha/beta structure with two pairs of conserved cysteine residues. These residues are predicted to form disulfide bonds.", "domain_architectures": 4, "interpro_id": "IPR059459", "known_evidence_count": null, "matches": 266, "name": "Domain of unknown function (DUF8415)", "partial_evidence_count": null, "pfam_id": "PF28478", "proteins": 262, "proteomes": 51, "short_name": "DUF8415", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28478", "structures": 0, "taxa": 254, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This archaebacterial protein family has no known function. The proteins are predicted to contain two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR002849", "known_evidence_count": null, "matches": 261, "name": "Protein of unknown function DUF131", "partial_evidence_count": null, "pfam_id": "PF01998", "proteins": 261, "proteomes": 193, "short_name": "DUF131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01998", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 225, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family was annotated as mitochondrial Ribosomal protein MRP8, based on the presumed similarity of the S.cerevisiae protein to an E.coli mitochondrial ribosomal protein; however, this similarity is spurious, and the function is not known [Wood, V].", "domain_architectures": 9, "interpro_id": "IPR012917", "known_evidence_count": null, "matches": 264, "name": "Protein of unknown function (DUF3294)", "partial_evidence_count": null, "pfam_id": "PF07957", "proteins": 261, "proteomes": 206, "short_name": "DUF3294", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07957", "structures": 0, "taxa": 535, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 171, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR020262", "known_evidence_count": null, "matches": 261, "name": "Protein of unknown function (DUF2766)", "partial_evidence_count": null, "pfam_id": "PF10964", "proteins": 261, "proteomes": 261, "short_name": "DUF2766", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10964", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently there is no known function.", "domain_architectures": 1, "interpro_id": "IPR021515", "known_evidence_count": null, "matches": 261, "name": "Protein of unknown function (DUF3177)", "partial_evidence_count": null, "pfam_id": "PF11375", "proteins": 261, "proteomes": 256, "short_name": "DUF3177", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11375", "structures": 0, "taxa": 739, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length. There are two completely conserved residues (G and R) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025029", "known_evidence_count": null, "matches": 261, "name": "Protein of unknown function (DUF3918)", "partial_evidence_count": null, "pfam_id": "PF13056", "proteins": 261, "proteomes": 261, "short_name": "DUF3918", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13056", "structures": 0, "taxa": 348, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 188 and 325 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046507", "known_evidence_count": null, "matches": 261, "name": "Family of unknown function (DUF6685)", "partial_evidence_count": null, "pfam_id": "PF20390", "proteins": 261, "proteomes": 240, "short_name": "DUF6685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20390", "structures": 0, "taxa": 446, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 252, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of proteins from halobacteria. It has several conserved motifs LGY, AERK/EWK/R, RCFV and YxWA. Members are predicted to show an alpha-beta configuration.", "domain_architectures": 1, "interpro_id": "IPR055540", "known_evidence_count": null, "matches": 261, "name": "Family of unknown function (DUF7116)", "partial_evidence_count": null, "pfam_id": "PF23429", "proteins": 261, "proteomes": 261, "short_name": "DUF7116", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23429", "structures": 0, "taxa": 407, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a metalloprotease-like domain found in ABC transporter permease from bacteria, predominantly Streptomyces spp. The function of this domain is unknown.", "domain_architectures": 1, "interpro_id": "IPR055648", "known_evidence_count": null, "matches": 261, "name": "Domain of unknown function (DUF7224)", "partial_evidence_count": null, "pfam_id": "PF23866", "proteins": 261, "proteomes": 232, "short_name": "DUF7224", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23866", "structures": 0, "taxa": 367, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from proteobacteria.", "domain_architectures": 5, "interpro_id": "IPR061605", "known_evidence_count": null, "matches": 261, "name": "Domain of unknown function (DUF8535)", "partial_evidence_count": null, "pfam_id": "PF29382", "proteins": 261, "proteomes": 223, "short_name": "DUF8535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29382", "structures": 0, "taxa": 374, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 254, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 2, "interpro_id": "IPR005489", "known_evidence_count": null, "matches": 261, "name": "Pyrococcus protein of unknown function, DUF257", "partial_evidence_count": null, "pfam_id": "PF03192", "proteins": 260, "proteomes": 35, "short_name": "DUF257", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03192", "structures": 1, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a C-terminal domain found in bacterial sequences of unknown function.", "domain_architectures": 3, "interpro_id": "IPR043770", "known_evidence_count": null, "matches": 261, "name": "Family of unknown function (DUF5716) C-terminal", "partial_evidence_count": null, "pfam_id": "PF18980", "proteins": 260, "proteomes": 259, "short_name": "DUF5716_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18980", "structures": 0, "taxa": 417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 273 and 325 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046575", "known_evidence_count": null, "matches": 389, "name": "Family of unknown function (DUF6635)", "partial_evidence_count": null, "pfam_id": "PF20340", "proteins": 260, "proteomes": 248, "short_name": "DUF6635", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20340", "structures": 0, "taxa": 437, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 292 and 316 amino acids in length. An AlphaFold prediction show similarity to the concanavalin superfamily suggesting that this family may be involved in carbohydrate binding.", "domain_architectures": 1, "interpro_id": "IPR046663", "known_evidence_count": null, "matches": 260, "name": "Domain of unknown function (DUF6772)", "partial_evidence_count": null, "pfam_id": "PF20562", "proteins": 260, "proteomes": 229, "short_name": "DUF6772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20562", "structures": 0, "taxa": 430, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein domain that is sometimes found associated with [pfam:PF01469]. The family also includes an N-terminal domain found in the Pseudomonas syringae InaZ ice nucleation protein.", "domain_architectures": 6, "interpro_id": "IPR056083", "known_evidence_count": null, "matches": 260, "name": "Domain of unknown function (DUF7666)", "partial_evidence_count": null, "pfam_id": "PF24703", "proteins": 260, "proteomes": 235, "short_name": "DUF7666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24703", "structures": 0, "taxa": 666, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 183, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the third domain found in DUF6079 family proteins. DUF6079 proteins are likely to be BREX (bacteriophage exclusion) system proteins.", "domain_architectures": 13, "interpro_id": "IPR058571", "known_evidence_count": null, "matches": 264, "name": "DUF6079 third domain", "partial_evidence_count": null, "pfam_id": "PF26384", "proteins": 260, "proteomes": 251, "short_name": "DUF6079_3rd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26384", "structures": 0, "taxa": 777, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 236, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the central domain found in a family of uncharacterised proteins from archaea. The proteins are predominantly found in the Halobacteria class, which includes members of the Haloferacaceae, Haloarculaceae, and Natrialbaceae families. The proteins in this family are typically around 550-580 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR058910", "known_evidence_count": null, "matches": 260, "name": "Domain of unknown function (DUF8186) central domain", "partial_evidence_count": null, "pfam_id": "PF26590", "proteins": 260, "proteomes": 156, "short_name": "DUF8186_M", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26590", "structures": 0, "taxa": 259, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 170 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025537", "known_evidence_count": null, "matches": 260, "name": "Domain of unknown function (DUF4423)", "partial_evidence_count": null, "pfam_id": "PF14394", "proteins": 259, "proteomes": 32, "short_name": "DUF4423", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14394", "structures": 0, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 175, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 160 residues in length and is mainly found in various Eubacterium and Clostridium species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032340", "known_evidence_count": null, "matches": 259, "name": "Domain of unknown function (DUF4860)", "partial_evidence_count": null, "pfam_id": "PF16152", "proteins": 259, "proteomes": 258, "short_name": "DUF4860", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16152", "structures": 0, "taxa": 475, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 850 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 26, "interpro_id": "IPR032532", "known_evidence_count": null, "matches": 261, "name": "Domain of unknown function (DUF4955)", "partial_evidence_count": null, "pfam_id": "PF16315", "proteins": 259, "proteomes": 193, "short_name": "DUF4955", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16315", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Proteobacteria and predicted to contain 2 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035308", "known_evidence_count": null, "matches": 259, "name": "Family of unknown function (DUF5368)", "partial_evidence_count": null, "pfam_id": "PF17336", "proteins": 259, "proteomes": 255, "short_name": "DUF5368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17336", "structures": 0, "taxa": 491, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mammalia.", "domain_architectures": 2, "interpro_id": "IPR040721", "known_evidence_count": null, "matches": 267, "name": "Family of unknown function (DUF5520)", "partial_evidence_count": null, "pfam_id": "PF17658", "proteins": 259, "proteomes": 146, "short_name": "DUF5520", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17658", "structures": 0, "taxa": 462, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045940", "known_evidence_count": null, "matches": 259, "name": "Family of unknown function (DUF6360)", "partial_evidence_count": null, "pfam_id": "PF19887", "proteins": 259, "proteomes": 237, "short_name": "DUF6360", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19887", "structures": 0, "taxa": 376, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 135 and 210 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR046499", "known_evidence_count": null, "matches": 272, "name": "Family of unknown function (DUF6677)", "partial_evidence_count": null, "pfam_id": "PF20382", "proteins": 259, "proteomes": 256, "short_name": "DUF6677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20382", "structures": 0, "taxa": 527, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a beta barrel domain which is found associated with [pfam:PF10020].", "domain_architectures": 3, "interpro_id": "IPR054286", "known_evidence_count": null, "matches": 259, "name": "Domain of unknown function (DUF7021)", "partial_evidence_count": null, "pfam_id": "PF22886", "proteins": 259, "proteomes": 210, "short_name": "DUF7021", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22886", "structures": 0, "taxa": 465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 242, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Halobacteria. It is frequently found in combination with [pfam:PF24420].", "domain_architectures": 2, "interpro_id": "IPR055974", "known_evidence_count": null, "matches": 259, "name": "Domain of unknown function (DUF7552)", "partial_evidence_count": null, "pfam_id": "PF24422", "proteins": 259, "proteomes": 200, "short_name": "DUF7552", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24422", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 245, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are about 160 amino acids in length and have an alpha helical domain fold. Shows structural similarity to the YutG/PgpA superfamily, which includes Phosphatidylglycerophosphatase. Thus this family may represent a similar enzyme.", "domain_architectures": 2, "interpro_id": "IPR058290", "known_evidence_count": null, "matches": 262, "name": "Domain of unknown function (DUF7984)", "partial_evidence_count": null, "pfam_id": "PF25945", "proteins": 259, "proteomes": 259, "short_name": "DUF7984", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25945", "structures": 0, "taxa": 408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 246, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. The proteins in this family adopt a six stranded barrel like topology with several inserted alpha helices. The barrel shows incomplete hydrogen bonding between strands.", "domain_architectures": 1, "interpro_id": "IPR058322", "known_evidence_count": null, "matches": 259, "name": "Domain of unknown function (DUF8009)", "partial_evidence_count": null, "pfam_id": "PF26033", "proteins": 259, "proteomes": 240, "short_name": "DUF8009", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26033", "structures": 0, "taxa": 379, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the fourth domain found in DUF6079 family proteins. DUF6079 proteins are likely to be BREX (bacteriophage exclusion) system proteins.", "domain_architectures": 13, "interpro_id": "IPR058572", "known_evidence_count": null, "matches": 260, "name": "Family of unknown function (DUF6079) 4th domain", "partial_evidence_count": null, "pfam_id": "PF26385", "proteins": 259, "proteomes": 252, "short_name": "DUF6079_4th", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26385", "structures": 0, "taxa": 788, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 246, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins in this family are predominantly found in Halobacteria, including members of the Haloferacaceae, Natrialbaceae, and Haloarculaceae families. The domain is approximately 70-90 amino acids in length. Proteins in this family contain two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058464", "known_evidence_count": null, "matches": 259, "name": "Domain of unknown function (DUF8151)", "partial_evidence_count": null, "pfam_id": "PF26478", "proteins": 259, "proteomes": 252, "short_name": "DUF8151", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26478", "structures": 0, "taxa": 394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found ata the C-terminal of a group of uncharacterised sequences from bacteria, which is associated with [pfam:PF18980] at the N-terminal. This domain may adopt a beta-sandwich fold.", "domain_architectures": 2, "interpro_id": "IPR061622", "known_evidence_count": null, "matches": 259, "name": "Domain of unknown function (DUF8552)", "partial_evidence_count": null, "pfam_id": "PF29432", "proteins": 259, "proteomes": 258, "short_name": "DUF8552", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29432", "structures": 0, "taxa": 414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025037", "known_evidence_count": null, "matches": 258, "name": "Protein of unknown function (DUF3923)", "partial_evidence_count": null, "pfam_id": "PF13061", "proteins": 258, "proteomes": 244, "short_name": "DUF3923", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13061", "structures": 0, "taxa": 383, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 210, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 133 and 267 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031670", "known_evidence_count": null, "matches": 278, "name": "Domain of unknown function (DUF4712)", "partial_evidence_count": null, "pfam_id": "PF15830", "proteins": 258, "proteomes": 200, "short_name": "DUF4712", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15830", "structures": 0, "taxa": 687, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 192, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 350 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032265", "known_evidence_count": null, "matches": 277, "name": "Domain of unknown function (DUF4831)", "partial_evidence_count": null, "pfam_id": "PF16115", "proteins": 258, "proteomes": 255, "short_name": "DUF4831", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16115", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a C-terminal domain of a family of unknown function found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR043774", "known_evidence_count": null, "matches": 259, "name": "Family of unknown function (DUF5717)C-terminal", "partial_evidence_count": null, "pfam_id": "PF18983", "proteins": 258, "proteomes": 257, "short_name": "DUF5717", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18983", "structures": 0, "taxa": 413, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of putative integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046119", "known_evidence_count": null, "matches": 258, "name": "Family of unknown function (DUF6116)", "partial_evidence_count": null, "pfam_id": "PF19611", "proteins": 258, "proteomes": 257, "short_name": "DUF6116", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19611", "structures": 0, "taxa": 365, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length. There is a conserved DQQRWIE sequence motif.", "domain_architectures": 1, "interpro_id": "IPR046501", "known_evidence_count": null, "matches": 258, "name": "Family of unknown function (DUF6679)", "partial_evidence_count": null, "pfam_id": "PF20384", "proteins": 258, "proteomes": 233, "short_name": "DUF6679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20384", "structures": 0, "taxa": 647, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 342 and 363 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR046509", "known_evidence_count": null, "matches": 260, "name": "Family of unknown function (DUF6687)", "partial_evidence_count": null, "pfam_id": "PF20392", "proteins": 258, "proteomes": 242, "short_name": "DUF6687", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20392", "structures": 0, "taxa": 454, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 162 and 222 amino acids in length. Structurally, proteins in this family are made of a Four Helix Bundle.", "domain_architectures": 2, "interpro_id": "IPR046547", "known_evidence_count": null, "matches": 259, "name": "Family of unknown function (DUF6803)", "partial_evidence_count": null, "pfam_id": "PF20617", "proteins": 258, "proteomes": 242, "short_name": "DUF6803", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20617", "structures": 0, "taxa": 519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This single domain protein is found a range of bacteria such as actinobacteria, bacteroidetes and firmicutes. It is functionally uncharacterised. The proteins are about 130 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR049193", "known_evidence_count": null, "matches": 258, "name": "Family of unknown function (DUF6855)", "partial_evidence_count": null, "pfam_id": "PF21619", "proteins": 258, "proteomes": 255, "short_name": "DUF6855", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21619", "structures": 0, "taxa": 445, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 248, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short archaeal proteins. Members are predicted to adopt an alpha-helical configuration.", "domain_architectures": 2, "interpro_id": "IPR055947", "known_evidence_count": null, "matches": 259, "name": "Family of unknown function (DUF7525)", "partial_evidence_count": null, "pfam_id": "PF24369", "proteins": 258, "proteomes": 258, "short_name": "DUF7525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24369", "structures": 0, "taxa": 405, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 220, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Family members include human RHEX proteins which regulates erythroid progenitor cell expansion and erythroblast development [[cite:PUB00088308]].", "domain_architectures": 2, "interpro_id": "IPR031517", "known_evidence_count": null, "matches": 297, "name": "Regulator of human erythroid cell expansion (RHEX)", "partial_evidence_count": null, "pfam_id": "PF15763", "proteins": 257, "proteomes": 178, "short_name": "DUF4692", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15763", "structures": 0, "taxa": 615, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chordata.", "domain_architectures": 3, "interpro_id": "IPR037668", "known_evidence_count": null, "matches": 257, "name": "Family of unknown function (DUF5530)", "partial_evidence_count": null, "pfam_id": "PF17670", "proteins": 257, "proteomes": 221, "short_name": "DUF5530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17670", "structures": 3, "taxa": 838, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 206 and 231 amino acids in length. There are two conserved sequence motifs: HLA and LFSR.", "domain_architectures": 2, "interpro_id": "IPR046159", "known_evidence_count": null, "matches": 257, "name": "Family of unknown function (DUF6161)", "partial_evidence_count": null, "pfam_id": "PF19658", "proteins": 257, "proteomes": 250, "short_name": "DUF6161", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19658", "structures": 0, "taxa": 677, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 226, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an Ig-like domain found in the middle region of a group of uncharacterised sequences from nematodes.", "domain_architectures": 26, "interpro_id": "IPR056006", "known_evidence_count": null, "matches": 261, "name": "Domain of unknown function (DUF7584)", "partial_evidence_count": null, "pfam_id": "PF24488", "proteins": 257, "proteomes": 5, "short_name": "DUF7584", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24488", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found at the C-terminus of a family of uncharacterised fungal proteins. These proteins are long and largely composed of disordered regions. This domain is predicted to adopt an alpha/beta structure.", "domain_architectures": 3, "interpro_id": "IPR059785", "known_evidence_count": null, "matches": 257, "name": "Domain of unknown function (DUF8553)", "partial_evidence_count": null, "pfam_id": "PF26805", "proteins": 257, "proteomes": 257, "short_name": "DUF8553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26805", "structures": 0, "taxa": 479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins. They are probably cytoplasmic proteins.", "domain_architectures": 1, "interpro_id": "IPR015079", "known_evidence_count": null, "matches": 256, "name": "Domain of unknown function (DUF1889)", "partial_evidence_count": null, "pfam_id": "PF08986", "proteins": 256, "proteomes": 248, "short_name": "DUF1889", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08986", "structures": 2, "taxa": 551, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and archaea, and is approximately 90 amino acids in length. The domain is usually found C-terminal to a pair of transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR043730", "known_evidence_count": null, "matches": 256, "name": "Domain of unknown function (DUF5673)", "partial_evidence_count": null, "pfam_id": "PF18923", "proteins": 256, "proteomes": 205, "short_name": "DUF5673", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18923", "structures": 0, "taxa": 448, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 137 and 167 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046167", "known_evidence_count": null, "matches": 256, "name": "Family of unknown function (DUF6169)", "partial_evidence_count": null, "pfam_id": "PF19666", "proteins": 256, "proteomes": 184, "short_name": "DUF6169", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19666", "structures": 0, "taxa": 290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of uncharacterised bacterial proteins. A member of a biosynthetic gene cluster (BGC). (BGC0000942) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a protein from the petrobactin biosynthetic gene cluster from Bacillus anthracis str. Ames [[cite:PUB00099423]].", "domain_architectures": 4, "interpro_id": "IPR046047", "known_evidence_count": null, "matches": 255, "name": "DUF6005 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF19468", "proteins": 255, "proteomes": 247, "short_name": "DUF6005", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19468", "structures": 0, "taxa": 424, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in uncharacterised proteins from bacteria, mainly from Cyanobacteria. It contains the conserved sequence motifs LEHAT, GF, CGTN and QxxxTT.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 255, "name": "Domain of unknown function (DUF6391)", "partial_evidence_count": null, "pfam_id": "PF19928", "proteins": 255, "proteomes": 236, "short_name": "DUF6391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19928", "structures": 0, "taxa": 680, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 2, "interpro_id": "", "known_evidence_count": null, "matches": 255, "name": "Domain of unknown function (DUF6485)", "partial_evidence_count": null, "pfam_id": "PF20095", "proteins": 255, "proteomes": 251, "short_name": "DUF6485", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20095", "structures": 0, "taxa": 718, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised, found in bacteria. It is around 120 amino acids in length. There is a conserved sequence motif GxxxRN.", "domain_architectures": 6, "interpro_id": "IPR046744", "known_evidence_count": null, "matches": 262, "name": "Domain of unknown function (DUF6794)", "partial_evidence_count": null, "pfam_id": "PF20594", "proteins": 255, "proteomes": 227, "short_name": "DUF6794", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20594", "structures": 0, "taxa": 554, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the fifth domain found in DUF6079 family proteins. DUF6079 proteins are likely to be BREX (bacteriophage exclusion) system proteins.", "domain_architectures": 11, "interpro_id": "IPR058573", "known_evidence_count": null, "matches": 255, "name": "Family of unknown function (DUF6079) 5th domain", "partial_evidence_count": null, "pfam_id": "PF26387", "proteins": 255, "proteomes": 247, "short_name": "DUF6079_5th", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26387", "structures": 0, "taxa": 771, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of hypothetical proteins specific to Oryza sativa. One sequence ([swissprot:Q943P1]) appears to be tandemly repeated.", "domain_architectures": 3, "interpro_id": "IPR010535", "known_evidence_count": null, "matches": 267, "name": "Protein of unknown function (DUF1110)", "partial_evidence_count": null, "pfam_id": "PF06533", "proteins": 254, "proteomes": 35, "short_name": "DUF1110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06533", "structures": 1, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 94 and 154 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR022231", "known_evidence_count": null, "matches": 254, "name": "Protein of unknown function (DUF3757)", "partial_evidence_count": null, "pfam_id": "PF12582", "proteins": 254, "proteomes": 212, "short_name": "DUF3757", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12582", "structures": 0, "taxa": 313, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 100 residues locates in the C-terminal of some uncharacterized proteins in various Bacteroides, Prevotella and Prevotella species. The function of this family remains unknown.", "domain_architectures": 11, "interpro_id": "IPR032280", "known_evidence_count": null, "matches": 255, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16373", "proteins": 254, "proteomes": 173, "short_name": "DUF4985", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16373", "structures": 0, "taxa": 355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 196, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 170 and 247 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046128", "known_evidence_count": null, "matches": 274, "name": "Family of unknown function (DUF6125)", "partial_evidence_count": null, "pfam_id": "PF19620", "proteins": 254, "proteomes": 235, "short_name": "DUF6125", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19620", "structures": 0, "taxa": 595, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 238, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins.", "domain_architectures": 2, "interpro_id": "IPR055708", "known_evidence_count": null, "matches": 257, "name": "Family of unknown function (DUF7284)", "partial_evidence_count": null, "pfam_id": "PF23955", "proteins": 254, "proteomes": 238, "short_name": "DUF7284", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23955", "structures": 0, "taxa": 377, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea and eukaryotes. Proteins in this family are typically between 288 and 372 amino acids in length. There are two completely conserved residues (G and E) that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR025488", "known_evidence_count": null, "matches": 253, "name": "Domain of unknown function (DUF4380)", "partial_evidence_count": null, "pfam_id": "PF14315", "proteins": 253, "proteomes": 244, "short_name": "DUF4380", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14315", "structures": 0, "taxa": 510, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of Firmicute sequences has members that are annotated as ribose-phosphate pyrophosphokinase; however there is no evidence for this attribution. Member proteins are all shorter than 100 residues in length.", "domain_architectures": 1, "interpro_id": "IPR027879", "known_evidence_count": null, "matches": 253, "name": "Domain of unknown function (DUF4649)", "partial_evidence_count": null, "pfam_id": "PF15507", "proteins": 253, "proteomes": 194, "short_name": "DUF4649", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15507", "structures": 1, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 241, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of small uncharacterised archaeal proteins. They are predicted to fold into a single alpha-helix.", "domain_architectures": 1, "interpro_id": "IPR055972", "known_evidence_count": null, "matches": 253, "name": "Family of unknown function (DUF7550)", "partial_evidence_count": null, "pfam_id": "PF24418", "proteins": 253, "proteomes": 252, "short_name": "DUF7550", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24418", "structures": 0, "taxa": 403, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It usually follows domain with papain-like fold.", "domain_architectures": 4, "interpro_id": "IPR062279", "known_evidence_count": null, "matches": 253, "name": "DUF6005 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF30710", "proteins": 253, "proteomes": 244, "short_name": "DUF6005_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30710", "structures": 0, "taxa": 418, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021564", "known_evidence_count": null, "matches": 252, "name": "Protein of unknown function (DUF3203)", "partial_evidence_count": null, "pfam_id": "PF11462", "proteins": 252, "proteomes": 251, "short_name": "DUF3203", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11462", "structures": 1, "taxa": 263, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins. They are predicted to adopt a globular alpha/beta structure consisting of a meander beta-sheet and two helices packed on one side on the sheet. These proteins contain three highly conserved histidines that in the predicted structure cluster close in space and could potentially form a metal binding site.", "domain_architectures": 1, "interpro_id": "IPR053916", "known_evidence_count": null, "matches": 252, "name": "Family of unknown function (DUF6978)", "partial_evidence_count": null, "pfam_id": "PF22398", "proteins": 252, "proteomes": 240, "short_name": "DUF6978", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22398", "structures": 0, "taxa": 705, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000561) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046004", "known_evidence_count": null, "matches": 251, "name": "Family of unknown function (DUF5960)", "partial_evidence_count": null, "pfam_id": "PF19385", "proteins": 251, "proteomes": 152, "short_name": "DUF5960", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19385", "structures": 0, "taxa": 265, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001735) is described by MIBiG as an example of the following biosynthetic class, other (unspecified), in particular the pentostatine biosynthetic gene cluster from Streptomyces antibioticus [[cite:PUB00098953]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR046250", "known_evidence_count": null, "matches": 251, "name": "Family of unknown function (DUF6283)", "partial_evidence_count": null, "pfam_id": "PF19800", "proteins": 251, "proteomes": 227, "short_name": "DUF6283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19800", "structures": 0, "taxa": 545, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in Proteobacteria. It shares significant sequence similarity with enzymes members of Heme oxygenase-like superfamily and are predicted to adopt similar structure consisting of a bundle of six alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR054248", "known_evidence_count": null, "matches": 251, "name": "Family of unknown function (DUF6975)", "partial_evidence_count": null, "pfam_id": "PF22391", "proteins": 251, "proteomes": 251, "short_name": "DUF6975", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22391", "structures": 0, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 220, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised worm proteins mainly from clade Rhabditida. It is predicted to adopt a globular structure composed of array of alpha-helices.", "domain_architectures": 10, "interpro_id": "IPR056676", "known_evidence_count": null, "matches": 254, "name": "Domain of unknown function (DUF7774)", "partial_evidence_count": null, "pfam_id": "PF24983", "proteins": 251, "proteomes": 63, "short_name": "DUF7774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24983", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Bacteroidota. It is predicted to fold into alpha/beta structure with unique topology. This domain is flanked by coiled coil regions.", "domain_architectures": 1, "interpro_id": "IPR059270", "known_evidence_count": null, "matches": 251, "name": "Domain of unknown function (DUF8226)", "partial_evidence_count": null, "pfam_id": "PF26677", "proteins": 251, "proteomes": 251, "short_name": "DUF8226", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26677", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 310 residues in length and is mainly found in various Bacteroides and Parabacteroides species. Several members are annotated as putative glycosyltransferases, but the specific function of this family is still unknown.", "domain_architectures": 11, "interpro_id": "IPR046320", "known_evidence_count": null, "matches": 250, "name": "Domain of unknown function (DUF4922)", "partial_evidence_count": null, "pfam_id": "PF16269", "proteins": 250, "proteomes": 243, "short_name": "DUF4922", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16269", "structures": 0, "taxa": 465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000262) is described by MIBiG as an example of the following biosynthetic classes, polyketide and saccharide, in particular the prejadomycin biosynthetic gene cluster from Streptomyces sp. PGA64 [[cite:PUB00099417],[cite:PUB00099451]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR046271", "known_evidence_count": null, "matches": 253, "name": "Family of unknown function (DUF6304)", "partial_evidence_count": null, "pfam_id": "PF19822", "proteins": 250, "proteomes": 248, "short_name": "DUF6304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19822", "structures": 0, "taxa": 398, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 250, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 121 and 132 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046600", "known_evidence_count": null, "matches": 250, "name": "Family of unknown function (DUF6659)", "partial_evidence_count": null, "pfam_id": "PF20364", "proteins": 250, "proteomes": 33, "short_name": "DUF6659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20364", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 223, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in archaea and bacteria. These proteins are predicted to adopt similar structure to the members of SufE/NifU superfamily. They contain three invariant cysteine residues and a fourth semi-conserved residue either cysteine or histidine. These residues are likely to define a potential Zn-binding site similar to the binding site observed in SufU.", "domain_architectures": 1, "interpro_id": "IPR054227", "known_evidence_count": null, "matches": 250, "name": "Family of unknown function (DUF6951)", "partial_evidence_count": null, "pfam_id": "PF22263", "proteins": 250, "proteomes": 155, "short_name": "DUF6951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22263", "structures": 0, "taxa": 382, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from bacteria.", "domain_architectures": 4, "interpro_id": "IPR058404", "known_evidence_count": null, "matches": 250, "name": "Domain of unknown function (DUF8091)", "partial_evidence_count": null, "pfam_id": "PF26351", "proteins": 250, "proteomes": 248, "short_name": "DUF8091", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26351", "structures": 0, "taxa": 481, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021498", "known_evidence_count": null, "matches": 249, "name": "Protein of unknown function (DUF3155)", "partial_evidence_count": null, "pfam_id": "PF11352", "proteins": 249, "proteomes": 236, "short_name": "DUF3155", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11352", "structures": 0, "taxa": 649, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 155, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of short bacterial proteins, a few of which are annotated as being minor tail protein. Otherwise the function is unknown.", "domain_architectures": 2, "interpro_id": "IPR021753", "known_evidence_count": null, "matches": 259, "name": "Protein of unknown function (DUF3319)", "partial_evidence_count": null, "pfam_id": "PF11782", "proteins": 249, "proteomes": 230, "short_name": "DUF3319", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11782", "structures": 0, "taxa": 287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 1, "interpro_id": "IPR045733", "known_evidence_count": null, "matches": 249, "name": "Family of unknown function (DUF6087)", "partial_evidence_count": null, "pfam_id": "PF19565", "proteins": 249, "proteomes": 215, "short_name": "DUF6087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19565", "structures": 0, "taxa": 254, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal Ig-like domain found in a family of uncharacterised proteins from archaea. The proteins are predominantly found in the Halobacteria class, which includes members of the Haloferacaceae, Haloarculaceae, and Natrialbaceae families. The proteins in this family are typically around 550-580 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR058911", "known_evidence_count": null, "matches": 249, "name": "Domain of unknown function (DUF8186) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26591", "proteins": 249, "proteomes": 153, "short_name": "DUF8186_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26591", "structures": 0, "taxa": 257, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 198, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several uncharacterised staphylococcal proteins. These proteins have been called conserved staphylococcal antigens (Csa) [[cite:PUB00081214]].", "domain_architectures": 1, "interpro_id": "IPR007595", "known_evidence_count": null, "matches": 248, "name": "Csa1 family", "partial_evidence_count": null, "pfam_id": "PF04507", "proteins": 248, "proteomes": 28, "short_name": "DUF576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04507", "structures": 4, "taxa": 59, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 206, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins which seem to be specific to Oryzias latipes (Japanese ricefish). Members of this family are typically around 200 residues in length. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR009803", "known_evidence_count": null, "matches": 278, "name": "Protein of unknown function (DUF1373)", "partial_evidence_count": null, "pfam_id": "PF07117", "proteins": 248, "proteomes": 76, "short_name": "DUF1373", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07117", "structures": 0, "taxa": 282, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a number of hypothetical bacterial proteins of unknown function approximately 100 residues in length.", "domain_architectures": 3, "interpro_id": "IPR009881", "known_evidence_count": null, "matches": 252, "name": "Protein of unknown function (DUF1433)", "partial_evidence_count": null, "pfam_id": "PF07252", "proteins": 248, "proteomes": 93, "short_name": "DUF1433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07252", "structures": 1, "taxa": 162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 4, "interpro_id": "IPR019215", "known_evidence_count": null, "matches": 249, "name": "Uncharacterized protein conserved in archaea (DUF2115)", "partial_evidence_count": null, "pfam_id": "PF09888", "proteins": 248, "proteomes": 130, "short_name": "DUF2115", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09888", "structures": 0, "taxa": 257, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus spp.", "domain_architectures": 1, "interpro_id": "IPR019687", "known_evidence_count": null, "matches": 248, "name": "Protein of unknown function (DUF2535)", "partial_evidence_count": null, "pfam_id": "PF10751", "proteins": 248, "proteomes": 243, "short_name": "DUF2535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10751", "structures": 0, "taxa": 325, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Mycobacterium spp.", "domain_architectures": 2, "interpro_id": "IPR024381", "known_evidence_count": null, "matches": 249, "name": "Protein of unknown function (DUF2561)", "partial_evidence_count": null, "pfam_id": "PF10812", "proteins": 248, "proteomes": 248, "short_name": "DUF2561", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10812", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are annotated in SwissProt as Putative glycerol transporters SwissProt:Q92EU1. Members of the family contain four potential transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR054200", "known_evidence_count": null, "matches": 248, "name": "Domain of unknown function (DUF6905)", "partial_evidence_count": null, "pfam_id": "PF21846", "proteins": 248, "proteomes": 112, "short_name": "DUF6905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21846", "structures": 0, "taxa": 256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in a group of uncharacterised proteins. It is remotely related to AbiEi winged helix domain and it is predicted to adopt the same structure.", "domain_architectures": 8, "interpro_id": "IPR054265", "known_evidence_count": null, "matches": 248, "name": "Domain of unknown function (DUF6996)", "partial_evidence_count": null, "pfam_id": "PF22515", "proteins": 248, "proteomes": 245, "short_name": "DUF6996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22515", "structures": 0, "taxa": 663, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 232, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised archaeal proteins. They contain three highly conserved negatively charged (aspartate and glutamate) residues.", "domain_architectures": 2, "interpro_id": "IPR055923", "known_evidence_count": null, "matches": 267, "name": "Family of unknown function (DUF7500)", "partial_evidence_count": null, "pfam_id": "PF24332", "proteins": 248, "proteomes": 229, "short_name": "DUF7500", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24332", "structures": 0, "taxa": 364, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018642", "known_evidence_count": null, "matches": 247, "name": "DUF2066", "partial_evidence_count": null, "pfam_id": "PF09839", "proteins": 247, "proteomes": 247, "short_name": "DUF2066", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09839", "structures": 0, "taxa": 349, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae.", "domain_architectures": 2, "interpro_id": "IPR019685", "known_evidence_count": null, "matches": 247, "name": "Protein of unknown function (DUF2534)", "partial_evidence_count": null, "pfam_id": "PF10749", "proteins": 247, "proteomes": 237, "short_name": "DUF2534", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10749", "structures": 0, "taxa": 321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in vertebrates. Proteins in this family are typically between 101 and 117 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR031699", "known_evidence_count": null, "matches": 248, "name": "Domain of unknown function (DUF4720)", "partial_evidence_count": null, "pfam_id": "PF15846", "proteins": 247, "proteomes": 226, "short_name": "DUF4720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15846", "structures": 0, "taxa": 837, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 263 and 305 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031832", "known_evidence_count": null, "matches": 247, "name": "Domain of unknown function (DUF4747)", "partial_evidence_count": null, "pfam_id": "PF15931", "proteins": 247, "proteomes": 244, "short_name": "DUF4747", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15931", "structures": 0, "taxa": 710, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR039452", "known_evidence_count": null, "matches": 247, "name": "Family of unknown function (DUF5403)", "partial_evidence_count": null, "pfam_id": "PF17395", "proteins": 247, "proteomes": 242, "short_name": "DUF5403", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17395", "structures": 0, "taxa": 538, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a small domain that is found in a variety of toxin proteins. The precise function of this domain is uncertain. It often follows [pfam:PF04829].", "domain_architectures": 122, "interpro_id": "IPR049271", "known_evidence_count": null, "matches": 247, "name": "Family of unknown function (DUF6862)", "partial_evidence_count": null, "pfam_id": "PF21726", "proteins": 247, "proteomes": 197, "short_name": "DUF6862", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21726", "structures": 1, "taxa": 434, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised bacterial proteins. Structure prediction shows these proteins are alpha helical with a long central alpha helix packed against two shorter N and C-terminal helices. Structure prediction suggests these proteins may form homodimers.", "domain_architectures": 1, "interpro_id": "IPR056084", "known_evidence_count": null, "matches": 247, "name": "Family of unknown function (DUF7667)", "partial_evidence_count": null, "pfam_id": "PF24704", "proteins": 247, "proteomes": 183, "short_name": "DUF7667", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24704", "structures": 0, "taxa": 241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised actinobacterial proteins that are related to [pfam:PF20115].", "domain_architectures": 1, "interpro_id": "IPR056132", "known_evidence_count": null, "matches": 247, "name": "Domain of unknown function (DUF7715)", "partial_evidence_count": null, "pfam_id": "PF24831", "proteins": 247, "proteomes": 230, "short_name": "DUF7715", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24831", "structures": 0, "taxa": 357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to contain two structural beta(3)-alpha repeats that swap their alpha-helix in a similar way as observed in the known ssDNA-binding transcriptional regulator domains. It is likely that this domain is distantly related to them and probably represents the minimal two repeat containing fold.", "domain_architectures": 5, "interpro_id": "IPR057200", "known_evidence_count": null, "matches": 247, "name": "Domain of unknown function (DUF7878)", "partial_evidence_count": null, "pfam_id": "PF25297", "proteins": 247, "proteomes": 231, "short_name": "DUF7878", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25297", "structures": 0, "taxa": 457, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 183, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in uncharacterised bacterial proteins. It is predicted to adopt Ig-like fold. It is usually found in combination with [pfam:PF26613] and [pfam:PF26614].", "domain_architectures": 8, "interpro_id": "IPR058508", "known_evidence_count": null, "matches": 250, "name": "Domain of unknown function (DUF8195)", "partial_evidence_count": null, "pfam_id": "PF26615", "proteins": 247, "proteomes": 166, "short_name": "DUF8195", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26615", "structures": 0, "taxa": 357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 238, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a Leucine Rich domain in uncharacterised proteins mainly from animals. Each Leucine Rich Repeat is composed of a beta-alpha unit. These units form elongated non-globular structures. Leucine Rich Repeats are often flanked by cysteine rich domains.", "domain_architectures": 12, "interpro_id": "IPR059390", "known_evidence_count": null, "matches": 249, "name": "Domain of unknown function (DUF8346)", "partial_evidence_count": null, "pfam_id": "PF27094", "proteins": 247, "proteomes": 7, "short_name": "DUF8346", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27094", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 215, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha/beta structure composed of a curved beta-sheet and alpha-helices packed on the concave side of it. It contains two highly conserved cysteine residues predicted to form disulfide bond. This domain is flanked by regions predicted as transmembrane.", "domain_architectures": 6, "interpro_id": "IPR059450", "known_evidence_count": null, "matches": 255, "name": "Domain of unknown function (DUF8406)", "partial_evidence_count": null, "pfam_id": "PF28465", "proteins": 247, "proteomes": 156, "short_name": "DUF8406", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28465", "structures": 0, "taxa": 387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length. There are two completely conserved residues (V and C) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR024522", "known_evidence_count": null, "matches": 246, "name": "Protein of unknown function (DUF3789)", "partial_evidence_count": null, "pfam_id": "PF12664", "proteins": 246, "proteomes": 161, "short_name": "DUF3789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12664", "structures": 0, "taxa": 324, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "this family consists of short uncharacterized proteins found mostly in different strains of Acinetobacter bumanii, but also in several Shewanella species and in some bacteria from the CFB group. Solved structure of ABAYE3784 protein from Acinetobacter baumannii AYE shows a five helical bundle with a very strong structural similarity to a bromodomain domain. However, the specific function of proteins from the DUF4844 family is unknown", "domain_architectures": 1, "interpro_id": "IPR032301", "known_evidence_count": null, "matches": 246, "name": "Domain of unknown function (DUF4844)", "partial_evidence_count": null, "pfam_id": "PF16133", "proteins": 246, "proteomes": 224, "short_name": "DUF4844", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16133", "structures": 1, "taxa": 397, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 187, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is mainly found in Proteobacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046480", "known_evidence_count": null, "matches": 246, "name": "Family of unknown function (DUF6573)", "partial_evidence_count": null, "pfam_id": "PF20213", "proteins": 246, "proteomes": 198, "short_name": "DUF6573", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20213", "structures": 0, "taxa": 534, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 231, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function, mainly found in a group of archaeal sequences such as HVO_1708 ([swissprot:D4H053]). This domain may have a fold related to glycosyltransferases.", "domain_architectures": 5, "interpro_id": "IPR057168", "known_evidence_count": null, "matches": 246, "name": "Domain of unknown function (DUF7846)", "partial_evidence_count": null, "pfam_id": "PF25230", "proteins": 246, "proteomes": 230, "short_name": "DUF7846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25230", "structures": 0, "taxa": 381, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins contain A C-terminal transmembrane helix and a beta sandwich domain.", "domain_architectures": 2, "interpro_id": "IPR058376", "known_evidence_count": null, "matches": 246, "name": "Family of unknown function (DUF8063)", "partial_evidence_count": null, "pfam_id": "PF26259", "proteins": 246, "proteomes": 166, "short_name": "DUF8063", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26259", "structures": 0, "taxa": 342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Cyanobacteria. Several members are annotated as the protein Ycf51. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019664", "known_evidence_count": null, "matches": 245, "name": "Protein of function (DUF2518)", "partial_evidence_count": null, "pfam_id": "PF10726", "proteins": 245, "proteomes": 243, "short_name": "DUF2518", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10726", "structures": 0, "taxa": 670, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from proteobacteria.", "domain_architectures": 5, "interpro_id": "IPR061604", "known_evidence_count": null, "matches": 245, "name": "Domain of unknown function (DUF8534)", "partial_evidence_count": null, "pfam_id": "PF29381", "proteins": 245, "proteomes": 225, "short_name": "DUF8534", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29381", "structures": 0, "taxa": 377, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021705", "known_evidence_count": null, "matches": 244, "name": "Protein of unknown function (DUF3288)", "partial_evidence_count": null, "pfam_id": "PF11691", "proteins": 244, "proteomes": 243, "short_name": "DUF3288", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11691", "structures": 0, "taxa": 668, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 168, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 270 residues in length and found in various Cytophagales, Sphingobacteriaceae and Ignavibacteriaceae species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032595", "known_evidence_count": null, "matches": 244, "name": "Domain of unknown function (DUF4905)", "partial_evidence_count": null, "pfam_id": "PF16248", "proteins": 244, "proteomes": 244, "short_name": "DUF4905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16248", "structures": 0, "taxa": 364, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 105 and 125 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046089", "known_evidence_count": null, "matches": 244, "name": "Family of unknown function (DUF6107)", "partial_evidence_count": null, "pfam_id": "PF19602", "proteins": 244, "proteomes": 243, "short_name": "DUF6107", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19602", "structures": 0, "taxa": 358, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in mammals.", "domain_architectures": 4, "interpro_id": "IPR027827", "known_evidence_count": null, "matches": 244, "name": "Protein of unknown function (DUF4523)", "partial_evidence_count": null, "pfam_id": "PF15023", "proteins": 243, "proteomes": 184, "short_name": "DUF4523", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15023", "structures": 0, "taxa": 692, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of uncharacterized proteins around 180 residues in length and is mainly found in various Pseudomonas species, especially in Pseudomonas aeruginosa. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032543", "known_evidence_count": null, "matches": 243, "name": "Domain of unknown function (DUF4946)", "partial_evidence_count": null, "pfam_id": "PF16304", "proteins": 243, "proteomes": 237, "short_name": "DUF4946", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16304", "structures": 0, "taxa": 270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 136, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of bacterial proteins with unknown function. They share sequence similarity with the N-terminal part of NADAR domain and are predicted to adopt structure that is globally similar to the structure of E.coli protein YbiA, a member of the NADAR domain family.", "domain_architectures": 3, "interpro_id": "IPR054219", "known_evidence_count": null, "matches": 244, "name": "Family of unknown function (DUF6939)", "partial_evidence_count": null, "pfam_id": "PF22075", "proteins": 243, "proteomes": 231, "short_name": "DUF6939", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22075", "structures": 0, "taxa": 510, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from phage. Structure prediction shows the proteins to be composed of an alpha helical N-terminal domain and a C-terminal domain composed of a 5 stranded beta meander.", "domain_architectures": 2, "interpro_id": "IPR055762", "known_evidence_count": null, "matches": 243, "name": "Family of unknown function (DUF7338)", "partial_evidence_count": null, "pfam_id": "PF24027", "proteins": 243, "proteomes": 236, "short_name": "DUF7338", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24027", "structures": 0, "taxa": 556, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 229, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea.", "domain_architectures": 1, "interpro_id": "IPR055942", "known_evidence_count": null, "matches": 243, "name": "Family of unknown function (DUF7520)", "partial_evidence_count": null, "pfam_id": "PF24364", "proteins": 243, "proteomes": 179, "short_name": "DUF7520", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24364", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Cyanobacteria. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019678", "known_evidence_count": null, "matches": 242, "name": "Protein of unknown function (DUF2555)", "partial_evidence_count": null, "pfam_id": "PF10742", "proteins": 242, "proteomes": 241, "short_name": "DUF2555", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10742", "structures": 0, "taxa": 654, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes the B. subtilis YjdJ protein [swissprot:O05524], which is functionally uncharacterised. This is not a homologue of E. coli YjdJ, which belongs to [pfam:PF00583]. This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 95 and 152 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025440", "known_evidence_count": null, "matches": 249, "name": "Domain of unknown function (DUF4306)", "partial_evidence_count": null, "pfam_id": "PF14154", "proteins": 242, "proteomes": 213, "short_name": "DUF4306", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14154", "structures": 0, "taxa": 306, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 229, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in a group of uncharacterised archaeal proteins. In some proteins, this domain precedes [[pfam:PF18069]] and [[pfam:PF18009]]. It is predicted to fold into a globular alpha/beta structure.", "domain_architectures": 1, "interpro_id": "IPR055772", "known_evidence_count": null, "matches": 242, "name": "Domain of unknown function (DUF7348)", "partial_evidence_count": null, "pfam_id": "PF24039", "proteins": 242, "proteomes": 242, "short_name": "DUF7348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24039", "structures": 0, "taxa": 385, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. Members of this family have a PGF-CTERM motif [pfam:PF18204] at the C-termini.", "domain_architectures": 4, "interpro_id": "IPR055913", "known_evidence_count": null, "matches": 462, "name": "Domain of unknown function (DUF7490)", "partial_evidence_count": null, "pfam_id": "PF24318", "proteins": 242, "proteomes": 231, "short_name": "DUF7490", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24318", "structures": 0, "taxa": 377, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 139, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins found in bacteria. These proteins are predicted to adopt globular structure that folds into a three helical bundle.", "domain_architectures": 3, "interpro_id": "IPR056094", "known_evidence_count": null, "matches": 245, "name": "Domain of unknown function (DUF7677)", "partial_evidence_count": null, "pfam_id": "PF24725", "proteins": 242, "proteomes": 238, "short_name": "DUF7677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24725", "structures": 0, "taxa": 507, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 172, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the sixth domain found in DUF6079 family proteins. DUF6079 proteins are likely to be BREX (bacteriophage exclusion) system proteins.", "domain_architectures": 10, "interpro_id": "IPR058574", "known_evidence_count": null, "matches": 242, "name": "Family of unknown function (DUF6079) 6th domain", "partial_evidence_count": null, "pfam_id": "PF26388", "proteins": 242, "proteomes": 235, "short_name": "DUF6079_6th", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26388", "structures": 0, "taxa": 731, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small integral membrane domain of approximately 50-70 amino acids with two predicted transmembrane helices. The family is found exclusively in halophilic archaea, restricted to the order Halobacteriales, particularly the families Haloferacaceae, Natrialbaceae and Haloarculaceae. Some members are found in proteins containing PEP-CTERM protein-sorting domains. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061597", "known_evidence_count": null, "matches": 242, "name": "Domain of unknown function (DUF8527)", "partial_evidence_count": null, "pfam_id": "PF29289", "proteins": 242, "proteomes": 242, "short_name": "DUF8527", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29289", "structures": 0, "taxa": 374, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Enterobacteriaceae. The family has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR020251", "known_evidence_count": null, "matches": 241, "name": "Protein of unknown function (DUF2543)", "partial_evidence_count": null, "pfam_id": "PF10820", "proteins": 241, "proteomes": 238, "short_name": "DUF2543", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10820", "structures": 0, "taxa": 331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR021468", "known_evidence_count": null, "matches": 243, "name": "Protein of unknown function (DUF3120)", "partial_evidence_count": null, "pfam_id": "PF11318", "proteins": 241, "proteomes": 239, "short_name": "DUF3120", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11318", "structures": 0, "taxa": 656, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR021551", "known_evidence_count": null, "matches": 242, "name": "Protein of unknown function (DUF3005)", "partial_evidence_count": null, "pfam_id": "PF11448", "proteins": 241, "proteomes": 197, "short_name": "DUF3005", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11448", "structures": 0, "taxa": 245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_0092, a conserved protein found in a conjugate transposon. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or other bacterial species vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 1, "interpro_id": "IPR024452", "known_evidence_count": null, "matches": 241, "name": "Domain of unknown function, B. Theta Gene description (DUF3876)", "partial_evidence_count": null, "pfam_id": "PF12992", "proteins": 241, "proteomes": 116, "short_name": "DUF3876", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12992", "structures": 0, "taxa": 198, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of lipoproteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 281 and 303 amino acids in length. There are two conserved sequence motifs: NCR and PYQ.", "domain_architectures": 1, "interpro_id": "IPR025389", "known_evidence_count": null, "matches": 241, "name": "Domain of unknown function (DUF4300)", "partial_evidence_count": null, "pfam_id": "PF14133", "proteins": 241, "proteomes": 225, "short_name": "DUF4300", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14133", "structures": 1, "taxa": 432, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 235, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found mostly in Metazoa.", "domain_architectures": 2, "interpro_id": "IPR035291", "known_evidence_count": null, "matches": 242, "name": "Family of unknown function (DUF5354)", "partial_evidence_count": null, "pfam_id": "PF17305", "proteins": 241, "proteomes": 78, "short_name": "DUF5354", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17305", "structures": 0, "taxa": 194, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is mainly found at the C-terminal of uncharacterised proteins, predominantly from Bacteriodetes. It is about 74 amino acids in length and it contains the GQ and GxxV/IV conserved sequence motifs. This domain has similarity to the Type IX secretion system targeting domain.", "domain_architectures": 22, "interpro_id": "IPR045963", "known_evidence_count": null, "matches": 241, "name": "Domain of unknown function (DUF6383)", "partial_evidence_count": null, "pfam_id": "PF19910", "proteins": 241, "proteomes": 55, "short_name": "DUF6383", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19910", "structures": 0, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 77 and 127 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046506", "known_evidence_count": null, "matches": 241, "name": "Family of unknown function (DUF6684)", "partial_evidence_count": null, "pfam_id": "PF20389", "proteins": 241, "proteomes": 190, "short_name": "DUF6684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20389", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal immunoglobulin-like domain of approximately 100 residues found in cyanobacterial proteins. These proteins contain an N-terminal NTF2-like domain followed by this Ig-like C-terminal domain. Proteomic studies have shown that one family member (Slr2144 in Synechocystis sp. PCC 6803) accumulates under salt stress and hexane stress conditions and is localised to the periplasm. The family is found exclusively in cyanobacteria, including Nostocales and Oscillatoriophycideae. The function of this domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061684", "known_evidence_count": null, "matches": 242, "name": "Domain of unknown function (DUF8623)", "partial_evidence_count": null, "pfam_id": "PF30546", "proteins": 241, "proteomes": 239, "short_name": "DUF8623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30546", "structures": 0, "taxa": 644, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 225, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 9, "interpro_id": "IPR008569", "known_evidence_count": null, "matches": 243, "name": "Protein of unknown function (DUF851)", "partial_evidence_count": null, "pfam_id": "PF05867", "proteins": 240, "proteomes": 68, "short_name": "DUF851", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05867", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 207, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is annotated as pyruvate formate-lyase activating enzyme ([ec:1.97.1.4]) in UniProt. It is not clear where this annotation comes from.", "domain_architectures": 2, "interpro_id": "IPR014846", "known_evidence_count": null, "matches": 241, "name": "Putative pyruvate format-lyase activating enzyme (DUF1786)", "partial_evidence_count": null, "pfam_id": "PF08735", "proteins": 240, "proteomes": 236, "short_name": "DUF1786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08735", "structures": 0, "taxa": 528, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 258 and 300 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025146", "known_evidence_count": null, "matches": 240, "name": "Protein of unknown function (DUF4088)", "partial_evidence_count": null, "pfam_id": "PF13317", "proteins": 240, "proteomes": 240, "short_name": "DUF4088", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13317", "structures": 0, "taxa": 262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal Helix-turn-helix domain in the DUF1699 family of proteins found in archaeabacterial sequences.", "domain_architectures": 2, "interpro_id": "IPR012546", "known_evidence_count": null, "matches": 239, "name": "Protein of unknown function (DUF1699) C-terminal HTH domain", "partial_evidence_count": null, "pfam_id": "PF08004", "proteins": 239, "proteomes": 50, "short_name": "DUF1699", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08004", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 170 amino acids in length. There is a single completely conserved residue S that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025075", "known_evidence_count": null, "matches": 239, "name": "Protein of unknown function (DUF3916)", "partial_evidence_count": null, "pfam_id": "PF13079", "proteins": 239, "proteomes": 229, "short_name": "DUF3916", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13079", "structures": 0, "taxa": 460, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to adopt a globular structure consisting of array of helices followed by a beta-hairpin.", "domain_architectures": 5, "interpro_id": "IPR056126", "known_evidence_count": null, "matches": 239, "name": "Domain of unknown function (DUF7709)", "partial_evidence_count": null, "pfam_id": "PF24813", "proteins": 239, "proteomes": 232, "short_name": "DUF7709", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24813", "structures": 0, "taxa": 539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble Zinc beta-ribbon domains.", "domain_architectures": 3, "interpro_id": "IPR057160", "known_evidence_count": null, "matches": 239, "name": "Domain of unknown function (DUF7838)", "partial_evidence_count": null, "pfam_id": "PF25208", "proteins": 239, "proteomes": 239, "short_name": "DUF7838", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25208", "structures": 0, "taxa": 443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised protein from Halogeometricum borinquense (Hbor_03000) and related prokaryotic proteins. This protein is found next to a toxic gene Hbor_02990 and is likely a immunity protein which is able to prevent self-intoxication [[cite:PUB00160456]]. This domain is predicted to fold into three four-stranded beta-sheets that pack in a similar way as blades in beta-propellers.", "domain_architectures": 2, "interpro_id": "IPR058263", "known_evidence_count": null, "matches": 240, "name": "Domain of unknown function (DUF7957)", "partial_evidence_count": null, "pfam_id": "PF25857", "proteins": 239, "proteomes": 200, "short_name": "DUF7957", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25857", "structures": 0, "taxa": 534, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 5, "interpro_id": "IPR004239", "known_evidence_count": null, "matches": 239, "name": "Lyme disease proteins of unknown function", "partial_evidence_count": null, "pfam_id": "PF02989", "proteins": 238, "proteomes": 30, "short_name": "DUF228", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02989", "structures": 7, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal proteins of unknown function.", "domain_architectures": 7, "interpro_id": "IPR009482", "known_evidence_count": null, "matches": 244, "name": "Protein of unknown function (DUF1102)", "partial_evidence_count": null, "pfam_id": "PF06510", "proteins": 238, "proteomes": 135, "short_name": "DUF1102", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06510", "structures": 0, "taxa": 245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 40 amino acids in length. There is a conserved LIPL sequence motif. There are two completely conserved G residues that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR028044", "known_evidence_count": null, "matches": 238, "name": "Domain of unknown function (DUF4444)", "partial_evidence_count": null, "pfam_id": "PF14563", "proteins": 238, "proteomes": 238, "short_name": "DUF4444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14563", "structures": 1, "taxa": 345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000223) is described by MIBiG as an example of the following biosynthetic class, polyketide, rabelomycin biosynthetic gene cluster from uncultured bacterium BAC AB649/1850 [[cite:PUB00098876]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR045927", "known_evidence_count": null, "matches": 239, "name": "Family of unknown function (DUF6346)", "partial_evidence_count": null, "pfam_id": "PF19873", "proteins": 238, "proteomes": 152, "short_name": "DUF6346", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19873", "structures": 0, "taxa": 218, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small domain is found in one or two copies in proteins from bacteria. The function of this domain is unknown.", "domain_architectures": 2, "interpro_id": "IPR014924", "known_evidence_count": null, "matches": 237, "name": "Domain of unknown function (DUF1803)", "partial_evidence_count": null, "pfam_id": "PF08820", "proteins": 237, "proteomes": 236, "short_name": "DUF1803", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08820", "structures": 0, "taxa": 339, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR021433", "known_evidence_count": null, "matches": 237, "name": "Protein of unknown function (DUF3083)", "partial_evidence_count": null, "pfam_id": "PF11281", "proteins": 237, "proteomes": 205, "short_name": "DUF3083", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11281", "structures": 0, "taxa": 258, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins are functionally uncharacterised. This family is only found in bacteria.", "domain_architectures": 4, "interpro_id": "IPR021767", "known_evidence_count": null, "matches": 237, "name": "Domain of unknown function (DUF3330)", "partial_evidence_count": null, "pfam_id": "PF11809", "proteins": 237, "proteomes": 175, "short_name": "DUF3330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11809", "structures": 0, "taxa": 418, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 201, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry includes the ORF1 protein from spiroplasma phages.", "domain_architectures": 6, "interpro_id": "IPR022160", "known_evidence_count": null, "matches": 248, "name": "Spiroplasma phage ORF1-like family", "partial_evidence_count": null, "pfam_id": "PF12461", "proteins": 237, "proteomes": 10, "short_name": "DUF3688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12461", "structures": 0, "taxa": 63, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 223, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a C2H2 zinc finger found in a group of uncharacterised proteins from archaea.", "domain_architectures": 1, "interpro_id": "IPR055833", "known_evidence_count": null, "matches": 237, "name": "Domain of unknown function (DUF7410)", "partial_evidence_count": null, "pfam_id": "PF24166", "proteins": 237, "proteomes": 168, "short_name": "DUF7410", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24166", "structures": 0, "taxa": 266, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 107, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised bacterial proteins. They are predicted to adopt a globular structure consisting of a five-stranded antiparallel beta-sheet and helices packed on one side of it.", "domain_architectures": 2, "interpro_id": "IPR056110", "known_evidence_count": null, "matches": 237, "name": "Domain of unknown function (DUF7693)", "partial_evidence_count": null, "pfam_id": "PF24745", "proteins": 237, "proteomes": 201, "short_name": "DUF7693", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24745", "structures": 0, "taxa": 285, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 225, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins from Halobacteria. They small in size (~80 aa) and are predicted to be largely disordered.", "domain_architectures": 1, "interpro_id": "IPR058742", "known_evidence_count": null, "matches": 237, "name": "Family of unknown function (DUF7989)", "partial_evidence_count": null, "pfam_id": "PF25951", "proteins": 237, "proteomes": 206, "short_name": "DUF7989", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25951", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a PUA-like domain of unknown function. It is found in prokaryotes.", "domain_architectures": 10, "interpro_id": "IPR061913", "known_evidence_count": null, "matches": 236, "name": "Domain of unknown function (DUF365)", "partial_evidence_count": null, "pfam_id": "PF04033", "proteins": 236, "proteomes": 214, "short_name": "DUF365", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04033", "structures": 1, "taxa": 620, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is about 100 amino acids in length and is functionally uncharacterised.", "domain_architectures": 1, "interpro_id": "IPR014943", "known_evidence_count": null, "matches": 236, "name": "Domain of unknown function (DUF1815)", "partial_evidence_count": null, "pfam_id": "PF08844", "proteins": 236, "proteomes": 221, "short_name": "DUF1815", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08844", "structures": 0, "taxa": 611, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR021437", "known_evidence_count": null, "matches": 239, "name": "Protein of unknown function (DUF3086)", "partial_evidence_count": null, "pfam_id": "PF11285", "proteins": 236, "proteomes": 233, "short_name": "DUF3086", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11285", "structures": 0, "taxa": 630, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of very short, approximately 60 residue, proteins from Firmicutes, that are all putatively annotated as being MutT/Nudix. However, the characteristic Nudix motif of GX(5)EX(7)REUXEE is absent.", "domain_architectures": 2, "interpro_id": "IPR025143", "known_evidence_count": null, "matches": 236, "name": "Domain of unknown function (DUF4083)", "partial_evidence_count": null, "pfam_id": "PF13314", "proteins": 236, "proteomes": 205, "short_name": "DUF4083", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13314", "structures": 0, "taxa": 332, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is a likely integral membrane domain that contains a glycine-zipper motif. This domain is found associated with toxin domains.", "domain_architectures": 53, "interpro_id": "IPR049195", "known_evidence_count": null, "matches": 236, "name": "Family of unknown function (DUF6861)", "partial_evidence_count": null, "pfam_id": "PF21724", "proteins": 236, "proteomes": 149, "short_name": "DUF6861", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21724", "structures": 0, "taxa": 407, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 224, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found several times in a group of uncharacterised proteins from nematodes. It is predicted to adopt a mainly beta configuration.", "domain_architectures": 12, "interpro_id": "IPR056039", "known_evidence_count": null, "matches": 255, "name": "Domain of unknown function (DUF7622)", "partial_evidence_count": null, "pfam_id": "PF24602", "proteins": 236, "proteomes": 55, "short_name": "DUF7622", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24602", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 139, "candidate_reasons": [ "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 140 residues found exclusively in cyanobacteria. The family is widely distributed across the phylum, including members of the orders Nostocales, Oscillatoriales, Synechococcales, and Chroococcales. Transcriptomic analysis of Trichodesmium erythraeum identified the homologue Tery_1686 among genes responsive to iron availability [[cite:PUB00163730]]. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 236, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF30525", "proteins": 236, "proteomes": 225, "short_name": "DUF", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30525", "structures": 0, "taxa": 604, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR021469", "known_evidence_count": null, "matches": 236, "name": "Protein of unknown function (DUF3122)", "partial_evidence_count": null, "pfam_id": "PF11320", "proteins": 235, "proteomes": 181, "short_name": "DUF3122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11320", "structures": 0, "taxa": 503, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes members in Actinobacteria. All family members present double transmembrane.", "domain_architectures": 2, "interpro_id": "IPR043762", "known_evidence_count": null, "matches": 235, "name": "Family of unknown function (DUF5708)", "partial_evidence_count": null, "pfam_id": "PF18969", "proteins": 235, "proteomes": 234, "short_name": "DUF5708", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18969", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 227, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short proteins from archaea. Members are predicted to adopt an alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR055893", "known_evidence_count": null, "matches": 235, "name": "Family of unknown function (DUF7470)", "partial_evidence_count": null, "pfam_id": "PF24282", "proteins": 235, "proteomes": 235, "short_name": "DUF7470", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24282", "structures": 0, "taxa": 370, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 187, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 129 and 161 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR028114", "known_evidence_count": null, "matches": 236, "name": "Domain of unknown function (DUF4658)", "partial_evidence_count": null, "pfam_id": "PF15555", "proteins": 234, "proteomes": 187, "short_name": "DUF4658", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15555", "structures": 0, "taxa": 695, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 203, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Diptera. Some family members carry [pfam:PF08445] on their C-terminal.", "domain_architectures": 12, "interpro_id": "IPR041506", "known_evidence_count": null, "matches": 240, "name": "Domain of unknown function (DUF5645)", "partial_evidence_count": null, "pfam_id": "PF18713", "proteins": 234, "proteomes": 114, "short_name": "DUF5645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18713", "structures": 1, "taxa": 460, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in cyanobacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046649", "known_evidence_count": null, "matches": 234, "name": "Family of unknown function (DUF6761)", "partial_evidence_count": null, "pfam_id": "PF20547", "proteins": 234, "proteomes": 233, "short_name": "DUF6761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20547", "structures": 0, "taxa": 630, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Several copies of this domain of unknown function are found in a group of uncharacterised proteins from lower eukaryotes. It is often found associated to [pfam:PF00648] and [pfam:PF01067].", "domain_architectures": 107, "interpro_id": "IPR056040", "known_evidence_count": null, "matches": 3841, "name": "Domain of unknown function (DUF7623)", "partial_evidence_count": null, "pfam_id": "PF24610", "proteins": 234, "proteomes": 29, "short_name": "DUF7623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24610", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt Ig-like fold. It is usually found C-terminal to [pfam:PF26613].", "domain_architectures": 10, "interpro_id": "IPR058507", "known_evidence_count": null, "matches": 234, "name": "Domain of unknown function (DUF8194)", "partial_evidence_count": null, "pfam_id": "PF26614", "proteins": 234, "proteomes": 164, "short_name": "DUF8194", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26614", "structures": 0, "taxa": 350, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 107 and 201 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031746", "known_evidence_count": null, "matches": 238, "name": "Domain of unknown function (DUF4732)", "partial_evidence_count": null, "pfam_id": "PF15876", "proteins": 233, "proteomes": 190, "short_name": "DUF4732", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15876", "structures": 0, "taxa": 690, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 100 amino acids in length. The family is found in association with [pfam:PF03791], [pfam:PF03790]. There are two completely conserved residues (H and I) that may be functionally important.", "domain_architectures": 6, "interpro_id": "IPR032084", "known_evidence_count": null, "matches": 233, "name": "Domain of unknown function (DUF4812)", "partial_evidence_count": null, "pfam_id": "PF16071", "proteins": 233, "proteomes": 212, "short_name": "DUF4812", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16071", "structures": 0, "taxa": 764, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is mainly found in bacteria and archaea, and is approximately 60 amino acids in length. There is a conserved WxxR sequence motif and a conserved Lys residue. Members of this entry may be transmembrane proteins.", "domain_architectures": 2, "interpro_id": "IPR046477", "known_evidence_count": null, "matches": 233, "name": "Domain of unknown function (DUF6798)", "partial_evidence_count": null, "pfam_id": "PF20604", "proteins": 233, "proteomes": 232, "short_name": "DUF6798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20604", "structures": 0, "taxa": 600, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha structure.", "domain_architectures": 2, "interpro_id": "IPR055957", "known_evidence_count": null, "matches": 233, "name": "Family of unknown function (DUF7535)", "partial_evidence_count": null, "pfam_id": "PF24379", "proteins": 233, "proteomes": 206, "short_name": "DUF7535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24379", "structures": 0, "taxa": 333, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into two meander beta-sheets that sandwich each other.", "domain_architectures": 5, "interpro_id": "IPR059271", "known_evidence_count": null, "matches": 254, "name": "Domain of unknown function (DUF8227)", "partial_evidence_count": null, "pfam_id": "PF26678", "proteins": 233, "proteomes": 29, "short_name": "DUF8227", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26678", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of proteins that were formerly part of the DUF3316 family. However, the family contained two unrelated groups of proteins. These members are split into this new family. The domain contains a three stranded beta sheet with a longer and shorter alpha helix packed on one side. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR059442", "known_evidence_count": null, "matches": 233, "name": "Domain of unknown function (DUF8398)", "partial_evidence_count": null, "pfam_id": "PF28439", "proteins": 233, "proteomes": 136, "short_name": "DUF8398", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28439", "structures": 0, "taxa": 188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in uncharacterised plant proteins. From structure predictions, it adopts an OB fold-like configuration.", "domain_architectures": 11, "interpro_id": "IPR061518", "known_evidence_count": null, "matches": 233, "name": "Domain of unknown function (DUF8448)", "partial_evidence_count": null, "pfam_id": "PF28721", "proteins": 233, "proteomes": 37, "short_name": "DUF8448", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28721", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family of uncharacterised archaeal proteins are related to Transglutaminase-like domains. This family has previously been called DUF553 and UPF0252.", "domain_architectures": 20, "interpro_id": "IPR007562", "known_evidence_count": null, "matches": 232, "name": "Transglutaminase-like domain", "partial_evidence_count": null, "pfam_id": "PF04473", "proteins": 232, "proteomes": 187, "short_name": "DUF553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04473", "structures": 0, "taxa": 505, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021702", "known_evidence_count": null, "matches": 232, "name": "Protein of unknown function (DUF3285)", "partial_evidence_count": null, "pfam_id": "PF11688", "proteins": 232, "proteomes": 230, "short_name": "DUF3285", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11688", "structures": 0, "taxa": 646, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length. There is a conserved GRC sequence motif.", "domain_architectures": 1, "interpro_id": "IPR022072", "known_evidence_count": null, "matches": 232, "name": "Protein of unknown function (DUF3624)", "partial_evidence_count": null, "pfam_id": "PF12292", "proteins": 232, "proteomes": 232, "short_name": "DUF3624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12292", "structures": 0, "taxa": 316, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 144 and 206 amino acids in length. The human member of this family is C3orf43.", "domain_architectures": 6, "interpro_id": "IPR027875", "known_evidence_count": null, "matches": 233, "name": "Domain of unknown function (DUF4547)", "partial_evidence_count": null, "pfam_id": "PF15080", "proteins": 232, "proteomes": 202, "short_name": "DUF4547", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15080", "structures": 0, "taxa": 707, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 191, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 99 and 306 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR027908", "known_evidence_count": null, "matches": 259, "name": "Domain of unknown function (DUF4640)", "partial_evidence_count": null, "pfam_id": "PF15480", "proteins": 232, "proteomes": 140, "short_name": "DUF4640", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15480", "structures": 0, "taxa": 438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 220 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032293", "known_evidence_count": null, "matches": 232, "name": "Domain of unknown function (DUF4840)", "partial_evidence_count": null, "pfam_id": "PF16128", "proteins": 232, "proteomes": 194, "short_name": "DUF4840", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16128", "structures": 0, "taxa": 285, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 222, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are approximately 50 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046645", "known_evidence_count": null, "matches": 232, "name": "Family of unknown function (DUF6757)", "partial_evidence_count": null, "pfam_id": "PF20542", "proteins": 232, "proteomes": 232, "short_name": "DUF6757", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20542", "structures": 0, "taxa": 378, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found mainly in actinomycetes. Their function is unknown. They are predicted to adopt OB fold with significant similarity to Rpa.", "domain_architectures": 5, "interpro_id": "IPR054284", "known_evidence_count": null, "matches": 233, "name": "Family of unknown function (DUF7019)", "partial_evidence_count": null, "pfam_id": "PF22880", "proteins": 232, "proteomes": 217, "short_name": "DUF7019", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22880", "structures": 0, "taxa": 381, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 220, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are small and adopt a five stranded beta barrel fold.", "domain_architectures": 2, "interpro_id": "IPR058312", "known_evidence_count": null, "matches": 233, "name": "Family of unknown function (DUF7999)", "partial_evidence_count": null, "pfam_id": "PF26006", "proteins": 232, "proteomes": 104, "short_name": "DUF7999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26006", "structures": 0, "taxa": 156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Chlamydia CHLPS proteins, the function of which are unknown.", "domain_architectures": 9, "interpro_id": "IPR008536", "known_evidence_count": null, "matches": 231, "name": "Chlamydia CHLPS protein (DUF818)", "partial_evidence_count": null, "pfam_id": "PF05677", "proteins": 231, "proteomes": 130, "short_name": "DUF818", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05677", "structures": 0, "taxa": 489, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 215, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from Drosophila melanogaster. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR009961", "known_evidence_count": null, "matches": 233, "name": "Protein of unknown function (DUF1487)", "partial_evidence_count": null, "pfam_id": "PF07368", "proteins": 231, "proteomes": 74, "short_name": "DUF1487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07368", "structures": 0, "taxa": 273, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "These conserved hypothetical proteins have so far been found only in the Cyanobacteria. They are about 170 amino acids long and contain a CxxCx(14)CxxH motif near the N-terminus.", "domain_architectures": 1, "interpro_id": "IPR013472", "known_evidence_count": null, "matches": 231, "name": "Protein of unknown function (DUF2396)", "partial_evidence_count": null, "pfam_id": "PF09654", "proteins": 231, "proteomes": 221, "short_name": "DUF2396", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09654", "structures": 0, "taxa": 616, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "PDB:3D4E shared structural similarity to beta-lactamase inhibitory proteins (BLIP) which already include 1XXM, 1S0W, 1JTG, 2G2U, 2G2W, 2B5R, and 3due. All of structures are involved in beta-lactamase inhibitor complex. (REF http://www.topsan.org/Proteins/JCSG/3d4e)", "domain_architectures": 2, "interpro_id": "IPR024418", "known_evidence_count": null, "matches": 231, "name": "Domain of Unknown Function with PDB structure (DUF3862)", "partial_evidence_count": null, "pfam_id": "PF12978", "proteins": 231, "proteomes": 186, "short_name": "DUF3862", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12978", "structures": 1, "taxa": 331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 105 and 155 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046617", "known_evidence_count": null, "matches": 231, "name": "Family of unknown function (DUF6730)", "partial_evidence_count": null, "pfam_id": "PF20503", "proteins": 231, "proteomes": 131, "short_name": "DUF6730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20503", "structures": 0, "taxa": 188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from actinopterygians that are distantly related and share overall similar domain organisation to the human NEDD4-binding protein 1 (N4BP1). This domain shares a weak sequence similarity to known UBA domains and it is predicted to fold into a typical three helical bundle.", "domain_architectures": 16, "interpro_id": "IPR055498", "known_evidence_count": null, "matches": 231, "name": "Domain of unknown function (DUF7070)", "partial_evidence_count": null, "pfam_id": "PF23255", "proteins": 231, "proteomes": 175, "short_name": "DUF7070", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23255", "structures": 0, "taxa": 614, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 206, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the N-terminal of uncharacterised sequences from Strongyloides species. This domain may consist of a beta-sandwich fold.", "domain_architectures": 20, "interpro_id": "IPR056007", "known_evidence_count": null, "matches": 237, "name": "Domain of unknown function (DUF7585)", "partial_evidence_count": null, "pfam_id": "PF24490", "proteins": 231, "proteomes": 5, "short_name": "DUF7585", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24490", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This very small protein (about 46 amino acids) consists largely of a single predicted membrane-spanning region. It is found in Photobacterium profundum SS9 and in three species of Vibrio, always near periplasmic nitrate reductase genes, but far from the periplasmic nitrate reductase genes in Aeromonas hydrophila ATCC 7966.", "domain_architectures": 1, "interpro_id": "IPR014175", "known_evidence_count": null, "matches": 230, "name": "Protein of unknown function (DUF2374)", "partial_evidence_count": null, "pfam_id": "PF09574", "proteins": 230, "proteomes": 222, "short_name": "DUF2374", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09574", "structures": 0, "taxa": 311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 72 and 107 amino acids in length. There is a conserved VSK sequence motif.", "domain_architectures": 1, "interpro_id": "IPR022069", "known_evidence_count": null, "matches": 230, "name": "Protein of unknown function (DUF3622)", "partial_evidence_count": null, "pfam_id": "PF12286", "proteins": 230, "proteomes": 215, "short_name": "DUF3622", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12286", "structures": 0, "taxa": 334, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is frequently found at the C-terminus of bacterial proteins carrying the family, Metallophos [pfam:PF00149].", "domain_architectures": 46, "interpro_id": "IPR025142", "known_evidence_count": null, "matches": 260, "name": "Domain of unknown function (DUF4073)", "partial_evidence_count": null, "pfam_id": "PF13285", "proteins": 230, "proteomes": 215, "short_name": "DUF4073", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13285", "structures": 0, "taxa": 324, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR035392", "known_evidence_count": null, "matches": 230, "name": "Family of unknown function (DUF5417)", "partial_evidence_count": null, "pfam_id": "PF17438", "proteins": 230, "proteomes": 226, "short_name": "DUF5417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17438", "structures": 0, "taxa": 501, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001740) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the phthoxazolin biosynthetic gene cluster from Streptomyces avermitilis [[cite:PUB00098835]].", "domain_architectures": 1, "interpro_id": "IPR045636", "known_evidence_count": null, "matches": 230, "name": "Family of unknown function (DUF6411)", "partial_evidence_count": null, "pfam_id": "PF19949", "proteins": 230, "proteomes": 222, "short_name": "DUF6411", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19949", "structures": 0, "taxa": 282, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins containing this domain are found predominantly in the Halobacteria class, including families such as Haloferacaceae, Haloarculaceae, and Natrialbaceae. The domain is approximately 160 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058467", "known_evidence_count": null, "matches": 230, "name": "Domain of unknown function (DUF8154)", "partial_evidence_count": null, "pfam_id": "PF26481", "proteins": 230, "proteomes": 146, "short_name": "DUF8154", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26481", "structures": 0, "taxa": 251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae. The family has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR019669", "known_evidence_count": null, "matches": 229, "name": "Protein of unknown function (DUF2525)", "partial_evidence_count": null, "pfam_id": "PF10733", "proteins": 229, "proteomes": 229, "short_name": "DUF2525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10733", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 130 and 224 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031695", "known_evidence_count": null, "matches": 234, "name": "Domain of unknown function (DUF4718)", "partial_evidence_count": null, "pfam_id": "PF15842", "proteins": 229, "proteomes": 142, "short_name": "DUF4718", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15842", "structures": 0, "taxa": 489, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chordata.", "domain_architectures": 3, "interpro_id": "IPR040027", "known_evidence_count": null, "matches": 241, "name": "Family of unknown function (DUF5529)", "partial_evidence_count": null, "pfam_id": "PF17669", "proteins": 229, "proteomes": 219, "short_name": "DUF5529", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17669", "structures": 0, "taxa": 794, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in the central region of Uncharacterized protein 254L from Invertebrate iridescent virus 6. This domain can also be found in cyanobacteria uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR045414", "known_evidence_count": null, "matches": 229, "name": "Domain of unknown function (DUF5895)", "partial_evidence_count": null, "pfam_id": "PF19247", "proteins": 229, "proteomes": 138, "short_name": "DUF5895", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19247", "structures": 0, "taxa": 390, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR055707", "known_evidence_count": null, "matches": 229, "name": "Family of unknown function (DUF7283)", "partial_evidence_count": null, "pfam_id": "PF23954", "proteins": 229, "proteomes": 216, "short_name": "DUF7283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23954", "structures": 0, "taxa": 335, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 221, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in proteins from C. elegans and related sequences from Caenorhabditis species. It may adopt a CUB-like domain fold.", "domain_architectures": 25, "interpro_id": "IPR056013", "known_evidence_count": null, "matches": 247, "name": "Domain of unknown function (DUF7591)", "partial_evidence_count": null, "pfam_id": "PF24511", "proteins": 229, "proteomes": 14, "short_name": "DUF7591", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24511", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a likely uncharacterised phage protein. The protein is composed of three alpha helices.", "domain_architectures": 3, "interpro_id": "IPR056644", "known_evidence_count": null, "matches": 229, "name": "Domain of unknown function (DUF7742)", "partial_evidence_count": null, "pfam_id": "PF24891", "proteins": 229, "proteomes": 229, "short_name": "DUF7742", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24891", "structures": 0, "taxa": 355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 50 residues found in bacterial proteins containing an RNase_T-like exonuclease domain ([pfam:PF00929]). It is found in Bacillota and Pseudomonadota. The function of this domain remains to be determined.", "domain_architectures": 11, "interpro_id": "IPR061687", "known_evidence_count": null, "matches": 229, "name": "Domain of unknown function (DUF8626)", "partial_evidence_count": null, "pfam_id": "PF30557", "proteins": 229, "proteomes": 191, "short_name": "DUF8626", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30557", "structures": 0, "taxa": 505, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021492", "known_evidence_count": null, "matches": 228, "name": "Protein of unknown function (DUF3146)", "partial_evidence_count": null, "pfam_id": "PF11344", "proteins": 228, "proteomes": 227, "short_name": "DUF3146", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11344", "structures": 0, "taxa": 632, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Bacteria, mainly in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR035232", "known_evidence_count": null, "matches": 228, "name": "Family of unknown function (DUF5347)", "partial_evidence_count": null, "pfam_id": "PF17282", "proteins": 228, "proteomes": 182, "short_name": "DUF5347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17282", "structures": 0, "taxa": 307, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A conserved domain of unknown function found in Platyhelminthes, closely related to glycosylphosphatidylinositol (GPI)-anchored protein GP50, known as Diagnostic antigen GP50. GP50 is a family of highly expressed antigens exclusive to tapeworms. This domain, according to structure predictions, seems to consist of two beta-sandwiches.", "domain_architectures": 4, "interpro_id": "IPR043785", "known_evidence_count": null, "matches": 247, "name": "Domain of unknown function (DUF5727)", "partial_evidence_count": null, "pfam_id": "PF18997", "proteins": 228, "proteomes": 9, "short_name": "DUF5727", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18997", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 132 and 168 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046583", "known_evidence_count": null, "matches": 229, "name": "Family of unknown function (DUF6631)", "partial_evidence_count": null, "pfam_id": "PF20336", "proteins": 228, "proteomes": 195, "short_name": "DUF6631", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20336", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in cyanobacteria. Proteins in this family are typically between 225 and 243 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046641", "known_evidence_count": null, "matches": 242, "name": "Family of unknown function (DUF6753)", "partial_evidence_count": null, "pfam_id": "PF20538", "proteins": 228, "proteomes": 117, "short_name": "DUF6753", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20538", "structures": 0, "taxa": 367, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised and is found in fungal sequences, N-terminal to a kinase domain. There are two conserved motifs: PD and QPxR.", "domain_architectures": 16, "interpro_id": "IPR049229", "known_evidence_count": null, "matches": 228, "name": "Domain of unknown function (DUF6826)", "partial_evidence_count": null, "pfam_id": "PF20713", "proteins": 228, "proteomes": 39, "short_name": "DUF6826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20713", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 216, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. They contain two pairs of conserved cysteines that are likely involved in metal coordination. It is predicted to structurally resemble Zinc-beta ribbon domains.", "domain_architectures": 1, "interpro_id": "IPR055981", "known_evidence_count": null, "matches": 228, "name": "Family of unknown function (DUF7559)", "partial_evidence_count": null, "pfam_id": "PF24440", "proteins": 228, "proteomes": 226, "short_name": "DUF7559", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24440", "structures": 0, "taxa": 376, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 213, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins have an immunoglobulin-like domain.", "domain_architectures": 1, "interpro_id": "IPR058280", "known_evidence_count": null, "matches": 228, "name": "Family of unknown function (DUF7974)", "partial_evidence_count": null, "pfam_id": "PF25929", "proteins": 228, "proteomes": 169, "short_name": "DUF7974", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25929", "structures": 0, "taxa": 287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins contain an N-terminal CXXC motif.", "domain_architectures": 1, "interpro_id": "IPR058320", "known_evidence_count": null, "matches": 228, "name": "Family of unknown function (DUF8007)", "partial_evidence_count": null, "pfam_id": "PF26029", "proteins": 228, "proteomes": 228, "short_name": "DUF8007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26029", "structures": 0, "taxa": 361, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 73 and 87 amino acids in length. There are two conserved sequence motifs: KIL and LLLAGLY.", "domain_architectures": 2, "interpro_id": "IPR045765", "known_evidence_count": null, "matches": 227, "name": "Family of unknown function (DUF6133)", "partial_evidence_count": null, "pfam_id": "PF19629", "proteins": 227, "proteomes": 140, "short_name": "DUF6133", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19629", "structures": 0, "taxa": 311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the central alpha helical domain from a large family of uncharacterised phage proteins that typically contain three domains.", "domain_architectures": 6, "interpro_id": "IPR055699", "known_evidence_count": null, "matches": 231, "name": "Domain of unknown function (DUF7275)", "partial_evidence_count": null, "pfam_id": "PF23940", "proteins": 227, "proteomes": 154, "short_name": "DUF7275", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23940", "structures": 0, "taxa": 412, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR055709", "known_evidence_count": null, "matches": 227, "name": "Family of unknown function (DUF7285)", "partial_evidence_count": null, "pfam_id": "PF23956", "proteins": 227, "proteomes": 219, "short_name": "DUF7285", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23956", "structures": 0, "taxa": 346, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 214, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is expressed in Plasmodium; its function is unknown. It may be the product of gene family pyst-b [[cite:PUB00044233]].", "domain_architectures": 3, "interpro_id": "IPR006484", "known_evidence_count": null, "matches": 232, "name": "Protein of unknown function (DUF2031)", "partial_evidence_count": null, "pfam_id": "PF09592", "proteins": 226, "proteomes": 6, "short_name": "DUF2031", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09592", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicute bacteria. Proteins in this family are typically between 388 and 427 amino acids in length. There are two conserved sequence motifs: PEV and DGT.", "domain_architectures": 3, "interpro_id": "IPR045714", "known_evidence_count": null, "matches": 233, "name": "Family of unknown function (DUF6070)", "partial_evidence_count": null, "pfam_id": "PF19546", "proteins": 226, "proteomes": 116, "short_name": "DUF6070", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19546", "structures": 0, "taxa": 199, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001856) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the caniferolide A biosynthetic gene cluster from Streptomyces caniferus [[cite:PUB00099460]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR046187", "known_evidence_count": null, "matches": 227, "name": "Family of unknown function (DUF6215)", "partial_evidence_count": null, "pfam_id": "PF19721", "proteins": 226, "proteomes": 220, "short_name": "DUF6215", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19721", "structures": 0, "taxa": 252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal beta sandwich domain found in the DUF6242 family of proteins. The C-terminal domain has a beta propeller structure.", "domain_architectures": 5, "interpro_id": "IPR046209", "known_evidence_count": null, "matches": 226, "name": "Domain of unknown function (DUF6242) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF19755", "proteins": 226, "proteomes": 221, "short_name": "DUF6242", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19755", "structures": 3, "taxa": 357, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain consisting of TPR repeats found at the N-terminal of of group of uncharacterised sequences predominantly from bacteria, which seem to be related to TOTE conflict systems as they are associated with [pfam:PF22708].", "domain_architectures": 17, "interpro_id": "IPR054283", "known_evidence_count": null, "matches": 226, "name": "Domain of unknown function (DUF7017)", "partial_evidence_count": null, "pfam_id": "PF22860", "proteins": 226, "proteomes": 219, "short_name": "DUF7017", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22860", "structures": 0, "taxa": 680, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 220, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 2, "interpro_id": "IPR058281", "known_evidence_count": null, "matches": 231, "name": "Family of unknown function (DUF7975)", "partial_evidence_count": null, "pfam_id": "PF25930", "proteins": 226, "proteomes": 223, "short_name": "DUF7975", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25930", "structures": 0, "taxa": 355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 217, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins have four predicted transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR058307", "known_evidence_count": null, "matches": 226, "name": "Family of unknown function (DUF7994)", "partial_evidence_count": null, "pfam_id": "PF25957", "proteins": 226, "proteomes": 152, "short_name": "DUF7994", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25957", "structures": 0, "taxa": 276, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins predominantly found in the Mycobacteriaceae family. The proteins in this family are primarily distributed across various species of Mycobacterium and Mycolicibacterium. The domain is typically found in proteins ranging from approximately 160 to 230 amino acids in length. Many of these proteins are predicted to be membrane-associated, as suggested by the presence of transmembrane helices. The precise function of this domain remains unknown. This domain belongs to the NTF2 superfamily.", "domain_architectures": 1, "interpro_id": "IPR058487", "known_evidence_count": null, "matches": 226, "name": "Domain of unknown function (DUF8174)", "partial_evidence_count": null, "pfam_id": "PF26525", "proteins": 226, "proteomes": 226, "short_name": "DUF8174", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26525", "structures": 0, "taxa": 256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is usually flanked by domains predicted as transmembrane. This domain is predicted to fold into a globular structure composed of a open barrel decorated with alpha-helices.", "domain_architectures": 9, "interpro_id": "IPR059464", "known_evidence_count": null, "matches": 226, "name": "Domain of unknown function (DUF8420)", "partial_evidence_count": null, "pfam_id": "PF28511", "proteins": 226, "proteomes": 124, "short_name": "DUF8420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28511", "structures": 0, "taxa": 230, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 40 residues found in anti-sigma factor antagonist proteins from spirochaetes, predominantly from Treponema and Leptospira species. The domain contains conserved cysteine residues in a CPIC...CSEC motif, suggesting potential metal binding. Anti-sigma factor antagonist proteins regulate sigma factor activity in bacterial stress responses. The protein TP0233 from Treponema pallidum has been shown to interact with flagellar motor components [[cite:PUB00163734]]. The specific function of this domain remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061582", "known_evidence_count": null, "matches": 226, "name": "Domain of unknown function (DUF8512)", "partial_evidence_count": null, "pfam_id": "PF29210", "proteins": 226, "proteomes": 122, "short_name": "DUF8512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29210", "structures": 0, "taxa": 234, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 87, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Siphovirus and Lactococcus proteins of unknown function. The viral sequences are thought to be tail component proteins.", "domain_architectures": 1, "interpro_id": "IPR008524", "known_evidence_count": null, "matches": 225, "name": "Protein of unknown function (DUF806)", "partial_evidence_count": null, "pfam_id": "PF05657", "proteins": 225, "proteomes": 211, "short_name": "DUF806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05657", "structures": 0, "taxa": 414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000399) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This family includes a protein from the orfamide A biosynthetic gene cluster from Pseudomonas protegens Pf-5 and appears to be predominantly found in Pseudomonadaceae [[cite:PUB00099440]].", "domain_architectures": 1, "interpro_id": "IPR046063", "known_evidence_count": null, "matches": 225, "name": "Family of unknown function (DUF6021)", "partial_evidence_count": null, "pfam_id": "PF19485", "proteins": 225, "proteomes": 224, "short_name": "DUF6021", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19485", "structures": 0, "taxa": 256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in cyanobacteria. Proteins in this family are typically between 87 and 98 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045511", "known_evidence_count": null, "matches": 225, "name": "Family of unknown function (DUF6439)", "partial_evidence_count": null, "pfam_id": "PF20035", "proteins": 225, "proteomes": 225, "short_name": "DUF6439", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20035", "structures": 0, "taxa": 615, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are composed of two tandem domains with similarity to SH3 domains, in particular to YorP.", "domain_architectures": 2, "interpro_id": "IPR053804", "known_evidence_count": null, "matches": 226, "name": "Family of unknown function (DUF6960)", "partial_evidence_count": null, "pfam_id": "PF22283", "proteins": 225, "proteomes": 222, "short_name": "DUF6960", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22283", "structures": 0, "taxa": 381, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 218, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins from Halobacteria. They are predicted to fold into a single alpha-helix and contain a highly conserved LYxGYG sequence motif.", "domain_architectures": 1, "interpro_id": "IPR055934", "known_evidence_count": null, "matches": 225, "name": "Family of unknown function (DUF7512)", "partial_evidence_count": null, "pfam_id": "PF24352", "proteins": 225, "proteomes": 185, "short_name": "DUF7512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24352", "structures": 0, "taxa": 315, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 219, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised halobacterial proteins that adopt a small beta sandwich domain structure with a glycine rich C-terminal tail.", "domain_architectures": 2, "interpro_id": "IPR058275", "known_evidence_count": null, "matches": 309, "name": "Domain of unknown function (DUF7969)", "partial_evidence_count": null, "pfam_id": "PF25923", "proteins": 225, "proteomes": 225, "short_name": "DUF7969", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25923", "structures": 0, "taxa": 360, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of very small uncharacterised proteins of approximately 60 residues found exclusively in cyanobacteria. The family is widely distributed across the phylum, including members of the orders Nostocales, Oscillatoriales, Synechococcales, and Chroococcales. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061682", "known_evidence_count": null, "matches": 225, "name": "Domain of unknown function (DUF8621)", "partial_evidence_count": null, "pfam_id": "PF30531", "proteins": 225, "proteomes": 220, "short_name": "DUF8621", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30531", "structures": 0, "taxa": 599, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of some uncharacterized proteins around 60 residues in length and is mainly found in various Lactobacillus and Selenomonas species. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR032488", "known_evidence_count": null, "matches": 224, "name": "Domain of unknown function (DUF5049)", "partial_evidence_count": null, "pfam_id": "PF16468", "proteins": 224, "proteomes": 190, "short_name": "DUF5049", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16468", "structures": 0, "taxa": 528, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Gammaproteobacteria. Proteins in this family are approximately 120 amino acids in length. There are two conserved motifs, LxxxYG and Y/FT/SxxQI/V.", "domain_architectures": 1, "interpro_id": "IPR046689", "known_evidence_count": null, "matches": 224, "name": "Family of unknown function (DUF6559)", "partial_evidence_count": null, "pfam_id": "PF20196", "proteins": 224, "proteomes": 190, "short_name": "DUF6559", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20196", "structures": 0, "taxa": 386, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 168, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 205 and 301 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046596", "known_evidence_count": null, "matches": 224, "name": "Family of unknown function (DUF6655)", "partial_evidence_count": null, "pfam_id": "PF20360", "proteins": 224, "proteomes": 190, "short_name": "DUF6655", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20360", "structures": 0, "taxa": 350, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a coiled-coil region found in uncharacterised archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR055734", "known_evidence_count": null, "matches": 224, "name": "Coiled-coil region of unknown function (DUF7310)", "partial_evidence_count": null, "pfam_id": "PF23991", "proteins": 224, "proteomes": 217, "short_name": "DUF7310", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23991", "structures": 0, "taxa": 363, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 149, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Streptococcus.", "domain_architectures": 1, "interpro_id": "IPR021688", "known_evidence_count": null, "matches": 223, "name": "Protein of unknown function (DUF3270)", "partial_evidence_count": null, "pfam_id": "PF11674", "proteins": 223, "proteomes": 207, "short_name": "DUF3270", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11674", "structures": 0, "taxa": 301, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 143 and 164 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031674", "known_evidence_count": null, "matches": 227, "name": "Domain of unknown function (DUF4714)", "partial_evidence_count": null, "pfam_id": "PF15833", "proteins": 223, "proteomes": 181, "short_name": "DUF4714", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15833", "structures": 0, "taxa": 629, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is mainly found in phages. It may represent structural phage proteins. There are several conserved motifs: FxxI, GxxxxP and FSxxxxP, and also 7 additional conserved Glycine residues.", "domain_architectures": 3, "interpro_id": "IPR045604", "known_evidence_count": null, "matches": 223, "name": "Family of unknown function (DUF6453)", "partial_evidence_count": null, "pfam_id": "PF20051", "proteins": 223, "proteomes": 201, "short_name": "DUF6453", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20051", "structures": 3, "taxa": 463, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046724", "known_evidence_count": null, "matches": 223, "name": "Family of unknown function (DUF6616)", "partial_evidence_count": null, "pfam_id": "PF20321", "proteins": 223, "proteomes": 220, "short_name": "DUF6616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20321", "structures": 0, "taxa": 435, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 190 and 350 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046553", "known_evidence_count": null, "matches": 223, "name": "Family of unknown function (DUF6707)", "partial_evidence_count": null, "pfam_id": "PF20453", "proteins": 223, "proteomes": 216, "short_name": "DUF6707", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20453", "structures": 0, "taxa": 358, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 182, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt beta-Trefoil fold.", "domain_architectures": 9, "interpro_id": "IPR057231", "known_evidence_count": null, "matches": 224, "name": "Domain of unknown function (DUF7909)", "partial_evidence_count": null, "pfam_id": "PF25486", "proteins": 223, "proteomes": 201, "short_name": "DUF7909", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25486", "structures": 0, "taxa": 420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins mainly from Moraxellales. It is predicted to fold into an array of alpha-helices. It contains two invariant cysteine residues which are predicted to form a disulfide bond.", "domain_architectures": 1, "interpro_id": "IPR057704", "known_evidence_count": null, "matches": 223, "name": "Domain of unknown function (DUF7944)", "partial_evidence_count": null, "pfam_id": "PF25642", "proteins": 223, "proteomes": 150, "short_name": "DUF7944", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25642", "structures": 0, "taxa": 198, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins usually contain a likely C-terminal transmembrane alpha helix.", "domain_architectures": 1, "interpro_id": "IPR058342", "known_evidence_count": null, "matches": 223, "name": "Family of unknown function (DUF8029)", "partial_evidence_count": null, "pfam_id": "PF26072", "proteins": 223, "proteomes": 221, "short_name": "DUF8029", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26072", "structures": 0, "taxa": 341, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058373", "known_evidence_count": null, "matches": 223, "name": "Domain of unknown function (DUF8060)", "partial_evidence_count": null, "pfam_id": "PF26256", "proteins": 223, "proteomes": 221, "short_name": "DUF8060", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26256", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal zinc-binding domain found in a family of uncharacterised proteins from halophilic archaea. The proteins are predominantly found in the Halobacteria class, including families such as Haloferacaceae, Haloarculaceae, and Natrialbaceae. The proteins in this family are typically around 150 to 230 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR058448", "known_evidence_count": null, "matches": 223, "name": "Domain of unknown function (DUF8135)", "partial_evidence_count": null, "pfam_id": "PF26456", "proteins": 223, "proteomes": 223, "short_name": "DUF8135", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26456", "structures": 0, "taxa": 342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains several highly conserved cysteine and histidine residues that may coordinate a metal ion. These residues come close in space and are predicted to form substructures each of which is reminiscent of treble-clef zinc fingers.", "domain_architectures": 10, "interpro_id": "IPR059465", "known_evidence_count": null, "matches": 271, "name": "Domain of unknown function (DUF8421)", "partial_evidence_count": null, "pfam_id": "PF28513", "proteins": 223, "proteomes": 216, "short_name": "DUF8421", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28513", "structures": 0, "taxa": 397, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram negative bacteria which are probably related to the RND tripartite drug efflux pumps. The domain represented in this entry folds into a six-stranded closed beta-barrel with a greek-key topology which has a structural similarity to the C-terminal domain of alanine racemase. This domain is interrupted by the barrel-sandwich hybrid domain which is inserted after the first beta-strand of the barrel. This model does not include the N-terminal strand.", "domain_architectures": 17, "interpro_id": "IPR061552", "known_evidence_count": null, "matches": 223, "name": "Domain of unknown function (DUF8482)", "partial_evidence_count": null, "pfam_id": "PF28935", "proteins": 223, "proteomes": 209, "short_name": "DUF8482", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28935", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins have no known function.", "domain_architectures": 4, "interpro_id": "IPR020075", "known_evidence_count": null, "matches": 222, "name": "Protein of unknown function (DUF2769)", "partial_evidence_count": null, "pfam_id": "PF10967", "proteins": 222, "proteomes": 95, "short_name": "DUF2769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10967", "structures": 0, "taxa": 200, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 204, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as multi-transmembrane proteins however this cannot be confirmed. Currently this family has no known function.", "domain_architectures": 2, "interpro_id": "IPR021691", "known_evidence_count": null, "matches": 226, "name": "Protein of unknown function (DUF3273)", "partial_evidence_count": null, "pfam_id": "PF11677", "proteins": 222, "proteomes": 61, "short_name": "DUF3273", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11677", "structures": 0, "taxa": 119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001285) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a protein from the pseudopyronine A biosynthetic gene cluster from Pseudomonas putida and appears to be predominantly found in Pseudomonas [[cite:PUB00099447]].", "domain_architectures": 1, "interpro_id": "IPR046068", "known_evidence_count": null, "matches": 222, "name": "Family of unknown function (DUF6026)", "partial_evidence_count": null, "pfam_id": "PF19491", "proteins": 222, "proteomes": 222, "short_name": "DUF6026", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19491", "structures": 0, "taxa": 244, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 209, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. These proteins are likely associated with the membrane. They are predicted to fold into a single helix.", "domain_architectures": 1, "interpro_id": "IPR055976", "known_evidence_count": null, "matches": 222, "name": "Family of unknown function (DUF7554)", "partial_evidence_count": null, "pfam_id": "PF24431", "proteins": 222, "proteomes": 222, "short_name": "DUF7554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24431", "structures": 0, "taxa": 352, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family consists of several short hypothetical Enterobacteria proteins of unknown function. Structural analysis of the surface features of the protein YvyC has revealed a single cluster of highly conserved residues on the surface. Additionally, these residues fall into two groups which lie within the two largest of the three cavities identified over the surface. The conclusion from this is that these two cavities with, Leu 58, Glu 75, Ile 82, and Glu 83 and Pro 86, conserved, are likely to be important for the molecular function and reflect the cavities found on the surface of the FlaG proteins in [pfam:PF03646].", "domain_architectures": 3, "interpro_id": "IPR009253", "known_evidence_count": null, "matches": 221, "name": "Bacterial protein of unknown function (DUF905)", "partial_evidence_count": null, "pfam_id": "PF06006", "proteins": 221, "proteomes": 132, "short_name": "DUF905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06006", "structures": 1, "taxa": 241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this protein is unknown. It is always found as part of a two-gene operon with IPR013416, a protein that appears to span the membrane seven times. It has so far been found in the bacteria Nostoc sp. PCC 7120, Agrobacterium tumefaciens, Rhizobium meliloti, and Gloeobacter violaceus.", "domain_architectures": 1, "interpro_id": "IPR013417", "known_evidence_count": null, "matches": 221, "name": "Protein of unknown function (DUF2393)", "partial_evidence_count": null, "pfam_id": "PF09624", "proteins": 221, "proteomes": 155, "short_name": "DUF2393", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09624", "structures": 0, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function is restricted to Enterobacteriaceae. The family has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR019671", "known_evidence_count": null, "matches": 221, "name": "Protein of unknown function (DUF2526)", "partial_evidence_count": null, "pfam_id": "PF10735", "proteins": 221, "proteomes": 221, "short_name": "DUF2526", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10735", "structures": 0, "taxa": 367, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 197, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021577", "known_evidence_count": null, "matches": 221, "name": "Protein of unknown function (DUF3209)", "partial_evidence_count": null, "pfam_id": "PF11483", "proteins": 221, "proteomes": 220, "short_name": "DUF3209", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11483", "structures": 1, "taxa": 394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 101 and 269 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025144", "known_evidence_count": null, "matches": 221, "name": "Protein of unknown function (DUF4085)", "partial_evidence_count": null, "pfam_id": "PF13315", "proteins": 221, "proteomes": 204, "short_name": "DUF4085", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13315", "structures": 0, "taxa": 360, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 244 and 363 amino acids in length. There is a conserved WEL sequence motif.", "domain_architectures": 7, "interpro_id": "IPR032064", "known_evidence_count": null, "matches": 223, "name": "Domain of unknown function (DUF4805)", "partial_evidence_count": null, "pfam_id": "PF16063", "proteins": 221, "proteomes": 169, "short_name": "DUF4805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16063", "structures": 0, "taxa": 630, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Alveolata species. It has a remote similarity to various Poly(ADP-ribose) polymerases PARPs and two of the residues involved in catalysis (His and Tyr) are conserved. The Af2 predicted models of many the members are not of a good quality.", "domain_architectures": 79, "interpro_id": "IPR059323", "known_evidence_count": null, "matches": 228, "name": "Domain of unknown function (DUF8279)", "partial_evidence_count": null, "pfam_id": "PF26928", "proteins": 221, "proteomes": 10, "short_name": "DUF8279", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26928", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins represents a fungal protein with unknown function.", "domain_architectures": 4, "interpro_id": "IPR021706", "known_evidence_count": null, "matches": 220, "name": "Protein of unknown function (DUF2990)", "partial_evidence_count": null, "pfam_id": "PF11693", "proteins": 220, "proteomes": 220, "short_name": "DUF2990", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11693", "structures": 0, "taxa": 378, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 143 and 191 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR027978", "known_evidence_count": null, "matches": 221, "name": "Domain of unknown function (DUF4644)", "partial_evidence_count": null, "pfam_id": "PF15486", "proteins": 220, "proteomes": 144, "short_name": "DUF4644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15486", "structures": 0, "taxa": 463, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 136, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and viruses. Proteins in this family are typically between 89 and 148 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR043720", "known_evidence_count": null, "matches": 220, "name": "Protein of unknown function (DUF5661)", "partial_evidence_count": null, "pfam_id": "PF18905", "proteins": 220, "proteomes": 212, "short_name": "DUF5661", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18905", "structures": 0, "taxa": 462, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 104, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a beta-barrel that has some similarity to the replication focus targeting sequence (RFTS) domain of Dnmt1 methyltransferase 1.", "domain_architectures": 1, "interpro_id": "IPR054232", "known_evidence_count": null, "matches": 220, "name": "Domain of unknown function (DUF6957)", "partial_evidence_count": null, "pfam_id": "PF22275", "proteins": 220, "proteomes": 172, "short_name": "DUF6957", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22275", "structures": 0, "taxa": 264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a Ig-like domain found in a group of uncharacterised sequences, mainly from archaea.", "domain_architectures": 2, "interpro_id": "IPR055806", "known_evidence_count": null, "matches": 220, "name": "Domain of unknown function (DUF7382)", "partial_evidence_count": null, "pfam_id": "PF24107", "proteins": 220, "proteomes": 215, "short_name": "DUF7382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24107", "structures": 0, "taxa": 333, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 136 and 171 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025462", "known_evidence_count": null, "matches": 223, "name": "Domain of unknown function (DUF4313)", "partial_evidence_count": null, "pfam_id": "PF14190", "proteins": 219, "proteomes": 156, "short_name": "DUF4313", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14190", "structures": 0, "taxa": 312, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 520 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032276", "known_evidence_count": null, "matches": 226, "name": "Domain of unknown function (DUF4836)", "partial_evidence_count": null, "pfam_id": "PF16120", "proteins": 219, "proteomes": 211, "short_name": "DUF4836", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16120", "structures": 0, "taxa": 361, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small putative integral membrane proteins with two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR054198", "known_evidence_count": null, "matches": 219, "name": "Family of unknown function (DUF6903)", "partial_evidence_count": null, "pfam_id": "PF21844", "proteins": 219, "proteomes": 219, "short_name": "DUF6903", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21844", "structures": 0, "taxa": 408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 206, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found mainly in Halobacteria. They are predicted to adopt a structure consisting of four alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR055963", "known_evidence_count": null, "matches": 219, "name": "Family of unknown function (DUF7541)", "partial_evidence_count": null, "pfam_id": "PF24396", "proteins": 219, "proteomes": 193, "short_name": "DUF7541", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24396", "structures": 0, "taxa": 310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. Proteins in this family contain two conserved transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058293", "known_evidence_count": null, "matches": 219, "name": "Family of unknown function (DUF7987)", "partial_evidence_count": null, "pfam_id": "PF25949", "proteins": 219, "proteomes": 162, "short_name": "DUF7987", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25949", "structures": 0, "taxa": 272, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_2286, a putative uncharacterized protein. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or other bacterial species vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 3, "interpro_id": "IPR024356", "known_evidence_count": null, "matches": 218, "name": "Domain of unknown function, B. Theta Gene description (DUF3873)", "partial_evidence_count": null, "pfam_id": "PF12989", "proteins": 218, "proteomes": 123, "short_name": "DUF3873", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12989", "structures": 0, "taxa": 217, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Gammaproteobacteri.", "domain_architectures": 2, "interpro_id": "IPR035292", "known_evidence_count": null, "matches": 218, "name": "Family of unknown function (DUF5363)", "partial_evidence_count": null, "pfam_id": "PF17320", "proteins": 218, "proteomes": 218, "short_name": "DUF5363", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17320", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are uncharacterised. This family is distantly related to [pfam:PF06853] currently known as DUF1249.", "domain_architectures": 30, "interpro_id": "IPR054203", "known_evidence_count": null, "matches": 218, "name": "Domain of unknown function (DUF6908)", "partial_evidence_count": null, "pfam_id": "PF21849", "proteins": 218, "proteomes": 167, "short_name": "DUF6908", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21849", "structures": 0, "taxa": 485, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 210, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-beta structure.", "domain_architectures": 2, "interpro_id": "IPR055954", "known_evidence_count": null, "matches": 219, "name": "Family of unknown function (DUF7532)", "partial_evidence_count": null, "pfam_id": "PF24376", "proteins": 218, "proteomes": 218, "short_name": "DUF7532", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24376", "structures": 0, "taxa": 345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 205, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins from halobacteria. Members are around 284 residues and are predicted to adopt a mainly beta configuration an the N-terminal and show short alpha helices in the C-terminal.", "domain_architectures": 3, "interpro_id": "IPR057179", "known_evidence_count": null, "matches": 218, "name": "Family of unknown function (DUF7857)", "partial_evidence_count": null, "pfam_id": "PF25256", "proteins": 218, "proteomes": 211, "short_name": "DUF7857", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25256", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 210, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins are predominantly found in the Halobacteria class, including families such as Haloferacaceae and Natrialbaceae. The domain is approximately 70 amino acids in length. Reviewed UniProt entry Q18JS4 from Haloquadratum walsbyi contains this domain. This domain is likely to be zinc binding based on conservation of cysteine and histidine residues.", "domain_architectures": 1, "interpro_id": "IPR058462", "known_evidence_count": null, "matches": 218, "name": "Domain of unknown function (DUF8149)", "partial_evidence_count": null, "pfam_id": "PF26476", "proteins": 218, "proteomes": 217, "short_name": "DUF8149", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26476", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 136, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from gram-negative bacteria. It contains highly conserved histidine and three cysteine residues arranged in HCCC pattern. These residues are predicted to be located in proximity and likely to coordinate a metal ion. This domain is usually found preceding HNH nuclease domain.", "domain_architectures": 3, "interpro_id": "IPR059289", "known_evidence_count": null, "matches": 218, "name": "Domain of unknown function (DUF8245)", "partial_evidence_count": null, "pfam_id": "PF26739", "proteins": 218, "proteomes": 214, "short_name": "DUF8245", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26739", "structures": 0, "taxa": 517, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 211, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 8, "interpro_id": "IPR004950", "known_evidence_count": null, "matches": 228, "name": "Caenorhabditis protein of unknown function, DUF267", "partial_evidence_count": null, "pfam_id": "PF03268", "proteins": 217, "proteomes": 49, "short_name": "DUF267", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03268", "structures": 0, "taxa": 127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Cyanobacteria. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019728", "known_evidence_count": null, "matches": 217, "name": "Protein of unknown function (DUF2605)", "partial_evidence_count": null, "pfam_id": "PF10792", "proteins": 217, "proteomes": 215, "short_name": "DUF2605", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10792", "structures": 0, "taxa": 593, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between and 178 amino acids in length. The human member of this family is C1orf105.", "domain_architectures": 6, "interpro_id": "IPR027845", "known_evidence_count": null, "matches": 225, "name": "Domain of unknown function (DUF4548)", "partial_evidence_count": null, "pfam_id": "PF15081", "proteins": 217, "proteomes": 123, "short_name": "DUF4548", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15081", "structures": 0, "taxa": 394, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 196 and 244 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR027955", "known_evidence_count": null, "matches": 220, "name": "Domain of unknown function (DUF4636)", "partial_evidence_count": null, "pfam_id": "PF15468", "proteins": 217, "proteomes": 185, "short_name": "DUF4636", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15468", "structures": 0, "taxa": 634, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 200 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046597", "known_evidence_count": null, "matches": 218, "name": "Family of unknown function (DUF6656)", "partial_evidence_count": null, "pfam_id": "PF20361", "proteins": 217, "proteomes": 206, "short_name": "DUF6656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20361", "structures": 0, "taxa": 265, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. There are two conserved sequence motifs: YFKAF and FRVSTG.", "domain_architectures": 1, "interpro_id": "IPR046635", "known_evidence_count": null, "matches": 217, "name": "Family of unknown function (DUF6747)", "partial_evidence_count": null, "pfam_id": "PF20532", "proteins": 217, "proteomes": 85, "short_name": "DUF6747", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20532", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 206, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an all-alpha structure.", "domain_architectures": 4, "interpro_id": "IPR055952", "known_evidence_count": null, "matches": 221, "name": "Family of unknown function (DUF7530)", "partial_evidence_count": null, "pfam_id": "PF24374", "proteins": 217, "proteomes": 215, "short_name": "DUF7530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24374", "structures": 0, "taxa": 345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a GNAT-like domain found at the N-terminal of uncharacterised sequences from nematodes.", "domain_architectures": 9, "interpro_id": "IPR056017", "known_evidence_count": null, "matches": 219, "name": "Domain of unknown function (DUF7596)", "partial_evidence_count": null, "pfam_id": "PF24524", "proteins": 217, "proteomes": 106, "short_name": "DUF7596", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24524", "structures": 0, "taxa": 232, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins found in Bacteroidales species.", "domain_architectures": 4, "interpro_id": "IPR024339", "known_evidence_count": null, "matches": 217, "name": "Family of unknown function (DUF3836)", "partial_evidence_count": null, "pfam_id": "PF12930", "proteins": 216, "proteomes": 98, "short_name": "DUF3836", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12930", "structures": 3, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 126, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 200 residues locates in the N-terminal of some uncharacterised proteins in various Bacteroides and Alistipes species. The function of this family remains unknown. The N-terminus of this model has been clipped by ~30 residues as it was capturing parts of collagen sequences, [pfam:PF01391].", "domain_architectures": 42, "interpro_id": "IPR032149", "known_evidence_count": null, "matches": 243, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16378", "proteins": 216, "proteomes": 88, "short_name": "DUF4988", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16378", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in proteobacteria. Proteins in this family are tipically between 95 and 160 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046651", "known_evidence_count": null, "matches": 216, "name": "Family of unknown function (DUF6763)", "partial_evidence_count": null, "pfam_id": "PF20549", "proteins": 216, "proteomes": 193, "short_name": "DUF6763", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20549", "structures": 0, "taxa": 364, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in bacteria and eukaryotes. These proteins are probably distantly related to HIT-containing uridylyltransferases and are likely to adopt the same structure.", "domain_architectures": 10, "interpro_id": "IPR054220", "known_evidence_count": null, "matches": 222, "name": "Family of unknown function (DUF6940)", "partial_evidence_count": null, "pfam_id": "PF22086", "proteins": 216, "proteomes": 162, "short_name": "DUF6940", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22086", "structures": 0, "taxa": 586, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found mainly in Proteobacteria. It is likely to consists of two domains that engage in extensive contacts mainly via hydrophobic residues. The predicted structure of the N-terminal domain has similarity to chorismatases.", "domain_architectures": 1, "interpro_id": "IPR054249", "known_evidence_count": null, "matches": 216, "name": "Family of unknown function (DUF6976)", "partial_evidence_count": null, "pfam_id": "PF22396", "proteins": 216, "proteomes": 197, "short_name": "DUF6976", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22396", "structures": 0, "taxa": 486, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 199, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry represents a four helical integral membrane domain found in nematode species. The function of this domain is unknown.", "domain_architectures": 9, "interpro_id": "IPR055514", "known_evidence_count": null, "matches": 219, "name": "Integral membrane domain of unknown function (DUF7087)", "partial_evidence_count": null, "pfam_id": "PF23346", "proteins": 216, "proteomes": 74, "short_name": "DUF7087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23346", "structures": 0, "taxa": 176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 203, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins.", "domain_architectures": 2, "interpro_id": "IPR055735", "known_evidence_count": null, "matches": 218, "name": "Domain of unknown function (DUF7311)", "partial_evidence_count": null, "pfam_id": "PF23993", "proteins": 216, "proteomes": 208, "short_name": "DUF7311", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23993", "structures": 0, "taxa": 324, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a HTH-like domain found in uncharacterised sequences from fungi.", "domain_architectures": 9, "interpro_id": "IPR056043", "known_evidence_count": null, "matches": 216, "name": "Domain of unknown function (DUF7626)", "partial_evidence_count": null, "pfam_id": "PF24625", "proteins": 216, "proteomes": 204, "short_name": "DUF7626", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24625", "structures": 0, "taxa": 494, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 610 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 3, "interpro_id": "IPR032313", "known_evidence_count": null, "matches": 215, "name": "Domain of unknown function (DUF4980)", "partial_evidence_count": null, "pfam_id": "PF16352", "proteins": 215, "proteomes": 182, "short_name": "DUF4980", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16352", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised prokaryotic proteins. These proteins share a common semi-conserved EExxWY sequence motif which is predicted as a solvent-exposed in a alpha/beta structure consisting of a four-stranded antiparallel beta-sheet and alpha-helices packed on one side of it.", "domain_architectures": 2, "interpro_id": "IPR056097", "known_evidence_count": null, "matches": 215, "name": "Domain of unknown function (DUF7680)", "partial_evidence_count": null, "pfam_id": "PF24728", "proteins": 215, "proteomes": 198, "short_name": "DUF7680", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24728", "structures": 0, "taxa": 579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Two structures have been solved form this DUF, PDB:4mjf and PDB:3sbu. TOPSAN records that both proteins are the only structural representatives of Pfam PF14254, DUF4348. There are no other significant hits in FFAS. DUF4348 has ~200 proteins, all from Bacteroidetes, and all with a single domain architecture with just one DUF4348 domain. There appears to be a possible gene duplication in the protein as the N-terminal domain (approx residues 25-174) and C-terminal domain (approx residues 175-286) superimpose quite well with ~1.9A r.m.s.d. and ~30% sequence identity.", "domain_architectures": 3, "interpro_id": "IPR025590", "known_evidence_count": null, "matches": 214, "name": "Domain of unknown function (DUF4348)", "partial_evidence_count": null, "pfam_id": "PF14254", "proteins": 214, "proteomes": 212, "short_name": "DUF4348", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14254", "structures": 2, "taxa": 344, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 115 and 155 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046557", "known_evidence_count": null, "matches": 214, "name": "Family of unknown function (DUF6711)", "partial_evidence_count": null, "pfam_id": "PF20458", "proteins": 214, "proteomes": 204, "short_name": "DUF6711", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20458", "structures": 0, "taxa": 439, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 212, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically around 520 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR046628", "known_evidence_count": null, "matches": 223, "name": "Family of unknown function (DUF6740)", "partial_evidence_count": null, "pfam_id": "PF20525", "proteins": 214, "proteomes": 3, "short_name": "DUF6740", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20525", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in uncharacterised sequences from Caenorhabditis spp. In SwissProt:O45754, it represents the second domain. It may adopt a CUB-like fold.", "domain_architectures": 23, "interpro_id": "IPR056014", "known_evidence_count": null, "matches": 231, "name": "Domain of unknown function (DUF7592)", "partial_evidence_count": null, "pfam_id": "PF24512", "proteins": 214, "proteomes": 14, "short_name": "DUF7592", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24512", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 169, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of a group of uncharacterised plant proteins. It is often found associated to [pfam:PF06839]. It has a conserved motif GWQK.", "domain_architectures": 12, "interpro_id": "IPR057222", "known_evidence_count": null, "matches": 214, "name": "Domain of unknown function (DUF7900)", "partial_evidence_count": null, "pfam_id": "PF25464", "proteins": 214, "proteomes": 22, "short_name": "DUF7900", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25464", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 208, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins containing this domain are predominantly found in the class Halobacteria, which are known for their extreme halophilic nature. The domain is typically found in proteins ranging from 59 to 80 amino acids in length. Proteins containing this domain are predicted to be integral membrane proteins, as suggested by the presence of multiple transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058420", "known_evidence_count": null, "matches": 214, "name": "Domain of unknown function (DUF8107)", "partial_evidence_count": null, "pfam_id": "PF26409", "proteins": 214, "proteomes": 214, "short_name": "DUF8107", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26409", "structures": 0, "taxa": 341, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is composed of hypothetical bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR012873", "known_evidence_count": null, "matches": 213, "name": "Protein of unknown function (DUF1672)", "partial_evidence_count": null, "pfam_id": "PF07901", "proteins": 213, "proteomes": 98, "short_name": "DUF1672", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07901", "structures": 1, "taxa": 178, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This short domain is sometimes found N terminal to [pfam:PF03981].", "domain_architectures": 4, "interpro_id": "IPR025217", "known_evidence_count": null, "matches": 213, "name": "Domain of unknown function (DUF3944)", "partial_evidence_count": null, "pfam_id": "PF13099", "proteins": 213, "proteomes": 194, "short_name": "DUF3944", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13099", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a immunoglobulin-like domain found in a functionally uncharacterised protein family. This family of proteins is found in vertebrates and includes human protein C1orf127.", "domain_architectures": 5, "interpro_id": "IPR049521", "known_evidence_count": null, "matches": 215, "name": "Domain of unknown function (DUF4556), Ig-like", "partial_evidence_count": null, "pfam_id": "PF15094", "proteins": 213, "proteomes": 160, "short_name": "DUF4556", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15094", "structures": 0, "taxa": 608, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 168, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes.", "domain_architectures": 5, "interpro_id": "IPR027919", "known_evidence_count": null, "matches": 218, "name": "Domain of unknown function (DUF4568)", "partial_evidence_count": null, "pfam_id": "PF15132", "proteins": 213, "proteomes": 120, "short_name": "DUF4568", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15132", "structures": 0, "taxa": 391, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is primarily found in Firmicute bacteria. Proteins in this family are typically between 251 and 390 amino acids in length. These proteins contain 4 conserved cysteines suggestive of a zinc-binding motif.", "domain_architectures": 1, "interpro_id": "IPR045722", "known_evidence_count": null, "matches": 213, "name": "Family of unknown function (DUF6076)", "partial_evidence_count": null, "pfam_id": "PF19553", "proteins": 213, "proteomes": 143, "short_name": "DUF6076", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19553", "structures": 0, "taxa": 333, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 136, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 120 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046502", "known_evidence_count": null, "matches": 213, "name": "Family of unknown function (DUF6680)", "partial_evidence_count": null, "pfam_id": "PF20385", "proteins": 213, "proteomes": 207, "short_name": "DUF6680", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20385", "structures": 0, "taxa": 594, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, and is around 250 amino acids in length. There is a conserved sequence motif GHSLGG. It may have an alpha/beta hydrolase fold suggesting a catalytic role.", "domain_architectures": 8, "interpro_id": "IPR046742", "known_evidence_count": null, "matches": 213, "name": "Domain of unknown function (DUF6792)", "partial_evidence_count": null, "pfam_id": "PF20591", "proteins": 213, "proteomes": 156, "short_name": "DUF6792", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20591", "structures": 0, "taxa": 318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised bacterial proteins. It is predicted to adopt a globular structure consisting of a curved beta-sheet and alpha helices packed on one side of it.", "domain_architectures": 19, "interpro_id": "IPR056724", "known_evidence_count": null, "matches": 214, "name": "Domain of unknown function (DUF7822)", "partial_evidence_count": null, "pfam_id": "PF25135", "proteins": 213, "proteomes": 202, "short_name": "DUF7822", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25135", "structures": 0, "taxa": 406, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 118, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 112 and 194 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR021077", "known_evidence_count": null, "matches": 213, "name": "Phage protein", "partial_evidence_count": null, "pfam_id": "PF12375", "proteins": 212, "proteomes": 170, "short_name": "DUF3653", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12375", "structures": 0, "taxa": 353, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001726) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the pactamides biosynthetic gene cluster from Streptomyces pactum [[cite:PUB00098964]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR045756", "known_evidence_count": null, "matches": 212, "name": "Family of unknown function (DUF6183)", "partial_evidence_count": null, "pfam_id": "PF19681", "proteins": 212, "proteomes": 201, "short_name": "DUF6183", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19681", "structures": 0, "taxa": 320, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, eukaryotes and viruses, and is approximately 110 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046593", "known_evidence_count": null, "matches": 212, "name": "Family of unknown function (DUF6651)", "partial_evidence_count": null, "pfam_id": "PF20356", "proteins": 212, "proteomes": 196, "short_name": "DUF6651", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20356", "structures": 0, "taxa": 416, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 194, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a group of uncharacterised proteins from Halobacteria. This domain contains a pair of highly conserved cysteine residues.", "domain_architectures": 4, "interpro_id": "IPR055973", "known_evidence_count": null, "matches": 212, "name": "Domain of unknown function (DUF7551)", "partial_evidence_count": null, "pfam_id": "PF24420", "proteins": 212, "proteomes": 176, "short_name": "DUF7551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24420", "structures": 0, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR007670", "known_evidence_count": null, "matches": 211, "name": "Protein of unknown function, DUF596", "partial_evidence_count": null, "pfam_id": "PF04591", "proteins": 211, "proteomes": 126, "short_name": "DUF596", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04591", "structures": 1, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 202, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are found in a set of hypothetical Archaeal proteins. Their exact function has not, as yet, been defined.", "domain_architectures": 3, "interpro_id": "IPR015266", "known_evidence_count": null, "matches": 211, "name": "Domain of unknown function (DUF1947)", "partial_evidence_count": null, "pfam_id": "PF09183", "proteins": 211, "proteomes": 211, "short_name": "DUF1947", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09183", "structures": 4, "taxa": 473, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is approximately 70 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031957", "known_evidence_count": null, "matches": 214, "name": "Domain of unknown function (DUF4777)", "partial_evidence_count": null, "pfam_id": "PF16007", "proteins": 211, "proteomes": 67, "short_name": "DUF4777", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16007", "structures": 0, "taxa": 273, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000758) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the capsular polysaccharide biosynthetic gene cluster from Staphylococcus aureus [[cite:PUB00007578]].", "domain_architectures": 2, "interpro_id": "IPR046100", "known_evidence_count": null, "matches": 212, "name": "Family of unknown function (DUF6037)", "partial_evidence_count": null, "pfam_id": "PF19503", "proteins": 211, "proteomes": 200, "short_name": "DUF6037", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19503", "structures": 0, "taxa": 508, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000385) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the lysobactin biosynthetic gene cluster from Lysobacter sp. ATCC 53042 [[cite:PUB00098898]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR046197", "known_evidence_count": null, "matches": 211, "name": "Family of unknown function (DUF6229)", "partial_evidence_count": null, "pfam_id": "PF19740", "proteins": 211, "proteomes": 169, "short_name": "DUF6229", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19740", "structures": 0, "taxa": 254, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 162, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 73 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046619", "known_evidence_count": null, "matches": 211, "name": "Family of unknown function (DUF6732)", "partial_evidence_count": null, "pfam_id": "PF20506", "proteins": 211, "proteomes": 210, "short_name": "DUF6732", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20506", "structures": 0, "taxa": 341, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. It is predicted to adopt a globular alpha/beta structure with a central antiparallel beta-sheet and helices packed on it.", "domain_architectures": 2, "interpro_id": "IPR054272", "known_evidence_count": null, "matches": 212, "name": "Family of unknown function (DUF7003)", "partial_evidence_count": null, "pfam_id": "PF22535", "proteins": 211, "proteomes": 195, "short_name": "DUF7003", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22535", "structures": 0, "taxa": 453, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from betaproteobacteria. It is predicted to adopt alpha-helical structure. In some proteins it is found repeated.", "domain_architectures": 5, "interpro_id": "IPR059279", "known_evidence_count": null, "matches": 211, "name": "Domain of unknown function (DUF8235)", "partial_evidence_count": null, "pfam_id": "PF26699", "proteins": 211, "proteomes": 210, "short_name": "DUF8235", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26699", "structures": 0, "taxa": 303, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a number of hypothetical proteins of unknown function from Arabidopsis thaliana.", "domain_architectures": 12, "interpro_id": "IPR009568", "known_evidence_count": null, "matches": 337, "name": "Protein of unknown function (DUF1184)", "partial_evidence_count": null, "pfam_id": "PF06683", "proteins": 210, "proteomes": 24, "short_name": "DUF1184", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06683", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 173 and 198 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046141", "known_evidence_count": null, "matches": 210, "name": "Family of unknown function (DUF6143)", "partial_evidence_count": null, "pfam_id": "PF19640", "proteins": 210, "proteomes": 179, "short_name": "DUF6143", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19640", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 198, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of short uncharacterised proteins from halobacteria. Members are predicted to adopt an alpha configuration.", "domain_architectures": 1, "interpro_id": "IPR057182", "known_evidence_count": null, "matches": 210, "name": "Family of unknown function (DUF7860)", "partial_evidence_count": null, "pfam_id": "PF25259", "proteins": 210, "proteomes": 200, "short_name": "DUF7860", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25259", "structures": 0, "taxa": 319, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt an alpha/beta structure with an unique topology. It contains several highly conserved histidine and aspartate residues that may be essential for function.", "domain_architectures": 4, "interpro_id": "IPR059448", "known_evidence_count": null, "matches": 210, "name": "Domain of unknown function (DUF8404)", "partial_evidence_count": null, "pfam_id": "PF28446", "proteins": 210, "proteomes": 182, "short_name": "DUF8404", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28446", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as a-gt.4 however currently no function is known.", "domain_architectures": 2, "interpro_id": "IPR022558", "known_evidence_count": null, "matches": 209, "name": "Protein of unknown function (DUF2654)", "partial_evidence_count": null, "pfam_id": "PF10849", "proteins": 209, "proteomes": 209, "short_name": "DUF2654", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10849", "structures": 0, "taxa": 509, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000291) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This family includes a protein from the A54145 biosynthetic gene cluster from Streptomyces fradiae [[cite:PUB00099441]].", "domain_architectures": 3, "interpro_id": "IPR046105", "known_evidence_count": null, "matches": 210, "name": "Family of unknown function (DUF6042)", "partial_evidence_count": null, "pfam_id": "PF19508", "proteins": 209, "proteomes": 197, "short_name": "DUF6042", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19508", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 198, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised prokaryotic proteins. Is has significant sequence similarity to GIY-YIG endonuclease domains and it is predicted to adopt similar structure.", "domain_architectures": 4, "interpro_id": "IPR055930", "known_evidence_count": null, "matches": 209, "name": "Domain of unknown function (DUF7508)", "partial_evidence_count": null, "pfam_id": "PF24348", "proteins": 209, "proteomes": 204, "short_name": "DUF7508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24348", "structures": 0, "taxa": 398, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 203, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised worm proteins. They are predicted to fold into two alpha-hairpins arranged in V-shape.", "domain_architectures": 7, "interpro_id": "IPR056709", "known_evidence_count": null, "matches": 210, "name": "Family of unknown function (DUF7807)", "partial_evidence_count": null, "pfam_id": "PF25093", "proteins": 209, "proteomes": 65, "short_name": "DUF7807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25093", "structures": 0, "taxa": 182, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 198, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised halobacterial proteins. The protein assumes a compact domain structure with an N-terminal helix that is packed onto the concave face of a twisted four stranded beta sheet.", "domain_architectures": 1, "interpro_id": "IPR058274", "known_evidence_count": null, "matches": 209, "name": "Family of unknown function (DUF7968)", "partial_evidence_count": null, "pfam_id": "PF25922", "proteins": 209, "proteomes": 165, "short_name": "DUF7968", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25922", "structures": 0, "taxa": 275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 206, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. The proteins are composed of four alpha helices.", "domain_architectures": 1, "interpro_id": "IPR058277", "known_evidence_count": null, "matches": 209, "name": "Family of unknown function (DUF7971)", "partial_evidence_count": null, "pfam_id": "PF25926", "proteins": 209, "proteomes": 209, "short_name": "DUF7971", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25926", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 1, "interpro_id": "IPR058379", "known_evidence_count": null, "matches": 209, "name": "Family of unknown function (DUF8066)", "partial_evidence_count": null, "pfam_id": "PF26262", "proteins": 209, "proteomes": 188, "short_name": "DUF8066", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26262", "structures": 0, "taxa": 375, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Ths domain is found in uncharacterised proteins from gram negative bacteria. It is found either standalone or in combination with other domains. It is predicted to fold into a very simple structure composed of a beta-hairpin flanked by two helices.", "domain_architectures": 3, "interpro_id": "IPR061576", "known_evidence_count": null, "matches": 209, "name": "Domain of unknown function (DUF8506)", "partial_evidence_count": null, "pfam_id": "PF29168", "proteins": 209, "proteomes": 198, "short_name": "DUF8506", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29168", "structures": 0, "taxa": 343, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 82, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a viral family of proteins with unknown function.", "domain_architectures": 8, "interpro_id": "IPR024416", "known_evidence_count": null, "matches": 217, "name": "Protein of unknown function (DUF2738)", "partial_evidence_count": null, "pfam_id": "PF10927", "proteins": 208, "proteomes": 52, "short_name": "DUF2738", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10927", "structures": 0, "taxa": 171, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 150 residues in length and is mainly found in various Clostridium species. The function of this family is unknown.", "domain_architectures": 10, "interpro_id": "IPR032256", "known_evidence_count": null, "matches": 209, "name": "Domain of unknown function (DUF4829)", "partial_evidence_count": null, "pfam_id": "PF16111", "proteins": 208, "proteomes": 167, "short_name": "DUF4829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16111", "structures": 0, "taxa": 385, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR035317", "known_evidence_count": null, "matches": 208, "name": "Family of unknown function (DUF5375)", "partial_evidence_count": null, "pfam_id": "PF17345", "proteins": 208, "proteomes": 155, "short_name": "DUF5375", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17345", "structures": 0, "taxa": 258, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 159 and 175 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046139", "known_evidence_count": null, "matches": 208, "name": "Family of unknown function (DUF6141)", "partial_evidence_count": null, "pfam_id": "PF19638", "proteins": 208, "proteomes": 196, "short_name": "DUF6141", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19638", "structures": 0, "taxa": 412, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage protein. These proteins adopt a compact globular domain. The predicted structure of the domain shows a positively charged surface suggesting a possible nucleic acid binding function.", "domain_architectures": 1, "interpro_id": "IPR055814", "known_evidence_count": null, "matches": 208, "name": "Domain of unknown function (DUF7390)", "partial_evidence_count": null, "pfam_id": "PF24116", "proteins": 208, "proteomes": 206, "short_name": "DUF7390", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24116", "structures": 0, "taxa": 457, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillus spp.", "domain_architectures": 1, "interpro_id": "IPR020314", "known_evidence_count": null, "matches": 207, "name": "Protein of unknown function (DUF2564)", "partial_evidence_count": null, "pfam_id": "PF10819", "proteins": 207, "proteomes": 206, "short_name": "DUF2564", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10819", "structures": 0, "taxa": 292, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 291 and 501 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR031934", "known_evidence_count": null, "matches": 257, "name": "Domain of unknown function (DUF4769)", "partial_evidence_count": null, "pfam_id": "PF15992", "proteins": 207, "proteomes": 64, "short_name": "DUF4769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15992", "structures": 0, "taxa": 267, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacilli.Family members contain two predicted trans-membrane regions.", "domain_architectures": 2, "interpro_id": "IPR020275", "known_evidence_count": null, "matches": 207, "name": "Family of unknown function (DUF5592)", "partial_evidence_count": null, "pfam_id": "PF17332", "proteins": 207, "proteomes": 179, "short_name": "DUF5592", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17332", "structures": 0, "taxa": 331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised phage proteins that are predicted to form a coiled-coil. However, structure predictions do not predict homodimeric or homotrimeric complexes.", "domain_architectures": 1, "interpro_id": "IPR056037", "known_evidence_count": null, "matches": 207, "name": "Family of unknown function (DUF7620)", "partial_evidence_count": null, "pfam_id": "PF24596", "proteins": 207, "proteomes": 202, "short_name": "DUF7620", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24596", "structures": 0, "taxa": 458, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to a family of Enterobacterial proteins. It has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR019672", "known_evidence_count": null, "matches": 206, "name": "Protein of unknown function (DUF2627)", "partial_evidence_count": null, "pfam_id": "PF10736", "proteins": 206, "proteomes": 206, "short_name": "DUF2527", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10736", "structures": 0, "taxa": 303, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. These proteins are likely to be lipoproteins (attachment site currently included in alignment).", "domain_architectures": 1, "interpro_id": "IPR025318", "known_evidence_count": null, "matches": 206, "name": "Protein of unknown function (DUF4223)", "partial_evidence_count": null, "pfam_id": "PF13978", "proteins": 206, "proteomes": 201, "short_name": "DUF4223", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13978", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 175, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in insects, and is approximately 230 amino acids in length. There is a single completely conserved residue D that may be functionally important. It adopts a C2-like fold.", "domain_architectures": 8, "interpro_id": "IPR031992", "known_evidence_count": null, "matches": 212, "name": "Domain of unknown function (DUF4788)", "partial_evidence_count": null, "pfam_id": "PF16032", "proteins": 206, "proteomes": 38, "short_name": "DUF4788", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16032", "structures": 0, "taxa": 142, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 90 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, particularly members of the families Demerecviridae and Straboviridae. Within these families, the proteins are predominantly found in the genera Tequintavirus and Epseptimavirus. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061603", "known_evidence_count": null, "matches": 206, "name": "Family of unknown function (DUF8533)", "partial_evidence_count": null, "pfam_id": "PF29380", "proteins": 206, "proteomes": 206, "short_name": "DUF8533", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29380", "structures": 0, "taxa": 455, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins.", "domain_architectures": 2, "interpro_id": "IPR015051", "known_evidence_count": null, "matches": 206, "name": "Domain of unknown function (DUF1869)", "partial_evidence_count": null, "pfam_id": "PF08956", "proteins": 205, "proteomes": 196, "short_name": "DUF1869", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08956", "structures": 1, "taxa": 297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of phage proteins are the product of the gene phiRv1, however no function is known.", "domain_architectures": 2, "interpro_id": "IPR024384", "known_evidence_count": null, "matches": 205, "name": "Protein of unknown function (DUF2742)", "partial_evidence_count": null, "pfam_id": "PF10888", "proteins": 205, "proteomes": 172, "short_name": "DUF2742", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10888", "structures": 0, "taxa": 260, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000267) is described by MIBiG as an example of the following biosynthetic classes, polyketide and saccharide. This entry includes a member from the saquayamycin Z biosynthetic gene cluster from Micromonospora sp. Tu 6368 [[cite:PUB00099446]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR046211", "known_evidence_count": null, "matches": 205, "name": "Family of unknown function (DUF6244)", "partial_evidence_count": null, "pfam_id": "PF19757", "proteins": 205, "proteomes": 112, "short_name": "DUF6244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19757", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small uncharacterised protein family. Members are composed of an N-terminal beta hairpin followed by three alpha helices.", "domain_architectures": 1, "interpro_id": "IPR056113", "known_evidence_count": null, "matches": 205, "name": "Family of unknown function (DUF7696)", "partial_evidence_count": null, "pfam_id": "PF24751", "proteins": 205, "proteomes": 169, "short_name": "DUF7696", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24751", "structures": 0, "taxa": 276, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the C-terminus of hypothetical Arabidopsis thaliana proteins of unknown function.", "domain_architectures": 11, "interpro_id": "IPR009544", "known_evidence_count": null, "matches": 210, "name": "Protein of unknown function (DUF1163)", "partial_evidence_count": null, "pfam_id": "PF06651", "proteins": 204, "proteomes": 25, "short_name": "DUF1163", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06651", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A predicted alpha+beta domain that is usually fused N-terminal to the JAB metallopeptidase. This protein in turn is found in conserved gene neighborhoods that include genes encoding the bacterial homologs of the ubiquitin modification system such as the E1, E2 and Ub proteins [[cite:PUB00034476]]. The domain is also known as the JAB-N domain. An AlphaFold3 prediction with A0A375JCV4 suggests that this domain likely mediate dimerisation (iPTM=0.87).", "domain_architectures": 3, "interpro_id": "IPR018560", "known_evidence_count": null, "matches": 204, "name": "Domain of unknown function (DUF2016)", "partial_evidence_count": null, "pfam_id": "PF09436", "proteins": 204, "proteomes": 181, "short_name": "DUF2016", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09436", "structures": 0, "taxa": 326, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in Enterobacteriaceae. This protein may have a phage origin being found in bacteriophage P2 [swissprot:Q06425]. The majority of proteins have a conserved cysteine residue close to their C-terminus which may have functional significance.", "domain_architectures": 2, "interpro_id": "IPR035404", "known_evidence_count": null, "matches": 205, "name": "Domain of unknown function (DUF5405)", "partial_evidence_count": null, "pfam_id": "PF17399", "proteins": 204, "proteomes": 152, "short_name": "DUF5405", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17399", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short proteins from archaea.", "domain_architectures": 1, "interpro_id": "IPR055958", "known_evidence_count": null, "matches": 204, "name": "Family of unknown function (DUF7536)", "partial_evidence_count": null, "pfam_id": "PF24380", "proteins": 204, "proteomes": 204, "short_name": "DUF7536", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24380", "structures": 0, "taxa": 313, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The domain is predominantly found in the class Halobacteria, which includes species from families such as Natrialbaceae and Haloferacaceae. The proteins containing this domain are typically around 60-70 amino acids in length. The domain contains two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058444", "known_evidence_count": null, "matches": 204, "name": "Domain of unknown function (DUF8131)", "partial_evidence_count": null, "pfam_id": "PF26452", "proteins": 204, "proteomes": 190, "short_name": "DUF8131", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26452", "structures": 0, "taxa": 304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal sequences and its function is unknown. It may adopt a structure consisting of four main alpha-helices with three beta-strands after the first helix.", "domain_architectures": 13, "interpro_id": "IPR061566", "known_evidence_count": null, "matches": 204, "name": "Domain of unknown function (DUF8496)", "partial_evidence_count": null, "pfam_id": "PF29051", "proteins": 204, "proteomes": 204, "short_name": "DUF8496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29051", "structures": 0, "taxa": 347, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 126, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of at least 7 paralogs in Myxococcus xanthus and 6 in Stigmatella aurantiaca, both members of the Deltaproteobacteria. The function is unknown.", "domain_architectures": 2, "interpro_id": "IPR011753", "known_evidence_count": null, "matches": 245, "name": "Protein of unknown function (DUF2379)", "partial_evidence_count": null, "pfam_id": "PF09543", "proteins": 203, "proteomes": 38, "short_name": "DUF2379", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09543", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 346 and 637 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR031532", "known_evidence_count": null, "matches": 217, "name": "Domain of unknown function (DUF4702)", "partial_evidence_count": null, "pfam_id": "PF15774", "proteins": 203, "proteomes": 165, "short_name": "DUF4702", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15774", "structures": 0, "taxa": 547, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicutes. Proteins in this family are approximately 180 amino acids in length. There are two conserved sequence motifs at the C-terminal: FGW/I and I/VGxM.", "domain_architectures": 1, "interpro_id": "IPR046680", "known_evidence_count": null, "matches": 203, "name": "Family of unknown function (DUF6550)", "partial_evidence_count": null, "pfam_id": "PF20187", "proteins": 203, "proteomes": 135, "short_name": "DUF6550", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20187", "structures": 0, "taxa": 299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are probably remotely related to His-Me finger endonucleases. The conservation of the putative active site residues in this family is not strict, in particular the position of the catalytic histidine. The residues involved in metal coordination are conserved. The presence in the vicinity of two invariant aspartate residues that point toward the putative active site suggests that these proteins may still function as enzymes but probably via a somewhat different catalytic mechanism. They may still retain their catalytic activity by employing these conserved aspartates that in the predicted AF2 models are well positioned to undertake a role in a potential nucleophilic attack.", "domain_architectures": 2, "interpro_id": "IPR054263", "known_evidence_count": null, "matches": 203, "name": "Family of unknown function (DUF6994)", "partial_evidence_count": null, "pfam_id": "PF22507", "proteins": 203, "proteomes": 178, "short_name": "DUF6994", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22507", "structures": 0, "taxa": 462, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 195, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins containing this domain are found predominantly in the class Halobacteria, which includes families such as Haloferacaceae, Haloarculaceae, and Natrialbaceae. The domain is typically around 100-110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058447", "known_evidence_count": null, "matches": 203, "name": "Domain of unknown function (DUF8134)", "partial_evidence_count": null, "pfam_id": "PF26455", "proteins": 203, "proteomes": 199, "short_name": "DUF8134", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26455", "structures": 0, "taxa": 317, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 8, "interpro_id": "IPR011087", "known_evidence_count": null, "matches": 322, "name": "Domain of Unknown Function (DUF1522)", "partial_evidence_count": null, "pfam_id": "PF07482", "proteins": 202, "proteomes": 75, "short_name": "DUF1522", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07482", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in cyanobacteria. Proteins in this family are approximately 90 amino acids in length. A member of this family, the ssr1528 gene was found to be regulated by an sRNA NsiR4 [[cite:PUB00088099]]. In addition the expression of that gene was repressed under conditions of nitrogen depletion suggesting it may have a role related to cellular nitrogen status [[cite:PUB00088099]].", "domain_architectures": 1, "interpro_id": "IPR025149", "known_evidence_count": null, "matches": 202, "name": "Protein of unknown function (DUF4090)", "partial_evidence_count": null, "pfam_id": "PF13319", "proteins": 202, "proteomes": 199, "short_name": "DUF4090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13319", "structures": 0, "taxa": 539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 200 residues in length and is mainly found in various Bacteroides species. Distant homology prediction algorithms consistently suggest a homology between this family and FKBP-type peptidyl-prolyl cis-trans isomerases (PF00254), but this relation is as yet not confirmed. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032252", "known_evidence_count": null, "matches": 202, "name": "Domain of unknown function (DUF4827)", "partial_evidence_count": null, "pfam_id": "PF16109", "proteins": 202, "proteomes": 202, "short_name": "DUF4827", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16109", "structures": 4, "taxa": 318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000100) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from monensin biosynthetic gene cluster from Streptomyces cinnamonensis [[cite:PUB00099424]].", "domain_architectures": 1, "interpro_id": "IPR046045", "known_evidence_count": null, "matches": 202, "name": "Family of unknown function (DUF6003)", "partial_evidence_count": null, "pfam_id": "PF19466", "proteins": 202, "proteomes": 193, "short_name": "DUF6003", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19466", "structures": 0, "taxa": 238, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 210 amino acids in length and their N-terminal share a similar structure with the Crispr-associated endoribonuclease Cas2.", "domain_architectures": 2, "interpro_id": "IPR046545", "known_evidence_count": null, "matches": 202, "name": "Family of unknown function (DUF6806)", "partial_evidence_count": null, "pfam_id": "PF20621", "proteins": 202, "proteomes": 202, "short_name": "DUF6806", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20621", "structures": 0, "taxa": 272, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 193, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins. These proteins are short in size (~50 residues long), contain a highly hydrophobic helix and are likely associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR055926", "known_evidence_count": null, "matches": 202, "name": "Family of unknown function (DUF7503)", "partial_evidence_count": null, "pfam_id": "PF24335", "proteins": 202, "proteomes": 149, "short_name": "DUF7503", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24335", "structures": 0, "taxa": 259, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from archaebacteria. These proteins contain and N and C-terminal transmembrane alpha helix. These alpha helices interact with each other. The central portion of the protein is likely to form a series of extracellular domains.", "domain_architectures": 3, "interpro_id": "IPR059275", "known_evidence_count": null, "matches": 217, "name": "Family of unknown function (DUF8231)", "partial_evidence_count": null, "pfam_id": "PF26687", "proteins": 202, "proteomes": 197, "short_name": "DUF8231", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26687", "structures": 0, "taxa": 304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from proteobacteria. It is predicted to fold into a partly open beta-barrel elaborated with alpha-helices. It is frequently found with [pfam:PF05567], a domain typical for Type IV pilus biogenesis factor PilY1 homologues. It contains two highly conserved cysteine residues which are predicted to form disulfide bond.", "domain_architectures": 3, "interpro_id": "IPR059399", "known_evidence_count": null, "matches": 202, "name": "Domain of unknown function (DUF8355)", "partial_evidence_count": null, "pfam_id": "PF27621", "proteins": 202, "proteomes": 164, "short_name": "DUF8355", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27621", "structures": 0, "taxa": 250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 126, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from bacteria and eukaryotes. It is predicted to fold into an alpha/beta structure composed of four-stranded antiparallel beta-sheet with strand order 2341 and alpha helices packed on one face of the sheet. This domain contains two pair of highly conserved cysteine residues that are predicted to form disulfide bonds. It is frequently found N-terminal to TIM-barrel domain.", "domain_architectures": 2, "interpro_id": "IPR059449", "known_evidence_count": null, "matches": 202, "name": "Domain of unknown function (DUF8405)", "partial_evidence_count": null, "pfam_id": "PF28464", "proteins": 202, "proteomes": 158, "short_name": "DUF8405", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28464", "structures": 0, "taxa": 303, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as uvdY.-2 which is an open reading frame within uvsY. However currently there is no known function.", "domain_architectures": 1, "interpro_id": "IPR024362", "known_evidence_count": null, "matches": 201, "name": "Protein of unknown function (DUF2685)", "partial_evidence_count": null, "pfam_id": "PF10886", "proteins": 201, "proteomes": 201, "short_name": "DUF2685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10886", "structures": 0, "taxa": 466, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length. There are two conserved sequence motifs: VEVV and SYVAT.", "domain_architectures": 2, "interpro_id": "IPR025135", "known_evidence_count": null, "matches": 201, "name": "Protein of unknown function (DUF4060)", "partial_evidence_count": null, "pfam_id": "PF13269", "proteins": 201, "proteomes": 174, "short_name": "DUF4060", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13269", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 162, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 130 and 288 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR031668", "known_evidence_count": null, "matches": 211, "name": "Domain of unknown function (DUF4711)", "partial_evidence_count": null, "pfam_id": "PF15829", "proteins": 201, "proteomes": 153, "short_name": "DUF4711", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15829", "structures": 0, "taxa": 535, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is expressed by Firmicutes. The function is not known.", "domain_architectures": 4, "interpro_id": "IPR031888", "known_evidence_count": null, "matches": 254, "name": "Domain of unknown function (DUF5068)", "partial_evidence_count": null, "pfam_id": "PF16781", "proteins": 201, "proteomes": 189, "short_name": "DUF5068", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16781", "structures": 1, "taxa": 303, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 126, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000801) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the galactoglucan biosynthetic gene cluster from Sinorhizobium meliloti [[cite:PUB00099407]]. This family appears to be predominantly found in proteobacteria.", "domain_architectures": 10, "interpro_id": "IPR046184", "known_evidence_count": null, "matches": 209, "name": "Family of unknown function (DUF6212)", "partial_evidence_count": null, "pfam_id": "PF19717", "proteins": 201, "proteomes": 177, "short_name": "DUF6212", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19717", "structures": 0, "taxa": 324, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 62 and 77 amino acids in length. There are two conserved sequence motifs: FILN and VVLIYLK. This family is related to [pfam:PF17259].", "domain_architectures": 1, "interpro_id": "IPR045938", "known_evidence_count": null, "matches": 201, "name": "Family of unknown function (DUF6358)", "partial_evidence_count": null, "pfam_id": "PF19885", "proteins": 201, "proteomes": 201, "short_name": "DUF6358", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19885", "structures": 0, "taxa": 235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They contain conserved Pro-Gly-rich motif with a semi- conserved pattern PGRxFPGx3QGD.", "domain_architectures": 3, "interpro_id": "IPR053801", "known_evidence_count": null, "matches": 201, "name": "Family of unknown function (DUF6959)", "partial_evidence_count": null, "pfam_id": "PF22281", "proteins": 201, "proteomes": 193, "short_name": "DUF6959", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22281", "structures": 0, "taxa": 355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 193, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Halobacteria. It has a detectable sequence similarity to TRAM domains and it is predicted to adopt a similar structure. It is found as standalone domain.", "domain_architectures": 2, "interpro_id": "IPR055935", "known_evidence_count": null, "matches": 203, "name": "Domain of unknown function (DUF7513)", "partial_evidence_count": null, "pfam_id": "PF24353", "proteins": 201, "proteomes": 199, "short_name": "DUF7513", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24353", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins primarily found in Bacteria. It has a detectable similarity to winged helix HTH domain and it is predicted to adopt similar structure. This domain is frequently found in combination with [pfam:PF21818] and [pfam:PF20815].", "domain_architectures": 10, "interpro_id": "IPR056086", "known_evidence_count": null, "matches": 201, "name": "Domain of unknown function (DUF7669)", "partial_evidence_count": null, "pfam_id": "PF24706", "proteins": 201, "proteomes": 184, "short_name": "DUF7669", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24706", "structures": 0, "taxa": 470, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 193, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised worm proteins. It has a detectable similarity to known PH domains and it is predicted to adopt similar structure.", "domain_architectures": 10, "interpro_id": "IPR056680", "known_evidence_count": null, "matches": 202, "name": "Domain of unknown function (DUF7778)", "partial_evidence_count": null, "pfam_id": "PF24998", "proteins": 201, "proteomes": 70, "short_name": "DUF7778", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24998", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This immunoglobulin-like (Ig-like) domain is found in a group of uncharacterised fungal proteins. It is often found associated with [pfam:PF01734] and has a highly conserved motif ISGFP.", "domain_architectures": 14, "interpro_id": "IPR059436", "known_evidence_count": null, "matches": 201, "name": "Domain of unknown function (DUF8392)", "partial_evidence_count": null, "pfam_id": "PF28431", "proteins": 201, "proteomes": 149, "short_name": "DUF8392", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28431", "structures": 0, "taxa": 406, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins has no known function. Several members are, however, annotated as being putative acyl-CoA synthetase, but this could not be confirmed.", "domain_architectures": 1, "interpro_id": "IPR061507", "known_evidence_count": null, "matches": 200, "name": "Protein of unknown function (DUF3316)", "partial_evidence_count": null, "pfam_id": "PF11777", "proteins": 200, "proteomes": 199, "short_name": "DUF3316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11777", "structures": 0, "taxa": 327, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 126, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Domain based on 1-364 domain of PDB:3LM3 which is encoded by the BDI_3119 gene from Parabacteroides distasonis atcc 8503.", "domain_architectures": 5, "interpro_id": "IPR024334", "known_evidence_count": null, "matches": 200, "name": "Domain of Unknown Function with PDB structure (DUF3863)", "partial_evidence_count": null, "pfam_id": "PF12979", "proteins": 200, "proteomes": 174, "short_name": "DUF3863", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12979", "structures": 1, "taxa": 319, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 139, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain was first discovered in BPSL1050, a highly immunoreactive protein found in Burkholderia pseudomallei. The domain's structure consists of three helical regions which pack onto an antiparallel beta sheet, formed by four strands. The beta sheet is solvent exposed on one side and packs tightly against the three helices on the other side, generating a network of hydrophobic and aromatic interactions that contribute to tight packing of the protein. Is is thought that the small loop L1, the main loop L2, and part of helix alpha-3 extending until Leu120 are the three main immunogenic sequences [[cite:PUB00091370]].", "domain_architectures": 1, "interpro_id": "IPR040953", "known_evidence_count": null, "matches": 200, "name": "Domain of unknown function (DUF5594)", "partial_evidence_count": null, "pfam_id": "PF18057", "proteins": 200, "proteomes": 169, "short_name": "DUF5594", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18057", "structures": 1, "taxa": 192, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in functionally uncharacterised proteins mainly from Proteobacteria and Bacteroidetes. It has similarity to PD-(D/E)XK nuclease domains and it is predicted to adopt similar structure..", "domain_architectures": 8, "interpro_id": "IPR046099", "known_evidence_count": null, "matches": 200, "name": "Domain of unknown function (DUF6035)", "partial_evidence_count": null, "pfam_id": "PF19500", "proteins": 200, "proteomes": 194, "short_name": "DUF6035", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19500", "structures": 0, "taxa": 479, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001916) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the lavendiol biosynthetic gene cluster from Streptomyces lavendulae [[cite:PUB00098885]].", "domain_architectures": 3, "interpro_id": "IPR045642", "known_evidence_count": null, "matches": 200, "name": "Family of unknown function (DUF6406)", "partial_evidence_count": null, "pfam_id": "PF19944", "proteins": 200, "proteomes": 145, "short_name": "DUF6406", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19944", "structures": 0, "taxa": 217, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain from a large family of uncharacterised phage proteins that typically contain three domains.", "domain_architectures": 9, "interpro_id": "IPR055701", "known_evidence_count": null, "matches": 200, "name": "Domain of unknown function (DUF7277)", "partial_evidence_count": null, "pfam_id": "PF23942", "proteins": 200, "proteomes": 136, "short_name": "DUF7277", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23942", "structures": 0, "taxa": 366, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 191, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR055742", "known_evidence_count": null, "matches": 200, "name": "Family of unknown function (DUF7318)", "partial_evidence_count": null, "pfam_id": "PF24002", "proteins": 200, "proteomes": 200, "short_name": "DUF7318", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24002", "structures": 0, "taxa": 310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 155, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised sequences from bacteria. According to structure predictions, these proteins may comprise novel repeats consisting of an arrangement of four beta-strands in which the second one is longer and curved. This arrangement is repeated eight times in SwissProt:A0A5B9QB27, which form a closed repeat.", "domain_architectures": 18, "interpro_id": "IPR055876", "known_evidence_count": null, "matches": 258, "name": "Family of unknown function (DUF7453)", "partial_evidence_count": null, "pfam_id": "PF24251", "proteins": 200, "proteomes": 104, "short_name": "DUF7453", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24251", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of very short uncharacterised sequences from halobacteria. Members are predicted to adopt an alpha-helical configuration.", "domain_architectures": 1, "interpro_id": "IPR057181", "known_evidence_count": null, "matches": 200, "name": "Family of unknown function (DUF7859)", "partial_evidence_count": null, "pfam_id": "PF25258", "proteins": 200, "proteomes": 200, "short_name": "DUF7859", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25258", "structures": 0, "taxa": 331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function is found in a limited set of Bradyrhizobium proteins. There appears to be a periodic -DG- motif in it.", "domain_architectures": 3, "interpro_id": "IPR011086", "known_evidence_count": null, "matches": 229, "name": "Domain of Unknown Function (DUF1521)", "partial_evidence_count": null, "pfam_id": "PF07481", "proteins": 199, "proteomes": 173, "short_name": "DUF1521", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07481", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR009181", "known_evidence_count": null, "matches": 199, "name": "Uncharacterized protein conserved in archaea (DUF2099)", "partial_evidence_count": null, "pfam_id": "PF09872", "proteins": 199, "proteomes": 157, "short_name": "DUF2099", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09872", "structures": 0, "taxa": 314, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025353", "known_evidence_count": null, "matches": 199, "name": "Protein of unknown function (DUF4257)", "partial_evidence_count": null, "pfam_id": "PF14074", "proteins": 199, "proteomes": 189, "short_name": "DUF4257", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14074", "structures": 0, "taxa": 300, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 71 and 317 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR031516", "known_evidence_count": null, "matches": 204, "name": "Domain of unknown function (DUF4691)", "partial_evidence_count": null, "pfam_id": "PF15762", "proteins": 199, "proteomes": 155, "short_name": "DUF4691", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15762", "structures": 0, "taxa": 506, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function, mostly found in Spirochaeta.", "domain_architectures": 2, "interpro_id": "IPR035196", "known_evidence_count": null, "matches": 201, "name": "Family of unknown function (DUF5312)", "partial_evidence_count": null, "pfam_id": "PF17239", "proteins": 199, "proteomes": 95, "short_name": "DUF5312", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17239", "structures": 0, "taxa": 170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Bacteria.", "domain_architectures": 3, "interpro_id": "IPR035315", "known_evidence_count": null, "matches": 199, "name": "Family of unknown function (DUF5372)", "partial_evidence_count": null, "pfam_id": "PF17342", "proteins": 199, "proteomes": 155, "short_name": "DUF5372", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17342", "structures": 0, "taxa": 411, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain found in a range of phage and bacterial proteins. Structurally it is composed of a three stranded beta meander packed against an alpha helix. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR054201", "known_evidence_count": null, "matches": 199, "name": "Domain of unknown function (DUF6906)", "partial_evidence_count": null, "pfam_id": "PF21847", "proteins": 199, "proteomes": 173, "short_name": "DUF6906", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21847", "structures": 0, "taxa": 337, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 189, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to fold into a four-helical bundle and it is likely associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR055737", "known_evidence_count": null, "matches": 199, "name": "Domain of unknown function (DUF7313)", "partial_evidence_count": null, "pfam_id": "PF23995", "proteins": 199, "proteomes": 198, "short_name": "DUF7313", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23995", "structures": 0, "taxa": 299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved family found in various bacteriophages, particularly those infecting Escherichia, Klebsiella, and other Enterobacteriaceae. The function of this domain is currently unknown. This family is commonly found in phages belonging to the Drexlerviridae family, including genera such as Webervirus, Tempevirinae, and Tunavirinae. This entry shows some structurally similar features to [pfam:PF24227].", "domain_architectures": 1, "interpro_id": "IPR055867", "known_evidence_count": null, "matches": 199, "name": "Family of unknown function (DUF7444)", "partial_evidence_count": null, "pfam_id": "PF24231", "proteins": 199, "proteomes": 197, "short_name": "DUF7444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24231", "structures": 0, "taxa": 450, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of bacterial proteins that based on structural similarities are likely to bind to heme or a related derivative molecule. Structural modelling suggests these proteins are likely to form homodimers and that this complex can bind to two heme-like molecules. Each heme binding site is composed of parts of both subunits.", "domain_architectures": 2, "interpro_id": "IPR056093", "known_evidence_count": null, "matches": 199, "name": "Family of unknown function (DUF7676)", "partial_evidence_count": null, "pfam_id": "PF24724", "proteins": 199, "proteomes": 188, "short_name": "DUF7676", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24724", "structures": 0, "taxa": 464, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta structure with unique topology.", "domain_architectures": 3, "interpro_id": "IPR058506", "known_evidence_count": null, "matches": 199, "name": "Domain of unknown function (DUF8193)", "partial_evidence_count": null, "pfam_id": "PF26613", "proteins": 199, "proteomes": 137, "short_name": "DUF8193", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26613", "structures": 0, "taxa": 298, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It has detectable similarity to members of Immunity protein 19 family [pfam:PF15563] and it is predicted to adopt similar structure.", "domain_architectures": 3, "interpro_id": "IPR059263", "known_evidence_count": null, "matches": 203, "name": "Domain of unknown function (DUF8219)", "partial_evidence_count": null, "pfam_id": "PF26656", "proteins": 199, "proteomes": 173, "short_name": "DUF8219", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26656", "structures": 0, "taxa": 326, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 40 residues in length found in Cyanobacteriota. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061685", "known_evidence_count": null, "matches": 199, "name": "Family of unknown function (DUF8624)", "partial_evidence_count": null, "pfam_id": "PF30555", "proteins": 199, "proteomes": 199, "short_name": "DUF8624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30555", "structures": 0, "taxa": 558, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 107, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of bacterial proteins that are related to the hypothetical protein yeeT.", "domain_architectures": 1, "interpro_id": "IPR009329", "known_evidence_count": null, "matches": 198, "name": "Protein of unknown function (DUF987)", "partial_evidence_count": null, "pfam_id": "PF06174", "proteins": 198, "proteomes": 125, "short_name": "DUF987", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06174", "structures": 0, "taxa": 245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 171, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family have an important role in methanogenesis. They assume an alpha-beta globular structure consisting of six beta-strands and three alpha-helices forming the secondary structural topological arrangement of alpha1-beta1-alpha2-beta2-beta3-beta4-beta5-beta6-alpha3 [[cite:PUB00035386]].", "domain_architectures": 2, "interpro_id": "IPR012031", "known_evidence_count": null, "matches": 199, "name": "Domain of unknown function (DUF1894)", "partial_evidence_count": null, "pfam_id": "PF08979", "proteins": 198, "proteomes": 145, "short_name": "DUF1894", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08979", "structures": 1, "taxa": 264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chordata.", "domain_architectures": 4, "interpro_id": "IPR038935", "known_evidence_count": null, "matches": 204, "name": "Family of unknown function (DUF5528)", "partial_evidence_count": null, "pfam_id": "PF17666", "proteins": 198, "proteomes": 173, "short_name": "DUF5528", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17666", "structures": 0, "taxa": 632, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001091) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the corallopyronin biosynthetic gene cluster from Corallococcus coralloides [[cite:PUB00098961]]. This family appears to be predominantly found in proteobacteria.", "domain_architectures": 4, "interpro_id": "IPR045750", "known_evidence_count": null, "matches": 199, "name": "Family of unknown function (DUF6178)", "partial_evidence_count": null, "pfam_id": "PF19676", "proteins": 198, "proteomes": 181, "short_name": "DUF6178", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19676", "structures": 0, "taxa": 417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 150 and 175 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR046592", "known_evidence_count": null, "matches": 198, "name": "Family of unknown function (DUF6650)", "partial_evidence_count": null, "pfam_id": "PF20355", "proteins": 198, "proteomes": 191, "short_name": "DUF6650", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20355", "structures": 0, "taxa": 506, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046643", "known_evidence_count": null, "matches": 198, "name": "Family of unknown function (DUF6755)", "partial_evidence_count": null, "pfam_id": "PF20540", "proteins": 198, "proteomes": 192, "short_name": "DUF6755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20540", "structures": 0, "taxa": 361, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short family of bacterial proteins contains a potential alpha helical solenoid structure. The function of these proteins is unknown. Proteins in this family are primarily found in Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR049221", "known_evidence_count": null, "matches": 224, "name": "Family of unknown function (DUF6869)", "partial_evidence_count": null, "pfam_id": "PF21746", "proteins": 198, "proteomes": 189, "short_name": "DUF6869", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21746", "structures": 0, "taxa": 422, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to fold into a four-helical bundle and it is likely associated with the membrane.", "domain_architectures": 2, "interpro_id": "IPR055745", "known_evidence_count": null, "matches": 198, "name": "Domain of unknown function (DUF7321)", "partial_evidence_count": null, "pfam_id": "PF24007", "proteins": 198, "proteomes": 197, "short_name": "DUF7321", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24007", "structures": 0, "taxa": 297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins have three transmembrane alpha helices.", "domain_architectures": 1, "interpro_id": "IPR058304", "known_evidence_count": null, "matches": 198, "name": "Family of unknown function (DUF7991)", "partial_evidence_count": null, "pfam_id": "PF25953", "proteins": 198, "proteomes": 198, "short_name": "DUF7991", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25953", "structures": 0, "taxa": 299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is believed to be involved in the type VII secretion system.", "domain_architectures": 1, "interpro_id": "IPR031664", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF5085)", "partial_evidence_count": null, "pfam_id": "PF16895", "proteins": 197, "proteomes": 127, "short_name": "DUF5085", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16895", "structures": 0, "taxa": 237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 84 and 107 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046168", "known_evidence_count": null, "matches": 197, "name": "Family of unknown function (DUF6170)", "partial_evidence_count": null, "pfam_id": "PF19667", "proteins": 197, "proteomes": 197, "short_name": "DUF6170", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19667", "structures": 0, "taxa": 264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins, found in bacteria and viruses, is functionally uncharacterised. Proteins in this family are typically between 179 and 275 amino acids in length. There are two conserved residues, a leucine and a tyrosine.", "domain_architectures": 9, "interpro_id": "IPR046258", "known_evidence_count": null, "matches": 197, "name": "Family of unknown function (DUF6291)", "partial_evidence_count": null, "pfam_id": "PF19808", "proteins": 197, "proteomes": 158, "short_name": "DUF6291", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19808", "structures": 0, "taxa": 356, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in Proteobacteria and viruses, and is approximately 90 amino acids in length. It contains the conserved motifs FDD and MGGW.", "domain_architectures": 3, "interpro_id": "IPR045521", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF6475)", "partial_evidence_count": null, "pfam_id": "PF20081", "proteins": 197, "proteomes": 176, "short_name": "DUF6475", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20081", "structures": 0, "taxa": 429, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain family is functionally uncharacterised. It is found in bacterial proteins and is typically 54 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046640", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF6752)", "partial_evidence_count": null, "pfam_id": "PF20537", "proteins": 197, "proteomes": 161, "short_name": "DUF6752", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20537", "structures": 0, "taxa": 227, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 187, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to fold into an alpha-helical hairpin and it is likely associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR055738", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF7314)", "partial_evidence_count": null, "pfam_id": "PF23996", "proteins": 197, "proteomes": 196, "short_name": "DUF7314", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23996", "structures": 0, "taxa": 297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 1, "interpro_id": "IPR058382", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF8069)", "partial_evidence_count": null, "pfam_id": "PF26266", "proteins": 197, "proteomes": 119, "short_name": "DUF8069", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26266", "structures": 0, "taxa": 207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from dinoflagellates. It is predicted to fold into an alpha-helical structure. It contains several invariant residues including aspartate and cysteine that may be essential for function.", "domain_architectures": 17, "interpro_id": "IPR059276", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF8232)", "partial_evidence_count": null, "pfam_id": "PF26692", "proteins": 197, "proteomes": 9, "short_name": "DUF8232", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26692", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found usually in tandem in uncharcaterised bacterial proteins. This domain shares similairty to domains members of the Bet v1-like superfamily.", "domain_architectures": 2, "interpro_id": "IPR061774", "known_evidence_count": null, "matches": 263, "name": "Domain of unknown function (DUF8713)", "partial_evidence_count": null, "pfam_id": "PF30732", "proteins": 197, "proteomes": 186, "short_name": "DUF8713", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30732", "structures": 0, "taxa": 377, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 181, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This Domain of unknown function 61 (DUF61) family of proteins are widely distributed in archaea. In crenarchaea, the genes of DUF61 proteins are in an operon containing two genes of box C/D RNA protein complexes. The NMR structure of a DUF61 family member from the hyperthermophilic archaeon Sulfolobus solfataricus revealed a rigid core structure and flexible N- and C-terminal regions, including a negatively-charged independent C-terminal helix. The core structure consists of N- and C-terminal subdomains, in which the C-terminal subdomain shows significant structural similarity with several nucleic acid binding proteins [[cite:PUB00098020]].", "domain_architectures": 1, "interpro_id": "IPR002746", "known_evidence_count": null, "matches": 196, "name": "Protein of unknown function DUF61", "partial_evidence_count": null, "pfam_id": "PF01886", "proteins": 196, "proteomes": 193, "short_name": "DUF61", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01886", "structures": 1, "taxa": 381, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR020216", "known_evidence_count": null, "matches": 196, "name": "Protein of unknown function (DUF2691)", "partial_evidence_count": null, "pfam_id": "PF10903", "proteins": 196, "proteomes": 189, "short_name": "DUF2691", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10903", "structures": 0, "taxa": 321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family is conserved in the Enterobacteriaceae family. Several members are named as YghW. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR022574", "known_evidence_count": null, "matches": 196, "name": "Protein of unknown function (DUF2623)", "partial_evidence_count": null, "pfam_id": "PF11115", "proteins": 196, "proteomes": 196, "short_name": "DUF2623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11115", "structures": 0, "taxa": 296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 107, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is the protein product of the gene XC5848 from Xanthomonas campestris. The protein has no known function however its structure has been determined. The protein adopts a Lsm fold however differences with the fold were observed at the N-terminal and internal regions [[cite:PUB00047306]].", "domain_architectures": 2, "interpro_id": "IPR021649", "known_evidence_count": null, "matches": 196, "name": "Domain of unknown function (DUF3247)", "partial_evidence_count": null, "pfam_id": "PF11607", "proteins": 196, "proteomes": 190, "short_name": "DUF3247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11607", "structures": 1, "taxa": 255, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Domain found on N-termina of few families of uncharacterized Clostridia proteins. Typically followed by a proline-rich domain or other kinds of repeats", "domain_architectures": 25, "interpro_id": "IPR029322", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF4474)", "partial_evidence_count": null, "pfam_id": "PF14751", "proteins": 196, "proteomes": 166, "short_name": "DUF4474", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14751", "structures": 0, "taxa": 358, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 71 and 116 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046120", "known_evidence_count": null, "matches": 196, "name": "Family of unknown function (DUF6117)", "partial_evidence_count": null, "pfam_id": "PF19612", "proteins": 196, "proteomes": 168, "short_name": "DUF6117", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19612", "structures": 0, "taxa": 342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR055896", "known_evidence_count": null, "matches": 196, "name": "Family of unknown function (DUF7473)", "partial_evidence_count": null, "pfam_id": "PF24285", "proteins": 196, "proteomes": 195, "short_name": "DUF7473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24285", "structures": 0, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 5, "interpro_id": "IPR022605", "known_evidence_count": null, "matches": 196, "name": "Protein of unknown function (DUF2920)", "partial_evidence_count": null, "pfam_id": "PF11144", "proteins": 195, "proteomes": 107, "short_name": "DUF2920", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11144", "structures": 0, "taxa": 228, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is primarily found in Clostridia. Proteins in this family are typically between 212 and 271 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046097", "known_evidence_count": null, "matches": 195, "name": "Protein of unknown function (DUF6033)", "partial_evidence_count": null, "pfam_id": "PF19498", "proteins": 195, "proteomes": 94, "short_name": "DUF6033", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19498", "structures": 0, "taxa": 212, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain four predicted transmembrane helices. These proteins are often found in genomic contexts with a glucose-6-phosphate isomerase family proteins, which is usually diver gently transcribed to the gene in this family. SecD and SecF homologoues are also found in the genomic neighbourhood perhaps suggesting a role in secretion. Additionally members of [pfam:PF19129] are found as well.", "domain_architectures": 1, "interpro_id": "IPR058369", "known_evidence_count": null, "matches": 195, "name": "Domain of unknown function (DUF8056)", "partial_evidence_count": null, "pfam_id": "PF26243", "proteins": 195, "proteomes": 195, "short_name": "DUF8056", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26243", "structures": 0, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 188, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halophilic archaea, including members of the Haloarculaceae, Natrialbaceae, and Haloferacaceae families. These proteins are approximately 40-45 residues in length. Structure prediction shows these proteins adopt a helical hairpin structure. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061624", "known_evidence_count": null, "matches": 195, "name": "Family of unknown function (DUF8555)", "partial_evidence_count": null, "pfam_id": "PF29446", "proteins": 195, "proteomes": 195, "short_name": "DUF8555", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29446", "structures": 0, "taxa": 330, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR019205", "known_evidence_count": null, "matches": 194, "name": "Putative transposon-encoded protein (DUF2080)", "partial_evidence_count": null, "pfam_id": "PF09853", "proteins": 194, "proteomes": 131, "short_name": "DUF2080", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09853", "structures": 0, "taxa": 322, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacteroidales.", "domain_architectures": 1, "interpro_id": "IPR021670", "known_evidence_count": null, "matches": 194, "name": "Protein of unknown function (DUF3256)", "partial_evidence_count": null, "pfam_id": "PF11644", "proteins": 194, "proteomes": 191, "short_name": "DUF3256", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11644", "structures": 1, "taxa": 302, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 82, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteria.", "domain_architectures": 1, "interpro_id": "IPR035286", "known_evidence_count": null, "matches": 194, "name": "Family of unknown function (DUF5361)", "partial_evidence_count": null, "pfam_id": "PF17318", "proteins": 194, "proteomes": 182, "short_name": "DUF5361", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17318", "structures": 0, "taxa": 423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes. Proteins in this family are around 230 amino acids in length. They contain the conserved motifs GGxDY and LYxNC in addition to three Y/F conserved residues.", "domain_architectures": 3, "interpro_id": "IPR046693", "known_evidence_count": null, "matches": 195, "name": "Family of unknown function (DUF6563)", "partial_evidence_count": null, "pfam_id": "PF20201", "proteins": 194, "proteomes": 184, "short_name": "DUF6563", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20201", "structures": 0, "taxa": 321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to fold into an alpha-helical hairpin and it is likely associated with the membrane.", "domain_architectures": 2, "interpro_id": "IPR055739", "known_evidence_count": null, "matches": 199, "name": "Domain of unknown function (DUF7315)", "partial_evidence_count": null, "pfam_id": "PF23997", "proteins": 194, "proteomes": 194, "short_name": "DUF7315", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23997", "structures": 0, "taxa": 294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 186, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal sequences.", "domain_architectures": 2, "interpro_id": "IPR055812", "known_evidence_count": null, "matches": 196, "name": "Family of unknown function (DUF7388)", "partial_evidence_count": null, "pfam_id": "PF24114", "proteins": 194, "proteomes": 193, "short_name": "DUF7388", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24114", "structures": 0, "taxa": 332, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of phage proteins. The core structure of these proteins is a conserved four helix bundle. The function of these proteins is unknown.", "domain_architectures": 2, "interpro_id": "IPR056642", "known_evidence_count": null, "matches": 194, "name": "Domain of unknown function (DUF7740)", "partial_evidence_count": null, "pfam_id": "PF24886", "proteins": 194, "proteomes": 170, "short_name": "DUF7740", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24886", "structures": 0, "taxa": 330, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found mostly in Trypanosoma. According to structure predictions it could adopt an ATP-grasp fold which is characterised by two alpha-beta subdomains that grasp the ATP molecules between them [[cite:PUB00020972],[cite:PUB00015342]].", "domain_architectures": 16, "interpro_id": "IPR057680", "known_evidence_count": null, "matches": 258, "name": "Domain of unknown function (DUF7920)", "partial_evidence_count": null, "pfam_id": "PF25536", "proteins": 194, "proteomes": 137, "short_name": "DUF7920", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25536", "structures": 0, "taxa": 493, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found predominantly in halophilic archaea. The proteins in this family are primarily distributed among the Halobacteria class, including families such as Haloferacaceae and Haloarculaceae. The domain is typically found in proteins ranging from 170 to 230 amino acids in length. Many of these proteins exhibit regions of disorder, particularly towards the C-terminal end, which are rich in acidic residues. According to the TED database proteins in this family are composed of three small domains.", "domain_architectures": 1, "interpro_id": "IPR058427", "known_evidence_count": null, "matches": 194, "name": "Family of unknown function (DUF8114)", "partial_evidence_count": null, "pfam_id": "PF26419", "proteins": 194, "proteomes": 193, "short_name": "DUF8114", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26419", "structures": 0, "taxa": 294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Archaeal domain of unknown function.", "domain_architectures": 4, "interpro_id": "IPR007162", "known_evidence_count": null, "matches": 195, "name": "Domain of unknown function (DUF366)", "partial_evidence_count": null, "pfam_id": "PF04017", "proteins": 193, "proteomes": 193, "short_name": "DUF366", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04017", "structures": 1, "taxa": 381, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Bacillales.", "domain_architectures": 4, "interpro_id": "IPR020208", "known_evidence_count": null, "matches": 201, "name": "Protein of unknown function (DUF2712)", "partial_evidence_count": null, "pfam_id": "PF10916", "proteins": 193, "proteomes": 157, "short_name": "DUF2712", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10916", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 133, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 100 residues locates in the C-terminal of some uncharacterized proteins in various Bacteroides and Parabacteroides species. The function of this family remains unknown. It has an Ig like fold.", "domain_architectures": 3, "interpro_id": "IPR032165", "known_evidence_count": null, "matches": 193, "name": "Ig-like domain", "partial_evidence_count": null, "pfam_id": "PF16392", "proteins": 193, "proteomes": 185, "short_name": "DUF5001", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16392", "structures": 1, "taxa": 373, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised Bacteroidia sequences.", "domain_architectures": 1, "interpro_id": "IPR033410", "known_evidence_count": null, "matches": 193, "name": "Domain of unknown function (DUF5119)", "partial_evidence_count": null, "pfam_id": "PF17145", "proteins": 193, "proteomes": 93, "short_name": "DUF5119", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17145", "structures": 1, "taxa": 159, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Lactobacillales.", "domain_architectures": 2, "interpro_id": "IPR035528", "known_evidence_count": null, "matches": 193, "name": "Family of unknown function (DUF5388)", "partial_evidence_count": null, "pfam_id": "PF17363", "proteins": 193, "proteomes": 144, "short_name": "DUF5388", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17363", "structures": 0, "taxa": 251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 2, "interpro_id": "IPR046248", "known_evidence_count": null, "matches": 205, "name": "Family of unknown function (DUF6281)", "partial_evidence_count": null, "pfam_id": "PF19797", "proteins": 193, "proteomes": 173, "short_name": "DUF6281", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19797", "structures": 0, "taxa": 228, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are distantly related to [pfam:PF03625]. Their function is as yet unknown.", "domain_architectures": 1, "interpro_id": "IPR049204", "known_evidence_count": null, "matches": 193, "name": "Family of unknown function (DUF6858)", "partial_evidence_count": null, "pfam_id": "PF21651", "proteins": 193, "proteomes": 182, "short_name": "DUF6858", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21651", "structures": 0, "taxa": 375, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 185, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 2, "interpro_id": "IPR058311", "known_evidence_count": null, "matches": 194, "name": "Domain of unknown function (DUF7998)", "partial_evidence_count": null, "pfam_id": "PF25979", "proteins": 193, "proteomes": 181, "short_name": "DUF7998", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25979", "structures": 0, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are predicted to form a small alpha helical bundle composed of three helices with a fourth perpendicular helix. The three helices are likely to form transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058319", "known_evidence_count": null, "matches": 193, "name": "Domain of unknown function (DUF8006)", "partial_evidence_count": null, "pfam_id": "PF26028", "proteins": 193, "proteomes": 193, "short_name": "DUF8006", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26028", "structures": 0, "taxa": 290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found mainly in Clostridia. Proteins in this family are typically between 103 and 122 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046113", "known_evidence_count": null, "matches": 192, "name": "Family of unknown function (DUF6050)", "partial_evidence_count": null, "pfam_id": "PF19517", "proteins": 192, "proteomes": 135, "short_name": "DUF6050", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19517", "structures": 0, "taxa": 256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins, functionally uncharacterised, is found in bacteria and viruses. Proteins in this family are typically between 341 and 365 amino acids in length. Some members are thought to be coat proteins.", "domain_architectures": 3, "interpro_id": "IPR046227", "known_evidence_count": null, "matches": 193, "name": "Family of unknown function (DUF6260)", "partial_evidence_count": null, "pfam_id": "PF19774", "proteins": 192, "proteomes": 187, "short_name": "DUF6260", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19774", "structures": 2, "taxa": 465, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 87, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicute bacteria and their phage. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046242", "known_evidence_count": null, "matches": 192, "name": "Family of unknown function (DUF6275)", "partial_evidence_count": null, "pfam_id": "PF19791", "proteins": 192, "proteomes": 180, "short_name": "DUF6275", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19791", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of phage proteins of unknown function. AlphaFold shows confident dimer interaction.", "domain_architectures": 1, "interpro_id": "IPR054285", "known_evidence_count": null, "matches": 192, "name": "Domain of unknown function (DUF7020)", "partial_evidence_count": null, "pfam_id": "PF22885", "proteins": 192, "proteomes": 192, "short_name": "DUF7020", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22885", "structures": 0, "taxa": 412, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This uncharacterised protein is found in the T5 bacteriophage. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR054287", "known_evidence_count": null, "matches": 192, "name": "Family of unknown function (DUF7022)", "partial_evidence_count": null, "pfam_id": "PF22887", "proteins": 192, "proteomes": 192, "short_name": "DUF7022", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22887", "structures": 0, "taxa": 423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of an uncharacterised family of phage proteins.", "domain_architectures": 2, "interpro_id": "IPR055765", "known_evidence_count": null, "matches": 192, "name": "Domain of unknown function (DUF7341)", "partial_evidence_count": null, "pfam_id": "PF24030", "proteins": 192, "proteomes": 183, "short_name": "DUF7341", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24030", "structures": 0, "taxa": 372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 275 and 313 amino acids in length. There are two conserved sequence motifs: RGF and DAY. There are two completely conserved residues (P and D) that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR025387", "known_evidence_count": null, "matches": 191, "name": "Domain of unknown function (DUF4299)", "partial_evidence_count": null, "pfam_id": "PF14132", "proteins": 191, "proteomes": 164, "short_name": "DUF4299", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14132", "structures": 0, "taxa": 364, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, archaea and viruses. Proteins in this family are typically between 304 and 335 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046718", "known_evidence_count": null, "matches": 196, "name": "Family of unknown function (DUF6610)", "partial_evidence_count": null, "pfam_id": "PF20314", "proteins": 191, "proteomes": 137, "short_name": "DUF6610", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20314", "structures": 0, "taxa": 320, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 180, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins. They are predicted to fold into a four helical bundle.", "domain_architectures": 1, "interpro_id": "IPR055970", "known_evidence_count": null, "matches": 191, "name": "Family of unknown function (DUF7548)", "partial_evidence_count": null, "pfam_id": "PF24416", "proteins": 191, "proteomes": 188, "short_name": "DUF7548", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24416", "structures": 0, "taxa": 290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. The proteins are composed of an N-terminal three helical bundle followed by an alpha helical region at the C-terminus.", "domain_architectures": 2, "interpro_id": "IPR055992", "known_evidence_count": null, "matches": 191, "name": "Family of unknown function (DUF7570)", "partial_evidence_count": null, "pfam_id": "PF24454", "proteins": 191, "proteomes": 191, "short_name": "DUF7570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24454", "structures": 0, "taxa": 436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 190, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal proteins of unknown function.", "domain_architectures": 6, "interpro_id": "IPR009321", "known_evidence_count": null, "matches": 193, "name": "Protein of unknown function (DUF973)", "partial_evidence_count": null, "pfam_id": "PF06157", "proteins": 190, "proteomes": 53, "short_name": "DUF973", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06157", "structures": 0, "taxa": 156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 172 and 203 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR016489", "known_evidence_count": null, "matches": 190, "name": "Protein of unknown function (DUF3996)", "partial_evidence_count": null, "pfam_id": "PF13161", "proteins": 190, "proteomes": 47, "short_name": "DUF3996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13161", "structures": 0, "taxa": 106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 5, "interpro_id": "IPR027972", "known_evidence_count": null, "matches": 232, "name": "Domain of unknown function (DUF4489)", "partial_evidence_count": null, "pfam_id": "PF14879", "proteins": 190, "proteomes": 93, "short_name": "DUF4489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14879", "structures": 0, "taxa": 173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 90 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown. Structure prediction strongly suggests that four copies of this protein form a homotetramer complex where each monomer forms a single blade of a beta propeller structure. Proteins in this family contain an N-terminal lipoprotein attachment motif.", "domain_architectures": 2, "interpro_id": "IPR032618", "known_evidence_count": null, "matches": 190, "name": "Domain of unknown function (DUF4884)", "partial_evidence_count": null, "pfam_id": "PF16225", "proteins": 190, "proteomes": 190, "short_name": "DUF4884", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16225", "structures": 0, "taxa": 478, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 138, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins. They are predicted to adopt a fold typical for cysteine proteinases and topology similar to that of NlpC/P60 family proteins. These proteins are likely enzymes as they have similar active site architecture.", "domain_architectures": 7, "interpro_id": "IPR056106", "known_evidence_count": null, "matches": 190, "name": "Domain of unknown function (DUF7689)", "partial_evidence_count": null, "pfam_id": "PF24738", "proteins": 190, "proteomes": 164, "short_name": "DUF7689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24738", "structures": 0, "taxa": 539, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 177, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins containing this domain are predominantly found in the class Halobacteria, which includes families such as Haloferacaceae, Natrialbaceae, and Haloarculaceae. The domain is typically found in proteins ranging from 87 to 167 amino acids in length. This domain adopts a four helical bundle structure.", "domain_architectures": 1, "interpro_id": "IPR058465", "known_evidence_count": null, "matches": 190, "name": "Domain of unknown function (DUF8152)", "partial_evidence_count": null, "pfam_id": "PF26479", "proteins": 190, "proteomes": 179, "short_name": "DUF8152", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26479", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharcaterised bacterial proteins. Members of this family are encoded in a surface polysaccharide biosynthesis locus. They are related to the O-antigen polysaccharide polymerase Wzy.", "domain_architectures": 1, "interpro_id": "IPR061773", "known_evidence_count": null, "matches": 190, "name": "Domain of unknown function (DUF8712)", "partial_evidence_count": null, "pfam_id": "PF30730", "proteins": 190, "proteomes": 189, "short_name": "DUF8712", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30730", "structures": 0, "taxa": 424, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "his is a family of microsporidial-specific sequences of unknown function. There is one transmembrane domain towards the C-terminus.", "domain_architectures": 6, "interpro_id": "IPR031537", "known_evidence_count": null, "matches": 196, "name": "Domain of unknown function (DUF5092)", "partial_evidence_count": null, "pfam_id": "PF17010", "proteins": 189, "proteomes": 109, "short_name": "DUF5092", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17010", "structures": 0, "taxa": 322, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes. Proteins in this family are typically between 340 and 430 amino acids in length and have the conserved motifs WAD, RP and TxxG. Some members are hypothetical Fimbrillin-A associated anchor protein Mfa1/Mfa2 and related to [pfam:PF08842].", "domain_architectures": 6, "interpro_id": "IPR046692", "known_evidence_count": null, "matches": 190, "name": "Family of unknown function (DUF6562)", "partial_evidence_count": null, "pfam_id": "PF20200", "proteins": 189, "proteomes": 85, "short_name": "DUF6562", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20200", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised sequences from archaea. This domain may have a beta-sandwich fold.", "domain_architectures": 15, "interpro_id": "IPR055830", "known_evidence_count": null, "matches": 189, "name": "Domain of unknown function (DUF7407)", "partial_evidence_count": null, "pfam_id": "PF24156", "proteins": 189, "proteomes": 178, "short_name": "DUF7407", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24156", "structures": 3, "taxa": 372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 160 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR025056", "known_evidence_count": null, "matches": 188, "name": "Protein of unknown function (DUF3993)", "partial_evidence_count": null, "pfam_id": "PF13158", "proteins": 188, "proteomes": 185, "short_name": "DUF3993", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13158", "structures": 0, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 4, "interpro_id": "IPR027826", "known_evidence_count": null, "matches": 188, "name": "Domain of unknown function (DUF4431)", "partial_evidence_count": null, "pfam_id": "PF14485", "proteins": 188, "proteomes": 174, "short_name": "DUF4431", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14485", "structures": 0, "taxa": 407, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a likely zinc-binding domain found at the C-terminus of the C17orf50 protein found in eukaryotes. Proteins in this family are typically between 142 and 178 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR029174", "known_evidence_count": null, "matches": 188, "name": "C17orf50 C-terminal zinc-binding domain", "partial_evidence_count": null, "pfam_id": "PF15470", "proteins": 188, "proteomes": 164, "short_name": "DUF4637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15470", "structures": 0, "taxa": 588, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 149 and 210 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031534", "known_evidence_count": null, "matches": 191, "name": "Domain of unknown function (DUF4703)", "partial_evidence_count": null, "pfam_id": "PF15775", "proteins": 188, "proteomes": 137, "short_name": "DUF4703", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15775", "structures": 0, "taxa": 431, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacilli. Family members are predicted to have 2 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR020205", "known_evidence_count": null, "matches": 188, "name": "Family of unknown function (DUF5392)", "partial_evidence_count": null, "pfam_id": "PF17370", "proteins": 188, "proteomes": 184, "short_name": "DUF5392", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17370", "structures": 0, "taxa": 267, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 179, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR055743", "known_evidence_count": null, "matches": 188, "name": "Domain of unknown function (DUF7319)", "partial_evidence_count": null, "pfam_id": "PF24003", "proteins": 188, "proteomes": 187, "short_name": "DUF7319", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24003", "structures": 0, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 150 residues in length and is mainly found in Clostridium, Eubacterium, and Ruminococcus species. The function of this family is unknown.", "domain_architectures": 8, "interpro_id": "IPR032257", "known_evidence_count": null, "matches": 187, "name": "Domain of unknown function (DUF4830)", "partial_evidence_count": null, "pfam_id": "PF16112", "proteins": 187, "proteomes": 180, "short_name": "DUF4830", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16112", "structures": 0, "taxa": 361, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 340 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032333", "known_evidence_count": null, "matches": 187, "name": "Domain of unknown function (DUF4857)", "partial_evidence_count": null, "pfam_id": "PF16149", "proteins": 187, "proteomes": 167, "short_name": "DUF4857", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16149", "structures": 0, "taxa": 397, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 158 and 180 amino acids in length. Proteins in this family have a metzincin-like fold and are most closely related to the structure of the YbeY endoribonuclease proteins.", "domain_architectures": 2, "interpro_id": "IPR046589", "known_evidence_count": null, "matches": 187, "name": "Domain of unknown function (DUF6647)", "partial_evidence_count": null, "pfam_id": "PF20352", "proteins": 187, "proteomes": 172, "short_name": "DUF6647", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20352", "structures": 0, "taxa": 345, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of small, about 60 residues in length, bacterial proteins. They are predicted to adopt a globular structure consisting of three helices. The N- and C-terminal helices contain highly conserved aromatic residues in addition to the nearly invariant glycines located at the interhelical connecting loops.", "domain_architectures": 1, "interpro_id": "IPR054234", "known_evidence_count": null, "matches": 187, "name": "Family of unknown function (DUF6961)", "partial_evidence_count": null, "pfam_id": "PF22284", "proteins": 187, "proteomes": 131, "short_name": "DUF6961", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22284", "structures": 0, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 360 and 412 amino acids in length. This entry corresponds to the alpha-helical C-terminal domain.", "domain_architectures": 2, "interpro_id": "IPR056491", "known_evidence_count": null, "matches": 187, "name": "DUF6688 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF23543", "proteins": 187, "proteomes": 184, "short_name": "DUF6688_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23543", "structures": 0, "taxa": 388, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in phage, predominantly those infecting bacteria in the Enterobacteriaceae family such as Escherichia, Salmonella, Klebsiella and Vibrio. The protein is typically around 80 to 100 amino acids in length. In some phage the protein contains a predicted central coiled-coil region. The function of this protein family is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR055603", "known_evidence_count": null, "matches": 187, "name": "Family of unknown function (DUF7179)", "partial_evidence_count": null, "pfam_id": "PF23804", "proteins": 187, "proteomes": 186, "short_name": "DUF7179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23804", "structures": 0, "taxa": 397, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 184, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins from halobacteria. Members are around 100 residues and are predicted to adopt a mainly alpha-configuration.", "domain_architectures": 1, "interpro_id": "IPR057175", "known_evidence_count": null, "matches": 187, "name": "Family of unknown function (DUF7853)", "partial_evidence_count": null, "pfam_id": "PF25251", "proteins": 187, "proteomes": 172, "short_name": "DUF7853", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25251", "structures": 0, "taxa": 280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR025083", "known_evidence_count": null, "matches": 186, "name": "Protein of unknown function (DUF3969)", "partial_evidence_count": null, "pfam_id": "PF13108", "proteins": 186, "proteomes": 156, "short_name": "DUF3969", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13108", "structures": 0, "taxa": 339, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 115 and 196 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR027813", "known_evidence_count": null, "matches": 197, "name": "Domain of unknown function (DUF4642)", "partial_evidence_count": null, "pfam_id": "PF15484", "proteins": 186, "proteomes": 140, "short_name": "DUF4642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15484", "structures": 0, "taxa": 443, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 178, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of uncharacterized proteins is mostly found in Chromadorea. Family members include dct-5 proteins. Dct-5 is a target of DAF-16, a forkhead transcription factor, which is a key regulator of longevity, metabolism and dauer diapause in Caenorhabditis elegans [[cite:PUB00045322]].", "domain_architectures": 6, "interpro_id": "IPR035161", "known_evidence_count": null, "matches": 187, "name": "Family of unknown function (DUF5332)", "partial_evidence_count": null, "pfam_id": "PF17266", "proteins": 186, "proteomes": 90, "short_name": "DUF5332", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17266", "structures": 0, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 179, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are typically between 194 and 253 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046604", "known_evidence_count": null, "matches": 188, "name": "Family of unknown function (DUF6663)", "partial_evidence_count": null, "pfam_id": "PF20368", "proteins": 186, "proteomes": 172, "short_name": "DUF6663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20368", "structures": 0, "taxa": 269, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from Halobacteria. It has detectable sequence similarity to domains members of the N-(deoxy)ribosyltransferase-like superfamily and it is predicted to adopt similar structure.", "domain_architectures": 3, "interpro_id": "IPR055931", "known_evidence_count": null, "matches": 188, "name": "Domain of unknown function (DUF7509)", "partial_evidence_count": null, "pfam_id": "PF24349", "proteins": 186, "proteomes": 147, "short_name": "DUF7509", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24349", "structures": 0, "taxa": 253, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 175, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this integral membrane protein family are found exclusively in halophilic archaea. In at least three species (Haloarcula marismortui, Haloquadratum walsbyi, and Haloferax volcanii), members are found in the gene neighbourhood of archaeosortase A, suggesting a role in protein sorting. Structure prediction show these proteins have four likely transmembrane helices, with a four stranded beta meander inserted between helices one and two. The structure of this domain shows significant structural similarity to claudin proteins. This suggests that these proteins may be accessory components of an as yet unidentified membrane complex.", "domain_architectures": 1, "interpro_id": "IPR058363", "known_evidence_count": null, "matches": 186, "name": "Domain of unknown function (DUF8050)", "partial_evidence_count": null, "pfam_id": "PF26224", "proteins": 186, "proteomes": 186, "short_name": "DUF8050", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26224", "structures": 0, "taxa": 291, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 174, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short archaeal proteins, that are distantly related to [pfam:PF03683].", "domain_architectures": 3, "interpro_id": "IPR055741", "known_evidence_count": null, "matches": 185, "name": "Family of unknown function (DUF7317)", "partial_evidence_count": null, "pfam_id": "PF24001", "proteins": 185, "proteomes": 143, "short_name": "DUF7317", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24001", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-beta structure.", "domain_architectures": 2, "interpro_id": "IPR055953", "known_evidence_count": null, "matches": 186, "name": "Family of unknown function (DUF7531)", "partial_evidence_count": null, "pfam_id": "PF24375", "proteins": 185, "proteomes": 185, "short_name": "DUF7531", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24375", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as yceO however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR024494", "known_evidence_count": null, "matches": 184, "name": "Protein of unknown function (DUF2770)", "partial_evidence_count": null, "pfam_id": "PF10968", "proteins": 184, "proteomes": 184, "short_name": "DUF2770", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10968", "structures": 0, "taxa": 287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 215 and 413 amino acids in length. There is a conserved DSNGYS sequence motif.", "domain_architectures": 9, "interpro_id": "IPR022222", "known_evidence_count": null, "matches": 185, "name": "Protein of unknown function (DUF3747)", "partial_evidence_count": null, "pfam_id": "PF12565", "proteins": 184, "proteomes": 112, "short_name": "DUF3747", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12565", "structures": 0, "taxa": 335, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 70 and 139 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR027930", "known_evidence_count": null, "matches": 184, "name": "Domain of unknown function (DUF4609)", "partial_evidence_count": null, "pfam_id": "PF15382", "proteins": 184, "proteomes": 147, "short_name": "DUF4609", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15382", "structures": 0, "taxa": 511, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function can be found in Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR035228", "known_evidence_count": null, "matches": 184, "name": "Family of unknown function (DUF5340)", "partial_evidence_count": null, "pfam_id": "PF17275", "proteins": 184, "proteomes": 182, "short_name": "DUF5340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17275", "structures": 0, "taxa": 519, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 111, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillaceae.", "domain_architectures": 1, "interpro_id": "IPR035314", "known_evidence_count": null, "matches": 184, "name": "Family of unknown function (DUF5370)", "partial_evidence_count": null, "pfam_id": "PF17340", "proteins": 184, "proteomes": 180, "short_name": "DUF5370", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17340", "structures": 0, "taxa": 254, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt an alpha/beta structure consisting of a cradle-like beta-sheet with alpha-helices pocked on the convex side of it. It contains a highly conserved GYMDFTYF sequence motif that may be of functional importance.", "domain_architectures": 4, "interpro_id": "IPR054269", "known_evidence_count": null, "matches": 184, "name": "Domain of unknown function (DUF7000)", "partial_evidence_count": null, "pfam_id": "PF22526", "proteins": 184, "proteomes": 179, "short_name": "DUF7000", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22526", "structures": 0, "taxa": 446, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical cyanobacterial proteins of around 150 residues in length which seem to be specific to Anabaena species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009824", "known_evidence_count": null, "matches": 183, "name": "Protein of unknown function (DUF1392)", "partial_evidence_count": null, "pfam_id": "PF07154", "proteins": 183, "proteomes": 26, "short_name": "DUF1392", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07154", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 111, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 2 } }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 2, "interpro_id": "IPR018742", "known_evidence_count": null, "matches": 185, "name": "Uncharacterized conserved protein (DUF2290)", "partial_evidence_count": null, "pfam_id": "PF10053", "proteins": 183, "proteomes": 178, "short_name": "DUF2290", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10053", "structures": 0, "taxa": 565, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001281) is described by MIBiG as an example of the following biosynthetic class, polyketide.", "domain_architectures": 2, "interpro_id": "IPR045992", "known_evidence_count": null, "matches": 187, "name": "Family of unknown function (DUF5948)", "partial_evidence_count": null, "pfam_id": "PF19373", "proteins": 183, "proteomes": 92, "short_name": "DUF5948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19373", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046736", "known_evidence_count": null, "matches": 183, "name": "Family of unknown function (DUF6628)", "partial_evidence_count": null, "pfam_id": "PF20333", "proteins": 183, "proteomes": 183, "short_name": "DUF6628", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20333", "structures": 0, "taxa": 216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in phage and bacterial proteins.", "domain_architectures": 2, "interpro_id": "IPR055641", "known_evidence_count": null, "matches": 183, "name": "Domain of unknown function (DUF7217)", "partial_evidence_count": null, "pfam_id": "PF23854", "proteins": 183, "proteomes": 181, "short_name": "DUF7217", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23854", "structures": 0, "taxa": 393, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in putative Ras GEF and other uncharacterised proteins mostly found in fungi. This domain belongs to proteins with a conserved four or five- helix up-and-down bundle structure. This structure is typical of focal adhesion targeting (FAT) domains and is responsible for dimerisation. These proteins are also present in transcriptional regulators where the bundle structure is important for their dynamic conformational equilibrium to control target specificity. The conserved helical bundle architecture enables these proteins to function in protein- protein interactions and regulatory processes [[cite:PUB00075415],[cite:PUB00004911],[cite:PUB00161916]].", "domain_architectures": 7, "interpro_id": "IPR059358", "known_evidence_count": null, "matches": 183, "name": "Domain of unknown function (DUF8314)", "partial_evidence_count": null, "pfam_id": "PF26988", "proteins": 183, "proteomes": 175, "short_name": "DUF8314", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26988", "structures": 0, "taxa": 420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as ywbB however currently there is no known function.", "domain_architectures": 1, "interpro_id": "IPR024250", "known_evidence_count": null, "matches": 182, "name": "Protein of unknown function (DUF2711)", "partial_evidence_count": null, "pfam_id": "PF10924", "proteins": 182, "proteomes": 180, "short_name": "DUF2711", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10924", "structures": 0, "taxa": 388, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as YaiY however no function is known. The family appears to be restricted to Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR020513", "known_evidence_count": null, "matches": 182, "name": "Protein of unknown function (DUF2755)", "partial_evidence_count": null, "pfam_id": "PF10954", "proteins": 182, "proteomes": 180, "short_name": "DUF2755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10954", "structures": 0, "taxa": 263, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a viral family of proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR021404", "known_evidence_count": null, "matches": 182, "name": "Protein of unknown function (DUF2774)", "partial_evidence_count": null, "pfam_id": "PF11242", "proteins": 182, "proteomes": 181, "short_name": "DUF2774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11242", "structures": 0, "taxa": 417, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised bacterial proteins. The protein forms a single beta barrel domain which shows some structural similarity to the N-terminal domain of the PriA protein. However, structure prediction does not support this protein having a DNA-binding function like PriA.", "domain_architectures": 1, "interpro_id": "IPR056088", "known_evidence_count": null, "matches": 182, "name": "Family of unknown function (DUF7671)", "partial_evidence_count": null, "pfam_id": "PF24710", "proteins": 182, "proteomes": 182, "short_name": "DUF7671", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24710", "structures": 0, "taxa": 258, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of phage proteins from Uroviricota. These proteins are about 300 amino acids in length. They may represent phage structural proteins.", "domain_architectures": 7, "interpro_id": "IPR057701", "known_evidence_count": null, "matches": 187, "name": "Family of unknown function (DUF7941)", "partial_evidence_count": null, "pfam_id": "PF25613", "proteins": 182, "proteomes": 38, "short_name": "DUF7941", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25613", "structures": 1, "taxa": 112, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 167, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058309", "known_evidence_count": null, "matches": 182, "name": "Family of unknown function (DUF7996)", "partial_evidence_count": null, "pfam_id": "PF25959", "proteins": 182, "proteomes": 155, "short_name": "DUF7996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25959", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 171, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small N-terminal domain of approximately 40-60 amino acids found exclusively in halophilic archaea. The family is restricted to the order Halobacteriales, particularly the families Natrialbaceae, Haloferacaceae and Haloarculaceae. This domain is consistently found N-terminal to a winged helix-turn-helix domain. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061598", "known_evidence_count": null, "matches": 182, "name": "Domain of unknown function (DUF8528)", "partial_evidence_count": null, "pfam_id": "PF29291", "proteins": 182, "proteomes": 182, "short_name": "DUF8528", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29291", "structures": 0, "taxa": 301, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 87, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001575) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the dipeptide aldehydes biosynthetic gene cluster from Ruminococcus sp. 5_1_39BFAA [[cite:PUB00099391]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR046191", "known_evidence_count": null, "matches": 181, "name": "Family of unknown function (DUF6219)", "partial_evidence_count": null, "pfam_id": "PF19727", "proteins": 181, "proteomes": 101, "short_name": "DUF6219", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19727", "structures": 0, "taxa": 185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically 136 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046660", "known_evidence_count": null, "matches": 181, "name": "Family of unknown function (DUF6769)", "partial_evidence_count": null, "pfam_id": "PF20558", "proteins": 181, "proteomes": 174, "short_name": "DUF6769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20558", "structures": 0, "taxa": 321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial domain of unknown function. The domain is around 270 to 300 amino acids in length. It is found in a variety of bacterial phyla including Actinobacteria, Bacteroidota, Pseudomonadota and Verrucomicrobiota. The domain is also found in some bacterial phages. The function of this domain is unknown. The structure of this domain shows similarity to VWFA domains.", "domain_architectures": 2, "interpro_id": "IPR055616", "known_evidence_count": null, "matches": 181, "name": "Domain of unknown function (DUF7192)", "partial_evidence_count": null, "pfam_id": "PF23822", "proteins": 181, "proteomes": 154, "short_name": "DUF7192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23822", "structures": 0, "taxa": 383, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 172, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to contain transmembrane helices that assemble in a four helical bundle.", "domain_architectures": 5, "interpro_id": "IPR055802", "known_evidence_count": null, "matches": 189, "name": "Domain of unknown function (DUF7378)", "partial_evidence_count": null, "pfam_id": "PF24095", "proteins": 181, "proteomes": 32, "short_name": "DUF7378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24095", "structures": 0, "taxa": 109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 176, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Structure prediction suggests this protein forms a loose arrangement of three alpha helices.", "domain_architectures": 1, "interpro_id": "IPR058282", "known_evidence_count": null, "matches": 181, "name": "Family of unknown function (DUF7976)", "partial_evidence_count": null, "pfam_id": "PF25931", "proteins": 181, "proteomes": 181, "short_name": "DUF7976", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25931", "structures": 0, "taxa": 294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021524", "known_evidence_count": null, "matches": 180, "name": "Protein of unknown function (DUF3188)", "partial_evidence_count": null, "pfam_id": "PF11384", "proteins": 180, "proteomes": 174, "short_name": "DUF3188", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11384", "structures": 0, "taxa": 273, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in Bacteroides, Paraprevotella, and Sphingobacterium. The members in this family are around 550 residues in length.", "domain_architectures": 8, "interpro_id": "IPR032175", "known_evidence_count": null, "matches": 180, "name": "Domain of unknown function (DUF5008)", "partial_evidence_count": null, "pfam_id": "PF16400", "proteins": 180, "proteomes": 134, "short_name": "DUF5008", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16400", "structures": 0, "taxa": 171, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001120) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from the Burkholderia acid biosynthetic gene cluster from Burkholderia thailandensis E264 and appears to be predominantly found in Burkholderiaceae [[cite:PUB00099376],[cite:PUB00099398]]", "domain_architectures": 1, "interpro_id": "IPR046055", "known_evidence_count": null, "matches": 180, "name": "Family of unknown function (DUF6013)", "partial_evidence_count": null, "pfam_id": "PF19476", "proteins": 180, "proteomes": 180, "short_name": "DUF6013", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19476", "structures": 0, "taxa": 212, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000693) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the butirosin A biosynthetic gene cluster from Bacillus circulans and appears to be predominantly found in Bacilli [[cite:PUB00008404],[cite:PUB00076502]].", "domain_architectures": 1, "interpro_id": "IPR046064", "known_evidence_count": null, "matches": 180, "name": "Family of unknown function (DUF6022)", "partial_evidence_count": null, "pfam_id": "PF19486", "proteins": 180, "proteomes": 161, "short_name": "DUF6022", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19486", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a short highly motif that is found in some phage proteins, usually at the N-terminus. The function of this motif is unknown.", "domain_architectures": 5, "interpro_id": "IPR055635", "known_evidence_count": null, "matches": 194, "name": "Family of unknown function (DUF7211)", "partial_evidence_count": null, "pfam_id": "PF23847", "proteins": 180, "proteomes": 59, "short_name": "DUF7211", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23847", "structures": 0, "taxa": 153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Proteins in this family are predicted to form a homodimeric structure.", "domain_architectures": 2, "interpro_id": "IPR058366", "known_evidence_count": null, "matches": 181, "name": "Domain of unknown function (DUF8053)", "partial_evidence_count": null, "pfam_id": "PF26227", "proteins": 180, "proteomes": 121, "short_name": "DUF8053", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26227", "structures": 0, "taxa": 219, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins with no known function. The family is rich in proline residues.", "domain_architectures": 7, "interpro_id": "IPR018904", "known_evidence_count": null, "matches": 182, "name": "Protein of unknown function (DUF2477)", "partial_evidence_count": null, "pfam_id": "PF10631", "proteins": 179, "proteomes": 168, "short_name": "DUF2477", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10631", "structures": 0, "taxa": 657, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 88, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillales.", "domain_architectures": 1, "interpro_id": "IPR035324", "known_evidence_count": null, "matches": 179, "name": "Family of unknown function (DUF5381)", "partial_evidence_count": null, "pfam_id": "PF17353", "proteins": 179, "proteomes": 120, "short_name": "DUF5381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17353", "structures": 0, "taxa": 196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are about 80 amino acids in length and adopt a compact fold composed of a 5 stranded beta sheet with two alpha helices packed on one side. The sheet has a simple 1-2-3-4-5 topology of strands.", "domain_architectures": 1, "interpro_id": "IPR058314", "known_evidence_count": null, "matches": 179, "name": "Family of unknown function (DUF8001)", "partial_evidence_count": null, "pfam_id": "PF26008", "proteins": 179, "proteomes": 175, "short_name": "DUF8001", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26008", "structures": 0, "taxa": 271, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in the Halobacteria class. These proteins are predominantly found in various families within the Methanobacteriota phylum, including Haloferacaceae, Haloarculaceae, and Natrialbaceae. The proteins in this family are typically between 70 to 100 amino acids in length. They are predicted to be integral membrane proteins, often featuring two transmembrane helices. The reviewed protein from Haloferax volcanii ([swissprot:D4GZ12]) is an example of this domain's occurrence.", "domain_architectures": 1, "interpro_id": "IPR058455", "known_evidence_count": null, "matches": 179, "name": "Domain of unknown function (DUF8142)", "partial_evidence_count": null, "pfam_id": "PF26465", "proteins": 179, "proteomes": 179, "short_name": "DUF8142", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26465", "structures": 0, "taxa": 283, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the class Halobacteria, which includes various genera such as Halorubrum, Haloarcula, and Natrialba. The domain is typically found in proteins ranging from 59 to 484 amino acids in length. The proteins in this family are integral membrane proteins usually with four transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR058460", "known_evidence_count": null, "matches": 179, "name": "Domain of unknown function (DUF8147)", "partial_evidence_count": null, "pfam_id": "PF26472", "proteins": 179, "proteomes": 155, "short_name": "DUF8147", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26472", "structures": 0, "taxa": 259, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 173, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several proteins of unknown function from C.elegans. The GO annotation suggests that this protein is involved in nematode development and has a positive regulation on growth rate.", "domain_architectures": 5, "interpro_id": "IPR007883", "known_evidence_count": null, "matches": 184, "name": "Protein of unknown function (DUF713)", "partial_evidence_count": null, "pfam_id": "PF05218", "proteins": 178, "proteomes": 14, "short_name": "DUF713", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05218", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 110 residues in length. Members of this family appear to be found exclusively in Ralstonia solanacearum. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009957", "known_evidence_count": null, "matches": 178, "name": "Protein of unknown function (DUF1484)", "partial_evidence_count": null, "pfam_id": "PF07363", "proteins": 178, "proteomes": 61, "short_name": "DUF1484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07363", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 88, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 230 amino acids in length. This domain is the C terminal of the putative ecf-type sigma factor negative effector.", "domain_architectures": 3, "interpro_id": "IPR022019", "known_evidence_count": null, "matches": 182, "name": "Domain of unknown function (DUF3600)", "partial_evidence_count": null, "pfam_id": "PF12207", "proteins": 178, "proteomes": 167, "short_name": "DUF3600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12207", "structures": 2, "taxa": 223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and viruses, and is approximately 60 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR021096", "known_evidence_count": null, "matches": 178, "name": "Phage related protein", "partial_evidence_count": null, "pfam_id": "PF12472", "proteins": 178, "proteomes": 148, "short_name": "DUF3693", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12472", "structures": 0, "taxa": 314, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised.This family of proteins is found in bacteria. Proteins in this family are typically between 189 and 206 amino acids in length. There are two conserved sequence motifs: PEERWWL and GWR. This family is found in a very sporadic set of bacterial species, suggesting that it may have been horizontally transferred. One protein is annotated as plasmid borne.", "domain_architectures": 3, "interpro_id": "IPR024220", "known_evidence_count": null, "matches": 178, "name": "Protein of unknown function (DUF3780)", "partial_evidence_count": null, "pfam_id": "PF12635", "proteins": 178, "proteomes": 174, "short_name": "DUF3780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12635", "structures": 0, "taxa": 579, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 126, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 115 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046562", "known_evidence_count": null, "matches": 178, "name": "Family of unknown function (DUF6717)", "partial_evidence_count": null, "pfam_id": "PF20475", "proteins": 178, "proteomes": 169, "short_name": "DUF6717", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20475", "structures": 0, "taxa": 425, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in fungi, and is approximately 130 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046629", "known_evidence_count": null, "matches": 180, "name": "Domain of unknown function (DUF6741)", "partial_evidence_count": null, "pfam_id": "PF20526", "proteins": 178, "proteomes": 165, "short_name": "DUF6741", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20526", "structures": 0, "taxa": 402, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a conserved viral protein domain of unknown function (DUF4241). The domain is approximately 130-160 amino acids in length and is found in various bacteriophages and large DNA viruses. The alignment shows several conserved residues, including a highly conserved DCC motif. The protein contains a beta sandwich domain structural.", "domain_architectures": 1, "interpro_id": "IPR055871", "known_evidence_count": null, "matches": 178, "name": "Domain of unknown function (DUF7448)", "partial_evidence_count": null, "pfam_id": "PF24240", "proteins": 178, "proteomes": 178, "short_name": "DUF7448", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24240", "structures": 0, "taxa": 506, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised prokaryotic proteins. They are likely to contain two domains that create a compact elongated structure. Toward the C terminus, these proteins have two highly conserved pairs of cysteines which are likely to be involved in metal coordination.", "domain_architectures": 1, "interpro_id": "IPR056131", "known_evidence_count": null, "matches": 178, "name": "Family of unknown function (DUF7714)", "partial_evidence_count": null, "pfam_id": "PF24830", "proteins": 178, "proteomes": 172, "short_name": "DUF7714", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24830", "structures": 0, "taxa": 339, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It shares similarity with members of the C1q and TNF superfamily.", "domain_architectures": 1, "interpro_id": "IPR061850", "known_evidence_count": null, "matches": 178, "name": "Domain of unknown function (DUF8789)", "partial_evidence_count": null, "pfam_id": "PF31050", "proteins": 178, "proteomes": 113, "short_name": "DUF8789", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31050", "structures": 0, "taxa": 397, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 308 and 484 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR031945", "known_evidence_count": null, "matches": 177, "name": "Domain of unknown function (DUF4775)", "partial_evidence_count": null, "pfam_id": "PF16001", "proteins": 177, "proteomes": 126, "short_name": "DUF4775", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16001", "structures": 0, "taxa": 475, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 161, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 189 and 203 amino acids in length. There are two conserved sequence motifs: PLPL and LGN. There is a single completely conserved residue N that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR032007", "known_evidence_count": null, "matches": 180, "name": "Domain of unknown function (DUF4791)", "partial_evidence_count": null, "pfam_id": "PF16039", "proteins": 177, "proteomes": 64, "short_name": "DUF4791", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16039", "structures": 0, "taxa": 275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins found in bacteria and viruses is functionally uncharacterised. Proteins in this family are typically between 205 and 235 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046213", "known_evidence_count": null, "matches": 177, "name": "Family of unknown function (DUF6246)", "partial_evidence_count": null, "pfam_id": "PF19759", "proteins": 177, "proteomes": 171, "short_name": "DUF6246", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19759", "structures": 0, "taxa": 383, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 360 and 412 amino acids in length. This entry corresponds to the N-terminal integral membrane domain.", "domain_architectures": 2, "interpro_id": "IPR046510", "known_evidence_count": null, "matches": 177, "name": "DUF6688 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20394", "proteins": 177, "proteomes": 172, "short_name": "DUF6688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20394", "structures": 0, "taxa": 367, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. Proteins in this family are approximately 90 amino acids in length and are predominantly found in Deltaproteobacteria. There are several conserved motifs: ExCxGCxR, PxxKW, GxCNFATH and KxNPLKASK.", "domain_architectures": 1, "interpro_id": "IPR047766", "known_evidence_count": null, "matches": 177, "name": "Family of unknown function (DUF6811)", "partial_evidence_count": null, "pfam_id": "PF20657", "proteins": 177, "proteomes": 175, "short_name": "DUF6811", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20657", "structures": 0, "taxa": 372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins predominantly from bacteria. It is predicted to adopt a complex alpha/beta structure. These proteins share similarity with the Clan MA zinc-dependent metallopeptidases.", "domain_architectures": 3, "interpro_id": "IPR057219", "known_evidence_count": null, "matches": 181, "name": "Domain of unknown function (DUF7897)", "partial_evidence_count": null, "pfam_id": "PF25448", "proteins": 177, "proteomes": 144, "short_name": "DUF7897", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25448", "structures": 0, "taxa": 260, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR020490", "known_evidence_count": null, "matches": 176, "name": "Protein of unknown function (DUF2754)", "partial_evidence_count": null, "pfam_id": "PF10953", "proteins": 176, "proteomes": 176, "short_name": "DUF2754", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10953", "structures": 0, "taxa": 251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 151, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 94 and 123 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR027990", "known_evidence_count": null, "matches": 178, "name": "Domain of unknown function (DUF4633)", "partial_evidence_count": null, "pfam_id": "PF15464", "proteins": 176, "proteomes": 148, "short_name": "DUF4633", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15464", "structures": 0, "taxa": 477, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 200 residues in length and is mainly found in various Bacteroides and Parabacteroides species. The function of this family is unknown. This domain is distantly related to lipocalins.", "domain_architectures": 2, "interpro_id": "IPR032575", "known_evidence_count": null, "matches": 176, "name": "Lipocalin-like domain (DUF4923)", "partial_evidence_count": null, "pfam_id": "PF16270", "proteins": 176, "proteomes": 170, "short_name": "DUF4923", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16270", "structures": 0, "taxa": 301, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This BGC (BGC0001740) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the phthoxazolin biosynthetic gene cluster from Streptomyces avermitilis [[cite:PUB00098835]].", "domain_architectures": 2, "interpro_id": "IPR045948", "known_evidence_count": null, "matches": 180, "name": "Family of unknown function (DUF6368)", "partial_evidence_count": null, "pfam_id": "PF19895", "proteins": 176, "proteomes": 162, "short_name": "DUF6368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19895", "structures": 0, "taxa": 322, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 170, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of small proteins mainly from Halobacteria. It contains highly conserved cysteine and histidine residues arranged in two CxxC and HxxC motifs that likely coordinate zinc. This domain is predicted to adopt a fold similar to the classical C2H2 and variant C2HC zinc fingers containing beta-hairpin and an alpha helix. In addition, it is predicted to contain an extra N-terminal strand that contributes to the formation of a three-stranded antiparallel beta-sheet. This domain also has a number of highly conserved negatively charged residues.", "domain_architectures": 1, "interpro_id": "IPR055552", "known_evidence_count": null, "matches": 176, "name": "Domain of unknown function (DUF7128)", "partial_evidence_count": null, "pfam_id": "PF23447", "proteins": 176, "proteomes": 175, "short_name": "DUF7128", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23447", "structures": 0, "taxa": 342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes a group of uncharacterised sequences from bacteria and archaea, which, according to structure predictions, they may have a novel repeat fold. They may consist of 5-6 antiparallel beta-strands decorated with short alpha-helices.", "domain_architectures": 5, "interpro_id": "IPR055905", "known_evidence_count": null, "matches": 179, "name": "Domain of unknown function (DUF7482)", "partial_evidence_count": null, "pfam_id": "PF24298", "proteins": 176, "proteomes": 151, "short_name": "DUF7482", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24298", "structures": 0, "taxa": 426, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain found in DUF7855 family proteins found in halobacteria. This domain is predicted to mediate dimerisation as well as DNA-binding. This domain belongs to the dimeric alpha/beta barrel superfamily. There is a notable pocket in each subunit beneath the DNA-binding interface that might might to a small molecule to regulate DNA-binding. The protein A0A371M7Z4 appears to bind to the DNA sequence GAGGTTACCTGGGCCAGGTAACCTC (pTM-0.9 iPTM=0.89).", "domain_architectures": 2, "interpro_id": "IPR057177", "known_evidence_count": null, "matches": 176, "name": "DUF7855 N-terminal dimerisation domain", "partial_evidence_count": null, "pfam_id": "PF25253", "proteins": 176, "proteomes": 176, "short_name": "DUF7855", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25253", "structures": 0, "taxa": 264, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 166, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 2, "interpro_id": "IPR058291", "known_evidence_count": null, "matches": 177, "name": "Family of unknown function (DUF7985)", "partial_evidence_count": null, "pfam_id": "PF25946", "proteins": 176, "proteomes": 114, "short_name": "DUF7985", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25946", "structures": 0, "taxa": 193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of Halobacterial proteins that are composed of an N-terminal helical bundle domain followed by a C-terminal tail with three short conserved motifs within it.", "domain_architectures": 1, "interpro_id": "IPR058370", "known_evidence_count": null, "matches": 176, "name": "Family of unknown function (DUF8057)", "partial_evidence_count": null, "pfam_id": "PF26244", "proteins": 176, "proteomes": 170, "short_name": "DUF8057", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26244", "structures": 0, "taxa": 262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This repeat is found as seven tandem copies in carbohydrate-binding proteins, including Fucose-binding Lectin from Photorhabdus laumondii ([swissprot:Q7N8J0]) and similar fungal and bacterial proteins. It is composed of beta-strands and forms a seven-bladed beta-propeller structure [[cite:PUB00100843],[cite:PUB00100844]]. It is found in association with BNR repeats, which also form a beta-propeller.", "domain_architectures": 53, "interpro_id": "IPR007132", "known_evidence_count": null, "matches": 538, "name": "Repeat of unknown function (DUF346)", "partial_evidence_count": null, "pfam_id": "PF03984", "proteins": 175, "proteomes": 134, "short_name": "DUF346", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03984", "structures": 0, "taxa": 352, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 7 } }, "demotion_reasons": [], "description": "This entry describes a domain of unkown function found generally at the N-terminal of YubA and YubB in enterobacteriaceae. This domain is mostly found in Escherichia coli, Salmonella typhimurium and Shigella species. YubA and YubB have not been fully functionally characterised. YubB was identified as undecaprenyl diphosphate phosphatase (UPPP) due to its association with cell wall synthesis and bacitracin resistance when disrupted. YubA was inferred to be a transporter, possibly related to cell wall synthesis, based on its predicted membrane protein structure and its genomic association with the UPPP gene. These experiments were done using transposon mutagenesis [[cite:PUB00160281]].", "domain_architectures": 3, "interpro_id": "IPR009694", "known_evidence_count": null, "matches": 175, "name": "Protein of unknown function (DUF1281)", "partial_evidence_count": null, "pfam_id": "PF06924", "proteins": 175, "proteomes": 119, "short_name": "DUF1281", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06924", "structures": 1, "taxa": 215, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021240", "known_evidence_count": null, "matches": 175, "name": "Protein of unknown function (DUF2776)", "partial_evidence_count": null, "pfam_id": "PF10951", "proteins": 175, "proteomes": 171, "short_name": "DUF2776", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10951", "structures": 0, "taxa": 332, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family of proteins is found in mammals. There is a conserved KVKPL sequence motif.", "domain_architectures": 3, "interpro_id": "IPR031711", "known_evidence_count": null, "matches": 175, "name": "Domain of unknown function (DUF4724)", "partial_evidence_count": null, "pfam_id": "PF15852", "proteins": 175, "proteomes": 97, "short_name": "DUF4724", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15852", "structures": 0, "taxa": 332, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised bacterial proteins.", "domain_architectures": 3, "interpro_id": "IPR056127", "known_evidence_count": null, "matches": 175, "name": "Domain of unknown function (DUF7710)", "partial_evidence_count": null, "pfam_id": "PF24819", "proteins": 175, "proteomes": 174, "short_name": "DUF7710", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24819", "structures": 0, "taxa": 387, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 160, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins from halobacteria.", "domain_architectures": 4, "interpro_id": "IPR057178", "known_evidence_count": null, "matches": 176, "name": "Family of unknown function (DUF7856)", "partial_evidence_count": null, "pfam_id": "PF25254", "proteins": 175, "proteomes": 175, "short_name": "DUF7856", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25254", "structures": 0, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. This entry contains a predicted compact alpha helical domain.", "domain_architectures": 1, "interpro_id": "IPR058368", "known_evidence_count": null, "matches": 175, "name": "Domain of unknown function (DUF8055)", "partial_evidence_count": null, "pfam_id": "PF26240", "proteins": 175, "proteomes": 168, "short_name": "DUF8055", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26240", "structures": 0, "taxa": 272, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of a series of repeated sequences from one hypothetical protein ([swissprot:Q96WV6]) found in Schizosaccharomyces pombe. The function of this family is unknown.", "domain_architectures": 64, "interpro_id": "IPR009306", "known_evidence_count": null, "matches": 325, "name": "Schizosaccharomyces pombe repeat of unknown function (DUF963)", "partial_evidence_count": null, "pfam_id": "PF06131", "proteins": 174, "proteomes": 151, "short_name": "DUF963", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06131", "structures": 0, "taxa": 813, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in vertebrates. Proteins in this family are typically between 40 and 110 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR031714", "known_evidence_count": null, "matches": 176, "name": "Domain of unknown function (DUF4726)", "partial_evidence_count": null, "pfam_id": "PF15855", "proteins": 174, "proteomes": 132, "short_name": "DUF4726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15855", "structures": 0, "taxa": 438, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses, as well as in bacteria. It is predicted to be a pentapeptide repeat-containing protein.", "domain_architectures": 5, "interpro_id": "IPR043919", "known_evidence_count": null, "matches": 174, "name": "Family of unknown function (DUF5758)", "partial_evidence_count": null, "pfam_id": "PF19062", "proteins": 174, "proteomes": 142, "short_name": "DUF5758", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19062", "structures": 0, "taxa": 327, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 105 and 121 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046140", "known_evidence_count": null, "matches": 174, "name": "Family of unknown function (DUF6142)", "partial_evidence_count": null, "pfam_id": "PF19639", "proteins": 174, "proteomes": 173, "short_name": "DUF6142", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19639", "structures": 0, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 157, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain three predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058324", "known_evidence_count": null, "matches": 174, "name": "Family of unknown function (DUF8011)", "partial_evidence_count": null, "pfam_id": "PF26041", "proteins": 174, "proteomes": 125, "short_name": "DUF8011", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26041", "structures": 0, "taxa": 234, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 163, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins contains a domain with a five stranded beta sheet with helices packed against one face.", "domain_architectures": 3, "interpro_id": "IPR058367", "known_evidence_count": null, "matches": 175, "name": "Domain of unknown function (DUF8572)", "partial_evidence_count": null, "pfam_id": "PF26239", "proteins": 174, "proteomes": 173, "short_name": "DUF8572", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26239", "structures": 0, "taxa": 261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the C-terminal domain in a group of uncharacterised proteins from halobacteria. Members are around 100 residues and are predicted to adopt an alpha-helical domain.", "domain_architectures": 1, "interpro_id": "IPR058577", "known_evidence_count": null, "matches": 174, "name": "Family of unknown function (DUF7855) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26293", "proteins": 174, "proteomes": 174, "short_name": "DUF7855_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26293", "structures": 0, "taxa": 262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length. There are two conserved sequence motifs: EATN and KGYAI.", "domain_architectures": 1, "interpro_id": "IPR046137", "known_evidence_count": null, "matches": 173, "name": "Family of unknown function (DUF6139)", "partial_evidence_count": null, "pfam_id": "PF19636", "proteins": 173, "proteomes": 173, "short_name": "DUF6139", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19636", "structures": 0, "taxa": 216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of bacterial proteins that have an alpha/alpha(6) toroid structure. This suggests that these proteins are likely to be an as yet uncharacterised family of glycosyl hydrolases.", "domain_architectures": 1, "interpro_id": "IPR054197", "known_evidence_count": null, "matches": 173, "name": "Domain of unknown function (DUF6902)", "partial_evidence_count": null, "pfam_id": "PF21843", "proteins": 173, "proteomes": 171, "short_name": "DUF6902", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21843", "structures": 0, "taxa": 253, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins from halobacteria. Members are around 100 residues and are predicted to adopt an N-terminal subdomain composed of two alpha helices with a C-terminal alpha/beta domain. The N-terminal subdomain appears to mediate homodimerisation A0A1G9SIF6 (AlphaFold 3 ipTM=0.69 pTM=0.68).", "domain_architectures": 1, "interpro_id": "IPR057176", "known_evidence_count": null, "matches": 173, "name": "Family of unknown function (DUF7854)", "partial_evidence_count": null, "pfam_id": "PF25252", "proteins": 173, "proteomes": 173, "short_name": "DUF7854", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25252", "structures": 0, "taxa": 258, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins from halobacteria. Members are predicted to adopt a mainly alpha configuration.", "domain_architectures": 1, "interpro_id": "IPR057180", "known_evidence_count": null, "matches": 173, "name": "Family of unknown function (DUF7858)", "partial_evidence_count": null, "pfam_id": "PF25257", "proteins": 173, "proteomes": 173, "short_name": "DUF7858", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25257", "structures": 0, "taxa": 263, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Acid-adaptive protein possibly of physiological significance when H.pylori colonises the human stomach, which adopts a unique four alpha-helical triangular conformations. The biologically active form is thought to be a tetramer. The protein is expressed along with six other proteins, some of which are related to iron storage and haem biosynthesis [[cite:PUB00039697]].", "domain_architectures": 2, "interpro_id": "IPR018563", "known_evidence_count": null, "matches": 172, "name": "Domain of unknown function (DUF2018)", "partial_evidence_count": null, "pfam_id": "PF09442", "proteins": 172, "proteomes": 172, "short_name": "DUF2018", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09442", "structures": 5, "taxa": 271, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 6, "interpro_id": "", "known_evidence_count": null, "matches": 173, "name": "Protein of unknown function (DUF3161)", "partial_evidence_count": null, "pfam_id": "PF11362", "proteins": 172, "proteomes": 144, "short_name": "DUF3161", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11362", "structures": 0, "taxa": 588, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This putative zinc finger domain is found in uncharacterised bacterial proteins.", "domain_architectures": 8, "interpro_id": "IPR027872", "known_evidence_count": null, "matches": 173, "name": "Domain of unknown function (DUF4428)", "partial_evidence_count": null, "pfam_id": "PF14471", "proteins": 172, "proteomes": 161, "short_name": "DUF4428", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14471", "structures": 0, "taxa": 376, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicute bacteria. Proteins in this family are typically between 83 and 94 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046085", "known_evidence_count": null, "matches": 172, "name": "Family of unknown function (DUF6103)", "partial_evidence_count": null, "pfam_id": "PF19598", "proteins": 172, "proteomes": 97, "short_name": "DUF6103", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19598", "structures": 0, "taxa": 240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins either as standalone or in combination with other domains. It is predicted to adopt an alpha-beta structure with ferredoxin-like topology.", "domain_architectures": 2, "interpro_id": "IPR054231", "known_evidence_count": null, "matches": 172, "name": "Domain of unknown function (DUF6956)", "partial_evidence_count": null, "pfam_id": "PF22273", "proteins": 172, "proteomes": 104, "short_name": "DUF6956", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22273", "structures": 0, "taxa": 181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several uncharacterised Baculovirus proteins.", "domain_architectures": 2, "interpro_id": "IPR007827", "known_evidence_count": null, "matches": 171, "name": "Protein of unknown function (DUF705)", "partial_evidence_count": null, "pfam_id": "PF05152", "proteins": 171, "proteomes": 166, "short_name": "DUF705", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05152", "structures": 5, "taxa": 408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are approximately 150 amino acids in length. The proteins are described as coiled-coil domain-containing protein ENSP00000299415-like.", "domain_architectures": 3, "interpro_id": "IPR031678", "known_evidence_count": null, "matches": 172, "name": "Domain of unknown function (DUF4715)", "partial_evidence_count": null, "pfam_id": "PF15835", "proteins": 171, "proteomes": 169, "short_name": "DUF4715", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15835", "structures": 0, "taxa": 578, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of archaeal sequences.", "domain_architectures": 2, "interpro_id": "IPR055813", "known_evidence_count": null, "matches": 171, "name": "Domain of unknown function (DUF7389)", "partial_evidence_count": null, "pfam_id": "PF24115", "proteins": 171, "proteomes": 105, "short_name": "DUF7389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24115", "structures": 0, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein family found exclusively in spirochaetes, predominantly from Treponema and Leptospira species. The proteins are approximately 125 residues in length. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061583", "known_evidence_count": null, "matches": 171, "name": "Domain of unknown function (DUF8513)", "partial_evidence_count": null, "pfam_id": "PF29211", "proteins": 171, "proteomes": 171, "short_name": "DUF8513", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29211", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR024469", "known_evidence_count": null, "matches": 170, "name": "Protein of unknown function (DUF2538)", "partial_evidence_count": null, "pfam_id": "PF10804", "proteins": 170, "proteomes": 159, "short_name": "DUF2538", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10804", "structures": 1, "taxa": 245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 202 and 224 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031499", "known_evidence_count": null, "matches": 172, "name": "Domain of unknown function (DUF4689)", "partial_evidence_count": null, "pfam_id": "PF15755", "proteins": 170, "proteomes": 150, "short_name": "DUF4689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15755", "structures": 0, "taxa": 515, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 165 and 185 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046719", "known_evidence_count": null, "matches": 170, "name": "Family of unknown function (DUF6611)", "partial_evidence_count": null, "pfam_id": "PF20315", "proteins": 170, "proteomes": 158, "short_name": "DUF6611", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20315", "structures": 0, "taxa": 230, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 150 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046581", "known_evidence_count": null, "matches": 170, "name": "Family of unknown function (DUF6641)", "partial_evidence_count": null, "pfam_id": "PF20346", "proteins": 170, "proteomes": 134, "short_name": "DUF6641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20346", "structures": 0, "taxa": 310, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 145, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains several conserved cysteine residues that may be involved in metal coordination.", "domain_architectures": 7, "interpro_id": "IPR059458", "known_evidence_count": null, "matches": 171, "name": "Domain of unknown function (DUF8414)", "partial_evidence_count": null, "pfam_id": "PF28477", "proteins": 170, "proteomes": 87, "short_name": "DUF8414", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28477", "structures": 0, "taxa": 248, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found at the N-terminal of a group of uncharacterised sequences from bacteria, found associated with [pfam:PF19672] at the C-terminal. This domain may adopt an elongated fold consisting of three beta-strands and three alpha-helices.", "domain_architectures": 4, "interpro_id": "IPR061665", "known_evidence_count": null, "matches": 171, "name": "Domain of unknown function (DUF8604)", "partial_evidence_count": null, "pfam_id": "PF29985", "proteins": 170, "proteomes": 159, "short_name": "DUF8604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29985", "structures": 0, "taxa": 334, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains a number of viral proteins of unknown function approximately 200 residues long. Family members seem to be restricted to badnaviruses.", "domain_architectures": 23, "interpro_id": "IPR010746", "known_evidence_count": null, "matches": 176, "name": "Protein of unknown function (DUF1319)", "partial_evidence_count": null, "pfam_id": "PF07028", "proteins": 169, "proteomes": 66, "short_name": "DUF1319", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07028", "structures": 0, "taxa": 183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. Many of these proteins are annotated as gp11, but the origin of this annotation is unclear. Structure prediction shows this protein adopts an alpha helical fold.", "domain_architectures": 2, "interpro_id": "IPR055794", "known_evidence_count": null, "matches": 169, "name": "Family of unknown function (DUF7370)", "partial_evidence_count": null, "pfam_id": "PF24085", "proteins": 169, "proteomes": 162, "short_name": "DUF7370", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24085", "structures": 0, "taxa": 368, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised eukaryotic proteins. It contains six highly conserved cysteines which are predicted to form disulfide bonds. This domain is predicted to adopt structure similar to C-type lectins.", "domain_architectures": 46, "interpro_id": "IPR055918", "known_evidence_count": null, "matches": 455, "name": "Domain of unknown function (DUF7495)", "partial_evidence_count": null, "pfam_id": "PF24325", "proteins": 169, "proteomes": 35, "short_name": "DUF7495", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24325", "structures": 0, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from bacteria and eukaryotes. It is predicted to fold into a globular structure composed of a mixed beta-sheet and alpha-helices packed on both sides of it. It contains several conserved cysteine residues which are predicted to form disulfide bonds. In addition, there highly conserved aspartate, glutamate and histidine residues suggesting that some members may have enzymatic activity.", "domain_architectures": 11, "interpro_id": "IPR059405", "known_evidence_count": null, "matches": 187, "name": "Domain of unknown function (DUF8361)", "partial_evidence_count": null, "pfam_id": "PF27674", "proteins": 169, "proteomes": 59, "short_name": "DUF8361", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27674", "structures": 0, "taxa": 249, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins appear to be restricted to Enterobacteriaceae. Some members in the family are annotated as YjeO however no function for this protein is currently known.", "domain_architectures": 1, "interpro_id": "IPR022553", "known_evidence_count": null, "matches": 168, "name": "Protein of unknown function (DUF2645)", "partial_evidence_count": null, "pfam_id": "PF10840", "proteins": 168, "proteomes": 125, "short_name": "DUF2645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10840", "structures": 0, "taxa": 216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025034", "known_evidence_count": null, "matches": 168, "name": "Protein of unknown function (DUF3948)", "partial_evidence_count": null, "pfam_id": "PF13134", "proteins": 168, "proteomes": 33, "short_name": "DUF3948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13134", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in mammals. In human this protein is known as C4orf36.", "domain_architectures": 2, "interpro_id": "IPR027825", "known_evidence_count": null, "matches": 168, "name": "Protein of unknown function (DUF4522)", "partial_evidence_count": null, "pfam_id": "PF15022", "proteins": 168, "proteomes": 151, "short_name": "DUF4522", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15022", "structures": 0, "taxa": 527, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 300 residues in length and is mainly found in various Clostridium species. The function of this family is unknown.", "domain_architectures": 6, "interpro_id": "IPR032290", "known_evidence_count": null, "matches": 168, "name": "Domain of unknown function (DUF4839)", "partial_evidence_count": null, "pfam_id": "PF16127", "proteins": 168, "proteomes": 166, "short_name": "DUF4839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16127", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 514 and 521 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046661", "known_evidence_count": null, "matches": 187, "name": "Family of unknown function (DUF6770)", "partial_evidence_count": null, "pfam_id": "PF20559", "proteins": 168, "proteomes": 148, "short_name": "DUF6770", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20559", "structures": 0, "taxa": 251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a beta-propeller domain found in a group on uncharacterised proteins from fungi. The function of this domain is unknown.", "domain_architectures": 11, "interpro_id": "IPR055525", "known_evidence_count": null, "matches": 171, "name": "Domain of unknown function (DUF7099)", "partial_evidence_count": null, "pfam_id": "PF23388", "proteins": 168, "proteomes": 155, "short_name": "DUF7099", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23388", "structures": 0, "taxa": 352, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins that have a small N-terminal domain composed of three beta strands and an alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055726", "known_evidence_count": null, "matches": 168, "name": "Family of unknown function (DUF7302)", "partial_evidence_count": null, "pfam_id": "PF23976", "proteins": 168, "proteomes": 164, "short_name": "DUF7302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23976", "structures": 0, "taxa": 424, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Streptococcus thermophilus bacteriophage proteins of around 130 residues in length. One of the sequences in this family, from phage Sfi11 ([swissprot:O80186]) is known as Gp149. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009796", "known_evidence_count": null, "matches": 167, "name": "Protein of unknown function (DUF1366)", "partial_evidence_count": null, "pfam_id": "PF07104", "proteins": 167, "proteomes": 146, "short_name": "DUF1366", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07104", "structures": 0, "taxa": 307, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins. Their exact function has not, as yet, been described.", "domain_architectures": 2, "interpro_id": "IPR015235", "known_evidence_count": null, "matches": 167, "name": "Domain of unknown function (DUF1937)", "partial_evidence_count": null, "pfam_id": "PF09152", "proteins": 167, "proteomes": 142, "short_name": "DUF1937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09152", "structures": 1, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR012356", "known_evidence_count": null, "matches": 167, "name": "Uncharacterized protein conserved in archaea (DUF2112)", "partial_evidence_count": null, "pfam_id": "PF09885", "proteins": 167, "proteomes": 158, "short_name": "DUF2112", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09885", "structures": 0, "taxa": 302, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 155, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical archaeal proteins have no known function.", "domain_architectures": 5, "interpro_id": "IPR019254", "known_evidence_count": null, "matches": 225, "name": "Uncharacterized protein conserved in archaea (DUF2250)", "partial_evidence_count": null, "pfam_id": "PF10007", "proteins": 167, "proteomes": 159, "short_name": "DUF2250", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10007", "structures": 0, "taxa": 403, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR018747", "known_evidence_count": null, "matches": 167, "name": "Uncharacterized conserved protein (DUF2299)", "partial_evidence_count": null, "pfam_id": "PF10061", "proteins": 167, "proteomes": 127, "short_name": "DUF2299", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10061", "structures": 1, "taxa": 286, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of short, approx 65 residue-long, bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR025065", "known_evidence_count": null, "matches": 167, "name": "Family of unknown function (DUF4006)", "partial_evidence_count": null, "pfam_id": "PF13179", "proteins": 167, "proteomes": 167, "short_name": "DUF4006", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13179", "structures": 0, "taxa": 253, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 340 residues in length and is mainly found in various Bacteroides and Prevotella species. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR032509", "known_evidence_count": null, "matches": 167, "name": "Domain of unknown function (DUF4973)", "partial_evidence_count": null, "pfam_id": "PF16343", "proteins": 167, "proteomes": 104, "short_name": "DUF4973", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16343", "structures": 4, "taxa": 173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": { "TraitMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 297 and 311 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046618", "known_evidence_count": null, "matches": 167, "name": "Family of unknown function (DUF6731)", "partial_evidence_count": null, "pfam_id": "PF20505", "proteins": 167, "proteomes": 162, "short_name": "DUF6731", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20505", "structures": 0, "taxa": 505, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 165, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised nematode proteins. It is predicted to adopt a globular alpha/beta structure.", "domain_architectures": 14, "interpro_id": "IPR055805", "known_evidence_count": null, "matches": 206, "name": "Domain of unknown function (DUF7381)", "partial_evidence_count": null, "pfam_id": "PF24100", "proteins": 167, "proteomes": 4, "short_name": "DUF7381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24100", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 158, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This immunoglobulin-like (Ig-like) domain is found in a group of uncharacterised proteins from worms. It has several highly conserved W, Y and C residues. Its specific function is unknown.", "domain_architectures": 5, "interpro_id": "IPR059435", "known_evidence_count": null, "matches": 168, "name": "Domain of unknown function (DUF8391)", "partial_evidence_count": null, "pfam_id": "PF28429", "proteins": 167, "proteomes": 98, "short_name": "DUF8391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28429", "structures": 0, "taxa": 225, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR041008", "known_evidence_count": null, "matches": 166, "name": "Domain of unknown function (DUF5625)", "partial_evidence_count": null, "pfam_id": "PF18539", "proteins": 166, "proteomes": 94, "short_name": "DUF5625", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18539", "structures": 1, "taxa": 213, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000755) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the capsular polysaccharide biosynthetic gene cluster from Avibacterium paragallinarum 221 [[cite:PUB00098895]]. This family appears to be predominantly found in Actinobacteria and Firmicutes.", "domain_architectures": 3, "interpro_id": "IPR045654", "known_evidence_count": null, "matches": 166, "name": "Family of unknown function (DUF6395)", "partial_evidence_count": null, "pfam_id": "PF19932", "proteins": 166, "proteomes": 163, "short_name": "DUF6395", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19932", "structures": 0, "taxa": 273, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 117 and 141 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046559", "known_evidence_count": null, "matches": 166, "name": "Family of unknown function (DUF6713)", "partial_evidence_count": null, "pfam_id": "PF20460", "proteins": 166, "proteomes": 163, "short_name": "DUF6713", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20460", "structures": 0, "taxa": 401, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. They are predicted to adopt a globular structure consisting of an antiparallel beta-sheet and alpha helix packed on it. Most members contain a highly conserved HhW sequence motif where h is hydrophobic residue.", "domain_architectures": 1, "interpro_id": "IPR056111", "known_evidence_count": null, "matches": 166, "name": "Domain of unknown function (DUF7694)", "partial_evidence_count": null, "pfam_id": "PF24746", "proteins": 166, "proteomes": 159, "short_name": "DUF7694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24746", "structures": 0, "taxa": 476, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 154, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into a beta-sandwich with structural similarity to Transthyretin-like domains in particular to SPH (Self-Incompatibility Protein Homologue) proteins.", "domain_architectures": 2, "interpro_id": "IPR056673", "known_evidence_count": null, "matches": 183, "name": "Domain of unknown function (DUF7771)", "partial_evidence_count": null, "pfam_id": "PF24974", "proteins": 166, "proteomes": 37, "short_name": "DUF7771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24974", "structures": 0, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 159, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in various archaea, particularly within the Halobacteria class. The proteins in this family are typically around 340 amino acids in length. According to the TED database these proteins are composed of three domains that are nested within each other. The outer domain is composed of six transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR058440", "known_evidence_count": null, "matches": 166, "name": "Family of unknown function (DUF8127)", "partial_evidence_count": null, "pfam_id": "PF26448", "proteins": 166, "proteomes": 111, "short_name": "DUF8127", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26448", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 2, "interpro_id": "IPR004884", "known_evidence_count": null, "matches": 165, "name": "Protein of unknown function, DUF261", "partial_evidence_count": null, "pfam_id": "PF03196", "proteins": 165, "proteomes": 33, "short_name": "DUF261", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03196", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 150, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in eukaryotes. This domain is about 80 amino acids in length and is found associated with [pfam:PF08246], and [pfam:PF00112].", "domain_architectures": 7, "interpro_id": "IPR021981", "known_evidence_count": null, "matches": 167, "name": "Protein of unknown function (DUF3586)", "partial_evidence_count": null, "pfam_id": "PF12131", "proteins": 165, "proteomes": 29, "short_name": "DUF3586", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12131", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of gut microbes of unknown function.", "domain_architectures": 2, "interpro_id": "IPR031344", "known_evidence_count": null, "matches": 168, "name": "Domain of unknown function (DUF5104)", "partial_evidence_count": null, "pfam_id": "PF17117", "proteins": 165, "proteomes": 97, "short_name": "DUF5104", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17117", "structures": 1, "taxa": 220, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR040988", "known_evidence_count": null, "matches": 165, "name": "Domain of unknown function (DUF5618)", "partial_evidence_count": null, "pfam_id": "PF18498", "proteins": 165, "proteomes": 46, "short_name": "DUF5618", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18498", "structures": 1, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal of a group of proteins that is functionally uncharacterised, found in bacteria. This domain may adopt a fold similar to that in TolB_N superfamily.", "domain_architectures": 2, "interpro_id": "IPR046173", "known_evidence_count": null, "matches": 165, "name": "Domain of unknown function (DUF6175)", "partial_evidence_count": null, "pfam_id": "PF19672", "proteins": 165, "proteomes": 155, "short_name": "DUF6175", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19672", "structures": 0, "taxa": 316, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 220 and 300 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046556", "known_evidence_count": null, "matches": 165, "name": "Family of unknown function (DUF6710)", "partial_evidence_count": null, "pfam_id": "PF20457", "proteins": 165, "proteomes": 132, "short_name": "DUF6710", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20457", "structures": 0, "taxa": 382, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The domain is around 80 amino acids in length. It occurs in phage that infect a variety of bacteria including Escherichia, Salmonella, Shigella, Klebsiella, Vibrio, Pantoea, Pectobacterium, Yersinia and Serratia.", "domain_architectures": 1, "interpro_id": "IPR055601", "known_evidence_count": null, "matches": 165, "name": "Family of unknown function (DUF7177)", "partial_evidence_count": null, "pfam_id": "PF23801", "proteins": 165, "proteomes": 164, "short_name": "DUF7177", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23801", "structures": 0, "taxa": 346, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of fungal proteins with unknown function. A member of this family has been found to localise in the mitochondria [[cite:PUB00016470]].", "domain_architectures": 4, "interpro_id": "IPR012470", "known_evidence_count": null, "matches": 164, "name": "Protein of unknown function (DUF1689)", "partial_evidence_count": null, "pfam_id": "PF07954", "proteins": 164, "proteomes": 136, "short_name": "DUF1689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07954", "structures": 0, "taxa": 290, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 138, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018685", "known_evidence_count": null, "matches": 164, "name": "Uncharacterized conserved protein (DUF2173)", "partial_evidence_count": null, "pfam_id": "PF09941", "proteins": 164, "proteomes": 81, "short_name": "DUF2173", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09941", "structures": 0, "taxa": 195, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of N-terminal of several uncharacterized proteins and peptidases around 360 residues in length and is mainly found in various Streptomyces species. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032490", "known_evidence_count": null, "matches": 164, "name": "Domain of unknown function (DUF5047)", "partial_evidence_count": null, "pfam_id": "PF16466", "proteins": 164, "proteomes": 152, "short_name": "DUF5047", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16466", "structures": 0, "taxa": 262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 156, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found mostly in Eukaryota.", "domain_architectures": 4, "interpro_id": "IPR035274", "known_evidence_count": null, "matches": 175, "name": "Family of unknown function (DUF5352)", "partial_evidence_count": null, "pfam_id": "PF17303", "proteins": 164, "proteomes": 35, "short_name": "DUF5352", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17303", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of largely cyanobacterial proteins of unknown function. Predictions of structure suggest a non-globular alpha helical fold.", "domain_architectures": 1, "interpro_id": "IPR058286", "known_evidence_count": null, "matches": 164, "name": "Family of unknown function (DUF7980)", "partial_evidence_count": null, "pfam_id": "PF25937", "proteins": 164, "proteomes": 156, "short_name": "DUF7980", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25937", "structures": 0, "taxa": 449, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 144, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR012025", "known_evidence_count": null, "matches": 163, "name": "Uncharacterized protein conserved in archaea (DUF2102)", "partial_evidence_count": null, "pfam_id": "PF09875", "proteins": 163, "proteomes": 158, "short_name": "DUF2102", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09875", "structures": 0, "taxa": 302, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Cyanobacteria. Most of the family members are predicted to have several trans-membrane regions.", "domain_architectures": 2, "interpro_id": "IPR020360", "known_evidence_count": null, "matches": 166, "name": "Family of unknown function (DUF5357)", "partial_evidence_count": null, "pfam_id": "PF17310", "proteins": 163, "proteomes": 162, "short_name": "DUF5357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17310", "structures": 0, "taxa": 442, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Clostridia. Proteins in this family are typically between 203 and 265 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046103", "known_evidence_count": null, "matches": 163, "name": "Family of unknown function (DUF6040)", "partial_evidence_count": null, "pfam_id": "PF19506", "proteins": 163, "proteomes": 98, "short_name": "DUF6040", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19506", "structures": 0, "taxa": 192, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the istamycin biosynthetic gene cluster from Streptomyces tenjimariensis [[cite:PUB00098957]]. This family appears to be predominantly found in actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046270", "known_evidence_count": null, "matches": 163, "name": "Family of unknown function (DUF6303)", "partial_evidence_count": null, "pfam_id": "PF19820", "proteins": 163, "proteomes": 141, "short_name": "DUF6303", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19820", "structures": 0, "taxa": 180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This Archaeal family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR020501", "known_evidence_count": null, "matches": 162, "name": "Protein of unknown function (DUF2551)", "partial_evidence_count": null, "pfam_id": "PF10826", "proteins": 162, "proteomes": 106, "short_name": "DUF2551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10826", "structures": 0, "taxa": 213, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 146, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically around 140 amino acids in length. The human member of this family is C19orf69.", "domain_architectures": 2, "interpro_id": "IPR029202", "known_evidence_count": null, "matches": 163, "name": "Domain of unknown function (DUF4530)", "partial_evidence_count": null, "pfam_id": "PF15039", "proteins": 162, "proteomes": 146, "short_name": "DUF4530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15039", "structures": 0, "taxa": 497, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000833) is described by MIBiG as an example of the following biosynthetic classes, saccharide and other (unspecified). This family includes a protein from the coumermycin A1 biosynthetic gene cluster from Streptomyces rishiriensis [[cite:PUB00099450]].", "domain_architectures": 2, "interpro_id": "IPR046044", "known_evidence_count": null, "matches": 162, "name": "Family of unknown function (DUF6002)", "partial_evidence_count": null, "pfam_id": "PF19465", "proteins": 162, "proteomes": 158, "short_name": "DUF6002", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19465", "structures": 0, "taxa": 252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 98, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000202) is described by MIBiG as an example of the following biosynthetic class, polyketide.", "domain_architectures": 2, "interpro_id": "IPR046274", "known_evidence_count": null, "matches": 162, "name": "Family of unknown function (DUF6307)", "partial_evidence_count": null, "pfam_id": "PF19826", "proteins": 162, "proteomes": 137, "short_name": "DUF6307", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19826", "structures": 0, "taxa": 188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 104, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins either standalone or in combination with other domains. It is distantly related to the type II restriction endonucleases with predicted similar active site architecture. These proteins are most likely endonucleases based on the strict conservation of the putative active site residues.", "domain_architectures": 3, "interpro_id": "IPR054024", "known_evidence_count": null, "matches": 162, "name": "Domain of unknown function (DUF6946)", "partial_evidence_count": null, "pfam_id": "PF22187", "proteins": 162, "proteomes": 150, "short_name": "DUF6946", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22187", "structures": 0, "taxa": 423, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in a group of proteins mainly from alphaproteobacteria. It is normally found N-terminal to [pfam:PF10074]. It is predicted to adopt a configuration formed mainly by beta-strands.", "domain_architectures": 3, "interpro_id": "IPR054278", "known_evidence_count": null, "matches": 162, "name": "Domain of unknown function (DUF7012)", "partial_evidence_count": null, "pfam_id": "PF22792", "proteins": 162, "proteomes": 135, "short_name": "DUF7012", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22792", "structures": 0, "taxa": 262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain from a family of uncharacterised proteins in Methanobacteriota. The proteins are predominantly found in archaea, specifically within the Methanobacteriota phylum. This includes orders such as Methanobacteriales, Methanosarcinales, and Methanomicrobiales. The proteins in this family are approximately 500 amino acids in length. This domain shows structural similarity to cyclophilin type peptidyl-prolyl cis-trans isomerases. Domains 2 and 3 in these proteins also adopt the same fold.", "domain_architectures": 2, "interpro_id": "IPR058492", "known_evidence_count": null, "matches": 162, "name": "Putative peptidyl-prolyl cis-trans isomerase domain", "partial_evidence_count": null, "pfam_id": "PF26548", "proteins": 162, "proteomes": 159, "short_name": "DUF8179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26548", "structures": 3, "taxa": 304, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain has no known function. It is found in various Streptococcal proteins.", "domain_architectures": 1, "interpro_id": "IPR015026", "known_evidence_count": null, "matches": 161, "name": "Domain of unknown function (DUF1912)", "partial_evidence_count": null, "pfam_id": "PF08930", "proteins": 161, "proteomes": 161, "short_name": "DUF1912", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08930", "structures": 1, "taxa": 233, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR016762", "known_evidence_count": null, "matches": 161, "name": "Uncharacterized protein conserved in archaea (DUF2113)", "partial_evidence_count": null, "pfam_id": "PF09886", "proteins": 161, "proteomes": 159, "short_name": "DUF2113", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09886", "structures": 3, "taxa": 304, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR008303", "known_evidence_count": null, "matches": 161, "name": "Uncharacterized protein conserved in archaea (DUF2114)", "partial_evidence_count": null, "pfam_id": "PF09887", "proteins": 161, "proteomes": 157, "short_name": "DUF2114", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09887", "structures": 0, "taxa": 278, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in proteins typically around 200 amino acids in length. It is found in phage that infect Mycobacteria, Gordonia, and Nocardia. The exact function is unknown. The structure of the domain shows an extended beta sandwich fold where one sheet is hinged in the middle to form a kink.", "domain_architectures": 1, "interpro_id": "IPR055596", "known_evidence_count": null, "matches": 161, "name": "Domain of unknown function (DUF7172)", "partial_evidence_count": null, "pfam_id": "PF23787", "proteins": 161, "proteomes": 64, "short_name": "DUF7172", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23787", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of putative membrane proteins found in various bacteriophages. The proteins in this family typically contain two transmembrane helices. The function of these proteins is currently unknown. They are predominantly found in phages infecting Salmonella, Escherichia, and other enterobacteria. The proteins in this family are generally short, with most members being around 80-81 amino acids in length", "domain_architectures": 1, "interpro_id": "IPR055865", "known_evidence_count": null, "matches": 161, "name": "Phage membrane protein Family of unknown function (DUF7442)", "partial_evidence_count": null, "pfam_id": "PF24226", "proteins": 161, "proteomes": 160, "short_name": "DUF7442", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24226", "structures": 0, "taxa": 335, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are uncharacterised proteins found in cyanobacteria that grow with a filamentous morphology [[cite:PUB00154605]].", "domain_architectures": 2, "interpro_id": "IPR054638", "known_evidence_count": null, "matches": 161, "name": "Family of unknown function (DUF7469)", "partial_evidence_count": null, "pfam_id": "PF24276", "proteins": 161, "proteomes": 158, "short_name": "DUF7469", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24276", "structures": 0, "taxa": 441, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein domain that forms an intimate self-self dimer. The domain is found at the C-terminus of proteins that often have a [pfam:PF24735] domain.", "domain_architectures": 5, "interpro_id": "IPR056130", "known_evidence_count": null, "matches": 161, "name": "Domain of unknown function (DUF7713)", "partial_evidence_count": null, "pfam_id": "PF24828", "proteins": 161, "proteomes": 138, "short_name": "DUF7713", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24828", "structures": 0, "taxa": 321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This predicted oligonucleotide/oligosaccharide binding (OB) domain is found in a group of uncharacterised animal proteins. Its function is unknown. It has conserved motifs GL/VGxV and GQ.", "domain_architectures": 57, "interpro_id": "IPR061571", "known_evidence_count": null, "matches": 163, "name": "Domain of unknown function (DUF8501)", "partial_evidence_count": null, "pfam_id": "PF29071", "proteins": 161, "proteomes": 132, "short_name": "DUF8501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29071", "structures": 0, "taxa": 508, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 104, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. There is a conserved DKT sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025134", "known_evidence_count": null, "matches": 160, "name": "Protein of unknown function (DUF4059)", "partial_evidence_count": null, "pfam_id": "PF13268", "proteins": 160, "proteomes": 159, "short_name": "DUF4059", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13268", "structures": 0, "taxa": 223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 207 and 359 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR029288", "known_evidence_count": null, "matches": 166, "name": "Domain of unknown function (DUF4607)", "partial_evidence_count": null, "pfam_id": "PF15380", "proteins": 160, "proteomes": 106, "short_name": "DUF4607", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15380", "structures": 0, "taxa": 386, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found predominantly in viruses. However, some matches with predicted proteins from Archaea and Eukaryotes were also found. This domain is likely to be a zinc-binding domain.", "domain_architectures": 12, "interpro_id": "IPR043914", "known_evidence_count": null, "matches": 160, "name": "Domain of unknown function (DUF5763)", "partial_evidence_count": null, "pfam_id": "PF19067", "proteins": 160, "proteomes": 152, "short_name": "DUF5763", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19067", "structures": 0, "taxa": 393, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0002024) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular, the nargenicin biosynthetic gene cluster from Nocardia argentinensis [[cite:PUB00099422]]. This family appears to be predominantly found in bacteria and unclassified phages.", "domain_architectures": 2, "interpro_id": "IPR046267", "known_evidence_count": null, "matches": 160, "name": "Family of unknown function (DUF6300)", "partial_evidence_count": null, "pfam_id": "PF19817", "proteins": 160, "proteomes": 147, "short_name": "DUF6300", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19817", "structures": 0, "taxa": 222, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein of approximately 70-100 amino acids found in mycobacteriophages. The function of this protein is currently unknown. It is found in phages belonging to the Gracegardnervirinae subfamily, including Cheoctovirus and Terapinvirus genera. This protein forms a confident dimer according to an AlphaFold model of [swissprot:S5Z4M5]. The dimer forms a central four stranded beta sheet with two alpha helices packed orthogonally to the direction of the beta strands on each face of the sheet.", "domain_architectures": 1, "interpro_id": "IPR055637", "known_evidence_count": null, "matches": 160, "name": "Family of unknown function (DUF7213)", "partial_evidence_count": null, "pfam_id": "PF23850", "proteins": 160, "proteomes": 156, "short_name": "DUF7213", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23850", "structures": 0, "taxa": 374, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This immunoglobulin-like (Ig-like) domain is found in a group of uncharacterised EFG-containing proteins from amoebas that are predicted to show several Ig-like domains. This entry is often found associated with [pfam:PF22933], [pfam:PF23033], and [pfam:PF23034].", "domain_architectures": 28, "interpro_id": "IPR059434", "known_evidence_count": null, "matches": 166, "name": "Domain of unknown function (DUF8390)", "partial_evidence_count": null, "pfam_id": "PF28405", "proteins": 160, "proteomes": 6, "short_name": "DUF8390", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28405", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Lactococcus phage middle-3 (M3) proteins of around 160 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009773", "known_evidence_count": null, "matches": 159, "name": "Lactococcus phage M3 protein", "partial_evidence_count": null, "pfam_id": "PF07066", "proteins": 159, "proteomes": 147, "short_name": "DUF3882", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07066", "structures": 2, "taxa": 339, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 152, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Caenorhabditis elegans proteins of around 85 residues in length. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR009924", "known_evidence_count": null, "matches": 161, "name": "Protein of unknown function (DUF1459)", "partial_evidence_count": null, "pfam_id": "PF07312", "proteins": 159, "proteomes": 29, "short_name": "DUF1459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07312", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR019209", "known_evidence_count": null, "matches": 159, "name": "Uncharacterized protein conserved in archaea (DUF2098)", "partial_evidence_count": null, "pfam_id": "PF09871", "proteins": 159, "proteomes": 154, "short_name": "DUF2098", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09871", "structures": 3, "taxa": 288, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 490 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 93, "interpro_id": "IPR032510", "known_evidence_count": null, "matches": 180, "name": "Domain of unknown function (DUF4972)", "partial_evidence_count": null, "pfam_id": "PF16342", "proteins": 159, "proteomes": 95, "short_name": "DUF4972", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16342", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 237 and 288 amino acids in length. The protein is largeley composed of a likely coiled-coil. It contains a small three helix bundle domain at the C-terminus.", "domain_architectures": 2, "interpro_id": "IPR046118", "known_evidence_count": null, "matches": 177, "name": "Family of unknown function (DUF6115)", "partial_evidence_count": null, "pfam_id": "PF19610", "proteins": 159, "proteomes": 157, "short_name": "DUF6115", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19610", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055853", "known_evidence_count": null, "matches": 159, "name": "Family of unknown function (DUF7430)", "partial_evidence_count": null, "pfam_id": "PF24207", "proteins": 159, "proteomes": 159, "short_name": "DUF7430", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24207", "structures": 0, "taxa": 331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function at the N-terminal in uncharacterised proteins mainly from Pseudomonadati. This domain contains a RNase like fold. The core architecture typically features a central five-stranded beta-sheet flanked by several alpha-helices.", "domain_architectures": 2, "interpro_id": "", "known_evidence_count": null, "matches": 159, "name": "Domain of unknown function (DUF8569)", "partial_evidence_count": null, "pfam_id": "PF27038", "proteins": 159, "proteomes": 158, "short_name": "DUF8569", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27038", "structures": 0, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram negative bacteria. It shares similarity with known galactose binding domains and it is predicted to adopt similar jelly-roll structure.", "domain_architectures": 3, "interpro_id": "IPR061550", "known_evidence_count": null, "matches": 159, "name": "Domain of unknown function (DUF8480)", "partial_evidence_count": null, "pfam_id": "PF28920", "proteins": 159, "proteomes": 159, "short_name": "DUF8480", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28920", "structures": 0, "taxa": 253, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are multigene family 530 proteins from African swine fever viruses. These proteins may be involved in promoting survival of infected macrophages [[cite:PUB00007712]].", "domain_architectures": 1, "interpro_id": "IPR004858", "known_evidence_count": null, "matches": 158, "name": "Multigene family 530 protein", "partial_evidence_count": null, "pfam_id": "PF03158", "proteins": 158, "proteomes": 17, "short_name": "DUF249", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03158", "structures": 0, "taxa": 26, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 8, "interpro_id": "IPR019249", "known_evidence_count": null, "matches": 176, "name": "Uncharacterized protein conserved in archaea (DUF2226)", "partial_evidence_count": null, "pfam_id": "PF09987", "proteins": 158, "proteomes": 126, "short_name": "DUF2226", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09987", "structures": 0, "taxa": 310, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in Bacteroidetes, and is approximately 110 amino acids in length. The family is found in association with [pfam:PF00072]. There is a conserved PIL sequence motif.", "domain_architectures": 2, "interpro_id": "IPR045976", "known_evidence_count": null, "matches": 158, "name": "Family of unknown function (DUF5932)", "partial_evidence_count": null, "pfam_id": "PF19355", "proteins": 158, "proteomes": 157, "short_name": "DUF5932", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19355", "structures": 0, "taxa": 245, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 137 and 172 amino acids in length. Protein in this family belong to the ferritin clan.", "domain_architectures": 6, "interpro_id": "IPR046273", "known_evidence_count": null, "matches": 159, "name": "Domain of unknown function (DUF6306)", "partial_evidence_count": null, "pfam_id": "PF19825", "proteins": 158, "proteomes": 150, "short_name": "DUF6306", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19825", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 223 and 298 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046708", "known_evidence_count": null, "matches": 158, "name": "Family of unknown function (DUF6781)", "partial_evidence_count": null, "pfam_id": "PF20572", "proteins": 158, "proteomes": 148, "short_name": "DUF6781", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20572", "structures": 0, "taxa": 331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from phage. Structure predictions suggest the protein is composed of a larger N-terminal domain with an 8 stranded beta sheet. Followed by a C-terminal helical domain.", "domain_architectures": 1, "interpro_id": "IPR055988", "known_evidence_count": null, "matches": 158, "name": "Family of unknown function (DUF7566)", "partial_evidence_count": null, "pfam_id": "PF24450", "proteins": 158, "proteomes": 155, "short_name": "DUF7566", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24450", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble Zinc beta-ribbon domains.", "domain_architectures": 1, "interpro_id": "IPR055989", "known_evidence_count": null, "matches": 158, "name": "Family of unknown function (DUF7567)", "partial_evidence_count": null, "pfam_id": "PF24451", "proteins": 158, "proteomes": 110, "short_name": "DUF7567", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24451", "structures": 0, "taxa": 201, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of short hypothetical proteins found in Rhodopirellula baltica.", "domain_architectures": 2, "interpro_id": "IPR011474", "known_evidence_count": null, "matches": 157, "name": "Protein of unknown function (DUF1580)", "partial_evidence_count": null, "pfam_id": "PF07618", "proteins": 157, "proteomes": 73, "short_name": "DUF1580", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07618", "structures": 0, "taxa": 161, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Mycobacteriaceae.", "domain_architectures": 3, "interpro_id": "IPR024296", "known_evidence_count": null, "matches": 157, "name": "Protein of unknown function (DUF2710)", "partial_evidence_count": null, "pfam_id": "PF10921", "proteins": 157, "proteomes": 143, "short_name": "DUF2710", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10921", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025009", "known_evidence_count": null, "matches": 157, "name": "Protein of unknown function (DUF3977)", "partial_evidence_count": null, "pfam_id": "PF13122", "proteins": 157, "proteomes": 153, "short_name": "DUF3977", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13122", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of C-terminal of uncharacterized proteins around 100 residues in length and is mainly found in various Prevotella species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032483", "known_evidence_count": null, "matches": 157, "name": "Domain of unknown function (DUF5053)", "partial_evidence_count": null, "pfam_id": "PF16476", "proteins": 157, "proteomes": 109, "short_name": "DUF5053", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16476", "structures": 0, "taxa": 229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses and Bacteria.", "domain_architectures": 3, "interpro_id": "IPR043803", "known_evidence_count": null, "matches": 157, "name": "Family of unknown function (DUF5872)", "partial_evidence_count": null, "pfam_id": "PF19197", "proteins": 157, "proteomes": 157, "short_name": "DUF5872", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19197", "structures": 0, "taxa": 325, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "NaturalProductMech": 1, "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001986) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a member from the purincyclamide biosynthetic gene cluster from Streptomyces chrestomyceticus and appears to be predominantly found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR046074", "known_evidence_count": null, "matches": 157, "name": "Family of unknown function (DUF6092)", "partial_evidence_count": null, "pfam_id": "PF19585", "proteins": 157, "proteomes": 150, "short_name": "DUF6092", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19585", "structures": 2, "taxa": 307, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in a family of uncharacterised bacterial proteins. This domain has a significant sequence similarity to the C-terminal domains of a number of proteins members of UDP-Glycosyltransferase/glycogen phosphorylase superfamily. It is predicted to adopt the same alpha/beta structure.", "domain_architectures": 5, "interpro_id": "IPR054218", "known_evidence_count": null, "matches": 158, "name": "Domain of unknown function (DUF6938)", "partial_evidence_count": null, "pfam_id": "PF22053", "proteins": 157, "proteomes": 141, "short_name": "DUF6938", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22053", "structures": 0, "taxa": 377, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised protein ZK892.6 from Caenorhabditis elegans and related proteins. It is found either standalone or in combination with other domains. Some proteins contain multiple copies of this domain. It is predicted to adopt a globular structure consisting of an antiparallel six-stranded beta-sheet and alpha-helices packed on both sides of it. This domain contains a highly conserved PxxPP motif.", "domain_architectures": 11, "interpro_id": "IPR056649", "known_evidence_count": null, "matches": 398, "name": "Domain of unknown function (DUF7747)", "partial_evidence_count": null, "pfam_id": "PF24927", "proteins": 157, "proteomes": 56, "short_name": "DUF7747", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24927", "structures": 0, "taxa": 128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from plants. It is predicted to fold into a beta-sandwich.", "domain_architectures": 4, "interpro_id": "IPR056650", "known_evidence_count": null, "matches": 158, "name": "Domain of unknown function (DUF7748)", "partial_evidence_count": null, "pfam_id": "PF24928", "proteins": 157, "proteomes": 5, "short_name": "DUF7748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24928", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 153, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised halobacterial protein family. This family is surprisingly composed of half a TIM-barrel fold, related to the [pfam:PF01261] domain found in xylose isomerase.", "domain_architectures": 1, "interpro_id": "IPR058267", "known_evidence_count": null, "matches": 157, "name": "Domain of unknown function (DUF8564)", "partial_evidence_count": null, "pfam_id": "PF25905", "proteins": 157, "proteomes": 157, "short_name": "DUF8564", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25905", "structures": 0, "taxa": 257, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 200 residues found in cyanobacterial histidine kinases. These proteins are part of two-component signal transduction systems. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061689", "known_evidence_count": null, "matches": 157, "name": "Domain of unknown function (DUF8628)", "partial_evidence_count": null, "pfam_id": "PF30559", "proteins": 157, "proteomes": 156, "short_name": "DUF8628", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30559", "structures": 0, "taxa": 441, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of unknown function which appear to be found largely in Helicobacter pylori. The structure of HP0721 protein consists of a bundle of four alpha-helices connected by loops and stabilised by hydrophobic interactions. It has been suggested that this protein might represent a novel H. pylori [[cite:PUB00097448]].", "domain_architectures": 4, "interpro_id": "IPR009488", "known_evidence_count": null, "matches": 156, "name": "Protein of unknown function (DUF1104)", "partial_evidence_count": null, "pfam_id": "PF06518", "proteins": 156, "proteomes": 109, "short_name": "DUF1104", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06518", "structures": 1, "taxa": 180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of paralogous proteins in Leptospira interrogans.", "domain_architectures": 3, "interpro_id": "IPR011455", "known_evidence_count": null, "matches": 158, "name": "Protein of unknown function (DUF1561)", "partial_evidence_count": null, "pfam_id": "PF07598", "proteins": 156, "proteomes": 41, "short_name": "DUF1561", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07598", "structures": 0, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Pasteurellaceae.", "domain_architectures": 1, "interpro_id": "IPR020300", "known_evidence_count": null, "matches": 156, "name": "Protein of unknown function (DUF2644)", "partial_evidence_count": null, "pfam_id": "PF10841", "proteins": 156, "proteomes": 124, "short_name": "DUF2644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10841", "structures": 0, "taxa": 261, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length. There are two conserved sequence motifs: RLF and TWH.", "domain_architectures": 1, "interpro_id": "IPR025014", "known_evidence_count": null, "matches": 156, "name": "Protein of unknown function (DUF3958)", "partial_evidence_count": null, "pfam_id": "PF13125", "proteins": 156, "proteomes": 71, "short_name": "DUF3958", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13125", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 533 and 570 amino acids in length.", "domain_architectures": 7, "interpro_id": "IPR027979", "known_evidence_count": null, "matches": 166, "name": "Domain of unknown function (DUF4655)", "partial_evidence_count": null, "pfam_id": "PF15548", "proteins": 156, "proteomes": 122, "short_name": "DUF4655", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15548", "structures": 0, "taxa": 420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a protein repeats whose length varies between 50 and 80 residues. It is found in a variety of iridoviruses. It may be distantly related to minor tail protein found in phages.", "domain_architectures": 50, "interpro_id": "IPR045571", "known_evidence_count": null, "matches": 616, "name": "Repeat of unknown function (DUF5907)", "partial_evidence_count": null, "pfam_id": "PF19264", "proteins": 156, "proteomes": 88, "short_name": "DUF5907", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19264", "structures": 0, "taxa": 226, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, mainly Firmicutes and Actinobacteria, and is approximately 80 amino acids in length. It contains a highly conserved tryptophan residue and the conserved sequence YxxxxxxY.", "domain_architectures": 7, "interpro_id": "IPR046526", "known_evidence_count": null, "matches": 166, "name": "Family of unknown function (DUF6591)", "partial_evidence_count": null, "pfam_id": "PF20234", "proteins": 156, "proteomes": 134, "short_name": "DUF6591", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20234", "structures": 0, "taxa": 288, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found standalone in bacteria. Its function is unknown but it has a significant sequence similarity to the C-terminal SAM-binding regulatory domain of 5,10-methylenetetrahydrofolate reductase (MTHFR).", "domain_architectures": 5, "interpro_id": "IPR054212", "known_evidence_count": null, "matches": 157, "name": "Domain of unknown function (DUF6919)", "partial_evidence_count": null, "pfam_id": "PF21897", "proteins": 156, "proteomes": 142, "short_name": "DUF6919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21897", "structures": 0, "taxa": 342, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 148, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Halobacteria. These proteins are likely associated with the membrane. They are predicted to fold into a three helical bundle.", "domain_architectures": 2, "interpro_id": "IPR055977", "known_evidence_count": null, "matches": 156, "name": "Family of unknown function (DUF7555)", "partial_evidence_count": null, "pfam_id": "PF24432", "proteins": 156, "proteomes": 148, "short_name": "DUF7555", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24432", "structures": 0, "taxa": 278, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of proteins from proteobacteria, including T6SS lipase effector (Tle) proteins. The function of this domain is unknown but in Tle, it precedes the lipase domain.", "domain_architectures": 13, "interpro_id": "IPR058406", "known_evidence_count": null, "matches": 156, "name": "Domain of unknown function (DUF8093)", "partial_evidence_count": null, "pfam_id": "PF26362", "proteins": 156, "proteomes": 105, "short_name": "DUF8093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26362", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Staphylococcus aureus and Staphylococcus aureus bacteriophage proteins of around 65 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009812", "known_evidence_count": null, "matches": 155, "name": "Protein of unknown function (DUF1381)", "partial_evidence_count": null, "pfam_id": "PF07129", "proteins": 155, "proteomes": 130, "short_name": "DUF1381", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07129", "structures": 0, "taxa": 257, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently there is no known function.", "domain_architectures": 1, "interpro_id": "IPR021506", "known_evidence_count": null, "matches": 155, "name": "Protein of unknown function (DUF3165)", "partial_evidence_count": null, "pfam_id": "PF11364", "proteins": 155, "proteomes": 155, "short_name": "DUF3165", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11364", "structures": 0, "taxa": 219, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001485) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the 3-demethylchuangxinmycin biosynthetic gene cluster from Actinoplanes tsinanensis [[cite:PUB00099369]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR046176", "known_evidence_count": null, "matches": 189, "name": "Family of unknown function (DUF6185)", "partial_evidence_count": null, "pfam_id": "PF19683", "proteins": 155, "proteomes": 139, "short_name": "DUF6185", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19683", "structures": 0, "taxa": 187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 98, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised bacterial proteins that were predicted to possess defence functions [[cite:PUB00152882]]. They contain highly conserved aspartate and histidine residues that may have functional role.", "domain_architectures": 1, "interpro_id": "IPR055679", "known_evidence_count": null, "matches": 155, "name": "Family of unknown function (DUF7255)", "partial_evidence_count": null, "pfam_id": "PF23913", "proteins": 155, "proteomes": 150, "short_name": "DUF7255", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23913", "structures": 0, "taxa": 275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of bacterial proteins are thought to be membrane transporters, but their exact function has not, as yet, been elucidated.", "domain_architectures": 1, "interpro_id": "IPR017199", "known_evidence_count": null, "matches": 154, "name": "Predicted transporter (DUF2162)", "partial_evidence_count": null, "pfam_id": "PF09930", "proteins": 154, "proteomes": 125, "short_name": "DUF2162", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09930", "structures": 0, "taxa": 297, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 136, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in eukaryotes.", "domain_architectures": 2, "interpro_id": "IPR027950", "known_evidence_count": null, "matches": 155, "name": "Domain of unknown function (DUF4576)", "partial_evidence_count": null, "pfam_id": "PF15144", "proteins": 154, "proteomes": 132, "short_name": "DUF4576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15144", "structures": 0, "taxa": 426, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 107, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 200 residues in length and is mainly found in various Firmicutes species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032484", "known_evidence_count": null, "matches": 155, "name": "Domain of unknown function (DUF5052)", "partial_evidence_count": null, "pfam_id": "PF16475", "proteins": 154, "proteomes": 150, "short_name": "DUF5052", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16475", "structures": 0, "taxa": 304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals. Family members have one or several predicted trans-membrane regions.", "domain_architectures": 6, "interpro_id": "IPR037549", "known_evidence_count": null, "matches": 156, "name": "Family of unknown function (DUF5534)", "partial_evidence_count": null, "pfam_id": "PF17686", "proteins": 154, "proteomes": 124, "short_name": "DUF5534", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17686", "structures": 0, "taxa": 427, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised metazoan proteins. It has a detectable sequence similarity to HTH winged helix domains and it is predicted to adopt similar structure.", "domain_architectures": 16, "interpro_id": "IPR055937", "known_evidence_count": null, "matches": 156, "name": "Domain of unknown function (DUF7515)", "partial_evidence_count": null, "pfam_id": "PF24359", "proteins": 154, "proteomes": 39, "short_name": "DUF7515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24359", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is found in uncharacterised sequences from Plasmodium falciparum and similar sequences from Apicomplexa. This domain may adopt a TNF receptor-like fold.", "domain_architectures": 25, "interpro_id": "IPR056048", "known_evidence_count": null, "matches": 154, "name": "Domain of unknown function (DUF7631)", "partial_evidence_count": null, "pfam_id": "PF24634", "proteins": 154, "proteomes": 50, "short_name": "DUF7631", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24634", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found at the N-terminus of a set of bacterial and phage proteins. It is often associated with a C-terminal small beta barrel domain.", "domain_architectures": 2, "interpro_id": "IPR057706", "known_evidence_count": null, "matches": 154, "name": "Domain of unknown function (DUF7946)", "partial_evidence_count": null, "pfam_id": "PF25678", "proteins": 154, "proteomes": 152, "short_name": "DUF7946", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25678", "structures": 0, "taxa": 409, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function with structural similarity to ribosomal protein L29 (L29p) as identified by ECOD classification. The domain is primarily found in nematode proteins, particularly in Caenorhabditis species. The specific function of this domain has not yet been experimentally determined.", "domain_architectures": 5, "interpro_id": "IPR058430", "known_evidence_count": null, "matches": 154, "name": "Domain of unknown function (DUF8117)", "partial_evidence_count": null, "pfam_id": "PF26431", "proteins": 154, "proteomes": 128, "short_name": "DUF8117", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26431", "structures": 0, "taxa": 441, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 144, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halobacteria. The proteins containing this domain are predominantly found in archaea, specifically within the Halobacteria class. Proteins in this family are typically around 150-200 amino acids in length. The domain is predicted to be part of integral membrane proteins with six predicted transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR058477", "known_evidence_count": null, "matches": 155, "name": "Domain of unknown function (DUF8163)", "partial_evidence_count": null, "pfam_id": "PF26496", "proteins": 154, "proteomes": 140, "short_name": "DUF8163", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26496", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 65 and 178 amino acids in length. There are two conserved sequence motifs: VISRM and ENE.", "domain_architectures": 4, "interpro_id": "IPR031464", "known_evidence_count": null, "matches": 159, "name": "Domain of unknown function (DUF4680)", "partial_evidence_count": null, "pfam_id": "PF15730", "proteins": 153, "proteomes": 140, "short_name": "DUF4680", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15730", "structures": 0, "taxa": 498, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 290 and 350 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046632", "known_evidence_count": null, "matches": 157, "name": "Family of unknown function (DUF6744)", "partial_evidence_count": null, "pfam_id": "PF20529", "proteins": 153, "proteomes": 117, "short_name": "DUF6744", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20529", "structures": 0, "taxa": 320, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal zinc binding domain of an uncharacterised family of phage proteins.", "domain_architectures": 2, "interpro_id": "IPR055764", "known_evidence_count": null, "matches": 153, "name": "Domain of unknown function (DUF7340)", "partial_evidence_count": null, "pfam_id": "PF24029", "proteins": 153, "proteomes": 146, "short_name": "DUF7340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24029", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Proteins in this family have a predicted structure with a likely N-terminal coiled-coil region and a C-terminal structure with two possible subdomains.", "domain_architectures": 1, "interpro_id": "IPR058321", "known_evidence_count": null, "matches": 153, "name": "Family of unknown function (DUF8008)", "partial_evidence_count": null, "pfam_id": "PF26032", "proteins": 153, "proteomes": 72, "short_name": "DUF8008", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26032", "structures": 0, "taxa": 141, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found primarily in nematodes, but also other some other simpler animals..", "domain_architectures": 21, "interpro_id": "IPR058390", "known_evidence_count": null, "matches": 160, "name": "Domain of unknown function (DUF8077)", "partial_evidence_count": null, "pfam_id": "PF26284", "proteins": 153, "proteomes": 108, "short_name": "DUF8077", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26284", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Drosophila.", "domain_architectures": 8, "interpro_id": "IPR021349", "known_evidence_count": null, "matches": 211, "name": "Protein of unknown function (DUF2967)", "partial_evidence_count": null, "pfam_id": "PF11179", "proteins": 152, "proteomes": 104, "short_name": "DUF2967", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11179", "structures": 0, "taxa": 408, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in vertebrates. Proteins in this family are typically between 86 and 203 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031708", "known_evidence_count": null, "matches": 165, "name": "Domain of unknown function (DUF4722)", "partial_evidence_count": null, "pfam_id": "PF15849", "proteins": 152, "proteomes": 122, "short_name": "DUF4722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15849", "structures": 0, "taxa": 436, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterized. It is found mainly in Firmicutes. Proteins in this family are around 130 amino acids in length. Based on NMR structure 2MCT, it forms an alpha/beta structure with a 6 stranded antiparallel b-sheet planked by a single alpha helix. The only protein with similar structures is a putative lipoprotein (PDB code 4R7R).", "domain_architectures": 7, "interpro_id": "IPR033782", "known_evidence_count": null, "matches": 152, "name": "Domain of unknown function (DUF5300)", "partial_evidence_count": null, "pfam_id": "PF17225", "proteins": 152, "proteomes": 140, "short_name": "DUF5301", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17225", "structures": 1, "taxa": 304, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 110 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046131", "known_evidence_count": null, "matches": 152, "name": "Family of unknown function (DUF6128)", "partial_evidence_count": null, "pfam_id": "PF19623", "proteins": 152, "proteomes": 151, "short_name": "DUF6128", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19623", "structures": 0, "taxa": 250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000368) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the streptobactin biosynthetic gene cluster from Streptomyces sp. ATCC 700974 [[cite:PUB00099408]].", "domain_architectures": 2, "interpro_id": "IPR045937", "known_evidence_count": null, "matches": 153, "name": "Family of unknown function (DUF6357)", "partial_evidence_count": null, "pfam_id": "PF19884", "proteins": 152, "proteomes": 133, "short_name": "DUF6357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19884", "structures": 0, "taxa": 207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 141, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in plants, and is approximately 70 amino acids in length.", "domain_architectures": 13, "interpro_id": "IPR046626", "known_evidence_count": null, "matches": 152, "name": "Domain of unknown function (DUF6738)", "partial_evidence_count": null, "pfam_id": "PF20523", "proteins": 152, "proteomes": 21, "short_name": "DUF6738", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20523", "structures": 0, "taxa": 104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is usually associated with [pfam:PF13218] and [pfam:PF10077] that flank this domain from N- and C-terminal ends, respectively. This domain is distantly related to SUFU-like domains.", "domain_architectures": 4, "interpro_id": "IPR053886", "known_evidence_count": null, "matches": 152, "name": "Protein of unknown function (DUF4026) C-terminal", "partial_evidence_count": null, "pfam_id": "PF22789", "proteins": 152, "proteomes": 148, "short_name": "DUF4026_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22789", "structures": 0, "taxa": 296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in T4-like bacteriophages. It is found between the cd and pseT genes in the T4 phage genome. The function of this protein is unknown. Structure prediction suggests these proteins have a compact fold composed of five beta strands and an alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055744", "known_evidence_count": null, "matches": 152, "name": "Domain of unknown function (DUF7320)", "partial_evidence_count": null, "pfam_id": "PF24005", "proteins": 152, "proteomes": 145, "short_name": "DUF7320", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24005", "structures": 0, "taxa": 318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to contain two subdomains one of which is consisting of a five-stranded antiparallel beta-sheet and a helix packed on it followed by a zinc beta-ribbon domain.", "domain_architectures": 1, "interpro_id": "IPR055990", "known_evidence_count": null, "matches": 152, "name": "Family of unknown function (DUF7568)", "partial_evidence_count": null, "pfam_id": "PF24452", "proteins": 152, "proteomes": 100, "short_name": "DUF7568", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24452", "structures": 0, "taxa": 172, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 1, "interpro_id": "IPR058294", "known_evidence_count": null, "matches": 152, "name": "Domain of unknown function (DUF7988)", "partial_evidence_count": null, "pfam_id": "PF25950", "proteins": 152, "proteomes": 152, "short_name": "DUF7988", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25950", "structures": 0, "taxa": 262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function at the C-terminal in uncharacterised proteins mainly from Pseudomonadati. This domain contains a RNase like fold. The core architecture typically features a central five-stranded beta-sheet flanked by several alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR059385", "known_evidence_count": null, "matches": 152, "name": "Domain of unknown function (DUF8341)", "partial_evidence_count": null, "pfam_id": "PF27037", "proteins": 152, "proteomes": 151, "short_name": "DUF8341", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27037", "structures": 0, "taxa": 227, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins are found in Bacteroidales. It contains an N-terminal signal peptide suggesting it is a secreted protein. Overall they show relatively low levels of conservation except for a conserved C-terminal 11 residue motif that is likely important for function.", "domain_architectures": 2, "interpro_id": "IPR059484", "known_evidence_count": null, "matches": 152, "name": "Family of unknown function (DUF8440)", "partial_evidence_count": null, "pfam_id": "PF28586", "proteins": 152, "proteomes": 62, "short_name": "DUF8440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28586", "structures": 0, "taxa": 118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of uncharacterised bacterial and archaeal proteins.", "domain_architectures": 2, "interpro_id": "IPR010397", "known_evidence_count": null, "matches": 152, "name": "Protein of unknown function (DUF996)", "partial_evidence_count": null, "pfam_id": "PF06195", "proteins": 151, "proteomes": 105, "short_name": "DUF996", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06195", "structures": 0, "taxa": 313, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]]. This domain frequently seen with DUF3849.", "domain_architectures": 7, "interpro_id": "IPR024380", "known_evidence_count": null, "matches": 151, "name": "Protein of unknown function (DUF3848)", "partial_evidence_count": null, "pfam_id": "PF12959", "proteins": 151, "proteomes": 98, "short_name": "DUF3848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12959", "structures": 0, "taxa": 203, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mammalia. Family members have one or several predicted trans-membrane regions.", "domain_architectures": 3, "interpro_id": "IPR038788", "known_evidence_count": null, "matches": 157, "name": "Family of unknown function (DUF5531)", "partial_evidence_count": null, "pfam_id": "PF17671", "proteins": 151, "proteomes": 132, "short_name": "DUF5531", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17671", "structures": 0, "taxa": 428, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001615) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular hexose-palythine-serine biosynthetic gene cluster from Heteroscytonema crispum UCFS10 [[cite:PUB00099381]].", "domain_architectures": 2, "interpro_id": "IPR046298", "known_evidence_count": null, "matches": 152, "name": "Family of unknown function (DUF6335)", "partial_evidence_count": null, "pfam_id": "PF19861", "proteins": 151, "proteomes": 140, "short_name": "DUF6335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19861", "structures": 0, "taxa": 422, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 98, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045503", "known_evidence_count": null, "matches": 151, "name": "Family of unknown function (DUF6488)", "partial_evidence_count": null, "pfam_id": "PF20098", "proteins": 151, "proteomes": 138, "short_name": "DUF6488", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20098", "structures": 0, "taxa": 356, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 111, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046722", "known_evidence_count": null, "matches": 151, "name": "Family of unknown function (DUF6614)", "partial_evidence_count": null, "pfam_id": "PF20319", "proteins": 151, "proteomes": 149, "short_name": "DUF6614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20319", "structures": 0, "taxa": 273, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of bacterial proteins. Structure prediction ([swissprot:B2VAQ8] AF3 iPTM=0.93) suggests that these proteins form dimers. The monomer is composed of three alpha helices. STRING provides some weak evidence that these proteins may be immunity proteins or perhaps part of a plasmid addiction system.", "domain_architectures": 1, "interpro_id": "IPR056123", "known_evidence_count": null, "matches": 151, "name": "Family of unknown function (DUF7706)", "partial_evidence_count": null, "pfam_id": "PF24806", "proteins": 151, "proteomes": 109, "short_name": "DUF7706", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24806", "structures": 0, "taxa": 282, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 111, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It has three highly conserved cysteine residues and a histidine that may be involved in zinc coordination.", "domain_architectures": 8, "interpro_id": "IPR057152", "known_evidence_count": null, "matches": 151, "name": "Domain of unknown function (DUF7830)", "partial_evidence_count": null, "pfam_id": "PF25169", "proteins": 151, "proteomes": 148, "short_name": "DUF7830", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25169", "structures": 0, "taxa": 395, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 143, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved domain within a number of proteins of unknown function that seem to be specific to C. elegans. Note that some family members contain more than one copy of this region.", "domain_architectures": 5, "interpro_id": "IPR009658", "known_evidence_count": null, "matches": 152, "name": "Protein of unknown function (DUF1248)", "partial_evidence_count": null, "pfam_id": "PF06852", "proteins": 150, "proteomes": 31, "short_name": "DUF1248", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06852", "structures": 0, "taxa": 79, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Mycobacterium spp.", "domain_architectures": 1, "interpro_id": "IPR024426", "known_evidence_count": null, "matches": 150, "name": "Protein of unknown function (DUF2694)", "partial_evidence_count": null, "pfam_id": "PF10904", "proteins": 150, "proteomes": 147, "short_name": "DUF2694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10904", "structures": 0, "taxa": 170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]]. This domain frequently seen with DUF3848.", "domain_architectures": 1, "interpro_id": "IPR024330", "known_evidence_count": null, "matches": 150, "name": "Protein of unknown function (DUF3852)", "partial_evidence_count": null, "pfam_id": "PF12963", "proteins": 150, "proteomes": 108, "short_name": "DUF3852", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12963", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 106 and 128 amino acids in length. There is a conserved KVI sequence motif.", "domain_architectures": 4, "interpro_id": "IPR031903", "known_evidence_count": null, "matches": 202, "name": "Domain of unknown function (DUF4766)", "partial_evidence_count": null, "pfam_id": "PF15973", "proteins": 150, "proteomes": 36, "short_name": "DUF4766", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15973", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals.", "domain_architectures": 4, "interpro_id": "IPR040022", "known_evidence_count": null, "matches": 150, "name": "Family of unknown function (DUF5532)", "partial_evidence_count": null, "pfam_id": "PF17673", "proteins": 150, "proteomes": 115, "short_name": "DUF5532", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17673", "structures": 0, "taxa": 370, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are approximately 800 amino acids in length. This entry corresponds to a 6 helical hairpin domain.", "domain_architectures": 35, "interpro_id": "IPR046255", "known_evidence_count": null, "matches": 151, "name": "Domain of unknown function (DUF6288)", "partial_evidence_count": null, "pfam_id": "PF19805", "proteins": 150, "proteomes": 53, "short_name": "DUF6288", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19805", "structures": 0, "taxa": 126, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 147, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt a mainly alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR055897", "known_evidence_count": null, "matches": 150, "name": "Family of unknown function (DUF7474)", "partial_evidence_count": null, "pfam_id": "PF24286", "proteins": 150, "proteomes": 147, "short_name": "DUF7474", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24286", "structures": 0, "taxa": 221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram negative bacteria. It is predicted to fold into array of alpha helices.", "domain_architectures": 1, "interpro_id": "IPR061561", "known_evidence_count": null, "matches": 150, "name": "Domain of unknown function (DUF8491)", "partial_evidence_count": null, "pfam_id": "PF28981", "proteins": 150, "proteomes": 149, "short_name": "DUF8491", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28981", "structures": 0, "taxa": 225, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021358", "known_evidence_count": null, "matches": 149, "name": "Protein of unknown function (DUF2977)", "partial_evidence_count": null, "pfam_id": "PF11192", "proteins": 149, "proteomes": 138, "short_name": "DUF2977", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11192", "structures": 3, "taxa": 303, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 340 residues in length and is mainly found in various Bacteroides and Prevotella species. The function of this family is unknown.", "domain_architectures": 16, "interpro_id": "IPR032339", "known_evidence_count": null, "matches": 176, "name": "Domain of unknown function (DUF4859)", "partial_evidence_count": null, "pfam_id": "PF16151", "proteins": 149, "proteomes": 95, "short_name": "DUF4859", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16151", "structures": 0, "taxa": 191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is functionally uncharacterised. This family of proteins is found in proteobacteria. Proteins in this family are typically 74 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046565", "known_evidence_count": null, "matches": 149, "name": "Family of unknown function (DUF6719)", "partial_evidence_count": null, "pfam_id": "PF20477", "proteins": 149, "proteomes": 134, "short_name": "DUF6719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20477", "structures": 0, "taxa": 185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicutes bacteria. Proteins in this family are approximately 135 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046650", "known_evidence_count": null, "matches": 149, "name": "Family of unknown function (DUF6762)", "partial_evidence_count": null, "pfam_id": "PF20548", "proteins": 149, "proteomes": 148, "short_name": "DUF6762", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20548", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an alpha-helical domain found at the N-terminal of a group of uncharacterised proteins from fungi. The function of this domain is unknown. Members of this entry also have a beta-propeller at the C-terminal ([pfam:PF23388]).", "domain_architectures": 10, "interpro_id": "IPR055526", "known_evidence_count": null, "matches": 161, "name": "Domain of unknown function (DUF7100)", "partial_evidence_count": null, "pfam_id": "PF23391", "proteins": 149, "proteomes": 144, "short_name": "DUF7100", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23391", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a highly conserved domain found in various bacteriophages, particularly those infecting Salmonella and related bacteria. The domain is also present in some bacterial species, suggesting possible horizontal gene transfer. The function is unknown, but the high degree of conservation implies an important role in phage biology. A conserved motif DVT is present centrally in many family members. The aspartate and threonine form side chain hydrogen bonds that help stabilise the dimeric interaction. Structure prediction suggests these proteins form a confident homodimer (iPTM=0.83).", "domain_architectures": 2, "interpro_id": "IPR055869", "known_evidence_count": null, "matches": 149, "name": "Family of unknown function (DUF7446)", "partial_evidence_count": null, "pfam_id": "PF24233", "proteins": 149, "proteomes": 144, "short_name": "DUF7446", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24233", "structures": 0, "taxa": 384, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from uncharacterised proteins mainly found in Actinomycetes. They are predicted to adopt an OB fold-like beta-barrel.", "domain_architectures": 3, "interpro_id": "IPR055912", "known_evidence_count": null, "matches": 149, "name": "Domain of unknown function (DUF7489)", "partial_evidence_count": null, "pfam_id": "PF24315", "proteins": 149, "proteomes": 144, "short_name": "DUF7489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24315", "structures": 0, "taxa": 241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the C-terminal of worm proteins. It may be related to BACK domains.", "domain_architectures": 7, "interpro_id": "IPR056656", "known_evidence_count": null, "matches": 149, "name": "Domain of unknown function (DUF7754)", "partial_evidence_count": null, "pfam_id": "PF24937", "proteins": 149, "proteomes": 80, "short_name": "DUF7754", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24937", "structures": 0, "taxa": 180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Gammaproteobacteria. This domain is found usually associated with [pfam:PF11195].", "domain_architectures": 3, "interpro_id": "IPR056725", "known_evidence_count": null, "matches": 149, "name": "Domain of unknown function (DUF7823)", "partial_evidence_count": null, "pfam_id": "PF25136", "proteins": 149, "proteomes": 39, "short_name": "DUF7823", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25136", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a variety of mycobacteriophage. Structure prediction suggests that these proteins form a confident homodimer. The domain is composed of a four stranded beta sheet with two helices packed on one side. The homo-oligomer interaction is mediated by the C-terminal beta strand. The function of this protein is not known.", "domain_architectures": 2, "interpro_id": "IPR059321", "known_evidence_count": null, "matches": 149, "name": "Domain of unknown function (DUF8277)", "partial_evidence_count": null, "pfam_id": "PF26922", "proteins": 149, "proteomes": 149, "short_name": "DUF8277", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26922", "structures": 0, "taxa": 353, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 140, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins. Some (such as [swissprot:O01625]) are annotated as having possible G-protein-coupled receptor-like activity.", "domain_architectures": 8, "interpro_id": "IPR006874", "known_evidence_count": null, "matches": 172, "name": "Protein of unknown function (DUF621)", "partial_evidence_count": null, "pfam_id": "PF04789", "proteins": 148, "proteomes": 44, "short_name": "DUF621", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04789", "structures": 0, "taxa": 133, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as sugar transferase proteins, however this cannot be confirmed.", "domain_architectures": 2, "interpro_id": "", "known_evidence_count": null, "matches": 148, "name": "Protein of unknown function (DUF2972)", "partial_evidence_count": null, "pfam_id": "PF11186", "proteins": 148, "proteomes": 41, "short_name": "DUF2972", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11186", "structures": 0, "taxa": 116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterized proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]].", "domain_architectures": 2, "interpro_id": "IPR024214", "known_evidence_count": null, "matches": 218, "name": "Protein of unknown function (DUF3843)", "partial_evidence_count": null, "pfam_id": "PF12954", "proteins": 148, "proteomes": 132, "short_name": "DUF3843", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12954", "structures": 0, "taxa": 235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 157 and 195 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR031458", "known_evidence_count": null, "matches": 150, "name": "Domain of unknown function (DUF4677)", "partial_evidence_count": null, "pfam_id": "PF15726", "proteins": 148, "proteomes": 142, "short_name": "DUF4677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15726", "structures": 0, "taxa": 450, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, mainly Proteobacteria. Proteins in this family are approximately 90 amino acids in length and some members are associated with Ubiquinone biosynthesis methyltransferases.", "domain_architectures": 1, "interpro_id": "IPR046682", "known_evidence_count": null, "matches": 148, "name": "Family of unknown function (DUF6552)", "partial_evidence_count": null, "pfam_id": "PF20189", "proteins": 148, "proteomes": 145, "short_name": "DUF6552", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20189", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 259 and 297 amino acids in length. There are two conserved sequence motifs: AMKIP and SMN.", "domain_architectures": 1, "interpro_id": "IPR046656", "known_evidence_count": null, "matches": 148, "name": "Family of unknown function (DUF6674)", "partial_evidence_count": null, "pfam_id": "PF20379", "proteins": 148, "proteomes": 116, "short_name": "DUF6674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20379", "structures": 0, "taxa": 300, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 104, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046552", "known_evidence_count": null, "matches": 148, "name": "Family of unknown function (DUF6706)", "partial_evidence_count": null, "pfam_id": "PF20449", "proteins": 148, "proteomes": 135, "short_name": "DUF6706", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20449", "structures": 0, "taxa": 280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in viruses that infect Streptococcus thermophilus bacteria. All members are from Caudoviricetes viruses. The domain is approximately 50 amino acids in length. The function of this domain is currently unknown. An AlphaFold model shows these proteins adopt a compact domain composed of a three stranded beta sheet with a single alpha helix.", "domain_architectures": 2, "interpro_id": "IPR055628", "known_evidence_count": null, "matches": 148, "name": "Domain of unknown function (DUF7204)", "partial_evidence_count": null, "pfam_id": "PF23834", "proteins": 148, "proteomes": 148, "short_name": "DUF7204", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23834", "structures": 0, "taxa": 316, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised lipoproteins. The family includes a range of both bacteria and phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055847", "known_evidence_count": null, "matches": 148, "name": "Domain of unknown function (DUF7424)", "partial_evidence_count": null, "pfam_id": "PF24199", "proteins": 148, "proteomes": 144, "short_name": "DUF7424", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24199", "structures": 0, "taxa": 343, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 139, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins form a compact alpha helical domain composed of four short alpha helices.", "domain_architectures": 3, "interpro_id": "IPR058326", "known_evidence_count": null, "matches": 148, "name": "Domain of unknown function (DUF8013)", "partial_evidence_count": null, "pfam_id": "PF26043", "proteins": 148, "proteomes": 100, "short_name": "DUF8013", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26043", "structures": 0, "taxa": 177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in putative TLC domain-containing and other uncharacterised proteins mostly found in fungi. These proteins contain a SNARE-like fold. They are characterised by their tetrameric coiled-coil structures that facilitate membrane fusion processes. SNARE proteins are present in synaptic terminals, endoplasmic reticulum, and Golgi apparatus where the coiled-coil structure is important for membrane targeting and fusion specificity. The conserved coiled-coil architecture enables these proteins to function in vesicle trafficking and membrane fusion events [[cite:PUB00161918]].", "domain_architectures": 5, "interpro_id": "IPR059379", "known_evidence_count": null, "matches": 151, "name": "Domain of unknown function (DUF8335)", "partial_evidence_count": null, "pfam_id": "PF27019", "proteins": 148, "proteomes": 143, "short_name": "DUF8335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27019", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal of [pfam:PF18729] and its function is unknown. It adopts a TPR-like fold.", "domain_architectures": 2, "interpro_id": "IPR061668", "known_evidence_count": null, "matches": 148, "name": "Domain of unknown function (DUF8607)", "partial_evidence_count": null, "pfam_id": "PF30167", "proteins": 148, "proteomes": 141, "short_name": "DUF8607", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30167", "structures": 0, "taxa": 219, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found at the N-terminal of a group of uncharacterised sequences from bacteria, that is usually found associated with [pfam:PF13643]. This domain may adopt an elongated beta-stranded fold.", "domain_architectures": 2, "interpro_id": "IPR061669", "known_evidence_count": null, "matches": 148, "name": "Domain of unknown function (DUF8608)", "partial_evidence_count": null, "pfam_id": "PF30171", "proteins": 148, "proteomes": 146, "short_name": "DUF8608", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30171", "structures": 0, "taxa": 421, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of uncharacterised Archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR007417", "known_evidence_count": null, "matches": 147, "name": "Protein of unknown function (DUF473)", "partial_evidence_count": null, "pfam_id": "PF04322", "proteins": 147, "proteomes": 147, "short_name": "DUF473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04322", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in functionally uncharacterised bacterial proteins. This domain is found in association with [pfam:PF22789] and [pfam:PF10077], that are located C-terminal.", "domain_architectures": 2, "interpro_id": "IPR025102", "known_evidence_count": null, "matches": 147, "name": "Protein of unknown function (DUF4026) N-terminal", "partial_evidence_count": null, "pfam_id": "PF13218", "proteins": 147, "proteomes": 143, "short_name": "DUF4026_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13218", "structures": 0, "taxa": 278, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 360 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032129", "known_evidence_count": null, "matches": 147, "name": "Domain of unknown function (DUF5056)", "partial_evidence_count": null, "pfam_id": "PF16479", "proteins": 147, "proteomes": 147, "short_name": "DUF5056", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16479", "structures": 0, "taxa": 264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 183 and 215 amino acids in length. This family may be distantly related to [pfam:PF09370] suggesting these proteins may function as an enzyme of unknown activity.", "domain_architectures": 3, "interpro_id": "IPR046272", "known_evidence_count": null, "matches": 147, "name": "Domain of unknown function (DUF6305)", "partial_evidence_count": null, "pfam_id": "PF19823", "proteins": 147, "proteomes": 108, "short_name": "DUF6305", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19823", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046662", "known_evidence_count": null, "matches": 147, "name": "Domain of unknown function (DUF6771)", "partial_evidence_count": null, "pfam_id": "PF20561", "proteins": 147, "proteomes": 109, "short_name": "DUF6771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20561", "structures": 0, "taxa": 145, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 138, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in archaea. They contain four pairs of conserved cysteines as well as several conserved histidines. It is likely that these residues are involved in metal coordination.", "domain_architectures": 2, "interpro_id": "IPR055980", "known_evidence_count": null, "matches": 148, "name": "Family of unknown function (DUF7558)", "partial_evidence_count": null, "pfam_id": "PF24439", "proteins": 147, "proteomes": 98, "short_name": "DUF7558", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24439", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised eukaryotic proteins.", "domain_architectures": 4, "interpro_id": "IPR061833", "known_evidence_count": null, "matches": 148, "name": "Domain of unknown function (DUF8772)", "partial_evidence_count": null, "pfam_id": "PF30974", "proteins": 147, "proteomes": 116, "short_name": "DUF8772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30974", "structures": 0, "taxa": 311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 130 residues in length. Members of this family seem to be found exclusively in Rhizobium species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010889", "known_evidence_count": null, "matches": 146, "name": "Protein of unknown function (DUF1515)", "partial_evidence_count": null, "pfam_id": "PF07439", "proteins": 146, "proteomes": 113, "short_name": "DUF1515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07439", "structures": 0, "taxa": 182, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 72, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Two members of this family are found in Colwellia psychrerythraea (strain 34H / ATCC BAA-681) and one each in various other species of Colwellia and Shewanella. One member from C. psychrerythraea is of special interest because it is preceded by the same cis-regulatory site as a number of genes that have the PEP-CTERM domain described by PEP_anchor (IPR013424).", "domain_architectures": 2, "interpro_id": "IPR014271", "known_evidence_count": null, "matches": 147, "name": "Protein of unknown function (DUF2375)", "partial_evidence_count": null, "pfam_id": "PF09558", "proteins": 146, "proteomes": 96, "short_name": "DUF2375", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09558", "structures": 0, "taxa": 131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR020248", "known_evidence_count": null, "matches": 146, "name": "Family of unknown function (DUF5491)", "partial_evidence_count": null, "pfam_id": "PF17595", "proteins": 146, "proteomes": 146, "short_name": "DUF5491", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17595", "structures": 0, "taxa": 321, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001062) is described by MIBiG as an example of the following biosynthetic class, polyketide.", "domain_architectures": 2, "interpro_id": "IPR046001", "known_evidence_count": null, "matches": 146, "name": "Family of unknown function (DUF5957)", "partial_evidence_count": null, "pfam_id": "PF19382", "proteins": 146, "proteomes": 143, "short_name": "DUF5957", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19382", "structures": 0, "taxa": 237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000838) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the flexirubin biosynthetic gene cluster from Flavobacterium johnsoniae. This protein has no known function. It is found in Actinobacteria, Proteobacteria and Bacteroidetes. Proteins in this family are typically between 234 and 271 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046026", "known_evidence_count": null, "matches": 147, "name": "Family of unknown function (DUF5984)", "partial_evidence_count": null, "pfam_id": "PF19446", "proteins": 146, "proteomes": 143, "short_name": "DUF5984", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19446", "structures": 0, "taxa": 308, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001890) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). The exemplar is the amphi-enterobactin 1 biosynthetic gene cluster from Vibrio campbellii [[cite:PUB00099429]].", "domain_architectures": 4, "interpro_id": "IPR046033", "known_evidence_count": null, "matches": 146, "name": "Family of unknown function (DUF5991)", "partial_evidence_count": null, "pfam_id": "PF19453", "proteins": 146, "proteomes": 142, "short_name": "DUF5991", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19453", "structures": 0, "taxa": 297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes bacteria. Proteins in this family are typically between 377 and 403 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046114", "known_evidence_count": null, "matches": 147, "name": "Family of unknown function (DUF6051)", "partial_evidence_count": null, "pfam_id": "PF19519", "proteins": 146, "proteomes": 143, "short_name": "DUF6051", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19519", "structures": 0, "taxa": 252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001055) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the yersiniabactin biosynthetic gene cluster from Escherichia coli [[cite:PUB00098903]]. This family appears to be predominantly found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR046188", "known_evidence_count": null, "matches": 146, "name": "Family of unknown function (DUF6216)", "partial_evidence_count": null, "pfam_id": "PF19723", "proteins": 146, "proteomes": 143, "short_name": "DUF6216", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19723", "structures": 0, "taxa": 281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "This family includes uncharacterised proteins from Firmicutes and phages, some members are phage tail-related proteins. Included in this entry is the prophage-derived protein YomH from Bacillus subtilis (swiss:O31977). This entry contains a RIFT-related beta barrel domain.", "domain_architectures": 6, "interpro_id": "IPR046688", "known_evidence_count": null, "matches": 146, "name": "Phage tail protein N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20195", "proteins": 146, "proteomes": 143, "short_name": "DUF6558", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20195", "structures": 0, "taxa": 280, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in various bacteriophages that infect Salmonella, Escherichia, Shigella, Pantoea and Serratia species. This family includes a member in bacteriophage T5. The function of this protein is currently unknown. Structure prediction does not predict a globular compact fold for this protein.", "domain_architectures": 1, "interpro_id": "IPR055719", "known_evidence_count": null, "matches": 146, "name": "Family of unknown function (DUF7295)", "partial_evidence_count": null, "pfam_id": "PF23967", "proteins": 146, "proteomes": 145, "short_name": "DUF7295", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23967", "structures": 0, "taxa": 302, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a small domain found in a group of uncharacterised archaeal sequences. This small domain may have an all-beta fold.", "domain_architectures": 4, "interpro_id": "IPR055829", "known_evidence_count": null, "matches": 146, "name": "Domain of unknown function (DUF7406)", "partial_evidence_count": null, "pfam_id": "PF24155", "proteins": 146, "proteomes": 136, "short_name": "DUF7406", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24155", "structures": 0, "taxa": 225, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved domain of unknown function (DUF7678) found in various bacterial species. The domain is approximately 75-100 amino acids in length and contains several highly conserved residues. The function of this domain remains to be determined. Structure prediction suggests this domain is composed of a 6 stranded beta sheet with an Alpha helix packed on one side.", "domain_architectures": 1, "interpro_id": "IPR056095", "known_evidence_count": null, "matches": 146, "name": "Domain of unknown function (DUF7678)", "partial_evidence_count": null, "pfam_id": "PF24726", "proteins": 146, "proteomes": 128, "short_name": "DUF7678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24726", "structures": 0, "taxa": 334, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Structure prediction suggests these proteins may adopt an alpha helical structure.", "domain_architectures": 1, "interpro_id": "IPR058318", "known_evidence_count": null, "matches": 146, "name": "Family of unknown function (DUF8005)", "partial_evidence_count": null, "pfam_id": "PF26027", "proteins": 146, "proteomes": 124, "short_name": "DUF8005", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26027", "structures": 0, "taxa": 208, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram-negative bacteria. It is usually preceded by a hydrophobic alpha-helix predicted as transmembrane. This domain is predicted to adopt an OB-fold and has a significant structural similarity to bacterial enterotoxins and related domains members of this superfamily.", "domain_architectures": 1, "interpro_id": "IPR058501", "known_evidence_count": null, "matches": 146, "name": "Domain of unknown function (DUF8188)", "partial_evidence_count": null, "pfam_id": "PF26603", "proteins": 146, "proteomes": 48, "short_name": "DUF8188", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26603", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 68 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, particularly members of the family Demerecviridae. Within this family, the proteins are predominantly found in the genera Tequintavirus and Epseptimavirus. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061606", "known_evidence_count": null, "matches": 146, "name": "Family of unknown function (DUF8536)", "partial_evidence_count": null, "pfam_id": "PF29384", "proteins": 146, "proteomes": 146, "short_name": "DUF8536", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29384", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins from Escherichia coli and Citrobacter rodentium. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR010437", "known_evidence_count": null, "matches": 145, "name": "Protein of unknown function (DUF1039)", "partial_evidence_count": null, "pfam_id": "PF06287", "proteins": 145, "proteomes": 127, "short_name": "DUF1039", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06287", "structures": 2, "taxa": 238, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001073) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide.", "domain_architectures": 4, "interpro_id": "IPR046000", "known_evidence_count": null, "matches": 149, "name": "Family of unknown function (DUF5956)", "partial_evidence_count": null, "pfam_id": "PF19381", "proteins": 145, "proteomes": 132, "short_name": "DUF5956", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19381", "structures": 0, "taxa": 228, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 159 and 191 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046644", "known_evidence_count": null, "matches": 145, "name": "Family of unknown function (DUF6756)", "partial_evidence_count": null, "pfam_id": "PF20541", "proteins": 145, "proteomes": 135, "short_name": "DUF6756", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20541", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 87, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins. They are predicted to fold into a globular structure consisting mainly of alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR053917", "known_evidence_count": null, "matches": 145, "name": "Family of unknown function (DUF6979)", "partial_evidence_count": null, "pfam_id": "PF22399", "proteins": 145, "proteomes": 138, "short_name": "DUF6979", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22399", "structures": 0, "taxa": 347, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins that have a predicted N-terminal transmembrane helix and a coiled-coil region. Structure prediction suggests that these proteins may adopt a trimeric coiled-coil structure. Many of these proteins are annotated as holins, however the origin of that annotation is unclear.", "domain_architectures": 2, "interpro_id": "IPR055789", "known_evidence_count": null, "matches": 145, "name": "Coiled-coil region of unknown function (DUF7365)", "partial_evidence_count": null, "pfam_id": "PF24073", "proteins": 145, "proteomes": 138, "short_name": "DUF7365", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24073", "structures": 0, "taxa": 325, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small uncharacterised enterobacterial phage protein family. Structure prediction suggests these proteins might adopt a pair of alpha helices.", "domain_architectures": 1, "interpro_id": "IPR055839", "known_evidence_count": null, "matches": 145, "name": "Family of unknown function (DUF7416)", "partial_evidence_count": null, "pfam_id": "PF24188", "proteins": 145, "proteomes": 145, "short_name": "DUF7416", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24188", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 87, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised cyanobacterial proteins that are probably related to Psb35 protein and are restricted to species that have photosystem II.", "domain_architectures": 1, "interpro_id": "IPR058095", "known_evidence_count": null, "matches": 145, "name": "Family of unknown function (DUF8210)", "partial_evidence_count": null, "pfam_id": "PF26637", "proteins": 145, "proteomes": 132, "short_name": "DUF8210", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26637", "structures": 0, "taxa": 388, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 139, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in the class Halobacteria. The proteins containing this domain are predominantly found in various genera within the Halobacteriales order. The domain is typically found in proteins ranging from 129 to 225 amino acids in length. These proteins are predicted to be integral membrane proteins, as suggested by the presence of two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058528", "known_evidence_count": null, "matches": 145, "name": "Domain of unknown function (DUF8215)", "partial_evidence_count": null, "pfam_id": "PF26650", "proteins": 145, "proteomes": 96, "short_name": "DUF8215", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26650", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001448) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the malacidin A biosynthetic gene cluster from uncultured bacterium [[cite:PUB00099471]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR046182", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF6210)", "partial_evidence_count": null, "pfam_id": "PF19715", "proteins": 144, "proteomes": 140, "short_name": "DUF6210", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19715", "structures": 0, "taxa": 320, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found mainly in Bacteroidetes. Proteins in this family are approximately 120 amino acids in length. There is a conserved motif NF/Y and two conserved residues, a Cys and an Asn.", "domain_architectures": 2, "interpro_id": "IPR046697", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF6567)", "partial_evidence_count": null, "pfam_id": "PF20205", "proteins": 144, "proteomes": 129, "short_name": "DUF6567", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20205", "structures": 0, "taxa": 287, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 90, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 188 and 366 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046728", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF6620)", "partial_evidence_count": null, "pfam_id": "PF20325", "proteins": 144, "proteomes": 143, "short_name": "DUF6620", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20325", "structures": 0, "taxa": 270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group on uncharacterised proteins from fungi. The function of this domain is unknown. According to structural predictions, this domain likely adopts an alpha-beta-beta-beta-beta-alpha fold. This domain is usually found associated with an alpha-helical domain at the N-terminal ([pfam:PF23391]) and a beta-propeller at the C-terminal ([pfam:PF23388]).", "domain_architectures": 8, "interpro_id": "IPR055527", "known_evidence_count": null, "matches": 145, "name": "Domain of unknown function (DUF7101)", "partial_evidence_count": null, "pfam_id": "PF23392", "proteins": 144, "proteomes": 140, "short_name": "DUF7101", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23392", "structures": 0, "taxa": 317, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of short bacterial phage proteins, typically around 90 amino acids in length, that contain two transmembrane helices. The family is found in phages that infect Enterobacteria.", "domain_architectures": 1, "interpro_id": "IPR055600", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF7176)", "partial_evidence_count": null, "pfam_id": "PF23800", "proteins": 144, "proteomes": 144, "short_name": "DUF7176", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23800", "structures": 0, "taxa": 300, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. The family includes the y13F protein from bacteriophage T4 [swissprot:P39499]. Structure prediction shows this protein has a compact globular fold composed of three beta strands and two alpha helices.", "domain_architectures": 1, "interpro_id": "IPR055779", "known_evidence_count": null, "matches": 144, "name": "Domain of unknown function (DUF7355)", "partial_evidence_count": null, "pfam_id": "PF24051", "proteins": 144, "proteomes": 144, "short_name": "DUF7355", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24051", "structures": 0, "taxa": 315, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins from enterobacterial phage. The proteins are around 56 residues in length.", "domain_architectures": 1, "interpro_id": "IPR056035", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF7616)", "partial_evidence_count": null, "pfam_id": "PF24592", "proteins": 144, "proteomes": 144, "short_name": "DUF7616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24592", "structures": 0, "taxa": 300, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised protein from Leptospira interrogans serogroup Icterohaemorrhagiae serovar Copenhageni and related bacterial proteins. Its structure was determined (PDB:6ULO) and shares a significant similarity to various methyltransferases.", "domain_architectures": 3, "interpro_id": "IPR056692", "known_evidence_count": null, "matches": 154, "name": "Domain of unknown function (DUF7790)", "partial_evidence_count": null, "pfam_id": "PF25046", "proteins": 144, "proteomes": 99, "short_name": "DUF7790", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25046", "structures": 1, "taxa": 204, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Streptococcus bacteriophage sequences and related proteins from Streptococcus species. Members of this family are typically around 100 residues in length and their function is unknown.", "domain_architectures": 1, "interpro_id": "IPR010779", "known_evidence_count": null, "matches": 143, "name": "Protein of unknown function (DUF1372)", "partial_evidence_count": null, "pfam_id": "PF07116", "proteins": 143, "proteomes": 138, "short_name": "DUF1372", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07116", "structures": 0, "taxa": 297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR012032", "known_evidence_count": null, "matches": 144, "name": "Uncharacterized protein conserved in archaea (DUF2117)", "partial_evidence_count": null, "pfam_id": "PF09890", "proteins": 143, "proteomes": 132, "short_name": "DUF2117", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09890", "structures": 0, "taxa": 264, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of small integral membrane proteins is functionally uncharacterised. This family may be distantly related to [pfam:PF05987]. This family of proteins is found in proteobacteria. Proteins in this family are typically between 104 and 121 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046515", "known_evidence_count": null, "matches": 143, "name": "Family of unknown function (DUF6693)", "partial_evidence_count": null, "pfam_id": "PF20403", "proteins": 143, "proteomes": 142, "short_name": "DUF6693", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20403", "structures": 0, "taxa": 296, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicutes bacteria. Proteins in this family are typically 115 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046639", "known_evidence_count": null, "matches": 143, "name": "Family of unknown function (DUF6751)", "partial_evidence_count": null, "pfam_id": "PF20536", "proteins": 143, "proteomes": 126, "short_name": "DUF6751", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20536", "structures": 0, "taxa": 265, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "These proteins are found in various phages infecting bacteria from the Enterobacteriaceae family, such as Escherichia, Salmonella, Shigella, Klebsiella, and Yersinia. They are typically around 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR055627", "known_evidence_count": null, "matches": 143, "name": "Family of unknown function (DUF7203)", "partial_evidence_count": null, "pfam_id": "PF23833", "proteins": 143, "proteomes": 143, "short_name": "DUF7203", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23833", "structures": 0, "taxa": 312, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in various cyanophages, bacteriophages and bacteria species. The domain is approximately 100-160 amino acids in length. Structure prediction shows this domain is alpha helical.", "domain_architectures": 1, "interpro_id": "IPR055646", "known_evidence_count": null, "matches": 143, "name": "Domain of unknown function (DUF7222)", "partial_evidence_count": null, "pfam_id": "PF23864", "proteins": 143, "proteomes": 126, "short_name": "DUF7222", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23864", "structures": 0, "taxa": 281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a set of uncharacterised phage proteins that are related to the Pam3 phage gp33 protein.", "domain_architectures": 2, "interpro_id": "IPR055731", "known_evidence_count": null, "matches": 146, "name": "Pam3 gp33-like protein", "partial_evidence_count": null, "pfam_id": "PF23984", "proteins": 143, "proteomes": 138, "short_name": "DUF7307", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23984", "structures": 0, "taxa": 411, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised metazoan proteins. It has a detectable sequence similarity to HTH winged helix domains and it is predicted to adopt similar structure. In some proteins, this domain is found two copies and usually associated with [pfam:PF24359].", "domain_architectures": 17, "interpro_id": "IPR055938", "known_evidence_count": null, "matches": 146, "name": "Domain of unknown function (DUF7516)", "partial_evidence_count": null, "pfam_id": "PF24360", "proteins": 143, "proteomes": 48, "short_name": "DUF7516", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24360", "structures": 0, "taxa": 138, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised worm proteins. They contain highly conserved cysteine residues that are predicted to form disulfide bonds. It is likely that these proteins are secreted.", "domain_architectures": 3, "interpro_id": "IPR056674", "known_evidence_count": null, "matches": 143, "name": "Family of unknown function (DUF7772)", "partial_evidence_count": null, "pfam_id": "PF24977", "proteins": 143, "proteomes": 14, "short_name": "DUF7772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24977", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 135, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in Halobacteria. The domain is found in proteins from various archaeal species, predominantly within the Halobacteriales order. Proteins containing this domain are typically around 70-90 amino acids in length. This domain adopts a five stranded beta barrel fold.", "domain_architectures": 2, "interpro_id": "IPR058452", "known_evidence_count": null, "matches": 143, "name": "Domain of unknown function (DUF8139)", "partial_evidence_count": null, "pfam_id": "PF26460", "proteins": 143, "proteomes": 101, "short_name": "DUF8139", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26460", "structures": 0, "taxa": 201, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 142, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 10, "interpro_id": "IPR005044", "known_evidence_count": null, "matches": 174, "name": "Caenorhabditis protein of unknown function, DUF282", "partial_evidence_count": null, "pfam_id": "PF03380", "proteins": 142, "proteomes": 14, "short_name": "DUF282", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03380", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family are around 120 amino acids in length and are found in some archaebacteria. The function of this family is unknown. However it contains a conserved motif IHPPAH that may be involved in its function.", "domain_architectures": 1, "interpro_id": "IPR007154", "known_evidence_count": null, "matches": 142, "name": "Protein of unknown function (DUF356)", "partial_evidence_count": null, "pfam_id": "PF04009", "proteins": 142, "proteomes": 137, "short_name": "DUF356", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04009", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR020157", "known_evidence_count": null, "matches": 142, "name": "Protein of unknown function (DUF2552)", "partial_evidence_count": null, "pfam_id": "PF10827", "proteins": 142, "proteomes": 142, "short_name": "DUF2552", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10827", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals. Family members have one or several predicted transmembrane regions.", "domain_architectures": 3, "interpro_id": "IPR040425", "known_evidence_count": null, "matches": 143, "name": "Family of unknown function (DUF5562)", "partial_evidence_count": null, "pfam_id": "PF17717", "proteins": 142, "proteomes": 131, "short_name": "DUF5562", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17717", "structures": 0, "taxa": 420, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 3, "interpro_id": "IPR045930", "known_evidence_count": null, "matches": 143, "name": "Family of unknown function (DUF6349)", "partial_evidence_count": null, "pfam_id": "PF19876", "proteins": 142, "proteomes": 131, "short_name": "DUF6349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19876", "structures": 0, "taxa": 217, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046734", "known_evidence_count": null, "matches": 142, "name": "Family of unknown function (DUF6626)", "partial_evidence_count": null, "pfam_id": "PF20331", "proteins": 142, "proteomes": 97, "short_name": "DUF6626", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20331", "structures": 0, "taxa": 234, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a number of uncharacterised bacterial proteins that are likely associated with the membrane.", "domain_architectures": 2, "interpro_id": "IPR054258", "known_evidence_count": null, "matches": 142, "name": "Domain of unknown function (DUF6989)", "partial_evidence_count": null, "pfam_id": "PF22497", "proteins": 142, "proteomes": 140, "short_name": "DUF6989", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22497", "structures": 0, "taxa": 297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small phage protein forms a predicted strand swapped dimer using AlphaFold. It is composed of three beta strands and two alpha helices.There is also some weaker evidence for a tetramer. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR055591", "known_evidence_count": null, "matches": 142, "name": "Domain of unknown function (DUF7167)", "partial_evidence_count": null, "pfam_id": "PF23768", "proteins": 142, "proteomes": 135, "short_name": "DUF7167", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23768", "structures": 0, "taxa": 344, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a family of identified in phage metagenomic datasets. The family contains proteins from a variety of phages that infect actinobacteria, particularly Mycobacterium, Gordonia, and Streptomyces. The exact specificity and function of this metagenomic family is currently unknown. Some members are described as N-glycosylases but the source of that information is uncertain.", "domain_architectures": 4, "interpro_id": "IPR055602", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF7178)", "partial_evidence_count": null, "pfam_id": "PF23802", "proteins": 142, "proteomes": 139, "short_name": "DUF7178", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23802", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "ThiS entry represents a family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055792", "known_evidence_count": null, "matches": 142, "name": "Family of unknown function (DUF7368)", "partial_evidence_count": null, "pfam_id": "PF24076", "proteins": 142, "proteomes": 141, "short_name": "DUF7368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24076", "structures": 0, "taxa": 336, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 136, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins found in Halobacteria. They contain three invariant cysteine residues and a histidine that probably constitute a metal binding site. These proteins are probably C2HC zinc fingers that are variant of the classical C2H2 zinc finger domains.", "domain_architectures": 2, "interpro_id": "IPR055924", "known_evidence_count": null, "matches": 142, "name": "Family of unknown function (DUF7501)", "partial_evidence_count": null, "pfam_id": "PF24333", "proteins": 142, "proteomes": 131, "short_name": "DUF7501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24333", "structures": 0, "taxa": 229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble Zinc beta-ribbon domains.", "domain_architectures": 2, "interpro_id": "IPR057159", "known_evidence_count": null, "matches": 142, "name": "Domain of unknown function (DUF7837)", "partial_evidence_count": null, "pfam_id": "PF25207", "proteins": 142, "proteomes": 100, "short_name": "DUF7837", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25207", "structures": 0, "taxa": 223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of sequences from hypothetical bacterial and bacteriophage proteins. The region in question is approximately 150 residues long and is highly conserved throughout the family.", "domain_architectures": 1, "interpro_id": "IPR011675", "known_evidence_count": null, "matches": 141, "name": "Protein of unknown function (DUF1617)", "partial_evidence_count": null, "pfam_id": "PF07761", "proteins": 141, "proteomes": 114, "short_name": "DUF1617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07761", "structures": 0, "taxa": 255, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR018701", "known_evidence_count": null, "matches": 141, "name": "Predicted membrane protein (DUF2206)", "partial_evidence_count": null, "pfam_id": "PF09971", "proteins": 141, "proteomes": 114, "short_name": "DUF2206", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09971", "structures": 0, "taxa": 262, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in mycobacteria. Proteins in this family are typically around 1200 amino acids in length. Mycoplasma contain three homologues in this family per genome.", "domain_architectures": 2, "interpro_id": "IPR022186", "known_evidence_count": null, "matches": 141, "name": "Protein of unknown function (DUF3713)", "partial_evidence_count": null, "pfam_id": "PF12506", "proteins": 141, "proteomes": 29, "short_name": "DUF3713", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12506", "structures": 3, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 120 and 154 amino acids in length. There are two conserved sequence motifs: LEQ and DLE.", "domain_architectures": 2, "interpro_id": "IPR027880", "known_evidence_count": null, "matches": 142, "name": "Domain of unknown function (DUF4635)", "partial_evidence_count": null, "pfam_id": "PF15466", "proteins": 141, "proteomes": 127, "short_name": "DUF4635", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15466", "structures": 0, "taxa": 414, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes the OrfY protein from the hyperthermophilic archaeum Thermoproteus tenax. This protein co-occurs with the treS/P protein in an operon regulating the synthesis of trehalose. The structure of this protein shows it contains an internal duplication [[cite:PUB00094669]].", "domain_architectures": 6, "interpro_id": "IPR044036", "known_evidence_count": null, "matches": 141, "name": "Family of unknown function (DUF5752)", "partial_evidence_count": null, "pfam_id": "PF19027", "proteins": 141, "proteomes": 140, "short_name": "DUF5752", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19027", "structures": 1, "taxa": 454, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are typically between 969 and 1090 amino acids in length. Some members of this family are thought to be related to the Flagellar hook-length control protein FliK.", "domain_architectures": 8, "interpro_id": "IPR046207", "known_evidence_count": null, "matches": 246, "name": "Family of unknown function (DUF6240)", "partial_evidence_count": null, "pfam_id": "PF19753", "proteins": 141, "proteomes": 137, "short_name": "DUF6240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19753", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in a family of uncharacterised bacterial proteins. This domain has a significant sequence similarity to the N-terminal domains of a number of proteins members of UDP-Glycosyltransferase/glycogen phosphorylase superfamily. It is predicted to adopt the same alpha/beta structure.", "domain_architectures": 5, "interpro_id": "IPR054217", "known_evidence_count": null, "matches": 141, "name": "Domain of unknown function (DUF6937)", "partial_evidence_count": null, "pfam_id": "PF22052", "proteins": 141, "proteomes": 130, "short_name": "DUF6937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22052", "structures": 0, "taxa": 331, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. Family members are largely found in mycobacterial phage.", "domain_architectures": 1, "interpro_id": "IPR055850", "known_evidence_count": null, "matches": 141, "name": "Family of unknown function (DUF7427)", "partial_evidence_count": null, "pfam_id": "PF24202", "proteins": 141, "proteomes": 137, "short_name": "DUF7427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24202", "structures": 0, "taxa": 315, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 130, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in the uncharacterised protein ZK1098.2 from Caenorhabditis elegans and similar sequences. It is predicted to adopt an alpha/beta configuration.", "domain_architectures": 18, "interpro_id": "IPR059291", "known_evidence_count": null, "matches": 141, "name": "Domain of unknown function (DUF8247)", "partial_evidence_count": null, "pfam_id": "PF26742", "proteins": 141, "proteomes": 33, "short_name": "DUF8247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26742", "structures": 0, "taxa": 154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found towards the C-terminal end of a group of uncharacterised proteins from molluscs. It is predicted to adopt a mainly beta configuration.", "domain_architectures": 3, "interpro_id": "IPR061861", "known_evidence_count": null, "matches": 141, "name": "Domain of unknown function (DUF8800)", "partial_evidence_count": null, "pfam_id": "PF31068", "proteins": 141, "proteomes": 10, "short_name": "DUF8800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31068", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Eubacterium rectale gene EUBREC_0237. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14737), it appears to be upregulated in the presence of Bacteroides thetaiotaomicron vs when isolated in culture [[cite:PUB00056060]].", "domain_architectures": 4, "interpro_id": "IPR024539", "known_evidence_count": null, "matches": 141, "name": "Domain of unknown function, E. rectale Gene description (DUF3877)", "partial_evidence_count": null, "pfam_id": "PF12993", "proteins": 140, "proteomes": 134, "short_name": "DUF3877", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12993", "structures": 0, "taxa": 223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025047", "known_evidence_count": null, "matches": 140, "name": "Protein of unknown function (DUF3986)", "partial_evidence_count": null, "pfam_id": "PF13143", "proteins": 140, "proteomes": 110, "short_name": "DUF3986", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13143", "structures": 0, "taxa": 185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 255 and 305 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045933", "known_evidence_count": null, "matches": 140, "name": "Family of unknown function (DUF6353)", "partial_evidence_count": null, "pfam_id": "PF19880", "proteins": 140, "proteomes": 62, "short_name": "DUF6353", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19880", "structures": 0, "taxa": 160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins that are largely composed of a single alpha helix. Some members of the family are found on phage. The function of these proteins is unknown.", "domain_architectures": 3, "interpro_id": "IPR054182", "known_evidence_count": null, "matches": 140, "name": "Family of unknown function (DUF6889)", "partial_evidence_count": null, "pfam_id": "PF21829", "proteins": 140, "proteomes": 135, "short_name": "DUF6889", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21829", "structures": 0, "taxa": 329, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains a pair of conserved cysteines and it is predicted to adopt a fold which is typical for zinc-ribbon domains.", "domain_architectures": 2, "interpro_id": "IPR056112", "known_evidence_count": null, "matches": 140, "name": "Domain of unknown function (DUF7695)", "partial_evidence_count": null, "pfam_id": "PF24749", "proteins": 140, "proteomes": 135, "short_name": "DUF7695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24749", "structures": 0, "taxa": 350, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised Actinomycete proteins. These proteins may form homodimers (AlphaFold3 A6WE73 ipTM = 0.79). The dimerisation is mediated by a C-terminal alpha helical subdomain.", "domain_architectures": 2, "interpro_id": "IPR056128", "known_evidence_count": null, "matches": 140, "name": "Domain of unknown function (DUF7711)", "partial_evidence_count": null, "pfam_id": "PF24821", "proteins": 140, "proteomes": 135, "short_name": "DUF7711", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24821", "structures": 0, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains highly conserved cysteine and histidine residues that are likely involved in zinc coordination.", "domain_architectures": 5, "interpro_id": "IPR057150", "known_evidence_count": null, "matches": 140, "name": "Domain of unknown function (DUF7828)", "partial_evidence_count": null, "pfam_id": "PF25165", "proteins": 140, "proteomes": 74, "short_name": "DUF7828", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25165", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 131, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins in halobacteria. The proteins in this family are found primarily in halophilic archaea, including members of the Halobacteriales order. The domain is typically found in proteins ranging from 280 to 295 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058485", "known_evidence_count": null, "matches": 140, "name": "Family of unknown function (DUF8172)", "partial_evidence_count": null, "pfam_id": "PF26511", "proteins": 140, "proteomes": 110, "short_name": "DUF8172", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26511", "structures": 0, "taxa": 197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 104, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from aquatic invertebrates. It is predicted to fold into a very distinct curved beta-sheet and alpha-helices packed on the concave side of it.", "domain_architectures": 4, "interpro_id": "IPR059282", "known_evidence_count": null, "matches": 141, "name": "Domain of unknown function (DUF8238)", "partial_evidence_count": null, "pfam_id": "PF26709", "proteins": 140, "proteomes": 12, "short_name": "DUF8238", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26709", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 137, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of worm domain has no known function. The boundaries of the presumed domain are rather uncertain.", "domain_architectures": 9, "interpro_id": "IPR005098", "known_evidence_count": null, "matches": 202, "name": "Domain of unknown function (DUF281)", "partial_evidence_count": null, "pfam_id": "PF03436", "proteins": 139, "proteomes": 10, "short_name": "DUF281", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03436", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 30 amino acids in length. There is a conserved NFS sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025030", "known_evidence_count": null, "matches": 139, "name": "Domain of unknown function (DUF3950)", "partial_evidence_count": null, "pfam_id": "PF13132", "proteins": 139, "proteomes": 124, "short_name": "DUF3950", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13132", "structures": 0, "taxa": 301, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in T7 viruses.", "domain_architectures": 1, "interpro_id": "IPR035111", "known_evidence_count": null, "matches": 139, "name": "Family of unknown function (DUF5516)", "partial_evidence_count": null, "pfam_id": "PF17637", "proteins": 139, "proteomes": 137, "short_name": "DUF5516", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17637", "structures": 0, "taxa": 297, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised bacterial proteins.", "domain_architectures": 7, "interpro_id": "IPR046534", "known_evidence_count": null, "matches": 140, "name": "Family of unknown function (DUF6599)", "partial_evidence_count": null, "pfam_id": "PF20244", "proteins": 139, "proteomes": 123, "short_name": "DUF6599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20244", "structures": 0, "taxa": 334, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 200 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046729", "known_evidence_count": null, "matches": 139, "name": "Family of unknown function (DUF6621)", "partial_evidence_count": null, "pfam_id": "PF20326", "proteins": 139, "proteomes": 138, "short_name": "DUF6621", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20326", "structures": 0, "taxa": 216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 180 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046590", "known_evidence_count": null, "matches": 140, "name": "Family of unknown function (DUF6648)", "partial_evidence_count": null, "pfam_id": "PF20353", "proteins": 139, "proteomes": 137, "short_name": "DUF6648", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20353", "structures": 0, "taxa": 271, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry describes a domain of unknown function (DUF). It is found in phage proteins, generally around 70 amino acids in length. The domain is found in a variety of phages infecting hosts such as Escherichia, Shigella, Yersinia, Erwinia, Providencia, and Pectobacterium. No functional information is known. An AlphaFold model shows this protein adopts a three stranded beta sheet structure.", "domain_architectures": 1, "interpro_id": "IPR055626", "known_evidence_count": null, "matches": 139, "name": "Domain of unknown function (DUF7202)", "partial_evidence_count": null, "pfam_id": "PF23832", "proteins": 139, "proteomes": 138, "short_name": "DUF7202", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23832", "structures": 0, "taxa": 313, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055761", "known_evidence_count": null, "matches": 139, "name": "Family of unknown function (DUF7337)", "partial_evidence_count": null, "pfam_id": "PF24026", "proteins": 139, "proteomes": 139, "short_name": "DUF7337", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24026", "structures": 0, "taxa": 289, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 133, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in uncharacterised archaeal sequences.", "domain_architectures": 3, "interpro_id": "IPR055832", "known_evidence_count": null, "matches": 139, "name": "Domain of unknown function (DUF7409)", "partial_evidence_count": null, "pfam_id": "PF24158", "proteins": 139, "proteomes": 139, "short_name": "DUF7409", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24158", "structures": 0, "taxa": 229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is usually associated with von Willebrand factor type A domain (e.g. [pfam:PF00092]), which is inserted into the domain core. Members of this entry are likely to contain an intramolecular isopeptide bond. The domain represented by this entry is predicted to fold into a beta-sandwich but does not include the two N-terminal strands that precede the von Willebrand factor type A domain.", "domain_architectures": 60, "interpro_id": "IPR055384", "known_evidence_count": null, "matches": 143, "name": "Domain of unknown function (DUF7604)", "partial_evidence_count": null, "pfam_id": "PF24558", "proteins": 139, "proteomes": 113, "short_name": "DUF7604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24558", "structures": 3, "taxa": 232, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 1, "interpro_id": "IPR058338", "known_evidence_count": null, "matches": 139, "name": "Domain of unknown function (DUF8025)", "partial_evidence_count": null, "pfam_id": "PF26068", "proteins": 139, "proteomes": 104, "short_name": "DUF8025", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26068", "structures": 0, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds. Some proteins contain multiple tandem copies of this domain.", "domain_architectures": 37, "interpro_id": "IPR059296", "known_evidence_count": null, "matches": 215, "name": "Domain of unknown function (DUF8252)", "partial_evidence_count": null, "pfam_id": "PF26780", "proteins": 139, "proteomes": 44, "short_name": "DUF8252", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26780", "structures": 0, "taxa": 99, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This proteins is the product of the gene MPN330 and is thought to involved in a cellular function that has yet to be characterised. The proteins has 11 helices and a novel fold [[cite:PUB00037695]]. No function is currently known for this protein.", "domain_architectures": 2, "interpro_id": "IPR024503", "known_evidence_count": null, "matches": 138, "name": "Protein of unknown function (DUF3196)", "partial_evidence_count": null, "pfam_id": "PF11428", "proteins": 138, "proteomes": 138, "short_name": "DUF3196", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11428", "structures": 1, "taxa": 249, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 72, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025017", "known_evidence_count": null, "matches": 138, "name": "Protein of unknown function (DUF3954)", "partial_evidence_count": null, "pfam_id": "PF13128", "proteins": 138, "proteomes": 116, "short_name": "DUF3954", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13128", "structures": 0, "taxa": 208, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 76 and 140 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031487", "known_evidence_count": null, "matches": 138, "name": "Domain of unknown function (DUF4687)", "partial_evidence_count": null, "pfam_id": "PF15747", "proteins": 138, "proteomes": 128, "short_name": "DUF4687", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15747", "structures": 0, "taxa": 411, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in various Platyhelminthes, with many of the sequences annotated as being the polyprotein of the transposon Ty3-I Gag-Pol. However, the genomic location of other members suggests that this region is not always found in a transposon. The family members are characterised by a highly conserved DxDxDxCC motif. The function of this family is currently unknown.", "domain_architectures": 11, "interpro_id": "IPR043784", "known_evidence_count": null, "matches": 138, "name": "Family of unknown function (DUF5726)", "partial_evidence_count": null, "pfam_id": "PF18996", "proteins": 138, "proteomes": 5, "short_name": "DUF5726", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18996", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 96 and 117 amino acids in length. There are two conserved sequence motifs: RNT and VYGE.", "domain_architectures": 1, "interpro_id": "IPR046154", "known_evidence_count": null, "matches": 138, "name": "Family of unknown function (DUF6156)", "partial_evidence_count": null, "pfam_id": "PF19653", "proteins": 138, "proteomes": 138, "short_name": "DUF6156", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19653", "structures": 0, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of proteins which are functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046571", "known_evidence_count": null, "matches": 138, "name": "Domain of unknown function (DUF6725)", "partial_evidence_count": null, "pfam_id": "PF20486", "proteins": 138, "proteomes": 136, "short_name": "DUF6725", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20486", "structures": 0, "taxa": 193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins.", "domain_architectures": 2, "interpro_id": "IPR055925", "known_evidence_count": null, "matches": 139, "name": "Family of unknown function (DUF7502)", "partial_evidence_count": null, "pfam_id": "PF24334", "proteins": 138, "proteomes": 131, "short_name": "DUF7502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24334", "structures": 0, "taxa": 222, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 132, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins containing this domain are predominantly found in the class Halobacteria, which includes genera such as Halorubrum, Haloarculaceae, and Haloferacaceae. These proteins are typically found in extreme halophilic environments. The proteins in this family generally range from 88 to 138 amino acids in length. AlphaFold3 predicts this protein can form a homodimer [swissprot:U1Q8T4] (ipTM=0.81 pTM=0.81) which is composed of a four stranded beta sheet with a pair of helices packed on one side and two stacked pairs of helices on the other.", "domain_architectures": 1, "interpro_id": "IPR058426", "known_evidence_count": null, "matches": 138, "name": "Domain of unknown function (DUF8113)", "partial_evidence_count": null, "pfam_id": "PF26418", "proteins": 138, "proteomes": 126, "short_name": "DUF8113", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26418", "structures": 0, "taxa": 207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal of a group of uncharacterised bacterial sequences and it is predicted to adopt a single-stranded right-handed beta-helix with similarity to ice-binding proteins and other adhesive domains. These proteins are usually associated with tandem Ig-like domain, such as [swissprot:A1S2S0] which has five Ig-like domains.", "domain_architectures": 36, "interpro_id": "IPR061540", "known_evidence_count": null, "matches": 139, "name": "Domain of unknown function (DUF8470)", "partial_evidence_count": null, "pfam_id": "PF28862", "proteins": 138, "proteomes": 132, "short_name": "DUF8470", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28862", "structures": 0, "taxa": 249, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a conserved region found in uncharacterised eukaryotic proteins. It contains several conserved cysteine and histidine residues.", "domain_architectures": 5, "interpro_id": "IPR061832", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF8771)", "partial_evidence_count": null, "pfam_id": "PF30973", "proteins": 138, "proteomes": 71, "short_name": "DUF8771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30973", "structures": 0, "taxa": 301, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains hypothetical proteins of unknown function expressed by two archaeal species.", "domain_architectures": 1, "interpro_id": "IPR012874", "known_evidence_count": null, "matches": 137, "name": "Protein of unknown function (DUF1673)", "partial_evidence_count": null, "pfam_id": "PF07895", "proteins": 137, "proteomes": 33, "short_name": "DUF1673", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07895", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a beta sandwich domain found in a variety of bacterial cell surface proteins.", "domain_architectures": 30, "interpro_id": "IPR055890", "known_evidence_count": null, "matches": 247, "name": "Domain of unknown function (DUF7467)", "partial_evidence_count": null, "pfam_id": "PF24269", "proteins": 137, "proteomes": 83, "short_name": "DUF7467", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24269", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 87, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is usually found next to [pfam:PF24734]. It is predicted to adopt alpha/beta structure consisting of a four-stranded beta-sheet curved around an alpha-helix.", "domain_architectures": 5, "interpro_id": "IPR056103", "known_evidence_count": null, "matches": 137, "name": "Domain of unknown function (DUF7686)", "partial_evidence_count": null, "pfam_id": "PF24735", "proteins": 137, "proteomes": 119, "short_name": "DUF7686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24735", "structures": 0, "taxa": 270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised prokaryotic proteins. It is predicted to adopt alpha/beta structure consisting of a meander beta-sheet and a kinked alpha-helix. It contains several conserved aspartate and histidine residues that are predicted to come close in space and may constitute a metal binding site.", "domain_architectures": 2, "interpro_id": "IPR056135", "known_evidence_count": null, "matches": 137, "name": "Domain of unknown function (DUF7718)", "partial_evidence_count": null, "pfam_id": "PF24839", "proteins": 137, "proteomes": 101, "short_name": "DUF7718", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24839", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins in archaea. The proteins are predominantly found in the class Halobacteria, which includes families such as Natrialbaceae, Haloferacaceae, and Haloarculaceae. This family contains proteins ranging from 50 to 115 amino acids in length. These proteins contain and N-terminal transmembrane helix followed by a likely disordered C-terminus.", "domain_architectures": 1, "interpro_id": "IPR058456", "known_evidence_count": null, "matches": 137, "name": "Family of unknown function (DUF8143)", "partial_evidence_count": null, "pfam_id": "PF26467", "proteins": 137, "proteomes": 137, "short_name": "DUF8143", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26467", "structures": 0, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 73 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, particularly members of the family Demerecviridae. Within this family, the proteins are found in the genera Tequintavirus and Epseptimavirus. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061608", "known_evidence_count": null, "matches": 137, "name": "Family of unknown function (DUF8538)", "partial_evidence_count": null, "pfam_id": "PF29389", "proteins": 137, "proteomes": 136, "short_name": "DUF8538", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29389", "structures": 0, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 127, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of functionally uncharacterised domains are found in various Oryza sativa mutator-like transposases.", "domain_architectures": 16, "interpro_id": "IPR015401", "known_evidence_count": null, "matches": 138, "name": "Domain of unknown function (DUF1979)", "partial_evidence_count": null, "pfam_id": "PF09322", "proteins": 136, "proteomes": 22, "short_name": "DUF1979", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09322", "structures": 0, "taxa": 91, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 102, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins and in the RNA polymerase sigma factor, has no known function.", "domain_architectures": 5, "interpro_id": "IPR018734", "known_evidence_count": null, "matches": 136, "name": "Predicted integral membrane protein (DUF2275)", "partial_evidence_count": null, "pfam_id": "PF10039", "proteins": 136, "proteomes": 135, "short_name": "DUF2275", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10039", "structures": 0, "taxa": 223, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 98, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a Proteobacterial family of unknown function. Some of the proteins in this family are annotated as being kinesin-like proteins.", "domain_architectures": 2, "interpro_id": "IPR025002", "known_evidence_count": null, "matches": 136, "name": "Protein of unknown function (DUF3972)", "partial_evidence_count": null, "pfam_id": "PF13118", "proteins": 136, "proteomes": 133, "short_name": "DUF3972", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13118", "structures": 0, "taxa": 253, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 134, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of archaeal proteins. The domain is a putative gyrase domain.", "domain_architectures": 6, "interpro_id": "IPR029349", "known_evidence_count": null, "matches": 136, "name": "Domain of unknown function (DUF4443)", "partial_evidence_count": null, "pfam_id": "PF14544", "proteins": 136, "proteomes": 126, "short_name": "DUF4443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14544", "structures": 1, "taxa": 265, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 345 and 672 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR032086", "known_evidence_count": null, "matches": 164, "name": "Domain of unknown function (DUF4813)", "partial_evidence_count": null, "pfam_id": "PF16072", "proteins": 136, "proteomes": 42, "short_name": "DUF4813", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16072", "structures": 0, "taxa": 160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. There are highly conserved sequence motifs: FSxWFF and ExxxFP. There are eleven conserved tryptophan residues, which may suggest to play an important role. Proteins members of this family are likely composed of transmembrane helices and probably carry out transporter activity.", "domain_architectures": 2, "interpro_id": "IPR046712", "known_evidence_count": null, "matches": 148, "name": "Family of unknown function (DUF6785)", "partial_evidence_count": null, "pfam_id": "PF20581", "proteins": 136, "proteomes": 72, "short_name": "DUF6785", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20581", "structures": 0, "taxa": 238, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a domain of unknown function found in phage proteins. The proteins containing this domain average 90 to 100 amino acids in length and is found in a variety of phage proteins, particularly those from Streptomyces and Mycobacterium phages. The domain usually occurs near the middle or C-terminus of proteins. The domain forms a small beta barrel.", "domain_architectures": 1, "interpro_id": "IPR055670", "known_evidence_count": null, "matches": 136, "name": "Domain of unknown function (DUF7246)", "partial_evidence_count": null, "pfam_id": "PF23904", "proteins": 136, "proteomes": 136, "short_name": "DUF7246", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23904", "structures": 0, "taxa": 337, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small uncharacterised phage protein has a 5 stranded beta barrel fold.", "domain_architectures": 1, "interpro_id": "IPR055817", "known_evidence_count": null, "matches": 136, "name": "Domain of unknown function (DUF7393)", "partial_evidence_count": null, "pfam_id": "PF24119", "proteins": 136, "proteomes": 136, "short_name": "DUF7393", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24119", "structures": 0, "taxa": 311, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an alpha/beta structure with unique topology.", "domain_architectures": 4, "interpro_id": "IPR058503", "known_evidence_count": null, "matches": 137, "name": "Domain of unknown function (DUF8190)", "partial_evidence_count": null, "pfam_id": "PF26608", "proteins": 136, "proteomes": 48, "short_name": "DUF8190", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26608", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised Bacteroidia proteins that contain a single domain. There is some evidence from structure prediction that these proteins may form homodimers.", "domain_architectures": 1, "interpro_id": "IPR061512", "known_evidence_count": null, "matches": 136, "name": "Domain of unknown function (DUF8442)", "partial_evidence_count": null, "pfam_id": "PF28605", "proteins": 136, "proteomes": 136, "short_name": "DUF8442", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28605", "structures": 0, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 117, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The hypothetical eukaryotic proteins found in this family are of unknown function.", "domain_architectures": 3, "interpro_id": "IPR012872", "known_evidence_count": null, "matches": 141, "name": "Protein of unknown function (DUF1670)", "partial_evidence_count": null, "pfam_id": "PF07900", "proteins": 135, "proteomes": 48, "short_name": "DUF1670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07900", "structures": 0, "taxa": 186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Streptococcus.", "domain_architectures": 1, "interpro_id": "IPR021690", "known_evidence_count": null, "matches": 135, "name": "Protein of unknown function (DUF3272)", "partial_evidence_count": null, "pfam_id": "PF11676", "proteins": 135, "proteomes": 135, "short_name": "DUF3272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11676", "structures": 0, "taxa": 192, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in insects. Proteins in this family are typically between 186 and 228 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031754", "known_evidence_count": null, "matches": 135, "name": "Domain of unknown function (DUF4736)", "partial_evidence_count": null, "pfam_id": "PF15883", "proteins": 135, "proteomes": 53, "short_name": "DUF4736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15883", "structures": 0, "taxa": 195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Nematoda.", "domain_architectures": 4, "interpro_id": "IPR035231", "known_evidence_count": null, "matches": 138, "name": "Family of unknown function (DUF5346)", "partial_evidence_count": null, "pfam_id": "PF17281", "proteins": 135, "proteomes": 84, "short_name": "DUF5346", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17281", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR035134", "known_evidence_count": null, "matches": 135, "name": "Family of unknown function (DUF5498)", "partial_evidence_count": null, "pfam_id": "PF17602", "proteins": 135, "proteomes": 135, "short_name": "DUF5498", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17602", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 177 and 198 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046599", "known_evidence_count": null, "matches": 136, "name": "Family of unknown function (DUF6658)", "partial_evidence_count": null, "pfam_id": "PF20363", "proteins": 135, "proteomes": 106, "short_name": "DUF6658", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20363", "structures": 0, "taxa": 299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found mainly in Flavobacteriales lineage. It is predicted to fold into a small beta-sandwich elaborated with long loops.", "domain_architectures": 7, "interpro_id": "IPR059334", "known_evidence_count": null, "matches": 135, "name": "Domain of unknown function (DUF8290)", "partial_evidence_count": null, "pfam_id": "PF26939", "proteins": 135, "proteomes": 103, "short_name": "DUF8290", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26939", "structures": 0, "taxa": 115, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Epsilon-proteobacteria. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019724", "known_evidence_count": null, "matches": 134, "name": "Protein of unknown function (DUF2603)", "partial_evidence_count": null, "pfam_id": "PF10788", "proteins": 134, "proteomes": 118, "short_name": "DUF2603", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10788", "structures": 0, "taxa": 200, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 190 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR024218", "known_evidence_count": null, "matches": 134, "name": "Protein of unknown function (DUF3867)", "partial_evidence_count": null, "pfam_id": "PF12983", "proteins": 134, "proteomes": 134, "short_name": "DUF3867", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12983", "structures": 0, "taxa": 193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 250 residues in length and is mainly found in various Acinetobacter species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032322", "known_evidence_count": null, "matches": 134, "name": "Domain of unknown function (DUF4850)", "partial_evidence_count": null, "pfam_id": "PF16142", "proteins": 134, "proteomes": 128, "short_name": "DUF4850", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16142", "structures": 0, "taxa": 229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 160 residues in length and is mainly found in various Clostridium species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032619", "known_evidence_count": null, "matches": 134, "name": "Domain of unknown function (DUF4883)", "partial_evidence_count": null, "pfam_id": "PF16224", "proteins": 134, "proteomes": 132, "short_name": "DUF4883", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16224", "structures": 1, "taxa": 191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 128, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This C-type lectin domain is present in the IGP 'invariant glycoprotein' family of proteins from Trypanosoma and Leishmania [[cite:PUB00078718]].", "domain_architectures": 2, "interpro_id": "IPR031797", "known_evidence_count": null, "matches": 135, "name": "IGP family C-type lectin domain", "partial_evidence_count": null, "pfam_id": "PF16825", "proteins": 134, "proteomes": 27, "short_name": "DUF5075", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16825", "structures": 0, "taxa": 64, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 98, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001063) is described by MIBiG as an example of the following biosynthetic classes, polyketide and NRP (non-ribosomal peptide). It includes a member from the undecylprodigiosin biosynthetic gene cluster from Streptomyces coelicolor A3(2) [[cite:PUB00098992],[cite:PUB00098991]]. This family appears to be predominantly present in bacteria.", "domain_architectures": 3, "interpro_id": "IPR045780", "known_evidence_count": null, "matches": 134, "name": "Family of unknown function (DUF6206)", "partial_evidence_count": null, "pfam_id": "PF19709", "proteins": 134, "proteomes": 131, "short_name": "DUF6206", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19709", "structures": 0, "taxa": 264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins including from bacteriophage T6.", "domain_architectures": 2, "interpro_id": "IPR055630", "known_evidence_count": null, "matches": 137, "name": "Family of unknown function (DUF7206)", "partial_evidence_count": null, "pfam_id": "PF23836", "proteins": 134, "proteomes": 134, "short_name": "DUF7206", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23836", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. This family is composed of small proteins that are predicted to bind to zinc using three conserved cysteines an a conserved histidine.", "domain_architectures": 1, "interpro_id": "IPR058327", "known_evidence_count": null, "matches": 134, "name": "Domain of unknown function (DUF8014)", "partial_evidence_count": null, "pfam_id": "PF26046", "proteins": 134, "proteomes": 134, "short_name": "DUF8014", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26046", "structures": 0, "taxa": 232, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Eurotiomycetes. They are predicted to fold in a very distinct six-stranded beta-barrel structure which is topologically very similar to phage Gp54 protein structure.", "domain_architectures": 4, "interpro_id": "IPR059266", "known_evidence_count": null, "matches": 136, "name": "Domain of unknown function (DUF8222)", "partial_evidence_count": null, "pfam_id": "PF26667", "proteins": 134, "proteomes": 125, "short_name": "DUF8222", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26667", "structures": 0, "taxa": 197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 150 residues in length. Its members are found in human gut Firmicutes and are also abundant in human gut metagenomics datasets. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032360", "known_evidence_count": null, "matches": 133, "name": "Domain of unknown function (DUF4869)", "partial_evidence_count": null, "pfam_id": "PF16163", "proteins": 133, "proteomes": 94, "short_name": "DUF4869", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16163", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is frequently found upstream of family HATPase_c [pfam:PF00025]1.", "domain_architectures": 6, "interpro_id": "IPR033405", "known_evidence_count": null, "matches": 133, "name": "Domain of unknown function (DUF5112)", "partial_evidence_count": null, "pfam_id": "PF17139", "proteins": 133, "proteomes": 132, "short_name": "DUF5112", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17139", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is typically between 47 and 65 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046655", "known_evidence_count": null, "matches": 133, "name": "Family of unknown function (DUF6673)", "partial_evidence_count": null, "pfam_id": "PF20378", "proteins": 133, "proteomes": 119, "short_name": "DUF6673", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20378", "structures": 0, "taxa": 268, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in various phages that infect bacteria including Escherichia, Salmonella, Shigella, Klebsiella, Enterobacter, Citrobacter and Cronobacter. The protein ranges in length from around 66 to 98 amino acids. The protein forms a single compact domain composed of a four stranded beta sheet and two alpha helices. The structure shows some weak structural similarity to the BRICHOS domain. No clear function is known for these proteins.", "domain_architectures": 1, "interpro_id": "IPR055624", "known_evidence_count": null, "matches": 133, "name": "Domain of unknown function (DUF7200)", "partial_evidence_count": null, "pfam_id": "PF23830", "proteins": 133, "proteomes": 128, "short_name": "DUF7200", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23830", "structures": 0, "taxa": 280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of proteins from Halobacteria. It is predicted to adopt a structure that is reminiscent of ribbon-helix-helix fold. Members of this entry are likely to form dimers. They have a stretch of positively charged residues at the N terminus.", "domain_architectures": 1, "interpro_id": "IPR056109", "known_evidence_count": null, "matches": 133, "name": "Domain of unknown function (DUF7692)", "partial_evidence_count": null, "pfam_id": "PF24743", "proteins": 133, "proteomes": 87, "short_name": "DUF7692", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24743", "structures": 0, "taxa": 181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from lower eukaryotes. This domain is often associated with [pfam:PF13385]. It is predicted to show an alpha-beta configuration.", "domain_architectures": 3, "interpro_id": "IPR058332", "known_evidence_count": null, "matches": 133, "name": "Domain of unknown function (DUF8019)", "partial_evidence_count": null, "pfam_id": "PF26058", "proteins": 133, "proteomes": 62, "short_name": "DUF8019", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26058", "structures": 0, "taxa": 160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of plasmid encoded proteins with unknown function.", "domain_architectures": 2, "interpro_id": "IPR010416", "known_evidence_count": null, "matches": 132, "name": "Protein of unknown function (DUF1010)", "partial_evidence_count": null, "pfam_id": "PF06231", "proteins": 132, "proteomes": 25, "short_name": "DUF1010", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06231", "structures": 0, "taxa": 146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Streptococcus thermophilus bacteriophage proteins of around 235 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009774", "known_evidence_count": null, "matches": 132, "name": "Protein of unknown function (DUF1340)", "partial_evidence_count": null, "pfam_id": "PF07067", "proteins": 132, "proteomes": 132, "short_name": "DUF1340", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07067", "structures": 0, "taxa": 275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This repeat is found in a small number of proteins and is apparently limited to Coxiella and related species.", "domain_architectures": 75, "interpro_id": "IPR011632", "known_evidence_count": null, "matches": 481, "name": "Protein of unknown function (DUF1601)", "partial_evidence_count": null, "pfam_id": "PF07671", "proteins": 132, "proteomes": 45, "short_name": "DUF1601", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07671", "structures": 0, "taxa": 218, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 4, "interpro_id": "IPR061509", "known_evidence_count": null, "matches": 132, "name": "Uncharacterized protein conserved in archaea (DUF2111)", "partial_evidence_count": null, "pfam_id": "PF09884", "proteins": 132, "proteomes": 118, "short_name": "DUF2111", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09884", "structures": 0, "taxa": 234, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of N-terminal of several uncharacterised proteins around 260 residues in length and is mainly found in various Bacteroides and Parabacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032492", "known_evidence_count": null, "matches": 132, "name": "Domain of unknown function (DUF5045)", "partial_evidence_count": null, "pfam_id": "PF16464", "proteins": 132, "proteomes": 82, "short_name": "DUF5045", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16464", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is frequently found downstream of family HATPase_c [pfam:PF00025]1 in duplicate.", "domain_architectures": 5, "interpro_id": "IPR033406", "known_evidence_count": null, "matches": 261, "name": "Domain of unknown function (DUF5113)", "partial_evidence_count": null, "pfam_id": "PF17140", "proteins": 132, "proteomes": 130, "short_name": "DUF5113", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17140", "structures": 0, "taxa": 197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 61 and 97 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR046710", "known_evidence_count": null, "matches": 133, "name": "Family of unknown function (DUF6783)", "partial_evidence_count": null, "pfam_id": "PF20574", "proteins": 132, "proteomes": 18, "short_name": "DUF6783", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20574", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in uncharacterised bacterial proteins either as standalone or in combination with other domains. It is remotely related to soluble lipid-binding protein MlaC and it is predicted to adopt a similar structure with a typical NTF2-like topology.", "domain_architectures": 6, "interpro_id": "IPR053907", "known_evidence_count": null, "matches": 136, "name": "Domain of unknown function (DUF6935)", "partial_evidence_count": null, "pfam_id": "PF22043", "proteins": 132, "proteomes": 122, "short_name": "DUF6935", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22043", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found at the C-terminus of a family of uncharacterised proteins found in halobacteria. These proteins contain a [pfam:PF25256] domain at the N-terminus and this helical domain at the C-terminus. Structure prediction suggests this domain may mediate homodimerisation.", "domain_architectures": 4, "interpro_id": "IPR058393", "known_evidence_count": null, "matches": 132, "name": "Domain of unknown function (DUF8080)", "partial_evidence_count": null, "pfam_id": "PF26296", "proteins": 132, "proteomes": 131, "short_name": "DUF8080", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26296", "structures": 0, "taxa": 191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 129, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of family of uncharacterised proteins found in halobacteria. The C-terminal domain is part of the PD-(D/E)XK nuclease superfamily.", "domain_architectures": 2, "interpro_id": "IPR058394", "known_evidence_count": null, "matches": 132, "name": "Domain of unknown function (DUF8081)", "partial_evidence_count": null, "pfam_id": "PF26297", "proteins": 132, "proteomes": 117, "short_name": "DUF8081", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26297", "structures": 0, "taxa": 192, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 121, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial family that belongs to the PD-(D/E)XK nuclease superfamily. Proteins in this family generally contain a long N-terminal alpha helix that likely forms a trimeric coiled-coil structure according to AlphaFold prediction. The proteins are predominantly present in the Thermoprotei class of archaea and the Pseudomonadati class of bacteria.", "domain_architectures": 2, "interpro_id": "IPR058509", "known_evidence_count": null, "matches": 132, "name": "Domain of unknown function (DUF8196)", "partial_evidence_count": null, "pfam_id": "PF26618", "proteins": 132, "proteomes": 82, "short_name": "DUF8196", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26618", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short C. elegans proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR008498", "known_evidence_count": null, "matches": 131, "name": "Caenorhabditis elegans protein of unknown function (DUF780)", "partial_evidence_count": null, "pfam_id": "PF05611", "proteins": 131, "proteomes": 42, "short_name": "DUF780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05611", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 124, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal proteins of around 350 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009927", "known_evidence_count": null, "matches": 131, "name": "Protein of unknown function (DUF1464)", "partial_evidence_count": null, "pfam_id": "PF07318", "proteins": 131, "proteomes": 126, "short_name": "DUF1464", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07318", "structures": 0, "taxa": 299, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 112, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 200 and 298 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR027891", "known_evidence_count": null, "matches": 131, "name": "Domain of unknown function (DUF4645)", "partial_evidence_count": null, "pfam_id": "PF15488", "proteins": 131, "proteomes": 122, "short_name": "DUF4645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15488", "structures": 0, "taxa": 384, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain family is found in bacteria and archaea. Proteins in this family are typically between 64 and 76 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR043734", "known_evidence_count": null, "matches": 131, "name": "Family of unknown function (DUF5678)", "partial_evidence_count": null, "pfam_id": "PF18929", "proteins": 131, "proteomes": 105, "short_name": "DUF5678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18929", "structures": 0, "taxa": 388, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes bacteria. Proteins in this family are typically between 238 and 400 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046110", "known_evidence_count": null, "matches": 141, "name": "Family of unknown function (DUF6047)", "partial_evidence_count": null, "pfam_id": "PF19513", "proteins": 131, "proteomes": 33, "short_name": "DUF6047", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19513", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 101 and 403 amino acids in length. There some conserved motifs, Y/FL, WL and LP.", "domain_architectures": 6, "interpro_id": "IPR046482", "known_evidence_count": null, "matches": 131, "name": "Family of unknown function (DUF6575)", "partial_evidence_count": null, "pfam_id": "PF20215", "proteins": 131, "proteomes": 126, "short_name": "DUF6575", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20215", "structures": 0, "taxa": 391, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 59 and 74 amino acids in length. There are two conserved sequence motifs: VTGP and DPE. The proteins contain four conserved cysteines. Proteins in this family are found in actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR046658", "known_evidence_count": null, "matches": 131, "name": "Domain of unknown function (DUF6767)", "partial_evidence_count": null, "pfam_id": "PF20555", "proteins": 131, "proteomes": 128, "short_name": "DUF6767", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20555", "structures": 0, "taxa": 211, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 107, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. Proteins in this family are found in bacteria. There is a conserved RxxD sequence motif.", "domain_architectures": 3, "interpro_id": "IPR049210", "known_evidence_count": null, "matches": 143, "name": "Family of unknown function (DUF6812)", "partial_evidence_count": null, "pfam_id": "PF20660", "proteins": 131, "proteomes": 128, "short_name": "DUF6812", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20660", "structures": 0, "taxa": 372, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 125, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are composed of an alpha helical hairpin.", "domain_architectures": 1, "interpro_id": "IPR058325", "known_evidence_count": null, "matches": 131, "name": "Family of unknown function (DUF8012)", "partial_evidence_count": null, "pfam_id": "PF26042", "proteins": 131, "proteomes": 95, "short_name": "DUF8012", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26042", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the central HTH domain found in a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 5, "interpro_id": "IPR058809", "known_evidence_count": null, "matches": 132, "name": "Family of unknown function (DUF8073), central HTH domain", "partial_evidence_count": null, "pfam_id": "PF26271", "proteins": 131, "proteomes": 97, "short_name": "DUF8073_M", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26271", "structures": 0, "taxa": 170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins found predominantly in the class Halobacteria within the Archaea domain. The proteins containing this domain are primarily distributed among various genera such as Halorubrum, Halalkalicoccus, and Natronococcus. The domain is typically found in proteins ranging from 90 to 250 amino acids in length. These domains contain to CXXC motifs suggesting they are zinc binding domains.", "domain_architectures": 1, "interpro_id": "IPR058425", "known_evidence_count": null, "matches": 131, "name": "Domain of unknown function (DUF8112)", "partial_evidence_count": null, "pfam_id": "PF26417", "proteins": 131, "proteomes": 80, "short_name": "DUF8112", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26417", "structures": 0, "taxa": 152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 90, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a globular structure with significant similarity to C-type lectin. Compared to known C-type lectin domains this domain contains a large insertion comprising a six-stranded beta-meander. Some proteins contain two copies of this domain.", "domain_architectures": 15, "interpro_id": "IPR059281", "known_evidence_count": null, "matches": 132, "name": "Domain of unknown function (DUF8237)", "partial_evidence_count": null, "pfam_id": "PF26707", "proteins": 131, "proteomes": 67, "short_name": "DUF8237", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26707", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 140 residues in length. Members of this family seem to be specific to Enterobacteria. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009811", "known_evidence_count": null, "matches": 130, "name": "Protein of unknown function (DUF1380)", "partial_evidence_count": null, "pfam_id": "PF07128", "proteins": 130, "proteomes": 78, "short_name": "DUF1380", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07128", "structures": 0, "taxa": 165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 251 and 262 amino acids in length. There is a conserved YLNG sequence motif.", "domain_architectures": 2, "interpro_id": "IPR025031", "known_evidence_count": null, "matches": 130, "name": "Protein of unknown function (DUF3919)", "partial_evidence_count": null, "pfam_id": "PF13057", "proteins": 130, "proteomes": 117, "short_name": "DUF3919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13057", "structures": 0, "taxa": 193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR025429", "known_evidence_count": null, "matches": 130, "name": "Domain of unknown function (DUF4165)", "partial_evidence_count": null, "pfam_id": "PF13752", "proteins": 130, "proteomes": 56, "short_name": "DUF4165", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13752", "structures": 0, "taxa": 128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 2, "interpro_id": "IPR020303", "known_evidence_count": null, "matches": 130, "name": "Family of unknown function (DUF5495)", "partial_evidence_count": null, "pfam_id": "PF17599", "proteins": 130, "proteomes": 130, "short_name": "DUF5495", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17599", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals.", "domain_architectures": 2, "interpro_id": "IPR040906", "known_evidence_count": null, "matches": 132, "name": "Family of unknown function (DUF5535)", "partial_evidence_count": null, "pfam_id": "PF17687", "proteins": 130, "proteomes": 93, "short_name": "DUF5535", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17687", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals.", "domain_architectures": 3, "interpro_id": "IPR038963", "known_evidence_count": null, "matches": 144, "name": "Family of unknown function (DUF5536)", "partial_evidence_count": null, "pfam_id": "PF17688", "proteins": 130, "proteomes": 101, "short_name": "DUF5536", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17688", "structures": 0, "taxa": 355, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 123, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in Archaea. They have sequence similarity to Zincin-like metalloproteases and are predicted to adopt the same structure. Only one of the two zinc binding sites are conserved suggesting that these proteins may possess different function.", "domain_architectures": 1, "interpro_id": "IPR054270", "known_evidence_count": null, "matches": 130, "name": "Family of unknown function (DUF7001)", "partial_evidence_count": null, "pfam_id": "PF22529", "proteins": 130, "proteomes": 130, "short_name": "DUF7001", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22529", "structures": 0, "taxa": 229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised bacterial membrane proteins that contain four transmembrane alpha helices.", "domain_architectures": 1, "interpro_id": "IPR056087", "known_evidence_count": null, "matches": 130, "name": "Domain of unknown function (DUF7670)", "partial_evidence_count": null, "pfam_id": "PF24709", "proteins": 130, "proteomes": 115, "short_name": "DUF7670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24709", "structures": 0, "taxa": 354, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the class Halobacteria, which includes families such as Halobacteriaceae, Haloferacaceae, and Natrialbaceae. The domain is approximately 70-90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058463", "known_evidence_count": null, "matches": 130, "name": "Family of unknown function (DUF8150)", "partial_evidence_count": null, "pfam_id": "PF26477", "proteins": 130, "proteomes": 118, "short_name": "DUF8150", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26477", "structures": 0, "taxa": 241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised fungal proteins. The N- and C-terminal ends of this domain contain cysteine residues that are predicted to form a disulfide bond. The exact sequence position of these cysteines is not strictly conserved.", "domain_architectures": 37, "interpro_id": "IPR059419", "known_evidence_count": null, "matches": 130, "name": "Domain of unknown function (DUF8375)", "partial_evidence_count": null, "pfam_id": "PF28210", "proteins": 130, "proteomes": 109, "short_name": "DUF8375", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28210", "structures": 0, "taxa": 256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "family of short, secreted proteins specific to the Streptococcus genus, with distant homologs, not recognized by this HMM, found in other cocci. In all sequenced genomes, proteins from this family appear in a conserved genomic context with an thioredoxin, tRNA synthase and tRNA binding protein, but the functional implication of this is unclear", "domain_architectures": 1, "interpro_id": "IPR028105", "known_evidence_count": null, "matches": 129, "name": "Domain of unknown function (DUF4651)", "partial_evidence_count": null, "pfam_id": "PF15513", "proteins": 129, "proteomes": 129, "short_name": "DUF4651", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15513", "structures": 1, "taxa": 182, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 237 and 332 amino acids in length. There are two completely conserved residues (C and R) that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR031883", "known_evidence_count": null, "matches": 130, "name": "Domain of unknown function (DUF4763)", "partial_evidence_count": null, "pfam_id": "PF15960", "proteins": 129, "proteomes": 38, "short_name": "DUF4763", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15960", "structures": 0, "taxa": 157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and phage. Proteins in this family are typically between 124 and 138 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046078", "known_evidence_count": null, "matches": 129, "name": "Family of unknown function (DUF6096)", "partial_evidence_count": null, "pfam_id": "PF19591", "proteins": 129, "proteomes": 129, "short_name": "DUF6096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19591", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of protein domains related to [pfam:PF19808].", "domain_architectures": 5, "interpro_id": "IPR057155", "known_evidence_count": null, "matches": 129, "name": "Family of unknown function (DUF7833)", "partial_evidence_count": null, "pfam_id": "PF25200", "proteins": 129, "proteomes": 96, "short_name": "DUF7833", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25200", "structures": 0, "taxa": 223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Escherichia coli and bacteriophage lambda-like proteins of around 60 residues in length. The function of this family is unknown. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 1, "interpro_id": "IPR009814", "known_evidence_count": null, "matches": 128, "name": "Protein of unknown function (DUF1382)", "partial_evidence_count": null, "pfam_id": "PF07131", "proteins": 128, "proteomes": 112, "short_name": "DUF1382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07131", "structures": 1, "taxa": 281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function. It has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR021337", "known_evidence_count": null, "matches": 128, "name": "Protein of unknown function (DUF2951)", "partial_evidence_count": null, "pfam_id": "PF11166", "proteins": 128, "proteomes": 116, "short_name": "DUF2951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11166", "structures": 0, "taxa": 247, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found at the C-terminal end of proteins mainly from Legionella, including lpg0944 from Legionella pneumophila ([swissprot:Q5ZWY9]), which is thought to be an effector of the Icm/Dot translocation system from this bacteria. This domain folds into an all-alpha structure [[cite:PUB00091363]].", "domain_architectures": 12, "interpro_id": "IPR041234", "known_evidence_count": null, "matches": 128, "name": "Domain of unknown function (DUF5617)", "partial_evidence_count": null, "pfam_id": "PF18493", "proteins": 128, "proteomes": 50, "short_name": "DUF5617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18493", "structures": 2, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 82, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043910", "known_evidence_count": null, "matches": 128, "name": "Family of unknown function (DUF5767)", "partial_evidence_count": null, "pfam_id": "PF19071", "proteins": 128, "proteomes": 106, "short_name": "DUF5767", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19071", "structures": 0, "taxa": 338, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is predominantly found in uncharacterised bacterial proteins and its function is unknown. This domain is approximately 60 amino acids in length and it contains three conserved residues, a cysteine, a leucine and a tryptophan.", "domain_architectures": 9, "interpro_id": "IPR046292", "known_evidence_count": null, "matches": 128, "name": "Family of unknown function (DUF6329)", "partial_evidence_count": null, "pfam_id": "PF19854", "proteins": 128, "proteomes": 107, "short_name": "DUF6329", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19854", "structures": 0, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from fungi. It shares a significant sequence similarity of Ig-like domains found in Trs120 and it is predicted to adopt a structure with a similar topology.", "domain_architectures": 30, "interpro_id": "IPR055504", "known_evidence_count": null, "matches": 128, "name": "Domain of unknown function (DUF7076)", "partial_evidence_count": null, "pfam_id": "PF23273", "proteins": 128, "proteomes": 123, "short_name": "DUF7076", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23273", "structures": 0, "taxa": 328, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised archaeal proteins. They are predicted to have a structure composed of seven nearly orthogonally packed strands, four of which are located at the N-terminus and three at the C-terminus. The N- and C-terminal strands clamp to form a beta-sandwich. They are separated by a ~50 aa long disordered region which contains a repetitive SPY sequence motif.", "domain_architectures": 2, "interpro_id": "IPR055932", "known_evidence_count": null, "matches": 129, "name": "Family of unknown function (DUF7510)", "partial_evidence_count": null, "pfam_id": "PF24350", "proteins": 128, "proteomes": 127, "short_name": "DUF7510", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24350", "structures": 0, "taxa": 190, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 119, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised halobacterial proteins. Structure prediction shows that these proteins form a non-compact fold composed of four alpha helices. There is weak evidence from structure prediction that this protein may form a domain swapped homodimer", "domain_architectures": 1, "interpro_id": "IPR058272", "known_evidence_count": null, "matches": 128, "name": "Family of unknown function (DUF7966)", "partial_evidence_count": null, "pfam_id": "PF25920", "proteins": 128, "proteomes": 128, "short_name": "DUF7966", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25920", "structures": 0, "taxa": 188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several putative head-tail joining bacteriophage proteins.", "domain_architectures": 2, "interpro_id": "IPR009406", "known_evidence_count": null, "matches": 127, "name": "Protein of unknown function (DUF1056)", "partial_evidence_count": null, "pfam_id": "PF06341", "proteins": 127, "proteomes": 125, "short_name": "DUF1056", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06341", "structures": 0, "taxa": 275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein of approx. 100 residues is found in bacteria. It contains up to five alpha helices and up to seven beta strands and is probably monomeric. Its function is unknown. It is cited as a major prophage head protein [[cite:PUB00044231]], so might generally be of viral origin.", "domain_architectures": 1, "interpro_id": "IPR018599", "known_evidence_count": null, "matches": 127, "name": "Protein of unknown function (DUF2026)", "partial_evidence_count": null, "pfam_id": "PF09641", "proteins": 127, "proteomes": 126, "short_name": "DUF2026", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09641", "structures": 1, "taxa": 283, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 69 and 87 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025032", "known_evidence_count": null, "matches": 127, "name": "Protein of unknown function (DUF3949)", "partial_evidence_count": null, "pfam_id": "PF13133", "proteins": 127, "proteomes": 105, "short_name": "DUF3949", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13133", "structures": 0, "taxa": 153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR035141", "known_evidence_count": null, "matches": 127, "name": "Family of unknown function (DUF5484)", "partial_evidence_count": null, "pfam_id": "PF17583", "proteins": 127, "proteomes": 127, "short_name": "DUF5484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17583", "structures": 0, "taxa": 285, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found mainly in bacteria.", "domain_architectures": 11, "interpro_id": "IPR041132", "known_evidence_count": null, "matches": 127, "name": "Domain of unknown function (DUF5624)", "partial_evidence_count": null, "pfam_id": "PF18538", "proteins": 127, "proteomes": 124, "short_name": "DUF5624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18538", "structures": 1, "taxa": 289, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001774) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the spicamycin biosynthetic gene cluster from Streptomyces fimbriatus [[cite:PUB00098963]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 2, "interpro_id": "IPR045754", "known_evidence_count": null, "matches": 129, "name": "Family of unknown function (DUF6182)", "partial_evidence_count": null, "pfam_id": "PF19680", "proteins": 127, "proteomes": 120, "short_name": "DUF6182", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19680", "structures": 0, "taxa": 187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Alphaproteobacteria. Proteins in this family are typically between 76 and 122 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR045496", "known_evidence_count": null, "matches": 127, "name": "Family of unknown function (DUF6437)", "partial_evidence_count": null, "pfam_id": "PF20031", "proteins": 127, "proteomes": 97, "short_name": "DUF6437", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20031", "structures": 0, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal helical domain found in a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 4, "interpro_id": "IPR058810", "known_evidence_count": null, "matches": 127, "name": "Family of unknown function (DUF8073) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26270", "proteins": 127, "proteomes": 95, "short_name": "DUF8073_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26270", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised insect proteins. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds. Many proteins contain multiple copies of this domain.", "domain_architectures": 6, "interpro_id": "IPR059302", "known_evidence_count": null, "matches": 163, "name": "Domain of unknown function (DUF8258)", "partial_evidence_count": null, "pfam_id": "PF26786", "proteins": 127, "proteomes": 31, "short_name": "DUF8258", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26786", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 88, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Mycoplasmataceae.", "domain_architectures": 3, "interpro_id": "IPR021222", "known_evidence_count": null, "matches": 127, "name": "Protein of unknown function (DUF2714)", "partial_evidence_count": null, "pfam_id": "PF10896", "proteins": 126, "proteomes": 105, "short_name": "DUF2714", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10896", "structures": 0, "taxa": 185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as gene protein 30.1. Currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR021405", "known_evidence_count": null, "matches": 126, "name": "Protein of unknown function (DUF3045)", "partial_evidence_count": null, "pfam_id": "PF11243", "proteins": 126, "proteomes": 126, "short_name": "DUF3045", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11243", "structures": 0, "taxa": 272, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins composed largely of a single alpha helix. Some proteins in this family are annotated as from phage. The function of these proteins is unknown.", "domain_architectures": 5, "interpro_id": "IPR054184", "known_evidence_count": null, "matches": 126, "name": "Family of unknown function (DUF6890)", "partial_evidence_count": null, "pfam_id": "PF21830", "proteins": 126, "proteomes": 118, "short_name": "DUF6890", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21830", "structures": 0, "taxa": 264, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a family of uncharacterized proteins in nematodes. In some proteins, this domain appears internally duplicated.", "domain_architectures": 15, "interpro_id": "IPR055466", "known_evidence_count": null, "matches": 134, "name": "Domain of unknown function (DUF7038)", "partial_evidence_count": null, "pfam_id": "PF23047", "proteins": 126, "proteomes": 27, "short_name": "DUF7038", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23047", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterized proteins is found in various phages that infect bacterial hosts such as Bacillus, Staphylococcus, Enterococcus, Listeria, Lactobacillus, and Brochothrix species. The proteins in the family are typically 75 to 100 amino acids in length. The protein contains a small N-terminal domain represented by this entry followed by a C-terminal disordered region.", "domain_architectures": 1, "interpro_id": "IPR055773", "known_evidence_count": null, "matches": 126, "name": "Domain of unknown function (DUF7349)", "partial_evidence_count": null, "pfam_id": "PF24040", "proteins": 126, "proteomes": 126, "short_name": "DUF7349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24040", "structures": 0, "taxa": 280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal proteins. They are predicted to adopt alpha/beta structure consisting of five-stranded antiparallel beta-sheet and five alpha-helices protruding from it.", "domain_architectures": 2, "interpro_id": "IPR055971", "known_evidence_count": null, "matches": 131, "name": "Family of unknown function (DUF7549)", "partial_evidence_count": null, "pfam_id": "PF24417", "proteins": 126, "proteomes": 126, "short_name": "DUF7549", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24417", "structures": 0, "taxa": 193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found mainly in Halobacteria. They contain four pairs of conserved cysteines that are likely involved in metal coordination.", "domain_architectures": 1, "interpro_id": "IPR055993", "known_evidence_count": null, "matches": 126, "name": "Family of unknown function (DUF7571)", "partial_evidence_count": null, "pfam_id": "PF24455", "proteins": 126, "proteomes": 123, "short_name": "DUF7571", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24455", "structures": 0, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 120, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a domain found in the uncharacterised protein B0303.14 from C.elegans and related sequences from nematodes.", "domain_architectures": 6, "interpro_id": "IPR056044", "known_evidence_count": null, "matches": 131, "name": "Repeat of unknown function (DUF7627)", "partial_evidence_count": null, "pfam_id": "PF24628", "proteins": 126, "proteomes": 89, "short_name": "DUF7627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24628", "structures": 0, "taxa": 214, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha- helical bundle. This domain is found in the hypothetical protein ESA_00282 from Cronobacter sakazakii that plays a significant role in biofilm formation and bacterial adhesion. This protein contributes to the adhesion of C. sakazakii to biotic surfaces, such as intestinal epithelial cells and play a role in the pathogenesis [[cite:PUB00159769]].", "domain_architectures": 1, "interpro_id": "IPR057703", "known_evidence_count": null, "matches": 126, "name": "Domain of unknown function (DUF7943)", "partial_evidence_count": null, "pfam_id": "PF25639", "proteins": 126, "proteomes": 126, "short_name": "DUF7943", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25639", "structures": 0, "taxa": 185, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family pf phage proteins that show some weak structural similarity to GNAT family acetyltransferases. This family includes Phage PhiTE gene phiTE_083.", "domain_architectures": 1, "interpro_id": "IPR058346", "known_evidence_count": null, "matches": 126, "name": "Family of unknown function (DUF8033)", "partial_evidence_count": null, "pfam_id": "PF26096", "proteins": 126, "proteomes": 124, "short_name": "DUF8033", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26096", "structures": 0, "taxa": 352, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from bacilli and their phage. The family includes the C. subtilis YjzI and YoyH genes.", "domain_architectures": 1, "interpro_id": "IPR058409", "known_evidence_count": null, "matches": 126, "name": "Domain of unknown function (DUF8096)", "partial_evidence_count": null, "pfam_id": "PF26372", "proteins": 126, "proteomes": 97, "short_name": "DUF8096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26372", "structures": 0, "taxa": 163, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in putative Ig-domain-containing proteins mainly from animals. This domain contains a Spectrin fold with a conserved three-helix bundle structure that is typically arranged in tandem repeats. These repeats confer mechanical flexibility and structural resilience, allowing the proteins to maintain cell shape and organisation. Spectrin-repeat proteins form elongated scaffolds beneath the plasma membrane and contribute to cytoskeletal integrity and membrane stability [[cite:PUB00161917]].", "domain_architectures": 29, "interpro_id": "IPR059370", "known_evidence_count": null, "matches": 126, "name": "Domain of unknown function (DUF8326)", "partial_evidence_count": null, "pfam_id": "PF27005", "proteins": 126, "proteomes": 87, "short_name": "DUF8326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27005", "structures": 0, "taxa": 206, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins from Staphylococcus aureus as well as a number of phage proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009494", "known_evidence_count": null, "matches": 125, "name": "Protein of unknown function (DUF1108)", "partial_evidence_count": null, "pfam_id": "PF06531", "proteins": 125, "proteomes": 105, "short_name": "DUF1108", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06531", "structures": 0, "taxa": 218, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Members of this family, that are synthesised by Saccharomycetes, adopt a structure consisting of a four-stranded beta-sheet, with strand order beta2-beta1-beta4-beta3, and two alpha-helices, with an overall topology of beta-beta-alpha-beta-beta-alpha. They have no known function [[cite:PUB00029007]].", "domain_architectures": 4, "interpro_id": "IPR015080", "known_evidence_count": null, "matches": 125, "name": "Protein of unknown function (DUF1892)", "partial_evidence_count": null, "pfam_id": "PF08987", "proteins": 125, "proteomes": 119, "short_name": "DUF1892", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08987", "structures": 1, "taxa": 242, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is a domain of unknown function which is mostly found at the C-terminal of ACT domains such as [pfam:PF01842].", "domain_architectures": 4, "interpro_id": "IPR040537", "known_evidence_count": null, "matches": 125, "name": "Domain of unknown function (DUF5612)", "partial_evidence_count": null, "pfam_id": "PF18462", "proteins": 125, "proteomes": 122, "short_name": "DUF5612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18462", "structures": 1, "taxa": 254, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry likely contains an N-terminal Helix-tun-helix motif and is therefore likely to be a transcriptional regulator.", "domain_architectures": 1, "interpro_id": "IPR043752", "known_evidence_count": null, "matches": 125, "name": "Family of unknown function (DUF5697)", "partial_evidence_count": null, "pfam_id": "PF18954", "proteins": 125, "proteomes": 104, "short_name": "DUF5697", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18954", "structures": 0, "taxa": 197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of putative phage membrane proteins. It is characterized by a single transmembrane helix at the N-terminus that likely serves to anchor these proteins to the membrane. The exact functions of the proteins containing this domain remain unknown.", "domain_architectures": 1, "interpro_id": "IPR055622", "known_evidence_count": null, "matches": 125, "name": "Family of unknown function (DUF7198)", "partial_evidence_count": null, "pfam_id": "PF23828", "proteins": 125, "proteomes": 122, "short_name": "DUF7198", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23828", "structures": 0, "taxa": 257, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 122, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from nematodes. It is composed of repetitive alpha-helical hairpins and has detectable similarity to 14-3-3 proteins.", "domain_architectures": 5, "interpro_id": "IPR056660", "known_evidence_count": null, "matches": 126, "name": "Domain of unknown function (DUF7758)", "partial_evidence_count": null, "pfam_id": "PF24944", "proteins": 125, "proteomes": 65, "short_name": "DUF7758", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24944", "structures": 0, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 90 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, particularly members of the family Demerecviridae. Within this family, the proteins are found in the genera Tequintavirus and Epseptimavirus. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061611", "known_evidence_count": null, "matches": 125, "name": "Family of unknown function (DUF8541)", "partial_evidence_count": null, "pfam_id": "PF29392", "proteins": 125, "proteomes": 125, "short_name": "DUF8541", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29392", "structures": 0, "taxa": 265, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 82, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR020117", "known_evidence_count": null, "matches": 124, "name": "Protein of unknown function (DUF2554)", "partial_evidence_count": null, "pfam_id": "PF10829", "proteins": 124, "proteomes": 124, "short_name": "DUF2554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10829", "structures": 0, "taxa": 180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins from Clostridia and Bacilli classes has an unusual structure of three beta propeller repeats that do not form a barrel, as in well known 6-, 7- etc beta propeller barrels, but instead are stacked in a three-layer beta-sheet sandwich. The function of all the proteins from this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR028102", "known_evidence_count": null, "matches": 124, "name": "Domain of unknown function (DUF4652)", "partial_evidence_count": null, "pfam_id": "PF15525", "proteins": 124, "proteomes": 115, "short_name": "DUF4652", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15525", "structures": 1, "taxa": 203, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria, archaea, eukaryotes and viruses. Proteins in this family are typically between 79 and 98 amino acids in length. The region contains two predicted transmembrane helices. The Eukaryotic examples are found in the Foraminiferan Reticulomyxa filosa that contains several proteins with this family.s", "domain_architectures": 1, "interpro_id": "IPR043713", "known_evidence_count": null, "matches": 124, "name": "Family of unknown function (DUF5654)", "partial_evidence_count": null, "pfam_id": "PF18898", "proteins": 124, "proteomes": 116, "short_name": "DUF5654", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18898", "structures": 0, "taxa": 302, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein that is found in a variety of phage, predominantly infecting bacteria from the Enterobacteriaceae family such as Escherichia and Salmonella. The protein is typically between 75-120 amino acids in length. These proteins have a highly conserved N-terminus.", "domain_architectures": 1, "interpro_id": "IPR055604", "known_evidence_count": null, "matches": 124, "name": "Family of unknown function (DUF7180)", "partial_evidence_count": null, "pfam_id": "PF23805", "proteins": 124, "proteomes": 122, "short_name": "DUF7180", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23805", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in Halobacteria. They are composed of N-terminal transmembrane helix and alpha/beta globular domain.", "domain_architectures": 2, "interpro_id": "IPR055686", "known_evidence_count": null, "matches": 125, "name": "Family of unknown function (DUF7262)", "partial_evidence_count": null, "pfam_id": "PF23923", "proteins": 124, "proteomes": 123, "short_name": "DUF7262", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23923", "structures": 0, "taxa": 199, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Epsilonproteobacteria. It is predicted to adopt a globular structure with a beta-sandwich topology.", "domain_architectures": 14, "interpro_id": "IPR055917", "known_evidence_count": null, "matches": 124, "name": "Domain of unknown function (DUF7494)", "partial_evidence_count": null, "pfam_id": "PF24323", "proteins": 124, "proteomes": 121, "short_name": "DUF7494", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24323", "structures": 2, "taxa": 183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family found in Methanobacteriota. Structure prediction suggests that this protein binds to a zinc ion. This family includes gene HVO_1405 from Haloferax volcanii.", "domain_architectures": 1, "interpro_id": "IPR058266", "known_evidence_count": null, "matches": 124, "name": "Family of unknown function (DUF7960)", "partial_evidence_count": null, "pfam_id": "PF25901", "proteins": 124, "proteomes": 124, "short_name": "DUF7960", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25901", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins contain a 100 residue long domain that forms a 6 stranded beta sheet with helices packed on each side. This family has matches to halophage proteins.", "domain_architectures": 1, "interpro_id": "IPR058343", "known_evidence_count": null, "matches": 124, "name": "Domain of unknown function (DUF8030)", "partial_evidence_count": null, "pfam_id": "PF26073", "proteins": 124, "proteomes": 89, "short_name": "DUF8030", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26073", "structures": 0, "taxa": 163, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is majoritarily found in Caenorhabditis proteins and has no known function. It has a ubiquitin fold. The GO annotation for the protein indicates that it has a function in nematode larval development.", "domain_architectures": 7, "interpro_id": "IPR004987", "known_evidence_count": null, "matches": 135, "name": "Domain of unknown function (DUF272), N-terminal", "partial_evidence_count": null, "pfam_id": "PF03312", "proteins": 123, "proteomes": 25, "short_name": "DUF272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03312", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical bacterial proteins.", "domain_architectures": 1, "interpro_id": "IPR015061", "known_evidence_count": null, "matches": 123, "name": "Domain of unknown function (DUF1882)", "partial_evidence_count": null, "pfam_id": "PF08966", "proteins": 123, "proteomes": 123, "short_name": "DUF1882", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08966", "structures": 1, "taxa": 188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR035136", "known_evidence_count": null, "matches": 123, "name": "Family of unknown function (DUF5486)", "partial_evidence_count": null, "pfam_id": "PF17588", "proteins": 123, "proteomes": 123, "short_name": "DUF5486", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17588", "structures": 0, "taxa": 276, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins, predominantly found in Caudovirales, is functionally uncharacterised. Proteins in this family are approximately 150 amino acids in length. There are conserved sequences: ETINSMDYNTGY at the N-terminal, WTG in the centre and TDTTS at the C-terminal.", "domain_architectures": 1, "interpro_id": "IPR046285", "known_evidence_count": null, "matches": 123, "name": "Family of unknown function (DUF6322)", "partial_evidence_count": null, "pfam_id": "PF19847", "proteins": 123, "proteomes": 74, "short_name": "DUF6322", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19847", "structures": 0, "taxa": 221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein of approximately 54 amino acids found in T5-like bacteriophages that infect Escherichia coli and Salmonella. Homologs have been identified in several T5-like phages including bacteriophage T5, Salmonella phage vB_SenS_SB13, and Escherichia phage vB_EcoS-26175V. Structure prediction suggests that this protein forms a strand swapped homodimeric arrangement. The dimeric structure forms two four stranded sheets that are connected by two alpha helices. The C-terminal of each protein is donated to the sheet made by the other monomer.", "domain_architectures": 1, "interpro_id": "IPR055717", "known_evidence_count": null, "matches": 123, "name": "Family of unknown function (DUF7293)", "partial_evidence_count": null, "pfam_id": "PF23965", "proteins": 123, "proteomes": 122, "short_name": "DUF7293", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23965", "structures": 0, "taxa": 256, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from alphaproteobacteria. This domain is usually found associated with [pfam:PF13400] and is predicted to form a three -sided beta-helix.", "domain_architectures": 7, "interpro_id": "IPR057189", "known_evidence_count": null, "matches": 137, "name": "Domain of unknown function (DUF7867)", "partial_evidence_count": null, "pfam_id": "PF25269", "proteins": 123, "proteomes": 96, "short_name": "DUF7867", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25269", "structures": 0, "taxa": 168, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 54-55 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, particularly members of the family Demerecviridae. Within this family, the proteins are found in the genera Tequintavirus and Epseptimavirus. The function of these proteins remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061609", "known_evidence_count": null, "matches": 123, "name": "Family of unknown function (DUF8539)", "partial_evidence_count": null, "pfam_id": "PF29390", "proteins": 123, "proteomes": 123, "short_name": "DUF8539", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29390", "structures": 0, "taxa": 258, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 104, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical archaeal proteins.", "domain_architectures": 2, "interpro_id": "IPR012033", "known_evidence_count": null, "matches": 122, "name": "Domain of unknown function (DUF1890)", "partial_evidence_count": null, "pfam_id": "PF09001", "proteins": 122, "proteomes": 111, "short_name": "DUF1890", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09001", "structures": 1, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Saccharomycetales. This family appears to be related to [pfam:PF03097].", "domain_architectures": 3, "interpro_id": "IPR035278", "known_evidence_count": null, "matches": 124, "name": "Family of unknown function (DUF5355)", "partial_evidence_count": null, "pfam_id": "PF17306", "proteins": 122, "proteomes": 114, "short_name": "DUF5355", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17306", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is mainly found in Bifidobacteria. Proteins in this family are approximately 190 amino acids in length. They contain the conserved motifs QQQQ, SxxLT and KPW. Members in this family are probably cell surface proteins, some of them are likely elastin binding proteins.", "domain_architectures": 2, "interpro_id": "IPR046314", "known_evidence_count": null, "matches": 122, "name": "Family of unknown function (DUF6466)", "partial_evidence_count": null, "pfam_id": "PF20070", "proteins": 122, "proteomes": 122, "short_name": "DUF6466", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20070", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in proteins predominantly found in Gammaproteobacteria such as Hypothetical protein FTT_1539c from Francisella tularensis. It is located in the centre of the proteins included in this entry.", "domain_architectures": 2, "interpro_id": "IPR049286", "known_evidence_count": null, "matches": 122, "name": "Domain of unknown function (DUF6844)", "partial_evidence_count": null, "pfam_id": "PF20891", "proteins": 122, "proteomes": 121, "short_name": "DUF6844", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20891", "structures": 1, "taxa": 258, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in various bacteriophages that infect cyanobacteria and other bacterial hosts. The protein ranges in length from approximately 75 to 136 amino acids.", "domain_architectures": 1, "interpro_id": "IPR055631", "known_evidence_count": null, "matches": 122, "name": "Family of unknown function (DUF7207)", "partial_evidence_count": null, "pfam_id": "PF23837", "proteins": 122, "proteomes": 121, "short_name": "DUF7207", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23837", "structures": 0, "taxa": 314, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins most of which likely associated with proteins located in pilBC operon. It is frequently found inserted in [[pfam:PF23960]]. This domain is predicted to fold into a globular structure with a beta-sandwich topology.", "domain_architectures": 2, "interpro_id": "IPR055732", "known_evidence_count": null, "matches": 122, "name": "Domain of unknown function (DUF7308)", "partial_evidence_count": null, "pfam_id": "PF23985", "proteins": 122, "proteomes": 105, "short_name": "DUF7308", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23985", "structures": 0, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised prokaryotic proteins. It is predicted to adopt mainly alpha-helical structure with unique topology. It is found in combination with [pfam:PF00271] and [pfam:PF00176].", "domain_architectures": 6, "interpro_id": "IPR059320", "known_evidence_count": null, "matches": 122, "name": "Domain of unknown function (DUF8276)", "partial_evidence_count": null, "pfam_id": "PF26921", "proteins": 122, "proteomes": 121, "short_name": "DUF8276", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26921", "structures": 0, "taxa": 323, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes several uncharacterised proteins from Borrelia species.", "domain_architectures": 1, "interpro_id": "IPR006739", "known_evidence_count": null, "matches": 121, "name": "Protein of unknown function, DUF603", "partial_evidence_count": null, "pfam_id": "PF04645", "proteins": 121, "proteomes": 27, "short_name": "DUF603", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04645", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 110, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR009183", "known_evidence_count": null, "matches": 121, "name": "Uncharacterized protein conserved in archaea (DUF2124)", "partial_evidence_count": null, "pfam_id": "PF09897", "proteins": 121, "proteomes": 116, "short_name": "DUF2124", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09897", "structures": 1, "taxa": 225, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021687", "known_evidence_count": null, "matches": 121, "name": "Protein of unknown function (DUF3269)", "partial_evidence_count": null, "pfam_id": "PF11673", "proteins": 121, "proteomes": 111, "short_name": "DUF3269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11673", "structures": 0, "taxa": 221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes and viruses. Proteins in this family are typically between 53 and 3115 amino acids in length. There are two completely conserved residues (A and F) that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR022108", "known_evidence_count": null, "matches": 121, "name": "Protein of unknown function (DUF3648)", "partial_evidence_count": null, "pfam_id": "PF12364", "proteins": 121, "proteomes": 29, "short_name": "DUF3648", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12364", "structures": 0, "taxa": 98, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 218 and 231 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046579", "known_evidence_count": null, "matches": 121, "name": "Family of unknown function (DUF6639)", "partial_evidence_count": null, "pfam_id": "PF20344", "proteins": 121, "proteomes": 104, "short_name": "DUF6639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20344", "structures": 0, "taxa": 222, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several mycobacteriophage putative membrane proteins of around 99 amino acids in length. These proteins are characterized by an N-terminal transmembrane helix, a small central putative zinc binding domain containing 2 conserved cysteine and 2 histidine residues and disordered C-terminal region rich in basic and acidic residues.", "domain_architectures": 1, "interpro_id": "IPR055623", "known_evidence_count": null, "matches": 121, "name": "Family of unknown function (DUF7199)", "partial_evidence_count": null, "pfam_id": "PF23829", "proteins": 121, "proteomes": 121, "short_name": "DUF7199", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23829", "structures": 0, "taxa": 275, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from uncharacterised proteins found mainly in Campylobacterota. Members of this entry contain two highly conserved cysteine residues.", "domain_architectures": 5, "interpro_id": "IPR055911", "known_evidence_count": null, "matches": 121, "name": "Domain of unknown function (DUF7488)", "partial_evidence_count": null, "pfam_id": "PF24314", "proteins": 121, "proteomes": 119, "short_name": "DUF7488", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24314", "structures": 1, "taxa": 177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins from Escherichia coli and Salmonella typhi. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR010382", "known_evidence_count": null, "matches": 120, "name": "Bacterial protein of unknown function (DUF977)", "partial_evidence_count": null, "pfam_id": "PF06163", "proteins": 120, "proteomes": 105, "short_name": "DUF977", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06163", "structures": 0, "taxa": 295, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 115, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several archaeal proteins of around 370 residues in length. The function of this family is unknown. This entry corresponds to the N-terminal domain.", "domain_architectures": 2, "interpro_id": "IPR056460", "known_evidence_count": null, "matches": 120, "name": "Protein of unknown function (DUF1512) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF07431", "proteins": 120, "proteomes": 118, "short_name": "DUF1512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07431", "structures": 0, "taxa": 288, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 531 and 1277 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR031473", "known_evidence_count": null, "matches": 184, "name": "Domain of unknown function (DUF4684)", "partial_evidence_count": null, "pfam_id": "PF15736", "proteins": 120, "proteomes": 84, "short_name": "DUF4684", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15736", "structures": 0, "taxa": 301, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 190 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046142", "known_evidence_count": null, "matches": 120, "name": "Family of unknown function (DUF6144)", "partial_evidence_count": null, "pfam_id": "PF19641", "proteins": 120, "proteomes": 107, "short_name": "DUF6144", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19641", "structures": 0, "taxa": 309, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 140 and 200 amino acids in length. There is a quite conserved EMTFxxG motif.", "domain_architectures": 2, "interpro_id": "IPR046687", "known_evidence_count": null, "matches": 120, "name": "Family of unknown function (DUF6557)", "partial_evidence_count": null, "pfam_id": "PF20194", "proteins": 120, "proteomes": 106, "short_name": "DUF6557", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20194", "structures": 0, "taxa": 281, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 109, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in Halobacteria.", "domain_architectures": 1, "interpro_id": "IPR055687", "known_evidence_count": null, "matches": 120, "name": "Family of unknown function (DUF7263)", "partial_evidence_count": null, "pfam_id": "PF23924", "proteins": 120, "proteomes": 119, "short_name": "DUF7263", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23924", "structures": 0, "taxa": 187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 118, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-beta structure.", "domain_architectures": 1, "interpro_id": "IPR055950", "known_evidence_count": null, "matches": 120, "name": "Family of unknown function (DUF7528)", "partial_evidence_count": null, "pfam_id": "PF24372", "proteins": 120, "proteomes": 90, "short_name": "DUF7528", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24372", "structures": 0, "taxa": 153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in multiple copies in a number of bacterial proteins mainly from Actinomycetales. It is closely related to domains represented by [pfam:PF01345] and [pfam:PF24346]. Similarly to them, this domain contains a conserved N-terminal lysine and a C-terminal asparagine with central aspartate/glutamate residues suggesting that some members may contain an isopeptide bond. This domain is sometimes found in combination with [pfam:PF01345] or [pfam:PF24346].", "domain_architectures": 15, "interpro_id": "IPR055388", "known_evidence_count": null, "matches": 190, "name": "Domain of unknown function (DUF7617)", "partial_evidence_count": null, "pfam_id": "PF24593", "proteins": 120, "proteomes": 95, "short_name": "DUF7617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24593", "structures": 0, "taxa": 148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 116, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins form a six stranded beta barrel.", "domain_architectures": 1, "interpro_id": "IPR058385", "known_evidence_count": null, "matches": 120, "name": "Domain of unknown function (DUF8072)", "partial_evidence_count": null, "pfam_id": "PF26269", "proteins": 120, "proteomes": 118, "short_name": "DUF8072", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26269", "structures": 0, "taxa": 199, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR020295", "known_evidence_count": null, "matches": 119, "name": "Protein of unknown function (DUF2737)", "partial_evidence_count": null, "pfam_id": "PF10930", "proteins": 119, "proteomes": 115, "short_name": "DUF2737", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10930", "structures": 0, "taxa": 276, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Large family of predicted secreted proteins mostly from CFG group, but also from Burkholderia, Pseudomonas and Streptomyces. Function of these proteins is not known. A 3D structure of a representative of this family from Bacteroides uniformis was solved by JCSG and deposited to PDB as 4ghb. There is some overlap with RHS-repeat (PF05593) family despite lack of obvious repeats in the structure.", "domain_architectures": 3, "interpro_id": "IPR027931", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF4595) with porin-like fold", "partial_evidence_count": null, "pfam_id": "PF15283", "proteins": 119, "proteomes": 93, "short_name": "DUF4595", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15283", "structures": 1, "taxa": 176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 90, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 59 and 190 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR027952", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF4632)", "partial_evidence_count": null, "pfam_id": "PF15451", "proteins": 119, "proteomes": 110, "short_name": "DUF4632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15451", "structures": 0, "taxa": 368, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 260 residues in length and found in various Caulobacter and Brevundimonas species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032591", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF4908)", "partial_evidence_count": null, "pfam_id": "PF16252", "proteins": 119, "proteomes": 116, "short_name": "DUF4908", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16252", "structures": 0, "taxa": 184, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry consists of several uncharacterized proteins mainly found in Bacteroides. This entry represents the N-terminal domain which adopts a fold similar to that in arrestins.", "domain_architectures": 3, "interpro_id": "IPR032522", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF4961)", "partial_evidence_count": null, "pfam_id": "PF16328", "proteins": 119, "proteomes": 113, "short_name": "DUF4961", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16328", "structures": 0, "taxa": 173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicute bacteria. Proteins in this family are approximately 220 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046082", "known_evidence_count": null, "matches": 119, "name": "Family of unknown function (DUF6100)", "partial_evidence_count": null, "pfam_id": "PF19595", "proteins": 119, "proteomes": 94, "short_name": "DUF6100", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19595", "structures": 0, "taxa": 177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 80 amino acids in length. It has a conserved sequence GGLxxxGRxxY and a conserved tryptophan residue at the C-terminal.", "domain_architectures": 3, "interpro_id": "IPR046284", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF6321)", "partial_evidence_count": null, "pfam_id": "PF19846", "proteins": 119, "proteomes": 119, "short_name": "DUF6321", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19846", "structures": 0, "taxa": 325, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 114, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several archaeal proteins of around 370 residues in length. This entry corresponds to the C-terminal domain. The function of this family is unknown. This domain shows structural similarity to peptidyl tRNA hydrolase enzymes.", "domain_architectures": 1, "interpro_id": "IPR056461", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF1512) C-terminal", "partial_evidence_count": null, "pfam_id": "PF23542", "proteins": 119, "proteomes": 118, "short_name": "DUF1512_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23542", "structures": 0, "taxa": 288, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of phage integral membrane proteins. The proteins are found in phage of S. aureus and B. subtilis. These proteins contain three potential transmembrane helices. There is a conserved GXXPL motif that is highly conserved between helices 1 and 2.", "domain_architectures": 1, "interpro_id": "IPR055843", "known_evidence_count": null, "matches": 119, "name": "Family of unknown function (DUF7420)", "partial_evidence_count": null, "pfam_id": "PF24195", "proteins": 119, "proteomes": 118, "short_name": "DUF7420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24195", "structures": 0, "taxa": 247, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to fold into a small open beta-barrel with an alpha-hairpin packed on one side.", "domain_architectures": 1, "interpro_id": "IPR059280", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF8236)", "partial_evidence_count": null, "pfam_id": "PF26703", "proteins": 119, "proteomes": 105, "short_name": "DUF8236", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26703", "structures": 0, "taxa": 220, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised metazoan proteins. It is predicted to fold into a beta-sandwich. It contains conserved cysteine residues which are predicted to form disulfide bonds.", "domain_architectures": 4, "interpro_id": "IPR059401", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF8357)", "partial_evidence_count": null, "pfam_id": "PF27623", "proteins": 119, "proteomes": 62, "short_name": "DUF8357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27623", "structures": 0, "taxa": 230, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein domain found in Myxococcota, particularly Myxococcales. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061644", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF8583)", "partial_evidence_count": null, "pfam_id": "PF29742", "proteins": 119, "proteomes": 72, "short_name": "DUF8583", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29742", "structures": 0, "taxa": 255, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised plant proteins that are predicted to mainly adopt a disordered fold. They are rich in G residues.", "domain_architectures": 1, "interpro_id": "IPR061909", "known_evidence_count": null, "matches": 119, "name": "Family of unknown function (DUF8848)", "partial_evidence_count": null, "pfam_id": "PF31268", "proteins": 119, "proteomes": 66, "short_name": "DUF8848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31268", "structures": 0, "taxa": 221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Several members of this family are Borrelia burgdorferi plasmid proteins of uncharacterized function.", "domain_architectures": 2, "interpro_id": "IPR004335", "known_evidence_count": null, "matches": 118, "name": "Uncharacterized protein family (ORF7) DUF", "partial_evidence_count": null, "pfam_id": "PF03112", "proteins": 118, "proteomes": 28, "short_name": "DUF244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03112", "structures": 0, "taxa": 67, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 225 residues in length. Members of this family appear to be specific Borrelia burgdorferi (Lyme disease spirochete). The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR009791", "known_evidence_count": null, "matches": 118, "name": "Protein of unknown function (DUF1357)", "partial_evidence_count": null, "pfam_id": "PF07094", "proteins": 118, "proteomes": 31, "short_name": "DUF1357", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07094", "structures": 9, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Proteobacteria. One member is annotated as being elongation factor P but this could not be confirmed. This domain is related to the Ribbon-helix-helix superfamily so may be a DNA-binding protein.", "domain_architectures": 17, "interpro_id": "IPR021277", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF2610)", "partial_evidence_count": null, "pfam_id": "PF11020", "proteins": 118, "proteomes": 117, "short_name": "DUF2610", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11020", "structures": 0, "taxa": 334, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this entry are functionally uncharacterised. They are found in various Bacteroides and Alistipes species. This entry represents a Ig-like domain found at the N-terminal of these sequences.", "domain_architectures": 7, "interpro_id": "IPR032186", "known_evidence_count": null, "matches": 118, "name": "Domain of unknown function (DUF5018)", "partial_evidence_count": null, "pfam_id": "PF16410", "proteins": 118, "proteomes": 97, "short_name": "DUF5018", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16410", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR035133", "known_evidence_count": null, "matches": 118, "name": "Family of unknown function (DUF5499)", "partial_evidence_count": null, "pfam_id": "PF17603", "proteins": 118, "proteomes": 118, "short_name": "DUF5499", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17603", "structures": 0, "taxa": 258, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001381) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the brasilinolide A biosynthetic gene cluster from Nocardia terpenica [[cite:PUB00098914]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 2, "interpro_id": "IPR045674", "known_evidence_count": null, "matches": 118, "name": "Family of unknown function (DUF6196)", "partial_evidence_count": null, "pfam_id": "PF19696", "proteins": 118, "proteomes": 117, "short_name": "DUF6196", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19696", "structures": 0, "taxa": 276, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 240 and 250 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046620", "known_evidence_count": null, "matches": 121, "name": "Family of unknown function (DUF6733)", "partial_evidence_count": null, "pfam_id": "PF20507", "proteins": 118, "proteomes": 115, "short_name": "DUF6733", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20507", "structures": 0, "taxa": 235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of uncharacterised short sequences from actinobacteria, including the predicted secreted protein [swissprot:K5BB12] from Mycolicibacterium hassiacum [[cite:PUB00155614]].", "domain_architectures": 1, "interpro_id": "IPR055579", "known_evidence_count": null, "matches": 118, "name": "Family of unknown function (DUF7155)", "partial_evidence_count": null, "pfam_id": "PF23710", "proteins": 118, "proteomes": 113, "short_name": "DUF7155", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23710", "structures": 0, "taxa": 125, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a family of uncharacterized proteins, around 70 amino acids in length, found in mycobacteriophages. The family members share sequence similarity but their function is currently unknown. The domain is found as a single copy in the phage proteins. The domain adopts a compact globular fold with a four stranded beta sheet followed by an alpha helix.", "domain_architectures": 3, "interpro_id": "IPR055728", "known_evidence_count": null, "matches": 118, "name": "Domain of unknown function (DUF7304)", "partial_evidence_count": null, "pfam_id": "PF23979", "proteins": 118, "proteomes": 118, "short_name": "DUF7304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23979", "structures": 0, "taxa": 286, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an all-beta domain found in a group of uncharacterised sequences from bacteria. It is found at the N-terminal of [pfam:PF10460] which is a peptidase M30 domain.", "domain_architectures": 8, "interpro_id": "IPR061636", "known_evidence_count": null, "matches": 118, "name": "Domain of unknown function (DUF8571)", "partial_evidence_count": null, "pfam_id": "PF29596", "proteins": 118, "proteomes": 85, "short_name": "DUF8571", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29596", "structures": 0, "taxa": 136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Staphylococcus aureus and Staphylococcus aureus phage phi proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009368", "known_evidence_count": null, "matches": 117, "name": "Protein of unknown function (DUF1024)", "partial_evidence_count": null, "pfam_id": "PF06260", "proteins": 117, "proteomes": 108, "short_name": "DUF1024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06260", "structures": 0, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain largely confined to sequences from Methanomicrobiales found on putative lipases. The function is not known.", "domain_architectures": 9, "interpro_id": "IPR024277", "known_evidence_count": null, "matches": 117, "name": "Domain of unknown function (DUF3821)", "partial_evidence_count": null, "pfam_id": "PF12863", "proteins": 117, "proteomes": 36, "short_name": "DUF3821", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12863", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in the putative secreted protein BF4250 from Bacteroides fragilis ([swissprot:Q5L7M9]) and similar bacterial functionally uncharacterised proteins. This domain seems to be related to [pfam:PF16410].", "domain_architectures": 3, "interpro_id": "IPR054460", "known_evidence_count": null, "matches": 117, "name": "DUF5018-related", "partial_evidence_count": null, "pfam_id": "PF22243", "proteins": 117, "proteomes": 94, "short_name": "DUF5018-rel", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22243", "structures": 2, "taxa": 185, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Arthropods. This is a relatively small domain that is predicted to contain mainly alpha-helices.", "domain_architectures": 7, "interpro_id": "IPR055511", "known_evidence_count": null, "matches": 117, "name": "Domain of unknown function (DUF7084)", "partial_evidence_count": null, "pfam_id": "PF23311", "proteins": 117, "proteomes": 65, "short_name": "DUF7084", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23311", "structures": 0, "taxa": 238, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised sequences from Plasmodium falciparum and related sequences from Apicomplexa. The function is unknown.", "domain_architectures": 5, "interpro_id": "IPR056022", "known_evidence_count": null, "matches": 117, "name": "Domain of unknown function (DUF7602)", "partial_evidence_count": null, "pfam_id": "PF24549", "proteins": 117, "proteomes": 59, "short_name": "DUF7602", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24549", "structures": 0, "taxa": 128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 98, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an Ig-like domain found towards the C-terminal of a group of uncharacterised sequences from Strongyloides spp. and similar sequences from nematodes.", "domain_architectures": 60, "interpro_id": "IPR056069", "known_evidence_count": null, "matches": 117, "name": "Domain of unknown function (DUF7652)", "partial_evidence_count": null, "pfam_id": "PF24665", "proteins": 117, "proteomes": 93, "short_name": "DUF7652", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24665", "structures": 0, "taxa": 216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is found sometimes in combination with (DUF6128) [pfam:PF19623]. This domains is predicted to adopt a beta-sandwich with an Ig-like topology.", "domain_architectures": 4, "interpro_id": "IPR057682", "known_evidence_count": null, "matches": 117, "name": "Domain of unknown function (DUF7922)", "partial_evidence_count": null, "pfam_id": "PF25538", "proteins": 117, "proteomes": 116, "short_name": "DUF7922", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25538", "structures": 0, "taxa": 208, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in Pseudomonadati bacteria. This domain is found as a single domain protein or more rarely as the C-terminal domain of reverse transcriptase enzymes.", "domain_architectures": 2, "interpro_id": "IPR061538", "known_evidence_count": null, "matches": 117, "name": "Domain of unknown function (DUF8468)", "partial_evidence_count": null, "pfam_id": "PF28814", "proteins": 117, "proteomes": 88, "short_name": "DUF8468", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28814", "structures": 0, "taxa": 214, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical bacterial proteins have no known function.", "domain_architectures": 5, "interpro_id": "IPR016891", "known_evidence_count": null, "matches": 117, "name": "Uncharacterized protein conserved in bacteria (DUF2321)", "partial_evidence_count": null, "pfam_id": "PF10083", "proteins": 116, "proteomes": 115, "short_name": "DUF2321", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10083", "structures": 0, "taxa": 391, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family is found in various Bacteroides species. Proteins in this family are around 660 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR032184", "known_evidence_count": null, "matches": 116, "name": "Domain of unknown function (DUF5016)", "partial_evidence_count": null, "pfam_id": "PF16408", "proteins": 116, "proteomes": 108, "short_name": "DUF5016", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16408", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000663) is described by MIBiG as an example of the following biosynthetic class, terpene, in particular the hopene biosynthetic gene cluster from Streptomyces coelicolor A3(2) [[cite:PUB00098992]].", "domain_architectures": 1, "interpro_id": "IPR045960", "known_evidence_count": null, "matches": 116, "name": "Family of unknown function (DUF6380)", "partial_evidence_count": null, "pfam_id": "PF19907", "proteins": 116, "proteomes": 116, "short_name": "DUF6380", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19907", "structures": 0, "taxa": 134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 65 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046568", "known_evidence_count": null, "matches": 116, "name": "Family of unknown function (DUF6722)", "partial_evidence_count": null, "pfam_id": "PF20482", "proteins": 116, "proteomes": 63, "short_name": "DUF6722", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20482", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This presumed domain family is functionally uncharacterised. This domain is found in bacterial and eukaryotic proteins. It is around 100 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046636", "known_evidence_count": null, "matches": 117, "name": "Domain of unknown function (DUF6748)", "partial_evidence_count": null, "pfam_id": "PF20533", "proteins": 116, "proteomes": 77, "short_name": "DUF6748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20533", "structures": 0, "taxa": 213, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins. Proteins in this family are primarily found in Proteobacteria. The structure of these proteins contains a six stranded beta sheet.", "domain_architectures": 2, "interpro_id": "IPR054205", "known_evidence_count": null, "matches": 116, "name": "Family of unknown function (DUF6911)", "partial_evidence_count": null, "pfam_id": "PF21852", "proteins": 116, "proteomes": 102, "short_name": "DUF6911", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21852", "structures": 1, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in a group of bacterial sequences, functionally uncharacterised. It may adopt a beta-propeller structure.", "domain_architectures": 8, "interpro_id": "IPR061570", "known_evidence_count": null, "matches": 116, "name": "Domain of unknown function (DUF8500)", "partial_evidence_count": null, "pfam_id": "PF29068", "proteins": 116, "proteomes": 99, "short_name": "DUF8500", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29068", "structures": 0, "taxa": 186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018694", "known_evidence_count": null, "matches": 115, "name": "Uncharacterized protein conserved in archaea (DUF2193)", "partial_evidence_count": null, "pfam_id": "PF09959", "proteins": 115, "proteomes": 107, "short_name": "DUF2193", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09959", "structures": 0, "taxa": 234, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in eukaryotes, and is typically between 138 and 167 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR031764", "known_evidence_count": null, "matches": 119, "name": "Domain of unknown function (DUF4739)", "partial_evidence_count": null, "pfam_id": "PF15893", "proteins": 115, "proteomes": 60, "short_name": "DUF4739", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15893", "structures": 0, "taxa": 228, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein of unknown function found in phage proteins. The domain contains approximately 77 residues and may contain a single transmembrane helix near the N-terminus.", "domain_architectures": 1, "interpro_id": "IPR055661", "known_evidence_count": null, "matches": 115, "name": "Family of unknown function (DUF7237)", "partial_evidence_count": null, "pfam_id": "PF23884", "proteins": 115, "proteomes": 115, "short_name": "DUF7237", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23884", "structures": 0, "taxa": 241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR055756", "known_evidence_count": null, "matches": 115, "name": "Family of unknown function (DUF7332)", "partial_evidence_count": null, "pfam_id": "PF24019", "proteins": 115, "proteomes": 112, "short_name": "DUF7332", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24019", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is specific to Borrelia burgdorferi. The protein is encoded on extra-chromosomal DNA. This domain has no known function.", "domain_architectures": 1, "interpro_id": "IPR005096", "known_evidence_count": null, "matches": 114, "name": "DUF276", "partial_evidence_count": null, "pfam_id": "PF03434", "proteins": 114, "proteomes": 33, "short_name": "DUF276", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03434", "structures": 0, "taxa": 63, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from Borrelia burgdorferi (Lyme disease spirochete). There is some evidence to suggest that the proteins may be outer surface proteins.", "domain_architectures": 2, "interpro_id": "IPR007777", "known_evidence_count": null, "matches": 127, "name": "Protein of unknown function (DUF685)", "partial_evidence_count": null, "pfam_id": "PF05085", "proteins": 114, "proteomes": 31, "short_name": "DUF685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05085", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 330 residues in length and is mainly found in various Bacteria species, such as Enterobacteriales, Clostridiales, Actinomycetales and so on. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032564", "known_evidence_count": null, "matches": 114, "name": "Domain of unknown function (DUF4928)", "partial_evidence_count": null, "pfam_id": "PF16280", "proteins": 114, "proteomes": 108, "short_name": "DUF4928", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16280", "structures": 0, "taxa": 362, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR043731", "known_evidence_count": null, "matches": 114, "name": "Protein of unknown function (DUF5674)", "partial_evidence_count": null, "pfam_id": "PF18924", "proteins": 114, "proteomes": 74, "short_name": "DUF5674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18924", "structures": 0, "taxa": 262, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046138", "known_evidence_count": null, "matches": 114, "name": "Family of unknown function (DUF6140)", "partial_evidence_count": null, "pfam_id": "PF19637", "proteins": 114, "proteomes": 101, "short_name": "DUF6140", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19637", "structures": 0, "taxa": 198, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small zinc-binding domain found to the N-terminus of proteins that belong to the ParE toxin superfamily. The exact function of this domain is unknown. The zinc ligands are composed of the cys and his in the N-terminal CGH motif and the cys residues in the C-terminal CHXC motif.", "domain_architectures": 3, "interpro_id": "IPR056099", "known_evidence_count": null, "matches": 114, "name": "Zinc-binding Domain of unknown function (DUF7682)", "partial_evidence_count": null, "pfam_id": "PF24730", "proteins": 114, "proteomes": 112, "short_name": "DUF7682", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24730", "structures": 0, "taxa": 318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains two pairs of conserved cysteine residues and it is predicted to adopt a fold typical for treble clef zinc fingers. It has a detectable similarity to the N-terminal zinc finger domain of the bacterial AAA+ disaggregase ClpG, which confers extreme heat resistance to bacteria. The latter is is crucial for structural integrity and disaggregase functionality of ClpG.", "domain_architectures": 6, "interpro_id": "IPR056102", "known_evidence_count": null, "matches": 114, "name": "Domain of unknown function (DUF7685)", "partial_evidence_count": null, "pfam_id": "PF24734", "proteins": 114, "proteomes": 103, "short_name": "DUF7685", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24734", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins from halobacteria. Members are around 100 residues and are predicted to adopt a mainly beta configuration.", "domain_architectures": 2, "interpro_id": "IPR057183", "known_evidence_count": null, "matches": 115, "name": "Family of unknown function (DUF7861)", "partial_evidence_count": null, "pfam_id": "PF25260", "proteins": 114, "proteomes": 111, "short_name": "DUF7861", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25260", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal alpha-helical domain from a family of putative primase protein in halophilic archaea. The proteins in this family are predominantly found in the class Halobacteria, which includes several families such as Haloferacaceae, Halobacteriaceae, and Natrialbaceae. The proteins containing this domain are typically around 500 amino acids in length, as observed in several sequences from the SEED alignment. This domain is associated with proteins that are often encoded on plasmids in various halophilic archaea.", "domain_architectures": 5, "interpro_id": "IPR058424", "known_evidence_count": null, "matches": 115, "name": "Putative primase C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26416", "proteins": 114, "proteomes": 88, "short_name": "DUF8111", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26416", "structures": 0, "taxa": 170, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 113, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several archaeal proteins of around 180 residues in length. Members of this family seem to be found exclusively in Sulfolobus tokodaii and Sulfolobus solfataricus. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009844", "known_evidence_count": null, "matches": 113, "name": "Protein of unknown function (DUF1404)", "partial_evidence_count": null, "pfam_id": "PF07185", "proteins": 113, "proteomes": 33, "short_name": "DUF1404", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07185", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 64 and 331 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR025119", "known_evidence_count": null, "matches": 179, "name": "Protein of unknown function (DUF4046)", "partial_evidence_count": null, "pfam_id": "PF13255", "proteins": 113, "proteomes": 95, "short_name": "DUF4046", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13255", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 101 and 127 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR031465", "known_evidence_count": null, "matches": 116, "name": "Domain of unknown function (DUF4681)", "partial_evidence_count": null, "pfam_id": "PF15732", "proteins": 113, "proteomes": 82, "short_name": "DUF4681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15732", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 600 residues in length and is mainly found in various Thermotoga and Fervidobaterium species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032601", "known_evidence_count": null, "matches": 113, "name": "Domain of unknown function (DUF4900)", "partial_evidence_count": null, "pfam_id": "PF16241", "proteins": 113, "proteomes": 91, "short_name": "DUF4900", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16241", "structures": 0, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR020156", "known_evidence_count": null, "matches": 113, "name": "Family of unknown function (DUF5490)", "partial_evidence_count": null, "pfam_id": "PF17593", "proteins": 113, "proteomes": 113, "short_name": "DUF5490", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17593", "structures": 0, "taxa": 243, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000274) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the tetarimycin A biosynthetic gene cluster from uncultured bacterium [[cite:PUB00099401]].", "domain_architectures": 2, "interpro_id": "IPR046296", "known_evidence_count": null, "matches": 114, "name": "Family of unknown function (DUF6333)", "partial_evidence_count": null, "pfam_id": "PF19859", "proteins": 113, "proteomes": 82, "short_name": "DUF6333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19859", "structures": 0, "taxa": 110, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a small family of proteins that are likely to adopt a papain-like fold. Most members of this family have conserved residues in equivalent positions as the residues that constitute the active site of cysteine proteases.", "domain_architectures": 3, "interpro_id": "IPR049252", "known_evidence_count": null, "matches": 119, "name": "Family of unknown function (DUF6885)", "partial_evidence_count": null, "pfam_id": "PF21819", "proteins": 113, "proteomes": 113, "short_name": "DUF6885", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21819", "structures": 0, "taxa": 206, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. These proteins share partial sequence similarity to the collagenase catalytic core with invariant HExxH motif.", "domain_architectures": 3, "interpro_id": "IPR054274", "known_evidence_count": null, "matches": 119, "name": "Family of unknown function (DUF7005)", "partial_evidence_count": null, "pfam_id": "PF22541", "proteins": 113, "proteomes": 106, "short_name": "DUF7005", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22541", "structures": 0, "taxa": 305, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in Halobacteria. They are predicted to contain three transmembrane helices and likely associate with the membrane.", "domain_architectures": 1, "interpro_id": "IPR055692", "known_evidence_count": null, "matches": 113, "name": "Family of unknown function (DUF7268)", "partial_evidence_count": null, "pfam_id": "PF23930", "proteins": 113, "proteomes": 113, "short_name": "DUF7268", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23930", "structures": 0, "taxa": 196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins found mainly in Halobacteria. They are predicted to adopt a globular alpha/beta structure consisting of five-stranded beta-sheet and an alpha-helix packed on it.", "domain_architectures": 1, "interpro_id": "IPR055965", "known_evidence_count": null, "matches": 113, "name": "Family of unknown function (DUF7543)", "partial_evidence_count": null, "pfam_id": "PF24399", "proteins": 113, "proteomes": 113, "short_name": "DUF7543", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24399", "structures": 0, "taxa": 171, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It share similarity with known CHORD domains and it is predicted to adopt similar structure. In some proteins it is found in combination with AAA+ domains [pfam:PF00004]. It contains several cysteine and histidine residues which are highly conserved and likely involved in metal coordination.", "domain_architectures": 3, "interpro_id": "IPR059298", "known_evidence_count": null, "matches": 113, "name": "Domain of unknown function (DUF8254)", "partial_evidence_count": null, "pfam_id": "PF26782", "proteins": 113, "proteomes": 43, "short_name": "DUF8254", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26782", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt ubiquitin-like fold.", "domain_architectures": 19, "interpro_id": "IPR061794", "known_evidence_count": null, "matches": 118, "name": "Domain of unknown function (DUF8733)", "partial_evidence_count": null, "pfam_id": "PF30780", "proteins": 113, "proteomes": 23, "short_name": "DUF8733", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30780", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR022543", "known_evidence_count": null, "matches": 113, "name": "Protein of unknown function (DUF2572)", "partial_evidence_count": null, "pfam_id": "PF10833", "proteins": 112, "proteomes": 110, "short_name": "DUF2572", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10833", "structures": 0, "taxa": 187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes. Proteins in this family are typically between 148 and 173 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046090", "known_evidence_count": null, "matches": 112, "name": "Family of unknown function (DUF6108)", "partial_evidence_count": null, "pfam_id": "PF19603", "proteins": 112, "proteomes": 110, "short_name": "DUF6108", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19603", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Firmicutes. Proteins in this family are typically between 130 and 155 amino acids in length. Some members are predicted histone acetyltransferases.", "domain_architectures": 1, "interpro_id": "IPR046686", "known_evidence_count": null, "matches": 112, "name": "Family of unknown function (DUF6556)", "partial_evidence_count": null, "pfam_id": "PF20193", "proteins": 112, "proteomes": 112, "short_name": "DUF6556", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20193", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. Structure prediction suggests that this protein forms a small domain that likely forms a stable dimeric complex. In this predicted complex there is a C-terminal alpha helix that binds to the opposite oligomer in a helix swapped arrangement.", "domain_architectures": 1, "interpro_id": "IPR055793", "known_evidence_count": null, "matches": 112, "name": "Domain of unknown function (DUF7369)", "partial_evidence_count": null, "pfam_id": "PF24084", "proteins": 112, "proteomes": 112, "short_name": "DUF7369", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24084", "structures": 0, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta structure.", "domain_architectures": 1, "interpro_id": "IPR059353", "known_evidence_count": null, "matches": 112, "name": "Domain of unknown function (DUF8309)", "partial_evidence_count": null, "pfam_id": "PF26977", "proteins": 112, "proteomes": 100, "short_name": "DUF8309", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26977", "structures": 0, "taxa": 251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR014514", "known_evidence_count": null, "matches": 111, "name": "Uncharacterized protein conserved in archaea (DUF2209)", "partial_evidence_count": null, "pfam_id": "PF09974", "proteins": 111, "proteomes": 110, "short_name": "DUF2209", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09974", "structures": 0, "taxa": 198, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 105, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 48 and 61 amino acids in length. There is a conserved LRF sequence motif.", "domain_architectures": 9, "interpro_id": "IPR022256", "known_evidence_count": null, "matches": 111, "name": "Protein of unknown function (DUF3778)", "partial_evidence_count": null, "pfam_id": "PF12620", "proteins": 111, "proteomes": 9, "short_name": "DUF3778", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12620", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 318 and 395 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031460", "known_evidence_count": null, "matches": 115, "name": "Domain of unknown function (DUF4678)", "partial_evidence_count": null, "pfam_id": "PF15727", "proteins": 111, "proteomes": 100, "short_name": "DUF4678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15727", "structures": 0, "taxa": 344, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a repeating region found in filamentous hemagglutinin proteins from various bacteria. This entry may contain a beta helix structure.", "domain_architectures": 81, "interpro_id": "IPR043710", "known_evidence_count": null, "matches": 1169, "name": "Repeat of unknown function (DUF5650)", "partial_evidence_count": null, "pfam_id": "PF18888", "proteins": 111, "proteomes": 75, "short_name": "DUF5650", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18888", "structures": 0, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-beta structure.", "domain_architectures": 2, "interpro_id": "IPR055960", "known_evidence_count": null, "matches": 118, "name": "Family of unknown function (DUF7538)", "partial_evidence_count": null, "pfam_id": "PF24382", "proteins": 111, "proteomes": 111, "short_name": "DUF7538", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24382", "structures": 0, "taxa": 165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the C-terminal of a group of worm proteins. This domain may adopt a hairpin fold.", "domain_architectures": 3, "interpro_id": "IPR056655", "known_evidence_count": null, "matches": 111, "name": "Domain of unknown function (DUF7753)", "partial_evidence_count": null, "pfam_id": "PF24936", "proteins": 111, "proteomes": 99, "short_name": "DUF7753", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24936", "structures": 0, "taxa": 221, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR022540", "known_evidence_count": null, "matches": 110, "name": "Protein of unknown function (DUF2556)", "partial_evidence_count": null, "pfam_id": "PF10831", "proteins": 110, "proteomes": 110, "short_name": "DUF2556", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10831", "structures": 0, "taxa": 164, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 213 and 412 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR031461", "known_evidence_count": null, "matches": 110, "name": "Domain of unknown function (DUF4679)", "partial_evidence_count": null, "pfam_id": "PF15728", "proteins": 110, "proteomes": 101, "short_name": "DUF4679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15728", "structures": 0, "taxa": 386, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 5, "interpro_id": "IPR033429", "known_evidence_count": null, "matches": 122, "name": "Domain of unknown function (DUF5125)", "partial_evidence_count": null, "pfam_id": "PF17163", "proteins": 110, "proteomes": 104, "short_name": "DUF5125", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17163", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR035279", "known_evidence_count": null, "matches": 110, "name": "Family of unknown function (DUF5358)", "partial_evidence_count": null, "pfam_id": "PF17311", "proteins": 110, "proteomes": 80, "short_name": "DUF5358", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17311", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR020087", "known_evidence_count": null, "matches": 110, "name": "Family of unknown function (DUF5487)", "partial_evidence_count": null, "pfam_id": "PF17589", "proteins": 110, "proteomes": 109, "short_name": "DUF5487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17589", "structures": 0, "taxa": 237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 72, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry contains proteins of unknown function found predominantly in the Phycodnaviridae, Mimiviridae, Marseilleviridae and Iridoviridae virus families.", "domain_architectures": 6, "interpro_id": "IPR043872", "known_evidence_count": null, "matches": 122, "name": "Family of unknown function (DUF5832)", "partial_evidence_count": null, "pfam_id": "PF19150", "proteins": 110, "proteomes": 91, "short_name": "DUF5832", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19150", "structures": 0, "taxa": 257, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000081) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the kedarcidin biosynthetic gene cluster from Streptoalloteichus sp. ATCC 53650 [[cite:PUB00098878]].", "domain_architectures": 1, "interpro_id": "IPR045661", "known_evidence_count": null, "matches": 110, "name": "Family of unknown function (DUF6389)", "partial_evidence_count": null, "pfam_id": "PF19926", "proteins": 110, "proteomes": 109, "short_name": "DUF6389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19926", "structures": 0, "taxa": 232, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of integral membrane proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 180 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046717", "known_evidence_count": null, "matches": 110, "name": "Family of unknown function (DUF6609)", "partial_evidence_count": null, "pfam_id": "PF20313", "proteins": 110, "proteomes": 107, "short_name": "DUF6609", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20313", "structures": 0, "taxa": 250, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length. Proteins in this family might have an RNA polymerase activity.", "domain_architectures": 1, "interpro_id": "IPR046743", "known_evidence_count": null, "matches": 110, "name": "Family of unknown function (DUF6793)", "partial_evidence_count": null, "pfam_id": "PF20593", "proteins": 110, "proteomes": 108, "short_name": "DUF6793", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20593", "structures": 0, "taxa": 188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length and have conserved Arginine residues. This family may have an alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR046479", "known_evidence_count": null, "matches": 110, "name": "Family of unknown function (DUF6800)", "partial_evidence_count": null, "pfam_id": "PF20607", "proteins": 110, "proteomes": 109, "short_name": "DUF6800", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20607", "structures": 0, "taxa": 200, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 108, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found mainly in Halobacteria. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble treble-clef zinc fingers.", "domain_architectures": 1, "interpro_id": "IPR055991", "known_evidence_count": null, "matches": 110, "name": "Family of unknown function (DUF7569)", "partial_evidence_count": null, "pfam_id": "PF24453", "proteins": 110, "proteomes": 110, "short_name": "DUF7569", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24453", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 106, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in Halobacteria. The proteins containing this domain are predominantly found in various genera within the Haloferacaceae family, including Halonotius, Halorubrum, and others. The domain is typically found in proteins ranging from approximately 88 to 133 amino acids in length. The reviewed protein D4GXW3 from Haloferax volcanii contains this domain. This domain is composed of a four stranded beta sheet with alpha helices packed on one side.", "domain_architectures": 1, "interpro_id": "IPR058437", "known_evidence_count": null, "matches": 110, "name": "Domain of unknown function (DUF8124)", "partial_evidence_count": null, "pfam_id": "PF26445", "proteins": 110, "proteomes": 110, "short_name": "DUF8124", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26445", "structures": 0, "taxa": 159, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 101, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of hypothetical archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR007501", "known_evidence_count": null, "matches": 109, "name": "Protein of unknown function (DUF531)", "partial_evidence_count": null, "pfam_id": "PF04407", "proteins": 109, "proteomes": 109, "short_name": "DUF531", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04407", "structures": 0, "taxa": 213, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function. Some of the sequences are annotated as ea10 however the function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR024252", "known_evidence_count": null, "matches": 109, "name": "Protein of unknown function (DUF2528)", "partial_evidence_count": null, "pfam_id": "PF10800", "proteins": 109, "proteomes": 103, "short_name": "DUF2528", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10800", "structures": 0, "taxa": 327, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 88, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals.", "domain_architectures": 1, "interpro_id": "IPR041537", "known_evidence_count": null, "matches": 109, "name": "Family of unknown function (DUF5547)", "partial_evidence_count": null, "pfam_id": "PF17701", "proteins": 109, "proteomes": 101, "short_name": "DUF5547", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17701", "structures": 0, "taxa": 359, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000087) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the lasalocid biosynthetic gene cluster from Streptomyces lasaliensis [[cite:PUB00098916]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046302", "known_evidence_count": null, "matches": 109, "name": "Family of unknown function (DUF6417)", "partial_evidence_count": null, "pfam_id": "PF19981", "proteins": 109, "proteomes": 77, "short_name": "DUF6417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19981", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 98, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised archaeal sequences containing a galactose binding-like domain.", "domain_architectures": 2, "interpro_id": "IPR055807", "known_evidence_count": null, "matches": 109, "name": "Family of unknown function (DUF7383)", "partial_evidence_count": null, "pfam_id": "PF24108", "proteins": 109, "proteomes": 108, "short_name": "DUF7383", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24108", "structures": 0, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found at the C-terminus of a set of bacterial and phage proteins. It forms small five stranded beta barrel domain.", "domain_architectures": 2, "interpro_id": "IPR057707", "known_evidence_count": null, "matches": 109, "name": "Family of unknown function (DUF7947)", "partial_evidence_count": null, "pfam_id": "PF25679", "proteins": 109, "proteomes": 108, "short_name": "DUF7947", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25679", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 105, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is majoritarily found in Caenorhabditis proteins and has no known function. It has a ubiquitin fold. The GO annotation for the protein indicates that it has a function in nematode larval development.", "domain_architectures": 6, "interpro_id": "IPR060073", "known_evidence_count": null, "matches": 115, "name": "Domain of unknown function (DUF272), C-terminal", "partial_evidence_count": null, "pfam_id": "PF26704", "proteins": 109, "proteomes": 12, "short_name": "DUF272_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26704", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the istamycin biosynthetic gene cluster from Streptomyces tenjimariensis [[cite:PUB00098957]].", "domain_architectures": 1, "interpro_id": "IPR046224", "known_evidence_count": null, "matches": 108, "name": "Family of unknown function (DUF6257)", "partial_evidence_count": null, "pfam_id": "PF19771", "proteins": 108, "proteomes": 88, "short_name": "DUF6257", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19771", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046605", "known_evidence_count": null, "matches": 109, "name": "Family of unknown function (DUF6664)", "partial_evidence_count": null, "pfam_id": "PF20369", "proteins": 108, "proteomes": 71, "short_name": "DUF6664", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20369", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins that have a single transmembrane helix followed by a conserved C-terminal sequence. The family includes proteins from phage T4 and T6.", "domain_architectures": 1, "interpro_id": "IPR055672", "known_evidence_count": null, "matches": 108, "name": "Family of unknown function (DUF7248)", "partial_evidence_count": null, "pfam_id": "PF23906", "proteins": 108, "proteomes": 108, "short_name": "DUF7248", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23906", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a pair of domains found in family of uncharacterised proteins from halophilic archaea. Based on structural similarity of other domains in these proteins this family may represents a family of primase proteins. This entry represents a pair of protein domains with one nested within the loop of another. The proteins in this family are predominantly found in the class Halobacteria, which includes families such as Natrialbaceae, Halobacteriaceae, and Haloarculaceae. The proteins are typically around 500 amino acids in length. Many of these proteins are encoded on plasmids, suggesting a potential role in plasmid-associated functions.", "domain_architectures": 5, "interpro_id": "IPR058453", "known_evidence_count": null, "matches": 108, "name": "Family of unknown function (DUF8140)", "partial_evidence_count": null, "pfam_id": "PF26463", "proteins": 108, "proteomes": 83, "short_name": "DUF8140", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26463", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in vertebrates. There are a number of conserved cysteines, but the domain is not a zinc-finger.", "domain_architectures": 6, "interpro_id": "IPR031715", "known_evidence_count": null, "matches": 109, "name": "Domain of unknown function (DUF4727)", "partial_evidence_count": null, "pfam_id": "PF15856", "proteins": 107, "proteomes": 94, "short_name": "DUF4727", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15856", "structures": 0, "taxa": 336, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chromadorea.", "domain_architectures": 6, "interpro_id": "IPR020149", "known_evidence_count": null, "matches": 108, "name": "Family of unknown function (DUF5356)", "partial_evidence_count": null, "pfam_id": "PF17309", "proteins": 107, "proteomes": 68, "short_name": "DUF5356", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17309", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR020231", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF5384)", "partial_evidence_count": null, "pfam_id": "PF17358", "proteins": 107, "proteomes": 106, "short_name": "DUF5384", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17358", "structures": 0, "taxa": 229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function mostly found in Legionella.", "domain_architectures": 5, "interpro_id": "IPR040808", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF5630)", "partial_evidence_count": null, "pfam_id": "PF18632", "proteins": 107, "proteomes": 51, "short_name": "DUF5630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18632", "structures": 3, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 235 and 254 amino acids in length. There is a single completely conserved residue R that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR046028", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF5986)", "partial_evidence_count": null, "pfam_id": "PF19448", "proteins": 107, "proteomes": 101, "short_name": "DUF5986", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19448", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000299) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the alterochromide A biosynthetic gene cluster from Pseudoalteromonas piscicida JCM 20779 and appears to be predominantly found in gammaproteobacteria [[cite:PUB00098870]].", "domain_architectures": 1, "interpro_id": "IPR045614", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF6136)", "partial_evidence_count": null, "pfam_id": "PF19632", "proteins": 107, "proteomes": 105, "short_name": "DUF6136", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19632", "structures": 0, "taxa": 162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the istamycin biosynthetic gene cluster from Streptomyces tenjimariensis [[cite:PUB00098957]].", "domain_architectures": 1, "interpro_id": "IPR046218", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF6251)", "partial_evidence_count": null, "pfam_id": "PF19764", "proteins": 107, "proteomes": 89, "short_name": "DUF6251", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19764", "structures": 0, "taxa": 119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 357 and 490 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046607", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF6666)", "partial_evidence_count": null, "pfam_id": "PF20371", "proteins": 107, "proteomes": 84, "short_name": "DUF6666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20371", "structures": 0, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 185 and 199 amino acids in length. There are two semi-conserved sequence motifs: HLA and GFVPYI.", "domain_architectures": 4, "interpro_id": "IPR054259", "known_evidence_count": null, "matches": 167, "name": "Family of unknown function (DUF6990)", "partial_evidence_count": null, "pfam_id": "PF22499", "proteins": 107, "proteomes": 58, "short_name": "DUF6990", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22499", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in a family of uncharacterised proteins in nematodes.", "domain_architectures": 16, "interpro_id": "IPR055468", "known_evidence_count": null, "matches": 114, "name": "Domain of unknown function (DUF7040)", "partial_evidence_count": null, "pfam_id": "PF23051", "proteins": 107, "proteomes": 10, "short_name": "DUF7040", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23051", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. Structure prediction suggests this protein adopts a rather open conformation of three alpha helices and a possible beta strand suggesting it must interact with other proteins to function.", "domain_architectures": 1, "interpro_id": "IPR055691", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF7267)", "partial_evidence_count": null, "pfam_id": "PF23929", "proteins": 107, "proteomes": 107, "short_name": "DUF7267", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23929", "structures": 0, "taxa": 243, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 2, "interpro_id": "IPR019216", "known_evidence_count": null, "matches": 106, "name": "Probable treble clef", "partial_evidence_count": null, "pfam_id": "PF09889", "proteins": 106, "proteomes": 101, "short_name": "DUF2116", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09889", "structures": 0, "taxa": 262, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function, which can be found mostly in Ascomycota.", "domain_architectures": 2, "interpro_id": "IPR035237", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF5341)", "partial_evidence_count": null, "pfam_id": "PF17276", "proteins": 106, "proteomes": 44, "short_name": "DUF5341", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17276", "structures": 0, "taxa": 135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function mostly found in bacilli.", "domain_architectures": 2, "interpro_id": "IPR040915", "known_evidence_count": null, "matches": 106, "name": "Family of unknown function (DUF5634)", "partial_evidence_count": null, "pfam_id": "PF18681", "proteins": 106, "proteomes": 103, "short_name": "DUF5634", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18681", "structures": 1, "taxa": 153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001796) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the tauramamide biosynthetic gene cluster from Brevibacillus laterosporus DSM 25 [[cite:PUB00098905]].", "domain_architectures": 1, "interpro_id": "IPR045665", "known_evidence_count": null, "matches": 106, "name": "Family of unknown function (DUF6386)", "partial_evidence_count": null, "pfam_id": "PF19923", "proteins": 106, "proteomes": 104, "short_name": "DUF6386", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19923", "structures": 0, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in various phages that infect bacteria. The function of this protein is currently unknown. It is typically around 300-340 amino acids in length. This protein contains a predicted coiled-coil region near its C-terminus.", "domain_architectures": 2, "interpro_id": "IPR055659", "known_evidence_count": null, "matches": 108, "name": "Family of unknown function (DUF7235)", "partial_evidence_count": null, "pfam_id": "PF23882", "proteins": 106, "proteomes": 105, "short_name": "DUF7235", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23882", "structures": 0, "taxa": 224, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of bacterial and phage proteins that are uncharacterised. The domain is composed of three alpha helices, which dimerise to create a larger structure. Some members of the families contain two copies of this domain, most appear to homodimerise.", "domain_architectures": 3, "interpro_id": "IPR056638", "known_evidence_count": null, "matches": 108, "name": "Domain of unknown function (DUF7736)", "partial_evidence_count": null, "pfam_id": "PF24875", "proteins": 106, "proteomes": 102, "short_name": "DUF7736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24875", "structures": 0, "taxa": 316, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from Borrelia burgdorferi (Lyme disease spirochete).", "domain_architectures": 2, "interpro_id": "IPR007800", "known_evidence_count": null, "matches": 108, "name": "Protein of unknown function (DUF693)", "partial_evidence_count": null, "pfam_id": "PF05113", "proteins": 105, "proteomes": 31, "short_name": "DUF693", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05113", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Borrelia burgdorferi (Lyme disease spirochete) proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR007910", "known_evidence_count": null, "matches": 105, "name": "Protein of unknown function (DUF735)", "partial_evidence_count": null, "pfam_id": "PF05246", "proteins": 105, "proteomes": 30, "short_name": "DUF735", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05246", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 95, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain appears to be found only in a small family of Chlamydia species [[cite:PUB00097825]]. It is usually found repeated. This domain can be found in translocated actin-recruiting phosphoprotein (Tarp) from Chlamydia trachomatis serovar L2. Tarp appears to initiate or participate in signalling events that regulate the actin recruitment, which ultimately leads to internalisation [[cite:PUB00075564]].", "domain_architectures": 7, "interpro_id": "IPR011443", "known_evidence_count": null, "matches": 235, "name": "Domain of Unknown Function (DUF1547)", "partial_evidence_count": null, "pfam_id": "PF07577", "proteins": 105, "proteomes": 17, "short_name": "DUF1547", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07577", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be largely found in spirochaete bacteria. It is related to membrane beta barrel proteins.", "domain_architectures": 2, "interpro_id": "IPR024471", "known_evidence_count": null, "matches": 108, "name": "Domain of unknown function (DUF2715)", "partial_evidence_count": null, "pfam_id": "PF10895", "proteins": 105, "proteomes": 50, "short_name": "DUF2715", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10895", "structures": 0, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 450 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 18, "interpro_id": "IPR032502", "known_evidence_count": null, "matches": 145, "name": "Domain of unknown function (DUF4979)", "partial_evidence_count": null, "pfam_id": "PF16351", "proteins": 105, "proteomes": 80, "short_name": "DUF4979", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16351", "structures": 0, "taxa": 152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 103, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. It is found in eukaryotes (predominantly in the marine diatom Thalassiosira) and is approximately 50 amino acids in length. There are several conserved motifs: TSAGR/QARxM, FAV and DNxGRRAM/IG.", "domain_architectures": 7, "interpro_id": "IPR049223", "known_evidence_count": null, "matches": 107, "name": "Domain of unknown function (DUF6820)", "partial_evidence_count": null, "pfam_id": "PF20699", "proteins": 105, "proteomes": 1, "short_name": "DUF6820", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20699", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 135 and 1024 amino acids in length. This family of proteins are structurally related to [pfam:PF03614] a family of transcriptional repressors of phase-1 flagellin genes. The family appears to contain two related subdomains with Sm-like topology.", "domain_architectures": 2, "interpro_id": "IPR054251", "known_evidence_count": null, "matches": 105, "name": "Family of unknown function (DUF6982)", "partial_evidence_count": null, "pfam_id": "PF22478", "proteins": 105, "proteomes": 88, "short_name": "DUF6982", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22478", "structures": 0, "taxa": 170, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 90, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a SH2 domain found mainly in nematodes such as Trichuris trichura, Toxocara canis and Trichinella sp. The function of this domain is unknown.", "domain_architectures": 15, "interpro_id": "IPR055491", "known_evidence_count": null, "matches": 168, "name": "Domain of unknown function (DUF7063)", "partial_evidence_count": null, "pfam_id": "PF23205", "proteins": 105, "proteomes": 37, "short_name": "DUF7063", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23205", "structures": 0, "taxa": 109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The DUF7170 domain family consists of several uncharacterized phage proteins of around 50 amino acids in length. The family is found in a variety of phages that infect bacterial hosts such as Escherichia, Salmonella, Klebsiella, Vibrio, Citrobacter, Shigella, Pseudomonas and Aeromonas. A few longer proteins of around 60-90 amino acids are also included.", "domain_architectures": 1, "interpro_id": "IPR055594", "known_evidence_count": null, "matches": 105, "name": "Protein of unknown function (DUF7170)", "partial_evidence_count": null, "pfam_id": "PF23776", "proteins": 105, "proteomes": 105, "short_name": "DUF7170", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23776", "structures": 0, "taxa": 241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is found in caudoviruses, which are tailed bacteriophages. The protein is typically around 150-180 amino acids in length. Its function is currently unknown. It is found in viruses from the Drexlerviridae family, including Rogunavirinae, Braunvirinae, Tempevirinae, and Kyungwonvirus genera.", "domain_architectures": 1, "interpro_id": "IPR055598", "known_evidence_count": null, "matches": 105, "name": "Family of unknown function (DUF7174)", "partial_evidence_count": null, "pfam_id": "PF23796", "proteins": 105, "proteomes": 103, "short_name": "DUF7174", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23796", "structures": 0, "taxa": 244, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised nematode proteins. It is predicted to fold into a five-bladed beta-propeller.", "domain_architectures": 6, "interpro_id": "IPR057233", "known_evidence_count": null, "matches": 110, "name": "Domain of unknown function (DUF7911)", "partial_evidence_count": null, "pfam_id": "PF25492", "proteins": 105, "proteomes": 83, "short_name": "DUF7911", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25492", "structures": 0, "taxa": 193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins predominantly from cyanobacteria. It is predicted to fold into a beta-sandwich. Some members are likely to contain an isopeptide bond.", "domain_architectures": 3, "interpro_id": "IPR057685", "known_evidence_count": null, "matches": 105, "name": "Domain of unknown function (DUF7925)", "partial_evidence_count": null, "pfam_id": "PF25546", "proteins": 105, "proteomes": 96, "short_name": "DUF7925", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25546", "structures": 0, "taxa": 294, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain four predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058364", "known_evidence_count": null, "matches": 105, "name": "Domain of unknown function (DUF8051)", "partial_evidence_count": null, "pfam_id": "PF26225", "proteins": 105, "proteomes": 104, "short_name": "DUF8051", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26225", "structures": 0, "taxa": 280, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins contain two subdomains. Overall the protein contains several conserved cysteine and histidine residues that are likely to bind zinc ions.", "domain_architectures": 1, "interpro_id": "IPR058375", "known_evidence_count": null, "matches": 105, "name": "Family of unknown function (DUF8062)", "partial_evidence_count": null, "pfam_id": "PF26258", "proteins": 105, "proteomes": 105, "short_name": "DUF8062", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26258", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family includes proteins that are about 200 amino acids in length. The proteins are all from baculoviruses. This family includes ORF107 from Orgyia pseudotsugata multicapsid polyhedrosis virus (OpMNPV) and a variety of other numbered ORF proteins, such as ORF52 [swissprot:Q91F03], ORF140 [swissprot:Q9YMI8]. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR008534", "known_evidence_count": null, "matches": 104, "name": "Baculovirus protein of unknown function (DUF816)", "partial_evidence_count": null, "pfam_id": "PF05674", "proteins": 104, "proteomes": 100, "short_name": "DUF816", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05674", "structures": 0, "taxa": 203, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in mammalian proteins. There are a number of conserved cysteines but it is unlikely to be a zinc-finger family. This entry includes PATE4 from mice. According to structure predictions (AlphaFold models and DALI server), this domain is structurally similar to members of the uPar/Lys6 domain superfamily.", "domain_architectures": 1, "interpro_id": "IPR031710", "known_evidence_count": null, "matches": 104, "name": "Domain of unknown function (DUF4723)", "partial_evidence_count": null, "pfam_id": "PF15851", "proteins": 104, "proteomes": 84, "short_name": "DUF4723", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15851", "structures": 0, "taxa": 308, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 390 residues in length and is mainly found in various Bacillus subtilis species. This family is predicted to be functional in biosynthesis of rhizocticins and antifungal phosphonate oligopeptides, but the specific function of this family is still unknown.", "domain_architectures": 2, "interpro_id": "IPR032617", "known_evidence_count": null, "matches": 110, "name": "Domain of unknown function (DUF4885)", "partial_evidence_count": null, "pfam_id": "PF16226", "proteins": 104, "proteomes": 78, "short_name": "DUF4885", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16226", "structures": 0, "taxa": 176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Pasteurellaceae.", "domain_architectures": 2, "interpro_id": "IPR020511", "known_evidence_count": null, "matches": 104, "name": "Family of unknown function (DUF5374)", "partial_evidence_count": null, "pfam_id": "PF17344", "proteins": 104, "proteomes": 103, "short_name": "DUF5374", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17344", "structures": 0, "taxa": 165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found at the C-terminal region of Helicobacterial proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR041543", "known_evidence_count": null, "matches": 104, "name": "Family of unknown function (DUF5644)", "partial_evidence_count": null, "pfam_id": "PF18712", "proteins": 104, "proteomes": 104, "short_name": "DUF5644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18712", "structures": 1, "taxa": 154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 315 and 341 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046725", "known_evidence_count": null, "matches": 104, "name": "Family of unknown function (DUF6617)", "partial_evidence_count": null, "pfam_id": "PF20322", "proteins": 104, "proteomes": 97, "short_name": "DUF6617", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20322", "structures": 0, "taxa": 180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of phage proteins found to be associated with membranes, based on transmembrane region predictions. They are typically around 110 amino acids in length with a C-terminal membrane helix. Many also contain predicted coiled-coil region spanning the rest of the protein. The specific function is unknown. However, it could play a role in membrane fusion.", "domain_architectures": 1, "interpro_id": "IPR055625", "known_evidence_count": null, "matches": 104, "name": "Coiled-coil region of unknown function (DUF7201)", "partial_evidence_count": null, "pfam_id": "PF23831", "proteins": 104, "proteomes": 97, "short_name": "DUF7201", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23831", "structures": 0, "taxa": 318, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised protein found in bacteria. They are predicted to adopt alpha+beta structure defined as beta(2)alpha(2)beta(2) structural elements in which the beta-strands form an antiparallel beta-sheet.The function of these proteins is unknown.", "domain_architectures": 2, "interpro_id": "IPR056105", "known_evidence_count": null, "matches": 104, "name": "Domain of unknown function (DUF7688)", "partial_evidence_count": null, "pfam_id": "PF24737", "proteins": 104, "proteomes": 78, "short_name": "DUF7688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24737", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 100, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain three predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058362", "known_evidence_count": null, "matches": 104, "name": "Domain of unknown function (DUF8049)", "partial_evidence_count": null, "pfam_id": "PF26223", "proteins": 104, "proteomes": 104, "short_name": "DUF8049", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26223", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain found in a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 3, "interpro_id": "IPR058811", "known_evidence_count": null, "matches": 104, "name": "Family of unknown function (DUF8073) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26272", "proteins": 104, "proteomes": 86, "short_name": "DUF8073_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26272", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins found in both cyanobacteria and archaea. The domain is present in a wide range of species, including members of the Leptolyngbya group and Halobacteria. Proteins containing this domain are typically around 200 amino acids in length. The domain is highly conserved across different species, suggesting a potentially important but yet unidentified function.", "domain_architectures": 3, "interpro_id": "IPR058479", "known_evidence_count": null, "matches": 110, "name": "Domain of unknown function (DUF8166)", "partial_evidence_count": null, "pfam_id": "PF26500", "proteins": 104, "proteomes": 104, "short_name": "DUF8166", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26500", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial and phage proteins of around 60 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009750", "known_evidence_count": null, "matches": 103, "name": "Protein of unknown function (DUF1317)", "partial_evidence_count": null, "pfam_id": "PF07026", "proteins": 103, "proteomes": 93, "short_name": "DUF1317", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07026", "structures": 0, "taxa": 236, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is thought to be the product of the gene TT1592 from Thermus thermophilus however this cannot be confirmed. Currently there is no known function.", "domain_architectures": 1, "interpro_id": "IPR021650", "known_evidence_count": null, "matches": 103, "name": "Protein of unknown function (DUF3248)", "partial_evidence_count": null, "pfam_id": "PF11609", "proteins": 103, "proteomes": 103, "short_name": "DUF3248", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11609", "structures": 1, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Deinococci bacteria. Proteins in this family are typically between 117 and 157 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR024219", "known_evidence_count": null, "matches": 103, "name": "Protein of unknown function (DUF3809)", "partial_evidence_count": null, "pfam_id": "PF12723", "proteins": 103, "proteomes": 103, "short_name": "DUF3809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12723", "structures": 2, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC00001940) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the pyxidicycline A biosynthetic gene cluster from Pyxidicoccus fallax [[cite:PUB00099476]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 4, "interpro_id": "IPR046181", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF6209)", "partial_evidence_count": null, "pfam_id": "PF19714", "proteins": 103, "proteomes": 55, "short_name": "DUF6209", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19714", "structures": 0, "taxa": 154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in gamma proteobacteria. Proteins in this family are typically between 273 and 287 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046511", "known_evidence_count": null, "matches": 103, "name": "Family of unknown function (DUF6689)", "partial_evidence_count": null, "pfam_id": "PF20396", "proteins": 103, "proteomes": 99, "short_name": "DUF6689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20396", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in bacteriophage proteins, particularly those infecting Lactococcus species. The domain is approximately 115 amino acids in length. It is found in a small number of bacterial proteins as well.", "domain_architectures": 1, "interpro_id": "IPR055763", "known_evidence_count": null, "matches": 103, "name": "Domain of unknown function (DUF7339)", "partial_evidence_count": null, "pfam_id": "PF24028", "proteins": 103, "proteomes": 99, "short_name": "DUF7339", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24028", "structures": 0, "taxa": 220, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 97, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the Halobacteria class, specifically within the Haloferacaceae and Haloarculaceae families. The domain is approximately 68-86 amino acids in length. Reviewed UniProt entry Q18K22 from Haloquadratum walsbyi is included in this family. The domain is characterized by a conserved CPxCG motif, suggesting a potential zinc finger-like structure, although its exact function remains unknown.", "domain_architectures": 1, "interpro_id": "IPR058458", "known_evidence_count": null, "matches": 103, "name": "Domain of unknown function (DUF8145)", "partial_evidence_count": null, "pfam_id": "PF26470", "proteins": 103, "proteomes": 103, "short_name": "DUF8145", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26470", "structures": 0, "taxa": 160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins predominantly found in the bacterial phylum Thermodesulfobacteriota. The proteins containing this domain are mainly distributed among the orders Desulfovibrionales and Desulfobacterales. The domain is approximately 85 amino acids in length. Proteins containing this domain are predicted to be involved in various cellular processes, but their exact function remains unknown. The domain is sometimes associated with the [pfam:PF11823] domain, which is a putative Se/S carrier protein-like domain. This domain shows structure similarity to the N-terminal domain of Enolase.", "domain_architectures": 2, "interpro_id": "IPR058495", "known_evidence_count": null, "matches": 103, "name": "Domain of unknown function (DUF8182)", "partial_evidence_count": null, "pfam_id": "PF26554", "proteins": 103, "proteomes": 102, "short_name": "DUF8182", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26554", "structures": 0, "taxa": 270, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found C-terminal in uncharacterised bacterial proteins. It is predicted to fold into L-shaped beta-sandwich. Most proteins containing this domain also contain a lipoprotein lipid attachment site at the N-terminus suggesting they may be associated with the membrane.", "domain_architectures": 3, "interpro_id": "IPR059446", "known_evidence_count": null, "matches": 103, "name": "Domain of unknown function (DUF8402)", "partial_evidence_count": null, "pfam_id": "PF28444", "proteins": 103, "proteomes": 97, "short_name": "DUF8402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28444", "structures": 0, "taxa": 163, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a putative Fe-S binding reductase ([swissprot:Q72J89]) whose structure adopts an alpha and beta fold.", "domain_architectures": 1, "interpro_id": "IPR018987", "known_evidence_count": null, "matches": 102, "name": "Protein of unknown function (DUF1999)", "partial_evidence_count": null, "pfam_id": "PF09390", "proteins": 102, "proteomes": 102, "short_name": "DUF1999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09390", "structures": 2, "taxa": 152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021576", "known_evidence_count": null, "matches": 102, "name": "Protein of unknown function (DUF3208)", "partial_evidence_count": null, "pfam_id": "PF11482", "proteins": 102, "proteomes": 102, "short_name": "DUF3208", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11482", "structures": 3, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised.This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length. These proteins share two CXXC motifs suggesting these are zinc binding proteins. This protein is found in clostridia in an operon with three signalling proteins, suggesting this protein may be a DNA-binding transcription regulator downstream of an as yet unknown signalling pathway (Bateman A pers obs).", "domain_architectures": 1, "interpro_id": "IPR024210", "known_evidence_count": null, "matches": 102, "name": "Protein of unknown function (DUF3785)", "partial_evidence_count": null, "pfam_id": "PF12653", "proteins": 102, "proteomes": 102, "short_name": "DUF3785", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12653", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001101) is described by MIBiG as an example of the following biosynthetic classes, NRP and Polyketide (Macrolide). This family includes a protein from the leinamycin biosynthetic gene cluster from Streptomyces atroolivaceus and appears to be predominantly found in Actinobacteria [[cite:PUB00099409]].", "domain_architectures": 2, "interpro_id": "IPR046102", "known_evidence_count": null, "matches": 104, "name": "Family of unknown function (DUF6039)", "partial_evidence_count": null, "pfam_id": "PF19505", "proteins": 102, "proteomes": 46, "short_name": "DUF6039", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19505", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This BGC (BGC0000081) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the kedarcidin biosynthetic gene cluster from Streptoalloteichus sp. ATCC 53650CC [[cite:PUB00098878]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR046261", "known_evidence_count": null, "matches": 102, "name": "Family of unknown function (DUF6294)", "partial_evidence_count": null, "pfam_id": "PF19811", "proteins": 102, "proteomes": 96, "short_name": "DUF6294", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19811", "structures": 0, "taxa": 186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in viruses and bacteria, including Mycobacteriophages, Nocardia, Streptomyces and Rhodococcus species. The domain is typically between 50-99 amino acids in length. In some proteins, the domain is found at the C-terminus. AlphaFold prediction shows a small domain composed of three beta strands in a sheet with a single alpha helix between strands 2 and 3.", "domain_architectures": 1, "interpro_id": "IPR055620", "known_evidence_count": null, "matches": 102, "name": "Domain of unknown function (DUF7196)", "partial_evidence_count": null, "pfam_id": "PF23826", "proteins": 102, "proteomes": 99, "short_name": "DUF7196", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23826", "structures": 0, "taxa": 183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function mostly found in SAR organisms which includes stramenopiles, alveolates and rhizarians. It contains a similar fold to large ribosomal subunit proteins mL53 (MRPL44) which contains a beta-sheet connected to two alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR059346", "known_evidence_count": null, "matches": 102, "name": "Domain of unknown function (DUF8302)", "partial_evidence_count": null, "pfam_id": "PF26962", "proteins": 102, "proteomes": 59, "short_name": "DUF8302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26962", "structures": 2, "taxa": 165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 44 residues in length. Members are found in Cyanobacteriota and in cyanophages (Kyanoviridae). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061690", "known_evidence_count": null, "matches": 102, "name": "Family of unknown function (DUF8629)", "partial_evidence_count": null, "pfam_id": "PF30561", "proteins": 102, "proteomes": 99, "short_name": "DUF8629", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30561", "structures": 8, "taxa": 335, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 64 residues found in uncharacterised proteins from Cyanobacteriota. The domain can occur once or twice per protein. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061691", "known_evidence_count": null, "matches": 102, "name": "Domain of unknown function (DUF8630)", "partial_evidence_count": null, "pfam_id": "PF30563", "proteins": 102, "proteomes": 100, "short_name": "DUF8630", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30563", "structures": 0, "taxa": 325, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of unknown function from Borrelia burgdorferi (Lyme disease spirochete).", "domain_architectures": 1, "interpro_id": "IPR008495", "known_evidence_count": null, "matches": 101, "name": "Borrelia burgdorferi protein of unknown function (DUF777)", "partial_evidence_count": null, "pfam_id": "PF05606", "proteins": 101, "proteomes": 31, "short_name": "DUF777", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05606", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. There is a conserved NPKY sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025088", "known_evidence_count": null, "matches": 101, "name": "Protein of unknown function (DUF3970)", "partial_evidence_count": null, "pfam_id": "PF13113", "proteins": 101, "proteomes": 100, "short_name": "DUF3970", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13113", "structures": 0, "taxa": 177, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 2, "interpro_id": "IPR043930", "known_evidence_count": null, "matches": 101, "name": "Family of unknown function (DUF5754)", "partial_evidence_count": null, "pfam_id": "PF19058", "proteins": 101, "proteomes": 36, "short_name": "DUF5754", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19058", "structures": 0, "taxa": 144, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Clostridia. Proteins in this family are typically between 51 and 67 amino acids in length and have a single transmembrane helix.", "domain_architectures": 1, "interpro_id": "IPR046061", "known_evidence_count": null, "matches": 101, "name": "Family of unknown function (DUF6019)", "partial_evidence_count": null, "pfam_id": "PF19483", "proteins": 101, "proteomes": 93, "short_name": "DUF6019", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19483", "structures": 0, "taxa": 217, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001060) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the dynemicin A biosynthetic gene cluster from Micromonospora chersina [[cite:PUB00078772]].", "domain_architectures": 3, "interpro_id": "IPR046294", "known_evidence_count": null, "matches": 101, "name": "Family of unknown function (DUF6331)", "partial_evidence_count": null, "pfam_id": "PF19856", "proteins": 101, "proteomes": 100, "short_name": "DUF6331", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19856", "structures": 0, "taxa": 244, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 89, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of small uncharacterised proteins found in bacteria and archaea. They are predicted to adopt an alpha/beta globular structure consisting of a cradle-like beta-sheet and alpha-helices packed on the convex side of the sheet.", "domain_architectures": 1, "interpro_id": "IPR054230", "known_evidence_count": null, "matches": 101, "name": "Family of unknown function (DUF6955)", "partial_evidence_count": null, "pfam_id": "PF22271", "proteins": 101, "proteomes": 99, "short_name": "DUF6955", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22271", "structures": 0, "taxa": 246, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 99, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in the homologues of uncharacterised soybean proteins.", "domain_architectures": 12, "interpro_id": "IPR055695", "known_evidence_count": null, "matches": 101, "name": "Domain of unknown function (DUF7271)", "partial_evidence_count": null, "pfam_id": "PF23935", "proteins": 101, "proteomes": 2, "short_name": "DUF7271", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23935", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage protein domains. The domain adopts a compact beta sheet made of six strands.", "domain_architectures": 1, "interpro_id": "IPR055698", "known_evidence_count": null, "matches": 101, "name": "Domain of unknown function (DUF7274)", "partial_evidence_count": null, "pfam_id": "PF23939", "proteins": 101, "proteomes": 88, "short_name": "DUF7274", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23939", "structures": 0, "taxa": 196, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 91, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Nucleopolyhedrovirus proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR009235", "known_evidence_count": null, "matches": 101, "name": "Nucleopolyhedrovirus protein of unknown function (DUF884)", "partial_evidence_count": null, "pfam_id": "PF05959", "proteins": 100, "proteomes": 97, "short_name": "DUF884", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05959", "structures": 0, "taxa": 198, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 4, "interpro_id": "IPR033430", "known_evidence_count": null, "matches": 114, "name": "Domain of unknown function (DUF5121)", "partial_evidence_count": null, "pfam_id": "PF17165", "proteins": 100, "proteomes": 98, "short_name": "DUF5121", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17165", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a protein that is a component of the virion particle in several bacteriophages infecting hosts such as Bacillus, Staphylococcus, Listeria, Enterococcus and Lactobacillus. The exact function is unknown but it is likely to play a structural role. The protein is typically between 65-80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR055633", "known_evidence_count": null, "matches": 100, "name": "Family of unknown function (DUF7209)", "partial_evidence_count": null, "pfam_id": "PF23839", "proteins": 100, "proteomes": 100, "short_name": "DUF7209", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23839", "structures": 0, "taxa": 213, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins found mainly in Halobacteria. They are predicted to adopt a globular alpha/beta structure consisting of three-stranded beta-sheet and two alpha-helices one of which is packed on the beta-sheet.", "domain_architectures": 1, "interpro_id": "IPR055964", "known_evidence_count": null, "matches": 100, "name": "Family of unknown function (DUF7542)", "partial_evidence_count": null, "pfam_id": "PF24398", "proteins": 100, "proteomes": 100, "short_name": "DUF7542", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24398", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterized proteins. It is predicted to fold into an alpha-helical structure which is usually found inserted into endonuclease domain (CL0530). It contains a highly conserved Gx(2)Rx(2)SxPDRxTN sequence motif which is predicted to face the endonuclease domain active site and is likely involved in substrate recognition/binding.", "domain_architectures": 9, "interpro_id": "IPR059278", "known_evidence_count": null, "matches": 101, "name": "Domain of unknown function (DUF8234)", "partial_evidence_count": null, "pfam_id": "PF26695", "proteins": 100, "proteomes": 51, "short_name": "DUF8234", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26695", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. This domain is predicted to fold into a beta-barrel structure which has topological similarity to domains members of Phage tail beta-barrel superfamily.", "domain_architectures": 2, "interpro_id": "IPR059447", "known_evidence_count": null, "matches": 100, "name": "Domain of unknown function (DUF8403)", "partial_evidence_count": null, "pfam_id": "PF28445", "proteins": 100, "proteomes": 97, "short_name": "DUF8403", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28445", "structures": 0, "taxa": 173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of proteins of unknown function from Borrelia burgdorferi (Lyme disease spirochete).", "domain_architectures": 1, "interpro_id": "IPR008483", "known_evidence_count": null, "matches": 99, "name": "Borrelia burgdorferi protein of unknown function (DUF764)", "partial_evidence_count": null, "pfam_id": "PF05561", "proteins": 99, "proteomes": 31, "short_name": "DUF764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05561", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals.", "domain_architectures": 3, "interpro_id": "IPR037649", "known_evidence_count": null, "matches": 101, "name": "Family of unknown function (DUF5569)", "partial_evidence_count": null, "pfam_id": "PF17729", "proteins": 99, "proteomes": 98, "short_name": "DUF5569", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17729", "structures": 0, "taxa": 348, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this family are found in Firmicutes. They are approximately 120 amino acids in length and are predicted to adopt an alpha helical structure. Members of this family contain two highly conserved acid residues aspartate and glutamate.", "domain_architectures": 2, "interpro_id": "IPR054275", "known_evidence_count": null, "matches": 101, "name": "Family of unknown function (DUF7006)", "partial_evidence_count": null, "pfam_id": "PF22652", "proteins": 99, "proteomes": 44, "short_name": "DUF7006", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22652", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 94, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt an alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR055956", "known_evidence_count": null, "matches": 99, "name": "Family of unknown function (DUF7534)", "partial_evidence_count": null, "pfam_id": "PF24378", "proteins": 99, "proteomes": 92, "short_name": "DUF7534", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24378", "structures": 0, "taxa": 164, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in Halobacteria. The proteins containing this domain are primarily found in various genera within the Halobacteriales order, including Halorubrum, Haloarculaceae, and Haloferacaceae. The domain is approximately 109 amino acids in length. The domain is composed of four alpha helices.", "domain_architectures": 1, "interpro_id": "IPR058471", "known_evidence_count": null, "matches": 99, "name": "Domain of unknown function (DUF8158)", "partial_evidence_count": null, "pfam_id": "PF26488", "proteins": 99, "proteomes": 79, "short_name": "DUF8158", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26488", "structures": 0, "taxa": 146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to fold into a six-stranded beta-barrel with unique topology. It contains a conserved HDRxE sequence motif toward the C-termini.", "domain_architectures": 2, "interpro_id": "IPR059361", "known_evidence_count": null, "matches": 99, "name": "Domain of unknown function (DUF8317)", "partial_evidence_count": null, "pfam_id": "PF26991", "proteins": 99, "proteomes": 92, "short_name": "DUF8317", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26991", "structures": 0, "taxa": 214, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 250 residues in length and is mainly found in various human gut Firmicute species and abundant in human gut metagenomic datasets. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032357", "known_evidence_count": null, "matches": 98, "name": "Domain of unknown function (DUF4866)", "partial_evidence_count": null, "pfam_id": "PF16160", "proteins": 98, "proteomes": 94, "short_name": "DUF4866", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16160", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Proteobacteria. Family members contain three predicted trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035210", "known_evidence_count": null, "matches": 98, "name": "Family of unknown function (DUF5455)", "partial_evidence_count": null, "pfam_id": "PF17537", "proteins": 98, "proteomes": 95, "short_name": "DUF5455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17537", "structures": 3, "taxa": 207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR035135", "known_evidence_count": null, "matches": 98, "name": "Family of unknown function (DUF5496)", "partial_evidence_count": null, "pfam_id": "PF17600", "proteins": 98, "proteomes": 96, "short_name": "DUF5496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17600", "structures": 0, "taxa": 207, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phycodnaviridae. This entry includes proteins that are also found in Fungi.", "domain_architectures": 12, "interpro_id": "IPR043659", "known_evidence_count": null, "matches": 166, "name": "Family of unknown function (DUF5874)", "partial_evidence_count": null, "pfam_id": "PF19202", "proteins": 98, "proteomes": 62, "short_name": "DUF5874", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19202", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of short uncharacterised proteins. They are predicted to adopt a three helical structure.", "domain_architectures": 1, "interpro_id": "IPR049242", "known_evidence_count": null, "matches": 98, "name": "Family of unknown function (DUF6877)", "partial_evidence_count": null, "pfam_id": "PF21793", "proteins": 98, "proteomes": 87, "short_name": "DUF6877", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21793", "structures": 0, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised domains found in bacterial lipoproteins.", "domain_architectures": 1, "interpro_id": "IPR058408", "known_evidence_count": null, "matches": 98, "name": "Domain of unknown function (DUF8095)", "partial_evidence_count": null, "pfam_id": "PF26367", "proteins": 98, "proteomes": 77, "short_name": "DUF8095", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26367", "structures": 0, "taxa": 136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 87, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins containing this domain are primarily found in the class Halobacteria, which includes various families such as Haloferacaceae, Halobacteriaceae, and Natrialbaceae. These proteins are typically around 190-200 amino acids in length. The domain shows a high overlap with TED domains, suggesting a conserved structure. Several proteins in this family are predicted to be lipoproteins, indicating a potential association with membranes. This domain adopts an Ig-like fold.", "domain_architectures": 4, "interpro_id": "IPR058443", "known_evidence_count": null, "matches": 98, "name": "Domain of unknown function (DUF8130)", "partial_evidence_count": null, "pfam_id": "PF26451", "proteins": 98, "proteomes": 85, "short_name": "DUF8130", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26451", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 96, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in archaea, and is approximately 60 amino acids in length. There is a conserved QTV sequence motif.", "domain_architectures": 2, "interpro_id": "IPR025471", "known_evidence_count": null, "matches": 97, "name": "Domain of unknown function (DUF4322)", "partial_evidence_count": null, "pfam_id": "PF14210", "proteins": 97, "proteomes": 11, "short_name": "DUF4322", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14210", "structures": 0, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 93, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 116 and 180 amino acids in length. There is a conserved FFFGQY sequence motif.", "domain_architectures": 2, "interpro_id": "IPR031931", "known_evidence_count": null, "matches": 98, "name": "Domain of unknown function (DUF4768)", "partial_evidence_count": null, "pfam_id": "PF15989", "proteins": 97, "proteomes": 29, "short_name": "DUF4768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15989", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical lipoproteins around 270 residues in length and is mainly found in Pseudomonas species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032249", "known_evidence_count": null, "matches": 97, "name": "Domain of unknown function (DUF4824)", "partial_evidence_count": null, "pfam_id": "PF16106", "proteins": 97, "proteomes": 96, "short_name": "DUF4824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16106", "structures": 0, "taxa": 213, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Myoviridae.", "domain_architectures": 1, "interpro_id": "IPR035146", "known_evidence_count": null, "matches": 97, "name": "Family of unknown function (DUF5481)", "partial_evidence_count": null, "pfam_id": "PF17578", "proteins": 97, "proteomes": 95, "short_name": "DUF5481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17578", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001447) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the primycin biosynthetic gene cluster from Saccharomonospora azurea SZMC 14600 [[cite:PUB00098889],[cite:PUB00098888]].", "domain_architectures": 1, "interpro_id": "IPR045645", "known_evidence_count": null, "matches": 97, "name": "Family of unknown function (DUF6403)", "partial_evidence_count": null, "pfam_id": "PF19941", "proteins": 97, "proteomes": 96, "short_name": "DUF6403", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19941", "structures": 0, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR045615", "known_evidence_count": null, "matches": 97, "name": "Family of unknown function (DUF6447)", "partial_evidence_count": null, "pfam_id": "PF20045", "proteins": 97, "proteomes": 85, "short_name": "DUF6447", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20045", "structures": 0, "taxa": 208, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 84, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 242 and 267 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046745", "known_evidence_count": null, "matches": 97, "name": "Family of unknown function (DUF6675)", "partial_evidence_count": null, "pfam_id": "PF20380", "proteins": 97, "proteomes": 65, "short_name": "DUF6675", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20380", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small uncharacterised family of phage proteins. It adopts a novel triangular beta prism structure.", "domain_architectures": 1, "interpro_id": "IPR055841", "known_evidence_count": null, "matches": 97, "name": "Domain of unknown function (DUF7418)", "partial_evidence_count": null, "pfam_id": "PF24193", "proteins": 97, "proteomes": 96, "short_name": "DUF7418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24193", "structures": 0, "taxa": 219, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 90, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in a group of uncharacterised sequences from diatoms. This domain may adopt a beta-solenoid fold and in some members is repeated twice or three times.", "domain_architectures": 13, "interpro_id": "IPR056057", "known_evidence_count": null, "matches": 157, "name": "Domain of unknown function (DUF7640)", "partial_evidence_count": null, "pfam_id": "PF24646", "proteins": 97, "proteomes": 13, "short_name": "DUF7640", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24646", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins.It is predicted to adopt a complex unique structure.", "domain_architectures": 2, "interpro_id": "IPR059403", "known_evidence_count": null, "matches": 97, "name": "Domain of unknown function (DUF8359)", "partial_evidence_count": null, "pfam_id": "PF27633", "proteins": 97, "proteomes": 37, "short_name": "DUF8359", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27633", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from the Lyme disease spirochete Borrelia burgdorferi.", "domain_architectures": 1, "interpro_id": "IPR008510", "known_evidence_count": null, "matches": 96, "name": "Borrelia burgdorferi protein of unknown function (DUF792)", "partial_evidence_count": null, "pfam_id": "PF05632", "proteins": 96, "proteomes": 31, "short_name": "DUF792", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05632", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR019202", "known_evidence_count": null, "matches": 96, "name": "Uncharacterized protein conserved in archaea (DUF2067)", "partial_evidence_count": null, "pfam_id": "PF09840", "proteins": 96, "proteomes": 96, "short_name": "DUF2067", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09840", "structures": 0, "taxa": 221, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 147 and 199 amino acids in length.", "domain_architectures": 5, "interpro_id": "IPR046731", "known_evidence_count": null, "matches": 96, "name": "Family of unknown function (DUF6623)", "partial_evidence_count": null, "pfam_id": "PF20328", "proteins": 96, "proteomes": 81, "short_name": "DUF6623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20328", "structures": 0, "taxa": 284, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein family is found in eukaryotes. There are highly conserved motifs: QQE and RFDLR.", "domain_architectures": 2, "interpro_id": "IPR049226", "known_evidence_count": null, "matches": 96, "name": "Family of unknown function (DUF6823)", "partial_evidence_count": null, "pfam_id": "PF20709", "proteins": 96, "proteomes": 78, "short_name": "DUF6823", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20709", "structures": 0, "taxa": 241, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins mainly from Actinomycetes. It is predicted to fold into a beta-sandwich with topological similarity to domains members of the adhesin superfamily. Most members contain conserved lysine aspartate and asparagine residues that are likely to form an isopeptide bond. This domain is frequently found in combination with DUF5979.", "domain_architectures": 28, "interpro_id": "IPR057686", "known_evidence_count": null, "matches": 96, "name": "Domain of unknown function (DUF7926)", "partial_evidence_count": null, "pfam_id": "PF25548", "proteins": 96, "proteomes": 38, "short_name": "DUF7926", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25548", "structures": 0, "taxa": 79, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein domain found predominantly in Firmicutes, particularly Clostridium, Paenibacillus, and Bacillus species. The domain is approximately 181-185 amino acids in length and typically occurs as part of multi-domain proteins. The family is also found in bacteriophages that infect Firmicutes, suggesting horizontal gene transfer from bacterial hosts. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061621", "known_evidence_count": null, "matches": 96, "name": "Domain of unknown function (DUF8551)", "partial_evidence_count": null, "pfam_id": "PF29429", "proteins": 96, "proteomes": 58, "short_name": "DUF8551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29429", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is believed to be involved in the type VII secretion system.", "domain_architectures": 2, "interpro_id": "IPR031682", "known_evidence_count": null, "matches": 96, "name": "Domain of unknown function (DUF5081)", "partial_evidence_count": null, "pfam_id": "PF16887", "proteins": 95, "proteomes": 87, "short_name": "DUF5081", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16887", "structures": 0, "taxa": 168, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacilli. Family members are predicted to have 4 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR020204", "known_evidence_count": null, "matches": 95, "name": "Family of unknown function (DUF5391)", "partial_evidence_count": null, "pfam_id": "PF17369", "proteins": 95, "proteomes": 90, "short_name": "DUF5391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17369", "structures": 0, "taxa": 173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 57 and 70 amino acids in length. There is a conserved sequence motif QLGDTL.", "domain_architectures": 1, "interpro_id": "IPR046665", "known_evidence_count": null, "matches": 95, "name": "Family of unknown function (DUF6774)", "partial_evidence_count": null, "pfam_id": "PF20564", "proteins": 95, "proteomes": 82, "short_name": "DUF6774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20564", "structures": 0, "taxa": 156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of unknown function found in bacterial proteins. The function of this protein remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061642", "known_evidence_count": null, "matches": 101, "name": "Family of unknown function (DUF8581)", "partial_evidence_count": null, "pfam_id": "PF29725", "proteins": 95, "proteomes": 92, "short_name": "DUF8581", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29725", "structures": 0, "taxa": 277, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of a number of hypothetical proteins of unknown function from Borrelia burgdorferi (Lyme disease spirochete).", "domain_architectures": 2, "interpro_id": "IPR008505", "known_evidence_count": null, "matches": 94, "name": "DUF787, N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF05619", "proteins": 94, "proteomes": 31, "short_name": "DUF787", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05619", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represent the N-terminal domain of the structure. In two related Bacteroides species the gene lies immediately upstream from a putative ATP binding component of an ATP transporter and a putative histidinol phosphatase. The structure of this domain is strikingly similar to the N-terminal structure of 1tui, also of unknown function. The domain carries four conserved tryptophan residues.", "domain_architectures": 2, "interpro_id": "IPR024315", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF3805)", "partial_evidence_count": null, "pfam_id": "PF12712", "proteins": 94, "proteomes": 93, "short_name": "DUF3805", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12712", "structures": 1, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function mostly found in firmicutes.", "domain_architectures": 1, "interpro_id": "IPR040491", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF5626)", "partial_evidence_count": null, "pfam_id": "PF18540", "proteins": 94, "proteomes": 87, "short_name": "DUF5626", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18540", "structures": 1, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and archaea. Proteins in this family are typically between 78 and 90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR043718", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF5659)", "partial_evidence_count": null, "pfam_id": "PF18903", "proteins": 94, "proteomes": 82, "short_name": "DUF5659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18903", "structures": 0, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is mainly found in Clostridia. Proteins in this family are typically between 466 and 533 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046098", "known_evidence_count": null, "matches": 114, "name": "Family of unknown function (DUF6034)", "partial_evidence_count": null, "pfam_id": "PF19499", "proteins": 94, "proteomes": 62, "short_name": "DUF6034", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19499", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, mainly Firmicutes. Proteins in this family are typically between 157 and 193 amino acids in length. There are three highly conserved residues, tryptophan, phenylalanine/ tyrosine and lysine.", "domain_architectures": 1, "interpro_id": "IPR046690", "known_evidence_count": null, "matches": 94, "name": "Family of unknown function (DUF6560)", "partial_evidence_count": null, "pfam_id": "PF20197", "proteins": 94, "proteomes": 78, "short_name": "DUF6560", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20197", "structures": 0, "taxa": 204, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 189 and 210 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046594", "known_evidence_count": null, "matches": 102, "name": "Family of unknown function (DUF6652)", "partial_evidence_count": null, "pfam_id": "PF20357", "proteins": 94, "proteomes": 88, "short_name": "DUF6652", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20357", "structures": 0, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046564", "known_evidence_count": null, "matches": 94, "name": "Family of unknown function (DUF6718)", "partial_evidence_count": null, "pfam_id": "PF20476", "proteins": 94, "proteomes": 85, "short_name": "DUF6718", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20476", "structures": 3, "taxa": 171, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function that is found in archaea and bacteria. This domain is typically around 110 amino acids in length. There are two conserved motifs, RW and VSG.", "domain_architectures": 2, "interpro_id": "IPR049214", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF6808)", "partial_evidence_count": null, "pfam_id": "PF20647", "proteins": 94, "proteomes": 81, "short_name": "DUF6808", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20647", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a set of uncharacterized proteins found predominantly in viruses, particularly bacteriophages. The proteins are typically 130-150 amino acids in length. AlphaFold models of this family show some weak partial structural similarity to the Recombination-associated protein RdgC.", "domain_architectures": 1, "interpro_id": "IPR055597", "known_evidence_count": null, "matches": 94, "name": "Family of unknown function (DUF7173)", "partial_evidence_count": null, "pfam_id": "PF23791", "proteins": 94, "proteomes": 86, "short_name": "DUF7173", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23791", "structures": 0, "taxa": 238, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents an uncharacterized protein domain found in phage proteins, mostly from Caudovirales. The domain is around 70-120 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR055673", "known_evidence_count": null, "matches": 94, "name": "Family of unknown function (DUF7249)", "partial_evidence_count": null, "pfam_id": "PF23907", "proteins": 94, "proteomes": 92, "short_name": "DUF7249", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23907", "structures": 0, "taxa": 293, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a presumed domain found in a group of uncharacterised proteins from bacteria. This domain may adopt an all-beta configuration.", "domain_architectures": 9, "interpro_id": "IPR055875", "known_evidence_count": null, "matches": 146, "name": "Domain of unknown function (DUF7452)", "partial_evidence_count": null, "pfam_id": "PF24249", "proteins": 94, "proteomes": 72, "short_name": "DUF7452", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24249", "structures": 0, "taxa": 204, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins containing this domain are predominantly found in the class Halobacteria, which includes genera such as Halalkalicoccus, Haladaptatus, and Natrialbaceae. The domain is typically found in proteins ranging from approximately 60 to 200 amino acids in length. This domain contains conserved cysteine residues suggestive of zinc binding. Some proteins in this family are predicted to contain transmembrane helices, suggesting a possible membrane-associated role.", "domain_architectures": 4, "interpro_id": "IPR058431", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF8118)", "partial_evidence_count": null, "pfam_id": "PF26435", "proteins": 94, "proteomes": 57, "short_name": "DUF8118", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26435", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins containing this domain are predominantly found in members of the Halobacteria class, including families such as Haloarculaceae, Natrialbaceae, and Haloferacaceae. The domain is typically found in proteins ranging from approximately 240 to 300 amino acids in length. This domain shows structural similarity to the Csm1 protein covering the HD-like domain and domain A [[cite:PUB00091420]]. This finding suggests that this domain may have DNase activity.", "domain_architectures": 1, "interpro_id": "IPR058481", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF8574)", "partial_evidence_count": null, "pfam_id": "PF26506", "proteins": 94, "proteomes": 75, "short_name": "DUF8574", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26506", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an unique alpha/beta structure composed on a four-stranded mixed beta-sheet (order 2143) and alpha-helices that pack on one face of the sheet, spanning edge to edge.", "domain_architectures": 2, "interpro_id": "IPR059264", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF8220)", "partial_evidence_count": null, "pfam_id": "PF26665", "proteins": 94, "proteomes": 89, "short_name": "DUF8220", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26665", "structures": 0, "taxa": 239, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 90, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in uncharacterised proteins mostly from plants. This domain contains a Spectring fold with a conserved three-helix bundle structure that is typically arranged in tandem repeats. These repeats confer mechanical flexibility and structural resilience, allowing the proteins to maintain cell shape and organisation. Spectrin-repeat proteins form elongated scaffolds beneath the plasma membrane and contribute to cytoskeletal integrity and membrane stability.", "domain_architectures": 6, "interpro_id": "IPR059368", "known_evidence_count": null, "matches": 126, "name": "Domain of unknown function (DUF8324)", "partial_evidence_count": null, "pfam_id": "PF27003", "proteins": 94, "proteomes": 24, "short_name": "DUF8324", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27003", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical 9.4 kDa Borrelia burgdorferi (Lyme disease spirochete) proteins of around 78 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009753", "known_evidence_count": null, "matches": 93, "name": "Protein of unknown function (DUF1322)", "partial_evidence_count": null, "pfam_id": "PF07032", "proteins": 93, "proteomes": 31, "short_name": "DUF1322", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07032", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 150 residues in length. Members of this family seem to be found exclusively in Borrelia burgdorferi (Lyme disease spirochete). The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009941", "known_evidence_count": null, "matches": 93, "name": "Protein of unknown function (DUF1473)", "partial_evidence_count": null, "pfam_id": "PF07341", "proteins": 93, "proteomes": 31, "short_name": "DUF1473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07341", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 130 residues in length. Members of this family seem to be specific to Borrelia burgdorferi (Lyme disease spirochete). The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010875", "known_evidence_count": null, "matches": 93, "name": "Domain of unknown function (DUF1506)", "partial_evidence_count": null, "pfam_id": "PF07405", "proteins": 93, "proteomes": 30, "short_name": "DUF1506", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07405", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function which is mainly found in Deinococcus-Thermus. Some family members can be found in the C-terminal region of [pfam:PF01565].", "domain_architectures": 2, "interpro_id": "IPR040948", "known_evidence_count": null, "matches": 93, "name": "Family of unknown function (DUF5639)", "partial_evidence_count": null, "pfam_id": "PF18690", "proteins": 93, "proteomes": 92, "short_name": "DUF5639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18690", "structures": 1, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of bacterial proteins is functionally uncharacterised. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046293", "known_evidence_count": null, "matches": 93, "name": "Family of unknown function (DUF6330)", "partial_evidence_count": null, "pfam_id": "PF19855", "proteins": 93, "proteomes": 85, "short_name": "DUF6330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19855", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family of proteins is unknown. They are predicted to adopt a five-bladed beta-propeller and are probably distantly related to apyrase.", "domain_architectures": 3, "interpro_id": "IPR053852", "known_evidence_count": null, "matches": 93, "name": "Family of unknown function (DUF6910)", "partial_evidence_count": null, "pfam_id": "PF21851", "proteins": 93, "proteomes": 92, "short_name": "DUF6910", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21851", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Alphaproteobacteria. It is predicted to adopt a beta- sandwich with unique topology. It contains four highly conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 2, "interpro_id": "IPR059261", "known_evidence_count": null, "matches": 94, "name": "Domain of unknown function (DUF8217)", "partial_evidence_count": null, "pfam_id": "PF26654", "proteins": 93, "proteomes": 92, "short_name": "DUF8217", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26654", "structures": 0, "taxa": 136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of a number of hypothetical proteins of unknown function from Borrelia burgdorferi (Lyme disease spirochete).", "domain_architectures": 2, "interpro_id": "IPR062987", "known_evidence_count": null, "matches": 93, "name": "DUF787, C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF29467", "proteins": 93, "proteomes": 31, "short_name": "DUF787_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29467", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 140 residues in length. Members of this family seem to be found exclusively in Borrelia burgdorferi (Lyme disease spirochete). The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009925", "known_evidence_count": null, "matches": 92, "name": "Domain of unknown function (DUF1463)", "partial_evidence_count": null, "pfam_id": "PF07316", "proteins": 92, "proteomes": 31, "short_name": "DUF1463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07316", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is conserved in Gammaproteobacteria. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019731", "known_evidence_count": null, "matches": 92, "name": "Protein of unknown function (DUF2607)", "partial_evidence_count": null, "pfam_id": "PF10795", "proteins": 92, "proteomes": 91, "short_name": "DUF2607", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10795", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Large family of predicted lipoproteins from Gram-positive bacteria Experimentally determined structure shows a cystatitin-like fold, allowing us to classify this family in the NFT2 clan, despite lack of any detectable sequence similarity between members of this family and other families in this clan", "domain_architectures": 1, "interpro_id": "IPR028075", "known_evidence_count": null, "matches": 92, "name": "Domain of unknown function with cystatin-like fold (DUF4467)", "partial_evidence_count": null, "pfam_id": "PF14729", "proteins": 92, "proteomes": 66, "short_name": "DUF4467", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14729", "structures": 1, "taxa": 112, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 120 and 137 amino acids in length. There is a conserved GGCNAC sequence motif.", "domain_architectures": 1, "interpro_id": "IPR032080", "known_evidence_count": null, "matches": 92, "name": "Domain of unknown function (DUF4809)", "partial_evidence_count": null, "pfam_id": "PF16067", "proteins": 92, "proteomes": 86, "short_name": "DUF4809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16067", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001543) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the chejuenolide A biosynthetic gene cluster from Hahella chejuensis [[cite:PUB00099414]].", "domain_architectures": 1, "interpro_id": "IPR046297", "known_evidence_count": null, "matches": 92, "name": "Family of unknown function (DUF6334)", "partial_evidence_count": null, "pfam_id": "PF19860", "proteins": 92, "proteomes": 89, "short_name": "DUF6334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19860", "structures": 0, "taxa": 260, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from flagellate Discoba. It has detectable similarity to known PDZ domains and it is predicted to adopt similar structure. It is frequently found in multiple tandem copies.", "domain_architectures": 3, "interpro_id": "IPR056661", "known_evidence_count": null, "matches": 92, "name": "Domain of unknown function (DUF7759)", "partial_evidence_count": null, "pfam_id": "PF24945", "proteins": 92, "proteomes": 28, "short_name": "DUF7759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24945", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 85, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in the class Halobacteria. These proteins are predominantly found in members of the Haloferacaceae family, which are part of the Methanobacteriota phylum. The proteins in this family are typically around 60 amino acids in length. They are predicted to contain two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058491", "known_evidence_count": null, "matches": 92, "name": "Family of unknown function (DUF8178)", "partial_evidence_count": null, "pfam_id": "PF26546", "proteins": 92, "proteomes": 92, "short_name": "DUF8178", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26546", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 56 residues in length. Members are found in Cyanobacteriota and in cyanophages (Kyanoviridae). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061699", "known_evidence_count": null, "matches": 92, "name": "Domain of unknown function (DUF8638)", "partial_evidence_count": null, "pfam_id": "PF30571", "proteins": 92, "proteomes": 83, "short_name": "DUF8638", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30571", "structures": 0, "taxa": 237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 92, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This group of proteins is found in eukaryotes. They show several highly conserved P residues.", "domain_architectures": 5, "interpro_id": "IPR061856", "known_evidence_count": null, "matches": 147, "name": "Family of unknown function (DUF8795)", "partial_evidence_count": null, "pfam_id": "PF31056", "proteins": 92, "proteomes": 7, "short_name": "DUF8795", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31056", "structures": 2, "taxa": 104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Staphylococcus aureus and phage proteins of 53 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009682", "known_evidence_count": null, "matches": 91, "name": "Protein of unknown function (DUF1270)", "partial_evidence_count": null, "pfam_id": "PF06900", "proteins": 91, "proteomes": 82, "short_name": "DUF1270", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06900", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Most of these Rhodopirellula baltica hypothetical proteins also match [pfam:PF07619].", "domain_architectures": 17, "interpro_id": "IPR011475", "known_evidence_count": null, "matches": 111, "name": "Protein of unknown function (DUF1583) C domain", "partial_evidence_count": null, "pfam_id": "PF07622", "proteins": 91, "proteomes": 39, "short_name": "DUF1583", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07622", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 170 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR027909", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF4447)", "partial_evidence_count": null, "pfam_id": "PF14590", "proteins": 91, "proteomes": 90, "short_name": "DUF4447", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14590", "structures": 1, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0002018) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the azomycin biosynthetic gene cluster from Streptomyces cattleya NRRL 8057 = DSM 46488. This family appears to be predominantly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR045685", "known_evidence_count": null, "matches": 91, "name": "Family of unknown function (DUF6190)", "partial_evidence_count": null, "pfam_id": "PF19689", "proteins": 91, "proteomes": 86, "short_name": "DUF6190", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19689", "structures": 2, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000896) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the cycloserine biosynthetic gene cluster from Streptomyces lavendulae subsp. lavendulae [[cite:PUB00098976]].", "domain_architectures": 2, "interpro_id": "IPR045772", "known_evidence_count": null, "matches": 92, "name": "Family of unknown function (DUF6225)", "partial_evidence_count": null, "pfam_id": "PF19735", "proteins": 91, "proteomes": 80, "short_name": "DUF6225", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19735", "structures": 0, "taxa": 153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 3, "interpro_id": "IPR046269", "known_evidence_count": null, "matches": 91, "name": "Family of unknown function (DUF6302)", "partial_evidence_count": null, "pfam_id": "PF19819", "proteins": 91, "proteomes": 76, "short_name": "DUF6302", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19819", "structures": 0, "taxa": 104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from Kinetoplastida. It is found on its own or in combination with [[pfam:PF00650]]. It is predicted adopt a UBA-like alpha-helical bundle.", "domain_architectures": 2, "interpro_id": "IPR055777", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF7353)", "partial_evidence_count": null, "pfam_id": "PF24044", "proteins": 91, "proteomes": 29, "short_name": "DUF7353", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24044", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of Lactobacillus proteins of unknown function. The predicted structure suggests these proteins contain two subdomains, with an N-terminal partly open beta barrel and C-terminal alpha/beta subdomain.", "domain_architectures": 1, "interpro_id": "IPR056096", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF7679)", "partial_evidence_count": null, "pfam_id": "PF24727", "proteins": 91, "proteomes": 79, "short_name": "DUF7679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24727", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in N-terminal in uncharacterised eukaryotic proteins. It is predicted to be composed of HEAT repeats. It is often found in combination with [pfam:PF25405].", "domain_architectures": 6, "interpro_id": "IPR058392", "known_evidence_count": null, "matches": 91, "name": "Repeat of unknown function (DUF8079)", "partial_evidence_count": null, "pfam_id": "PF26290", "proteins": 91, "proteomes": 56, "short_name": "DUF8079", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26290", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 82, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins found predominantly in the Halobacteria class of Archaea. The proteins containing this domain are primarily distributed among members of the Haloarculaceae and Haloferacaceae families. The domain is typically found in proteins ranging from 85 to 117 amino acids in length. The domain adopts a four helical bundle structure.", "domain_architectures": 1, "interpro_id": "IPR058414", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF8101)", "partial_evidence_count": null, "pfam_id": "PF26403", "proteins": 91, "proteomes": 91, "short_name": "DUF8101", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26403", "structures": 0, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains two pairs of highly conserved cysteine residues that are likely involved in metal coordination. This domain is predicted to fold into a structure which closely resembles domains members of the Zn(2)-Cys(6) binuclear cluster superfamily. Despite its conserved residues occupy equivalent spacial positions as the metal coordinating residues in Zn(2)-Cys(6) domains, this domain contains only four cysteines of six suggesting it can only coordinate one zinc atom.", "domain_architectures": 4, "interpro_id": "IPR059301", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF8257)", "partial_evidence_count": null, "pfam_id": "PF26785", "proteins": 91, "proteomes": 52, "short_name": "DUF8257", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26785", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from alphaproteobacteria. It is predicted to fold into an alpha/beta structure composed of a four-stranded beta-sheet and alpha-helix. It contains to highly conserved cysteine residues that are predicted to form disulfide bond bridging the alpha-helix and the beta-sheet. Besides the conserved cysteine residues, this domain contains a conserved NLxDP sequence motif which may have a functional role.", "domain_architectures": 1, "interpro_id": "IPR059309", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF8265)", "partial_evidence_count": null, "pfam_id": "PF26795", "proteins": 91, "proteomes": 68, "short_name": "DUF8265", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26795", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This Ig-like domain is found in uncharacterised bacterial proteins.", "domain_architectures": 5, "interpro_id": "IPR061517", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF8447)", "partial_evidence_count": null, "pfam_id": "PF28718", "proteins": 91, "proteomes": 74, "short_name": "DUF8447", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28718", "structures": 0, "taxa": 141, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several short Nucleopolyhedrovirus proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR009265", "known_evidence_count": null, "matches": 90, "name": "Nucleopolyhedrovirus protein of unknown function (DUF919)", "partial_evidence_count": null, "pfam_id": "PF06034", "proteins": 90, "proteomes": 90, "short_name": "DUF919", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06034", "structures": 0, "taxa": 229, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Domain based on 366-449 domain of PDB:3LM3 which is encoded by the BDI_3119 gene from Parabacteroides distasonis atcc 8503.", "domain_architectures": 2, "interpro_id": "IPR024335", "known_evidence_count": null, "matches": 90, "name": "Domain of Unknown Function with PDB structure (DUF3864)", "partial_evidence_count": null, "pfam_id": "PF12980", "proteins": 90, "proteomes": 77, "short_name": "DUF3864", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12980", "structures": 1, "taxa": 156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR024988", "known_evidence_count": null, "matches": 90, "name": "Domain of unknown function (DUF3890)", "partial_evidence_count": null, "pfam_id": "PF13029", "proteins": 90, "proteomes": 31, "short_name": "DUF3890", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13029", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 14 } }, "demotion_reasons": [], "description": "This family is found in Proteobacteria. The function is not known.", "domain_architectures": 4, "interpro_id": "IPR025385", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF4092)", "partial_evidence_count": null, "pfam_id": "PF13322", "proteins": 90, "proteomes": 76, "short_name": "DUF4092", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13322", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Pasteurellaceae.", "domain_architectures": 1, "interpro_id": "IPR035318", "known_evidence_count": null, "matches": 90, "name": "Family of unknown function (DUF5377)", "partial_evidence_count": null, "pfam_id": "PF17347", "proteins": 90, "proteomes": 90, "short_name": "DUF5377", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17347", "structures": 0, "taxa": 144, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Pasteurellaceae. Family members are predicted to have 3 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035333", "known_evidence_count": null, "matches": 90, "name": "Family of unknown function (DUF5389)", "partial_evidence_count": null, "pfam_id": "PF17364", "proteins": 90, "proteomes": 90, "short_name": "DUF5389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17364", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR040531", "known_evidence_count": null, "matches": 90, "name": "Domain of unknown function (DUF5623)", "partial_evidence_count": null, "pfam_id": "PF18536", "proteins": 90, "proteomes": 85, "short_name": "DUF5623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18536", "structures": 1, "taxa": 208, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. Structure prediction suggests these proteins are composed of a three stranded beta sheet packed against a pair of alpha helices.", "domain_architectures": 1, "interpro_id": "IPR055836", "known_evidence_count": null, "matches": 90, "name": "Domain of unknown function (DUF7413)", "partial_evidence_count": null, "pfam_id": "PF24185", "proteins": 90, "proteomes": 86, "short_name": "DUF7413", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24185", "structures": 0, "taxa": 195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins are likely to be phage derived. This domain likely forms a homodimeric structure composed of three beta strands provided by each monomer, with one strand swapped with the other monomer.", "domain_architectures": 2, "interpro_id": "IPR057653", "known_evidence_count": null, "matches": 90, "name": "Family of unknown function (DUF5983) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF25638", "proteins": 90, "proteomes": 53, "short_name": "DUF5983_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25638", "structures": 0, "taxa": 104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an alpha-helical domain from a family of uncharacterised proteins in the Halobacteria class of Archaea. The proteins containing this domain are predominantly found in members of the Haloferacaceae family, including genera such as Halonotius, Halobellus, and Halorubrum. The domain is typically found in proteins ranging from 209 to 263 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR058429", "known_evidence_count": null, "matches": 92, "name": "Domain of unknown function (DUF8116)", "partial_evidence_count": null, "pfam_id": "PF26426", "proteins": 90, "proteomes": 89, "short_name": "DUF8116", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26426", "structures": 0, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Eubacterium rectale gene EUBREC_1343. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14737), it appears to be upregulated in the presence of Bacteroides thetaiotaomicron vs when isolated in culture [[cite:PUB00056060]].", "domain_architectures": 1, "interpro_id": "IPR024540", "known_evidence_count": null, "matches": 89, "name": "Domain of unknown function (DUF3879)", "partial_evidence_count": null, "pfam_id": "PF12995", "proteins": 89, "proteomes": 39, "short_name": "DUF3879", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12995", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in bacteroidetes.", "domain_architectures": 2, "interpro_id": "IPR028072", "known_evidence_count": null, "matches": 91, "name": "Domain of unknown function (DUF4466)", "partial_evidence_count": null, "pfam_id": "PF14725", "proteins": 89, "proteomes": 88, "short_name": "DUF4466", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14725", "structures": 1, "taxa": 164, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in proteobacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046638", "known_evidence_count": null, "matches": 89, "name": "Family of unknown function (DUF6750)", "partial_evidence_count": null, "pfam_id": "PF20535", "proteins": 89, "proteomes": 64, "short_name": "DUF6750", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20535", "structures": 0, "taxa": 204, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised bacterial proteins. They are enriched in hydrophobic residues and are likely associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR054229", "known_evidence_count": null, "matches": 89, "name": "Family of unknown function (DUF6954)", "partial_evidence_count": null, "pfam_id": "PF22268", "proteins": 89, "proteomes": 89, "short_name": "DUF6954", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22268", "structures": 0, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha- helical structure.", "domain_architectures": 6, "interpro_id": "IPR057151", "known_evidence_count": null, "matches": 89, "name": "Domain of unknown function (DUF7829)", "partial_evidence_count": null, "pfam_id": "PF25167", "proteins": 89, "proteomes": 86, "short_name": "DUF7829", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25167", "structures": 0, "taxa": 206, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins which form a compact domain. Structure prediction of [swissprot:K2M825] suggests a highly confident homodimer (iPTM=0.93). This protein is found in a mixture of bacteria and phage.", "domain_architectures": 5, "interpro_id": "IPR057153", "known_evidence_count": null, "matches": 93, "name": "Family of unknown function (DUF7831)", "partial_evidence_count": null, "pfam_id": "PF25176", "proteins": 89, "proteomes": 83, "short_name": "DUF7831", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25176", "structures": 0, "taxa": 260, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 71, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Bacteroidetes.", "domain_architectures": 2, "interpro_id": "IPR061637", "known_evidence_count": null, "matches": 89, "name": "Domain of unknown function (DUF8576)", "partial_evidence_count": null, "pfam_id": "PF29636", "proteins": 89, "proteomes": 88, "short_name": "DUF8576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29636", "structures": 1, "taxa": 164, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Staphylococcus aureus and related bacteriophage proteins of around 65 residues in length. The function of this family is unknown. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 1, "interpro_id": "IPR009999", "known_evidence_count": null, "matches": 88, "name": "Protein of unknown function (DUF1514)", "partial_evidence_count": null, "pfam_id": "PF07438", "proteins": 88, "proteomes": 77, "short_name": "DUF1514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07438", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 79, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 321 and 791 amino acids in length. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR031958", "known_evidence_count": null, "matches": 93, "name": "Domain of unknown function (DUF4778)", "partial_evidence_count": null, "pfam_id": "PF16008", "proteins": 88, "proteomes": 25, "short_name": "DUF4778", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16008", "structures": 0, "taxa": 93, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is found in Euryarchaeota, predominantly in Methanomicrobia and Archaeoglobi. No known function for this family has been demonstrated.", "domain_architectures": 1, "interpro_id": "IPR035258", "known_evidence_count": null, "matches": 88, "name": "Family of unknown function (DUF5350)", "partial_evidence_count": null, "pfam_id": "PF17299", "proteins": 88, "proteomes": 87, "short_name": "DUF5350", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17299", "structures": 3, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001589) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the exopolysaccharides biosynthetic gene cluster from Burkholderia cenocepacia J2315 [[cite:PUB00099462]]. This family appears to be predominantly found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR046303", "known_evidence_count": null, "matches": 88, "name": "Family of unknown function (DUF6418)", "partial_evidence_count": null, "pfam_id": "PF19982", "proteins": 88, "proteomes": 86, "short_name": "DUF6418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19982", "structures": 0, "taxa": 204, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This putative domain is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 200 amino acids in length. This domain appears to belong to the NTF2 superfamily.", "domain_architectures": 3, "interpro_id": "IPR046563", "known_evidence_count": null, "matches": 90, "name": "Domain of unknown function (DUF6715)", "partial_evidence_count": null, "pfam_id": "PF20462", "proteins": 88, "proteomes": 85, "short_name": "DUF6715", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20462", "structures": 0, "taxa": 195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from archaea. The proteins in this family are primarily found in the Halobacteria class, including members of the Halorubrum and Haloferax genera. The family is also present in various viruses that infect these archaea. The proteins are typically around 250 to 280 amino acids in length. Many of these proteins are predicted to be membrane-associated, featuring one or more transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR058438", "known_evidence_count": null, "matches": 88, "name": "Family of unknown function (DUF8125)", "partial_evidence_count": null, "pfam_id": "PF26446", "proteins": 88, "proteomes": 72, "short_name": "DUF8125", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26446", "structures": 0, "taxa": 156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of a family of uncharacterised proteins from archaea. The proteins in this family are primarily found in the Halobacteria class, including members of the Halorubrum and Haloferax genera. The family is also present in various viruses that infect these archaea. The proteins are typically around 250 to 280 amino acids in length. Many of these proteins are predicted to be membrane-associated, featuring one or more transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR058439", "known_evidence_count": null, "matches": 88, "name": "Domain of unknown function (DUF8125) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26447", "proteins": 88, "proteomes": 67, "short_name": "DUF8126", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26447", "structures": 0, "taxa": 146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 82, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of hypothetical archaeal proteins.", "domain_architectures": 2, "interpro_id": "IPR007503", "known_evidence_count": null, "matches": 101, "name": "Protein of unknown function (DUF530)", "partial_evidence_count": null, "pfam_id": "PF04409", "proteins": 87, "proteomes": 87, "short_name": "DUF530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04409", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 372 to 530 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR021956", "known_evidence_count": null, "matches": 87, "name": "Protein of unknown function (DUF3573)", "partial_evidence_count": null, "pfam_id": "PF12097", "proteins": 87, "proteomes": 27, "short_name": "DUF3573", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12097", "structures": 0, "taxa": 56, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 60 amino acids in length. There is a single completely conserved Y residue that may be functionally important. This domain is from a bacterial lipoprotein, a major virulence factor in Gram negative bacteria.", "domain_architectures": 1, "interpro_id": "IPR020961", "known_evidence_count": null, "matches": 87, "name": "Bacterial lipoprotein", "partial_evidence_count": null, "pfam_id": "PF12182", "proteins": 87, "proteomes": 71, "short_name": "DUF3642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12182", "structures": 2, "taxa": 106, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Eubacterium rectale gene EUBREC_0973. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14737). it appears to be upregulated in the presence of Bacteroides thetaiotaomicron vs when isolated in culture [[cite:PUB00056060]].", "domain_architectures": 1, "interpro_id": "IPR024538", "known_evidence_count": null, "matches": 87, "name": "Domain of unknown function (DUF3878)", "partial_evidence_count": null, "pfam_id": "PF12994", "proteins": 87, "proteomes": 86, "short_name": "DUF3878", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12994", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in fungi. Proteins in this family are typically between 172 and 313 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031426", "known_evidence_count": null, "matches": 90, "name": "Domain of unknown function (DUF4667)", "partial_evidence_count": null, "pfam_id": "PF15700", "proteins": 87, "proteomes": 67, "short_name": "DUF4667", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15700", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in bacteroides. Proteins in this family are around 600 amino acids in length. This family is related to glycosyl hydrolase family 99.", "domain_architectures": 16, "interpro_id": "IPR032178", "known_evidence_count": null, "matches": 89, "name": "Domain of unknown function (DUF5010)", "partial_evidence_count": null, "pfam_id": "PF16402", "proteins": 87, "proteomes": 73, "short_name": "DUF5010", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16402", "structures": 0, "taxa": 222, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 200 in length and is mainly found in Eubacterium and Clostridium. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032209", "known_evidence_count": null, "matches": 87, "name": "Domain of unknown function (DUF5028)", "partial_evidence_count": null, "pfam_id": "PF16431", "proteins": 87, "proteomes": 66, "short_name": "DUF5028", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16431", "structures": 0, "taxa": 163, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000666) is described by MIBiG as an example of the following biosynthetic class, terpene.", "domain_architectures": 1, "interpro_id": "IPR046023", "known_evidence_count": null, "matches": 87, "name": "Family of unknown function (DUF5980)", "partial_evidence_count": null, "pfam_id": "PF19410", "proteins": 87, "proteomes": 77, "short_name": "DUF5980", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19410", "structures": 0, "taxa": 118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a family of proteins that are functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 340 and 435 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR046555", "known_evidence_count": null, "matches": 87, "name": "Domain of unknown function (DUF6709)", "partial_evidence_count": null, "pfam_id": "PF20456", "proteins": 87, "proteomes": 78, "short_name": "DUF6709", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20456", "structures": 0, "taxa": 202, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in the central region of a group of uncharacterised sequences from bacteria, found after the FtsH ternary system domain X7 at the N-terminal.", "domain_architectures": 5, "interpro_id": "IPR061649", "known_evidence_count": null, "matches": 87, "name": "Domain of unknown function (DUF8588)", "partial_evidence_count": null, "pfam_id": "PF29808", "proteins": 87, "proteomes": 78, "short_name": "DUF8588", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29808", "structures": 0, "taxa": 186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 86, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021442", "known_evidence_count": null, "matches": 86, "name": "Protein of unknown function (DUF3091)", "partial_evidence_count": null, "pfam_id": "PF11291", "proteins": 86, "proteomes": 2, "short_name": "DUF3091", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11291", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins found in firmicutes and high GC Gram+ bacteria associated with human and animal guts. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR032327", "known_evidence_count": null, "matches": 86, "name": "Domain of unknown function (DUF4854)", "partial_evidence_count": null, "pfam_id": "PF16146", "proteins": 86, "proteomes": 75, "short_name": "DUF4854", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16146", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001992) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a protein from the thioguanine biosynthetic gene cluster from Erwinia amylovora CFBP1430 [[cite:PUB00099374]].", "domain_architectures": 1, "interpro_id": "IPR046066", "known_evidence_count": null, "matches": 86, "name": "Family of unknown function (DUF6024)", "partial_evidence_count": null, "pfam_id": "PF19488", "proteins": 86, "proteomes": 85, "short_name": "DUF6024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19488", "structures": 1, "taxa": 146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Most of these Rhodopirellula baltica hypothetical proteins also match [pfam:PF07619].", "domain_architectures": 25, "interpro_id": "IPR046518", "known_evidence_count": null, "matches": 107, "name": "Domain of unknown function (DUF1583_N)", "partial_evidence_count": null, "pfam_id": "PF20407", "proteins": 86, "proteomes": 31, "short_name": "DUF1583_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20407", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 250 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046642", "known_evidence_count": null, "matches": 86, "name": "Domain of unknown function (DUF6754)", "partial_evidence_count": null, "pfam_id": "PF20539", "proteins": 86, "proteomes": 76, "short_name": "DUF6754", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20539", "structures": 0, "taxa": 216, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of archaeal sequences of unknown function.", "domain_architectures": 1, "interpro_id": "IPR055810", "known_evidence_count": null, "matches": 86, "name": "Family of unknown function (DUF7386)", "partial_evidence_count": null, "pfam_id": "PF24111", "proteins": 86, "proteomes": 71, "short_name": "DUF7386", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24111", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from nematodes. It is predicted to adopt a globular structure consisting of a four-stranded antiparallel beta-sheet and two alpha-helices packed on one side of it.", "domain_architectures": 11, "interpro_id": "IPR056054", "known_evidence_count": null, "matches": 86, "name": "Domain of unknown function (DUF7637)", "partial_evidence_count": null, "pfam_id": "PF24643", "proteins": 86, "proteomes": 29, "short_name": "DUF7637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24643", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain family of uncharacterised proteins found in halobacteria. These proteins show some structural similarity to RadA proteins in their P-loop domain, however this family of proteins lack the P-loop consensus motifs.", "domain_architectures": 1, "interpro_id": "IPR058389", "known_evidence_count": null, "matches": 86, "name": "Domain of unknown function (DUF8076)", "partial_evidence_count": null, "pfam_id": "PF26277", "proteins": 86, "proteomes": 74, "short_name": "DUF8076", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26277", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins are predominantly found in the Halobacteria class, including genera such as Halorubrum, Haloferax, and Halogeometricum. The domain is typically 60 to 70 amino acids in length. Proteins containing this domain contain two putative transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058433", "known_evidence_count": null, "matches": 86, "name": "Family of unknown function (DUF8120)", "partial_evidence_count": null, "pfam_id": "PF26439", "proteins": 86, "proteomes": 79, "short_name": "DUF8120", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26439", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Spirochaetia lineage. It is predicted to fold into a complex alpha/beta structure resembling open beta-barrel decorated with alpha/helices.", "domain_architectures": 1, "interpro_id": "IPR059339", "known_evidence_count": null, "matches": 86, "name": "Domain of unknown function (DUF8295)", "partial_evidence_count": null, "pfam_id": "PF26945", "proteins": 86, "proteomes": 86, "short_name": "DUF8295", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26945", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a number of hypothetical proteins from Escherichia coli O157:H7 and Salmonella typhi. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR010557", "known_evidence_count": null, "matches": 85, "name": "Protein of unknown function (DUF1133)", "partial_evidence_count": null, "pfam_id": "PF06576", "proteins": 85, "proteomes": 76, "short_name": "DUF1133", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06576", "structures": 0, "taxa": 142, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the C-terminus of a number of Arabidopsis thaliana hypothetical proteins of unknown function. Family members contain a conserved DFD motif.", "domain_architectures": 12, "interpro_id": "IPR009596", "known_evidence_count": null, "matches": 87, "name": "Protein of unknown function (DUF1204)", "partial_evidence_count": null, "pfam_id": "PF06721", "proteins": 85, "proteomes": 12, "short_name": "DUF1204", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06721", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 83, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Caenorhabditis elegans proteins of around 70-75 residues in length. The function of this family is unknown.", "domain_architectures": 5, "interpro_id": "IPR009853", "known_evidence_count": null, "matches": 87, "name": "Protein of unknown function (DUF1412)", "partial_evidence_count": null, "pfam_id": "PF07203", "proteins": 85, "proteomes": 13, "short_name": "DUF1412", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07203", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Several Rhodopirellula baltica proteins share this probable domain. Most of these proteins are predicted to be secreted or membrane-associated.", "domain_architectures": 24, "interpro_id": "IPR022660", "known_evidence_count": null, "matches": 105, "name": "Protein of unknown function (DUF1581)", "partial_evidence_count": null, "pfam_id": "PF07619", "proteins": 85, "proteomes": 30, "short_name": "DUF1581", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07619", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bradyrhizobiaceae. Family members contain 3 or 4 predicted trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035399", "known_evidence_count": null, "matches": 85, "name": "Family of unknown function (DUF5413)", "partial_evidence_count": null, "pfam_id": "PF17434", "proteins": 85, "proteomes": 85, "short_name": "DUF5413", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17434", "structures": 0, "taxa": 106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Bacteroidetes. Proteins in this family are typically between 293 and 398 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046106", "known_evidence_count": null, "matches": 86, "name": "Family of unknown function (DUF6043)", "partial_evidence_count": null, "pfam_id": "PF19509", "proteins": 85, "proteomes": 59, "short_name": "DUF6043", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19509", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is mainly found in bacteria, and is typically between 120 and 180 amino acids in length. There are two highly conserved residues, an aspartate and a tryptophan, and a NP conserved motif.", "domain_architectures": 3, "interpro_id": "IPR046679", "known_evidence_count": null, "matches": 85, "name": "Family of unknown function (DUF6549)", "partial_evidence_count": null, "pfam_id": "PF20186", "proteins": 85, "proteomes": 73, "short_name": "DUF6549", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20186", "structures": 0, "taxa": 193, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteriophages, mainly in Myovirus. Proteins in this family are approximately 80 amino acids in length. There are two conserved sequence motifs: EP and PxxxxxxxY.", "domain_architectures": 1, "interpro_id": "IPR046691", "known_evidence_count": null, "matches": 85, "name": "Family of unknown function (DUF6561)", "partial_evidence_count": null, "pfam_id": "PF20198", "proteins": 85, "proteomes": 69, "short_name": "DUF6561", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20198", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of short archaeal proteins. Members are predicted to adopt an alpha-beta configuration.", "domain_architectures": 1, "interpro_id": "IPR055948", "known_evidence_count": null, "matches": 85, "name": "Family of unknown function (DUF7526)", "partial_evidence_count": null, "pfam_id": "PF24370", "proteins": 85, "proteomes": 83, "short_name": "DUF7526", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24370", "structures": 0, "taxa": 128, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised archaeal proteins, including HVO_1906 ([swissprot:D4GTD9]) from Haloferax volcanii. It has several conserved residues R, W and H.", "domain_architectures": 4, "interpro_id": "IPR061657", "known_evidence_count": null, "matches": 85, "name": "Domain of unknown function (DUF8596)", "partial_evidence_count": null, "pfam_id": "PF29882", "proteins": 85, "proteomes": 84, "short_name": "DUF8596", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29882", "structures": 0, "taxa": 197, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of uncharacterized proteins around 140 residues in length and is mainly found in various Legionella pneumophila and longbeachae species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032540", "known_evidence_count": null, "matches": 84, "name": "Domain of unknown function (DUF4949)", "partial_evidence_count": null, "pfam_id": "PF16307", "proteins": 84, "proteomes": 56, "short_name": "DUF4949", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16307", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 150 residues in length and is mainly found in various Leptospira, Pseudomonas, Stenotrophomonas and Desulfovibrio species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032537", "known_evidence_count": null, "matches": 84, "name": "Domian of unknown function (DUF4952)", "partial_evidence_count": null, "pfam_id": "PF16310", "proteins": 84, "proteomes": 83, "short_name": "DUF4952", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16310", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR035335", "known_evidence_count": null, "matches": 84, "name": "Family of unknown function (DUF5397)", "partial_evidence_count": null, "pfam_id": "PF17375", "proteins": 84, "proteomes": 81, "short_name": "DUF5397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17375", "structures": 1, "taxa": 218, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 78, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 200 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046598", "known_evidence_count": null, "matches": 84, "name": "Family of unknown function (DUF6657)", "partial_evidence_count": null, "pfam_id": "PF20362", "proteins": 84, "proteomes": 83, "short_name": "DUF6657", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20362", "structures": 0, "taxa": 220, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in CHAT domain-containing protein, such as SwissProt:A0A100JVW6, from Streptomyces scabiei. This domain may be found in association with TCAD7 ([pfam:PF19973]) and CHAT ([pfam:PF12770]) domains.", "domain_architectures": 9, "interpro_id": "IPR055787", "known_evidence_count": null, "matches": 84, "name": "Domain of unknown function (DUF7363)", "partial_evidence_count": null, "pfam_id": "PF24063", "proteins": 84, "proteomes": 81, "short_name": "DUF7363", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24063", "structures": 0, "taxa": 199, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from nematodes. These proteins contain a semi-conserved PPChHPGQ motif (where h is a hydrophobic residue) and are predicted to fold into a incomplete beta-sandwich.", "domain_architectures": 32, "interpro_id": "IPR055928", "known_evidence_count": null, "matches": 84, "name": "Domain of unknown function (DUF7505)", "partial_evidence_count": null, "pfam_id": "PF24337", "proteins": 84, "proteomes": 69, "short_name": "DUF7505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24337", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins mainly from tailed bacteriophages.", "domain_architectures": 1, "interpro_id": "IPR056134", "known_evidence_count": null, "matches": 84, "name": "Family of unknown function (DUF7717)", "partial_evidence_count": null, "pfam_id": "PF24835", "proteins": 84, "proteomes": 84, "short_name": "DUF7717", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24835", "structures": 0, "taxa": 248, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins in this family are predominantly found in the class Halobacteria, which are known for their adaptation to high-salt environments. The proteins in this family are generally around 130 amino acids in length. Structure prediction with AlphaFold 3 suggests that proteins in this family may form intertwined homodimers [swissprot:B9LW05] (ipTM=0.68 pTM=0.69).", "domain_architectures": 1, "interpro_id": "IPR058428", "known_evidence_count": null, "matches": 84, "name": "Domain of unknown function (DUF8115)", "partial_evidence_count": null, "pfam_id": "PF26424", "proteins": 84, "proteomes": 68, "short_name": "DUF8115", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26424", "structures": 0, "taxa": 160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised bacterial proteins which are predicted to be composed of transmembrane alpha- helices.", "domain_architectures": 1, "interpro_id": "IPR061840", "known_evidence_count": null, "matches": 84, "name": "Family of unknown function (DUF8779)", "partial_evidence_count": null, "pfam_id": "PF31039", "proteins": 84, "proteomes": 82, "short_name": "DUF8779", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31039", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found in 1 to 3 copies in archaebacterial proteins. The function of the domain is unknown. This family appears to be expanded in Archaeoglobus fulgidus.", "domain_architectures": 3, "interpro_id": "IPR002572", "known_evidence_count": null, "matches": 101, "name": "Domain of unknown function DUF22", "partial_evidence_count": null, "pfam_id": "PF01629", "proteins": 83, "proteomes": 72, "short_name": "DUF22", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01629", "structures": 0, "taxa": 153, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family may be related to the FARP (FMRFamide) family, [pfam:PF01581].", "domain_architectures": 25, "interpro_id": "IPR005529", "known_evidence_count": null, "matches": 298, "name": "Protein of unknown function (DUF321)", "partial_evidence_count": null, "pfam_id": "PF03778", "proteins": 83, "proteomes": 8, "short_name": "DUF321", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03778", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical phage and bacterial proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009520", "known_evidence_count": null, "matches": 83, "name": "Protein of unknown function (DUF1140)", "partial_evidence_count": null, "pfam_id": "PF06600", "proteins": 83, "proteomes": 74, "short_name": "DUF1140", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06600", "structures": 0, "taxa": 181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. These proteins are predicted to adopt structure similar to the members of Zn-dependent exopeptidases clan.", "domain_architectures": 1, "interpro_id": "IPR019218", "known_evidence_count": null, "matches": 83, "name": "Uncharacterized protein conserved in archaea (DUF2119)", "partial_evidence_count": null, "pfam_id": "PF09892", "proteins": 83, "proteomes": 80, "short_name": "DUF2119", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09892", "structures": 0, "taxa": 145, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 81, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018665", "known_evidence_count": null, "matches": 83, "name": "RecB-family nuclease (DUF2122)", "partial_evidence_count": null, "pfam_id": "PF09895", "proteins": 83, "proteomes": 83, "short_name": "DUF2122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09895", "structures": 0, "taxa": 200, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of bacterial proteins that adopt a beta-sandwich domain. The function of these proteins is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR049197", "known_evidence_count": null, "matches": 83, "name": "Domain of unknown function (DUF6864)", "partial_evidence_count": null, "pfam_id": "PF21732", "proteins": 83, "proteomes": 83, "short_name": "DUF6864", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21732", "structures": 0, "taxa": 202, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in bacterial proteins. It is probably distantly related to dodecin. It is predicted to adopt a simple fold consisting of a core of 3 strands, forming a curved sheet, and two short helices.", "domain_architectures": 3, "interpro_id": "IPR053839", "known_evidence_count": null, "matches": 83, "name": "Domain of unknown function (DUF6926)", "partial_evidence_count": null, "pfam_id": "PF21977", "proteins": 83, "proteomes": 64, "short_name": "DUF6926", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21977", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small transmembrane protein found in Lactococcus 936-type phages. The function of this protein is unknown. It contains a single transmembrane helix.", "domain_architectures": 1, "interpro_id": "IPR055610", "known_evidence_count": null, "matches": 83, "name": "Family of unknown function (DUF7186)", "partial_evidence_count": null, "pfam_id": "PF23815", "proteins": 83, "proteomes": 81, "short_name": "DUF7186", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23815", "structures": 0, "taxa": 179, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised protein PM0657 and its paralogue PM1082 from Pasteurella multocida and related bacterial proteins. It is predicted to adopt a alpha/beta globular structure consisting of a central antiparallel beta- sheet and helices packed on both sides.", "domain_architectures": 2, "interpro_id": "IPR056723", "known_evidence_count": null, "matches": 83, "name": "Domain of unknown function (DUF7821)", "partial_evidence_count": null, "pfam_id": "PF25134", "proteins": 83, "proteomes": 75, "short_name": "DUF7821", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25134", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain has a restriction endonuclease-like structure, suggesting this protein may function as an endonuclease.", "domain_architectures": 3, "interpro_id": "IPR058992", "known_evidence_count": null, "matches": 83, "name": "DUF7961 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF25902", "proteins": 83, "proteomes": 77, "short_name": "DUF7961_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25902", "structures": 0, "taxa": 153, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in the middle region of a group of bacterial proteins, functionally uncharacterised. It is found associated with [pfam:PF12358] at the N-terminal and [pfam:PF30174] at the C-terminal. It may adopt an helical fold.", "domain_architectures": 4, "interpro_id": "IPR061672", "known_evidence_count": null, "matches": 83, "name": "Domain of unknown function (DUF8611)", "partial_evidence_count": null, "pfam_id": "PF30175", "proteins": 83, "proteomes": 82, "short_name": "DUF8611", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30175", "structures": 0, "taxa": 252, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical bacterial proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018696", "known_evidence_count": null, "matches": 82, "name": "Uncharacterized protein conserved in bacteria (DUF2195)", "partial_evidence_count": null, "pfam_id": "PF09961", "proteins": 82, "proteomes": 76, "short_name": "DUF2195", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09961", "structures": 0, "taxa": 166, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. There is a conserved TTC sequence motif.", "domain_architectures": 2, "interpro_id": "IPR031882", "known_evidence_count": null, "matches": 82, "name": "Domain of unknown function (DUF4762)", "partial_evidence_count": null, "pfam_id": "PF15959", "proteins": 82, "proteomes": 74, "short_name": "DUF4762", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15959", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function is associated with the tenuecyclamide A biosynthetic gene cluster.", "domain_architectures": 1, "interpro_id": "IPR044050", "known_evidence_count": null, "matches": 82, "name": "Family of unknown function (DUF5837)", "partial_evidence_count": null, "pfam_id": "PF19155", "proteins": 82, "proteomes": 18, "short_name": "DUF5837", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19155", "structures": 4, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 72, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal alpha+beta domain found in DUF6866 family proteins. The function of these proteins is unknown. Proteins in this family are primarily found in Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR049199", "known_evidence_count": null, "matches": 82, "name": "Family of unknown function (DUF6866) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF21739", "proteins": 82, "proteomes": 82, "short_name": "DUF6866_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21739", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 72, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal alpha-helical domain found in DUF6866 family proteins. The function of these proteins is unknown. Proteins in this family are primarily found in Proteobacteria.", "domain_architectures": 2, "interpro_id": "IPR049200", "known_evidence_count": null, "matches": 82, "name": "Family of unknown function (DUF6866) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF21740", "proteins": 82, "proteomes": 82, "short_name": "DUF6866_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21740", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found various uncharacterised bacterial proteins that according to ECOD adopts a profilin-like fold.", "domain_architectures": 1, "interpro_id": "IPR055702", "known_evidence_count": null, "matches": 82, "name": "Profilin-like domain of unknown function (DUF7278)", "partial_evidence_count": null, "pfam_id": "PF23944", "proteins": 82, "proteomes": 82, "short_name": "DUF7278", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23944", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found to the C-terminus of a restriction endonuclease-like domain [pfam:PF25902]. Many members of this family contain two copies of this domain. The structure of the domain forms a small partial beta barrel.", "domain_architectures": 4, "interpro_id": "IPR058993", "known_evidence_count": null, "matches": 128, "name": "DUF7961 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF25903", "proteins": 82, "proteomes": 76, "short_name": "DUF7961_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25903", "structures": 0, "taxa": 149, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 77, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 1, "interpro_id": "IPR058378", "known_evidence_count": null, "matches": 82, "name": "Family of unknown function (DUF8065)", "partial_evidence_count": null, "pfam_id": "PF26261", "proteins": 82, "proteomes": 66, "short_name": "DUF8065", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26261", "structures": 0, "taxa": 132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins from pseudomonadati and bacillati species.", "domain_architectures": 1, "interpro_id": "IPR061537", "known_evidence_count": null, "matches": 82, "name": "Domain of unknown function (DUF8467)", "partial_evidence_count": null, "pfam_id": "PF28812", "proteins": 82, "proteomes": 74, "short_name": "DUF8467", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28812", "structures": 0, "taxa": 217, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small helical bundle domain of approximately 60-80 residues found in spirochaetes, including Treponema and Spirochaeta species. This domain is found in multi-domain proteins and is typically located between an N-terminal domain and a C-terminal domain. The function of this domain remains to be determined.", "domain_architectures": 5, "interpro_id": "IPR061584", "known_evidence_count": null, "matches": 82, "name": "Domain of unknown function (DUF8514)", "partial_evidence_count": null, "pfam_id": "PF29217", "proteins": 82, "proteomes": 82, "short_name": "DUF8514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29217", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 55 residues found in Cyanobacteriota. The domain contains conserved cysteine residues suggesting it may bind zinc. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061700", "known_evidence_count": null, "matches": 82, "name": "Domain of unknown function (DUF8639)", "partial_evidence_count": null, "pfam_id": "PF30572", "proteins": 82, "proteomes": 81, "short_name": "DUF8639", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30572", "structures": 0, "taxa": 232, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 80, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR018693", "known_evidence_count": null, "matches": 81, "name": "Uncharacterized protein conserved in archaea (DUF2192)", "partial_evidence_count": null, "pfam_id": "PF09958", "proteins": 81, "proteomes": 74, "short_name": "DUF2192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09958", "structures": 0, "taxa": 195, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found immediately downstream of SusE, a putative starch-processing family, [pfam:PF14292]. It is possible that this domain represents a substrate-binding site.", "domain_architectures": 12, "interpro_id": "IPR033404", "known_evidence_count": null, "matches": 85, "name": "Domain of unknown function (DUF5111)", "partial_evidence_count": null, "pfam_id": "PF17138", "proteins": 81, "proteomes": 80, "short_name": "DUF5111", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17138", "structures": 0, "taxa": 148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001593) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the ficellomycin biosynthetic gene cluster from Streptomyces ficellus [[cite:PUB00099388]].", "domain_architectures": 1, "interpro_id": "IPR046299", "known_evidence_count": null, "matches": 81, "name": "Family of unknown function (DUF6336)", "partial_evidence_count": null, "pfam_id": "PF19862", "proteins": 81, "proteomes": 71, "short_name": "DUF6336", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19862", "structures": 0, "taxa": 99, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001960) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the hiroshidine biosynthetic gene cluster from Streptomyces hiroshimensis [[cite:PUB00099455]].", "domain_architectures": 2, "interpro_id": "IPR045945", "known_evidence_count": null, "matches": 84, "name": "Family of unknown function (DUF6365)", "partial_evidence_count": null, "pfam_id": "PF19892", "proteins": 81, "proteomes": 57, "short_name": "DUF6365", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19892", "structures": 0, "taxa": 146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria, mainly Firmicutes and Actinobacteria. Proteins in this family are approximately 200 amino acids in length and contain the conserved motifs RY and DxF/Y", "domain_architectures": 2, "interpro_id": "IPR046683", "known_evidence_count": null, "matches": 82, "name": "Family of unknown function (DUF6553)", "partial_evidence_count": null, "pfam_id": "PF20190", "proteins": 81, "proteomes": 81, "short_name": "DUF6553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20190", "structures": 0, "taxa": 144, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is predominantly found in sequences from Apicomplexa. There are highly conserved motifs: NWxD, EDxxDH and GxGLAI/LLRQ.", "domain_architectures": 4, "interpro_id": "IPR049230", "known_evidence_count": null, "matches": 81, "name": "Domain of unknown function (DUF6827)", "partial_evidence_count": null, "pfam_id": "PF20715", "proteins": 81, "proteomes": 64, "short_name": "DUF6827", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20715", "structures": 2, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small bacterial and archaeal proteins that have an SH3 like barrel structure that shows most similarity to the C-terminal domain of the ribosomal chaperone RimP [pfam:PF17384].", "domain_architectures": 2, "interpro_id": "IPR054192", "known_evidence_count": null, "matches": 81, "name": "Domain of unknown function (DUF6897)", "partial_evidence_count": null, "pfam_id": "PF21838", "proteins": 81, "proteomes": 47, "short_name": "DUF6897", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21838", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of a group of uncharacterised sequences from actinobacteria.", "domain_architectures": 3, "interpro_id": "IPR055581", "known_evidence_count": null, "matches": 81, "name": "Family of unknown function (DUF7157)", "partial_evidence_count": null, "pfam_id": "PF23715", "proteins": 81, "proteomes": 81, "short_name": "DUF7157", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23715", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain from a large family of uncharacterised phage proteins that typically contain three domains.", "domain_architectures": 8, "interpro_id": "IPR055700", "known_evidence_count": null, "matches": 83, "name": "Domain of unknown function (DUF7276)", "partial_evidence_count": null, "pfam_id": "PF23941", "proteins": 81, "proteomes": 9, "short_name": "DUF7276", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23941", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 76, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from archaea. Members are predicted to adopt a mainly alpha structure.", "domain_architectures": 1, "interpro_id": "IPR055961", "known_evidence_count": null, "matches": 81, "name": "Family of unknown function (DUF7539)", "partial_evidence_count": null, "pfam_id": "PF24383", "proteins": 81, "proteomes": 64, "short_name": "DUF7539", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24383", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins generally have an N-terminal transmembrane helix followed by a small small domain. This domain is also found at the C-terminus of a methyltransferase protein A0A4U3MRG3.", "domain_architectures": 2, "interpro_id": "IPR058339", "known_evidence_count": null, "matches": 81, "name": "Family of unknown function (DUF8026)", "partial_evidence_count": null, "pfam_id": "PF26069", "proteins": 81, "proteomes": 74, "short_name": "DUF8026", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26069", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains four pairs of highly conserved cysteine residues that may be involved in metal coordination. It is predicted to contain two zinc beta ribbon domains with one domain inserted into the other.", "domain_architectures": 1, "interpro_id": "IPR059299", "known_evidence_count": null, "matches": 81, "name": "Domain of unknown function (DUF8255)", "partial_evidence_count": null, "pfam_id": "PF26783", "proteins": 81, "proteomes": 57, "short_name": "DUF8255", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26783", "structures": 0, "taxa": 223, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain found in uncharacterised proteins from spirochaetes, predominantly from Treponema species. The domain is approximately 110 residues in length. This domain is found in combination with a C-terminal domain ([pfam:PF29207]) in proteins exclusive to spirochaetes. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061580", "known_evidence_count": null, "matches": 81, "name": "Domain of unknown function (DUF8510)", "partial_evidence_count": null, "pfam_id": "PF29208", "proteins": 81, "proteomes": 81, "short_name": "DUF8510", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29208", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 75, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of hypothetical Archaeal proteins.", "domain_architectures": 3, "interpro_id": "IPR007509", "known_evidence_count": null, "matches": 91, "name": "Protein of unknown function (DUF515)", "partial_evidence_count": null, "pfam_id": "PF04415", "proteins": 80, "proteomes": 79, "short_name": "DUF515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04415", "structures": 0, "taxa": 148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 74, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a pair of structurally similar domains with one nested within the other. Each domain has pseudo-thteefold symmetry. This family is found fused to a copper-binding protein at the C-terminus, family Copper-bind, [pfam:PF00127]. Its function is not known, and it is found in the Halobacteriaceae family in Archaea.", "domain_architectures": 3, "interpro_id": "IPR032445", "known_evidence_count": null, "matches": 81, "name": "Domain of unknown function (DUF5059)", "partial_evidence_count": null, "pfam_id": "PF16502", "proteins": 80, "proteomes": 78, "short_name": "DUF5059", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16502", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 134 and 164 amino acids in length. This family contains an N-terminal predicted transmembrane helix and a negatively charged C-terminus.", "domain_architectures": 1, "interpro_id": "IPR046654", "known_evidence_count": null, "matches": 80, "name": "Family of unknown function (DUF6672)", "partial_evidence_count": null, "pfam_id": "PF20377", "proteins": 80, "proteomes": 79, "short_name": "DUF6672", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20377", "structures": 0, "taxa": 194, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small phage proteins found in a variety of mycobacteriophage genomes. The family members are typically around 70-75 amino acids in length. The function of these proteins is currently unknown.", "domain_architectures": 2, "interpro_id": "IPR055665", "known_evidence_count": null, "matches": 80, "name": "Domain of unknown function (DUF7241)", "partial_evidence_count": null, "pfam_id": "PF23889", "proteins": 80, "proteomes": 79, "short_name": "DUF7241", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23889", "structures": 0, "taxa": 198, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of proteins. Structure prediction suggests these proteins form a four stranded beta sheet with a helix packed on one side. Structure prediction also suggests a confident dimer. The structure shows some weak similarity to large ribosomal subunit protein eL38.", "domain_architectures": 1, "interpro_id": "IPR055837", "known_evidence_count": null, "matches": 80, "name": "Domain of unknown function (DUF7414)", "partial_evidence_count": null, "pfam_id": "PF24186", "proteins": 80, "proteomes": 80, "short_name": "DUF7414", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24186", "structures": 0, "taxa": 190, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 72, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins are primarily found in the class Halobacteria, which includes families such as Halobacteriaceae and Haloarculaceae. The domain is approximately 65-75 amino acids in length and is predicted to contain two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058436", "known_evidence_count": null, "matches": 80, "name": "Domain of unknown function (DUF8123)", "partial_evidence_count": null, "pfam_id": "PF26444", "proteins": 80, "proteomes": 80, "short_name": "DUF8123", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26444", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from the Lyme disease spirochete Borrelia burgdorferi.", "domain_architectures": 2, "interpro_id": "IPR008478", "known_evidence_count": null, "matches": 83, "name": "Borrelia burgdorferi protein of unknown function (DUF759)", "partial_evidence_count": null, "pfam_id": "PF05537", "proteins": 79, "proteomes": 25, "short_name": "DUF759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05537", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins has no known function. It has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR021461", "known_evidence_count": null, "matches": 79, "name": "Protein of unknown function (DUF3113)", "partial_evidence_count": null, "pfam_id": "PF11310", "proteins": 79, "proteomes": 75, "short_name": "DUF3113", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11310", "structures": 0, "taxa": 165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000967) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the calyculin A biosynthetic gene cluster from uncultured Candidatus Entotheonella sp. [[cite:PUB00098893]]. This family appears to be predominantly found in proteobacteria and cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR045650", "known_evidence_count": null, "matches": 79, "name": "Family of unknown function (DUF6399)", "partial_evidence_count": null, "pfam_id": "PF19936", "proteins": 79, "proteomes": 38, "short_name": "DUF6399", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19936", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in phages, and is approximately 60 amino acids in length. It contains the conserved sequences WSxxxLTxY and DPTFIASVFTG.", "domain_architectures": 1, "interpro_id": "IPR045610", "known_evidence_count": null, "matches": 79, "name": "Domain of unknown function (DUF6450)", "partial_evidence_count": null, "pfam_id": "PF20048", "proteins": 79, "proteomes": 77, "short_name": "DUF6450", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20048", "structures": 0, "taxa": 235, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is predicted to fold into an alpha/beta structure composed of a five stranded beta-sheet and alpha-helices packed on one side of it. It is preceded by a transmembrane domain.", "domain_architectures": 8, "interpro_id": "IPR059432", "known_evidence_count": null, "matches": 83, "name": "Domain of unknown function (DUF8388)", "partial_evidence_count": null, "pfam_id": "PF28383", "proteins": 79, "proteomes": 19, "short_name": "DUF8388", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28383", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved domain of unknown function found in the Spirochaetes, including species of Treponema, Borrelia, and Spirochaeta. The domain is approximately 150-200 residues long. Analysis of AlphaFold models reveals this domain is typically followed by a larger C-terminal domain (approximately 200-280 residues) that shares no significant overlap with other Pfam families. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061585", "known_evidence_count": null, "matches": 79, "name": "Domain of unknown function (DUF8515)", "partial_evidence_count": null, "pfam_id": "PF29220", "proteins": 79, "proteomes": 79, "short_name": "DUF8515", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29220", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain found preceding the Peptidase_M23 domain in spirochaetes, particularly Treponema species. The domain consists of a pair of long alpha helices and is approximately 115 residues in length. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061586", "known_evidence_count": null, "matches": 79, "name": "Domain of unknown function (DUF8516)", "partial_evidence_count": null, "pfam_id": "PF29222", "proteins": 79, "proteomes": 77, "short_name": "DUF8516", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29222", "structures": 0, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein family found in Pseudomonas and related gammaproteobacteria. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061646", "known_evidence_count": null, "matches": 79, "name": "Family of unknown function (DUF8585)", "partial_evidence_count": null, "pfam_id": "PF29794", "proteins": 79, "proteomes": 77, "short_name": "DUF8585", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29794", "structures": 0, "taxa": 156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharcaterised proteins mainly from Leptospira lineage. It shares similarity with known C-type lectin fold domains.", "domain_architectures": 3, "interpro_id": "IPR061841", "known_evidence_count": null, "matches": 79, "name": "Domain of unknown function (DUF8780)", "partial_evidence_count": null, "pfam_id": "PF31040", "proteins": 79, "proteomes": 75, "short_name": "DUF8780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31040", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 193 and 612 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR022115", "known_evidence_count": null, "matches": 78, "name": "Protein of unknown function (DUF3654)", "partial_evidence_count": null, "pfam_id": "PF12376", "proteins": 78, "proteomes": 4, "short_name": "DUF3654", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12376", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 110 residues in length and is mainly found in various Staphylococcus aureus species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032613", "known_evidence_count": null, "matches": 78, "name": "Domain of unknown function (DUF4889)", "partial_evidence_count": null, "pfam_id": "PF16230", "proteins": 78, "proteomes": 67, "short_name": "DUF4889", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16230", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Rhabditida.", "domain_architectures": 3, "interpro_id": "IPR020376", "known_evidence_count": null, "matches": 79, "name": "Family of unknown function (DUF5380)", "partial_evidence_count": null, "pfam_id": "PF17351", "proteins": 78, "proteomes": 40, "short_name": "DUF5380", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17351", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein family found in a range of bacteriophage including Phage T2. These proteins include a beta barrel domain. Many members of the family are annotated as IP4 internal head protein, although the source of evidence for this annotation was not found.", "domain_architectures": 1, "interpro_id": "IPR055835", "known_evidence_count": null, "matches": 78, "name": "Family of unknown function (DUF7412)", "partial_evidence_count": null, "pfam_id": "PF24183", "proteins": 78, "proteomes": 74, "short_name": "DUF7412", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24183", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins found in mycobacterial phage.", "domain_architectures": 1, "interpro_id": "IPR055852", "known_evidence_count": null, "matches": 78, "name": "Family of unknown function (DUF7429)", "partial_evidence_count": null, "pfam_id": "PF24206", "proteins": 78, "proteomes": 78, "short_name": "DUF7429", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24206", "structures": 0, "taxa": 188, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved domain approximately 100 residues long, multiple copies of which are found within hypothetical Ureaplasma parvum proteins of unknown function, as well as related species.", "domain_architectures": 15, "interpro_id": "IPR009849", "known_evidence_count": null, "matches": 209, "name": "Protein of unknown function (DUF1410)", "partial_evidence_count": null, "pfam_id": "PF07198", "proteins": 77, "proteomes": 18, "short_name": "DUF1410", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07198", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins found in bacteriophage particularly of the SA bacteriophages 11, Mu50B, family, homologous to phi-ETA orf16.", "domain_architectures": 1, "interpro_id": "IPR018918", "known_evidence_count": null, "matches": 77, "name": "Hypothetical protein of unknown function (DUF2483)", "partial_evidence_count": null, "pfam_id": "PF10656", "proteins": 77, "proteomes": 67, "short_name": "DUF2483", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10656", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR024443", "known_evidence_count": null, "matches": 77, "name": "Protein of unknown function (DUF3197)", "partial_evidence_count": null, "pfam_id": "PF11432", "proteins": 77, "proteomes": 77, "short_name": "DUF3197", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11432", "structures": 9, "taxa": 116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 154 and 217 amino acids in length. There is a conserved SSGY sequence motif.", "domain_architectures": 2, "interpro_id": "IPR031520", "known_evidence_count": null, "matches": 77, "name": "Domain of unknown function (DUF4694)", "partial_evidence_count": null, "pfam_id": "PF15765", "proteins": 77, "proteomes": 75, "short_name": "DUF4694", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15765", "structures": 0, "taxa": 279, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 150 residues in length and found in various Staphylococcus aureus species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032561", "known_evidence_count": null, "matches": 77, "name": "Domain of unknown function (DUF4930)", "partial_evidence_count": null, "pfam_id": "PF16284", "proteins": 77, "proteomes": 76, "short_name": "DUF4930", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16284", "structures": 0, "taxa": 98, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is a membrane protein found in Mycobacterium [[cite:PUB00076065]].", "domain_architectures": 2, "interpro_id": "IPR031816", "known_evidence_count": null, "matches": 77, "name": "Domain of unknown function (DUF5073)", "partial_evidence_count": null, "pfam_id": "PF16817", "proteins": 77, "proteomes": 77, "short_name": "DUF5073", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16817", "structures": 1, "taxa": 100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised. It is predominantly found in eukaryotic sequences mostly from Alveolata. There are several highly conserved motifs: FGFNSFWS, FKxxxYD, PRxxY and YRC. Predictions of its structure suggest it folds into seven alpha helices.", "domain_architectures": 10, "interpro_id": "IPR049235", "known_evidence_count": null, "matches": 80, "name": "Domain of unknown function (DUF6832)", "partial_evidence_count": null, "pfam_id": "PF20725", "proteins": 77, "proteomes": 71, "short_name": "DUF6832", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20725", "structures": 2, "taxa": 209, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the Halobacteria class, including genera such as Halorhabdus, Haloarcula, and Haloferacaceae. The domain is approximately 160-200 amino acids in length. Many proteins in this family are predicted to be lipoproteins, suggesting a potential role in membrane-associated processes. The structure of this domain is predicted to adopt a large immunoglobulin-like fold.", "domain_architectures": 2, "interpro_id": "IPR058434", "known_evidence_count": null, "matches": 77, "name": "Domain of unknown function (DUF8121)", "partial_evidence_count": null, "pfam_id": "PF26441", "proteins": 77, "proteomes": 68, "short_name": "DUF8121", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26441", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Ascomycota lineage. It is predicted to adopt a globular structure composed of array of alpha-helices. It contains a semi-conserved CxxYPNH sequence motif which may have a functional importance.", "domain_architectures": 1, "interpro_id": "IPR059397", "known_evidence_count": null, "matches": 77, "name": "Domain of unknown function (DUF8353)", "partial_evidence_count": null, "pfam_id": "PF27619", "proteins": 77, "proteomes": 39, "short_name": "DUF8353", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27619", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function mostly found in gammaproteobacteria.", "domain_architectures": 2, "interpro_id": "IPR040708", "known_evidence_count": null, "matches": 76, "name": "Family of unknown function (DUF5636)", "partial_evidence_count": null, "pfam_id": "PF18686", "proteins": 76, "proteomes": 63, "short_name": "DUF5636", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18686", "structures": 1, "taxa": 145, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001902) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from the bengamide biosynthetic gene cluster from Myxococcus virescens and appears to be predominantly found in cystobacterineae [[cite:PUB00098946]].", "domain_architectures": 1, "interpro_id": "IPR045712", "known_evidence_count": null, "matches": 76, "name": "Family of unknown function (DUF6068)", "partial_evidence_count": null, "pfam_id": "PF19544", "proteins": 76, "proteomes": 40, "short_name": "DUF6068", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19544", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001662) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the mediomycin A biosynthetic gene cluster from Kitasatospora mediocidica [[cite:PUB00099386]].", "domain_architectures": 1, "interpro_id": "IPR046222", "known_evidence_count": null, "matches": 76, "name": "Family of unknown function (DUF6255)", "partial_evidence_count": null, "pfam_id": "PF19768", "proteins": 76, "proteomes": 31, "short_name": "DUF6255", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19768", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in Trichuris sp., Trichinella sp. and similar sequences from nematodes. This domain is repeated in some sequences from Trichuris spp. (two to four times) and it may adopt a SH2-like fold.", "domain_architectures": 13, "interpro_id": "IPR055569", "known_evidence_count": null, "matches": 143, "name": "Domain of unknown function (DUF7145)", "partial_evidence_count": null, "pfam_id": "PF23638", "proteins": 76, "proteomes": 15, "short_name": "DUF7145", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23638", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found at the C-terminal of a group of uncharacterised bacterial sequences, that is usually associated with [pfam:PF12358] at the N-terminal of these members. This domain may have a wHTH-like fold.", "domain_architectures": 4, "interpro_id": "IPR061671", "known_evidence_count": null, "matches": 76, "name": "Domain of unknown function (DUF8610)", "partial_evidence_count": null, "pfam_id": "PF30174", "proteins": 76, "proteomes": 76, "short_name": "DUF8610", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30174", "structures": 0, "taxa": 251, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharcaterised proteins found mainly in Streptococcus lineage. They are predicted to be composed of four transmembrane helices. The arrangement of these helices is similar to the one found in the tetraspanin family.", "domain_architectures": 1, "interpro_id": "IPR061838", "known_evidence_count": null, "matches": 76, "name": "Domain of unknown function (DUF8777)", "partial_evidence_count": null, "pfam_id": "PF31037", "proteins": 76, "proteomes": 76, "short_name": "DUF8777", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31037", "structures": 0, "taxa": 118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. This domain has a similarity with known PH domains.", "domain_architectures": 1, "interpro_id": "IPR061844", "known_evidence_count": null, "matches": 76, "name": "Domain of unknown function (DUF8783)", "partial_evidence_count": null, "pfam_id": "PF31043", "proteins": 76, "proteomes": 76, "short_name": "DUF8783", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31043", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR019208", "known_evidence_count": null, "matches": 75, "name": "Uncharacterized protein conserved in archaea (DUF2097)", "partial_evidence_count": null, "pfam_id": "PF09870", "proteins": 75, "proteomes": 52, "short_name": "DUF2097", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09870", "structures": 0, "taxa": 99, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR019217", "known_evidence_count": null, "matches": 75, "name": "Uncharacterized protein conserved in archaea (DUF2118)", "partial_evidence_count": null, "pfam_id": "PF09891", "proteins": 75, "proteomes": 75, "short_name": "DUF2118", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09891", "structures": 1, "taxa": 197, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses. It is thought to be part of the early transcription factor large subunit.", "domain_architectures": 3, "interpro_id": "IPR043920", "known_evidence_count": null, "matches": 75, "name": "Family of unknown function (DUF5757)", "partial_evidence_count": null, "pfam_id": "PF19061", "proteins": 75, "proteomes": 63, "short_name": "DUF5757", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19061", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001944) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the funisamine biosynthetic gene cluster from Streptosporangium sp. [[cite:PUB00098987]].", "domain_architectures": 2, "interpro_id": "IPR045777", "known_evidence_count": null, "matches": 75, "name": "Family of unknown function (DUF6203)", "partial_evidence_count": null, "pfam_id": "PF19706", "proteins": 75, "proteomes": 74, "short_name": "DUF6203", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19706", "structures": 0, "taxa": 110, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046577", "known_evidence_count": null, "matches": 75, "name": "Family of unknown function (DUF6637)", "partial_evidence_count": null, "pfam_id": "PF20342", "proteins": 75, "proteomes": 73, "short_name": "DUF6637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20342", "structures": 0, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of uncharacterised short sequences from actinobacteria. Some members are annotated as ESX-1 secretion-associated proteins. They are predicted to adopt a mainly alpha-helical configuration.", "domain_architectures": 1, "interpro_id": "IPR055586", "known_evidence_count": null, "matches": 75, "name": "Family of unknown function (DUF7162)", "partial_evidence_count": null, "pfam_id": "PF23721", "proteins": 75, "proteomes": 74, "short_name": "DUF7162", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23721", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family consists of a group of uncharacterized proteins, typically between 99 to 116 amino acids in length, found in bacteriophages that infect Microbacterium and Arthrobacter bacterial hosts. These proteins are encoded in the genomes of phages belonging to the Caudoviricetes class, primarily within the families Azeevirinae, Dismasvirus, Yangvirus, Manhattanvirus, Liebevirus, Zetavirus, and Armstrongvirus. An AlphaFold prediction shows these proteins are composed of two alpha helices. AlphaFold also predicts that these proteins likely form homodimers.", "domain_architectures": 2, "interpro_id": "IPR055593", "known_evidence_count": null, "matches": 75, "name": "Domain of unknown function (DUF7169)", "partial_evidence_count": null, "pfam_id": "PF23773", "proteins": 75, "proteomes": 73, "short_name": "DUF7169", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23773", "structures": 0, "taxa": 191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in bacterial and phage proteins, particularly in Gordonia phages. The domain is approximately 140 amino acids in length. It contains regions of disorder at the N- and C-termini.", "domain_architectures": 1, "interpro_id": "IPR055595", "known_evidence_count": null, "matches": 75, "name": "Protein of unknown function (DUF7171)", "partial_evidence_count": null, "pfam_id": "PF23785", "proteins": 75, "proteomes": 75, "short_name": "DUF7171", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23785", "structures": 0, "taxa": 180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function. It is found in uncharacterized phage proteins in the size range 90 to 120 amino acids. The domain does not appear to be related to any other known Pfam domain. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR055662", "known_evidence_count": null, "matches": 75, "name": "Family of unknown function (DUF7238)", "partial_evidence_count": null, "pfam_id": "PF23885", "proteins": 75, "proteomes": 75, "short_name": "DUF7238", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23885", "structures": 0, "taxa": 182, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in a group of uncharacterised sequences from worms. This domain may consist of eight beta-strands.", "domain_architectures": 8, "interpro_id": "IPR056643", "known_evidence_count": null, "matches": 77, "name": "Domain of unknown function (DUF7741)", "partial_evidence_count": null, "pfam_id": "PF24888", "proteins": 75, "proteomes": 60, "short_name": "DUF7741", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24888", "structures": 0, "taxa": 146, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised bacteriophage family of proteins. Structure prediction with [swissprot:G5H923] suggests that members of this family will form homodimeric complexes (iPTM=0.87 and pTM=0.89).", "domain_architectures": 1, "interpro_id": "IPR057163", "known_evidence_count": null, "matches": 75, "name": "Domain of unknown function (DUF7841)", "partial_evidence_count": null, "pfam_id": "PF25223", "proteins": 75, "proteomes": 72, "short_name": "DUF7841", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25223", "structures": 0, "taxa": 240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes a repeat of unknown function found at the C-terminal of uncharacterised proteins mainly from animals. It displays a TPR fold.", "domain_architectures": 11, "interpro_id": "IPR057711", "known_evidence_count": null, "matches": 75, "name": "Repeat of unknown function (DUF7951)", "partial_evidence_count": null, "pfam_id": "PF25824", "proteins": 75, "proteomes": 65, "short_name": "DUF7951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25824", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short presumed domain is found in a large number of hypothetical plant proteins. The domain is quite rich in conserved glycine residues. It occurs in some putative transposons but currently has no known function.", "domain_architectures": 5, "interpro_id": "IPR008552", "known_evidence_count": null, "matches": 77, "name": "Domain of unknown function (DUF834)", "partial_evidence_count": null, "pfam_id": "PF05754", "proteins": 74, "proteomes": 11, "short_name": "DUF834", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05754", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Several members of this family are annotated as being ATP/GTP-binding site motif A (P-loop) proteins, but this could not be confirmed. The one PDB:3NRF structure solved for this family exhibits an immunoglobin-like beta-sandwich fold. Crystal packing suggests that a tetramer is a significant oligomerisation state, and a disulfide bridge is formed between Cys 125 at the C-terminal end of the monomer, and Cys 69.", "domain_architectures": 1, "interpro_id": "IPR025581", "known_evidence_count": null, "matches": 74, "name": "Domain of unknown function (DUF4354)", "partial_evidence_count": null, "pfam_id": "PF14263", "proteins": 74, "proteomes": 70, "short_name": "DUF4354", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14263", "structures": 2, "taxa": 154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains uncharacterised proteins. It also contains the anacyclamide synthesis protein AcyE. Cyanobactins are small, cyclic peptides found in cyanobacteria. They are ribosomally synthesised and post-translationally modified. Cyanobactin biosynthesis clusters contain 7-12 genes [[cite:PUB00060495]]. Anaclyclamides are a type of cyanobactin produced in strains of the cyanobacteria Anabaena [[cite:PUB00060495]]. AcyE is a 49-amino-acid protein with N-terminal homology to the peptide precursor proteins in the other cyanobactin pathways [[cite:PUB00094616]]. The core peptide of AcyE is cleaved during post-translational processing of the precursor peptide [[cite:PUB00094616]].", "domain_architectures": 1, "interpro_id": "IPR031036", "known_evidence_count": null, "matches": 74, "name": "Family of unknown function (DUF5840)", "partial_evidence_count": null, "pfam_id": "PF19158", "proteins": 74, "proteomes": 22, "short_name": "DUF5840", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19158", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 155 and 173 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046145", "known_evidence_count": null, "matches": 74, "name": "Family of unknown function (DUF6147)", "partial_evidence_count": null, "pfam_id": "PF19644", "proteins": 74, "proteomes": 73, "short_name": "DUF6147", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19644", "structures": 0, "taxa": 136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001020) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the muraymycin C1 biosynthetic gene cluster from Streptomyces sp. NRRL 30471 [[cite:PUB00099464]].", "domain_architectures": 1, "interpro_id": "IPR045955", "known_evidence_count": null, "matches": 74, "name": "Family of unknown function (DUF6375)", "partial_evidence_count": null, "pfam_id": "PF19902", "proteins": 74, "proteomes": 72, "short_name": "DUF6375", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19902", "structures": 0, "taxa": 237, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in Planctomycete bacteria, and is approximately 170 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046512", "known_evidence_count": null, "matches": 74, "name": "Family of unknown function (DUF6690)", "partial_evidence_count": null, "pfam_id": "PF20397", "proteins": 74, "proteomes": 73, "short_name": "DUF6690", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20397", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 73, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria.", "domain_architectures": 1, "interpro_id": "IPR058380", "known_evidence_count": null, "matches": 74, "name": "Family of unknown function (DUF8067)", "partial_evidence_count": null, "pfam_id": "PF26263", "proteins": 74, "proteomes": 64, "short_name": "DUF8067", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26263", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Halobacteria. It is predicted to fold into an alpha/beta structure composed of a small four stranded antiparallel beta-sheet and alpha-helices packed on one side of it. It contains two conserved sequence motifs IPLH and RxRFW which may have functional importance. This domain is frequently found in combination with domains members of AAA superfamily.", "domain_architectures": 5, "interpro_id": "IPR059310", "known_evidence_count": null, "matches": 74, "name": "Domain of unknown function (DUF8266)", "partial_evidence_count": null, "pfam_id": "PF26796", "proteins": 74, "proteomes": 70, "short_name": "DUF8266", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26796", "structures": 0, "taxa": 126, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharcaterised proteins mainly from Leptospira lineage. It is predicted to fold into a pouch-like beta-barrel structure.", "domain_architectures": 1, "interpro_id": "IPR061843", "known_evidence_count": null, "matches": 74, "name": "Domain of unknown function (DUF8782)", "partial_evidence_count": null, "pfam_id": "PF31042", "proteins": 74, "proteomes": 74, "short_name": "DUF8782", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31042", "structures": 0, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of uncharacterised prokaryotic proteins.", "domain_architectures": 2, "interpro_id": "IPR007548", "known_evidence_count": null, "matches": 102, "name": "Protein of unknown function (DUF505)", "partial_evidence_count": null, "pfam_id": "PF04458", "proteins": 73, "proteomes": 66, "short_name": "DUF505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04458", "structures": 0, "taxa": 210, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of around 360 residues in length and seems to be specific to Caenorhabditis elegans. The function of this family is unknown. It appears to carry seven TM regions.", "domain_architectures": 2, "interpro_id": "IPR010601", "known_evidence_count": null, "matches": 76, "name": "Protein of unknown function (DUF1182)", "partial_evidence_count": null, "pfam_id": "PF06681", "proteins": 73, "proteomes": 21, "short_name": "DUF1182", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06681", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several archaeal proteins of around 320 residues in length. Members of this family seem to be found exclusively in Halobacterium and Haloferax species. The function of this family is unknown. This protein is probably a rep protein due to conservation of functional motifs.", "domain_architectures": 1, "interpro_id": "IPR009870", "known_evidence_count": null, "matches": 73, "name": "Putative rep protein (DUF1424)", "partial_evidence_count": null, "pfam_id": "PF07232", "proteins": 73, "proteomes": 56, "short_name": "DUF1424", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07232", "structures": 0, "taxa": 132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in bacteria and archaea.", "domain_architectures": 1, "interpro_id": "IPR041145", "known_evidence_count": null, "matches": 73, "name": "Domain of unknown function (DUF5619)", "partial_evidence_count": null, "pfam_id": "PF18505", "proteins": 73, "proteomes": 56, "short_name": "DUF5619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18505", "structures": 1, "taxa": 162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein containing two transmembrane helices. Many of these proteins are found in organisms in the Candidate Phyla Radiation.", "domain_architectures": 1, "interpro_id": "IPR043712", "known_evidence_count": null, "matches": 73, "name": "Family of unknown function (DUF5652)", "partial_evidence_count": null, "pfam_id": "PF18893", "proteins": 73, "proteomes": 72, "short_name": "DUF5652", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18893", "structures": 0, "taxa": 195, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 2, "interpro_id": "IPR046215", "known_evidence_count": null, "matches": 75, "name": "Family of unknown function (DUF6248)", "partial_evidence_count": null, "pfam_id": "PF19761", "proteins": 73, "proteomes": 70, "short_name": "DUF6248", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19761", "structures": 0, "taxa": 118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is primarily found in myoviruses. Proteins in this family are typically between 298 and 400 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR046234", "known_evidence_count": null, "matches": 89, "name": "Family of unknown function (DUF6267)", "partial_evidence_count": null, "pfam_id": "PF19782", "proteins": 73, "proteomes": 71, "short_name": "DUF6267", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19782", "structures": 0, "taxa": 203, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in phages. Proteins in this family are typically between 144 and 156 amino acids in length. Proteins in this family contain the conserved motifs NFD and LEGL.", "domain_architectures": 2, "interpro_id": "IPR045491", "known_evidence_count": null, "matches": 81, "name": "Family of unknown function (DUF6433)", "partial_evidence_count": null, "pfam_id": "PF20025", "proteins": 73, "proteomes": 73, "short_name": "DUF6433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20025", "structures": 0, "taxa": 208, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 120 amino acids in length. The family is found in association with [pfam:PF03629], [pfam:PF08410].", "domain_architectures": 3, "interpro_id": "IPR046587", "known_evidence_count": null, "matches": 73, "name": "Family of unknown function (DUF6645)", "partial_evidence_count": null, "pfam_id": "PF20350", "proteins": 73, "proteomes": 38, "short_name": "DUF6645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20350", "structures": 1, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised phage domain composed of a seven stranded beta sheet with a C-terminal alpha helix. Structure prediction suggests this protein may form a homodimer.", "domain_architectures": 1, "interpro_id": "IPR055671", "known_evidence_count": null, "matches": 73, "name": "Domain of unknown function (DUF7247)", "partial_evidence_count": null, "pfam_id": "PF23905", "proteins": 73, "proteomes": 73, "short_name": "DUF7247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23905", "structures": 0, "taxa": 173, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055723", "known_evidence_count": null, "matches": 73, "name": "Family of unknown function (DUF7299)", "partial_evidence_count": null, "pfam_id": "PF23973", "proteins": 73, "proteomes": 73, "short_name": "DUF7299", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23973", "structures": 0, "taxa": 172, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 55 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, particularly members of the family Demerecviridae. Within this family, the proteins are predominantly found in the genera Tequintavirus and Epseptimavirus. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061610", "known_evidence_count": null, "matches": 73, "name": "Family of unknown function (DUF8540)", "partial_evidence_count": null, "pfam_id": "PF29391", "proteins": 73, "proteomes": 73, "short_name": "DUF8540", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29391", "structures": 0, "taxa": 157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised archaeal proteins, including HVO_1919 ([swissprot:D4GTE8]) from Haloferax volcanii.", "domain_architectures": 1, "interpro_id": "IPR061660", "known_evidence_count": null, "matches": 73, "name": "Domain of unknown function (DUF8599)", "partial_evidence_count": null, "pfam_id": "PF29885", "proteins": 73, "proteomes": 73, "short_name": "DUF8599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29885", "structures": 0, "taxa": 134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. It is predicted to fold into an up-and-down four helical bindle.", "domain_architectures": 1, "interpro_id": "IPR061845", "known_evidence_count": null, "matches": 73, "name": "Domain of unknown function (DUF8784)", "partial_evidence_count": null, "pfam_id": "PF31044", "proteins": 73, "proteomes": 73, "short_name": "DUF8784", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31044", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR022544", "known_evidence_count": null, "matches": 72, "name": "Protein of unknown function (DUF2560)", "partial_evidence_count": null, "pfam_id": "PF10834", "proteins": 72, "proteomes": 59, "short_name": "DUF2560", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10834", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of several uncharacterized proteins around 170 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032546", "known_evidence_count": null, "matches": 72, "name": "Domain of unknown function (DUF4943)", "partial_evidence_count": null, "pfam_id": "PF16301", "proteins": 72, "proteomes": 70, "short_name": "DUF4943", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16301", "structures": 0, "taxa": 125, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001503) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the amycolamycin A biosynthetic gene cluster from Amycolatopsis sp. [[cite:PUB00099467]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046202", "known_evidence_count": null, "matches": 72, "name": "Family of unknown function (DUF6235)", "partial_evidence_count": null, "pfam_id": "PF19748", "proteins": 72, "proteomes": 60, "short_name": "DUF6235", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19748", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0002024) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the nargenicin biosynthetic gene cluster from Nocardia argentinensis [[cite:PUB00099422]].", "domain_architectures": 1, "interpro_id": "IPR045954", "known_evidence_count": null, "matches": 72, "name": "Family of unknown function (DUF6374)", "partial_evidence_count": null, "pfam_id": "PF19901", "proteins": 72, "proteomes": 59, "short_name": "DUF6374", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19901", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001749) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the epipyriculol biosynthetic gene cluster from Pyricularia oryzae 70-15 [[cite:PUB00098879]]. This family appears to be predominantly found in fungi.", "domain_architectures": 1, "interpro_id": "IPR045634", "known_evidence_count": null, "matches": 72, "name": "Family of unknown function (DUF6413)", "partial_evidence_count": null, "pfam_id": "PF19951", "proteins": 72, "proteomes": 13, "short_name": "DUF6413", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19951", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 62 and 74 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046570", "known_evidence_count": null, "matches": 72, "name": "Family of unknown function (DUF6724)", "partial_evidence_count": null, "pfam_id": "PF20485", "proteins": 72, "proteomes": 72, "short_name": "DUF6724", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20485", "structures": 0, "taxa": 131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in various phage and bacterial proteins. The domain length ranges from approximately 200 to 260 amino acids.", "domain_architectures": 1, "interpro_id": "IPR055651", "known_evidence_count": null, "matches": 72, "name": "Domain of unknown function (DUF7227)", "partial_evidence_count": null, "pfam_id": "PF23872", "proteins": 72, "proteomes": 70, "short_name": "DUF7227", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23872", "structures": 0, "taxa": 191, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised sequences from viruses. They may have a novel repeat fold consisting of two domains at the N- and C-terminal with beta-hairpin-beta-alpha configuration that are connected by nine alpha-helices linked by loops.", "domain_architectures": 5, "interpro_id": "IPR055910", "known_evidence_count": null, "matches": 84, "name": "Family of unknown function (DUF7487)", "partial_evidence_count": null, "pfam_id": "PF24308", "proteins": 72, "proteomes": 41, "short_name": "DUF7487", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24308", "structures": 0, "taxa": 181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an integral membrane domain of unknown function found in spirochaetes, predominantly Treponema species. The domain is approximately 90-100 residues in length. Interaction evidence from the IntAct database indicates that members of this family interact with FliR, a component of the flagellar export apparatus. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061591", "known_evidence_count": null, "matches": 72, "name": "Family of unknown function (DUF8521)", "partial_evidence_count": null, "pfam_id": "PF29236", "proteins": 72, "proteomes": 72, "short_name": "DUF8521", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29236", "structures": 0, "taxa": 141, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 50-70 amino acids found exclusively in tailed bacteriophages. The family is found in the class Caudoviricetes, with members in the family Demerecviridae and the subfamilies Markadamsvirinae and Mccorquodalevirinae. Members are found in diverse genera including Epseptimavirus, Myunavirus and Sugarlandvirus. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061613", "known_evidence_count": null, "matches": 72, "name": "Family of unknown function (DUF8543)", "partial_evidence_count": null, "pfam_id": "PF29394", "proteins": 72, "proteomes": 72, "short_name": "DUF8543", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29394", "structures": 0, "taxa": 159, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira.", "domain_architectures": 1, "interpro_id": "IPR061842", "known_evidence_count": null, "matches": 72, "name": "Domain of unknown function (DUF8781)", "partial_evidence_count": null, "pfam_id": "PF31041", "proteins": 72, "proteomes": 72, "short_name": "DUF8781", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31041", "structures": 0, "taxa": 106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains a number of hypothetical viral proteins of unknown function approximately 200 residues long.", "domain_architectures": 1, "interpro_id": "IPR009657", "known_evidence_count": null, "matches": 71, "name": "Protein of unknown function (DUF1247)", "partial_evidence_count": null, "pfam_id": "PF06851", "proteins": 71, "proteomes": 70, "short_name": "DUF1247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06851", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins which seem to be specific to Chlamydia pneumoniae. Members of this family are typically around 400 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010792", "known_evidence_count": null, "matches": 71, "name": "Protein of unknown function (DUF1389)", "partial_evidence_count": null, "pfam_id": "PF07146", "proteins": 71, "proteomes": 15, "short_name": "DUF1389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07146", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Nucleopolyhedrovirus proteins of around 100 resides in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009946", "known_evidence_count": null, "matches": 71, "name": "Protein of unknown function (DUF1477)", "partial_evidence_count": null, "pfam_id": "PF07346", "proteins": 71, "proteomes": 70, "short_name": "DUF1477", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07346", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of uncharacterised proteins found by clustering human gut metagenomic sequences [[cite:PUB00055601]].", "domain_architectures": 1, "interpro_id": "IPR024216", "known_evidence_count": null, "matches": 71, "name": "Protein of unknown function (DUF3851)", "partial_evidence_count": null, "pfam_id": "PF12962", "proteins": 71, "proteomes": 60, "short_name": "DUF3851", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12962", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_2585, a putative uncharacterised protein. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 1, "interpro_id": "IPR025185", "known_evidence_count": null, "matches": 71, "name": "Domain of unknown function (DUF4120)", "partial_evidence_count": null, "pfam_id": "PF13496", "proteins": 71, "proteomes": 49, "short_name": "DUF4120", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13496", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 160 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031863", "known_evidence_count": null, "matches": 71, "name": "Domain of unknown function (DUF4755)", "partial_evidence_count": null, "pfam_id": "PF15947", "proteins": 71, "proteomes": 65, "short_name": "DUF4755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15947", "structures": 0, "taxa": 133, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000128) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein encoded by the pyoluteorin biosynthetic gene cluster from Pseudomonas sp. M18 [[cite:PUB00099395],[cite:PUB00099404]]", "domain_architectures": 1, "interpro_id": "IPR046054", "known_evidence_count": null, "matches": 71, "name": "Family of unknown function (DUF6012)", "partial_evidence_count": null, "pfam_id": "PF19475", "proteins": 71, "proteomes": 63, "short_name": "DUF6012", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19475", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from bacteria. It is predicted to adopt an alpha-helical structure with a highly conserved DVHDxWxxW sequence motif which may constitute a ligand binding site. This domain is likely to form a homodimer. Investigation of STRING networks suggests this protein may functionally interact with [pfam:PF24838] a likely octameric membrane complex.", "domain_architectures": 3, "interpro_id": "IPR056118", "known_evidence_count": null, "matches": 71, "name": "Domain of unknown function (DUF7701)", "partial_evidence_count": null, "pfam_id": "PF24792", "proteins": 71, "proteomes": 69, "short_name": "DUF7701", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24792", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised halobacterial integral membrane proteins. These proteins have four transmembrane helices with the N and C-terminus likely being cytoplasmic.", "domain_architectures": 1, "interpro_id": "IPR058271", "known_evidence_count": null, "matches": 71, "name": "Family of unknown function (DUF7965)", "partial_evidence_count": null, "pfam_id": "PF25913", "proteins": 71, "proteomes": 71, "short_name": "DUF7965", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25913", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gram-negative bacteria. It is predicted to fold into an array of alpha-helices. It contains a number of conserved negatively charged residues that cluster on the surface.", "domain_architectures": 1, "interpro_id": "IPR059471", "known_evidence_count": null, "matches": 71, "name": "Domain of unknown function (DUF8427)", "partial_evidence_count": null, "pfam_id": "PF28531", "proteins": 71, "proteomes": 71, "short_name": "DUF8427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28531", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of proteins of approximately 320-330 amino acids found exclusively in tailed bacteriophages. The family is restricted to the class Caudoviricetes, particularly members of the family Demerecviridae. Within this family, the proteins are found in the genera Tequintavirus and Epseptimavirus. The function of these proteins remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061612", "known_evidence_count": null, "matches": 71, "name": "Family of unknown function (DUF8542)", "partial_evidence_count": null, "pfam_id": "PF29393", "proteins": 71, "proteomes": 69, "short_name": "DUF8542", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29393", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised prokaryotic proteins. It is predicted to fold into a beta-sandwich.", "domain_architectures": 1, "interpro_id": "IPR061770", "known_evidence_count": null, "matches": 71, "name": "Domain of unknown function (DUF8709)", "partial_evidence_count": null, "pfam_id": "PF30727", "proteins": 71, "proteomes": 71, "short_name": "DUF8709", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30727", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 70, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is likely to be related to solute-binding lipo-proteins.", "domain_architectures": 1, "interpro_id": "IPR024533", "known_evidence_count": null, "matches": 70, "name": "Protein of unknown function (DUF3834)", "partial_evidence_count": null, "pfam_id": "PF12916", "proteins": 70, "proteomes": 40, "short_name": "DUF3834", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12916", "structures": 1, "taxa": 116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 190 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032338", "known_evidence_count": null, "matches": 72, "name": "Domain of unknown function (DUF4858)", "partial_evidence_count": null, "pfam_id": "PF16150", "proteins": 70, "proteomes": 59, "short_name": "DUF4858", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16150", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000112) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the neocarzinostatin biosynthetic gene cluster from Streptomyces carzinostaticus subsp. neocarzinostaticus [[cite:PUB00099433]] and appears to be restricted to Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046050", "known_evidence_count": null, "matches": 70, "name": "Family of unknown function (DUF6008)", "partial_evidence_count": null, "pfam_id": "PF19471", "proteins": 70, "proteomes": 67, "short_name": "DUF6008", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19471", "structures": 0, "taxa": 115, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 65, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from flagellate Discoba. It has detectable similarity to known PDZ domains and it is predicted to adopt similar structure. It is frequently found in multiple tandem copies.", "domain_architectures": 4, "interpro_id": "IPR056664", "known_evidence_count": null, "matches": 70, "name": "Domain of unknown function (DUF7762)", "partial_evidence_count": null, "pfam_id": "PF24953", "proteins": 70, "proteomes": 27, "short_name": "DUF7762", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24953", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein family found in Clostridium species. This protein is composed of two transmembrane alpha helices. The function of this protein family remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061643", "known_evidence_count": null, "matches": 70, "name": "Family of unknown function (DUF8582)", "partial_evidence_count": null, "pfam_id": "PF29738", "proteins": 70, "proteomes": 63, "short_name": "DUF8582", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29738", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. It is predicted to fold into array of alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR061847", "known_evidence_count": null, "matches": 70, "name": "Domain of unknown function (DUF8786)", "partial_evidence_count": null, "pfam_id": "PF31046", "proteins": 70, "proteomes": 70, "short_name": "DUF8786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31046", "structures": 0, "taxa": 100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family is predominated by ORFs from Circoviridae. The function of this family remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR008474", "known_evidence_count": null, "matches": 69, "name": "Domain of unknown function (DUF755)", "partial_evidence_count": null, "pfam_id": "PF05501", "proteins": 69, "proteomes": 51, "short_name": "DUF755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05501", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Nucleopolyhedrovirus proteins with no known function.", "domain_architectures": 1, "interpro_id": "IPR009264", "known_evidence_count": null, "matches": 69, "name": "Nucleopolyhedrovirus protein of unknown function (DUF918)", "partial_evidence_count": null, "pfam_id": "PF06033", "proteins": 69, "proteomes": 68, "short_name": "DUF918", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06033", "structures": 0, "taxa": 135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Sapovirus proteins of around 165 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009949", "known_evidence_count": null, "matches": 69, "name": "Protein of unknown function (DUF1478)", "partial_evidence_count": null, "pfam_id": "PF07349", "proteins": 69, "proteomes": 5, "short_name": "DUF1478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07349", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a putative zinc finger domain. Proteins containing this domain typically consist of a beta-sheet region followed by an alpha-helix and an unstructured C-terminus. The beta-sheet region contains a CXCX...XCXC sequence with Cys residues located in two proximal loops and pointing towards each other. The precise function of this set of bacterial proteins is, as yet, unknown [[cite:PUB00008047]].", "domain_architectures": 1, "interpro_id": "IPR015166", "known_evidence_count": null, "matches": 69, "name": "Domain of unknown function (DUF1922)", "partial_evidence_count": null, "pfam_id": "PF09082", "proteins": 69, "proteomes": 69, "short_name": "DUF1922", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09082", "structures": 1, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various archaeal and bacterial proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018663", "known_evidence_count": null, "matches": 69, "name": "Predicted membrane protein (DUF2101)", "partial_evidence_count": null, "pfam_id": "PF09874", "proteins": 69, "proteomes": 68, "short_name": "DUF2101", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09874", "structures": 0, "taxa": 157, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 68, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 3, "interpro_id": "IPR009198", "known_evidence_count": null, "matches": 69, "name": "Predicted membrane protein (DUF2208)", "partial_evidence_count": null, "pfam_id": "PF09973", "proteins": 69, "proteomes": 69, "short_name": "DUF2208", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09973", "structures": 0, "taxa": 166, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 69, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 100 amino acids in length. There are two completely conserved A residues that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR022195", "known_evidence_count": null, "matches": 69, "name": "Protein of unknown function (DUF3720)", "partial_evidence_count": null, "pfam_id": "PF12517", "proteins": 69, "proteomes": 2, "short_name": "DUF3720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12517", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short domain is found only on a small subgroup of proteins from Gram-negative Proteobacteria that also carry a YARHG domain, [pfam:PF13308]. They carry three conserved tryptophan and three conserved cysteine residues.", "domain_architectures": 2, "interpro_id": "IPR027920", "known_evidence_count": null, "matches": 69, "name": "Domain of unknown function (DUF4453)", "partial_evidence_count": null, "pfam_id": "PF14627", "proteins": 69, "proteomes": 63, "short_name": "DUF4453", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14627", "structures": 0, "taxa": 116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry adopts a Greek-key beta sandwich topology, with long loops in some of the members. While a structure is known, the function of this domain is yet to be determined.", "domain_architectures": 9, "interpro_id": "IPR043939", "known_evidence_count": null, "matches": 75, "name": "Family of unknown function (DUF5780)", "partial_evidence_count": null, "pfam_id": "PF19092", "proteins": 69, "proteomes": 63, "short_name": "DUF5780", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19092", "structures": 1, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family is functionally uncharacterised. It is found in eukaryotes.", "domain_architectures": 7, "interpro_id": "IPR046627", "known_evidence_count": null, "matches": 105, "name": "Family of unknown function (DUF6739)", "partial_evidence_count": null, "pfam_id": "PF20524", "proteins": 69, "proteomes": 59, "short_name": "DUF6739", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20524", "structures": 0, "taxa": 172, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised mycobacteria phage proteins that adopt a zinc binding domain composed of 5 potential ligand residues. The zinc binding motif is composed of a CXXC and a CXXHH motif.", "domain_architectures": 1, "interpro_id": "IPR055842", "known_evidence_count": null, "matches": 69, "name": "Family of unknown function (DUF7419)", "partial_evidence_count": null, "pfam_id": "PF24194", "proteins": 69, "proteomes": 69, "short_name": "DUF7419", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24194", "structures": 0, "taxa": 159, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Actinomycetes. It is predicted to adopt a beta-sandwich structure with significant similarity to carbohydrate-binding modules in particular to CBM_4_9 ([pfam:PF02018]).", "domain_architectures": 10, "interpro_id": "IPR057172", "known_evidence_count": null, "matches": 72, "name": "Domain of unknown function (DUF7850)", "partial_evidence_count": null, "pfam_id": "PF25235", "proteins": 69, "proteomes": 69, "short_name": "DUF7850", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25235", "structures": 0, "taxa": 98, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halophilic archaea, including members of the Haloarculaceae and Haloferacaceae families. These proteins are small, approximately 30-35 residues in length, and appear to be single-domain proteins. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061625", "known_evidence_count": null, "matches": 69, "name": "Family of unknown function (DUF8556)", "partial_evidence_count": null, "pfam_id": "PF29451", "proteins": 69, "proteomes": 57, "short_name": "DUF8556", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29451", "structures": 0, "taxa": 99, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region found in several uncharacterised plant proteins.", "domain_architectures": 7, "interpro_id": "IPR006736", "known_evidence_count": null, "matches": 71, "name": "Protein of unknown function, DUF601", "partial_evidence_count": null, "pfam_id": "PF04642", "proteins": 68, "proteomes": 5, "short_name": "DUF601", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04642", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is found in eukaryotic, parasitic microsporidia. Its function is unknown.", "domain_architectures": 1, "interpro_id": "IPR019081", "known_evidence_count": null, "matches": 68, "name": "Protein of unknown function (DUF2463)", "partial_evidence_count": null, "pfam_id": "PF09591", "proteins": 68, "proteomes": 4, "short_name": "DUF2463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09591", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 165 and 199 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR031445", "known_evidence_count": null, "matches": 72, "name": "Domain of unknown function (DUF4672)", "partial_evidence_count": null, "pfam_id": "PF15716", "proteins": 68, "proteomes": 65, "short_name": "DUF4672", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15716", "structures": 0, "taxa": 240, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of several uncharacterized proteins around 325 residues in length and is mainly found in various Acinetobacter species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032620", "known_evidence_count": null, "matches": 69, "name": "Domain of unknown function (DUF4882)", "partial_evidence_count": null, "pfam_id": "PF16223", "proteins": 68, "proteomes": 33, "short_name": "DUF4882", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16223", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 125 and 138 amino acids in length. There is a conserved MGK sequence motif.", "domain_architectures": 1, "interpro_id": "IPR046123", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF6120)", "partial_evidence_count": null, "pfam_id": "PF19615", "proteins": 68, "proteomes": 46, "short_name": "DUF6120", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19615", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001503) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the amycolamycin A biosynthetic gene cluster from Amycolatopsis sp. [[cite:PUB00099467]].", "domain_architectures": 1, "interpro_id": "IPR046308", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF6423)", "partial_evidence_count": null, "pfam_id": "PF19987", "proteins": 68, "proteomes": 68, "short_name": "DUF6423", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19987", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046716", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF6608)", "partial_evidence_count": null, "pfam_id": "PF20312", "proteins": 68, "proteomes": 64, "short_name": "DUF6608", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20312", "structures": 0, "taxa": 167, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 98 and 116 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046726", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF6618)", "partial_evidence_count": null, "pfam_id": "PF20323", "proteins": 68, "proteomes": 52, "short_name": "DUF6618", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20323", "structures": 0, "taxa": 138, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry reprepsents a family of uncharacterised proteins found in mycobacterial phage.", "domain_architectures": 1, "interpro_id": "IPR055663", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF7239)", "partial_evidence_count": null, "pfam_id": "PF23886", "proteins": 68, "proteomes": 68, "short_name": "DUF7239", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23886", "structures": 0, "taxa": 187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised mycophage proteins. These proteins form a compact domain composed of 5 or 6 antiparallel beta strands that curve around a C-terminal alpha-helix.", "domain_architectures": 1, "interpro_id": "IPR055994", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF7572)", "partial_evidence_count": null, "pfam_id": "PF24457", "proteins": 68, "proteomes": 66, "short_name": "DUF7572", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24457", "structures": 0, "taxa": 174, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058381", "known_evidence_count": null, "matches": 68, "name": "Integral membrane family of unknown function (DUF8068)", "partial_evidence_count": null, "pfam_id": "PF26265", "proteins": 68, "proteomes": 67, "short_name": "DUF8068", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26265", "structures": 0, "taxa": 121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins found in archaea. The proteins in this family are predominantly found in the class Halobacteria, which includes genera such as Halorubrum, Natronorubrum, and Halovenus. The proteins containing this domain vary in length, with sequences ranging from approximately 59 to 347 amino acids. The structure of this domain adopts an alpha solenoid.", "domain_architectures": 1, "interpro_id": "IPR058450", "known_evidence_count": null, "matches": 68, "name": "Domain of unknown function (DUF8137)", "partial_evidence_count": null, "pfam_id": "PF26458", "proteins": 68, "proteomes": 45, "short_name": "DUF8137", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26458", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 67, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 230 amino acids in length.", "domain_architectures": 6, "interpro_id": "IPR022144", "known_evidence_count": null, "matches": 67, "name": "Protein of unknown function (DUF3676)", "partial_evidence_count": null, "pfam_id": "PF12429", "proteins": 67, "proteomes": 2, "short_name": "DUF3676", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12429", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 125 and 136 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR022152", "known_evidence_count": null, "matches": 67, "name": "Protein of unknown function (DUF3682)", "partial_evidence_count": null, "pfam_id": "PF12446", "proteins": 67, "proteomes": 7, "short_name": "DUF3682", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12446", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000379) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the glycinocin A biosynthetic gene cluster from streptomyces viridochromogenes [[cite:PUB00099403]].", "domain_architectures": 2, "interpro_id": "IPR046309", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF6424)", "partial_evidence_count": null, "pfam_id": "PF19988", "proteins": 67, "proteomes": 66, "short_name": "DUF6424", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19988", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 64, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a family of uncharacterised proteins in nematodes.", "domain_architectures": 11, "interpro_id": "IPR055467", "known_evidence_count": null, "matches": 70, "name": "Domain of unknown function (DUF7039)", "partial_evidence_count": null, "pfam_id": "PF23049", "proteins": 67, "proteomes": 9, "short_name": "DUF7039", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23049", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from halobacteria. It is predicted to fold into a beta-barrel structure which has a similarity to Heme iron utilization protein domains. The heme binding site is not conserved. Although, structurally it is more similar to HemS/ChuS-like domains, this domain has probably undergone a large deletion.", "domain_architectures": 1, "interpro_id": "IPR059284", "known_evidence_count": null, "matches": 67, "name": "Domain of unknown function (DUF8240)", "partial_evidence_count": null, "pfam_id": "PF26712", "proteins": 67, "proteomes": 65, "short_name": "DUF8240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26712", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 66, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins restricted to Dictyostelium. It is predicted to adopt alpha-helical structure.", "domain_architectures": 5, "interpro_id": "IPR061573", "known_evidence_count": null, "matches": 67, "name": "Domain of unknown function (DUF8503)", "partial_evidence_count": null, "pfam_id": "PF29088", "proteins": 67, "proteomes": 3, "short_name": "DUF8503", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29088", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 40 residues in length found in Cyanobacteriota and Actinomycetota. Structural analysis indicates similarity to the double-stranded RNA-binding domain fold. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061697", "known_evidence_count": null, "matches": 67, "name": "Domain of unknown function (DUF8636)", "partial_evidence_count": null, "pfam_id": "PF30569", "proteins": 67, "proteomes": 64, "short_name": "DUF8636", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30569", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes several uncharacterised proteins from Vibrio cholerae. There is some doubt regarding the existence of these proteins, they are encoded by open reading frames contained within a repeated region in the Vibrio superintegron.", "domain_architectures": 1, "interpro_id": "IPR006959", "known_evidence_count": null, "matches": 66, "name": "Protein of unknown function, DUF645", "partial_evidence_count": null, "pfam_id": "PF04875", "proteins": 66, "proteomes": 9, "short_name": "DUF645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04875", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bacillales.", "domain_architectures": 1, "interpro_id": "IPR021464", "known_evidence_count": null, "matches": 66, "name": "Protein of unknown function (DUF3116)", "partial_evidence_count": null, "pfam_id": "PF11313", "proteins": 66, "proteomes": 24, "short_name": "DUF3116", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11313", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_2588, a putative uncharacterised protein. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 1, "interpro_id": "IPR025189", "known_evidence_count": null, "matches": 66, "name": "Domain of unknown function (DUF4121)", "partial_evidence_count": null, "pfam_id": "PF13497", "proteins": 66, "proteomes": 47, "short_name": "DUF4121", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13497", "structures": 0, "taxa": 110, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This uncharacterized domain has a lipocalin fold.", "domain_architectures": 1, "interpro_id": "IPR032316", "known_evidence_count": null, "matches": 66, "name": "Domain of unknown function (DUF4847)", "partial_evidence_count": null, "pfam_id": "PF16139", "proteins": 66, "proteomes": 65, "short_name": "DUF4847", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16139", "structures": 2, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This coiled-coil is found in various Platyhelminthes, with many of the sequences annotated as being uveal autoantigen with coiled-coil. This region is one of the numerous coiled-coil regions which constitutes this antigen. The function is currently unknown.", "domain_architectures": 2, "interpro_id": "IPR043979", "known_evidence_count": null, "matches": 67, "name": "Family of unknown function (DUF5741)", "partial_evidence_count": null, "pfam_id": "PF19012", "proteins": 66, "proteomes": 35, "short_name": "DUF5741", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19012", "structures": 0, "taxa": 93, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 1, "interpro_id": "IPR046280", "known_evidence_count": null, "matches": 66, "name": "Family of unknown function (DUF6313)", "partial_evidence_count": null, "pfam_id": "PF19832", "proteins": 66, "proteomes": 55, "short_name": "DUF6313", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19832", "structures": 0, "taxa": 96, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in uncharacterised bacterial proteins. It is distantly related to class-II glutamine amidotransferase domains [pfam:PF13522].", "domain_architectures": 2, "interpro_id": "IPR054236", "known_evidence_count": null, "matches": 66, "name": "Domain of unknown function (DUF6963)", "partial_evidence_count": null, "pfam_id": "PF22288", "proteins": 66, "proteomes": 65, "short_name": "DUF6963", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22288", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found at the N-terminal of proteins containing DUF3994 at the C-terminal, in most instances. According to structure predictions, this domain consists of alpha helices suggesting they are the membrane spanning region of of these sequences.", "domain_architectures": 2, "interpro_id": "IPR053854", "known_evidence_count": null, "matches": 66, "name": "Domain of unknown function (DUF7018)", "partial_evidence_count": null, "pfam_id": "PF22872", "proteins": 66, "proteomes": 32, "short_name": "DUF7018", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22872", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function, which is found in phage proteins, predominantly from Arthrobacter and Gordonia phages. The domain is approximately 110 amino acids in length. It shows similarity to the Phage_barrel superfamily. These proteins are often components of the phage neck complex.", "domain_architectures": 1, "interpro_id": "IPR055677", "known_evidence_count": null, "matches": 66, "name": "Domain of unknown function (DUF7253)", "partial_evidence_count": null, "pfam_id": "PF23911", "proteins": 66, "proteomes": 65, "short_name": "DUF7253", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23911", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a small family of uncharacterised proteins from pseudomonas phage. These proteins range in length from 114 and 130 amino acids. Structure prediction suggests the proteins adopt an open set of alpha helical segments as a monomer. However, homodimer prediction shows a confident interaction (iPTM 0.79). The dimer shows distinct charge distribution with a linear positively charged surface.", "domain_architectures": 1, "interpro_id": "IPR055799", "known_evidence_count": null, "matches": 66, "name": "Family of unknown function (DUF7375)", "partial_evidence_count": null, "pfam_id": "PF24090", "proteins": 66, "proteomes": 66, "short_name": "DUF7375", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24090", "structures": 0, "taxa": 166, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. Structurally these are composed of a pair of alpha helices. Structure prediction suggests these proteins may homodimerise (iPTM=0.89). These proteins are annotated as RDF proteins but the source of this annotation is uncertain.", "domain_architectures": 1, "interpro_id": "IPR055889", "known_evidence_count": null, "matches": 66, "name": "Family of unknown function (DUF7466)", "partial_evidence_count": null, "pfam_id": "PF24265", "proteins": 66, "proteomes": 65, "short_name": "DUF7466", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24265", "structures": 0, "taxa": 149, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in bacteria and phage. Proteins in this family are typically between 128 and 147 amino acids in length. The proteins contain two subdomains separated by an alpha-helical linker.", "domain_architectures": 1, "interpro_id": "IPR056076", "known_evidence_count": null, "matches": 66, "name": "Family of unknown function (DUF7659)", "partial_evidence_count": null, "pfam_id": "PF24692", "proteins": 66, "proteomes": 54, "short_name": "DUF7659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24692", "structures": 0, "taxa": 154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halobacteria. The proteins in this family are predominantly found in archaea, specifically within the Halobacteria class. The taxonomic distribution includes genera such as Halorubrum, Haloquadratum, and Haloarcula, among others. The proteins in this family are typically around 116 to 118 amino acids in length. Some proteins in this family are associated with plasmids, suggesting potential roles in horizontal gene transfer or adaptation. The subcellular localization of these proteins is not well-defined, but they may contain zinc finger-like motifs, indicating potential roles in nucleic acid binding or protein-protein interactions.", "domain_architectures": 1, "interpro_id": "IPR058418", "known_evidence_count": null, "matches": 66, "name": "Family of unknown function (DUF8105)", "partial_evidence_count": null, "pfam_id": "PF26407", "proteins": 66, "proteomes": 60, "short_name": "DUF8105", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26407", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold in a beta-sandwich with unique topology.", "domain_architectures": 8, "interpro_id": "IPR059295", "known_evidence_count": null, "matches": 70, "name": "Domain of unknown function (DUF8251)", "partial_evidence_count": null, "pfam_id": "PF26770", "proteins": 66, "proteomes": 66, "short_name": "DUF8251", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26770", "structures": 0, "taxa": 203, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021477", "known_evidence_count": null, "matches": 65, "name": "Protein of unknown function (DUF3130", "partial_evidence_count": null, "pfam_id": "PF11328", "proteins": 65, "proteomes": 33, "short_name": "DUF3130", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11328", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are approximately 140 amino acids in length. There is a single completely conserved residue Y that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR025020", "known_evidence_count": null, "matches": 65, "name": "Protein of unknown function (DUF3908)", "partial_evidence_count": null, "pfam_id": "PF13048", "proteins": 65, "proteomes": 63, "short_name": "DUF3908", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13048", "structures": 0, "taxa": 145, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 102 and 113 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR043722", "known_evidence_count": null, "matches": 69, "name": "Protein of unknown function (DUF5663)", "partial_evidence_count": null, "pfam_id": "PF18908", "proteins": 65, "proteomes": 52, "short_name": "DUF5663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18908", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a conserved domain found in various Platyhelminthes. The function of this family is still unknown.", "domain_architectures": 2, "interpro_id": "IPR043792", "known_evidence_count": null, "matches": 66, "name": "Domain of unknown function (DUF5734)", "partial_evidence_count": null, "pfam_id": "PF19005", "proteins": 65, "proteomes": 11, "short_name": "DUF5734", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19005", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001300) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the anthracimycin biosynthetic gene cluster from Streptomyces sp. CNH365 [[cite:PUB00099456]].", "domain_architectures": 5, "interpro_id": "IPR046301", "known_evidence_count": null, "matches": 65, "name": "Family of unknown function (DUF6416)", "partial_evidence_count": null, "pfam_id": "PF19980", "proteins": 65, "proteomes": 64, "short_name": "DUF6416", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19980", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain that is found N-terminal to [pfam:PF26154].", "domain_architectures": 1, "interpro_id": "IPR058356", "known_evidence_count": null, "matches": 65, "name": "Domain of unknown function (DUF8043)", "partial_evidence_count": null, "pfam_id": "PF26159", "proteins": 65, "proteomes": 65, "short_name": "DUF8043", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26159", "structures": 0, "taxa": 131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a the central transmembrane domain from family of uncharacterised proteins from halophilic archaea. The family is predominantly found in the class Halobacteria, which includes members from the families Natrialbaceae and Haloferacaceae. Proteins in this family are typically between 150 and 350 amino acids in length. They are predicted to be membrane-associated, as suggested by the presence of two transmembrane helices represented by this domain.", "domain_architectures": 5, "interpro_id": "IPR058963", "known_evidence_count": null, "matches": 65, "name": "Domain of unknown function (DUF8108) central domain", "partial_evidence_count": null, "pfam_id": "PF26440", "proteins": 65, "proteomes": 62, "short_name": "DUF8108_M", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26440", "structures": 0, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Gram negative bacteria. It is predicted to fold into an alpha-beta-beta architecture featuring two sandwiched beta-sheets and alpha-helices packed on one side. This domain contains several negatively charged residues which are located on the domain surface and highly conserved.", "domain_architectures": 2, "interpro_id": "IPR059391", "known_evidence_count": null, "matches": 65, "name": "Domain of unknown function (DUF8347)", "partial_evidence_count": null, "pfam_id": "PF27110", "proteins": 65, "proteomes": 61, "short_name": "DUF8347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27110", "structures": 0, "taxa": 121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 63, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR014450", "known_evidence_count": null, "matches": 64, "name": "Uncharacterized protein conserved in archaea (DUF2153)", "partial_evidence_count": null, "pfam_id": "PF09921", "proteins": 64, "proteomes": 64, "short_name": "DUF2153", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09921", "structures": 0, "taxa": 144, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. However several proteins are annotated as Tagatose 1,6-diphosphate aldolase, but evidence to support this could not be found. This family of proteins is found in bacteria. Proteins in this family are typically between 61 and 106 amino acids in length. There are two completely conserved residues (Y and F) that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR024979", "known_evidence_count": null, "matches": 64, "name": "Protein of unknown function (DUF3884)", "partial_evidence_count": null, "pfam_id": "PF13024", "proteins": 64, "proteomes": 59, "short_name": "DUF3884", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13024", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 40 amino acids in length. There is a conserved YCI sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025003", "known_evidence_count": null, "matches": 64, "name": "Domain of unknown function (DUF3973)", "partial_evidence_count": null, "pfam_id": "PF13119", "proteins": 64, "proteomes": 59, "short_name": "DUF3973", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13119", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025090", "known_evidence_count": null, "matches": 64, "name": "Protein of unknown function (DUF4017)", "partial_evidence_count": null, "pfam_id": "PF13209", "proteins": 64, "proteomes": 61, "short_name": "DUF4017", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13209", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000106) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the naphthomycin A biosynthetic gene cluster from Streptomyces sp. CS [[cite:PUB00098883]].", "domain_architectures": 1, "interpro_id": "IPR045639", "known_evidence_count": null, "matches": 64, "name": "Family of unknown function (DUF6408)", "partial_evidence_count": null, "pfam_id": "PF19946", "proteins": 64, "proteomes": 63, "short_name": "DUF6408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19946", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 116 and 127 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046677", "known_evidence_count": null, "matches": 64, "name": "Family of unknown function (DUF6547)", "partial_evidence_count": null, "pfam_id": "PF20184", "proteins": 64, "proteomes": 64, "short_name": "DUF6547", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20184", "structures": 0, "taxa": 190, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 256 and 362 amino acids in length. There is a conserved HEXRH sequence motif which is characteristic of metallopeptidase enzymes.", "domain_architectures": 2, "interpro_id": "IPR046709", "known_evidence_count": null, "matches": 64, "name": "Putative metallopeptidase family (DUF6782)", "partial_evidence_count": null, "pfam_id": "PF20573", "proteins": 64, "proteomes": 57, "short_name": "DUF6782", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20573", "structures": 0, "taxa": 146, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. These proteins contain a small compact globular domain composed of a four stranded meander followed by a C-terminal alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055724", "known_evidence_count": null, "matches": 64, "name": "Domain of unknown function (DUF7300)", "partial_evidence_count": null, "pfam_id": "PF23974", "proteins": 64, "proteomes": 63, "short_name": "DUF7300", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23974", "structures": 0, "taxa": 160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes the Shigella phage Sf6 gene 22 protein [swissprot:Q716F3].", "domain_architectures": 2, "interpro_id": "IPR056641", "known_evidence_count": null, "matches": 64, "name": "Domain of unknown function (DUF7739)", "partial_evidence_count": null, "pfam_id": "PF24881", "proteins": 64, "proteomes": 58, "short_name": "DUF7739", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24881", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a complex alpha/beta structure.", "domain_architectures": 4, "interpro_id": "IPR059455", "known_evidence_count": null, "matches": 70, "name": "Domain of unknown function (DUF8411)", "partial_evidence_count": null, "pfam_id": "PF28471", "proteins": 64, "proteomes": 54, "short_name": "DUF8411", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28471", "structures": 0, "taxa": 181, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Arabidopsis thaliana proteins of unknown function.", "domain_architectures": 9, "interpro_id": "IPR007989", "known_evidence_count": null, "matches": 64, "name": "Protein of unknown function (DUF730)", "partial_evidence_count": null, "pfam_id": "PF05325", "proteins": 63, "proteomes": 10, "short_name": "DUF730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05325", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal and bacterial proteins of unknown function, including [swissprot:O67778] from Aquifex aeolicus. The structure of this protein has been solved [[cite:PUB00100674]] but its function remains unknown. Members of this family seem to have an acyl-CoA N-acyltransferase topology.", "domain_architectures": 1, "interpro_id": "IPR008304", "known_evidence_count": null, "matches": 63, "name": "Protein of unknown function (DUF1122)", "partial_evidence_count": null, "pfam_id": "PF06557", "proteins": 63, "proteomes": 63, "short_name": "DUF1122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06557", "structures": 4, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 60, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical prokaryotic proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018662", "known_evidence_count": null, "matches": 63, "name": "Uncharacterized protein conserved in archaea (DUF2095)", "partial_evidence_count": null, "pfam_id": "PF09868", "proteins": 63, "proteomes": 63, "short_name": "DUF2095", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09868", "structures": 0, "taxa": 133, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length. There are two completely conserved residues (Y and L) that may be functionally important.", "domain_architectures": 2, "interpro_id": "IPR024995", "known_evidence_count": null, "matches": 63, "name": "Protein of unknown function (DUF3895)", "partial_evidence_count": null, "pfam_id": "PF13034", "proteins": 63, "proteomes": 62, "short_name": "DUF3895", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13034", "structures": 0, "taxa": 104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 125 residues in length and is mainly found in various Acinetobacter baumannii species. The function of this family is unknown.", "domain_architectures": 5, "interpro_id": "IPR032538", "known_evidence_count": null, "matches": 63, "name": "Domain of unknown function (DUF4951)", "partial_evidence_count": null, "pfam_id": "PF16309", "proteins": 63, "proteomes": 63, "short_name": "DUF4951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16309", "structures": 1, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR035162", "known_evidence_count": null, "matches": 63, "name": "Family of unknown function (DUF5470)", "partial_evidence_count": null, "pfam_id": "PF17564", "proteins": 63, "proteomes": 62, "short_name": "DUF5470", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17564", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain s is functionally uncharacterised. It is predominantly found in eukaryotic sequences mostly from Alveolata. There are several highly conserved motifs, including YxKHxR and WPPE at the C terminus. The domain is predicted to adopt an alpha-beta fold.", "domain_architectures": 4, "interpro_id": "", "known_evidence_count": null, "matches": 63, "name": "Domain of unknown function (DUF6831)", "partial_evidence_count": null, "pfam_id": "PF20724", "proteins": 63, "proteomes": 57, "short_name": "DUF6831", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20724", "structures": 2, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins either standalone or in combination with other domains. It is probably distantly related to the C-terminal domain of CdiA toxin (CdiA-CT), known member of RNase A superfamily.", "domain_architectures": 3, "interpro_id": "IPR054245", "known_evidence_count": null, "matches": 63, "name": "Domain of unknown function (DUF6972)", "partial_evidence_count": null, "pfam_id": "PF22319", "proteins": 63, "proteomes": 52, "short_name": "DUF6972", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22319", "structures": 0, "taxa": 172, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from flagellate Discoba.", "domain_architectures": 4, "interpro_id": "IPR056663", "known_evidence_count": null, "matches": 63, "name": "Domain of unknown function (DUF7761)", "partial_evidence_count": null, "pfam_id": "PF24952", "proteins": 63, "proteomes": 27, "short_name": "DUF7761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24952", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Gram-negative bacteria. It is predicted to fold into a beta-sandwich which has some similarity to known carbohydrate binding domains. It is frequently found in combination with [pfam:PF07589] PEP-CTERM sorting motif suggesting that it may be associated with the membrane.", "domain_architectures": 3, "interpro_id": "IPR059283", "known_evidence_count": null, "matches": 65, "name": "Domain of unknown function (DUF8239)", "partial_evidence_count": null, "pfam_id": "PF26711", "proteins": 63, "proteomes": 61, "short_name": "DUF8239", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26711", "structures": 0, "taxa": 136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Proteins in this entry are functionally uncharacterised. They are found in various Bacteroides species. This entry represents a second Ig-like domain found a after [pfam:PF16410].", "domain_architectures": 8, "interpro_id": "IPR061569", "known_evidence_count": null, "matches": 63, "name": "Domain of unknown function (DUF8499)", "partial_evidence_count": null, "pfam_id": "PF29065", "proteins": 63, "proteomes": 58, "short_name": "DUF8499", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29065", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This region is found in a number of hypothetical proteins thought to be expressed by the eukaryote Encephalitozoon cuniculi, an obligate intracellular microsporidial parasite. It is approximately 200 residues long.", "domain_architectures": 2, "interpro_id": "IPR011667", "known_evidence_count": null, "matches": 62, "name": "Protein of unknown function (DUF1609)", "partial_evidence_count": null, "pfam_id": "PF07753", "proteins": 62, "proteomes": 5, "short_name": "DUF1609", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07753", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 61, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 40 amino acids in length.", "domain_architectures": 10, "interpro_id": "IPR022146", "known_evidence_count": null, "matches": 76, "name": "Protein of unknown function (DUF3678)", "partial_evidence_count": null, "pfam_id": "PF12435", "proteins": 62, "proteomes": 9, "short_name": "DUF3678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12435", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 62, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain family is functionally uncharacterised. This domain is found in Sar and is typically 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046631", "known_evidence_count": null, "matches": 62, "name": "Domain of unknown function (DUF6743)", "partial_evidence_count": null, "pfam_id": "PF20528", "proteins": 62, "proteomes": 1, "short_name": "DUF6743", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20528", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length. They are predicted to fold into a four-stranded beta-sheet meander and an alpha-helix. One face of this beta-sheet is enriched with conserved positively charged arginine and lysine residues.", "domain_architectures": 1, "interpro_id": "IPR054240", "known_evidence_count": null, "matches": 62, "name": "Family of unknown function (DUF6967)", "partial_evidence_count": null, "pfam_id": "PF22295", "proteins": 62, "proteomes": 62, "short_name": "DUF6967", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22295", "structures": 0, "taxa": 145, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in various bacteriophages that infect bacteria in the family Enterobacteriaceae, including phages of Escherichia, Shigella and Citrobacter. The protein is approximately 55-60 amino acids in length. An AlphaFold model shows this domain adopts a small beta barrel structure. This domain is possibly related to the KOW motif.", "domain_architectures": 1, "interpro_id": "IPR055668", "known_evidence_count": null, "matches": 62, "name": "Domain of unknown function (DUF7244)", "partial_evidence_count": null, "pfam_id": "PF23896", "proteins": 62, "proteomes": 62, "short_name": "DUF7244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23896", "structures": 0, "taxa": 169, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from proteobacteria. It is usually found C-terminal to [[pfam:PF22288]]. It is predicted to adopt a globular structure with a beta-barrel shape.", "domain_architectures": 2, "interpro_id": "IPR055683", "known_evidence_count": null, "matches": 62, "name": "Domain of unknown function (DUF7259)", "partial_evidence_count": null, "pfam_id": "PF23920", "proteins": 62, "proteomes": 62, "short_name": "DUF7259", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23920", "structures": 0, "taxa": 160, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Gammaproteobacteria. It is predicted to adopt a structure which has similarity to SPM domain. The Ca2+ binding sites are not conserved suggesting that this domain doesn't bind Ca2+ ions. This domain is frequently found in combination with [pfam:PF13645] representing a group of putative L,D-transpeptidase domains.", "domain_architectures": 1, "interpro_id": "IPR059292", "known_evidence_count": null, "matches": 62, "name": "Domain of unknown function (DUF8248)", "partial_evidence_count": null, "pfam_id": "PF26746", "proteins": 62, "proteomes": 62, "short_name": "DUF8248", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26746", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 57, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This LRR domain of unknown function is found in uncharacterised proteins predominantly from metazoan.", "domain_architectures": 3, "interpro_id": "IPR059424", "known_evidence_count": null, "matches": 62, "name": "Repeat of unknown function (DUF8380)", "partial_evidence_count": null, "pfam_id": "PF28313", "proteins": 62, "proteomes": 58, "short_name": "DUF8380", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28313", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the N-terminal region of several proteins found in C. elegans. The family is often found with [pfam:PF02363].", "domain_architectures": 5, "interpro_id": "IPR009475", "known_evidence_count": null, "matches": 61, "name": "Protein of unknown function (DUF1096)", "partial_evidence_count": null, "pfam_id": "PF06493", "proteins": 61, "proteomes": 15, "short_name": "DUF1096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06493", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function is restricted to Enterobacteriaceae. The sequence is highly conserved.", "domain_architectures": 1, "interpro_id": "IPR024470", "known_evidence_count": null, "matches": 61, "name": "Protein of unknown function (DUF2545)", "partial_evidence_count": null, "pfam_id": "PF10810", "proteins": 61, "proteomes": 61, "short_name": "DUF2545", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10810", "structures": 0, "taxa": 110, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR022020", "known_evidence_count": null, "matches": 61, "name": "Domain of unknown function (DUF3601)", "partial_evidence_count": null, "pfam_id": "PF12208", "proteins": 61, "proteomes": 50, "short_name": "DUF3601", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12208", "structures": 1, "taxa": 162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length. There is a conserved YGM sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025094", "known_evidence_count": null, "matches": 61, "name": "Protein of unknown function (DUF4021)", "partial_evidence_count": null, "pfam_id": "PF13213", "proteins": 61, "proteomes": 60, "short_name": "DUF4021", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13213", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function which is found at the C-terminal region of [pfam:PF13749] in actinobacteria.", "domain_architectures": 6, "interpro_id": "IPR040728", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF5635)", "partial_evidence_count": null, "pfam_id": "PF18685", "proteins": 61, "proteomes": 60, "short_name": "DUF5635", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18685", "structures": 1, "taxa": 119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 54, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in Platyhelminthes.", "domain_architectures": 1, "interpro_id": "IPR043789", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF5731)", "partial_evidence_count": null, "pfam_id": "PF19002", "proteins": 61, "proteomes": 39, "short_name": "DUF5731", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19002", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001804) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the tiancimycin biosynthetic gene cluster from Streptomyces sp. CB03234 and appears to be predominantly found in bacteria [[cite:PUB00098949]].", "domain_architectures": 1, "interpro_id": "IPR045719", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF6073)", "partial_evidence_count": null, "pfam_id": "PF19550", "proteins": 61, "proteomes": 59, "short_name": "DUF6073", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19550", "structures": 1, "taxa": 131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000696) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the gentamicin biosynthetic gene cluster from Micromonospora echinospora [[cite:PUB00099418],[cite:PUB00098957]].", "domain_architectures": 2, "interpro_id": "IPR046190", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF6218)", "partial_evidence_count": null, "pfam_id": "PF19726", "proteins": 61, "proteomes": 61, "short_name": "DUF6218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19726", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000081) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the kedarcidin biosynthetic gene cluster from Streptoalloteichus sp. ATCC 53650 [[cite:PUB00098878],[cite:PUB00099428]].", "domain_architectures": 1, "interpro_id": "IPR046206", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF6239)", "partial_evidence_count": null, "pfam_id": "PF19752", "proteins": 61, "proteomes": 57, "short_name": "DUF6239", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19752", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000434) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the SW-163C biosynthetic gene cluster from Streptomyces sp. SNA15896 [[cite:PUB00083668]].", "domain_architectures": 1, "interpro_id": "IPR045643", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF6405)", "partial_evidence_count": null, "pfam_id": "PF19943", "proteins": 61, "proteomes": 59, "short_name": "DUF6405", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19943", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is found in uncharacterized proteins from various mycobacteriophages and bacterial species including Nocardia and Mycobacterium. The protein is typically around 100 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR055664", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF7240)", "partial_evidence_count": null, "pfam_id": "PF23888", "proteins": 61, "proteomes": 60, "short_name": "DUF7240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23888", "structures": 0, "taxa": 145, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein family of unknown function found in various bacterial phage proteins. The family typically consists of proteins around 140-160 amino acids in length. It is found in phages that infect bacteria such as Salmonella, Escherichia, Shigella, and Dickeya. The function of this family remains unclear. Some members of this family are annotated as uncharacterized or hypothetical proteins. AlphaFold predictions suggest the proteins in this family contain two distinct domains, with a central domain composed of a three stranded beta sheet and a C-terminal small 3-helix bundle domain.", "domain_architectures": 1, "interpro_id": "IPR055863", "known_evidence_count": null, "matches": 61, "name": "Family of unknown function (DUF7440)", "partial_evidence_count": null, "pfam_id": "PF24224", "proteins": 61, "proteomes": 60, "short_name": "DUF7440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24224", "structures": 0, "taxa": 141, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised sequences mainly from bacteria.", "domain_architectures": 5, "interpro_id": "IPR061629", "known_evidence_count": null, "matches": 61, "name": "Domain of unknown function (DUF8560)", "partial_evidence_count": null, "pfam_id": "PF29528", "proteins": 61, "proteomes": 55, "short_name": "DUF8560", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29528", "structures": 0, "taxa": 157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of around 415 residues in length which seem to be specific to the bacterium Leptospira interrogans.", "domain_architectures": 2, "interpro_id": "IPR009630", "known_evidence_count": null, "matches": 118, "name": "Protein of unknown function (DUF1229)", "partial_evidence_count": null, "pfam_id": "PF06797", "proteins": 60, "proteomes": 9, "short_name": "DUF1229", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06797", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins that is highly conserved in Trypanosoma cruzi.", "domain_architectures": 2, "interpro_id": "IPR021547", "known_evidence_count": null, "matches": 60, "name": "Protein of unknown function (DUF2826)", "partial_evidence_count": null, "pfam_id": "PF11442", "proteins": 60, "proteomes": 4, "short_name": "DUF2826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11442", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This domain family is found in viruses, and is approximately 40 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR022230", "known_evidence_count": null, "matches": 60, "name": "Protein of unknown function (DUF3756)", "partial_evidence_count": null, "pfam_id": "PF12581", "proteins": 60, "proteomes": 2, "short_name": "DUF3756", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12581", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR024994", "known_evidence_count": null, "matches": 60, "name": "Protein of unknown function (DUF3896)", "partial_evidence_count": null, "pfam_id": "PF13035", "proteins": 60, "proteomes": 60, "short_name": "DUF3896", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13035", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Rickettsia.", "domain_architectures": 3, "interpro_id": "IPR020168", "known_evidence_count": null, "matches": 64, "name": "Family of unknown function (DUF5410)", "partial_evidence_count": null, "pfam_id": "PF17422", "proteins": 60, "proteomes": 32, "short_name": "DUF5410", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17422", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Ascoviridae. This family also includes uncharacterised proteins found in Bacteria.", "domain_architectures": 1, "interpro_id": "IPR043847", "known_evidence_count": null, "matches": 60, "name": "Family of unknown function (DUF5862)", "partial_evidence_count": null, "pfam_id": "PF19180", "proteins": 60, "proteomes": 39, "short_name": "DUF5862", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19180", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised protein rbstp2171 from Bacillus stearothermophilus and similar proteins found in bacteria and tailed bacteriophages.", "domain_architectures": 1, "interpro_id": "IPR049294", "known_evidence_count": null, "matches": 60, "name": "Domain of unknown function (DUF6848)", "partial_evidence_count": null, "pfam_id": "PF20941", "proteins": 60, "proteomes": 53, "short_name": "DUF6848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20941", "structures": 1, "taxa": 157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 392 and 442 amino acids in length. This entry represents the central immunoglobulin-like domain.", "domain_architectures": 1, "interpro_id": "IPR048296", "known_evidence_count": null, "matches": 60, "name": "Domain of unknown function (DUF4785) central domain", "partial_evidence_count": null, "pfam_id": "PF20942", "proteins": 60, "proteomes": 60, "short_name": "DUF4785_2nd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20942", "structures": 1, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised worm proteins mainly from clade Rhabditida. It contains a number of highly conserved cysteine residues that are predicted to form disulfide bonds. This domain is predicted to fold into a four-stranded antiparallel meander decorated with alpha-helices.", "domain_architectures": 6, "interpro_id": "IPR056675", "known_evidence_count": null, "matches": 60, "name": "Domain of unknown function (DUF7773)", "partial_evidence_count": null, "pfam_id": "PF24982", "proteins": 60, "proteomes": 48, "short_name": "DUF7773", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24982", "structures": 0, "taxa": 125, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Bacteroidota. It shares similarity with the CBMs of SusE/SusF and it is predicted to adopt similar structure.", "domain_architectures": 8, "interpro_id": "IPR058350", "known_evidence_count": null, "matches": 63, "name": "Domain of unknown function (DUF8037)", "partial_evidence_count": null, "pfam_id": "PF26123", "proteins": 60, "proteomes": 60, "short_name": "DUF8037", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26123", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from lower eukaryotes. This domain is often found associated with [pfam:PF00271] and is predicted to adopt an alpha-beta configuration.", "domain_architectures": 7, "interpro_id": "IPR061626", "known_evidence_count": null, "matches": 60, "name": "Family of unknown function (DUF8557)", "partial_evidence_count": null, "pfam_id": "PF29511", "proteins": 60, "proteomes": 55, "short_name": "DUF8557", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29511", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of bacterial proteins with undetermined function.", "domain_architectures": 4, "interpro_id": "IPR019726", "known_evidence_count": null, "matches": 59, "name": "Protein of Unknown function (DUF2604)", "partial_evidence_count": null, "pfam_id": "PF10790", "proteins": 59, "proteomes": 53, "short_name": "DUF2604", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10790", "structures": 6, "taxa": 172, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 164 and 197 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025108", "known_evidence_count": null, "matches": 59, "name": "Protein of unknown function (DUF4030)", "partial_evidence_count": null, "pfam_id": "PF13222", "proteins": 59, "proteomes": 52, "short_name": "DUF4030", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13222", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Caenorhabditis. Members of this family are predicted to contain 4 trans-membrane regions.", "domain_architectures": 3, "interpro_id": "IPR035321", "known_evidence_count": null, "matches": 60, "name": "Family of unknown function (DUF5373)", "partial_evidence_count": null, "pfam_id": "PF17343", "proteins": 59, "proteomes": 18, "short_name": "DUF5373", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17343", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 50, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Legionella.", "domain_architectures": 1, "interpro_id": "IPR040737", "known_evidence_count": null, "matches": 59, "name": "Family of unknown function (DUF5638)", "partial_evidence_count": null, "pfam_id": "PF18688", "proteins": 59, "proteomes": 30, "short_name": "DUF5638", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18688", "structures": 1, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function is associated with the biosynthetic gene cluster for glycocin F. The family appears to be restricted to Firmicutes.", "domain_architectures": 1, "interpro_id": "IPR043895", "known_evidence_count": null, "matches": 59, "name": "Family of unknown function (DUF5839)", "partial_evidence_count": null, "pfam_id": "PF19157", "proteins": 59, "proteomes": 50, "short_name": "DUF5839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19157", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001503) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the amycolamycin A biosynthetic gene cluster from Amycolatopsis sp. [[cite:PUB00099467]]. This family appears to be predominantly found in Actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR046178", "known_evidence_count": null, "matches": 59, "name": "Family of unknown function (DUF6187)", "partial_evidence_count": null, "pfam_id": "PF19685", "proteins": 59, "proteomes": 57, "short_name": "DUF6187", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19685", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function. It is typically between 120 and 250 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR055621", "known_evidence_count": null, "matches": 64, "name": "Family of unknown function (DUF7197)", "partial_evidence_count": null, "pfam_id": "PF23827", "proteins": 59, "proteomes": 40, "short_name": "DUF7197", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23827", "structures": 0, "taxa": 144, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins that are composed of two small domains connected by an alpha helix. Structure prediction suggests that these proteins may homodimerise or tetramerise. These proteins are primarily found in Gordonia phage.", "domain_architectures": 1, "interpro_id": "IPR055855", "known_evidence_count": null, "matches": 59, "name": "Family of unknown function (DUF7432)", "partial_evidence_count": null, "pfam_id": "PF24211", "proteins": 59, "proteomes": 57, "short_name": "DUF7432", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24211", "structures": 0, "taxa": 150, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small putative transmembrane proteins found primarily in Streptomyces phages and some bacteria. The family is characterized by a conserved transmembrane region typically located between residues 20-45 of the alignment. Many members of this family are around 70 amino acids in length. The function of this protein family is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR055862", "known_evidence_count": null, "matches": 59, "name": "Family of unknown function (DUF7439)", "partial_evidence_count": null, "pfam_id": "PF24220", "proteins": 59, "proteomes": 58, "short_name": "DUF7439", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24220", "structures": 0, "taxa": 142, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a very small group of proteins mainly from Phyllobacteriaceae. It is predicted to fold into a beta-sandwich with topological similarity to domains members of the adhesin superfamily. Members contain conserved lysine, aspartate and asparagine residues that are likely to form an isopeptide bond.", "domain_architectures": 2, "interpro_id": "IPR057689", "known_evidence_count": null, "matches": 59, "name": "Domain of unknown function (DUF7929)", "partial_evidence_count": null, "pfam_id": "PF25551", "proteins": 59, "proteomes": 59, "short_name": "DUF7929", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25551", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain four predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058372", "known_evidence_count": null, "matches": 59, "name": "Domain of unknown function (DUF8059)", "partial_evidence_count": null, "pfam_id": "PF26248", "proteins": 59, "proteomes": 59, "short_name": "DUF8059", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26248", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 59, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in Halobacteria. The domain is predominantly found in archaea, with a notable presence in the Halorubrum genus. Proteins containing this domain are typically between 150 and 190 amino acids in length. The domain is predicted to be part of integral membrane proteins with four predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058476", "known_evidence_count": null, "matches": 59, "name": "Domain of unknown function (DUF8162)", "partial_evidence_count": null, "pfam_id": "PF26494", "proteins": 59, "proteomes": 53, "short_name": "DUF8162", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26494", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from the Bacteroidota phylum, particularly within the Chitinophagales order. Proteins in this family are found in various bacterial species, including Chitinophaga and Flavobacterium. The proteins typically range from approximately 200 to 380 amino acids in length. This family corresponds to a duplication of a PH-domain-like fold.", "domain_architectures": 1, "interpro_id": "IPR058497", "known_evidence_count": null, "matches": 59, "name": "Family of unknown function (DUF8184)", "partial_evidence_count": null, "pfam_id": "PF26559", "proteins": 59, "proteomes": 53, "short_name": "DUF8184", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26559", "structures": 0, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved region found in uncharacterised proteins. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds. These disulfide bonds are shared between beta-hairpins and alpha-helical turns which are repeated along this region.", "domain_architectures": 4, "interpro_id": "IPR059375", "known_evidence_count": null, "matches": 63, "name": "Family of unknown function (DUF8331)", "partial_evidence_count": null, "pfam_id": "PF27011", "proteins": 59, "proteomes": 20, "short_name": "DUF8331", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27011", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Myxococcota lineage. It is predicted to fold into a globular structure comprising a four stranded beta-sheet packed with two helices. It contains two highly conserved cysteine and a histidine residues that may coordinate a metal ion. The position of the fourth residues is not conserved but it is always present in a close proximity.", "domain_architectures": 5, "interpro_id": "IPR059388", "known_evidence_count": null, "matches": 59, "name": "Domain of unknown function (DUF8344)", "partial_evidence_count": null, "pfam_id": "PF27043", "proteins": 59, "proteomes": 41, "short_name": "DUF8344", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27043", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in a group of uncharacterised sequences mainly from bacteria.", "domain_architectures": 5, "interpro_id": "IPR061628", "known_evidence_count": null, "matches": 59, "name": "Domain of unknown function (DUF8559)", "partial_evidence_count": null, "pfam_id": "PF29526", "proteins": 59, "proteomes": 53, "short_name": "DUF8559", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29526", "structures": 0, "taxa": 161, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised metazoan proteins predicted to fold into array of alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR061863", "known_evidence_count": null, "matches": 61, "name": "Domain of unknown function (DUF8802)", "partial_evidence_count": null, "pfam_id": "PF31071", "proteins": 59, "proteomes": 10, "short_name": "DUF8802", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31071", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 58, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical archaeal proteins of around 120 residues in length. All members of this family seem to be Sulfolobus species specific. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009705", "known_evidence_count": null, "matches": 58, "name": "Protein of unknown function (DUF1286)", "partial_evidence_count": null, "pfam_id": "PF06939", "proteins": 58, "proteomes": 36, "short_name": "DUF1286", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06939", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR016675", "known_evidence_count": null, "matches": 58, "name": "Uncharacterized protein conserved in archaea (DUF2139)", "partial_evidence_count": null, "pfam_id": "PF09910", "proteins": 58, "proteomes": 54, "short_name": "DUF2139", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09910", "structures": 0, "taxa": 128, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 470 amino acids in length. There are two conserved sequence motifs: HLL and RYL.", "domain_architectures": 4, "interpro_id": "IPR027863", "known_evidence_count": null, "matches": 58, "name": "Domain of unknown function (DUF4623)", "partial_evidence_count": null, "pfam_id": "PF15416", "proteins": 58, "proteomes": 56, "short_name": "DUF4623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15416", "structures": 1, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "NaturalProductMech": 2 } }, "demotion_reasons": [], "description": "This family of unknown function is associated with the biosynthetic gene cluster for anacyclamide A10. The family appears to be restricted to Cyanobacteria. Some matches also contain a methyltransferase domain at the N terminus.", "domain_architectures": 2, "interpro_id": "IPR031037", "known_evidence_count": null, "matches": 58, "name": "Family of unknown function (DUF5838)", "partial_evidence_count": null, "pfam_id": "PF19156", "proteins": 58, "proteomes": 32, "short_name": "DUF5838", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19156", "structures": 12, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of bacterial proteins composed of an all beta strand domain composed of 7 beta strands. Structure prediction suggests that these proteins will form a complex with proteins from [pfam:PF24848].", "domain_architectures": 1, "interpro_id": "IPR056141", "known_evidence_count": null, "matches": 58, "name": "Domain of unknown function (DUF7724)", "partial_evidence_count": null, "pfam_id": "PF24849", "proteins": 58, "proteomes": 55, "short_name": "DUF7724", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24849", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. These proteins are about 60 residues long and adopt a small compact alpha helical bundle domain.", "domain_architectures": 1, "interpro_id": "IPR058340", "known_evidence_count": null, "matches": 58, "name": "Domain of unknown function (DUF8027)", "partial_evidence_count": null, "pfam_id": "PF26070", "proteins": 58, "proteomes": 58, "short_name": "DUF8027", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26070", "structures": 0, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins from C. elegans.", "domain_architectures": 2, "interpro_id": "IPR007465", "known_evidence_count": null, "matches": 57, "name": "Domain of unknown function (DUF508)", "partial_evidence_count": null, "pfam_id": "PF04370", "proteins": 57, "proteomes": 33, "short_name": "DUF508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04370", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Chlamydia proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR007966", "known_evidence_count": null, "matches": 57, "name": "Protein of unknown function (DUF720)", "partial_evidence_count": null, "pfam_id": "PF05302", "proteins": 57, "proteomes": 19, "short_name": "DUF720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05302", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region approximately 130 residues long within a number of proteins of unknown function that seem to be specific to the white spot syndrome virus (WSSV).", "domain_architectures": 2, "interpro_id": "IPR009766", "known_evidence_count": null, "matches": 57, "name": "Protein of unknown function (DUF1335)", "partial_evidence_count": null, "pfam_id": "PF07056", "proteins": 57, "proteomes": 13, "short_name": "DUF1335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07056", "structures": 0, "taxa": 10, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 56, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family of hypothetical archaeal proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR017006", "known_evidence_count": null, "matches": 57, "name": "Uncharacterized protein conserved in archaea (DUF2286)", "partial_evidence_count": null, "pfam_id": "PF10051", "proteins": 57, "proteomes": 57, "short_name": "DUF2286", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10051", "structures": 0, "taxa": 130, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This cysteine-rich family is expressed by the double-stranded Nucleopolyhedrovirus, a member of the Baculoviridae family of dsDNA viruses. The function is not known.", "domain_architectures": 2, "interpro_id": "IPR020201", "known_evidence_count": null, "matches": 58, "name": "Protein of unknown function (DUF2616)", "partial_evidence_count": null, "pfam_id": "PF11077", "proteins": 57, "proteomes": 57, "short_name": "DUF2616", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11077", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 5 } }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as YqbG however this cannot be confirmed. Currently the proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR013514", "known_evidence_count": null, "matches": 57, "name": "Protein of unknown function (DUF3199)", "partial_evidence_count": null, "pfam_id": "PF11436", "proteins": 57, "proteomes": 51, "short_name": "DUF3199", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11436", "structures": 2, "taxa": 116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain family is found in viruses, and is approximately 70 amino acids in length. The family is found in association with [pfam:PF01577]. There is a conserved FLE sequence motif.", "domain_architectures": 6, "interpro_id": "IPR022199", "known_evidence_count": null, "matches": 57, "name": "Protein of unknown function (DUF3725)", "partial_evidence_count": null, "pfam_id": "PF12523", "proteins": 57, "proteomes": 8, "short_name": "DUF3725", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12523", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025023", "known_evidence_count": null, "matches": 57, "name": "Protein of unknown function (DUF3912)", "partial_evidence_count": null, "pfam_id": "PF13051", "proteins": 57, "proteomes": 57, "short_name": "DUF3912", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13051", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein of around 185-188 amino acids found in phages that infect Cutibacterium and Propionibacterium species. The function of this protein is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR055612", "known_evidence_count": null, "matches": 57, "name": "Family of unknown function (DUF7188)", "partial_evidence_count": null, "pfam_id": "PF23817", "proteins": 57, "proteomes": 57, "short_name": "DUF7188", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23817", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents and uncharacterised family of phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055694", "known_evidence_count": null, "matches": 57, "name": "Domain of unknown function (DUF7270)", "partial_evidence_count": null, "pfam_id": "PF23934", "proteins": 57, "proteomes": 56, "short_name": "DUF7270", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23934", "structures": 0, "taxa": 127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of domains found in phages that infect a variety of bacterial hosts including Streptococcus, Streptomyces, Pseudomonas and Paenibacillus species. The Domain is typically around 110-130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR055720", "known_evidence_count": null, "matches": 57, "name": "Domain of unknown function (DUF7296)", "partial_evidence_count": null, "pfam_id": "PF23969", "proteins": 57, "proteomes": 56, "short_name": "DUF7296", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23969", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal OB-fold domain found in nematode proteins that generally contain 3 OB-like domains.", "domain_architectures": 6, "interpro_id": "IPR057690", "known_evidence_count": null, "matches": 57, "name": "Domain of unknown function (DUF7930)", "partial_evidence_count": null, "pfam_id": "PF25558", "proteins": 57, "proteomes": 54, "short_name": "DUF7930", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25558", "structures": 0, "taxa": 132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins in this family are predominantly found in the class Halobacteria, which includes organisms such as Haloferacaceae and Halobacteriales. The proteins in this family typically range from 124 to 143 amino acids in length. Many proteins in this family contain predicted coiled-coil regions.", "domain_architectures": 2, "interpro_id": "IPR058417", "known_evidence_count": null, "matches": 57, "name": "Family of unknown function (DUF8104)", "partial_evidence_count": null, "pfam_id": "PF26406", "proteins": 57, "proteomes": 56, "short_name": "DUF8104", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26406", "structures": 0, "taxa": 131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several repeats of 31 residues in length and seems to be exclusive to Moraxella catarrhalis UspA proteins. The UspA1 and UspA2 proteins of Moraxella catarrhalis are structurally related and are exposed on the bacterial cell surface where can function adhesins [[cite:PUB00012385]]. This family is commonly found with the [pfam:PF03895] family.", "domain_architectures": 19, "interpro_id": "IPR010494", "known_evidence_count": null, "matches": 171, "name": "Repeat of unknown function (DUF1079)", "partial_evidence_count": null, "pfam_id": "PF06435", "proteins": 56, "proteomes": 4, "short_name": "DUF1079", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06435", "structures": 2, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as Plectrovirus orf 10 transmembrane proteins however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR021217", "known_evidence_count": null, "matches": 56, "name": "Protein of unknown function (DUF2649)", "partial_evidence_count": null, "pfam_id": "PF10854", "proteins": 56, "proteomes": 9, "short_name": "DUF2649", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10854", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 131 and 312 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR022131", "known_evidence_count": null, "matches": 56, "name": "Surface protein", "partial_evidence_count": null, "pfam_id": "PF12406", "proteins": 56, "proteomes": 1, "short_name": "DUF3664", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12406", "structures": 0, "taxa": 16, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "DUF4705 is a family of repeated domains that is found in eukaryotes. It can occur up to 10 times in any one sequence. The repeat is rich in glycine and proline residues.", "domain_architectures": 7, "interpro_id": "IPR031572", "known_evidence_count": null, "matches": 184, "name": "Domain of unknown function (DUF4705)", "partial_evidence_count": null, "pfam_id": "PF15788", "proteins": 56, "proteomes": 9, "short_name": "DUF4705", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15788", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chromadorea.", "domain_architectures": 8, "interpro_id": "", "known_evidence_count": null, "matches": 71, "name": "Family of unknown function (DUF5401)", "partial_evidence_count": null, "pfam_id": "PF17380", "proteins": 56, "proteomes": 45, "short_name": "DUF5401", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17380", "structures": 0, "taxa": 205, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001796) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the tauramamide biosynthetic gene cluster from Brevibacillus laterosporus DSM 25 and appears to be predominantly found in bacteria [[cite:PUB00098905]].", "domain_architectures": 1, "interpro_id": "IPR046079", "known_evidence_count": null, "matches": 56, "name": "Family of unknown function (DUF6097)", "partial_evidence_count": null, "pfam_id": "PF19592", "proteins": 56, "proteomes": 55, "short_name": "DUF6097", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19592", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found towards the centre of some PRiA4b ORF-3-like proteins from bacteria, such as SwissProt:A0A068QX925. This domain is generally associated to PriA4_ORF3 ([pfam:PF07929]) domain.", "domain_architectures": 6, "interpro_id": "IPR055825", "known_evidence_count": null, "matches": 56, "name": "Domain of unknown function (DUF7401)", "partial_evidence_count": null, "pfam_id": "PF24134", "proteins": 56, "proteomes": 56, "short_name": "DUF7401", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24134", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized family found in various bacteriophage proteins. It is predominantly found in phages infecting diverse bacterial species including Burkholderia, Bacillus, Streptomyces, Listeria, and Caulobacter. The proteins are typically around 100-150 amino acids in length. Many of the proteins containing this domain are annotated as uncharacterized or hypothetical proteins. The proteins form a compact domain composed of a four stranded antiparallel beta sheet.", "domain_architectures": 1, "interpro_id": "IPR055870", "known_evidence_count": null, "matches": 56, "name": "Family of unknown function (DUF7447)", "partial_evidence_count": null, "pfam_id": "PF24239", "proteins": 56, "proteomes": 53, "short_name": "DUF7447", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24239", "structures": 0, "taxa": 156, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of caudovirus proteins that lack a globular structure. The family include phage PhiTE phiTE_157 [swissprot:K9L4C5].", "domain_architectures": 1, "interpro_id": "IPR058360", "known_evidence_count": null, "matches": 56, "name": "Family of unknown function (DUF8047)", "partial_evidence_count": null, "pfam_id": "PF26220", "proteins": 56, "proteomes": 56, "short_name": "DUF8047", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26220", "structures": 0, "taxa": 127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins from halobacteria which are predicted to contain three transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR061600", "known_evidence_count": null, "matches": 56, "name": "Family of unknown function (DUF8530)", "partial_evidence_count": null, "pfam_id": "PF29293", "proteins": 56, "proteomes": 54, "short_name": "DUF8530", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29293", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of hypothetical Chlamydia proteins. This family may well comprise of two domains, as some members only match the N-terminus.", "domain_architectures": 1, "interpro_id": "IPR006974", "known_evidence_count": null, "matches": 55, "name": "Family of unknown function (DUF648)", "partial_evidence_count": null, "pfam_id": "PF04890", "proteins": 55, "proteomes": 13, "short_name": "DUF648", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04890", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 55, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 1, "interpro_id": "IPR018686", "known_evidence_count": null, "matches": 55, "name": "Uncharacterized protein conserved in archaea (DUF2175)", "partial_evidence_count": null, "pfam_id": "PF09943", "proteins": 55, "proteomes": 55, "short_name": "DUF2175", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09943", "structures": 0, "taxa": 144, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length. This domain is the phage-like element pbsx protein xkdh.", "domain_architectures": 1, "interpro_id": "IPR024556", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF3599)", "partial_evidence_count": null, "pfam_id": "PF12206", "proteins": 55, "proteomes": 49, "short_name": "DUF3599", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12206", "structures": 1, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 176 and 195 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025093", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF4020)", "partial_evidence_count": null, "pfam_id": "PF13212", "proteins": 55, "proteomes": 55, "short_name": "DUF4020", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13212", "structures": 0, "taxa": 165, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 350 residues in length and is mainly found in various Parabacteroides, Bacteroides and Porphyromonas species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032325", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF4852)", "partial_evidence_count": null, "pfam_id": "PF16144", "proteins": 55, "proteomes": 53, "short_name": "DUF4852", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16144", "structures": 0, "taxa": 189, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses. This family is also found in eukaryotes and Bacteria.", "domain_architectures": 4, "interpro_id": "IPR045417", "known_evidence_count": null, "matches": 55, "name": "Family of unknown function (DUF5898)", "partial_evidence_count": null, "pfam_id": "PF19250", "proteins": 55, "proteomes": 18, "short_name": "DUF5898", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19250", "structures": 0, "taxa": 102, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000081) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the kedarcidin biosynthetic gene cluster from Streptoalloteichus sp. ATCC 53650 [[cite:PUB00098878]].", "domain_architectures": 1, "interpro_id": "IPR045631", "known_evidence_count": null, "matches": 55, "name": "Family of unknown function (DUF6315)", "partial_evidence_count": null, "pfam_id": "PF19836", "proteins": 55, "proteomes": 55, "short_name": "DUF6315", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19836", "structures": 0, "taxa": 91, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterized bacteriophage proteins, typically around 70-80 amino acids in length. They are found in phages infecting Escherichia, Pseudomonas, Salmonella, Vibrio, and other bacterial hosts.", "domain_architectures": 1, "interpro_id": "IPR055619", "known_evidence_count": null, "matches": 55, "name": "Family of unknown function (DUF7195)", "partial_evidence_count": null, "pfam_id": "PF23825", "proteins": 55, "proteomes": 53, "short_name": "DUF7195", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23825", "structures": 0, "taxa": 135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in several bacteriophages that infect bacteria such as Escherichia coli, Enterobacter, Klebsiella and Shigella. The protein is short, around 44-51 amino acids in length. It is predicted to contain a single transmembrane helix. The function of this protein is currently unknown. One representative of this family is the [swissprot:P18922] protein from bacteriophage T4.", "domain_architectures": 1, "interpro_id": "IPR055820", "known_evidence_count": null, "matches": 55, "name": "Family of unknown function (DUF7396)", "partial_evidence_count": null, "pfam_id": "PF24129", "proteins": 55, "proteomes": 55, "short_name": "DUF7396", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24129", "structures": 0, "taxa": 129, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from uncharacterised proteins found mainly in Firmicutes. It is predicted to adopt a globular structure consisting of a curved beta-sheet and alpha-helices packed on one side of it. It contains a number of conserved aromatic hydrophobic residues, some of which are predicted to be solvent-exposed.", "domain_architectures": 1, "interpro_id": "IPR056115", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF7698)", "partial_evidence_count": null, "pfam_id": "PF24753", "proteins": 55, "proteomes": 50, "short_name": "DUF7698", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24753", "structures": 0, "taxa": 157, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised beta-sandwich domain found in a small family of uncharacterised halobacterial proteins. STRING shows that this protein is often found associated with a [pfam:PF10936] domain and an SpeE enzyme.", "domain_architectures": 1, "interpro_id": "IPR059273", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF8229)", "partial_evidence_count": null, "pfam_id": "PF26682", "proteins": 55, "proteomes": 53, "short_name": "DUF8229", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26682", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in uncharacterised sequences from nematodes. It may adopt a structure similar to that of the von Willebrand factor superfamily.", "domain_architectures": 3, "interpro_id": "IPR061520", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF8450)", "partial_evidence_count": null, "pfam_id": "PF28725", "proteins": 55, "proteomes": 40, "short_name": "DUF8450", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28725", "structures": 0, "taxa": 96, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt ubiquitin-like fold.", "domain_architectures": 16, "interpro_id": "IPR061793", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF8732)", "partial_evidence_count": null, "pfam_id": "PF30779", "proteins": 55, "proteomes": 14, "short_name": "DUF8732", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30779", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes several uncharacterised proteins from Caenorhabditis elegans.", "domain_architectures": 11, "interpro_id": "IPR006836", "known_evidence_count": null, "matches": 131, "name": "Protein of unknown function, DUF612", "partial_evidence_count": null, "pfam_id": "PF04747", "proteins": 54, "proteomes": 21, "short_name": "DUF612", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04747", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several enterobacterial and siphoviral sequences of unknown function.", "domain_architectures": 1, "interpro_id": "IPR008544", "known_evidence_count": null, "matches": 54, "name": "Protein of unknown function (DUF826)", "partial_evidence_count": null, "pfam_id": "PF05696", "proteins": 54, "proteomes": 37, "short_name": "DUF826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05696", "structures": 0, "taxa": 104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The members of this family are all derived from relatively short hypothetical proteins thought to be expressed by various Nucleopolyhedroviruses.", "domain_architectures": 1, "interpro_id": "IPR012428", "known_evidence_count": null, "matches": 54, "name": "Protein of unknown function (DUF1623)", "partial_evidence_count": null, "pfam_id": "PF07785", "proteins": 54, "proteomes": 53, "short_name": "DUF1623", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07785", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function.", "domain_architectures": 2, "interpro_id": "IPR014515", "known_evidence_count": null, "matches": 54, "name": "Uncharacterized protein conserved in archaea (DUF2120)", "partial_evidence_count": null, "pfam_id": "PF09893", "proteins": 54, "proteomes": 54, "short_name": "DUF2120", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09893", "structures": 0, "taxa": 114, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain found in archaeal proteins, including PF2050 from Pyrococcus furiosus ([swissprot:Q8TZE5]). PF2050, with an overall globular structure, contain this domain twice, each showing an antiparallel beta-sheet and an alpha-helical bundle, and shows a positively charged basic cleft on one side. This protein interacts with circular and linear dsDNA [[cite:PUB00100885]].", "domain_architectures": 3, "interpro_id": "IPR022620", "known_evidence_count": null, "matches": 85, "name": "Domain of unknown function (DUF2666)", "partial_evidence_count": null, "pfam_id": "PF10869", "proteins": 54, "proteomes": 54, "short_name": "DUF2666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10869", "structures": 1, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 52, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Plasmodium.", "domain_architectures": 2, "interpro_id": "IPR021689", "known_evidence_count": null, "matches": 59, "name": "Protein of unknown function (DUF3271)", "partial_evidence_count": null, "pfam_id": "PF11675", "proteins": 54, "proteomes": 15, "short_name": "DUF3271", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11675", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025033", "known_evidence_count": null, "matches": 54, "name": "Protein of unknown function (DUF3920)", "partial_evidence_count": null, "pfam_id": "PF13058", "proteins": 54, "proteomes": 54, "short_name": "DUF3920", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13058", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025039", "known_evidence_count": null, "matches": 54, "name": "Protein of unknown function (DUF3947)", "partial_evidence_count": null, "pfam_id": "PF13135", "proteins": 54, "proteomes": 28, "short_name": "DUF3947", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13135", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of Firmicute proteins is frequently associated with the EAL, GGDEF and PAS families, [pfam:PF00563], [pfam:PF00990], and [pfam:PF00989]. The exact function is not known.", "domain_architectures": 11, "interpro_id": "IPR025152", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF4084)", "partial_evidence_count": null, "pfam_id": "PF13321", "proteins": 54, "proteomes": 49, "short_name": "DUF4084", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13321", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_2607, a putative uncharacterized protein. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011],[cite:PUB00056012]].", "domain_architectures": 1, "interpro_id": "IPR025190", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF4122)", "partial_evidence_count": null, "pfam_id": "PF13498", "proteins": 54, "proteomes": 40, "short_name": "DUF4122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13498", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 100 residues in length and found in various Sulfolobus species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032603", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF4898)", "partial_evidence_count": null, "pfam_id": "PF16239", "proteins": 54, "proteomes": 25, "short_name": "DUF4898", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16239", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of unknown function is found in Saccharomycetales.", "domain_architectures": 2, "interpro_id": "IPR035303", "known_evidence_count": null, "matches": 57, "name": "Family of unknown function (DUF5364)", "partial_evidence_count": null, "pfam_id": "PF17322", "proteins": 54, "proteomes": 51, "short_name": "DUF5364", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17322", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000498) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046006", "known_evidence_count": null, "matches": 54, "name": "Family of unknown function (DUF5962)", "partial_evidence_count": null, "pfam_id": "PF19387", "proteins": 54, "proteomes": 40, "short_name": "DUF5962", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19387", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. These possibly have an N-terminal signal peptide followed by a small compact domain composed of a single alpha helix packed against a four stranded beta sheet.", "domain_architectures": 1, "interpro_id": "IPR055716", "known_evidence_count": null, "matches": 54, "name": "Family of unknown function (DUF7292)", "partial_evidence_count": null, "pfam_id": "PF23964", "proteins": 54, "proteomes": 54, "short_name": "DUF7292", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23964", "structures": 0, "taxa": 123, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 53, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in Halobacteria. The proteins are predominantly found in various genera such as Halorubrum, Halostagnicola, and Halobacterium. The domain is approximately 64-72 amino acids in length. Proteins containing this domain are predicted to be integral membrane proteins with two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058454", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF8141)", "partial_evidence_count": null, "pfam_id": "PF26464", "proteins": 54, "proteomes": 53, "short_name": "DUF8141", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26464", "structures": 0, "taxa": 98, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains invariant histidine and three cysteine residues that are likely to coordinate a metal ion. It belongs to the superfamily of HC3 zinc fingers.", "domain_architectures": 1, "interpro_id": "IPR059380", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF8336)", "partial_evidence_count": null, "pfam_id": "PF27025", "proteins": 54, "proteomes": 52, "short_name": "DUF8336", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27025", "structures": 0, "taxa": 176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins.", "domain_architectures": 38, "interpro_id": "IPR061756", "known_evidence_count": null, "matches": 55, "name": "Domain of unknown function (DUF8695)", "partial_evidence_count": null, "pfam_id": "PF30704", "proteins": 54, "proteomes": 51, "short_name": "DUF8695", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30704", "structures": 1, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. It contains several conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 1, "interpro_id": "IPR061780", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF8719)", "partial_evidence_count": null, "pfam_id": "PF30742", "proteins": 54, "proteomes": 44, "short_name": "DUF8719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30742", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Archaeal domain of unknown function. This domain has been solved as part of a structural genomics project and comprises of segregated helical and anti-parallel beta sheet regions.", "domain_architectures": 1, "interpro_id": "IPR008032", "known_evidence_count": null, "matches": 53, "name": "Domain of unknown function (DUF749)", "partial_evidence_count": null, "pfam_id": "PF05370", "proteins": 53, "proteomes": 53, "short_name": "DUF749", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05370", "structures": 2, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial and phage proteins of around 115 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009712", "known_evidence_count": null, "matches": 53, "name": "Protein of unknown function (DUF1293)", "partial_evidence_count": null, "pfam_id": "PF06950", "proteins": 53, "proteomes": 51, "short_name": "DUF1293", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06950", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. The domain shows structural similarity to KH domains suggesting it may have an RNA-binding function.", "domain_architectures": 1, "interpro_id": "IPR056730", "known_evidence_count": null, "matches": 53, "name": "DUF2096 C-terminal KH-like domain", "partial_evidence_count": null, "pfam_id": "PF09869", "proteins": 53, "proteomes": 53, "short_name": "KH_DUF2096_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09869", "structures": 0, "taxa": 101, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in viruses. Proteins in this family are typically between 162 and 495 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR022054", "known_evidence_count": null, "matches": 53, "name": "Protein of unknown function (DUF3614)", "partial_evidence_count": null, "pfam_id": "PF12267", "proteins": 53, "proteomes": 2, "short_name": "DUF3614", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12267", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in viruses, and is approximately 70 amino acids in length. The family is found in association with [pfam:PF00073], [pfam:PF08935].", "domain_architectures": 2, "interpro_id": "IPR022098", "known_evidence_count": null, "matches": 53, "name": "Protein of unknown function (DUF3637)", "partial_evidence_count": null, "pfam_id": "PF12337", "proteins": 53, "proteomes": 14, "short_name": "DUF3637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12337", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in viruses, and is approximately 80 amino acids in length. The family is found in association with [pfam:PF05533].", "domain_architectures": 2, "interpro_id": "IPR022239", "known_evidence_count": null, "matches": 53, "name": "Protein of unknown function (DUF3762)", "partial_evidence_count": null, "pfam_id": "PF12591", "proteins": 53, "proteomes": 1, "short_name": "DUF3762", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12591", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small, compact all-alpha helical domain of unknown function. This domain is currently only found in Clostridiales species.", "domain_architectures": 1, "interpro_id": "IPR024212", "known_evidence_count": null, "matches": 53, "name": "Domain of unknown function (DUF3837)", "partial_evidence_count": null, "pfam_id": "PF12939", "proteins": 53, "proteomes": 52, "short_name": "DUF3837", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12939", "structures": 1, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is believed to be involved in the type VII secretion system.", "domain_architectures": 1, "interpro_id": "IPR031690", "known_evidence_count": null, "matches": 53, "name": "Domain of unknown function (DUF5079)", "partial_evidence_count": null, "pfam_id": "PF16882", "proteins": 53, "proteomes": 25, "short_name": "DUF5079", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16882", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000990) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the epothilone biosynthetic gene cluster from Sorangium cellulosum [[cite:PUB00015753]]. This family appears to be predominantly found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR045757", "known_evidence_count": null, "matches": 53, "name": "Family of unknown function (DUF6184)", "partial_evidence_count": null, "pfam_id": "PF19682", "proteins": 53, "proteomes": 29, "short_name": "DUF6184", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19682", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain, found in various hypothetical archaeal proteins, has no known function. This N-terminal domain is composed of four alpha helices.", "domain_architectures": 1, "interpro_id": "IPR056731", "known_evidence_count": null, "matches": 53, "name": "DUF2096 N-terminal four-helical bundle domain", "partial_evidence_count": null, "pfam_id": "PF23100", "proteins": 53, "proteomes": 53, "short_name": "DUF2096_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23100", "structures": 0, "taxa": 101, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small transmembrane proteins found exclusively in extremely halophilic archaea (Halobacteria). Members of this family typically contain two transmembrane helices with a conserved cytoplasmic region. Most proteins in this family are approximately 115-130 amino acids in length. The family is widely distributed across different genera within Halobacteriales, including Halococcus, Haloferax, Natrialba, Natronobacterium, and Haladaptatus. The specific function of these proteins remains unknown, but their conservation suggests they may play an important role in the adaptation to high-salt environments.", "domain_architectures": 1, "interpro_id": "IPR058410", "known_evidence_count": null, "matches": 53, "name": "Domain of unknown function (DUF8097)", "partial_evidence_count": null, "pfam_id": "PF26397", "proteins": 53, "proteomes": 45, "short_name": "DUF8097", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26397", "structures": 0, "taxa": 99, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins in this family are predominantly found in halophilic archaea, specifically within the Halobacteria class. The family includes proteins from various genera such as Haloarculaceae, Natrialbaceae, and Haloferacaceae. Proteins in this family typically range from 320 to 400 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR058411", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF8098)", "partial_evidence_count": null, "pfam_id": "PF26400", "proteins": 53, "proteomes": 50, "short_name": "DUF8098", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26400", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 63 residues found in uncharacterised proteins from Cyanobacteriota. The proteins containing this domain are annotated as putative helix-turn-helix regulators. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061692", "known_evidence_count": null, "matches": 53, "name": "Domain of unknown function (DUF8631)", "partial_evidence_count": null, "pfam_id": "PF30564", "proteins": 53, "proteomes": 52, "short_name": "DUF8631", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30564", "structures": 0, "taxa": 158, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins with unknown function appear to be restricted to Alphaproteobacteria.", "domain_architectures": 3, "interpro_id": "IPR021387", "known_evidence_count": null, "matches": 61, "name": "Protein of unknown function (DUF3023)", "partial_evidence_count": null, "pfam_id": "PF11224", "proteins": 52, "proteomes": 7, "short_name": "DUF3023", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11224", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 150 residues locates in the C-terminal of some uncharacterized proteins in various Bacteroides and Prevotella species. The function of this family remains unknown.", "domain_architectures": 3, "interpro_id": "IPR032271", "known_evidence_count": null, "matches": 52, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16377", "proteins": 52, "proteomes": 40, "short_name": "DUF4987", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16377", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001943) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the vioprolides A biosynthetic gene cluster from Cystobacter sp. [[cite:PUB00098917]]. This family appears to be predominantly found in bacteria.", "domain_architectures": 3, "interpro_id": "IPR045680", "known_evidence_count": null, "matches": 52, "name": "Family of unknown function (DUF6200)", "partial_evidence_count": null, "pfam_id": "PF19702", "proteins": 52, "proteomes": 38, "short_name": "DUF6200", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19702", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of uncharacterized DUF3829-like proteins. It might be related to [pfam:PF12889]. Its function is unknown.", "domain_architectures": 2, "interpro_id": "IPR049273", "known_evidence_count": null, "matches": 52, "name": "Domain of unknown function (DUF6845)", "partial_evidence_count": null, "pfam_id": "PF20893", "proteins": 52, "proteomes": 48, "short_name": "DUF6845", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20893", "structures": 3, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 49, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain found in a family of uncharacterized proteins in nematodes. This domain is predicted to fold as a beta-sheet composed of four anti-parallel beta-strands.", "domain_architectures": 9, "interpro_id": "IPR055465", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF7037)", "partial_evidence_count": null, "pfam_id": "PF23045", "proteins": 52, "proteomes": 9, "short_name": "DUF7037", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23045", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in bacteriophage proteins, particularly those infecting Salmonella and Dickeya species. The domain is approximately 150 residues in length. The function of this domain is currently unknown.", "domain_architectures": 2, "interpro_id": "IPR055605", "known_evidence_count": null, "matches": 53, "name": "Domain of unknown function (DUF7181)", "partial_evidence_count": null, "pfam_id": "PF23808", "proteins": 52, "proteomes": 52, "short_name": "DUF7181", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23808", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of unknown function found in phage proteins, typically 120-130 amino acids in length. Some members contain a C-terminal region enriched in basic residues that is predicted to be disordered. The N-terminus of the proteins contain a small globular domain. These proteins are found in the Ackermannviridae family of phages that infect Enterobacteria such as Salmonella, Escherichia, Shigella, and Dickeya.", "domain_architectures": 1, "interpro_id": "IPR055655", "known_evidence_count": null, "matches": 52, "name": "Family of unknown function (DUF7231)", "partial_evidence_count": null, "pfam_id": "PF23877", "proteins": 52, "proteomes": 52, "short_name": "DUF7231", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23877", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised eukaryotic proteins. It contains two highly conserved cysteines. This domain is predicted to fold into Ig-like beta-sandwich.", "domain_architectures": 17, "interpro_id": "IPR055921", "known_evidence_count": null, "matches": 79, "name": "Domain of unknown function (DUF7498)", "partial_evidence_count": null, "pfam_id": "PF24328", "proteins": 52, "proteomes": 31, "short_name": "DUF7498", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24328", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. It shares detectable similarity to a number of type II restriction endonucleases such as DpnII and Ecl18kI and it is predicted to adopt similar structure. It is likely to possess endonuclease activity given the conservation of putative functional site residues.", "domain_architectures": 2, "interpro_id": "IPR056104", "known_evidence_count": null, "matches": 52, "name": "Domain of unknown function (DUF7687)", "partial_evidence_count": null, "pfam_id": "PF24736", "proteins": 52, "proteomes": 50, "short_name": "DUF7687", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24736", "structures": 0, "taxa": 187, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is usually found in tandem in uncharacterised bacterial proteins. It is predicted to adopt a globular structure consisting of a curved anti-parallel beta-sheet and alpha helices packed on one side of it. It contains highly conserved aspartate and histidine residues that may constitute a metal binding site.", "domain_architectures": 3, "interpro_id": "IPR056117", "known_evidence_count": null, "matches": 63, "name": "Domain of unknown function (DUF7700)", "partial_evidence_count": null, "pfam_id": "PF24777", "proteins": 52, "proteomes": 34, "short_name": "DUF7700", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24777", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly form gram-negative bacteria. It is predicted to fold into an unique alpha/beta structure composed of a central mixed beta-sheet and alpha-helices packed on it. Homologues contains several highly conserved positively charged residues.", "domain_architectures": 2, "interpro_id": "IPR058505", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF8192)", "partial_evidence_count": null, "pfam_id": "PF26612", "proteins": 52, "proteomes": 48, "short_name": "DUF8192", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26612", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a structure with a significant similarity to known galactose binding domains.", "domain_architectures": 1, "interpro_id": "IPR059485", "known_evidence_count": null, "matches": 52, "name": "Domain of unknown function (DUF8441)", "partial_evidence_count": null, "pfam_id": "PF28587", "proteins": 52, "proteomes": 50, "short_name": "DUF8441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28587", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group of uncharacterised sequences from bacteria, and is associated with [pfam:PF16283] at the N-terminal. This domain may adopt a structure with complex beta-sheets and associated alpha-helices similar to those found in HORMA domains.", "domain_architectures": 2, "interpro_id": "IPR061542", "known_evidence_count": null, "matches": 52, "name": "Domain of unknown function (DUF8472)", "partial_evidence_count": null, "pfam_id": "PF28875", "proteins": 52, "proteomes": 47, "short_name": "DUF8472", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28875", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. It is predicted to adopt Ig-like fold.", "domain_architectures": 2, "interpro_id": "IPR061766", "known_evidence_count": null, "matches": 52, "name": "Domain of unknown function (DUF8705)", "partial_evidence_count": null, "pfam_id": "PF30723", "proteins": 52, "proteomes": 52, "short_name": "DUF8705", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30723", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains a number of viral proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009641", "known_evidence_count": null, "matches": 51, "name": "Protein of unknown function (DUF1235)", "partial_evidence_count": null, "pfam_id": "PF06822", "proteins": 51, "proteomes": 33, "short_name": "DUF1235", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06822", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a small family of highly conserved proteins from bacteria, in particular Helicobacter species, The structure is a bundle of alpha helices. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019469", "known_evidence_count": null, "matches": 51, "name": "Protein of unknown function (DUF2443)", "partial_evidence_count": null, "pfam_id": "PF10398", "proteins": 51, "proteomes": 50, "short_name": "DUF2443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10398", "structures": 1, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae. The family has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR020155", "known_evidence_count": null, "matches": 51, "name": "Protein of unknown function (DUF2542)", "partial_evidence_count": null, "pfam_id": "PF10808", "proteins": 51, "proteomes": 51, "short_name": "DUF2542", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10808", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and viruses. Proteins in this family are typically between 90 and 105 amino acids in length. There is a conserved GLA sequence motif.", "domain_architectures": 1, "interpro_id": "IPR031858", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF4752)", "partial_evidence_count": null, "pfam_id": "PF15944", "proteins": 51, "proteomes": 47, "short_name": "DUF4752", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15944", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 210 residues in length and found in various Bacteroides and Prevotella species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032597", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF4903)", "partial_evidence_count": null, "pfam_id": "PF16246", "proteins": 51, "proteomes": 46, "short_name": "DUF4903", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16246", "structures": 0, "taxa": 96, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 400 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032573", "known_evidence_count": null, "matches": 67, "name": "Domain of unknown function (DUF4925)", "partial_evidence_count": null, "pfam_id": "PF16272", "proteins": 51, "proteomes": 31, "short_name": "DUF4925", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16272", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of uncharacterized proteins around 200 residues in length and is mainly found in various Bacteroides, Paraprevotella, Parabacteroides and Alistipes species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032541", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF4948)", "partial_evidence_count": null, "pfam_id": "PF16306", "proteins": 51, "proteomes": 40, "short_name": "DUF4948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16306", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 2, "interpro_id": "IPR043885", "known_evidence_count": null, "matches": 53, "name": "Family of unknown function (DUF5847)", "partial_evidence_count": null, "pfam_id": "PF19165", "proteins": 51, "proteomes": 12, "short_name": "DUF5847", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19165", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterized proteins is found in viruses, primarily cyanophages that infect cyanobacteria such as Synechococcus and Prochlorococcus species. The family contains short sequences, generally between 45-50 amino acid residues in length. No functional information is available for members of this family.", "domain_architectures": 1, "interpro_id": "IPR055615", "known_evidence_count": null, "matches": 51, "name": "Family of unknown function (DUF7191)", "partial_evidence_count": null, "pfam_id": "PF23821", "proteins": 51, "proteomes": 51, "short_name": "DUF7191", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23821", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins that adopt a compact domain composed of a four stranded beta sheet followed by two alpha helices packed on one side of the sheet.", "domain_architectures": 1, "interpro_id": "IPR055678", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF7254)", "partial_evidence_count": null, "pfam_id": "PF23912", "proteins": 51, "proteomes": 51, "short_name": "DUF7254", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23912", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. Structure prediction suggests these protein may form a homodimer. The dimer contains a large circular channel that is positively charged suggesting a possible DNA-binding function.", "domain_architectures": 2, "interpro_id": "IPR055800", "known_evidence_count": null, "matches": 51, "name": "Family of unknown function (DUF7376)", "partial_evidence_count": null, "pfam_id": "PF24091", "proteins": 51, "proteomes": 51, "short_name": "DUF7376", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24091", "structures": 0, "taxa": 134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 51, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain three predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058383", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF8070)", "partial_evidence_count": null, "pfam_id": "PF26267", "proteins": 51, "proteomes": 43, "short_name": "DUF8070", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26267", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved region located at the N terminus of uncharacterised fungal proteins. It contains a number of highly conserved arginine residues.", "domain_architectures": 3, "interpro_id": "IPR059262", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF8218)", "partial_evidence_count": null, "pfam_id": "PF26655", "proteins": 51, "proteomes": 51, "short_name": "DUF8218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26655", "structures": 0, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a family of proteins that are functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 340 and 435 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR061638", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF8577)", "partial_evidence_count": null, "pfam_id": "PF29640", "proteins": 51, "proteomes": 45, "short_name": "DUF8577", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29640", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of hypothetical bacterial and phage proteins of around 59 residues in length. Bacterial members of this family seem to be specific to Enterobacteria. The function of this family is unknown. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 1, "interpro_id": "IPR009808", "known_evidence_count": null, "matches": 50, "name": "Protein of unknown function (DUF1378)", "partial_evidence_count": null, "pfam_id": "PF07125", "proteins": 50, "proteomes": 36, "short_name": "DUF1378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07125", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 81 and 117 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR020274", "known_evidence_count": null, "matches": 50, "name": "Protein of unknown function (DUF2681)", "partial_evidence_count": null, "pfam_id": "PF10883", "proteins": 50, "proteomes": 41, "short_name": "DUF2681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10883", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins has no known function. Some members in the family are annotated as the P22 head assembly protein gp14 however this cannot be confirmed.", "domain_architectures": 2, "interpro_id": "IPR022568", "known_evidence_count": null, "matches": 50, "name": "Protein of unknown function (DUF2824)", "partial_evidence_count": null, "pfam_id": "PF11039", "proteins": 50, "proteomes": 44, "short_name": "DUF2824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11039", "structures": 0, "taxa": 145, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of uncharacterized proteins around 220 residues in length and is mainly found in various Streptococcus mutans species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032542", "known_evidence_count": null, "matches": 50, "name": "Domain of unknown function (DUF4947)", "partial_evidence_count": null, "pfam_id": "PF16305", "proteins": 50, "proteomes": 50, "short_name": "DUF4947", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16305", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteria.", "domain_architectures": 1, "interpro_id": "IPR035387", "known_evidence_count": null, "matches": 50, "name": "Family of unknown function (DUF5406)", "partial_evidence_count": null, "pfam_id": "PF17400", "proteins": 50, "proteomes": 48, "short_name": "DUF5406", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17400", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 45, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in various Platyhelminthes. This domain adopts a 6-bladed beta propeller structure.", "domain_architectures": 4, "interpro_id": "IPR043794", "known_evidence_count": null, "matches": 51, "name": "Domain of unknown function (DUF5736)", "partial_evidence_count": null, "pfam_id": "PF19007", "proteins": 50, "proteomes": 37, "short_name": "DUF5736", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19007", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 105 and 116 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046034", "known_evidence_count": null, "matches": 50, "name": "Family of unknown function (DUF5992)", "partial_evidence_count": null, "pfam_id": "PF19454", "proteins": 50, "proteomes": 33, "short_name": "DUF5992", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19454", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001387) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a protein from the nucleocidin biosynthetic gene cluster from Streptomyces calvus and appear to be predominantly found in Actinobacteria [[cite:PUB00099448]].", "domain_architectures": 1, "interpro_id": "IPR046069", "known_evidence_count": null, "matches": 50, "name": "Family of unknown function (DUF6027)", "partial_evidence_count": null, "pfam_id": "PF19492", "proteins": 50, "proteomes": 49, "short_name": "DUF6027", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19492", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria and archaea. Proteins in this family are approximately 160 amino acids in length. They are predicted to adopt globular alpha/beta structure. These proteins contain two highly conserved sequence motifs GxFDxWC and KRxKRLG that may be of functional importance.", "domain_architectures": 1, "interpro_id": "IPR054273", "known_evidence_count": null, "matches": 50, "name": "Family of unknown function (DUF7004)", "partial_evidence_count": null, "pfam_id": "PF22539", "proteins": 50, "proteomes": 50, "short_name": "DUF7004", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22539", "structures": 0, "taxa": 180, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in large phage virion structural proteins. The domain is approximately 290 to 330 amino acids in length. It is found in a variety of phage proteins infecting bacterial hosts such as Pseudomonas, Vibrio, Ralstonia, and Erwinia, among others.", "domain_architectures": 1, "interpro_id": "IPR055632", "known_evidence_count": null, "matches": 50, "name": "Family of unknown function (DUF7208)", "partial_evidence_count": null, "pfam_id": "PF23838", "proteins": 50, "proteomes": 49, "short_name": "DUF7208", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23838", "structures": 2, "taxa": 155, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in various phage and bacterial proteins. The domain is approximately 60-80 amino acids in length. The domain is composed of four alpha helices that form a small bundle. The surface of the domain is negatively charged.", "domain_architectures": 1, "interpro_id": "IPR055840", "known_evidence_count": null, "matches": 50, "name": "Domain of unknown function (DUF7417)", "partial_evidence_count": null, "pfam_id": "PF24192", "proteins": 50, "proteomes": 50, "short_name": "DUF7417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24192", "structures": 0, "taxa": 136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved protein family found in cyanophages that infect marine Synechococcus and Prochlorococcus. The function of this protein is unknown. It is typically 70-100 amino acids in length. The protein appears to be specific to cyanophages and is not found in their cyanobacterial hosts.", "domain_architectures": 1, "interpro_id": "IPR055891", "known_evidence_count": null, "matches": 50, "name": "Family of unknown function (DUF7468)", "partial_evidence_count": null, "pfam_id": "PF24272", "proteins": 50, "proteomes": 50, "short_name": "DUF7468", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24272", "structures": 0, "taxa": 148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes uncharacterised bacterial sequences that may adopt a novel fold consisting on three repeat units, each of them are type of beta-sandwich with three beta-strands on one side and four or five on the other.", "domain_architectures": 12, "interpro_id": "IPR055906", "known_evidence_count": null, "matches": 58, "name": "Domain of unknown function (DUF7483)", "partial_evidence_count": null, "pfam_id": "PF24299", "proteins": 50, "proteomes": 47, "short_name": "DUF7483", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24299", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised sequences that, according to structure predictions. they may consist on a novel repeat fold which comprise beta-hairpin-beta units organised in four and five units, forming two domains.", "domain_architectures": 5, "interpro_id": "IPR055909", "known_evidence_count": null, "matches": 68, "name": "Family of unknown function (DUF7486)", "partial_evidence_count": null, "pfam_id": "PF24307", "proteins": 50, "proteomes": 40, "short_name": "DUF7486", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24307", "structures": 0, "taxa": 183, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the Stenosarchaea group, including members of the Haloferacaceae, Natrialbaceae, and Methanomicrobiales. The domain is approximately 90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058449", "known_evidence_count": null, "matches": 50, "name": "Domain of unknown function (DUF8136)", "partial_evidence_count": null, "pfam_id": "PF26457", "proteins": 50, "proteomes": 45, "short_name": "DUF8136", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26457", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 48, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the class Halobacteria, which includes organisms from the orders Halobacteriales and families such as Haloferacaceae, Haloarculaceae, and Natrialbaceae. The proteins in this family are typically around 130-140 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR058475", "known_evidence_count": null, "matches": 50, "name": "Domain of unknown function (DUF8161) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26493", "proteins": 50, "proteomes": 41, "short_name": "DUF8161", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26493", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins predominantly from bacteria. It contains two pairs of conserved cysteine residues that may be involved in metal ion coordination. This domain is predicted to adopt a fold typical for zinc beta-ribbon domains.", "domain_architectures": 3, "interpro_id": "IPR059294", "known_evidence_count": null, "matches": 50, "name": "Domain of unknown function (DUF8250)", "partial_evidence_count": null, "pfam_id": "PF26757", "proteins": 50, "proteomes": 48, "short_name": "DUF8250", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26757", "structures": 0, "taxa": 186, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Protein of unknown function found in Borrelia burgdorferi, the Lyme disease spirochete.", "domain_architectures": 1, "interpro_id": "IPR006951", "known_evidence_count": null, "matches": 49, "name": "Protein of unknown function (DUF643)", "partial_evidence_count": null, "pfam_id": "PF04867", "proteins": 49, "proteomes": 15, "short_name": "DUF643", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04867", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR020325", "known_evidence_count": null, "matches": 49, "name": "Protein of unknown function (DUF2656)", "partial_evidence_count": null, "pfam_id": "PF10847", "proteins": 49, "proteomes": 45, "short_name": "DUF2656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10847", "structures": 0, "taxa": 168, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 142 and 211 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031427", "known_evidence_count": null, "matches": 49, "name": "Domain of unknown function (DUF4668)", "partial_evidence_count": null, "pfam_id": "PF15701", "proteins": 49, "proteomes": 10, "short_name": "DUF4668", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15701", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Drosophilidae. Proteins in this family are typically between 81 and 415 amino acids in length. This entry represents a conserved region found at the C-terminus of these proteins.", "domain_architectures": 2, "interpro_id": "IPR031806", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF4744)", "partial_evidence_count": null, "pfam_id": "PF15918", "proteins": 49, "proteomes": 26, "short_name": "DUF4744", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15918", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 190 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032215", "known_evidence_count": null, "matches": 49, "name": "Domain of unknown function (DUF5034)", "partial_evidence_count": null, "pfam_id": "PF16437", "proteins": 49, "proteomes": 47, "short_name": "DUF5034", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16437", "structures": 0, "taxa": 118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in various Platyhelminthes.", "domain_architectures": 2, "interpro_id": "IPR044041", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF5743)", "partial_evidence_count": null, "pfam_id": "PF19014", "proteins": 49, "proteomes": 25, "short_name": "DUF5743", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19014", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in Mimiviridae.", "domain_architectures": 2, "interpro_id": "IPR043908", "known_evidence_count": null, "matches": 57, "name": "Family of unknown function (DUF5769)", "partial_evidence_count": null, "pfam_id": "PF19073", "proteins": 49, "proteomes": 11, "short_name": "DUF5769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19073", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001171) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046007", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF5963)", "partial_evidence_count": null, "pfam_id": "PF19388", "proteins": 49, "proteomes": 47, "short_name": "DUF5963", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19388", "structures": 0, "taxa": 124, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000033) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the calicheamicin biosynthetic gene cluster from Micromonospora echinospora [[cite:PUB00099426]].", "domain_architectures": 1, "interpro_id": "IPR046046", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF6004)", "partial_evidence_count": null, "pfam_id": "PF19467", "proteins": 49, "proteomes": 48, "short_name": "DUF6004", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19467", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins that contain a small alpha helical bundle domain.", "domain_architectures": 1, "interpro_id": "IPR049239", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF6874)", "partial_evidence_count": null, "pfam_id": "PF21779", "proteins": 49, "proteomes": 46, "short_name": "DUF6874", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21779", "structures": 0, "taxa": 154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from fungi. This domain is predicted to adopt a globular structure consisting of a four helical bundle and having structural similarity to the alpha-helical domain inserted in the third Ig domain of the Trs130 component of the TRAPPII complex [[cite:PUB00153720]].", "domain_architectures": 8, "interpro_id": "IPR055506", "known_evidence_count": null, "matches": 49, "name": "Domain of unknown function (DUF7078)", "partial_evidence_count": null, "pfam_id": "PF23285", "proteins": 49, "proteomes": 48, "short_name": "DUF7078", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23285", "structures": 0, "taxa": 119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of viral proteins that are found in various bacteriophages infecting Gram-negative bacteria, such as Pseudomonas, Vibrio, Erwinia, Ralstonia, and Klebsiella. The family members are typically 800-1200 residues in length. Many are annotated as putative virion structural proteins, suggesting they may play a role in phage particle structure or assembly. However, the precise function of this family remains unknown.", "domain_architectures": 1, "interpro_id": "IPR055617", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF7193)", "partial_evidence_count": null, "pfam_id": "PF23823", "proteins": 49, "proteomes": 49, "short_name": "DUF7193", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23823", "structures": 1, "taxa": 176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from gammaproteobacteria. It is predicted to fold into a helical structure. It contains two highly conserved sequence motifs HxAWRYL and RAHNW that may be of functional importance.", "domain_architectures": 6, "interpro_id": "IPR059398", "known_evidence_count": null, "matches": 50, "name": "Domain of unknown function (DUF8354)", "partial_evidence_count": null, "pfam_id": "PF27620", "proteins": 49, "proteomes": 26, "short_name": "DUF8354", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27620", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta structure composed of a central four stranded beta-sheet packed on both sides with alpha helices.", "domain_architectures": 1, "interpro_id": "IPR059429", "known_evidence_count": null, "matches": 49, "name": "Domain of unknown function (DUF8385)", "partial_evidence_count": null, "pfam_id": "PF28363", "proteins": 49, "proteomes": 48, "short_name": "DUF8385", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28363", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a putative virion structural protein found in Caudoviricetes, the class of tailed bacteriophages. Proteins in this family are approximately 340-348 amino acids in length and appear to be single domain proteins. The specific function of this virion component remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061620", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF8550)", "partial_evidence_count": null, "pfam_id": "PF29428", "proteins": 49, "proteomes": 48, "short_name": "DUF8550", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29428", "structures": 1, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR022588", "known_evidence_count": null, "matches": 48, "name": "Protein of unknown function (DUF2659)", "partial_evidence_count": null, "pfam_id": "PF10858", "proteins": 48, "proteomes": 46, "short_name": "DUF2659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10858", "structures": 0, "taxa": 135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain is found in bacteria, and is typically between 97 and 111 amino acids in length, found at the C-terminal in most instances. According to structure predictions, it might have a beta-barrel fold.", "domain_architectures": 2, "interpro_id": "IPR025057", "known_evidence_count": null, "matches": 48, "name": "Domain of unknown function (DUF3994)", "partial_evidence_count": null, "pfam_id": "PF13159", "proteins": 48, "proteomes": 32, "short_name": "DUF3994", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13159", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes uncharacterised proteins predominantly found in Proteobacteria, such as [swissprot:Q9I380] from Pseudomonas aeruginosa. This protein folds into a five-stranded antiparallel beta -sheet sandwiched between two short alpha-helices [[cite:PUB00065044]].", "domain_architectures": 1, "interpro_id": "IPR031561", "known_evidence_count": null, "matches": 48, "name": "Domain of unknown function (DUF5086)", "partial_evidence_count": null, "pfam_id": "PF16985", "proteins": 48, "proteomes": 47, "short_name": "DUF5086", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16985", "structures": 1, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Euryarchaeota.", "domain_architectures": 1, "interpro_id": "IPR020073", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF5371)", "partial_evidence_count": null, "pfam_id": "PF17341", "proteins": 48, "proteomes": 33, "short_name": "DUF5371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17341", "structures": 0, "taxa": 71, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a probable zinc binding domain found at the C-terminus of some Firmicute bacteria. The function of these proteins is unknown.", "domain_architectures": 2, "interpro_id": "IPR043711", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF5651)", "partial_evidence_count": null, "pfam_id": "PF18892", "proteins": 48, "proteomes": 43, "short_name": "DUF5651", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18892", "structures": 0, "taxa": 104, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001772) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the scytophycin biosynthetic gene cluster from Anabaena sp. UHCC 0451 [[cite:PUB00099384]].", "domain_architectures": 6, "interpro_id": "IPR046279", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF6312)", "partial_evidence_count": null, "pfam_id": "PF19831", "proteins": 48, "proteomes": 36, "short_name": "DUF6312", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19831", "structures": 0, "taxa": 121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of uncharacterised short sequences from actinobacteria. Many members are annotated as UbiD family decarboxylases. They are predicted to adopt an all beta configuration.", "domain_architectures": 2, "interpro_id": "IPR055585", "known_evidence_count": null, "matches": 50, "name": "Family of unknown function (DUF7161)", "partial_evidence_count": null, "pfam_id": "PF23720", "proteins": 48, "proteomes": 46, "short_name": "DUF7161", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23720", "structures": 0, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small putative zinc binding motif found in a small number of uncharacterised phage proteins.", "domain_architectures": 2, "interpro_id": "IPR055748", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF7324)", "partial_evidence_count": null, "pfam_id": "PF24010", "proteins": 48, "proteomes": 48, "short_name": "DUF7324", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24010", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small region that is found in a variety of uncharacterised mycobacterial phage proteins. Structure prediction suggests it adopts an alpha helix and beta hairpin structure that likely homodimerises.", "domain_architectures": 1, "interpro_id": "IPR055856", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF7433)", "partial_evidence_count": null, "pfam_id": "PF24212", "proteins": 48, "proteomes": 48, "short_name": "DUF7433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24212", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in a family of uncharacterised phage proteins. Structure prediction suggests that this protein may homodimerise (A0A377YTN9 ipTM=0.68).", "domain_architectures": 1, "interpro_id": "IPR056028", "known_evidence_count": null, "matches": 48, "name": "Domain of unknown function (DUF7609)", "partial_evidence_count": null, "pfam_id": "PF24582", "proteins": 48, "proteomes": 47, "short_name": "DUF7609", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24582", "structures": 0, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 47, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058386", "known_evidence_count": null, "matches": 48, "name": "Domain of unknown function (DUF8565)", "partial_evidence_count": null, "pfam_id": "PF26274", "proteins": 48, "proteomes": 45, "short_name": "DUF8565", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26274", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain was found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta structure composed of three stranded antiparallel beta-sheet packed with two alpha-helices.", "domain_architectures": 3, "interpro_id": "IPR059324", "known_evidence_count": null, "matches": 48, "name": "Domain of unknown function (DUF8280)", "partial_evidence_count": null, "pfam_id": "PF26929", "proteins": 48, "proteomes": 47, "short_name": "DUF8280", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26929", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised sequences from arthropods, at their C-terminal end, associated with [pfam:PF03762] at the N-terminal. It may adopt a beta-sandwich fold.", "domain_architectures": 12, "interpro_id": "IPR061574", "known_evidence_count": null, "matches": 75, "name": "Domain of unknown function (DUF8504)", "partial_evidence_count": null, "pfam_id": "PF29105", "proteins": 48, "proteomes": 11, "short_name": "DUF8504", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29105", "structures": 0, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a virion protein found in Caudoviricetes, the class of tailed bacteriophages. Proteins in this family are approximately 248 amino acids in length and appear to be single domain proteins. The specific function of this virion protein remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061614", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF8544)", "partial_evidence_count": null, "pfam_id": "PF29419", "proteins": 48, "proteomes": 48, "short_name": "DUF8544", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29419", "structures": 0, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a putative virion structural protein found in Caudoviricetes, the class of tailed bacteriophages. Proteins in this family are approximately 385-460 amino acids in length and appear to be single domain proteins. The specific function of this virion component remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061619", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF8549)", "partial_evidence_count": null, "pfam_id": "PF29427", "proteins": 48, "proteomes": 48, "short_name": "DUF8549", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29427", "structures": 0, "taxa": 137, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in a group of uncharacterised proteins mainly found in firmicutes. This domain is predicted to adopt a mainly beta structure. It shows highly conserved motifs TAY and VxDxG.", "domain_architectures": 2, "interpro_id": "IPR061898", "known_evidence_count": null, "matches": 48, "name": "Domain of unknown function (DUF8837)", "partial_evidence_count": null, "pfam_id": "PF31189", "proteins": 48, "proteomes": 43, "short_name": "DUF8837", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31189", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes. Proteins in this family are typically between 80 and 365 amino acids in length. There is a single completely conserved residue H that may be functionally important.", "domain_architectures": 3, "interpro_id": "IPR032056", "known_evidence_count": null, "matches": 52, "name": "Domain of unknown function (DUF4798)", "partial_evidence_count": null, "pfam_id": "PF16055", "proteins": 47, "proteomes": 34, "short_name": "DUF4798", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16055", "structures": 0, "taxa": 133, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001905) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the violapyrone B biosynthetic gene cluster from Streptomyces somaliensis and appears to be predominantly found in Actinobacteria and Caudovirale bacteriophages [[cite:PUB00098956]].", "domain_architectures": 1, "interpro_id": "IPR045731", "known_evidence_count": null, "matches": 47, "name": "Family of unknown function (DUF6085)", "partial_evidence_count": null, "pfam_id": "PF19563", "proteins": 47, "proteomes": 47, "short_name": "DUF6085", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19563", "structures": 0, "taxa": 127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001877) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the cyphomycin biosynthetic gene cluster from Streptomyces sp. ISID311 [[cite:PUB00099474]].", "domain_architectures": 1, "interpro_id": "IPR045923", "known_evidence_count": null, "matches": 47, "name": "Family of unknown function (DUF6342)", "partial_evidence_count": null, "pfam_id": "PF19869", "proteins": 47, "proteomes": 42, "short_name": "DUF6342", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19869", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in eukaryotes (predominantly in the Dinoflagellate Symbiodinium microadriaticum). There are several highly conserved W residues.", "domain_architectures": 18, "interpro_id": "IPR049225", "known_evidence_count": null, "matches": 56, "name": "Family of unknown function (DUF6822)", "partial_evidence_count": null, "pfam_id": "PF20708", "proteins": 47, "proteomes": 2, "short_name": "DUF6822", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20708", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein family found in viruses from the order Caudoviricetes. The family contains proteins between 199 and 219 amino acids in length. The function of this family is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR055618", "known_evidence_count": null, "matches": 47, "name": "Family of unknown function (DUF7194)", "partial_evidence_count": null, "pfam_id": "PF23824", "proteins": 47, "proteomes": 47, "short_name": "DUF7194", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23824", "structures": 1, "taxa": 134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Bacteroidota. It is predicted to adopt a globular structure with SH3-like topology. It is sometimes found N-terminal to [pfam:PF22273].", "domain_architectures": 2, "interpro_id": "IPR055682", "known_evidence_count": null, "matches": 47, "name": "Domain of unknown function (DUF7258)", "partial_evidence_count": null, "pfam_id": "PF23919", "proteins": 47, "proteomes": 42, "short_name": "DUF7258", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23919", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in a variety of cyanophages. These proteins adopt of compact domain structure composed of four strands and one alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055718", "known_evidence_count": null, "matches": 47, "name": "Domain of unknown function (DUF7294)", "partial_evidence_count": null, "pfam_id": "PF23966", "proteins": 47, "proteomes": 47, "short_name": "DUF7294", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23966", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 2, "interpro_id": "IPR055996", "known_evidence_count": null, "matches": 47, "name": "Domain of unknown function (DUF7574)", "partial_evidence_count": null, "pfam_id": "PF24459", "proteins": 47, "proteomes": 47, "short_name": "DUF7574", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24459", "structures": 0, "taxa": 148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of proteins is found in bacteria and viruses. Proteins in this family are typically between 69 and 93 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR056092", "known_evidence_count": null, "matches": 47, "name": "Family of unknown function (DUF7675)", "partial_evidence_count": null, "pfam_id": "PF24723", "proteins": 47, "proteomes": 44, "short_name": "DUF7675", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24723", "structures": 0, "taxa": 154, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Bacteroidales lineage. It is predicted as a transmembrane.", "domain_architectures": 1, "interpro_id": "IPR061530", "known_evidence_count": null, "matches": 47, "name": "Domain of unknown function (DUF8460)", "partial_evidence_count": null, "pfam_id": "PF28780", "proteins": 47, "proteomes": 46, "short_name": "DUF8460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28780", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several poxvirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR007769", "known_evidence_count": null, "matches": 46, "name": "Protein of unknown function (DUF678)", "partial_evidence_count": null, "pfam_id": "PF05077", "proteins": 46, "proteomes": 44, "short_name": "DUF678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05077", "structures": 0, "taxa": 133, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a short conserved region found in some transposons. Structural modelling suggests this domain may bind nucleic acids [[cite:PUB00070793]].", "domain_architectures": 2, "interpro_id": "IPR008008", "known_evidence_count": null, "matches": 62, "name": "Domain of Unknown Function (DUF746)", "partial_evidence_count": null, "pfam_id": "PF05344", "proteins": 46, "proteomes": 39, "short_name": "DUF746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05344", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several herpesvirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR008550", "known_evidence_count": null, "matches": 46, "name": "Herpesvirus protein of unknown function (DUF832)", "partial_evidence_count": null, "pfam_id": "PF05734", "proteins": 46, "proteomes": 33, "short_name": "DUF832", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05734", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 46, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in eukaryotes. Proteins in this family are typically between 256 and 292 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR022079", "known_evidence_count": null, "matches": 47, "name": "Protein of unknown function (DUF3629)", "partial_evidence_count": null, "pfam_id": "PF12302", "proteins": 46, "proteomes": 9, "short_name": "DUF3629", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12302", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025026", "known_evidence_count": null, "matches": 46, "name": "Protein of unknown function (DUF3915)", "partial_evidence_count": null, "pfam_id": "PF13054", "proteins": 46, "proteomes": 42, "short_name": "DUF3915", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13054", "structures": 0, "taxa": 201, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 160 residues in length and is mainly found in various Bacillus species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032545", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF4944)", "partial_evidence_count": null, "pfam_id": "PF16302", "proteins": 46, "proteomes": 34, "short_name": "DUF4944", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16302", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteria.", "domain_architectures": 2, "interpro_id": "IPR035416", "known_evidence_count": null, "matches": 47, "name": "Family of unknown function (DUF5376)", "partial_evidence_count": null, "pfam_id": "PF17346", "proteins": 46, "proteomes": 21, "short_name": "DUF5376", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17346", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in Phycodnaviridae and Mimiviridae.", "domain_architectures": 2, "interpro_id": "IPR043918", "known_evidence_count": null, "matches": 46, "name": "Family of unknown function (DUF5760)", "partial_evidence_count": null, "pfam_id": "PF19064", "proteins": 46, "proteomes": 39, "short_name": "DUF5760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19064", "structures": 0, "taxa": 151, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000385) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the lysobactin biosynthetic gene cluster from Lysobacter sp. ATCC 53042 [[cite:PUB00098898]].", "domain_architectures": 1, "interpro_id": "IPR045752", "known_evidence_count": null, "matches": 46, "name": "Family of unknown function (DUF6180)", "partial_evidence_count": null, "pfam_id": "PF19678", "proteins": 46, "proteomes": 44, "short_name": "DUF6180", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19678", "structures": 0, "taxa": 93, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found either as standalone or in combination with other domains in a group of uncharacterised proteins. It is distantly related to EDC3 mRNA-decapping protein 3 and it could be involved in RNA-binding. It is predicted to adopt a barrel-like structure with a typical Sm-like fold. The pair of glycines responsible for maintaining the Sm-barrel curvature are also conserved in the members of this family.", "domain_architectures": 1, "interpro_id": "IPR054226", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF6948)", "partial_evidence_count": null, "pfam_id": "PF22253", "proteins": 46, "proteomes": 37, "short_name": "DUF6948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22253", "structures": 0, "taxa": 145, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in various mycobacteriophages. The domain averages around 150 amino acids in length. It is found as a single domain in the phage proteins. The function of this domain is currently unknown. One protein in this family [swissprot:G8I4J4] contains an N-terminal associated domain [pfam:PF18909].", "domain_architectures": 2, "interpro_id": "IPR055607", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF7183)", "partial_evidence_count": null, "pfam_id": "PF23811", "proteins": 46, "proteomes": 46, "short_name": "DUF7183", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23811", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. Many of them are annotated as phage tail assembly chaperones, but there does not appear to be any evidence to support this annotation.", "domain_architectures": 1, "interpro_id": "IPR055815", "known_evidence_count": null, "matches": 46, "name": "Family of unknown function (DUF7391)", "partial_evidence_count": null, "pfam_id": "PF24117", "proteins": 46, "proteomes": 39, "short_name": "DUF7391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24117", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised family of phage proteins. These proteins consist of two domains. The first is composed of four alpha helices that are contributed by both the N and C-terminus of the protein. The second domain is a central beta domain. Structure prediction suggests that these proteins might form a large homo-oligomeric ring of 8-10 subunits, but the iPTM scores are marginal.", "domain_architectures": 1, "interpro_id": "IPR055907", "known_evidence_count": null, "matches": 46, "name": "Family of unknown function (DUF7484)", "partial_evidence_count": null, "pfam_id": "PF24302", "proteins": 46, "proteomes": 46, "short_name": "DUF7484", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24302", "structures": 1, "taxa": 132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a globular structure composed of array of helices.", "domain_architectures": 6, "interpro_id": "IPR057185", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF7863)", "partial_evidence_count": null, "pfam_id": "PF25263", "proteins": 46, "proteomes": 44, "short_name": "DUF7863", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25263", "structures": 0, "taxa": 176, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the Halobacteria class, including genera such as Halogeometricum and Haloplanus. The proteins in this family are typically around 67 to 84 amino acids in length. These proteins are predicted to be integral membrane proteins with two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058445", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF8132)", "partial_evidence_count": null, "pfam_id": "PF26453", "proteins": 46, "proteomes": 46, "short_name": "DUF8132", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26453", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain from a family of uncharacterised proteins found predominantly in archaea, specifically within the Halobacteria class. The proteins in this family are typically found in species such as Halovenus, Halobellus, and Natrarchaeobaculum, among others. Additionally, some members are associated with viruses like the Pleolipoviridae family. The domain is approximately 60-70 amino acids in length. The proteins containing this domain are predicted to be involved in replication processes, although their exact function remains unknown. The domain is found in proteins that are generally around 600-700 amino acids in length. These proteins are primarily associated with replication functions, as indicated by their presence in replication proteins across various archaeal species and viruses.", "domain_architectures": 4, "interpro_id": "IPR059016", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF8148) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26475", "proteins": 46, "proteomes": 36, "short_name": "DUF8148_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26475", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins are predominantly found in the Halobacteria class, including genera such as Halorubrum, Natronomonas, and Halogeometricum. The domain is approximately 110-118 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058472", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF8165)", "partial_evidence_count": null, "pfam_id": "PF26489", "proteins": 46, "proteomes": 41, "short_name": "DUF8165", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26489", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It contains three repeats with topology similar to the C-terminal domain of defensin. Each of these repeats has two predicted disulfide bonds that are conserved and occupying the same spatial position as the disulfide bonds in defensin. This domain is frequently found in combination with [pfam:PF23106] and [pfam:PF13920].", "domain_architectures": 7, "interpro_id": "IPR059285", "known_evidence_count": null, "matches": 48, "name": "Domain of unknown function (DUF8241)", "partial_evidence_count": null, "pfam_id": "PF26721", "proteins": 46, "proteomes": 41, "short_name": "DUF8241", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26721", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It contains two pairs of conserved cysteine residues which are predicted to form disulfide bonds.", "domain_architectures": 1, "interpro_id": "IPR059314", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF8270)", "partial_evidence_count": null, "pfam_id": "PF26802", "proteins": 46, "proteomes": 43, "short_name": "DUF8270", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26802", "structures": 0, "taxa": 135, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from proteobacteria. It contain several conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 1, "interpro_id": "IPR059383", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF8339)", "partial_evidence_count": null, "pfam_id": "PF27031", "proteins": 46, "proteomes": 45, "short_name": "DUF8339", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27031", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in spirochaetes, predominantly Treponema and Spirochaeta species. The domain is approximately 70 residues in length and is found N-terminal to a peptidase M15 domain ([pfam:PF13539]). The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061588", "known_evidence_count": null, "matches": 46, "name": "Domain of unknown function (DUF8518)", "partial_evidence_count": null, "pfam_id": "PF29233", "proteins": 46, "proteomes": 41, "short_name": "DUF8518", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29233", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 47 residues in length found in cyanophages (Kyanoviridae). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061695", "known_evidence_count": null, "matches": 46, "name": "Family of unknown function (DUF8634)", "partial_evidence_count": null, "pfam_id": "PF30567", "proteins": 46, "proteomes": 46, "short_name": "DUF8634", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30567", "structures": 0, "taxa": 143, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from the Gammaherpesvirinae.", "domain_architectures": 2, "interpro_id": "IPR008566", "known_evidence_count": null, "matches": 45, "name": "Gammaherpesvirus protein of unknown function (DUF848)", "partial_evidence_count": null, "pfam_id": "PF05852", "proteins": 45, "proteomes": 36, "short_name": "DUF848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05852", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is typically between 89 and 105 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR022167", "known_evidence_count": null, "matches": 46, "name": "Protein of unknown function (DUF3698)", "partial_evidence_count": null, "pfam_id": "PF12479", "proteins": 45, "proteomes": 3, "short_name": "DUF3698", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12479", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025036", "known_evidence_count": null, "matches": 45, "name": "Protein of unknown function (DUF3921)", "partial_evidence_count": null, "pfam_id": "PF13060", "proteins": 45, "proteomes": 43, "short_name": "DUF3921", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13060", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are approximately 50 amino acids in length. There is a conserved SVL sequence motif. There is a single completely conserved residue D that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025169", "known_evidence_count": null, "matches": 45, "name": "Protein of unknown function (DUF3927)", "partial_evidence_count": null, "pfam_id": "PF13064", "proteins": 45, "proteomes": 42, "short_name": "DUF3927", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13064", "structures": 0, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 40 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025081", "known_evidence_count": null, "matches": 45, "name": "Domain of unknown function (DUF3961)", "partial_evidence_count": null, "pfam_id": "PF13106", "proteins": 45, "proteomes": 40, "short_name": "DUF3961", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13106", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Saccharomycetaceae.", "domain_architectures": 2, "interpro_id": "IPR035257", "known_evidence_count": null, "matches": 51, "name": "Family of unknown function (DUF5349)", "partial_evidence_count": null, "pfam_id": "PF17298", "proteins": 45, "proteomes": 42, "short_name": "DUF5349", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17298", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins related to Lysogeny maintenance protein PflM [[cite:PUB00159292]]. These proteins contain several conserved cysteine and histidine residues that may form zinc binding sites.", "domain_architectures": 1, "interpro_id": "IPR035229", "known_evidence_count": null, "matches": 45, "name": "Lysogeny maintenance protein PflM", "partial_evidence_count": null, "pfam_id": "PF17525", "proteins": 45, "proteomes": 37, "short_name": "DUF5447", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17525", "structures": 0, "taxa": 67, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in archaea-specific ribosomal proteins such as L46a which is suggested to directly bind to rRNA in the ribosome [[cite:PUB00091411]].", "domain_architectures": 1, "interpro_id": "IPR041043", "known_evidence_count": null, "matches": 45, "name": "Domain of unknown function (DUF5622)", "partial_evidence_count": null, "pfam_id": "PF18533", "proteins": 45, "proteomes": 44, "short_name": "DUF5622", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18533", "structures": 10, "taxa": 102, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Iridoviridae. The family contains a conserved motif towards the C-terminus of these proteins. This motif contains a central RGD sequence which suggests these viral proteins may bind to integrins.", "domain_architectures": 1, "interpro_id": "IPR043882", "known_evidence_count": null, "matches": 45, "name": "Family of unknown function (DUF5850)", "partial_evidence_count": null, "pfam_id": "PF19168", "proteins": 45, "proteomes": 45, "short_name": "DUF5850", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19168", "structures": 1, "taxa": 96, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000260) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family includes a protein from the prodigiosin biosynthetic gene cluster from Hahella chejuensis KCTC 2396 [[cite:PUB00099442]]", "domain_architectures": 3, "interpro_id": "IPR046104", "known_evidence_count": null, "matches": 45, "name": "Family of unknown function (DUF6041)", "partial_evidence_count": null, "pfam_id": "PF19507", "proteins": 45, "proteomes": 43, "short_name": "DUF6041", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19507", "structures": 0, "taxa": 110, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001133) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the taxlllaid A biosynthetic gene cluster from Xenorhabdus bovienii SS-2004 [[cite:PUB00098918]]. This family appears to be predominantly found in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR045681", "known_evidence_count": null, "matches": 45, "name": "Family of unknown function (DUF6201)", "partial_evidence_count": null, "pfam_id": "PF19703", "proteins": 45, "proteomes": 23, "short_name": "DUF6201", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19703", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the istamycin biosynthetic gene cluster from Streptomyces tenjimariensis [[cite:PUB00098957]].", "domain_architectures": 2, "interpro_id": "IPR046212", "known_evidence_count": null, "matches": 45, "name": "Family of unknown function (DUF6245)", "partial_evidence_count": null, "pfam_id": "PF19758", "proteins": 45, "proteomes": 39, "short_name": "DUF6245", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19758", "structures": 0, "taxa": 79, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000926) is described by MIBiG as an example of the following biosynthetic class, other (unspecified), in particular the rhizocticin A biosynthetic gene cluster from Bacillus subtilis subsp. spizizenii ATCC 6633 [[cite:PUB00098884]].", "domain_architectures": 1, "interpro_id": "IPR045640", "known_evidence_count": null, "matches": 45, "name": "Family of unknown function (DUF6407)", "partial_evidence_count": null, "pfam_id": "PF19945", "proteins": 45, "proteomes": 41, "short_name": "DUF6407", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19945", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in bacteriophage proteins, predominantly from mycobacteriophages and Gordonia phages. The domain is typically between 80-130 amino acids in length. It folds into a compact domain composed of a sheet of five beta strands with an alpha helix packed on one side.", "domain_architectures": 1, "interpro_id": "IPR055704", "known_evidence_count": null, "matches": 45, "name": "Family of unknown function (DUF7280)", "partial_evidence_count": null, "pfam_id": "PF23946", "proteins": 45, "proteomes": 45, "short_name": "DUF7280", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23946", "structures": 0, "taxa": 119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised enterobacterial phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055844", "known_evidence_count": null, "matches": 45, "name": "Family of unknown function (DUF7421)", "partial_evidence_count": null, "pfam_id": "PF24196", "proteins": 45, "proteomes": 45, "short_name": "DUF7421", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24196", "structures": 0, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 44, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. This domain shows some weak structural similarity to RING finger domains.", "domain_architectures": 1, "interpro_id": "IPR058388", "known_evidence_count": null, "matches": 45, "name": "Domain of unknown function (DUF8075)", "partial_evidence_count": null, "pfam_id": "PF26276", "proteins": 45, "proteomes": 44, "short_name": "DUF8075", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26276", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 43, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the class Halobacteria, which includes organisms from the orders Halobacteriales and families such as Haloferacaceae, Haloarculaceae, and Natrialbaceae. The proteins in this family are typically around 130-140 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR059014", "known_evidence_count": null, "matches": 45, "name": "Domain of unknown function (DUF8161) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26495", "proteins": 45, "proteomes": 39, "short_name": "DUF8161_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26495", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Alveolata lineage. It is predicted to fold into a simple structure composed of beta-hairpin followed by an alpha-hairpin. Many proteins contain tandem repeats of this domain. It is frequently found in combination with [pfam:PF26932] and [pfam:PF00575].", "domain_architectures": 7, "interpro_id": "IPR059328", "known_evidence_count": null, "matches": 97, "name": "Domain of unknown function (DUF8284)", "partial_evidence_count": null, "pfam_id": "PF26933", "proteins": 45, "proteomes": 9, "short_name": "DUF8284", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26933", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a unusual alpha/beta structure. It contains a conserved H[FY]F sequence motif.", "domain_architectures": 2, "interpro_id": "IPR059381", "known_evidence_count": null, "matches": 45, "name": "Domain of unknown function (DUF8337)", "partial_evidence_count": null, "pfam_id": "PF27026", "proteins": 45, "proteomes": 37, "short_name": "DUF8337", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27026", "structures": 0, "taxa": 106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 1, "interpro_id": "IPR061776", "known_evidence_count": null, "matches": 45, "name": "Domain of unknown function (DUF8715)", "partial_evidence_count": null, "pfam_id": "PF30738", "proteins": 45, "proteomes": 45, "short_name": "DUF8715", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30738", "structures": 0, "taxa": 71, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 335 residues in length. Members of this family are found exclusively in Escherichia coli and Salmonella species and are often referred to as YggM proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009592", "known_evidence_count": null, "matches": 44, "name": "Protein of unknown function (DUF1202)", "partial_evidence_count": null, "pfam_id": "PF06717", "proteins": 44, "proteomes": 41, "short_name": "DUF1202", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06717", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family containing bacterial proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR012447", "known_evidence_count": null, "matches": 44, "name": "Protein of unknown function (DUF1651)", "partial_evidence_count": null, "pfam_id": "PF07864", "proteins": 44, "proteomes": 13, "short_name": "DUF1651", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07864", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of membrane proteins with unknown function.", "domain_architectures": 2, "interpro_id": "IPR024251", "known_evidence_count": null, "matches": 45, "name": "Protein of unknown function (DUF2632)", "partial_evidence_count": null, "pfam_id": "PF10943", "proteins": 44, "proteomes": 3, "short_name": "DUF2632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10943", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and viruses, and is approximately 50 amino acids in length. There is a conserved CGN sequence motif.", "domain_architectures": 1, "interpro_id": "IPR024256", "known_evidence_count": null, "matches": 44, "name": "Domain of unknown function (DUF3797)", "partial_evidence_count": null, "pfam_id": "PF12677", "proteins": 44, "proteomes": 41, "short_name": "DUF3797", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12677", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 100 residues locates in the N-terminal of some uncharacterized proteins and glucuronyl hydrolases in various Bacteroides species. The function of this family remains unknown.", "domain_architectures": 3, "interpro_id": "IPR032159", "known_evidence_count": null, "matches": 44, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16386", "proteins": 44, "proteomes": 34, "short_name": "DUF4995", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16386", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000498) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046010", "known_evidence_count": null, "matches": 44, "name": "Family of unknown function (DUF5966)", "partial_evidence_count": null, "pfam_id": "PF19391", "proteins": 44, "proteomes": 32, "short_name": "DUF5966", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19391", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in phage proteins, typically 45-60 amino acids in length. It is found in Streptomyces phages of the Caudoviricetes order, primarily in the Arquatrovirinae subfamily. The domain does not contain any conserved motifs or residues that provide hints about its function. A structure prediction shows that it is composed of two non-interacting alpha helices.", "domain_architectures": 1, "interpro_id": "IPR055639", "known_evidence_count": null, "matches": 44, "name": "Family of unknown function (DUF7215)", "partial_evidence_count": null, "pfam_id": "PF23852", "proteins": 44, "proteomes": 44, "short_name": "DUF7215", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23852", "structures": 0, "taxa": 116, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in bacteriophage proteins. The domain is around 90-95 amino acids in length. It is found in uncharacterized proteins from phages that infect Enterobacteria such as Salmonella and Shigella species as well as Dickeya. The specific function of this domain remains unknown. Structure prediction suggests that these proteins may form a homotetramer (iPTM=0.88). The domain contains a three twisted stranded beta sheet.", "domain_architectures": 1, "interpro_id": "IPR055848", "known_evidence_count": null, "matches": 44, "name": "Domain of unknown function (DUF7425)", "partial_evidence_count": null, "pfam_id": "PF24200", "proteins": 44, "proteomes": 43, "short_name": "DUF7425", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24200", "structures": 0, "taxa": 99, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a beta-sandwich-like structure with a conserved acidic patch on the surface.", "domain_architectures": 2, "interpro_id": "IPR059411", "known_evidence_count": null, "matches": 44, "name": "Domain of unknown function (DUF8367)", "partial_evidence_count": null, "pfam_id": "PF28040", "proteins": 44, "proteomes": 40, "short_name": "DUF8367", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28040", "structures": 0, "taxa": 127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt a non-compact alpha-helical structure.", "domain_architectures": 3, "interpro_id": "IPR059451", "known_evidence_count": null, "matches": 45, "name": "Domain of unknown function (DUF8407)", "partial_evidence_count": null, "pfam_id": "PF28466", "proteins": 44, "proteomes": 42, "short_name": "DUF8407", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28466", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in spirochaetes. The domain is approximately 50-60 residues in length and consists of three alpha helices arranged in a non-compact triangular configuration. It is found N-terminal to the DbpA RNA binding domain ([pfam:PF03880]) and also occurs as the third domain in some helicase-like proteins. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061590", "known_evidence_count": null, "matches": 44, "name": "Family of unknown function (DUF8520)", "partial_evidence_count": null, "pfam_id": "PF29235", "proteins": 44, "proteomes": 44, "short_name": "DUF8520", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29235", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 56 residues in length found in cyanophages (Kyanoviridae). Members are annotated as Gp7 in phage genomes. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061701", "known_evidence_count": null, "matches": 44, "name": "Family of unknown function (DUF8640)", "partial_evidence_count": null, "pfam_id": "PF30573", "proteins": 44, "proteomes": 44, "short_name": "DUF8640", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30573", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Gammaproteobacteria.", "domain_architectures": 6, "interpro_id": "IPR061781", "known_evidence_count": null, "matches": 53, "name": "Domain of unknown function (DUF8720)", "partial_evidence_count": null, "pfam_id": "PF30745", "proteins": 44, "proteomes": 31, "short_name": "DUF8720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30745", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Caenorhabditis elegans proteins of around 106 residues in length. The function of the family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009564", "known_evidence_count": null, "matches": 43, "name": "Protein of unknown function (DUF1179)", "partial_evidence_count": null, "pfam_id": "PF06678", "proteins": 43, "proteomes": 15, "short_name": "DUF1179", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06678", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins appears to be restricted to Enterobacteriaceae. Members of the family are annotated as yehE however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR020386", "known_evidence_count": null, "matches": 43, "name": "Protein of unknown function (DUF2574)", "partial_evidence_count": null, "pfam_id": "PF10836", "proteins": 43, "proteomes": 43, "short_name": "DUF2574", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10836", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Rickettsia spp.", "domain_architectures": 2, "interpro_id": "IPR022715", "known_evidence_count": null, "matches": 43, "name": "Protein of unknown function (DUF2671)", "partial_evidence_count": null, "pfam_id": "PF10877", "proteins": 43, "proteomes": 42, "short_name": "DUF2671", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10877", "structures": 0, "taxa": 144, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 50 or 570 residues in length and found in various Thermotoga species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032605", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF4896)", "partial_evidence_count": null, "pfam_id": "PF16237", "proteins": 43, "proteomes": 40, "short_name": "DUF4896", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16237", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000561) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR045989", "known_evidence_count": null, "matches": 43, "name": "Family of unknown function (DUF5945)", "partial_evidence_count": null, "pfam_id": "PF19370", "proteins": 43, "proteomes": 34, "short_name": "DUF5945", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19370", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000561) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046009", "known_evidence_count": null, "matches": 43, "name": "Family of unknown function (DUF5965)", "partial_evidence_count": null, "pfam_id": "PF19390", "proteins": 43, "proteomes": 34, "short_name": "DUF5965", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19390", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is functionally uncharacterised. This domain family is found in archaea. An AlphaFold prediction shows close similarity to zinc dependent peptidases.", "domain_architectures": 2, "interpro_id": "IPR046666", "known_evidence_count": null, "matches": 45, "name": "Probable metallopeptidase family (DUF6775)", "partial_evidence_count": null, "pfam_id": "PF20565", "proteins": 43, "proteomes": 42, "short_name": "DUF6775", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20565", "structures": 0, "taxa": 101, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein family found in various phages infecting Gram-negative bacterial hosts, including Salmonella, Shigella, Erwinia, Aeromonas, Vibrio and Klebsiella phages. The family typically contains proteins between 80-120 amino acids in length. The function of this protein family is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR055599", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF7175)", "partial_evidence_count": null, "pfam_id": "PF23799", "proteins": 43, "proteomes": 43, "short_name": "DUF7175", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23799", "structures": 0, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein of approximately 60-70 amino acids that is found in various phages, predominantly phages that infect members of the Enterobacteriaceae family such as Escherichia, Shigella, and Klebsiella.", "domain_architectures": 1, "interpro_id": "IPR055613", "known_evidence_count": null, "matches": 43, "name": "Family of unknown function (DUF7189)", "partial_evidence_count": null, "pfam_id": "PF23819", "proteins": 43, "proteomes": 43, "short_name": "DUF7189", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23819", "structures": 0, "taxa": 108, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an C-terminal domain from a family of uncharacterised phage proteins. This domain has a beta sandwich fold.", "domain_architectures": 1, "interpro_id": "IPR055689", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF7265)", "partial_evidence_count": null, "pfam_id": "PF23927", "proteins": 43, "proteomes": 28, "short_name": "DUF7265", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23927", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised mycobacterial phage proteins. The proteins have a domain that contains a four helical bundle.", "domain_architectures": 1, "interpro_id": "IPR055846", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF7423)", "partial_evidence_count": null, "pfam_id": "PF24198", "proteins": 43, "proteomes": 43, "short_name": "DUF7423", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24198", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein family found in bacteriophages. The function of this family is currently unknown. Members of this family are typically around 90-100 amino acids in length. The family includes proteins from various phage species infecting bacteria such as Salmonella, Klebsiella, and Proteus. Some members of this family contain disordered regions, particularly in their C-terminal portions. Conserved basic and acidic residues are present in many family members, which may be functionally important. This entry represents the globular N-terminal domain of these proteins.", "domain_architectures": 1, "interpro_id": "IPR055866", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF7443)", "partial_evidence_count": null, "pfam_id": "PF24227", "proteins": 43, "proteomes": 43, "short_name": "DUF7443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24227", "structures": 0, "taxa": 121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of uncharacterised bacterial proteins are often found adjacent to proteins from [pfam:PF13711]. Structure prediction shows that these proteins are very likely to form a complex.", "domain_architectures": 1, "interpro_id": "IPR056140", "known_evidence_count": null, "matches": 43, "name": "Family of unknown function (DUF7723)", "partial_evidence_count": null, "pfam_id": "PF24848", "proteins": 43, "proteomes": 42, "short_name": "DUF7723", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24848", "structures": 0, "taxa": 115, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in halophilic archaea. The proteins in this family are primarily found within the Halobacteria class, including genera such as Halorubrum, Haloquadratum, and Haloplanus. The domain is approximately 95-147 amino acids in length. Proteins containing this domain are predicted to be integral membrane proteins.", "domain_architectures": 1, "interpro_id": "IPR058466", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF8153)", "partial_evidence_count": null, "pfam_id": "PF26480", "proteins": 43, "proteomes": 40, "short_name": "DUF8153", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26480", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the second domain found in uncharacterised proteins from spirochaetes, predominantly from Treponema species. The domain adopts a long alpha-helical hairpin structure and is approximately 110 residues in length. This domain is found between an N-terminal domain ([pfam:PF29208]) and a C-terminal domain ([pfam:PF29207]) in proteins exclusive to spirochaetes. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061581", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF8511)", "partial_evidence_count": null, "pfam_id": "PF29209", "proteins": 43, "proteomes": 43, "short_name": "DUF8511", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29209", "structures": 0, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in spirochaetes. The domain is approximately 100-130 residues in length and is found C-terminal to a heptaprenyl diphosphate synthase domain ([pfam:PF07456]). The family shows distant sequence similarity to the CbiQ domain ([pfam:PF02361]), a protein involved in cobalt transport. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061589", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF8519)", "partial_evidence_count": null, "pfam_id": "PF29234", "proteins": 43, "proteomes": 42, "short_name": "DUF8519", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29234", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a TPR-like domain found at the C-terminal of a group of uncharacterised sequences from bacteria that contain a FtsH ternary system domain X7 at the N-terminal.", "domain_architectures": 5, "interpro_id": "IPR061647", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF8586)", "partial_evidence_count": null, "pfam_id": "PF29804", "proteins": 43, "proteomes": 32, "short_name": "DUF8586", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29804", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 100 residues found in uncharacterised proteins from Cyanobacteriota. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061693", "known_evidence_count": null, "matches": 43, "name": "Domain of unknown function (DUF8632)", "partial_evidence_count": null, "pfam_id": "PF30565", "proteins": 43, "proteomes": 41, "short_name": "DUF8632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30565", "structures": 0, "taxa": 139, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains several uncharacterised Chlamydia proteins.", "domain_architectures": 5, "interpro_id": "IPR007787", "known_evidence_count": null, "matches": 43, "name": "Protein of unknown function (DUF687)", "partial_evidence_count": null, "pfam_id": "PF05095", "proteins": 42, "proteomes": 19, "short_name": "DUF687", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05095", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family are all hypothetical proteins of unknown function expressed by the eukaryotic parasite Encephalitozoon cuniculi GB-M1. The region in question is approximately 250 amino acids long.", "domain_architectures": 1, "interpro_id": "IPR012468", "known_evidence_count": null, "matches": 42, "name": "Protein of unknown function (DUF1686)", "partial_evidence_count": null, "pfam_id": "PF07937", "proteins": 42, "proteomes": 4, "short_name": "DUF1686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07937", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Nucleopolyhedrovirus.", "domain_architectures": 1, "interpro_id": "IPR020122", "known_evidence_count": null, "matches": 42, "name": "Protein of unknown function (DUF2719)", "partial_evidence_count": null, "pfam_id": "PF10891", "proteins": 42, "proteomes": 41, "short_name": "DUF2719", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10891", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chromadorea.", "domain_architectures": 2, "interpro_id": "IPR035332", "known_evidence_count": null, "matches": 49, "name": "Family of unknown function (DUF5386)", "partial_evidence_count": null, "pfam_id": "PF17360", "proteins": 42, "proteomes": 28, "short_name": "DUF5386", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17360", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found at the C-terminal in Protein 19.5 from Escherichia phage T7 [[cite:PUB00105779]].", "domain_architectures": 1, "interpro_id": "IPR035581", "known_evidence_count": null, "matches": 42, "name": "Domain of unknown function (DUF5465)", "partial_evidence_count": null, "pfam_id": "PF17553", "proteins": 42, "proteomes": 42, "short_name": "DUF5465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17553", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040874", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF5551)", "partial_evidence_count": null, "pfam_id": "PF17705", "proteins": 42, "proteomes": 38, "short_name": "DUF5551", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17705", "structures": 0, "taxa": 162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 37, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in gammaproteobacteria.", "domain_architectures": 3, "interpro_id": "IPR040945", "known_evidence_count": null, "matches": 42, "name": "Domain of unknown function (DUF5621)", "partial_evidence_count": null, "pfam_id": "PF18532", "proteins": 42, "proteomes": 35, "short_name": "DUF5621", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18532", "structures": 1, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phycodnaviridae. This family also includes uncharacterised proteins found in Archaea and Eukaryotes.", "domain_architectures": 3, "interpro_id": "IPR043653", "known_evidence_count": null, "matches": 44, "name": "Family of unknown function (DUF5880)", "partial_evidence_count": null, "pfam_id": "PF19208", "proteins": 42, "proteomes": 37, "short_name": "DUF5880", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19208", "structures": 0, "taxa": 138, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001016) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from then microcystin biosynthetic gene cluster from Anabaena sp. 90 [[cite:PUB00099379]].", "domain_architectures": 1, "interpro_id": "IPR046048", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF6006)", "partial_evidence_count": null, "pfam_id": "PF19469", "proteins": 42, "proteomes": 40, "short_name": "DUF6006", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19469", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001418) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from the myxochromide D biosynthetic gene cluster from Hyalangium minutum and appears to be predominantly found in Cystobacterineae[[cite:PUB00098945]].", "domain_architectures": 1, "interpro_id": "IPR045710", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF6066)", "partial_evidence_count": null, "pfam_id": "PF19542", "proteins": 42, "proteomes": 42, "short_name": "DUF6066", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19542", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family from archaebacteria based on protein PF1546. AlphaFold models show that a dimer of this protein forms a flattened 10 stranded beta barrel structure.", "domain_architectures": 2, "interpro_id": "IPR055556", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF7132)", "partial_evidence_count": null, "pfam_id": "PF23476", "proteins": 42, "proteomes": 40, "short_name": "DUF7132", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23476", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a putative membrane protein found in several mycobacteriophages, especially those belonging to the genus Cheoctovirus. The function is unknown. Most members contain a predicted transmembrane helix near the N-terminus. The family shows some length variation, especially at the C-terminus.", "domain_architectures": 1, "interpro_id": "IPR055614", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF7190)", "partial_evidence_count": null, "pfam_id": "PF23820", "proteins": 42, "proteomes": 40, "short_name": "DUF7190", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23820", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterized proteins is found in several Lactococcus phages. All members are short proteins, between 33-59 amino acids in length. The family shows some conserved polar residues at the N-terminus. These proteins appear to be disordered.", "domain_architectures": 1, "interpro_id": "IPR055652", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF7228)", "partial_evidence_count": null, "pfam_id": "PF23873", "proteins": 42, "proteomes": 41, "short_name": "DUF7228", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23873", "structures": 0, "taxa": 98, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a domain of unknown function, which is found in phage proteins ranging in length from 75 to 88 amino acids. The domain is found in phage that infect Salmonella, Shigella, Serratia, and Enterobacter species.", "domain_architectures": 1, "interpro_id": "IPR055658", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF7234)", "partial_evidence_count": null, "pfam_id": "PF23881", "proteins": 42, "proteomes": 42, "short_name": "DUF7234", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23881", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. These proteins contain a highly conserved RDR/KVL sequence motif that is likely functionally important.", "domain_architectures": 1, "interpro_id": "IPR055725", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF7301)", "partial_evidence_count": null, "pfam_id": "PF23975", "proteins": 42, "proteomes": 38, "short_name": "DUF7301", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23975", "structures": 0, "taxa": 109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small beta barrel domain found at the N-terminus of some phage proteins.", "domain_architectures": 2, "interpro_id": "IPR055747", "known_evidence_count": null, "matches": 42, "name": "Domain of unknown function (DUF7323)", "partial_evidence_count": null, "pfam_id": "PF24009", "proteins": 42, "proteomes": 42, "short_name": "DUF7323", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24009", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain four predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058384", "known_evidence_count": null, "matches": 42, "name": "Domain of unknown function (DUF8071)", "partial_evidence_count": null, "pfam_id": "PF26268", "proteins": 42, "proteomes": 39, "short_name": "DUF8071", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26268", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins containing this domain are predominantly found in the class Halobacteria, which is part of the Methanobacteriota phylum. This domain is typically found in proteins ranging from 57 to 88 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058412", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF8099)", "partial_evidence_count": null, "pfam_id": "PF26401", "proteins": 42, "proteomes": 42, "short_name": "DUF8099", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26401", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 42, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from archaea. The proteins in this family are predominantly found in the order Halobacteriales, which includes genera such as Natrinema and Halostagnicola. The proteins are relatively short, typically ranging from 74 to 114 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058451", "known_evidence_count": null, "matches": 42, "name": "Family of unknown function (DUF8138)", "partial_evidence_count": null, "pfam_id": "PF26459", "proteins": 42, "proteomes": 42, "short_name": "DUF8138", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26459", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins from Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR003225", "known_evidence_count": null, "matches": 41, "name": "Viral proteins of unknown function", "partial_evidence_count": null, "pfam_id": "PF03804", "proteins": 41, "proteomes": 37, "short_name": "DUF325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03804", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This archaeal family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR024505", "known_evidence_count": null, "matches": 41, "name": "Protein of unknown function (DUF3201)", "partial_evidence_count": null, "pfam_id": "PF11447", "proteins": 41, "proteomes": 41, "short_name": "DUF3201", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11447", "structures": 1, "taxa": 90, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 450 residues in length and is mainly found in various species, such as Bacteroides and Parabacteroides. Several members are annotated as putative transmembrane proteins, but the specific function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032559", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF4933)", "partial_evidence_count": null, "pfam_id": "PF16287", "proteins": 41, "proteomes": 26, "short_name": "DUF4933", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16287", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 230 residues in length and is mainly found in various Bacteroidales species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032222", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF5041)", "partial_evidence_count": null, "pfam_id": "PF16444", "proteins": 41, "proteomes": 39, "short_name": "DUF5041", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16444", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Iridoviridae.", "domain_architectures": 1, "interpro_id": "IPR043657", "known_evidence_count": null, "matches": 41, "name": "Family of unknown function (DUF5876)", "partial_evidence_count": null, "pfam_id": "PF19204", "proteins": 41, "proteomes": 29, "short_name": "DUF5876", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19204", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000573) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046005", "known_evidence_count": null, "matches": 41, "name": "Family of unknown function (DUF5961)", "partial_evidence_count": null, "pfam_id": "PF19386", "proteins": 41, "proteomes": 31, "short_name": "DUF5961", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19386", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000758) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the capsular polysaccharide biosynthetic gene cluster from Staphylococcus aureus [[cite:PUB00007578]]", "domain_architectures": 1, "interpro_id": "IPR046049", "known_evidence_count": null, "matches": 41, "name": "Family of unknown function (DUF6007)", "partial_evidence_count": null, "pfam_id": "PF19470", "proteins": 41, "proteomes": 35, "short_name": "DUF6007", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19470", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001503) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the amycolamycin A biosynthetic gene cluster from Amycolatopsis sp. [[cite:PUB00099467]].", "domain_architectures": 1, "interpro_id": "IPR046194", "known_evidence_count": null, "matches": 41, "name": "Family of unknown function (DUF6222)", "partial_evidence_count": null, "pfam_id": "PF19731", "proteins": 41, "proteomes": 39, "short_name": "DUF6222", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19731", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in fungi. Proteins in this family are typically between 305 and 340 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046566", "known_evidence_count": null, "matches": 43, "name": "Family of unknown function (DUF6720)", "partial_evidence_count": null, "pfam_id": "PF20480", "proteins": 41, "proteomes": 17, "short_name": "DUF6720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20480", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small phage protein that is composed of two alpha helices. According to AlphaFold prediction this protein forms a confident head to tail oriented dimer, forming a four helix bundle. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR055636", "known_evidence_count": null, "matches": 41, "name": "Family of unknown function (DUF7212)", "partial_evidence_count": null, "pfam_id": "PF23848", "proteins": 41, "proteomes": 41, "short_name": "DUF7212", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23848", "structures": 0, "taxa": 117, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised protein YnaC and related bacterial proteins. It is usually associated with ([pfam:PF22522]). This domain is a winged helix (WH) domain decorated at the C terminus with a small three stranded beta-sheet that packs on the WH domain to form a single globular structure.", "domain_architectures": 5, "interpro_id": "IPR055649", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF7225)", "partial_evidence_count": null, "pfam_id": "PF23870", "proteins": 41, "proteomes": 38, "short_name": "DUF7225", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23870", "structures": 0, "taxa": 132, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of various uncharacterized phage proteins and a few bacterial proteins. The family members range in length from 82 to 229 amino acids, with most in the 180 to 200 amino acid range. They are found in phages that infect Pseudomonas, Xanthomonas, Acinetobacter, Escherichia, Rhodobacter, Sphingomonas, Achromobacter, and Burkholderia bacteria. Bacterial proteins in the family are from Candidatus Macondimonas diazotrophica, Verrucomicrobium sp. GAS474 and Pelodictyon phaeoclathratiforme. The function of these proteins is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR055727", "known_evidence_count": null, "matches": 41, "name": "Family of unknown function (DUF7303)", "partial_evidence_count": null, "pfam_id": "PF23978", "proteins": 41, "proteomes": 41, "short_name": "DUF7303", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23978", "structures": 0, "taxa": 140, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 39, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain four predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058371", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8058)", "partial_evidence_count": null, "pfam_id": "PF26247", "proteins": 41, "proteomes": 40, "short_name": "DUF8058", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26247", "structures": 0, "taxa": 144, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in Halobacteria. These proteins are found predominantly in archaea, particularly within the Halobacteriales order. The domain is typically around 65 amino acids in length. Proteins containing this domain are predicted to be membrane-associated, as suggested by the presence of two transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058457", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8144)", "partial_evidence_count": null, "pfam_id": "PF26469", "proteins": 41, "proteomes": 36, "short_name": "DUF8144", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26469", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 41, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein domain found in a family of uncharacterised archaebacterial proteins. This domain shows strong structural similarity to the SycN protein from Y. pestis that forms a heterodimeric complex with YscB and acts as a secretion chaperone to YopN. This family of proteins contains a C-terminal HTH domain.", "domain_architectures": 1, "interpro_id": "IPR058496", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8183)", "partial_evidence_count": null, "pfam_id": "PF26556", "proteins": 41, "proteomes": 35, "short_name": "DUF8183", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26556", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Alveolata lineage It is predicted to adopt a complex structure composed of a four helical bundle that caps a small open beta-barrel which is formed by the N- and the C- terminal parts of the domain.", "domain_architectures": 8, "interpro_id": "IPR059430", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8386)", "partial_evidence_count": null, "pfam_id": "PF28378", "proteins": 41, "proteomes": 12, "short_name": "DUF8386", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28378", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a helical domain of unknown function found in spirochaetes. The domain is approximately 50-70 residues in length and is found N-terminal in proteins containing tetratricopeptide repeat (TPR) domains. The function of this domain remains to be determined.", "domain_architectures": 8, "interpro_id": "IPR061592", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8522)", "partial_evidence_count": null, "pfam_id": "PF29237", "proteins": 41, "proteomes": 41, "short_name": "DUF8522", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29237", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. It is predicted to adopt Ig-like fold.", "domain_architectures": 2, "interpro_id": "IPR061767", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8706)", "partial_evidence_count": null, "pfam_id": "PF30724", "proteins": 41, "proteomes": 41, "short_name": "DUF8706", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30724", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. It is predicted to adopt Ig-like fold.", "domain_architectures": 2, "interpro_id": "IPR061768", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8707)", "partial_evidence_count": null, "pfam_id": "PF30725", "proteins": 41, "proteomes": 41, "short_name": "DUF8707", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30725", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Leptospira lineage. It is predicted to adopt Ig-like fold.", "domain_architectures": 2, "interpro_id": "IPR061769", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF8708)", "partial_evidence_count": null, "pfam_id": "PF30726", "proteins": 41, "proteomes": 41, "short_name": "DUF8708", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30726", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the third domain found in a family of uncharacterised hypothetical prokaryotic proteins.", "domain_architectures": 8, "interpro_id": "IPR063021", "known_evidence_count": null, "matches": 41, "name": "DUF499 third domain", "partial_evidence_count": null, "pfam_id": "PF30798", "proteins": 41, "proteomes": 41, "short_name": "DUF499_3rd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30798", "structures": 0, "taxa": 145, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several short Chordopoxvirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009372", "known_evidence_count": null, "matches": 40, "name": "Protein of unknown function (DUF1029)", "partial_evidence_count": null, "pfam_id": "PF06269", "proteins": 40, "proteomes": 39, "short_name": "DUF1029", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06269", "structures": 0, "taxa": 121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Sulfolobus virus proteins of around 100 residues in length. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009804", "known_evidence_count": null, "matches": 40, "name": "Protein of unknown function (DUF1374)", "partial_evidence_count": null, "pfam_id": "PF07118", "proteins": 40, "proteomes": 13, "short_name": "DUF1374", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07118", "structures": 5, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR021407", "known_evidence_count": null, "matches": 40, "name": "Protein of unknown function (DUF2544)", "partial_evidence_count": null, "pfam_id": "PF11245", "proteins": 40, "proteomes": 29, "short_name": "DUF2544", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11245", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 30 amino acids in length. There are two conserved sequence motifs: RCLMK and LIEL.", "domain_architectures": 1, "interpro_id": "IPR022178", "known_evidence_count": null, "matches": 40, "name": "Protein of unknown function (DUF3709)", "partial_evidence_count": null, "pfam_id": "PF12493", "proteins": 40, "proteomes": 9, "short_name": "DUF3709", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12493", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 110 amino acids in length. There is a conserved VMSAS sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025019", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF3952)", "partial_evidence_count": null, "pfam_id": "PF13130", "proteins": 40, "proteomes": 15, "short_name": "DUF3952", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13130", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and viruses. Proteins in this family are approximately 40 amino acids in length. There is a conserved AWRN sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025041", "known_evidence_count": null, "matches": 40, "name": "Protein of unknown function (DUF3983)", "partial_evidence_count": null, "pfam_id": "PF13137", "proteins": 40, "proteomes": 32, "short_name": "DUF3983", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13137", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 200 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032242", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF5043)", "partial_evidence_count": null, "pfam_id": "PF16446", "proteins": 40, "proteomes": 18, "short_name": "DUF5043", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16446", "structures": 1, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function which can is found mainly in Proteobacteria.", "domain_architectures": 1, "interpro_id": "IPR035160", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF5334)", "partial_evidence_count": null, "pfam_id": "PF17268", "proteins": 40, "proteomes": 38, "short_name": "DUF5334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17268", "structures": 0, "taxa": 109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Rickettsiales.", "domain_architectures": 2, "interpro_id": "IPR020171", "known_evidence_count": null, "matches": 41, "name": "Family of unknown function (DUF5394)", "partial_evidence_count": null, "pfam_id": "PF17372", "proteins": 40, "proteomes": 40, "short_name": "DUF5394", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17372", "structures": 0, "taxa": 122, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040779", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF5538)", "partial_evidence_count": null, "pfam_id": "PF17692", "proteins": 40, "proteomes": 40, "short_name": "DUF5538", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17692", "structures": 0, "taxa": 175, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in proteins of unknown function. It has composed of eight antiparallel beta strands and carries a G-X-W motif in the N-terminal region. The conserved glycine-X-tryptophan (G-X-W) motif is characteristic for the lipocalin family [[cite:PUB00091384]].", "domain_architectures": 1, "interpro_id": "IPR040984", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF5640)", "partial_evidence_count": null, "pfam_id": "PF18692", "proteins": 40, "proteomes": 37, "short_name": "DUF5640", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18692", "structures": 1, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000078) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the incednine biosynthetic gene cluster from Streptomyces sp. ML694-90F3 [[cite:PUB00098990]].", "domain_architectures": 1, "interpro_id": "IPR046276", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF6309)", "partial_evidence_count": null, "pfam_id": "PF19828", "proteins": 40, "proteomes": 35, "short_name": "DUF6309", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19828", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in various mycobacteriophages. The protein is typically around 80 to 100 amino acids in length. It is found in phages belonging to cluster B, such as the Bclasvirinae and Coopervirus genera. The function of this protein is currently unknown.", "domain_architectures": 1, "interpro_id": "IPR055609", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF7185)", "partial_evidence_count": null, "pfam_id": "PF23814", "proteins": 40, "proteomes": 40, "short_name": "DUF7185", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23814", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of phage proteins. Structure prediction suggests that these proteins form a single long alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055752", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF7328)", "partial_evidence_count": null, "pfam_id": "PF24014", "proteins": 40, "proteomes": 40, "short_name": "DUF7328", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24014", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins, that includes the L1 protein from Lactococcus phage c2 [swissprot:Q38296]. Structure prediction indicates this small protein adopts a compact domain composed of a three stranded sheet with a single alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055819", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF7395)", "partial_evidence_count": null, "pfam_id": "PF24127", "proteins": 40, "proteomes": 34, "short_name": "DUF7395", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24127", "structures": 0, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry describes an uncharacterized protein found in several bacteriophages that infect Bacillus species. The protein ranges in length from 158 to 189 amino acids. It is found in the virions of phages from the Bastillevirinae subfamily of the Herelleviridae family. Structure prediction suggests the proteins are composed of a bundle of five alpha helices.", "domain_architectures": 1, "interpro_id": "IPR055822", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF7398)", "partial_evidence_count": null, "pfam_id": "PF24131", "proteins": 40, "proteomes": 40, "short_name": "DUF7398", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24131", "structures": 0, "taxa": 100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised eukaryotic proteins. It contains two highly conserved cysteines. This domain is predicted to fold into Ig-like beta-sandwich.", "domain_architectures": 13, "interpro_id": "IPR055920", "known_evidence_count": null, "matches": 49, "name": "Domain of unknown function (DUF7497)", "partial_evidence_count": null, "pfam_id": "PF24327", "proteins": 40, "proteomes": 27, "short_name": "DUF7497", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24327", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised bacterial proteins. It is found N-terminal to [pfam:PF24736]. This domain is predicted to adopt a globular structure composed of four alpha- helices.", "domain_architectures": 2, "interpro_id": "IPR056107", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF7690)", "partial_evidence_count": null, "pfam_id": "PF24739", "proteins": 40, "proteomes": 39, "short_name": "DUF7690", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24739", "structures": 0, "taxa": 152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 38, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058313", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF8000)", "partial_evidence_count": null, "pfam_id": "PF26007", "proteins": 40, "proteomes": 35, "short_name": "DUF8000", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26007", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an unique alpha/beta structure composed of a small central four-stranded antiparallel beta-sheet surrounded by alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR059286", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF8242)", "partial_evidence_count": null, "pfam_id": "PF26727", "proteins": 40, "proteomes": 40, "short_name": "DUF8242", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26727", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from phages and prophages. It is predicted to fold into a globular structure with sandwich-like topology. It contains a conserved Gx(3)WSA sequence motif.", "domain_architectures": 1, "interpro_id": "IPR059421", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF8377)", "partial_evidence_count": null, "pfam_id": "PF28254", "proteins": 40, "proteomes": 36, "short_name": "DUF8377", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28254", "structures": 0, "taxa": 100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a structure which resembles the conserved core of the N-terminal domain of PatA [pfam:PF14332].", "domain_architectures": 2, "interpro_id": "IPR059433", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF8389)", "partial_evidence_count": null, "pfam_id": "PF28390", "proteins": 40, "proteomes": 17, "short_name": "DUF8389", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28390", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 40, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Thermoproteota lineage. It is predicted to fold into a complex structure composed of a flatten beta-barrel in which a small beta-sandwich is inserted.", "domain_architectures": 1, "interpro_id": "IPR059468", "known_evidence_count": null, "matches": 40, "name": "Domain of unknown function (DUF8424)", "partial_evidence_count": null, "pfam_id": "PF28525", "proteins": 40, "proteomes": 27, "short_name": "DUF8424", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28525", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins specific to Helicobacter pylori. The function of this family is unknown.", "domain_architectures": 6, "interpro_id": "IPR008592", "known_evidence_count": null, "matches": 43, "name": "Helicobacter pylori protein of unknown function (DUF874)", "partial_evidence_count": null, "pfam_id": "PF05917", "proteins": 39, "proteomes": 25, "short_name": "DUF874", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05917", "structures": 0, "taxa": 163, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a group of sequences found in hypothetical proteins predicted to be expressed in a number of bacterial species. The region in question is approximately 150 amino acid residues long.", "domain_architectures": 2, "interpro_id": "IPR012432", "known_evidence_count": null, "matches": 39, "name": "Protein of unknown function (DUF1627)", "partial_evidence_count": null, "pfam_id": "PF07789", "proteins": 39, "proteomes": 31, "short_name": "DUF1627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07789", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family based of PDB:3B5P encoded by ZP_00108531 from nitrogen-fixing cyanobacterium Nostoc punctiforme pcc 73102 is a CADD-like protein of unknown function. Superposition between protein structures encoded by CT610 from Chlamydia trachomatis (PDB code 1rwc), pyrroloquinolinquinone synthase C (PqqC, PDB code 1otv) and ZP_00108531 revealed that putative active sites in CT610 and ZP_00108531 are identical. ( REF: http://www.topsan.org/Proteins/JCSG/3B5P).", "domain_architectures": 1, "interpro_id": "IPR024477", "known_evidence_count": null, "matches": 39, "name": "Domain of Unknown Function with PDB structure (DUF3865)", "partial_evidence_count": null, "pfam_id": "PF12981", "proteins": 39, "proteomes": 38, "short_name": "DUF3865", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12981", "structures": 2, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 120 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025045", "known_evidence_count": null, "matches": 39, "name": "Protein of unknown function (DUF3979)", "partial_evidence_count": null, "pfam_id": "PF13141", "proteins": 39, "proteomes": 39, "short_name": "DUF3979", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13141", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 200 in length and is mainly found in various Parabacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032206", "known_evidence_count": null, "matches": 39, "name": "Domain of unknown function (DUF5025)", "partial_evidence_count": null, "pfam_id": "PF16428", "proteins": 39, "proteomes": 36, "short_name": "DUF5025", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16428", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR041319", "known_evidence_count": null, "matches": 39, "name": "Family of unknown function (DUF5543)", "partial_evidence_count": null, "pfam_id": "PF17697", "proteins": 39, "proteomes": 26, "short_name": "DUF5543", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17697", "structures": 0, "taxa": 109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 2, "interpro_id": "IPR043977", "known_evidence_count": null, "matches": 39, "name": "Family of unknown function (DUF5759)", "partial_evidence_count": null, "pfam_id": "PF19063", "proteins": 39, "proteomes": 36, "short_name": "DUF5759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19063", "structures": 0, "taxa": 138, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000523) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046008", "known_evidence_count": null, "matches": 39, "name": "Family of unknown function (DUF5964)", "partial_evidence_count": null, "pfam_id": "PF19389", "proteins": 39, "proteomes": 37, "short_name": "DUF5964", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19389", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of around 60 residues found in Omarvirus and related bacteriophages that infect Streptomyces species. The function of this protein family is currently unknown. Homologous proteins are also found in a small number of Streptomyces genomes. The AlphaFold model of A0A7G7BJ30 shows a pair of alpha helices at the C-terminus of the protein.", "domain_architectures": 1, "interpro_id": "IPR055611", "known_evidence_count": null, "matches": 39, "name": "Family of unknown function (DUF7187)", "partial_evidence_count": null, "pfam_id": "PF23816", "proteins": 39, "proteomes": 39, "short_name": "DUF7187", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23816", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055750", "known_evidence_count": null, "matches": 39, "name": "Family of unknown function (DUF7326)", "partial_evidence_count": null, "pfam_id": "PF24012", "proteins": 39, "proteomes": 38, "short_name": "DUF7326", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24012", "structures": 0, "taxa": 120, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small uncharacterised domain from Staphylococcus phage. The domain is predicted to be largely composed of small alpha helices.", "domain_architectures": 1, "interpro_id": "IPR055790", "known_evidence_count": null, "matches": 39, "name": "Domain of unknown function (DUF7366)", "partial_evidence_count": null, "pfam_id": "PF24074", "proteins": 39, "proteomes": 38, "short_name": "DUF7366", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24074", "structures": 0, "taxa": 93, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of phage proteins. The family includes members from Phage T2 and T6. These proteins contain a small three stranded beta domain. Some members have an additional small C-terminal domain composed of a beta-alpha-alpha-beta hairpin domain.", "domain_architectures": 1, "interpro_id": "IPR055845", "known_evidence_count": null, "matches": 39, "name": "Family of unknown function (DUF7422)", "partial_evidence_count": null, "pfam_id": "PF24197", "proteins": 39, "proteomes": 35, "short_name": "DUF7422", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24197", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from Spirochaete bacteria.", "domain_architectures": 2, "interpro_id": "IPR058397", "known_evidence_count": null, "matches": 43, "name": "Family of unknown function (DUF8084)", "partial_evidence_count": null, "pfam_id": "PF26329", "proteins": 39, "proteomes": 36, "short_name": "DUF8084", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26329", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains a two pair of highly conserved cysteine residues that may be involved in metal coordination. It is predicted to fold into a structure typical for zinc beta ribbon domains. Some proteins contain multiple copies of this domain.", "domain_architectures": 2, "interpro_id": "IPR059304", "known_evidence_count": null, "matches": 39, "name": "Domain of unknown function (DUF8260)", "partial_evidence_count": null, "pfam_id": "PF26788", "proteins": 39, "proteomes": 34, "short_name": "DUF8260", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26788", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into array of alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR059343", "known_evidence_count": null, "matches": 39, "name": "Domain of unknown function (DUF8299)", "partial_evidence_count": null, "pfam_id": "PF26951", "proteins": 39, "proteomes": 37, "short_name": "DUF8299", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26951", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found mainly in Leptospira lineage. They are predicted to fold into a beta-barrel-like structures.", "domain_architectures": 1, "interpro_id": "IPR061848", "known_evidence_count": null, "matches": 39, "name": "Domain of unknown function (DUF8787)", "partial_evidence_count": null, "pfam_id": "PF31047", "proteins": 39, "proteomes": 39, "short_name": "DUF8787", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31047", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Enterobacterial proteins of around 50 residues in length. Members of this family are found in Escherichia coli and Salmonella typhi where they are often known as YdfA. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009821", "known_evidence_count": null, "matches": 38, "name": "Protein of unknown function (DUF1391)", "partial_evidence_count": null, "pfam_id": "PF07151", "proteins": 38, "proteomes": 25, "short_name": "DUF1391", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07151", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of around 170 residues in length which appear to be mouse specific. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009895", "known_evidence_count": null, "matches": 38, "name": "Protein of unknown function (DUF1438)", "partial_evidence_count": null, "pfam_id": "PF07270", "proteins": 38, "proteomes": 4, "short_name": "DUF1438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07270", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in viruses. Proteins in this family are about 360 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR021912", "known_evidence_count": null, "matches": 67, "name": "Protein of unknown function (DUF3525)", "partial_evidence_count": null, "pfam_id": "PF12039", "proteins": 38, "proteomes": 11, "short_name": "DUF3525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12039", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length. There is a single completely conserved residue F that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025467", "known_evidence_count": null, "matches": 38, "name": "Domain of unknown function (DUF4318)", "partial_evidence_count": null, "pfam_id": "PF14201", "proteins": 38, "proteomes": 38, "short_name": "DUF4318", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14201", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria, and is approximately 90 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031886", "known_evidence_count": null, "matches": 38, "name": "Domain of unknown function (DUF4765)", "partial_evidence_count": null, "pfam_id": "PF15962", "proteins": 38, "proteomes": 25, "short_name": "DUF4765", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15962", "structures": 3, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 220 residues in length and is mainly found in various Actinomyces species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032326", "known_evidence_count": null, "matches": 38, "name": "Domain of unknown function (DUF4853)", "partial_evidence_count": null, "pfam_id": "PF16145", "proteins": 38, "proteomes": 10, "short_name": "DUF4853", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16145", "structures": 1, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidial-specific proteins of unknown function. There is distant homology to synaptosomal-associated 25 family proteins.", "domain_architectures": 2, "interpro_id": "IPR031547", "known_evidence_count": null, "matches": 38, "name": "Domain of unknown function (DUF5089)", "partial_evidence_count": null, "pfam_id": "PF17002", "proteins": 38, "proteomes": 31, "short_name": "DUF5089", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17002", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 237 and 274 amino acids in length. These proteins are likely to be integral membrane proteins.", "domain_architectures": 1, "interpro_id": "IPR043715", "known_evidence_count": null, "matches": 38, "name": "Protein of unknown function (DUF5656)", "partial_evidence_count": null, "pfam_id": "PF18900", "proteins": 38, "proteomes": 38, "short_name": "DUF5656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18900", "structures": 0, "taxa": 134, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000919) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a protein from the phaseolotoxin biosynthetic gene cluster from Pseudomonas syringae [[cite:PUB00099372]].", "domain_architectures": 3, "interpro_id": "IPR046043", "known_evidence_count": null, "matches": 38, "name": "Family of unknown function (DUF6001)", "partial_evidence_count": null, "pfam_id": "PF19464", "proteins": 38, "proteomes": 32, "short_name": "DUF6001", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19464", "structures": 0, "taxa": 91, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of phage proteins adopt a structure composed of a pair of jelly roll fold domains with one nested within the other. This fold is suggestive of a phage head structural protein. Structure predictions suggest that these proteins can form pentameric or hexameric arrangements mediated by the outer of the two domains.", "domain_architectures": 1, "interpro_id": "IPR055667", "known_evidence_count": null, "matches": 38, "name": "Family of unknown function (DUF7243)", "partial_evidence_count": null, "pfam_id": "PF23891", "proteins": 38, "proteomes": 38, "short_name": "DUF7243", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23891", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised phage domain. In some members of the family this domain is found at the C-terminus of a longer protein which also contains [pfam:PF14594].", "domain_architectures": 2, "interpro_id": "IPR055722", "known_evidence_count": null, "matches": 38, "name": "Domain of unknown function (DUF7298)", "partial_evidence_count": null, "pfam_id": "PF23972", "proteins": 38, "proteomes": 36, "short_name": "DUF7298", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23972", "structures": 0, "taxa": 97, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of domains that includes an uncharacterised plasmid borne protein from Shigella. It also is found in large probably toxin proteins. This could suggest this protein acts as a toxin.", "domain_architectures": 5, "interpro_id": "IPR058351", "known_evidence_count": null, "matches": 39, "name": "Domain of unknown function (DUF8038)", "partial_evidence_count": null, "pfam_id": "PF26124", "proteins": 38, "proteomes": 35, "short_name": "DUF8038", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26124", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised bacterial proteins. They are probably associated with the membrane and are predicted to fold into a large barrel structure which in addition to an internal plug contains an insertion which points out of the barrel.", "domain_architectures": 2, "interpro_id": "IPR059440", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF8396)", "partial_evidence_count": null, "pfam_id": "PF28436", "proteins": 38, "proteomes": 36, "short_name": "DUF8396", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28436", "structures": 0, "taxa": 131, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR022714", "known_evidence_count": null, "matches": 37, "name": "Protein of unknown function (DUF2670)", "partial_evidence_count": null, "pfam_id": "PF10875", "proteins": 37, "proteomes": 37, "short_name": "DUF2670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10875", "structures": 0, "taxa": 106, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 368 to 823 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR021902", "known_evidence_count": null, "matches": 37, "name": "Protein of unknown function (DUF3514)", "partial_evidence_count": null, "pfam_id": "PF12027", "proteins": 37, "proteomes": 7, "short_name": "DUF3514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12027", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 130 amino acids in length. There are two conserved sequence motifs: TEA and FPKT.", "domain_architectures": 1, "interpro_id": "IPR025120", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF4047)", "partial_evidence_count": null, "pfam_id": "PF13256", "proteins": 37, "proteomes": 37, "short_name": "DUF4047", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13256", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is the N-terminal region of methyl-accepting chemotaxis proteins from Bacillus spp. The function is not known.", "domain_architectures": 4, "interpro_id": "IPR025278", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF4077)", "partial_evidence_count": null, "pfam_id": "PF13295", "proteins": 37, "proteomes": 34, "short_name": "DUF4077", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13295", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 250 residues in length and found in various Thermotoga species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032606", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF4895)", "partial_evidence_count": null, "pfam_id": "PF16236", "proteins": 37, "proteomes": 37, "short_name": "DUF4895", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16236", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a small family of uncharacterised proteins of around 200 residues in length, found in various archaeal and bacterial species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032604", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF4897)", "partial_evidence_count": null, "pfam_id": "PF16238", "proteins": 37, "proteomes": 37, "short_name": "DUF4897", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16238", "structures": 0, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 340 residues in length and found in various Thermotoga and Thermosipho species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032602", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF4899)", "partial_evidence_count": null, "pfam_id": "PF16240", "proteins": 37, "proteomes": 37, "short_name": "DUF4899", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16240", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in various Platyhelminthes.", "domain_architectures": 5, "interpro_id": "IPR043799", "known_evidence_count": null, "matches": 38, "name": "Domain of unknown function (DUF5738)", "partial_evidence_count": null, "pfam_id": "PF19009", "proteins": 37, "proteomes": 26, "short_name": "DUF5738", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19009", "structures": 0, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a highly conserved domain found in various Platyhelminthes. Its function is currently unknown, with some of the sequences annotated as being Palmitoyltransferase. This highly conserved domain is located at the amino terminus, next to a DHHC domain (named for its signature tetrapeptide Asp-His-His-Cys).", "domain_architectures": 4, "interpro_id": "IPR043955", "known_evidence_count": null, "matches": 39, "name": "Domain of unknown function (DUF5746)", "partial_evidence_count": null, "pfam_id": "PF19017", "proteins": 37, "proteomes": 32, "short_name": "DUF5746", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19017", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000709) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the neomycin biosynthetic gene cluster from Streptomyces fradiae ATCC 10745 = DSM 40063 and appears to be predominantly found in bacteria [[cite:PUB00098957]].", "domain_architectures": 1, "interpro_id": "IPR046135", "known_evidence_count": null, "matches": 37, "name": "Family of unknown function (DUF6137)", "partial_evidence_count": null, "pfam_id": "PF19634", "proteins": 37, "proteomes": 35, "short_name": "DUF6137", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19634", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001215) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the conglobatin biosynthetic gene cluster from Streptomyces conglobatus [[cite:PUB00099436]].", "domain_architectures": 3, "interpro_id": "IPR046223", "known_evidence_count": null, "matches": 37, "name": "Family of unknown function (DUF6256)", "partial_evidence_count": null, "pfam_id": "PF19770", "proteins": 37, "proteomes": 33, "short_name": "DUF6256", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19770", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 148 and 213 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046573", "known_evidence_count": null, "matches": 37, "name": "Family of unknown function (DUF6633)", "partial_evidence_count": null, "pfam_id": "PF20338", "proteins": 37, "proteomes": 32, "short_name": "DUF6633", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20338", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 150 and 161 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR046610", "known_evidence_count": null, "matches": 37, "name": "Family of unknown function (DUF6669)", "partial_evidence_count": null, "pfam_id": "PF20374", "proteins": 37, "proteomes": 36, "short_name": "DUF6669", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20374", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterized proteins found in Mycobacterium phages. The family members are typically around 67 amino acids in length. Structure prediction suggests these proteins form a small compact domain composed of four beta strands followed by an Alpha helix. The domain possibly shows weak structural similarity to integrase arm-type binding domain.", "domain_architectures": 2, "interpro_id": "IPR055858", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF7435)", "partial_evidence_count": null, "pfam_id": "PF24216", "proteins": 37, "proteomes": 26, "short_name": "DUF7435", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24216", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in the Halobacteria class of Archaea. Proteins containing this domain are found predominantly in the order Halobacteriales, with representatives in families such as Haloferacaceae and Halobacteriaceae. The domain is typically found in proteins ranging from 73 to 103 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR058416", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF8103)", "partial_evidence_count": null, "pfam_id": "PF26405", "proteins": 37, "proteomes": 36, "short_name": "DUF8103", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26405", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins from halophilic archaea. The proteins are primarily found in members of the Halobacteria class, including genera such as Natrialba, Natrarchaeobaculum, and Halobiforma. The proteins in this family typically range from 200 to 300 amino acids in length. These proteins contain an Ig-like fold.", "domain_architectures": 1, "interpro_id": "IPR058478", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF8164)", "partial_evidence_count": null, "pfam_id": "PF26498", "proteins": 37, "proteomes": 37, "short_name": "DUF8164", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26498", "structures": 0, "taxa": 100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry describes a set of proteins of unknown function, mainly from Dictyostelium discoideum. These uncharacterised proteins display a CUB-like fold, a structural motif of approximately 110 residues found almost exclusively in extracellular and plasma membrane-associated proteins [[cite:PUB00035659]].", "domain_architectures": 3, "interpro_id": "IPR059288", "known_evidence_count": null, "matches": 37, "name": "Family of unknown function (DUF8244)", "partial_evidence_count": null, "pfam_id": "PF26736", "proteins": 37, "proteomes": 16, "short_name": "DUF8244", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26736", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 90-100 residues found in spirochaetes, particularly Treponema species. The domain is located between an N-terminal helix-turn-helix domain and a C-terminal domain in these proteins. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061594", "known_evidence_count": null, "matches": 37, "name": "Domain of unknown function (DUF8524)", "partial_evidence_count": null, "pfam_id": "PF29241", "proteins": 37, "proteomes": 37, "short_name": "DUF8524", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29241", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised Caenorhabditis elegans proteins of around 115 resides in length. Members of this family contain 6 highly conserved cysteine residues. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR009981", "known_evidence_count": null, "matches": 38, "name": "Protein of unknown function (DUF1505)", "partial_evidence_count": null, "pfam_id": "PF07403", "proteins": 36, "proteomes": 10, "short_name": "DUF1505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07403", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR022589", "known_evidence_count": null, "matches": 36, "name": "Protein of unknown function (DUF2660)", "partial_evidence_count": null, "pfam_id": "PF10859", "proteins": 36, "proteomes": 36, "short_name": "DUF2660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10859", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025022", "known_evidence_count": null, "matches": 36, "name": "Protein of unknown function (DUF3911)", "partial_evidence_count": null, "pfam_id": "PF13050", "proteins": 36, "proteomes": 35, "short_name": "DUF3911", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13050", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025005", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF3974)", "partial_evidence_count": null, "pfam_id": "PF13120", "proteins": 36, "proteomes": 36, "short_name": "DUF3974", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13120", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are approximately 230 amino acids in length. The structure of PF2046 from pyrococcus furiosus has been solved. It shows an RNaseH like fold that conserves critical catalytic residues [[cite:PUB00057311]]. This suggests that these proteins may cleave nucleic acid.", "domain_architectures": 1, "interpro_id": "IPR025206", "known_evidence_count": null, "matches": 36, "name": "Protein of unknown function (DUF4152)", "partial_evidence_count": null, "pfam_id": "PF13680", "proteins": 36, "proteomes": 35, "short_name": "DUF4152", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13680", "structures": 9, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 210 residues in length and is mainly found in various Staphylococcus species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032615", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF4887)", "partial_evidence_count": null, "pfam_id": "PF16228", "proteins": 36, "proteomes": 36, "short_name": "DUF4887", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16228", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family lies further downstream of DUF5111, [pfam:PF17138], on proteins from Bacteroidetes that also carry a SusE family, [pfam:PF14292].", "domain_architectures": 6, "interpro_id": "IPR033407", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF5114)", "partial_evidence_count": null, "pfam_id": "PF17141", "proteins": 36, "proteomes": 36, "short_name": "DUF5114", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17141", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Methanobacteria and Methanococci.", "domain_architectures": 2, "interpro_id": "IPR020380", "known_evidence_count": null, "matches": 37, "name": "Family of unknown function (DUF5402)", "partial_evidence_count": null, "pfam_id": "PF17393", "proteins": 36, "proteomes": 31, "short_name": "DUF5402", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17393", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in Platyhelminthes.", "domain_architectures": 1, "interpro_id": "IPR043783", "known_evidence_count": null, "matches": 36, "name": "Family of unknown function (DUF5725)", "partial_evidence_count": null, "pfam_id": "PF18992", "proteins": 36, "proteomes": 35, "short_name": "DUF5725", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18992", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 34, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in Iridoviridae.", "domain_architectures": 1, "interpro_id": "IPR043907", "known_evidence_count": null, "matches": 36, "name": "Family of unknown function (DUF5770)", "partial_evidence_count": null, "pfam_id": "PF19074", "proteins": 36, "proteomes": 35, "short_name": "DUF5770", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19074", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 1, "interpro_id": "IPR045638", "known_evidence_count": null, "matches": 36, "name": "Family of unknown function (DUF6409)", "partial_evidence_count": null, "pfam_id": "PF19947", "proteins": 36, "proteomes": 35, "short_name": "DUF6409", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19947", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is based on the known structure of a protein from Ruminococcus gnavus PDB:3noh. The structure shows similarity to solute binding proteins. The exact function of these proteins is not yet known.", "domain_architectures": 1, "interpro_id": "IPR054214", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF6921)", "partial_evidence_count": null, "pfam_id": "PF21914", "proteins": 36, "proteomes": 35, "short_name": "DUF6921", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21914", "structures": 1, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found towards the N-terminal of some PRiA4b ORF-3-like proteins from bacteria, such as SwissProt:A0A1I7K0M5. This domain may adopt a TPR-like fold and is generally associated to PriA4_ORF3 ([pfam:PF07929]) domain.", "domain_architectures": 4, "interpro_id": "IPR055824", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF7400)", "partial_evidence_count": null, "pfam_id": "PF24133", "proteins": 36, "proteomes": 36, "short_name": "DUF7400", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24133", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR056036", "known_evidence_count": null, "matches": 36, "name": "Family of unknown function (DUF7618)", "partial_evidence_count": null, "pfam_id": "PF24594", "proteins": 36, "proteomes": 36, "short_name": "DUF7618", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24594", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain four predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058377", "known_evidence_count": null, "matches": 36, "name": "Family of unknown function (DUF8064)", "partial_evidence_count": null, "pfam_id": "PF26260", "proteins": 36, "proteomes": 35, "short_name": "DUF8064", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26260", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a the central domain from a family of uncharacterised proteins found predominantly in archaea, specifically within the Halobacteria class. The proteins in this family are typically found in species such as Halovenus, Halobellus, and Natrarchaeobaculum, among others. Additionally, some members are associated with viruses like the Pleolipoviridae family. The domain is approximately 60-70 amino acids in length. The proteins containing this domain are predicted to be involved in replication processes, although their exact function remains unknown. The domain is found in proteins that are generally around 600-700 amino acids in length. These proteins are primarily associated with replication functions, as indicated by their presence in replication proteins across various archaeal species and viruses.", "domain_architectures": 3, "interpro_id": "IPR059015", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF8148) central domain", "partial_evidence_count": null, "pfam_id": "PF26474", "proteins": 36, "proteomes": 27, "short_name": "DUF8148_M", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26474", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain from a family of uncharacterised proteins found predominantly in Proteobacteria that contain two domains. The proteins are distributed among various orders including Burkholderiales, Rhodobacterales, and Hyphomicrobiales. The proteins in this family are typically around 240 to 250 amino acids in length. This domain contains a conserved RHG motif that may be functionally important. This alpha helical domain belongs to the Hpt superfamily according to CATH.", "domain_architectures": 2, "interpro_id": "IPR059012", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF8168) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26504", "proteins": 36, "proteomes": 36, "short_name": "DUF8168_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26504", "structures": 0, "taxa": 152, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Alveolata lineage. It contains several highly conserved cysteine residues which are predicted to form disulfide bonds.", "domain_architectures": 10, "interpro_id": "IPR059377", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF8333)", "partial_evidence_count": null, "pfam_id": "PF27013", "proteins": 36, "proteomes": 10, "short_name": "DUF8333", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27013", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 36, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains several conserved cysteine residues which are predicted to form disulfide bonds.", "domain_architectures": 1, "interpro_id": "IPR059420", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF8376)", "partial_evidence_count": null, "pfam_id": "PF28252", "proteins": 36, "proteomes": 13, "short_name": "DUF8376", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28252", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an immunoglobulin-like domain found in outer membrane proteins of spirochaetes, particularly Treponema species. The domain is approximately 90-100 residues long and adopts the characteristic Ig-like fold consisting of two beta-sheets arranged in a sandwich configuration. These proteins are typically bipartite, containing this N-terminal periplasmic Ig-like domain and a C-terminal domain. The domain is found in proteins predicted to be outer membrane lipoproteins. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061593", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF8523)", "partial_evidence_count": null, "pfam_id": "PF29240", "proteins": 36, "proteomes": 36, "short_name": "DUF8523", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29240", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal helical domain of approximately 100 residues found in spirochaetes, particularly Treponema species. The domain adopts an alpha-helical hairpin structure and is predicted to contain transmembrane helices. It is typically found at the C-terminus of proteins that also contain multiple N-terminal domains. The function of this domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061595", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF8525)", "partial_evidence_count": null, "pfam_id": "PF29242", "proteins": 36, "proteomes": 34, "short_name": "DUF8525", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29242", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the fourth domain found in a family of uncharacterised hypothetical prokaryotic proteins.", "domain_architectures": 6, "interpro_id": "IPR063023", "known_evidence_count": null, "matches": 36, "name": "DUF499 4th domain", "partial_evidence_count": null, "pfam_id": "PF30799", "proteins": 36, "proteomes": 36, "short_name": "DUF499_4th", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30799", "structures": 0, "taxa": 101, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region approximately 50 residues long within a number of proteins of unknown function that seem to be restricted to C. elegans. The GO annotation for this protein indicate that its a protein involved in nematode larval development and has a positive regulation on growth rate.", "domain_architectures": 2, "interpro_id": "IPR009676", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF1265)", "partial_evidence_count": null, "pfam_id": "PF06887", "proteins": 35, "proteomes": 13, "short_name": "DUF1265", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06887", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Alphaherpesvirus proteins of around 200 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010741", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF1314)", "partial_evidence_count": null, "pfam_id": "PF07013", "proteins": 35, "proteomes": 20, "short_name": "DUF1314", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07013", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This viral family of proteins have no known function.", "domain_architectures": 1, "interpro_id": "IPR020387", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF2661)", "partial_evidence_count": null, "pfam_id": "PF10860", "proteins": 35, "proteomes": 32, "short_name": "DUF2661", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10860", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a bacterial family of proteins with unknown function.", "domain_architectures": 2, "interpro_id": "IPR020183", "known_evidence_count": null, "matches": 36, "name": "Protein of unknown function (DUF2748)", "partial_evidence_count": null, "pfam_id": "PF10871", "proteins": 35, "proteomes": 33, "short_name": "DUF2748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10871", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of archaeal proteins with unknown function appears to be restricted ton Thermococcaceae.", "domain_architectures": 2, "interpro_id": "IPR023108", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF3216)", "partial_evidence_count": null, "pfam_id": "PF11505", "proteins": 35, "proteomes": 35, "short_name": "DUF3216", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11505", "structures": 1, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025024", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF3913)", "partial_evidence_count": null, "pfam_id": "PF13052", "proteins": 35, "proteomes": 35, "short_name": "DUF3913", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13052", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025038", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF3924)", "partial_evidence_count": null, "pfam_id": "PF13062", "proteins": 35, "proteomes": 35, "short_name": "DUF3924", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13062", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length. There are two conserved sequence motifs: FYF and AFW.", "domain_architectures": 1, "interpro_id": "IPR025082", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF3964)", "partial_evidence_count": null, "pfam_id": "PF13107", "proteins": 35, "proteomes": 35, "short_name": "DUF3964", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13107", "structures": 0, "taxa": 56, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in found in Bacillus species. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR031998", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF5065)", "partial_evidence_count": null, "pfam_id": "PF16723", "proteins": 35, "proteomes": 18, "short_name": "DUF5065", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16723", "structures": 1, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycobacterium phages and bacteria.", "domain_architectures": 1, "interpro_id": "IPR039451", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF5419)", "partial_evidence_count": null, "pfam_id": "PF17441", "proteins": 35, "proteomes": 35, "short_name": "DUF5419", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17441", "structures": 0, "taxa": 96, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a 40 residue repeat that is often found in tandem in a small set of bacterial cell surface proteins. The function of this region is not known.", "domain_architectures": 20, "interpro_id": "IPR040912", "known_evidence_count": null, "matches": 48, "name": "Family of unknown function (DUF5633)", "partial_evidence_count": null, "pfam_id": "PF18656", "proteins": 35, "proteomes": 19, "short_name": "DUF5633", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18656", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This uncharacterised family is found in various Platyhelminthes. Most proteins in the family contain a C-terminal death domain. This region is composed of three alpha helices.", "domain_architectures": 4, "interpro_id": "IPR043801", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF5740)", "partial_evidence_count": null, "pfam_id": "PF19011", "proteins": 35, "proteomes": 22, "short_name": "DUF5740", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19011", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 35, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family of euryarchaeal proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR043960", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF5748)", "partial_evidence_count": null, "pfam_id": "PF19022", "proteins": 35, "proteomes": 35, "short_name": "DUF5748", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19022", "structures": 1, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of known function found in viruses, particularly in Conferred and Mummified.", "domain_architectures": 1, "interpro_id": "IPR043913", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF5764)", "partial_evidence_count": null, "pfam_id": "PF19068", "proteins": 35, "proteomes": 31, "short_name": "DUF5764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19068", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001096) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the FR901464 biosynthetic gene cluster from Pseudomonas sp. 2663 [[cite:PUB00099400]].", "domain_architectures": 1, "interpro_id": "IPR046244", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF6277)", "partial_evidence_count": null, "pfam_id": "PF19793", "proteins": 35, "proteomes": 33, "short_name": "DUF6277", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19793", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised mycobacterium phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055660", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF7236)", "partial_evidence_count": null, "pfam_id": "PF23883", "proteins": 35, "proteomes": 26, "short_name": "DUF7236", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23883", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins from phage. The structure of this family does not appear similar to any other known protein or family.", "domain_architectures": 1, "interpro_id": "IPR055696", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF7272)", "partial_evidence_count": null, "pfam_id": "PF23937", "proteins": 35, "proteomes": 35, "short_name": "DUF7272", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23937", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a beta-sandwich structure with significant topological similarity to known galactose-binding domains, in particular to lectin-like domain of the Cwp84, a surface layer associated protein of Clostridium difficile. It is likely that this domain is involved carbohydrate binding.", "domain_architectures": 11, "interpro_id": "IPR057223", "known_evidence_count": null, "matches": 41, "name": "Domain of unknown function (DUF7901)", "partial_evidence_count": null, "pfam_id": "PF25470", "proteins": 35, "proteomes": 28, "short_name": "DUF7901", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25470", "structures": 0, "taxa": 121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry corresponds to a mycobacterial domain of unknown function that shows structural similarity to [pfam:PF04603].", "domain_architectures": 1, "interpro_id": "IPR058262", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF7956)", "partial_evidence_count": null, "pfam_id": "PF25845", "proteins": 35, "proteomes": 26, "short_name": "DUF7956", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25845", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. These adopt a fold with similarity to the OB-fold. AlphaFold3 provides weak evidence that this protein may homodimerise.", "domain_architectures": 1, "interpro_id": "IPR058359", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF8046)", "partial_evidence_count": null, "pfam_id": "PF26219", "proteins": 35, "proteomes": 35, "short_name": "DUF8046", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26219", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins in this family are predominantly found in halophilic archaea, including members of the Halobacteriales order. Proteins containing this domain are typically around 140 amino acids in length. The domain is predicted to be part of integral membrane proteins, as suggested by the presence of multiple transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058446", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF8133)", "partial_evidence_count": null, "pfam_id": "PF26454", "proteins": 35, "proteomes": 35, "short_name": "DUF8133", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26454", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal winged helix domain from a family of uncharacterised proteins found predominantly in archaea, specifically within the Halobacteria class. The proteins in this family are typically found in species such as Halovenus, Halobellus, and Natrarchaeobaculum, among others. Additionally, some members are associated with viruses like the Pleolipoviridae family. The proteins containing this domain are predicted to be involved in replication processes, although their exact function remains unknown. The domain is found in proteins that are generally around 600-700 amino acids in length. These proteins are primarily associated with replication functions, as indicated by their presence in replication proteins across various archaeal species and viruses. The domain is sometimes found in association with other domains involved in replication, but specific domain associations are not consistently observed across all members of this family.", "domain_architectures": 2, "interpro_id": "IPR058461", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF8148) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26473", "proteins": 35, "proteomes": 26, "short_name": "DUF8148", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26473", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Microbacteriaceae. It contains repetitive QC sequence motif frequently found in the context of NQCN motif. This domain is predicted to fold into an unique beta-sandwich formed of these consecutive motifs.", "domain_architectures": 1, "interpro_id": "IPR059297", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF8253)", "partial_evidence_count": null, "pfam_id": "PF26781", "proteins": 35, "proteomes": 32, "short_name": "DUF8253", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26781", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains several highly conserved cysteine and histidine residues that may be involved in metal coordination. This domain is predicted to fold into a structure that resembles a double zinc ribbon domain with swapped knuckles.", "domain_architectures": 2, "interpro_id": "IPR059372", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF8328)", "partial_evidence_count": null, "pfam_id": "PF27007", "proteins": 35, "proteomes": 33, "short_name": "DUF8328", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27007", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an helical domain found at the middle region of a group of uncharacterised sequences from bacteria that contain a FtsH ternary system domain X7 at the N-terminal.", "domain_architectures": 3, "interpro_id": "IPR061648", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF8587)", "partial_evidence_count": null, "pfam_id": "PF29805", "proteins": 35, "proteomes": 26, "short_name": "DUF8587", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29805", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of the N termini of some human herpesvirus U58 proteins, and some cytomegalovirus UL87 proteins. This region is always found N terminal to the Pfam family UL87 ([pfam:PF03043]), which has no known function.", "domain_architectures": 1, "interpro_id": "IPR007618", "known_evidence_count": null, "matches": 34, "name": "Protein of unknown function (DUF587)", "partial_evidence_count": null, "pfam_id": "PF04532", "proteins": 34, "proteomes": 26, "short_name": "DUF587", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04532", "structures": 0, "taxa": 103, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "These proteins appear to be specific to Mycoplasma species.", "domain_architectures": 1, "interpro_id": "IPR011631", "known_evidence_count": null, "matches": 34, "name": "Protein of unknown function (DUF1600)", "partial_evidence_count": null, "pfam_id": "PF07667", "proteins": 34, "proteomes": 17, "short_name": "DUF1600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07667", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are found in 3-mercaptopyruvate sulfurtransferase, and have no known function. They adopt a structure consisting of a four-stranded antiparallel beta-sheet and an alpha-helix, arranged in a beta(2)-alpha-beta(2) fashion, and bearing a remarkable structural similarity to the FK506-binding protein class of peptidylprolyl cis/trans-isomerase [[cite:PUB00029481]].", "domain_architectures": 3, "interpro_id": "IPR015206", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF1930)", "partial_evidence_count": null, "pfam_id": "PF09122", "proteins": 34, "proteomes": 28, "short_name": "DUF1930", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09122", "structures": 1, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Rickettsiae.", "domain_architectures": 1, "interpro_id": "IPR022718", "known_evidence_count": null, "matches": 34, "name": "Protein of unknown function (DUF2672)", "partial_evidence_count": null, "pfam_id": "PF10878", "proteins": 34, "proteomes": 34, "short_name": "DUF2672", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10878", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in bacteria and eukaryotes, and is approximately 30 amino acids in length. There is a conserved WMPC sequence motif. There are two completely conserved residues (A and C) that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR022196", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function", "partial_evidence_count": null, "pfam_id": "PF12518", "proteins": 34, "proteomes": 16, "short_name": "DUF3721", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12518", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 40 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025000", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF3903)", "partial_evidence_count": null, "pfam_id": "PF13043", "proteins": 34, "proteomes": 33, "short_name": "DUF3903", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13043", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025021", "known_evidence_count": null, "matches": 34, "name": "Protein of unknown function (DUF3910)", "partial_evidence_count": null, "pfam_id": "PF13049", "proteins": 34, "proteomes": 34, "short_name": "DUF3910", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13049", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025168", "known_evidence_count": null, "matches": 34, "name": "Protein of unknown function (DUF3925)", "partial_evidence_count": null, "pfam_id": "PF13063", "proteins": 34, "proteomes": 34, "short_name": "DUF3925", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13063", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025078", "known_evidence_count": null, "matches": 34, "name": "Protein of unknown function (DUF3931)", "partial_evidence_count": null, "pfam_id": "PF13082", "proteins": 34, "proteomes": 34, "short_name": "DUF3931", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13082", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 380 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025087", "known_evidence_count": null, "matches": 34, "name": "Protein of unknown function (DUF3965)", "partial_evidence_count": null, "pfam_id": "PF13112", "proteins": 34, "proteomes": 34, "short_name": "DUF3965", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13112", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 72 and 89 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025046", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF3960)", "partial_evidence_count": null, "pfam_id": "PF13142", "proteins": 34, "proteomes": 34, "short_name": "DUF3960", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13142", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Podoviridae.", "domain_architectures": 1, "interpro_id": "IPR035148", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF5480)", "partial_evidence_count": null, "pfam_id": "PF17576", "proteins": 34, "proteomes": 31, "short_name": "DUF5480", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17576", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in various Platyhelminthes.", "domain_architectures": 2, "interpro_id": "IPR043800", "known_evidence_count": null, "matches": 36, "name": "Family of unknown function (DUF5739)", "partial_evidence_count": null, "pfam_id": "PF19010", "proteins": 34, "proteomes": 31, "short_name": "DUF5739", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19010", "structures": 0, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000938) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a protein from the fosfomycin biosynthetic gene cluster from Streptomyces fradiae [[cite:PUB00099438],[cite:PUB00099377]].", "domain_architectures": 1, "interpro_id": "IPR046067", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF6025)", "partial_evidence_count": null, "pfam_id": "PF19490", "proteins": 34, "proteomes": 32, "short_name": "DUF6025", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19490", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000919) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). This family includes a protein from the phaseolotoxin biosynthetic gene cluster from Pseudomonas syringae and appears to be predominantly found in bacteria [[cite:PUB00099406]].", "domain_architectures": 1, "interpro_id": "IPR046072", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF6031)", "partial_evidence_count": null, "pfam_id": "PF19496", "proteins": 34, "proteomes": 29, "short_name": "DUF6031", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19496", "structures": 0, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000976) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the curacin A biosynthetic gene cluster from Moorea producens 3L [[cite:PUB00099410],[cite:PUB00099420]]. This family appears to be predominantly found in Cyanobacteria.", "domain_architectures": 2, "interpro_id": "IPR046180", "known_evidence_count": null, "matches": 35, "name": "Family of unknown function (DUF6208)", "partial_evidence_count": null, "pfam_id": "PF19713", "proteins": 34, "proteomes": 31, "short_name": "DUF6208", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19713", "structures": 0, "taxa": 148, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 33, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is found C-terminal to [pfam:PF02933], in CDC48 proteins. Its function is unknown.", "domain_architectures": 1, "interpro_id": "IPR049295", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF6849)", "partial_evidence_count": null, "pfam_id": "PF20986", "proteins": 34, "proteomes": 34, "short_name": "DUF6849", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20986", "structures": 2, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in the phages infecting Mycobacterium and Gordonia. The domain is around 70-100 amino acids long.", "domain_architectures": 1, "interpro_id": "IPR055657", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF7233)", "partial_evidence_count": null, "pfam_id": "PF23880", "proteins": 34, "proteomes": 34, "short_name": "DUF7233", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23880", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins from proteobacteria. This domain is sometimes found N-terminal to [pfam:PF21832].", "domain_architectures": 2, "interpro_id": "IPR055680", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF7256)", "partial_evidence_count": null, "pfam_id": "PF23917", "proteins": 34, "proteomes": 32, "short_name": "DUF7256", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23917", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. Proteins in this family are around 250 residues in length.", "domain_architectures": 1, "interpro_id": "IPR055753", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF7329)", "partial_evidence_count": null, "pfam_id": "PF24015", "proteins": 34, "proteomes": 34, "short_name": "DUF7329", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24015", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of phage proteins. The proteins appear to contain two domains. The N-terminal domain contains a small beta sheet wrapped around an alpha helix. The second domain is composed of a pair of alpha helices. The proteins are found in several viruses within the proposed new Crassvirales order of bacteriophages.", "domain_architectures": 1, "interpro_id": "IPR055823", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF7399)", "partial_evidence_count": null, "pfam_id": "PF24132", "proteins": 34, "proteomes": 34, "short_name": "DUF7399", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24132", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved domain found predominantly in bacteriophage proteins. The domain is characterized by a highly conserved YDRH motif, which likely plays an important role in the domain's function or structure. This family includes proteins from various phages that infect cyanobacteria, particularly Synechococcus and Prochlorococcus species. The proteins contain a central small domain composed of a three stranded beta sheet with an alpha helix inserted between the second and third strands.", "domain_architectures": 1, "interpro_id": "IPR055864", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF7441)", "partial_evidence_count": null, "pfam_id": "PF24225", "proteins": 34, "proteomes": 34, "short_name": "DUF7441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24225", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised staphylococcal phage proteins. Structure prediction suggests they form a compact domain composed of a three stranded beta sheet packed against an alpha helix.", "domain_architectures": 1, "interpro_id": "IPR056061", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF7644)", "partial_evidence_count": null, "pfam_id": "PF24651", "proteins": 34, "proteomes": 34, "short_name": "DUF7644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24651", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in halobacteria. Proteins in this family form a compact structure with two long beta strands and an alpha helix. These proteins are predicted to form homooligomeric complexes. These proteins likely form large oligomeric ring complexes (E4NL25 14mer ipTM=0.84 pTM=0.85). The function of this complex are not known.", "domain_architectures": 1, "interpro_id": "IPR058315", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF8002)", "partial_evidence_count": null, "pfam_id": "PF26009", "proteins": 34, "proteomes": 34, "short_name": "DUF8002", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26009", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. Many members contain cysteine residues which are predicted to for disulfide bond. This domain is frequently found in tandem copies.", "domain_architectures": 19, "interpro_id": "IPR059335", "known_evidence_count": null, "matches": 58, "name": "Domain of unknown function (DUF8291)", "partial_evidence_count": null, "pfam_id": "PF26940", "proteins": 34, "proteomes": 22, "short_name": "DUF8291", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26940", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised plant proteins. It is predicted to fold into mainly helical structure and is frequently found in combination with ATPase domains.", "domain_architectures": 3, "interpro_id": "IPR059412", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF8368)", "partial_evidence_count": null, "pfam_id": "PF28041", "proteins": 34, "proteomes": 4, "short_name": "DUF8368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28041", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Gammaproteobacteria. It is predicted to fold into a beta-meander that curves around a single alpha-helix. It contains two conserved sequence motifs DxDGxxD and QxPP.", "domain_architectures": 1, "interpro_id": "IPR059423", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF8379)", "partial_evidence_count": null, "pfam_id": "PF28292", "proteins": 34, "proteomes": 34, "short_name": "DUF8379", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28292", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 30 residues found predominantly in cyanophages (Kyanoviridae) and also in their cyanobacterial hosts (Prochlorococcus). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061712", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF8651)", "partial_evidence_count": null, "pfam_id": "PF30587", "proteins": 34, "proteomes": 34, "short_name": "DUF8651", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30587", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Protein of unknown function, found in herpesvirus and cytomegalovirus.", "domain_architectures": 1, "interpro_id": "IPR007578", "known_evidence_count": null, "matches": 33, "name": "Protein of unknown function (DUF570)", "partial_evidence_count": null, "pfam_id": "PF04489", "proteins": 33, "proteomes": 22, "short_name": "DUF570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04489", "structures": 0, "taxa": 96, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Paramecium bursaria chlorella virus 1 (PBCV-1) proteins of around 250 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009820", "known_evidence_count": null, "matches": 33, "name": "Protein of unknown function (DUF1390)", "partial_evidence_count": null, "pfam_id": "PF07150", "proteins": 33, "proteomes": 4, "short_name": "DUF1390", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07150", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The backbone structure of this family of proteins has been determined however the function remains unknown. The protein has an alpha and beta structure with a ferredoxin-like fold [[cite:PUB00040528]].", "domain_architectures": 1, "interpro_id": "IPR021583", "known_evidence_count": null, "matches": 33, "name": "Protein of unknown function (DUF3213)", "partial_evidence_count": null, "pfam_id": "PF11491", "proteins": 33, "proteomes": 33, "short_name": "DUF3213", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11491", "structures": 1, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 32, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of bacterial proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021699", "known_evidence_count": null, "matches": 33, "name": "Protein of unknown function (DUF3281)", "partial_evidence_count": null, "pfam_id": "PF11685", "proteins": 33, "proteomes": 10, "short_name": "DUF3281", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11685", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025170", "known_evidence_count": null, "matches": 33, "name": "Protein of unknown function (DUF3928)", "partial_evidence_count": null, "pfam_id": "PF13065", "proteins": 33, "proteomes": 33, "short_name": "DUF3928", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13065", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 51 and 67 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025172", "known_evidence_count": null, "matches": 33, "name": "Protein of unknown function (DUF3930)", "partial_evidence_count": null, "pfam_id": "PF13067", "proteins": 33, "proteomes": 33, "short_name": "DUF3930", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13067", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025073", "known_evidence_count": null, "matches": 33, "name": "Protein of unknown function (DUF3909)", "partial_evidence_count": null, "pfam_id": "PF13077", "proteins": 33, "proteomes": 33, "short_name": "DUF3909", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13077", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of uncharacterized proteins around 140 residues in length and is mainly found in various Bacteroides species, such as Bacteroides fragilis and Bacteroides sp.. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032544", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF4945)", "partial_evidence_count": null, "pfam_id": "PF16303", "proteins": 33, "proteomes": 32, "short_name": "DUF4945", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16303", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 150 residues locates in the N-terminal of some uncharacterized proteins in various Bacteroides and Prevotella species. The function of this family remains unknown.", "domain_architectures": 4, "interpro_id": "IPR032155", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16383", "proteins": 33, "proteomes": 29, "short_name": "DUF4992", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16383", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is believed to be involved in the type VII secretion system.", "domain_architectures": 2, "interpro_id": "IPR031689", "known_evidence_count": null, "matches": 34, "name": "Domain of unknown function (DUF5080)", "partial_evidence_count": null, "pfam_id": "PF16883", "proteins": 33, "proteomes": 25, "short_name": "DUF5080", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16883", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteria. Family members have one predicted trans-membrane region.", "domain_architectures": 1, "interpro_id": "IPR035207", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF5457)", "partial_evidence_count": null, "pfam_id": "PF17540", "proteins": 33, "proteomes": 32, "short_name": "DUF5457", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17540", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function. Family members include the hypothetical protein TTHC002 from Thermus thermophilus. Its has an alpha-beta-alpha-beta(3) structure and forms a dimer with a single beta-sheet, folded in a barrel-like shape [[cite:PUB00094504]].", "domain_architectures": 1, "interpro_id": "IPR043707", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF5647)", "partial_evidence_count": null, "pfam_id": "PF18882", "proteins": 33, "proteomes": 18, "short_name": "DUF5647", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18882", "structures": 1, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in various Platyhelminthes.", "domain_architectures": 1, "interpro_id": "IPR043984", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF5742)", "partial_evidence_count": null, "pfam_id": "PF19013", "proteins": 33, "proteomes": 32, "short_name": "DUF5742", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19013", "structures": 0, "taxa": 91, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 2, "interpro_id": "IPR043886", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF5846)", "partial_evidence_count": null, "pfam_id": "PF19164", "proteins": 33, "proteomes": 11, "short_name": "DUF5846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19164", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000758) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the capsular polysaccharide biosynthetic gene cluster from Staphylococcus aureus [[cite:PUB00007578]].", "domain_architectures": 1, "interpro_id": "IPR046101", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF6038)", "partial_evidence_count": null, "pfam_id": "PF19504", "proteins": 33, "proteomes": 15, "short_name": "DUF6038", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19504", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001053) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the tubulysin A biosynthetic gene cluster from Archangium disciforme [[cite:PUB00099437]].", "domain_architectures": 1, "interpro_id": "IPR045947", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF6367)", "partial_evidence_count": null, "pfam_id": "PF19894", "proteins": 33, "proteomes": 32, "short_name": "DUF6367", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19894", "structures": 0, "taxa": 121, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a phage protein of unknown function. According to AlphaFold models the domain forms a four stranded beta sheet followed by a single alpha helix. This domain forms a confident dimer according to AlphaFold.", "domain_architectures": 1, "interpro_id": "IPR055638", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF7214)", "partial_evidence_count": null, "pfam_id": "PF23851", "proteins": 33, "proteomes": 33, "short_name": "DUF7214", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23851", "structures": 0, "taxa": 91, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. These proteins range in length from 94 to 110 amino acids and adopt a small domain composed of four alpha helices.", "domain_architectures": 1, "interpro_id": "IPR055791", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF7367)", "partial_evidence_count": null, "pfam_id": "PF24075", "proteins": 33, "proteomes": 33, "short_name": "DUF7367", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24075", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein of unknown function, found primarily in phage proteins of about 60 to 75 amino acids in length. It contains a single predicted transmembrane helix in many members. Most sequences also contain a region of predicted intrinsic disorder at the C-terminus rich in basic and acidic residues. Further experimental study is required to determine the function of these proteins. Some proteins are annotated as holins but the source of this annotation is unknown.", "domain_architectures": 1, "interpro_id": "IPR055818", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF7394)", "partial_evidence_count": null, "pfam_id": "PF24126", "proteins": 33, "proteomes": 33, "short_name": "DUF7394", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24126", "structures": 0, "taxa": 94, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised domains found in halobacteria.", "domain_architectures": 2, "interpro_id": "IPR058358", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF8045)", "partial_evidence_count": null, "pfam_id": "PF26193", "proteins": 33, "proteomes": 31, "short_name": "DUF8045", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26193", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from insects. It is predicted to adopt an alpha/beta structure composed of a curved six-stranded antiparallel beta-sheet packed with alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR059317", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF8273)", "partial_evidence_count": null, "pfam_id": "PF26842", "proteins": 33, "proteomes": 25, "short_name": "DUF8273", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26842", "structures": 0, "taxa": 130, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised phage proteins. It is predicted to fold into an alpha-helical structure.", "domain_architectures": 1, "interpro_id": "IPR059352", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF8308)", "partial_evidence_count": null, "pfam_id": "PF26975", "proteins": 33, "proteomes": 29, "short_name": "DUF8308", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26975", "structures": 0, "taxa": 102, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in the YonD protein from Bacillus subtilis and related proteins. It is predicted to fold into a curved beta-sheet enclosing an alpha-helix. The function of this domain is unknown.", "domain_architectures": 5, "interpro_id": "IPR061601", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF8531)", "partial_evidence_count": null, "pfam_id": "PF29301", "proteins": 33, "proteomes": 33, "short_name": "DUF8531", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29301", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 55 residues in length found in Cyanobacteriota, predominantly in Prochlorococcus species. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061694", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF8633)", "partial_evidence_count": null, "pfam_id": "PF30566", "proteins": 33, "proteomes": 16, "short_name": "DUF8633", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30566", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 55 residues in length found in Cyanobacteriota, predominantly in Prochlorococcus and Synechococcus species. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061696", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF8635)", "partial_evidence_count": null, "pfam_id": "PF30568", "proteins": 33, "proteomes": 18, "short_name": "DUF8635", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30568", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 85 residues in length that are predicted to be disordered. Members are found in Cyanobacteriota and in cyanophages (Kyanoviridae). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR063796", "known_evidence_count": null, "matches": 33, "name": "Disordered region of unknown function (DUF8643)", "partial_evidence_count": null, "pfam_id": "PF30576", "proteins": 33, "proteomes": 30, "short_name": "DUF8643", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30576", "structures": 0, "taxa": 99, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be conserved to Rickettsia spp.", "domain_architectures": 1, "interpro_id": "IPR024246", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF2674)", "partial_evidence_count": null, "pfam_id": "PF10879", "proteins": 32, "proteomes": 32, "short_name": "DUF2674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10879", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Rickettsiae spp.", "domain_architectures": 1, "interpro_id": "IPR024247", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF2673)", "partial_evidence_count": null, "pfam_id": "PF10880", "proteins": 32, "proteomes": 32, "short_name": "DUF2673", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10880", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Rickettsia spp.", "domain_architectures": 1, "interpro_id": "IPR024444", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF2706)", "partial_evidence_count": null, "pfam_id": "PF10913", "proteins": 32, "proteomes": 32, "short_name": "DUF2706", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10913", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR024484", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF2709)", "partial_evidence_count": null, "pfam_id": "PF10915", "proteins": 32, "proteomes": 31, "short_name": "DUF2709", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10915", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as KleF however no function is known.", "domain_architectures": 1, "interpro_id": "IPR024249", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF2761)", "partial_evidence_count": null, "pfam_id": "PF10959", "proteins": 32, "proteomes": 20, "short_name": "DUF2761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10959", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 70 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025171", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF3929)", "partial_evidence_count": null, "pfam_id": "PF13066", "proteins": 32, "proteomes": 32, "short_name": "DUF3929", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13066", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025173", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF3932)", "partial_evidence_count": null, "pfam_id": "PF13068", "proteins": 32, "proteomes": 32, "short_name": "DUF3932", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13068", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025070", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF3938)", "partial_evidence_count": null, "pfam_id": "PF13074", "proteins": 32, "proteomes": 32, "short_name": "DUF3938", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13074", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 260 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025080", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF3959)", "partial_evidence_count": null, "pfam_id": "PF13105", "proteins": 32, "proteomes": 32, "short_name": "DUF3959", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13105", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 58 and 86 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025084", "known_evidence_count": null, "matches": 32, "name": "Protein of unknown function (DUF3966)", "partial_evidence_count": null, "pfam_id": "PF13110", "proteins": 32, "proteomes": 32, "short_name": "DUF3966", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13110", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 190 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025089", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF4018)", "partial_evidence_count": null, "pfam_id": "PF13210", "proteins": 32, "proteomes": 31, "short_name": "DUF4018", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13210", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 160 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031864", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF4756)", "partial_evidence_count": null, "pfam_id": "PF15948", "proteins": 32, "proteomes": 30, "short_name": "DUF4756", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15948", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 140 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032611", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF4891)", "partial_evidence_count": null, "pfam_id": "PF16232", "proteins": 32, "proteomes": 27, "short_name": "DUF4891", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16232", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Helicobacteraceae. Family members are predicted to contain one trans-membrane region.", "domain_architectures": 1, "interpro_id": "IPR035366", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF5408)", "partial_evidence_count": null, "pfam_id": "PF17402", "proteins": 32, "proteomes": 31, "short_name": "DUF5408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17402", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Rickettsia. Family members are predicted to contain one trans-membrane region.", "domain_architectures": 2, "interpro_id": "IPR020182", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF5460)", "partial_evidence_count": null, "pfam_id": "PF17544", "proteins": 32, "proteomes": 32, "short_name": "DUF5460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17544", "structures": 0, "taxa": 93, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000566) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR045350", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF5968)", "partial_evidence_count": null, "pfam_id": "PF19393", "proteins": 32, "proteomes": 30, "short_name": "DUF5968", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19393", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are around 180 amino acids in length. They contain highly conserved motifs, YKxLD and I/LC at the N-terminal and LKxxRxxRN in the middle.", "domain_architectures": 2, "interpro_id": "IPR046678", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF6548)", "partial_evidence_count": null, "pfam_id": "PF20185", "proteins": 32, "proteomes": 30, "short_name": "DUF6548", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20185", "structures": 0, "taxa": 147, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins that are glycine rich.", "domain_architectures": 1, "interpro_id": "IPR055749", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF7325)", "partial_evidence_count": null, "pfam_id": "PF24011", "proteins": 32, "proteomes": 32, "short_name": "DUF7325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24011", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in pseudomonas phage. The protein contains a compact domain composed of two alpha helices followed by four beta strands that form a beta sheet.", "domain_architectures": 1, "interpro_id": "IPR055872", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF7449)", "partial_evidence_count": null, "pfam_id": "PF24242", "proteins": 32, "proteomes": 32, "short_name": "DUF7449", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24242", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in Mycobacterial phage. The family includes gene 48 from phage Bxb1.", "domain_architectures": 2, "interpro_id": "IPR055879", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF7456)", "partial_evidence_count": null, "pfam_id": "PF24255", "proteins": 32, "proteomes": 32, "short_name": "DUF7456", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24255", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR056038", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF7621)", "partial_evidence_count": null, "pfam_id": "PF24599", "proteins": 32, "proteomes": 32, "short_name": "DUF7621", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24599", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of a small set of proteins belonging to the [pfam:PF04465]. Structure prediction suggests that this domain may mediate dimerisation.", "domain_architectures": 2, "interpro_id": "IPR056646", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF7744)", "partial_evidence_count": null, "pfam_id": "PF24897", "proteins": 32, "proteomes": 31, "short_name": "DUF7744", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24897", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a globular alpha/beta structure with similarity to AAA proteins.", "domain_architectures": 3, "interpro_id": "IPR057186", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF7864)", "partial_evidence_count": null, "pfam_id": "PF25264", "proteins": 32, "proteomes": 31, "short_name": "DUF7864", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25264", "structures": 0, "taxa": 127, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 31, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in the archaeal phylum Thermoproteota. The proteins are predominantly found in the order Sulfolobales, which includes genera such as Acidianus, Metallosphaera, and Sulfolobus. The domain is approximately 110 amino acids in length. The reviewed protein SSO0428 from Saccharolobus solfataricus is a representative member of this family. Proteins in this family are predicted to form a single long alpha helix. Structure prediction suggests that this protein does not form a homomeric coiled-coil complex. Based on genomic context this protein may be an accessory subunit of the V-type ATP synthase complex.", "domain_architectures": 1, "interpro_id": "IPR058494", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF8181)", "partial_evidence_count": null, "pfam_id": "PF26552", "proteins": 32, "proteomes": 32, "short_name": "DUF8181", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26552", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in uncharacterised eukaryotic proteins mainly from Trypanosoma. This domain contains a RNase-like fold. The core architecture typically features a central five-stranded beta-sheet flanked by several alpha-helices. This domain can be found associated with [pfam:PF01612].", "domain_architectures": 3, "interpro_id": "IPR059387", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF8343)", "partial_evidence_count": null, "pfam_id": "PF27042", "proteins": 32, "proteomes": 29, "short_name": "DUF8343", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27042", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 90-100 residues found in serine proteases from spirochaetes, predominantly Treponema species. The domain is located N-terminal to a trypsin-like serine protease domain ([pfam:PF00089], [pfam:PF13365]) and is typically followed by one or two C-terminal PDZ domains. Members include the periplasmic serine protease TP0546 from Treponema pallidum. The function of this domain remains to be determined.", "domain_architectures": 4, "interpro_id": "IPR061587", "known_evidence_count": null, "matches": 32, "name": "Domain of unknown function (DUF8517)", "partial_evidence_count": null, "pfam_id": "PF29231", "proteins": 32, "proteomes": 31, "short_name": "DUF8517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29231", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several herpesvirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR008002", "known_evidence_count": null, "matches": 31, "name": "Protein of unknown function (DUF717)", "partial_evidence_count": null, "pfam_id": "PF05338", "proteins": 31, "proteomes": 26, "short_name": "DUF717", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05338", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This family consists of several short, hypothetical bacterial proteins of around 62 residues in length. Members of this family are found in Escherichia coli and Salmonella typhi. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009572", "known_evidence_count": null, "matches": 31, "name": "Protein of unknown function (DUF1187)", "partial_evidence_count": null, "pfam_id": "PF06688", "proteins": 31, "proteomes": 19, "short_name": "DUF1187", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06688", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 4, "interpro_id": "IPR011436", "known_evidence_count": null, "matches": 39, "name": "Domain of Unknown Function (DUF1539)", "partial_evidence_count": null, "pfam_id": "PF07560", "proteins": 31, "proteomes": 16, "short_name": "DUF1539", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07560", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family appears to be found only in a small family of Chlamydia proteins.", "domain_architectures": 3, "interpro_id": "IPR013044", "known_evidence_count": null, "matches": 31, "name": "Domain of Unknown Function (DUF1548)", "partial_evidence_count": null, "pfam_id": "PF07579", "proteins": 31, "proteomes": 15, "short_name": "DUF1548", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07579", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of bacterial proteins with unknown function. These proteins have been classified as membrane proteins", "domain_architectures": 2, "interpro_id": "IPR019730", "known_evidence_count": null, "matches": 31, "name": "Protein of unknown function (DUF2606)", "partial_evidence_count": null, "pfam_id": "PF10794", "proteins": 31, "proteomes": 30, "short_name": "DUF2606", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10794", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins is a viral family, annotated as UL96. Currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR022614", "known_evidence_count": null, "matches": 31, "name": "Protein of unknown function (DUF2664)", "partial_evidence_count": null, "pfam_id": "PF10867", "proteins": 31, "proteomes": 24, "short_name": "DUF2664", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10867", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 66 and 79 amino acids in length. There are two conserved sequence motifs: FNIC and MALLNLT.", "domain_architectures": 1, "interpro_id": "IPR024993", "known_evidence_count": null, "matches": 31, "name": "Protein of unknown function (DUF3894)", "partial_evidence_count": null, "pfam_id": "PF13033", "proteins": 31, "proteomes": 31, "short_name": "DUF3894", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13033", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025027", "known_evidence_count": null, "matches": 31, "name": "Protein of unknown function (DUF3917)", "partial_evidence_count": null, "pfam_id": "PF13055", "proteins": 31, "proteomes": 31, "short_name": "DUF3917", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13055", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 60 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR025174", "known_evidence_count": null, "matches": 31, "name": "Protein of unknown function (DUF3933)", "partial_evidence_count": null, "pfam_id": "PF13069", "proteins": 31, "proteomes": 31, "short_name": "DUF3933", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13069", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 40 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025008", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF3976)", "partial_evidence_count": null, "pfam_id": "PF13121", "proteins": 31, "proteomes": 31, "short_name": "DUF3976", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13121", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidial sequences of unknown function.", "domain_architectures": 2, "interpro_id": "IPR031543", "known_evidence_count": null, "matches": 35, "name": "Domain of unknown function (DUF5087)", "partial_evidence_count": null, "pfam_id": "PF17006", "proteins": 31, "proteomes": 27, "short_name": "DUF5087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17006", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Caenorhabditis. It has an NTF2-like fold.", "domain_architectures": 7, "interpro_id": "IPR035415", "known_evidence_count": null, "matches": 32, "name": "Family of unknown function (DUF5382) central domain", "partial_evidence_count": null, "pfam_id": "PF17354", "proteins": 31, "proteomes": 10, "short_name": "DUF5382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17354", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Trypanosomatidae.", "domain_architectures": 1, "interpro_id": "IPR035155", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5393)", "partial_evidence_count": null, "pfam_id": "PF17371", "proteins": 31, "proteomes": 25, "short_name": "DUF5393", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17371", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chlamydiales.", "domain_architectures": 1, "interpro_id": "IPR035336", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5398)", "partial_evidence_count": null, "pfam_id": "PF17376", "proteins": 31, "proteomes": 31, "short_name": "DUF5398", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17376", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function specific to Rickettsia amblyommii.", "domain_architectures": 1, "interpro_id": "IPR035354", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5424)", "partial_evidence_count": null, "pfam_id": "PF17462", "proteins": 31, "proteomes": 28, "short_name": "DUF5424", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17462", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillales.", "domain_architectures": 1, "interpro_id": "IPR020252", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5446)", "partial_evidence_count": null, "pfam_id": "PF17522", "proteins": 31, "proteomes": 31, "short_name": "DUF5446", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17522", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in predicted cysteine knot peptides.", "domain_architectures": 1, "interpro_id": "IPR041434", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5637)", "partial_evidence_count": null, "pfam_id": "PF18687", "proteins": 31, "proteomes": 17, "short_name": "DUF5637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18687", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in different Platyhelminthes.", "domain_architectures": 1, "interpro_id": "IPR043793", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5735)", "partial_evidence_count": null, "pfam_id": "PF19006", "proteins": 31, "proteomes": 30, "short_name": "DUF5735", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19006", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this family of proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR043962", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5750)", "partial_evidence_count": null, "pfam_id": "PF19024", "proteins": 31, "proteomes": 31, "short_name": "DUF5750", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19024", "structures": 1, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR043861", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5823)", "partial_evidence_count": null, "pfam_id": "PF19140", "proteins": 31, "proteomes": 28, "short_name": "DUF5823", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19140", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phycodnaviridae.", "domain_architectures": 1, "interpro_id": "IPR043804", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5871)", "partial_evidence_count": null, "pfam_id": "PF19196", "proteins": 31, "proteomes": 14, "short_name": "DUF5871", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19196", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 6, "interpro_id": "IPR046116", "known_evidence_count": null, "matches": 36, "name": "Family of unknown function (DUF6053)", "partial_evidence_count": null, "pfam_id": "PF19523", "proteins": 31, "proteomes": 2, "short_name": "DUF6053", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19523", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the istamycin biosynthetic gene cluster from Streptomyces tenjimariensis [[cite:PUB00098957]].", "domain_architectures": 1, "interpro_id": "IPR046305", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF6420)", "partial_evidence_count": null, "pfam_id": "PF19984", "proteins": 31, "proteomes": 31, "short_name": "DUF6420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19984", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "name_matches_duf", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found at the C-terminal end of uncharacterised DUF3829-like proteins. It is often found associated to [pfam:PF20893]. Its function is unknown. It shows four alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR053996", "known_evidence_count": null, "matches": 31, "name": "DUF3829-like, C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF22219", "proteins": 31, "proteomes": 28, "short_name": "DUF3829_2nd", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22219", "structures": 2, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of cyanophage proteins, including Gp130, that are found in a variety of Synechococcus and Prochlorococcus phages. The family members are typically around 100 amino acids in length. Structure predictions do not show a globular fold for this protein. The exact function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR055640", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF7216)", "partial_evidence_count": null, "pfam_id": "PF23853", "proteins": 31, "proteomes": 31, "short_name": "DUF7216", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23853", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in enterobacteria phages. The proteins are around 80 residues in length. The proteins assume a compact domain that has four beta strands forming a sheet followed by three alpha helices packed on one side.", "domain_architectures": 1, "interpro_id": "IPR055714", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF7290)", "partial_evidence_count": null, "pfam_id": "PF23962", "proteins": 31, "proteomes": 31, "short_name": "DUF7290", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23962", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055759", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF7335)", "partial_evidence_count": null, "pfam_id": "PF24023", "proteins": 31, "proteomes": 31, "short_name": "DUF7335", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24023", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small uncharacterised family of Pseudomonas phage proteins. Structure prediction suggests that these proteins adopt a pair of alpha helices. These proteins are predicted to dimerise to form a four helical bundle. In the predicted dimer there is a short C-terminal beta strand that forms an anti parallel cap at one end of the helical bundle.", "domain_architectures": 1, "interpro_id": "IPR055788", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF7364)", "partial_evidence_count": null, "pfam_id": "PF24069", "proteins": 31, "proteomes": 31, "short_name": "DUF7364", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24069", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from parasitic secernentean nematodes. It is predicted to adopt an OB-fold.", "domain_architectures": 10, "interpro_id": "IPR055929", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF7506)", "partial_evidence_count": null, "pfam_id": "PF24338", "proteins": 31, "proteomes": 25, "short_name": "DUF7506", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24338", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised integral membrane proteins found in halobacteria. These proteins contain two predicted transmembrane helices. Structure prediction suggests these proteins may form homodimers.", "domain_architectures": 1, "interpro_id": "IPR058387", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF8074)", "partial_evidence_count": null, "pfam_id": "PF26275", "proteins": 31, "proteomes": 30, "short_name": "DUF8074", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26275", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins in this family are predominantly found in halophilic archaea, particularly within the Halobacteria class. The proteins are generally short, with lengths ranging from 89 to 123 amino acids. The reviewed protein from Halogeometricum borinquense (UniProtKB:E4NSC8) is included in this family.", "domain_architectures": 1, "interpro_id": "IPR058423", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF8110)", "partial_evidence_count": null, "pfam_id": "PF26415", "proteins": 31, "proteomes": 29, "short_name": "DUF8110", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26415", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function at the N-terminal in uncharacterised fungal proteins. This domain contains a RNases-like fold. The core architecture typically features a central five-stranded beta-sheet flanked by several alpha-helices. Most RNases H also possess an active site with a conserved DEDD motif (aspartate and glutamate residues), essential for coordinating catalytically required metal ions, usually Mg [[cite:PUB00016297]].", "domain_architectures": 5, "interpro_id": "", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF8340) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF27032", "proteins": 31, "proteomes": 18, "short_name": "DUF8340_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27032", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function at the N-terminal in uncharacterised eukaryotic proteins mainly from Trypanosoma. This domain contains a RNase-like fold. The core architecture typically features a central five-stranded beta-sheet flanked by several alpha-helices. This domain can be found associated with [pfam:PF01612].", "domain_architectures": 2, "interpro_id": "IPR059386", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF8342)", "partial_evidence_count": null, "pfam_id": "PF27040", "proteins": 31, "proteomes": 28, "short_name": "DUF8342", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27040", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein Domain found in bacteriophages, including Punavirus species. The function of this family remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061676", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF8615)", "partial_evidence_count": null, "pfam_id": "PF30236", "proteins": 31, "proteomes": 25, "short_name": "DUF8615", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30236", "structures": 2, "taxa": 99, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins approximately 150 residues in length. Members are found in Cyanobacteriota and in cyanophages. Some members are annotated as putative serine hydroxymethyltransferases but this has not been experimentally verified. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061698", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF8637)", "partial_evidence_count": null, "pfam_id": "PF30570", "proteins": 31, "proteomes": 29, "short_name": "DUF8637", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30570", "structures": 0, "taxa": 93, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of uncharacterised prokaryotic proteins.", "domain_architectures": 1, "interpro_id": "IPR007556", "known_evidence_count": null, "matches": 30, "name": "Protein of unknown function (DUF483)", "partial_evidence_count": null, "pfam_id": "PF04467", "proteins": 30, "proteomes": 30, "short_name": "DUF483", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04467", "structures": 0, "taxa": 100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains several uncharacterised beak and feather disease virus proteins.", "domain_architectures": 1, "interpro_id": "IPR007772", "known_evidence_count": null, "matches": 30, "name": "Protein of unknown function (DUF681)", "partial_evidence_count": null, "pfam_id": "PF05080", "proteins": 30, "proteomes": 1, "short_name": "DUF681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05080", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found on peptidase C25 proteins and has no known function.", "domain_architectures": 14, "interpro_id": "IPR018832", "known_evidence_count": null, "matches": 36, "name": "Domain of unknown function (DUF2436)", "partial_evidence_count": null, "pfam_id": "PF10365", "proteins": 30, "proteomes": 11, "short_name": "DUF2436", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10365", "structures": 1, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR024386", "known_evidence_count": null, "matches": 30, "name": "Protein of unknown function (DUF2532)", "partial_evidence_count": null, "pfam_id": "PF10811", "proteins": 30, "proteomes": 30, "short_name": "DUF2532", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10811", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 130 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025074", "known_evidence_count": null, "matches": 30, "name": "Protein of unknown function (DUF3942)", "partial_evidence_count": null, "pfam_id": "PF13078", "proteins": 30, "proteomes": 27, "short_name": "DUF3942", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13078", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 73 and 85 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025095", "known_evidence_count": null, "matches": 30, "name": "Protein of unknown function (DUF4022)", "partial_evidence_count": null, "pfam_id": "PF13214", "proteins": 30, "proteomes": 30, "short_name": "DUF4022", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13214", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 220 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025126", "known_evidence_count": null, "matches": 30, "name": "Protein of unknown function (DUF4052)", "partial_evidence_count": null, "pfam_id": "PF13261", "proteins": 30, "proteomes": 30, "short_name": "DUF4052", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13261", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR027894", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF4620)", "partial_evidence_count": null, "pfam_id": "PF15399", "proteins": 30, "proteomes": 21, "short_name": "DUF4620", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15399", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of C-terminal of several uncharacterized proteins around 500 residues in length and is mainly found in various Faecalibacterium and Clostridium species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032489", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF5048)", "partial_evidence_count": null, "pfam_id": "PF16467", "proteins": 30, "proteomes": 29, "short_name": "DUF5048", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16467", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidial sequences of unknown function.", "domain_architectures": 3, "interpro_id": "IPR031540", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF5088)", "partial_evidence_count": null, "pfam_id": "PF17008", "proteins": 30, "proteomes": 28, "short_name": "DUF5088", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17008", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of largely microsporidial-specific proteins is of unknown function. However there may be distant homology to family Csm1, [pfam:PF12539].", "domain_architectures": 1, "interpro_id": "IPR031519", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF5094)", "partial_evidence_count": null, "pfam_id": "PF17015", "proteins": 30, "proteomes": 27, "short_name": "DUF5094", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17015", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function which is found in Mycoplasmataceae.Family members are predicted to contain 7 trans-membrane regions", "domain_architectures": 1, "interpro_id": "IPR035319", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF5378)", "partial_evidence_count": null, "pfam_id": "PF17349", "proteins": 30, "proteomes": 27, "short_name": "DUF5378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17349", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Methanobacteria and Methanococci. Members of this family are predicted to contain 4 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035350", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF5400)", "partial_evidence_count": null, "pfam_id": "PF17379", "proteins": 30, "proteomes": 30, "short_name": "DUF5400", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17379", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chlamydiales.", "domain_architectures": 2, "interpro_id": "IPR035365", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5407)", "partial_evidence_count": null, "pfam_id": "PF17401", "proteins": 30, "proteomes": 26, "short_name": "DUF5407", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17401", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata.", "domain_architectures": 1, "interpro_id": "IPR040735", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF5583)", "partial_evidence_count": null, "pfam_id": "PF17821", "proteins": 30, "proteomes": 30, "short_name": "DUF5583", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17821", "structures": 0, "taxa": 136, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Iridoviridae.", "domain_architectures": 1, "interpro_id": "IPR043658", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF5875)", "partial_evidence_count": null, "pfam_id": "PF19203", "proteins": 30, "proteomes": 29, "short_name": "DUF5875", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19203", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown functions predominantly found in Iridoviridae.", "domain_architectures": 1, "interpro_id": "IPR043656", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF5877)", "partial_evidence_count": null, "pfam_id": "PF19205", "proteins": 30, "proteomes": 29, "short_name": "DUF5877", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19205", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimivirus.", "domain_architectures": 1, "interpro_id": "IPR045365", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF5884)", "partial_evidence_count": null, "pfam_id": "PF19231", "proteins": 30, "proteomes": 10, "short_name": "DUF5884", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19231", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phycodnaviridae. This family also includes proteins found in plants.", "domain_architectures": 3, "interpro_id": "IPR045420", "known_evidence_count": null, "matches": 33, "name": "Family of unknown function (DUF5901)", "partial_evidence_count": null, "pfam_id": "PF19254", "proteins": 30, "proteomes": 16, "short_name": "DUF5901", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19254", "structures": 1, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001778) is described by MIBiG as an example of the following biosynthetic class, other (unspecified). It includes a member from the showdomycin biosynthetic gene cluster from Streptomyces showdoensis [[cite:PUB00099458]].", "domain_architectures": 1, "interpro_id": "IPR046220", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF6253)", "partial_evidence_count": null, "pfam_id": "PF19766", "proteins": 30, "proteomes": 30, "short_name": "DUF6253", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19766", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001281) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the ustilagic acid biosynthetic gene cluster from Ustilago maydis 521 [[cite:PUB00097885]]. This family appears to be predominantly found in fungi.", "domain_architectures": 1, "interpro_id": "IPR046310", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF6425)", "partial_evidence_count": null, "pfam_id": "PF19989", "proteins": 30, "proteomes": 29, "short_name": "DUF6425", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19989", "structures": 0, "taxa": 71, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in some PRiA4b ORF-3-like proteins from bacteria, such as SwissProt:A0A1I7K0M5. This domain may adopt an all-helical fold and is generally found alongside the PriA4_ORF3 ([pfam:PF07929]) domain.", "domain_architectures": 2, "interpro_id": "IPR055827", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF7403)", "partial_evidence_count": null, "pfam_id": "PF24136", "proteins": 30, "proteomes": 30, "short_name": "DUF7403", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24136", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. The structure of this family is predicted to be composed of a four stranded beta sheet and a single alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055851", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF7428)", "partial_evidence_count": null, "pfam_id": "PF24204", "proteins": 30, "proteomes": 30, "short_name": "DUF7428", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24204", "structures": 0, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from flagellate Discoba. It is predicted to adopt a globular structure consisting of array of helices.", "domain_architectures": 3, "interpro_id": "IPR056662", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF7760)", "partial_evidence_count": null, "pfam_id": "PF24949", "proteins": 30, "proteomes": 26, "short_name": "DUF7760", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24949", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised bacterial alpha solenoid proteins.", "domain_architectures": 1, "interpro_id": "IPR057148", "known_evidence_count": null, "matches": 30, "name": "Repeat of unknown function (DUF7826)", "partial_evidence_count": null, "pfam_id": "PF25159", "proteins": 30, "proteomes": 30, "short_name": "DUF7826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25159", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised lipoproteins from chlamydial species.", "domain_architectures": 1, "interpro_id": "IPR058398", "known_evidence_count": null, "matches": 30, "name": "Family of unknown function (DUF8085)", "partial_evidence_count": null, "pfam_id": "PF26330", "proteins": 30, "proteomes": 29, "short_name": "DUF8085", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26330", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Agaricomycetes. It is probably distantly related to chaperone protein CcmS, [pfam:PF26617] and [pfam:PF26632] and it is predicted to adopt topologically similar structure. It is found frequently in combination with zf-MYND [pfam:PF01753].", "domain_architectures": 2, "interpro_id": "IPR058527", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF8214)", "partial_evidence_count": null, "pfam_id": "PF26646", "proteins": 30, "proteomes": 28, "short_name": "DUF8214", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26646", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is predicted to fold into unique alpha/beta structure. It has two highly conserved histidines and a serine that may have functional importance.", "domain_architectures": 4, "interpro_id": "IPR059293", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF8249)", "partial_evidence_count": null, "pfam_id": "PF26754", "proteins": 30, "proteomes": 7, "short_name": "DUF8249", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26754", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into a two layer alpha/beta structure composed of an antiparallel beta-sheet and three alpha-helices packed on one side. It contains several highly conserved cysteine residues predicted to form disulfide bonds.", "domain_architectures": 1, "interpro_id": "IPR059409", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF8365)", "partial_evidence_count": null, "pfam_id": "PF28038", "proteins": 30, "proteomes": 26, "short_name": "DUF8365", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28038", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 30, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found at the C-terminal of a group of uncharacterised eukaryotic sequences related to mRNA export factor MEX67. This domain may adopt a helical structure consisting of seven short helices. This domain is found associated with [pfam:PF23056].", "domain_architectures": 2, "interpro_id": "IPR061623", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF8554)", "partial_evidence_count": null, "pfam_id": "PF29442", "proteins": 30, "proteomes": 29, "short_name": "DUF8554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29442", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins approximately 72 residues in length found in cyanophages (Kyanoviridae). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061702", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF8641)", "partial_evidence_count": null, "pfam_id": "PF30574", "proteins": 30, "proteomes": 26, "short_name": "DUF8641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30574", "structures": 0, "taxa": 87, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the fifth domain found in a family of uncharacterised hypothetical prokaryotic proteins. This domain has a beta sandwich fold.", "domain_architectures": 4, "interpro_id": "IPR063027", "known_evidence_count": null, "matches": 30, "name": "DUF499 fifth domain", "partial_evidence_count": null, "pfam_id": "PF30800", "proteins": 30, "proteomes": 30, "short_name": "DUF499_5th", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30800", "structures": 0, "taxa": 95, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised tobravirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR007968", "known_evidence_count": null, "matches": 29, "name": "Protein of unknown function (DUF728)", "partial_evidence_count": null, "pfam_id": "PF05304", "proteins": 29, "proteomes": 3, "short_name": "DUF728", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05304", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised hypothetical proteins from Rhizobium loti.", "domain_architectures": 1, "interpro_id": "IPR008486", "known_evidence_count": null, "matches": 29, "name": "Protein of unknown function (DUF768)", "partial_evidence_count": null, "pfam_id": "PF05589", "proteins": 29, "proteomes": 28, "short_name": "DUF768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05589", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 115 residues in length which seem to be specific to Escherichia coli. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009759", "known_evidence_count": null, "matches": 29, "name": "Protein of unknown function (DUF1327)", "partial_evidence_count": null, "pfam_id": "PF07041", "proteins": 29, "proteomes": 19, "short_name": "DUF1327", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07041", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain approximately 150 residues long that is sometimes repeated within some Babesia bovis proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR009850", "known_evidence_count": null, "matches": 38, "name": "Protein of unknown function (DUF1411)", "partial_evidence_count": null, "pfam_id": "PF07199", "proteins": 29, "proteomes": 4, "short_name": "DUF1411", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07199", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This viral family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR022594", "known_evidence_count": null, "matches": 29, "name": "Protein of unknown function (DUF2704)", "partial_evidence_count": null, "pfam_id": "PF10866", "proteins": 29, "proteomes": 29, "short_name": "DUF2704", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10866", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021618", "known_evidence_count": null, "matches": 29, "name": "Protein of unknown function (DUF3232)", "partial_evidence_count": null, "pfam_id": "PF11554", "proteins": 29, "proteomes": 27, "short_name": "DUF3232", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11554", "structures": 1, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025225", "known_evidence_count": null, "matches": 29, "name": "Protein of unknown function (DUF3956)", "partial_evidence_count": null, "pfam_id": "PF13104", "proteins": 29, "proteomes": 20, "short_name": "DUF3956", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13104", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025015", "known_evidence_count": null, "matches": 29, "name": "Protein of unknown function (DUF3975)", "partial_evidence_count": null, "pfam_id": "PF13126", "proteins": 29, "proteomes": 29, "short_name": "DUF3975", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13126", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family are putative mature parasite-infected erythrocyte surface antigen protein from Bacillus spp.", "domain_architectures": 1, "interpro_id": "IPR025276", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF4075)", "partial_evidence_count": null, "pfam_id": "PF13294", "proteins": 29, "proteomes": 29, "short_name": "DUF4075", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13294", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Small protein family, with members present in few proteobacteria mostly Desulfovibrio species, but also a Vibrio phage vB, suggesting a possible phage origin Experimentally determined structure shows a fold reminiscent of a thioesterase/thiol ester dehydrase-isomerase fold, but a functional consequences of this similarity are not clear", "domain_architectures": 2, "interpro_id": "IPR032383", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF4875)", "partial_evidence_count": null, "pfam_id": "PF16175", "proteins": 29, "proteomes": 28, "short_name": "DUF4875", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16175", "structures": 1, "taxa": 112, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is around 150 residues long and is located in the C-terminal of some uncharacterized proteins in various Bacteroides and Prevotella species. The function of this domain remains unknown.", "domain_architectures": 3, "interpro_id": "IPR032283", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF4984)", "partial_evidence_count": null, "pfam_id": "PF16372", "proteins": 29, "proteomes": 25, "short_name": "DUF4984", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16372", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 260 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 4, "interpro_id": "IPR032221", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF5040)", "partial_evidence_count": null, "pfam_id": "PF16443", "proteins": 29, "proteomes": 28, "short_name": "DUF5040", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16443", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidial-specific sequences of unknown function.", "domain_architectures": 3, "interpro_id": "IPR031527", "known_evidence_count": null, "matches": 31, "name": "Domain of unknown function (DUF5091)", "partial_evidence_count": null, "pfam_id": "PF17012", "proteins": 29, "proteomes": 28, "short_name": "DUF5091", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17012", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidia-specific sequences of unknown function.", "domain_architectures": 1, "interpro_id": "IPR031503", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF5099)", "partial_evidence_count": null, "pfam_id": "PF17025", "proteins": 29, "proteomes": 27, "short_name": "DUF5099", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17025", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chlamydiales.", "domain_architectures": 1, "interpro_id": "IPR035407", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF5399)", "partial_evidence_count": null, "pfam_id": "PF17377", "proteins": 29, "proteomes": 29, "short_name": "DUF5399", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17377", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR020123", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF5475)", "partial_evidence_count": null, "pfam_id": "PF17569", "proteins": 29, "proteomes": 28, "short_name": "DUF5475", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17569", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Fowl aviadenovirus.", "domain_architectures": 1, "interpro_id": "IPR020226", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF5506)", "partial_evidence_count": null, "pfam_id": "PF17611", "proteins": 29, "proteomes": 15, "short_name": "DUF5506", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17611", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Rickettsia. Family members are predicted to have 2 or 3 trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035116", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF5510)", "partial_evidence_count": null, "pfam_id": "PF17629", "proteins": 29, "proteomes": 29, "short_name": "DUF5510", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17629", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040507", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF5540)", "partial_evidence_count": null, "pfam_id": "PF17694", "proteins": 29, "proteomes": 28, "short_name": "DUF5540", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17694", "structures": 0, "taxa": 112, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in various Platyhelminthes. This domain adopts a PH-like domain fold.", "domain_architectures": 1, "interpro_id": "IPR043798", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF5737)", "partial_evidence_count": null, "pfam_id": "PF19008", "proteins": 29, "proteomes": 11, "short_name": "DUF5737", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19008", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 1, "interpro_id": "IPR043845", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF5864)", "partial_evidence_count": null, "pfam_id": "PF19182", "proteins": 29, "proteomes": 11, "short_name": "DUF5864", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19182", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in archaea. Proteins in this family are typically between 119 and 142 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046057", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF6015)", "partial_evidence_count": null, "pfam_id": "PF19479", "proteins": 29, "proteomes": 14, "short_name": "DUF6015", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19479", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000967) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from the calyculin A biosynthetic gene cluster from uncultured Candidatus Entotheonella sp. and appears to be predominantly found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR045718", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF6072)", "partial_evidence_count": null, "pfam_id": "PF19549", "proteins": 29, "proteomes": 21, "short_name": "DUF6072", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19549", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 1, "interpro_id": "IPR046183", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF6211)", "partial_evidence_count": null, "pfam_id": "PF19716", "proteins": 29, "proteomes": 29, "short_name": "DUF6211", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19716", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001975) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the atratumycin biosynthetic gene cluster from Streptomyces atratus [[cite:PUB00099465]].", "domain_architectures": 1, "interpro_id": "IPR046236", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF6269)", "partial_evidence_count": null, "pfam_id": "PF19784", "proteins": 29, "proteomes": 27, "short_name": "DUF6269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19784", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry includes a set of mycoplasma lipoproteins related to uncharacterized Mycoplasma genitalium lipoprotein MG348.", "domain_architectures": 1, "interpro_id": "IPR049194", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF6856)", "partial_evidence_count": null, "pfam_id": "PF21637", "proteins": 29, "proteomes": 29, "short_name": "DUF6856", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21637", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. A structure prediction suggests this protein forms a compact alpha helical domain followed by a disordered region.", "domain_architectures": 1, "interpro_id": "IPR055715", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF7291)", "partial_evidence_count": null, "pfam_id": "PF23963", "proteins": 29, "proteomes": 29, "short_name": "DUF7291", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23963", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of phage proteins. These proteins form a confident dimer according to structure prediction. The dimer adopts a novel fold composed of a long four stranded beta sheet with two alpha helical elements packed at each end of the twisted sheet. There is quite a bit of structural variability across the family with a variety of alternative elaborations.", "domain_architectures": 1, "interpro_id": "IPR055740", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF7316)", "partial_evidence_count": null, "pfam_id": "PF24000", "proteins": 29, "proteomes": 29, "short_name": "DUF7316", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24000", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins found in Haloferacales. They contain two pairs of conserved cysteines that are likely involved in metal coordination. These proteins are predicted to structurally resemble treble-clef zinc fingers.", "domain_architectures": 1, "interpro_id": "IPR055986", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF7564)", "partial_evidence_count": null, "pfam_id": "PF24445", "proteins": 29, "proteomes": 29, "short_name": "DUF7564", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24445", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a beta-sandwich with Ig-like topology.", "domain_architectures": 2, "interpro_id": "IPR057184", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF7862)", "partial_evidence_count": null, "pfam_id": "PF25262", "proteins": 29, "proteomes": 29, "short_name": "DUF7862", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25262", "structures": 0, "taxa": 115, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain of unknown function found in Trypanosoma proteins. According to structure predictions it could adopt a DNA clamp fold.", "domain_architectures": 1, "interpro_id": "IPR059038", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF7881) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF25363", "proteins": 29, "proteomes": 28, "short_name": "DUF7881_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25363", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain of unknown function found in Trypanosoma proteins. According to structure predictions it could adopt a DNA clamp fold.", "domain_architectures": 1, "interpro_id": "IPR059037", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF7881) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF25365", "proteins": 29, "proteomes": 28, "short_name": "DUF7881_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25365", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Trypanosomes. It is predicted to fold into a seven-bladed beta-propeller.", "domain_architectures": 2, "interpro_id": "IPR057236", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF7914)", "partial_evidence_count": null, "pfam_id": "PF25501", "proteins": 29, "proteomes": 27, "short_name": "DUF7914", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25501", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins found predominantly in the Halobacteria class of Archaea. The proteins containing this domain are typically between 217 and 254 amino acids in length. This entry contains two structural domains with one nested within the other.", "domain_architectures": 1, "interpro_id": "IPR058482", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF8169)", "partial_evidence_count": null, "pfam_id": "PF26507", "proteins": 29, "proteomes": 28, "short_name": "DUF8169", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26507", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Trypanosomatidae species. It is predicted to fold into a beta-barrel structure that is reminiscent to the beta-barrel observed in VirK family proteins [pfam:PF06903]. These two barrels, however, relate not only by circular permutation but also by strand flip with a change of directionality.", "domain_architectures": 1, "interpro_id": "IPR059315", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF8271)", "partial_evidence_count": null, "pfam_id": "PF26836", "proteins": 29, "proteomes": 27, "short_name": "DUF8271", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26836", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 29, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised eukaryotic proteins. It is predicted to five stranded antiparallel beta-sheet packed on one side with alpha helices.", "domain_architectures": 7, "interpro_id": "IPR059348", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF8304)", "partial_evidence_count": null, "pfam_id": "PF26966", "proteins": 29, "proteomes": 11, "short_name": "DUF8304", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26966", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Chlamydomonadales lineage. It is predicted to fold into an alpha/beta structure composed of a curved beta-sheet and array of alpha-helices packed on the concave side.", "domain_architectures": 2, "interpro_id": "IPR059461", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF8417)", "partial_evidence_count": null, "pfam_id": "PF28506", "proteins": 29, "proteomes": 10, "short_name": "DUF8417", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28506", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small protein family found in both bacteria and viruses. Bacterial members are present in Bacillus and related genera (Bacillaceae), whilst viral members are found in bacteriophages (Takahashivirus). One bacterial member is annotated as a putative secreted or membrane protein. AlphaFold structural predictions are available for some members. The function of this protein family remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061635", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF8570)", "partial_evidence_count": null, "pfam_id": "PF29593", "proteins": 29, "proteomes": 29, "short_name": "DUF8570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29593", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Staphylococcus aureus plasmid proteins with no characterised function.", "domain_architectures": 1, "interpro_id": "IPR005602", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF334)", "partial_evidence_count": null, "pfam_id": "PF03904", "proteins": 28, "proteomes": 18, "short_name": "DUF334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03904", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family containing bacterial proteins of unknown function. Many of the proteins in this family are hypothetical.", "domain_architectures": 2, "interpro_id": "IPR012456", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function (DUF1661)", "partial_evidence_count": null, "pfam_id": "PF07877", "proteins": 28, "proteomes": 3, "short_name": "DUF1661", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07877", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are found in hypothetical proteins synthesised by the Archaeal organism Sulfolobus. Their exact function has not, as yet, been determined.", "domain_architectures": 2, "interpro_id": "IPR015288", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF1955)", "partial_evidence_count": null, "pfam_id": "PF09205", "proteins": 28, "proteomes": 28, "short_name": "DUF1955", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09205", "structures": 1, "taxa": 79, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The function of this viral family of proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR022556", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function (DUF2576)", "partial_evidence_count": null, "pfam_id": "PF10845", "proteins": 28, "proteomes": 25, "short_name": "DUF2576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10845", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins with unknown function are annotated as immediate early protein ICP-18 however this cannot be confirmed.", "domain_architectures": 1, "interpro_id": "IPR022600", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function (DUF2888)", "partial_evidence_count": null, "pfam_id": "PF11135", "proteins": 28, "proteomes": 26, "short_name": "DUF2888", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11135", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as YfmB however currently no function for this protein is known.", "domain_architectures": 1, "interpro_id": "IPR021579", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function (DUF3212)", "partial_evidence_count": null, "pfam_id": "PF11486", "proteins": 28, "proteomes": 28, "short_name": "DUF3212", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11486", "structures": 1, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 90 amino acids in length. There are two conserved sequence motifs: FVF and LGV.", "domain_architectures": 1, "interpro_id": "IPR025176", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function (DUF3935)", "partial_evidence_count": null, "pfam_id": "PF13071", "proteins": 28, "proteomes": 28, "short_name": "DUF3935", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13071", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria and eukaryotes. Proteins in this family are typically between 46 and 63 amino acids in length. There is a single completely conserved residue P that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR025076", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function (DUF3926)", "partial_evidence_count": null, "pfam_id": "PF13080", "proteins": 28, "proteomes": 28, "short_name": "DUF3926", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13080", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 150 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025010", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function (DUF3978)", "partial_evidence_count": null, "pfam_id": "PF13123", "proteins": 28, "proteomes": 27, "short_name": "DUF3978", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13123", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "this domain is found in tandem repeats on the N-terminus of secreted LRR proteins from human associated Bacteroidetes domain boundaries are based on the JCSG solved 3D structure of JCSG target SP16667A (BT_0210)", "domain_architectures": 4, "interpro_id": "IPR027899", "known_evidence_count": null, "matches": 54, "name": "Domain of unknown function (DUF4458)", "partial_evidence_count": null, "pfam_id": "PF14660", "proteins": 28, "proteomes": 24, "short_name": "DUF4458", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14660", "structures": 1, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of C-terminal of uncharacterized proteins and F5/8 type C domain proteins around 360 residues in length and is mainly found in various Firmicutes species. The function of this family is unknown.", "domain_architectures": 10, "interpro_id": "IPR032480", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF5057)", "partial_evidence_count": null, "pfam_id": "PF16480", "proteins": 28, "proteomes": 28, "short_name": "DUF5057", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16480", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a microsporidial-specific family of proteins of unknown function. The family is likely to be of four transmembrane domains.", "domain_architectures": 2, "interpro_id": "IPR031539", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF5090)", "partial_evidence_count": null, "pfam_id": "PF17009", "proteins": 28, "proteomes": 28, "short_name": "DUF5090", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17009", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Caenorhabditis.", "domain_architectures": 2, "interpro_id": "IPR035334", "known_evidence_count": null, "matches": 30, "name": "Domain of unknown function (DUF5390)", "partial_evidence_count": null, "pfam_id": "PF17365", "proteins": 28, "proteomes": 10, "short_name": "DUF5390", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17365", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Archaea and Bacteria.", "domain_architectures": 1, "interpro_id": "IPR035157", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5395)", "partial_evidence_count": null, "pfam_id": "PF17373", "proteins": 28, "proteomes": 26, "short_name": "DUF5395", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17373", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR035273", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5431)", "partial_evidence_count": null, "pfam_id": "PF17496", "proteins": 28, "proteomes": 14, "short_name": "DUF5431", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17496", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 2, "interpro_id": "IPR041009", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF5550)", "partial_evidence_count": null, "pfam_id": "PF17704", "proteins": 28, "proteomes": 25, "short_name": "DUF5550", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17704", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in chordata. Family members contain a transmembrane region in the C-terminal and have been shown to be localized to the Golgi apparatus [[cite:PUB00091556]].", "domain_architectures": 2, "interpro_id": "IPR041391", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5570)", "partial_evidence_count": null, "pfam_id": "PF17731", "proteins": 28, "proteomes": 19, "short_name": "DUF5570", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17731", "structures": 0, "taxa": 79, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in Platyhelminthes.", "domain_architectures": 1, "interpro_id": "IPR043791", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5733)", "partial_evidence_count": null, "pfam_id": "PF19004", "proteins": 28, "proteomes": 11, "short_name": "DUF5733", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19004", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The function of this archaeal family is unknown.", "domain_architectures": 1, "interpro_id": "IPR043963", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5751)", "partial_evidence_count": null, "pfam_id": "PF19025", "proteins": 28, "proteomes": 28, "short_name": "DUF5751", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19025", "structures": 1, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins found in viruses, which presumably contain a Host Targeting (HT) motif. This motif is involved in targeting host proteins as part of the infection process in several organisms.", "domain_architectures": 1, "interpro_id": "IPR045408", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5890)", "partial_evidence_count": null, "pfam_id": "PF19240", "proteins": 28, "proteomes": 6, "short_name": "DUF5890", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19240", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001397) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. This family includes a protein from the lidamycin biosynthetic gene cluster from Streptomyces globisporus C-1027 and appears to be predominantly present in bacteria [[cite:PUB00099385]].", "domain_architectures": 1, "interpro_id": "IPR046115", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF6052)", "partial_evidence_count": null, "pfam_id": "PF19522", "proteins": 28, "proteomes": 28, "short_name": "DUF6052", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19522", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001065) is described by MIBiG as an example of the following biosynthetic class, polyketide. This family contains a protein from the herboxidiene biosynthetic gene cluster from Streptomyces chromofuscus [[cite:PUB00098901]].", "domain_architectures": 1, "interpro_id": "IPR045715", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF6071)", "partial_evidence_count": null, "pfam_id": "PF19547", "proteins": 28, "proteomes": 27, "short_name": "DUF6071", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19547", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001735) is described by MIBiG as an example of the following biosynthetic class, other (unspecified), in particular the pentostatine biosynthetic gene cluster from Streptomyces antibioticus [[cite:PUB00098953]].", "domain_architectures": 1, "interpro_id": "IPR045934", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF6354)", "partial_evidence_count": null, "pfam_id": "PF19881", "proteins": 28, "proteomes": 25, "short_name": "DUF6354", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19881", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Caenorhabditis. It has an NTF2-like fold.", "domain_architectures": 5, "interpro_id": "IPR048313", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5382) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20840", "proteins": 28, "proteomes": 9, "short_name": "DUF5382_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20840", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein found in various mycobacteriophages. The protein contains a predicted transmembrane helix and is typically around 60 amino acids in length. Its function is unknown.", "domain_architectures": 1, "interpro_id": "IPR055606", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF7182)", "partial_evidence_count": null, "pfam_id": "PF23810", "proteins": 28, "proteomes": 28, "short_name": "DUF7182", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23810", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small helical domain is found a small family of phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055653", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF7229)", "partial_evidence_count": null, "pfam_id": "PF23875", "proteins": 28, "proteomes": 28, "short_name": "DUF7229", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23875", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised lipoproteins from spirochaete bacteria.", "domain_architectures": 2, "interpro_id": "IPR058399", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF8086)", "partial_evidence_count": null, "pfam_id": "PF26331", "proteins": 28, "proteomes": 28, "short_name": "DUF8086", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26331", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins form Sulfolobales. It is predicted to fold into an elaborated with additional elements beta-barrel that may be remotely related to OB-fold domains.", "domain_architectures": 1, "interpro_id": "IPR059322", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF8278)", "partial_evidence_count": null, "pfam_id": "PF26923", "proteins": 28, "proteomes": 28, "short_name": "DUF8278", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26923", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Alveolata lineage. It is predicted to fold into an alpha-solenoid with a structural similarity to TAL effector repeats known to bind to double stranded DNA.", "domain_architectures": 7, "interpro_id": "IPR059327", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF8283)", "partial_evidence_count": null, "pfam_id": "PF26932", "proteins": 28, "proteomes": 8, "short_name": "DUF8283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26932", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from betaproteobacteria. It contains a pair of highly conserved cysteine residues which are predicted to form a disulfide bond.", "domain_architectures": 2, "interpro_id": "IPR059376", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF8332)", "partial_evidence_count": null, "pfam_id": "PF27012", "proteins": 28, "proteomes": 23, "short_name": "DUF8332", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27012", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of bacterial domains that have a beta sandwich fold. The domain occurs in proteins that are likely to be presented on the bacterial cell surface.", "domain_architectures": 10, "interpro_id": "IPR059389", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF8345)", "partial_evidence_count": null, "pfam_id": "PF27071", "proteins": 28, "proteomes": 22, "short_name": "DUF8345", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27071", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 105 residues found in uncharacterised proteins from Cyanobacteriota, predominantly in Prochlorococcus and Synechococcus species. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061707", "known_evidence_count": null, "matches": 28, "name": "Domain of unknown function (DUF8646)", "partial_evidence_count": null, "pfam_id": "PF30580", "proteins": 28, "proteomes": 26, "short_name": "DUF8646", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30580", "structures": 0, "taxa": 92, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 28, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins predominantly found in echinoderms. Members are predicted to show an alpha configuration. They have several highly conserved motifs EE and highly conserved residues K, Q, W and H.", "domain_architectures": 2, "interpro_id": "IPR061910", "known_evidence_count": null, "matches": 29, "name": "Family of unknown function (DUF8849)", "partial_evidence_count": null, "pfam_id": "PF31276", "proteins": 28, "proteomes": 1, "short_name": "DUF8849", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31276", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a number of Caenorhabditis elegans specific repeats of around 36 residues in length which are found in two hypothetical proteins. This family is found in conjunction with [pfam:PF00024].", "domain_architectures": 13, "interpro_id": "IPR009557", "known_evidence_count": null, "matches": 1427, "name": "Repeat of unknown function (DUF1174)", "partial_evidence_count": null, "pfam_id": "PF06671", "proteins": 27, "proteomes": 10, "short_name": "DUF1174", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06671", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "All the members of this very small, very short family are derived from bacteriophages, of the SA bacteriophages 11, Mu50B, system, and from the Staphylococcal_phi-Mu50B-like_prophages subsystem. All members are hypothetical proteins.", "domain_architectures": 1, "interpro_id": "IPR018917", "known_evidence_count": null, "matches": 27, "name": "Hypothetical protein of unknown function (DUF2482)", "partial_evidence_count": null, "pfam_id": "PF10655", "proteins": 27, "proteomes": 26, "short_name": "DUF2482", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10655", "structures": 0, "taxa": 73, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appear to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021483", "known_evidence_count": null, "matches": 27, "name": "Protein of unknown function (DUF3136)", "partial_evidence_count": null, "pfam_id": "PF11334", "proteins": 27, "proteomes": 14, "short_name": "DUF3136", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11334", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "TPR-like protein. The 2hr2 structure belongs to the SCOP all alpha class, TPR-like superfamily, CT2138-like family. A DALI search gives hits with the putative peptidyl-prolyl isomerase 2fbn (Z=16), the SGTA protein (Z=16), the PLCR protein 2qfc (Z=16), a putative FK506-binding protein (PDB:1qz2-A; DALI Z-score 15.3; RMSD 2.9; 16% sequence identity within 132 superimposed residues), and with the tetratricopeptide repeats of the protein phosphatase 5 (PDB:2bug; DALI Z-score 15.1; RMSD 2.5; 19% sequence identity within 117 superimposed residues).", "domain_architectures": 7, "interpro_id": "IPR024552", "known_evidence_count": null, "matches": 27, "name": "Domain of Unknown Function (DUF3856)", "partial_evidence_count": null, "pfam_id": "PF12968", "proteins": 27, "proteomes": 25, "short_name": "DUF3856", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12968", "structures": 1, "taxa": 118, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 170 amino acids in length. There is a conserved LGI sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025001", "known_evidence_count": null, "matches": 27, "name": "Protein of unknown function (DUF3902)", "partial_evidence_count": null, "pfam_id": "PF13042", "proteins": 27, "proteomes": 22, "short_name": "DUF3902", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13042", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 87 and 98 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025035", "known_evidence_count": null, "matches": 27, "name": "Protein of unknown function (DUF3992)", "partial_evidence_count": null, "pfam_id": "PF13059", "proteins": 27, "proteomes": 27, "short_name": "DUF3922", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13059", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025043", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF3981)", "partial_evidence_count": null, "pfam_id": "PF13139", "proteins": 27, "proteomes": 27, "short_name": "DUF3981", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13139", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of several uncharacterized proteins around 200 residues in length and is mainly found in various Desulfovibrio species. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR032621", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF4881)", "partial_evidence_count": null, "pfam_id": "PF16222", "proteins": 27, "proteomes": 27, "short_name": "DUF4881", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16222", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 240 residues in length and is mainly found in various Bacteroides and Parabacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032217", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF5036)", "partial_evidence_count": null, "pfam_id": "PF16439", "proteins": 27, "proteomes": 27, "short_name": "DUF5036", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16439", "structures": 0, "taxa": 56, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidial sequences that may be distantly related to RRP7, [pfam:PF12923], ribosomal-RNA-processing protein 7.", "domain_architectures": 1, "interpro_id": "IPR031533", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF5093)", "partial_evidence_count": null, "pfam_id": "PF17011", "proteins": 27, "proteomes": 23, "short_name": "DUF5093", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17011", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidial-specific sequences. The function is not known and there is no distant homology to any Pfam families so far.", "domain_architectures": 1, "interpro_id": "IPR031515", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF5095)", "partial_evidence_count": null, "pfam_id": "PF17016", "proteins": 27, "proteomes": 27, "short_name": "DUF5095", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17016", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidia-specific sequences of unknown function.", "domain_architectures": 1, "interpro_id": "IPR031495", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF5100)", "partial_evidence_count": null, "pfam_id": "PF17029", "proteins": 27, "proteomes": 27, "short_name": "DUF5100", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17029", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of short microsporidia-specific proteins of unknown function.", "domain_architectures": 2, "interpro_id": "IPR031492", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF5101)", "partial_evidence_count": null, "pfam_id": "PF17031", "proteins": 27, "proteomes": 26, "short_name": "DUF5101", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17031", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 3, "interpro_id": "IPR041032", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5546)", "partial_evidence_count": null, "pfam_id": "PF17700", "proteins": 27, "proteomes": 22, "short_name": "DUF5546", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17700", "structures": 0, "taxa": 111, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043887", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF5845)", "partial_evidence_count": null, "pfam_id": "PF19163", "proteins": 27, "proteomes": 21, "short_name": "DUF5845", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19163", "structures": 0, "taxa": 74, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 2, "interpro_id": "IPR045675", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF6195)", "partial_evidence_count": null, "pfam_id": "PF19695", "proteins": 27, "proteomes": 27, "short_name": "DUF6195", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19695", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 6 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Caenorhabditis. It has an NTF2-like fold.", "domain_architectures": 5, "interpro_id": "IPR048314", "known_evidence_count": null, "matches": 28, "name": "Family of unknown function (DUF5382) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20839", "proteins": 27, "proteomes": 9, "short_name": "DUF5382_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20839", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes [swissprot:Q6N4D8] from Rhodopseudomonas palustris, an uncharacterized protein that shows an alpha-beta structure and has some similarity with the structure predicted for members of [pfam:PF12976].", "domain_architectures": 1, "interpro_id": "IPR049277", "known_evidence_count": null, "matches": 27, "name": "DUF3860-like", "partial_evidence_count": null, "pfam_id": "PF21441", "proteins": 27, "proteomes": 23, "short_name": "DUF3860-like", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21441", "structures": 1, "taxa": 38, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from digenean species.", "domain_architectures": 9, "interpro_id": "IPR055490", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF7062)", "partial_evidence_count": null, "pfam_id": "PF23201", "proteins": 27, "proteomes": 24, "short_name": "DUF7062", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23201", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of uncharacterised short sequences from actinobacteria [[cite:PUB00155614]].", "domain_architectures": 1, "interpro_id": "IPR055580", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF7156)", "partial_evidence_count": null, "pfam_id": "PF23711", "proteins": 27, "proteomes": 26, "short_name": "DUF7156", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23711", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein domain found in viral proteins, primarily from Mycobacterium and Gordonia phages. The domain is approximately 120 amino acids in length. These proteins are composed of a small N-terminal zinc binding domain connected by an alpha helix to a small beta barrel domain at the C-terminus.", "domain_architectures": 1, "interpro_id": "IPR055669", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF7245)", "partial_evidence_count": null, "pfam_id": "PF23897", "proteins": 27, "proteomes": 27, "short_name": "DUF7245", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23897", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised mycobacterium phage proteins. These proteins adopt a compact three helical bundle domain.", "domain_architectures": 1, "interpro_id": "IPR055697", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF7273)", "partial_evidence_count": null, "pfam_id": "PF23938", "proteins": 27, "proteomes": 24, "short_name": "DUF7273", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23938", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. The family includes [swissprot:M9MUF4] which is annotated as a baseplate I protein. Proteins in this family are about 450 residues in length.", "domain_architectures": 1, "interpro_id": "IPR055721", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF7297)", "partial_evidence_count": null, "pfam_id": "PF23970", "proteins": 27, "proteomes": 27, "short_name": "DUF7297", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23970", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Streptococcus. It is predicted to adopt globular structure consisting of four alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR056665", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF7763)", "partial_evidence_count": null, "pfam_id": "PF24954", "proteins": 27, "proteomes": 27, "short_name": "DUF7763", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24954", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function (DUF) identified in Trypanosoma. Based on structural predictions, this domain is hypothesised to adopt a winged helix-turn-helix (HTH) fold. Winged helix DNA-binding proteins share a characteristic winged helix-turn-helix DNA-binding motif, in which the \"wings\", or loops, are small beta-sheets [[cite:PUB00013195]].", "domain_architectures": 1, "interpro_id": "IPR057205", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF7883)", "partial_evidence_count": null, "pfam_id": "PF25367", "proteins": 27, "proteomes": 27, "short_name": "DUF7883", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25367", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in the Halobacteria class of Archaea. Proteins in this family are predominantly found in the order Halobacteriales, including genera such as Halobacterium, Haladaptatus, and Halonotius. The proteins in this family typically range from 145 to 227 amino acids in length. These proteins are predicted to be integral membrane proteins, as they contain multiple transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058413", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF8100)", "partial_evidence_count": null, "pfam_id": "PF26402", "proteins": 27, "proteomes": 24, "short_name": "DUF8100", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26402", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain from a family of uncharacterised proteins found predominantly in Proteobacteria that contain two domains. The proteins are distributed among various orders including Burkholderiales, Rhodobacterales, and Hyphomicrobiales. The proteins in this family are typically around 240 to 250 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR059013", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF8168) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF26505", "proteins": 27, "proteomes": 27, "short_name": "DUF8168_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26505", "structures": 0, "taxa": 119, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to fold into a small open barrel structure decorated with helices.", "domain_architectures": 1, "interpro_id": "IPR059340", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF8296)", "partial_evidence_count": null, "pfam_id": "PF26948", "proteins": 27, "proteomes": 24, "short_name": "DUF8296", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26948", "structures": 0, "taxa": 100, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 27, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Kinetoplastea lineage. It is predicted to adopt a structure composed of array of alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR059428", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF8384)", "partial_evidence_count": null, "pfam_id": "PF28361", "proteins": 27, "proteomes": 26, "short_name": "DUF8384", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28361", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group of uncharacterised sequences from bacteria. It may adopt a Ig-like fold.", "domain_architectures": 3, "interpro_id": "IPR061547", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF8477)", "partial_evidence_count": null, "pfam_id": "PF28891", "proteins": 27, "proteomes": 24, "short_name": "DUF8477", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28891", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins from Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR061777", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF8716)", "partial_evidence_count": null, "pfam_id": "PF30739", "proteins": 27, "proteomes": 23, "short_name": "DUF8716", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30739", "structures": 2, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The function of this protein is unknown. It appears to only occur in Mycoplasma pneumoniae. The crystal structure revealed that this domain is composed of two separated homotrimeric coiled-coils [[cite:PUB00039581]].", "domain_architectures": 2, "interpro_id": "IPR002862", "known_evidence_count": null, "matches": 28, "name": "Protein of unknown function DUF16", "partial_evidence_count": null, "pfam_id": "PF01519", "proteins": 26, "proteomes": 1, "short_name": "DUF16", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01519", "structures": 1, "taxa": 10, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in viral proteins of unknown function.", "domain_architectures": 3, "interpro_id": "IPR008745", "known_evidence_count": null, "matches": 26, "name": "Viral domain of unknown function (DUF1717)", "partial_evidence_count": null, "pfam_id": "PF05414", "proteins": 26, "proteomes": 2, "short_name": "DUF1717", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05414", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This eukaryotic family of proteins has no known function.", "domain_architectures": 3, "interpro_id": "IPR021366", "known_evidence_count": null, "matches": 35, "name": "Protein of unknown function (DUF2981)", "partial_evidence_count": null, "pfam_id": "PF11200", "proteins": 26, "proteomes": 22, "short_name": "DUF2981", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11200", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family based on the N-terminal domain of 3KOG, which shows weak but consistent remote homology with adhesive families such as immunoglobulins and cadherins, suggesting it might form an attachment module.", "domain_architectures": 4, "interpro_id": "IPR024620", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF3869)", "partial_evidence_count": null, "pfam_id": "PF12985", "proteins": 26, "proteomes": 21, "short_name": "DUF3869", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12985", "structures": 2, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is often found at the C-terminal of proteins with [pfam:PF10899] domain, for instance in STY1911 protein from a multiple drug resistant Salmonella enterica serovar Typhi CT18.", "domain_architectures": 1, "interpro_id": "IPR025216", "known_evidence_count": null, "matches": 26, "name": "Protein of unknown function (DUF4427)", "partial_evidence_count": null, "pfam_id": "PF14468", "proteins": 26, "proteomes": 26, "short_name": "DUF4427", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14468", "structures": 0, "taxa": 101, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 140 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR031855", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF4751)", "partial_evidence_count": null, "pfam_id": "PF15942", "proteins": 26, "proteomes": 26, "short_name": "DUF4751", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15942", "structures": 0, "taxa": 75, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031881", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF4761)", "partial_evidence_count": null, "pfam_id": "PF15958", "proteins": 26, "proteomes": 24, "short_name": "DUF4761", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15958", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 170 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032216", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF5035)", "partial_evidence_count": null, "pfam_id": "PF16438", "proteins": 26, "proteomes": 26, "short_name": "DUF5035", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16438", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidia-specific proteins of unknown function. There is the possibility of very distant homology to the WAC domain.", "domain_architectures": 2, "interpro_id": "IPR031511", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF5097)", "partial_evidence_count": null, "pfam_id": "PF17020", "proteins": 26, "proteomes": 22, "short_name": "DUF5097", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17020", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is family of microsporidia-specific sequences with no known function. There is a very characteristic NPW sequence motif at the very C-terminus.", "domain_architectures": 2, "interpro_id": "IPR031505", "known_evidence_count": null, "matches": 29, "name": "Domain of unknown function (DUF5098)", "partial_evidence_count": null, "pfam_id": "PF17023", "proteins": 26, "proteomes": 24, "short_name": "DUF5098", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17023", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A highly conserved domain of unknown function found in Platyhelminthes, in which the first 21 residues correspond to a transmembrane domain.", "domain_architectures": 2, "interpro_id": "IPR043788", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF5730)", "partial_evidence_count": null, "pfam_id": "PF19001", "proteins": 26, "proteomes": 25, "short_name": "DUF5730", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19001", "structures": 0, "taxa": 79, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Iridoviridae.", "domain_architectures": 2, "interpro_id": "IPR045411", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF5892)", "partial_evidence_count": null, "pfam_id": "PF19243", "proteins": 26, "proteomes": 26, "short_name": "DUF5892", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19243", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000974) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide. It includes a member from the crocacin biosynthetic gene cluster from Chondromyces crocatus [[cite:PUB00099439]].", "domain_architectures": 1, "interpro_id": "IPR046225", "known_evidence_count": null, "matches": 26, "name": "Family of unknown function (DUF6258)", "partial_evidence_count": null, "pfam_id": "PF19772", "proteins": 26, "proteomes": 26, "short_name": "DUF6258", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19772", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000299) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the alterochromide A biosynthetic gene cluster from Pseudoalteromonas piscicida JCM 20779 [[cite:PUB00098870]].", "domain_architectures": 1, "interpro_id": "IPR046304", "known_evidence_count": null, "matches": 26, "name": "Family of unknown function (DUF6419)", "partial_evidence_count": null, "pfam_id": "PF19983", "proteins": 26, "proteomes": 25, "short_name": "DUF6419", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19983", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 25, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins from flatworms. It is predicted to adopt a PH-like fold with similarity to the PH-like domain found in Shulin and Spt16.", "domain_architectures": 7, "interpro_id": "IPR055512", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF7085)", "partial_evidence_count": null, "pfam_id": "PF23318", "proteins": 26, "proteomes": 23, "short_name": "DUF7085", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23318", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised phage proteins. AlphaFold multimer suggests this protein may form a dimeric ring arrangement.", "domain_architectures": 1, "interpro_id": "IPR055666", "known_evidence_count": null, "matches": 26, "name": "Family of unknown function (DUF7242)", "partial_evidence_count": null, "pfam_id": "PF23890", "proteins": 26, "proteomes": 26, "short_name": "DUF7242", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23890", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 26, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised metazoan proteins. It is predicted to adopt a structure typical for HTH winged helix domains. This domain is usually found associated with [pfam:PF24359] and [pfam:PF24360].", "domain_architectures": 3, "interpro_id": "IPR055939", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF7517)", "partial_evidence_count": null, "pfam_id": "PF24361", "proteins": 26, "proteomes": 19, "short_name": "DUF7517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24361", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. Structure prediction shows a compact domain composed of a three stranded beta sheet followed by two alpha helices packed on one side of the sheet.", "domain_architectures": 1, "interpro_id": "IPR057696", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF7936)", "partial_evidence_count": null, "pfam_id": "PF25590", "proteins": 26, "proteomes": 25, "short_name": "DUF7936", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25590", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta structure composed of antiparallel four-stranded beta-sheet packed with alpha-helices on one side. This domain is frequently found in combination with [pfam:PF13271].", "domain_architectures": 2, "interpro_id": "IPR059329", "known_evidence_count": null, "matches": 26, "name": "Domain of unknown function (DUF8285)", "partial_evidence_count": null, "pfam_id": "PF26934", "proteins": 26, "proteomes": 26, "short_name": "DUF8285", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26934", "structures": 0, "taxa": 107, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are found in various hypothetical proteins produced by the bacterium Chlamydia pneumoniae. Their exact function has not, as yet, been identified.", "domain_architectures": 1, "interpro_id": "IPR015400", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF1978)", "partial_evidence_count": null, "pfam_id": "PF09321", "proteins": 25, "proteomes": 3, "short_name": "DUF1978", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09321", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 110 amino acids in length. There are two conserved sequence motifs: KFDIR and DLW.", "domain_architectures": 1, "interpro_id": "IPR025025", "known_evidence_count": null, "matches": 25, "name": "Protein of unknown function (DUF3914)", "partial_evidence_count": null, "pfam_id": "PF13053", "proteins": 25, "proteomes": 24, "short_name": "DUF3914", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13053", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 90 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025044", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF3980)", "partial_evidence_count": null, "pfam_id": "PF13140", "proteins": 25, "proteomes": 25, "short_name": "DUF3980", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13140", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterized proteins around 190 residues in length and is mainly found in various Staphylococcus species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032614", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF4888)", "partial_evidence_count": null, "pfam_id": "PF16229", "proteins": 25, "proteomes": 10, "short_name": "DUF4888", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16229", "structures": 1, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of microsporidial sequences of unknown function. There is a well conserved Asp residue towards the C-terminus which may be functional.", "domain_architectures": 2, "interpro_id": "IPR031512", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF5096)", "partial_evidence_count": null, "pfam_id": "PF17019", "proteins": 25, "proteomes": 23, "short_name": "DUF5096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17019", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised yeast proteins.", "domain_architectures": 1, "interpro_id": "IPR033775", "known_evidence_count": null, "matches": 25, "name": "Protein of unknown function (DUF5137)", "partial_evidence_count": null, "pfam_id": "PF17220", "proteins": 25, "proteomes": 24, "short_name": "DUF5137", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17220", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 2, "interpro_id": "IPR041287", "known_evidence_count": null, "matches": 26, "name": "Family of unknown function (DUF5548)", "partial_evidence_count": null, "pfam_id": "PF17702", "proteins": 25, "proteomes": 24, "short_name": "DUF5548", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17702", "structures": 0, "taxa": 88, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in mammals.", "domain_architectures": 2, "interpro_id": "IPR040791", "known_evidence_count": null, "matches": 31, "name": "Family of unknown function (DUF5555)", "partial_evidence_count": null, "pfam_id": "PF17710", "proteins": 25, "proteomes": 24, "short_name": "DUF5555", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17710", "structures": 0, "taxa": 112, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040965", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF5559)", "partial_evidence_count": null, "pfam_id": "PF17714", "proteins": 25, "proteomes": 22, "short_name": "DUF5559", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17714", "structures": 0, "taxa": 113, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is found in various Platyhelminthes, with many of the sequences annotated as being the STARP-like antigen. This highly conserved domain is located next to the basic helix-loop-helix motif found in this antigen. The function of this family is currently unknown.", "domain_architectures": 2, "interpro_id": "IPR043790", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF5732)", "partial_evidence_count": null, "pfam_id": "PF19003", "proteins": 25, "proteomes": 9, "short_name": "DUF5732", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19003", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000703) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member from the kanamycin biosynthetic gene cluster from Streptomyces kanamyceticus [[cite:PUB00098882]].", "domain_architectures": 1, "interpro_id": "IPR045753", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF6181)", "partial_evidence_count": null, "pfam_id": "PF19679", "proteins": 25, "proteomes": 25, "short_name": "DUF6181", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19679", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found at the C-terminal of a group of bacterial proteins and, according to structure predictions, it may adopt a beta-barrel structure. It is often associated with an Ig-like domain ([pfam:PF08522]).", "domain_architectures": 2, "interpro_id": "IPR054281", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF7015)", "partial_evidence_count": null, "pfam_id": "PF22839", "proteins": 25, "proteomes": 25, "short_name": "DUF7015", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22839", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055751", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF7327)", "partial_evidence_count": null, "pfam_id": "PF24013", "proteins": 25, "proteomes": 25, "short_name": "DUF7327", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24013", "structures": 0, "taxa": 71, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. These proteins are around 50-60 residues in length.", "domain_architectures": 1, "interpro_id": "IPR055821", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF7397)", "partial_evidence_count": null, "pfam_id": "PF24130", "proteins": 25, "proteomes": 25, "short_name": "DUF7397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24130", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised mycobacterial phage. Some members are annotated as DNA primase. The family includes gene 53 from phage Bxb1.", "domain_architectures": 1, "interpro_id": "IPR055881", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF7458)", "partial_evidence_count": null, "pfam_id": "PF24257", "proteins": 25, "proteomes": 25, "short_name": "DUF7458", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24257", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of virus proteins that is likely zinc binding. It shows structural similarity to [pfam:PF03804]. The function of these proteins is unknown.", "domain_architectures": 1, "interpro_id": "IPR057201", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF7879)", "partial_evidence_count": null, "pfam_id": "PF25303", "proteins": 25, "proteomes": 23, "short_name": "DUF7879", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25303", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found at the N-terminus of a range of spirochete proteins. Based on structural similarity to LolA these proteins are likely to be involved in lipid transport.", "domain_architectures": 2, "interpro_id": "IPR058260", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF7954)", "partial_evidence_count": null, "pfam_id": "PF25843", "proteins": 25, "proteomes": 25, "short_name": "DUF7954", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25843", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in a family of spirochete proteins that are likely involved in lipid transport.", "domain_architectures": 2, "interpro_id": "IPR058261", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF7955)", "partial_evidence_count": null, "pfam_id": "PF25844", "proteins": 25, "proteomes": 24, "short_name": "DUF7955", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25844", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an unique structure composed of two meander beta-sheets that pack close.", "domain_architectures": 1, "interpro_id": "IPR059300", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF8256)", "partial_evidence_count": null, "pfam_id": "PF26784", "proteins": 25, "proteomes": 24, "short_name": "DUF8256", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26784", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Bacillales lineage. It is frequently found in combination with LXG domain ([pfam:PF04740]).", "domain_architectures": 2, "interpro_id": "IPR059345", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF8301)", "partial_evidence_count": null, "pfam_id": "PF26953", "proteins": 25, "proteomes": 23, "short_name": "DUF8301", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26953", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in a small group of proteins mostly found in animals , particularly nematodes. This domain contains a Spectrin fold with a conserved three-helix bundle structure that is typically arranged in tandem repeats. These repeats confer mechanical flexibility and structural resilience, allowing the proteins to maintain cell shape and organisation. Spectrin-repeat proteins form elongated scaffolds beneath the plasma membrane and contribute to cytoskeletal integrity and membrane stability [[cite:PUB00161917]]. This domain can be found associated with [pfam:PF00307].", "domain_architectures": 13, "interpro_id": "IPR059367", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF8323)", "partial_evidence_count": null, "pfam_id": "PF26998", "proteins": 25, "proteomes": 22, "short_name": "DUF8323", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26998", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 95 residues found in bacterial AAA ATPases. This small family of 16 proteins is restricted to Planctomycetota and Chloroflexota. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061751", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF8690)", "partial_evidence_count": null, "pfam_id": "PF30654", "proteins": 25, "proteomes": 25, "short_name": "DUF8690", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30654", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 24, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised bacterial proteins. They are predicted to be composed of eight transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR061775", "known_evidence_count": null, "matches": 25, "name": "Domain of unknown function (DUF8714)", "partial_evidence_count": null, "pfam_id": "PF30735", "proteins": 25, "proteomes": 24, "short_name": "DUF8714", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30735", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This viral family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR022621", "known_evidence_count": null, "matches": 24, "name": "Protein of unknown function (DUF2729)", "partial_evidence_count": null, "pfam_id": "PF10870", "proteins": 24, "proteomes": 23, "short_name": "DUF2729", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10870", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021305", "known_evidence_count": null, "matches": 24, "name": "Protein of unknown function (DUF2880)", "partial_evidence_count": null, "pfam_id": "PF11082", "proteins": 24, "proteomes": 24, "short_name": "DUF2880", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11082", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is approximately 130 residues. Dali search indicates this protein carries a NTF2-fold with a hydrophobic cavity as a structural homologue to 1JB2, 2R4I, 3FSD and 2UX0. In this hydrophobic cavity, Arg 118 provides the H-bonding force to hold a PEG molecule from crystallisation. The interface interaction suggests that the biomolecule of [swissprot:Q46KI2] is a dimer. Two members of the family are annotated as putative EF-Tu domain 2 but there is no match to this family so this is likely to be a false assignment. There are two highly conserved tryptophan residues towards the C-terminal end of the family.", "domain_architectures": 3, "interpro_id": "IPR024525", "known_evidence_count": null, "matches": 25, "name": "Protein of unknown function (DUF3804)", "partial_evidence_count": null, "pfam_id": "PF12707", "proteins": 24, "proteomes": 15, "short_name": "DUF3804", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12707", "structures": 1, "taxa": 82, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length. There is a conserved CLGGF sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025104", "known_evidence_count": null, "matches": 24, "name": "Protein of unknown function (DUF4027)", "partial_evidence_count": null, "pfam_id": "PF13219", "proteins": 24, "proteomes": 24, "short_name": "DUF4027", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13219", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 95 and 119 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025107", "known_evidence_count": null, "matches": 24, "name": "Protein of unknown function (DUF4029)", "partial_evidence_count": null, "pfam_id": "PF13221", "proteins": 24, "proteomes": 24, "short_name": "DUF4029", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13221", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins around 180 in length and is mainly found in various Clostridiales species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032208", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF5027)", "partial_evidence_count": null, "pfam_id": "PF16430", "proteins": 24, "proteomes": 18, "short_name": "DUF5027", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16430", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Borreliella burgdorferi.", "domain_architectures": 1, "interpro_id": "IPR035340", "known_evidence_count": null, "matches": 24, "name": "Family of unknown function (DUF5425)", "partial_evidence_count": null, "pfam_id": "PF17472", "proteins": 24, "proteomes": 21, "short_name": "DUF5425", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17472", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR041240", "known_evidence_count": null, "matches": 24, "name": "Family of unknown function (DUF5541)", "partial_evidence_count": null, "pfam_id": "PF17695", "proteins": 24, "proteomes": 20, "short_name": "DUF5541", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17695", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Iridoviridae.", "domain_architectures": 2, "interpro_id": "IPR043880", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF5852)", "partial_evidence_count": null, "pfam_id": "PF19170", "proteins": 24, "proteomes": 23, "short_name": "DUF5852", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19170", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in uncharacterised sequences from plasmodium falciparum (SwissProt:Q8IBR8) and similar sequences from Apicomplexa. It may adopt a beta-propeller-like fold, which, from structure predictions, it seems incomplete.", "domain_architectures": 4, "interpro_id": "IPR056052", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF7635)", "partial_evidence_count": null, "pfam_id": "PF24640", "proteins": 24, "proteomes": 23, "short_name": "DUF7635", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24640", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from eukaryotes. It is predicted to adopt a three alpha-helical bundle", "domain_architectures": 13, "interpro_id": "IPR058344", "known_evidence_count": null, "matches": 98, "name": "Domain of unknown function (DUF8031)", "partial_evidence_count": null, "pfam_id": "PF26081", "proteins": 24, "proteomes": 5, "short_name": "DUF8031", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26081", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt an alpha/beta structure consisting of an antiparallel beta-sheet and alpha-helices packed on one side of it.", "domain_architectures": 1, "interpro_id": "IPR059311", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF8267)", "partial_evidence_count": null, "pfam_id": "PF26797", "proteins": 24, "proteomes": 24, "short_name": "DUF8267", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26797", "structures": 0, "taxa": 109, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 32 residues found in Cyanobacteriota, predominantly in Prochlorococcus species. The domain forms a helical hairpin structure and contains conserved residues that may coordinate zinc. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061703", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF8642)", "partial_evidence_count": null, "pfam_id": "PF30575", "proteins": 24, "proteomes": 13, "short_name": "DUF8642", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30575", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a beta-sandwich.", "domain_architectures": 1, "interpro_id": "IPR061771", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF8710)", "partial_evidence_count": null, "pfam_id": "PF30728", "proteins": 24, "proteomes": 13, "short_name": "DUF8710", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30728", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of short hypothetical proteins in Rhodopirellula baltica.", "domain_architectures": 1, "interpro_id": "IPR011480", "known_evidence_count": null, "matches": 23, "name": "Protein of unknown function (DUF1589)", "partial_evidence_count": null, "pfam_id": "PF07628", "proteins": 23, "proteomes": 5, "short_name": "DUF1589", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07628", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae.", "domain_architectures": 2, "interpro_id": "IPR024497", "known_evidence_count": null, "matches": 23, "name": "Protein of unknown function (DUF2773)", "partial_evidence_count": null, "pfam_id": "PF10971", "proteins": 23, "proteomes": 17, "short_name": "DUF2773", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10971", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 40 amino acids in length. There is a conserved RDE sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025099", "known_evidence_count": null, "matches": 23, "name": "Protein of unknown function (DUF4024)", "partial_evidence_count": null, "pfam_id": "PF13216", "proteins": 23, "proteomes": 23, "short_name": "DUF4024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13216", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 230 amino acids in length. There is a conserved WYK sequence motif.", "domain_architectures": 4, "interpro_id": "IPR027959", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF4627)", "partial_evidence_count": null, "pfam_id": "PF15425", "proteins": 23, "proteomes": 23, "short_name": "DUF4627", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15425", "structures": 1, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 250 residues in length and is mainly found in various Desulfovibrio species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032323", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF4851)", "partial_evidence_count": null, "pfam_id": "PF16143", "proteins": 23, "proteomes": 14, "short_name": "DUF4851", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16143", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry consists of uncharacterised proteins around 400 residues in length and is mainly found in various species, such as Bacteroides, Capnocytophaga and Prevotella. The function of this proteins is unknown. This entry represents the N-terminal domain of these sequences which may adopt a Ig-like fold.", "domain_architectures": 2, "interpro_id": "IPR032562", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF4929)", "partial_evidence_count": null, "pfam_id": "PF16283", "proteins": 23, "proteomes": 23, "short_name": "DUF4929", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16283", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycoplasmataceae. Family members are predicted to have one trans-membrane region.", "domain_architectures": 2, "interpro_id": "IPR035325", "known_evidence_count": null, "matches": 27, "name": "Family of unknown function (DUF5385)", "partial_evidence_count": null, "pfam_id": "PF17359", "proteins": 23, "proteomes": 23, "short_name": "DUF5385", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17359", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR035191", "known_evidence_count": null, "matches": 23, "name": "Family of unknown function (DUF5462)", "partial_evidence_count": null, "pfam_id": "PF17547", "proteins": 23, "proteomes": 12, "short_name": "DUF5462", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17547", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 3, "interpro_id": "IPR041041", "known_evidence_count": null, "matches": 40, "name": "Family of unknown function (DUF5539)", "partial_evidence_count": null, "pfam_id": "PF17693", "proteins": 23, "proteomes": 14, "short_name": "DUF5539", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17693", "structures": 0, "taxa": 69, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040821", "known_evidence_count": null, "matches": 23, "name": "Family of unknown function (DUF5544)", "partial_evidence_count": null, "pfam_id": "PF17698", "proteins": 23, "proteomes": 23, "short_name": "DUF5544", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17698", "structures": 0, "taxa": 86, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043846", "known_evidence_count": null, "matches": 23, "name": "Family of unknown function (DUF5863)", "partial_evidence_count": null, "pfam_id": "PF19181", "proteins": 23, "proteomes": 21, "short_name": "DUF5863", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19181", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins from Bacteroidetes. This domain is found to the N-terminus of a WD40-like domain in DUF4784 family protein.", "domain_architectures": 2, "interpro_id": "IPR046546", "known_evidence_count": null, "matches": 23, "name": "DUF4784 N-terminal Ig-like domain", "partial_evidence_count": null, "pfam_id": "PF20264", "proteins": 23, "proteomes": 23, "short_name": "DUF4784_N", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20264", "structures": 1, "taxa": 48, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in Histone-lysine N-methyltransferase, H3 lysine-4 specific from Plasmodium falciparum ([swissprot:W4J2P1]) and similar sequences from alveolates. In some proteins this domain is found associated with [pfam:PF00628]. It shows a conserved motif LLxxYKxKI/LxDLL.", "domain_architectures": 3, "interpro_id": "IPR055501", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF7073)", "partial_evidence_count": null, "pfam_id": "PF23264", "proteins": 23, "proteomes": 22, "short_name": "DUF7073", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23264", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function. It is structurally similar to Frag1-like domain, composed of a six-alpha-helix bundle transmembrane region [[cite:PUB00155610]].", "domain_architectures": 1, "interpro_id": "IPR055529", "known_evidence_count": null, "matches": 23, "name": "Family of unknown function (DUF7103)", "partial_evidence_count": null, "pfam_id": "PF23396", "proteins": 23, "proteomes": 23, "short_name": "DUF7103", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23396", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found at the N-terminal of CHAT domain-containing, such as SwissProt:A0A100JVW6, protein from Streptomyces scabiei. This domain may be found in association with TCAD7 ([pfam:PF19973]) and CHAT ([pfam:PF12770]) domains.", "domain_architectures": 4, "interpro_id": "IPR055786", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF7362)", "partial_evidence_count": null, "pfam_id": "PF24062", "proteins": 23, "proteomes": 23, "short_name": "DUF7362", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24062", "structures": 0, "taxa": 80, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins found in Chlamydiia. They adopt a globular alpha/beta structure consisting of a curved mixed beta-sheet and alpha-helices packed on both sides (PDB:6UXC).", "domain_architectures": 1, "interpro_id": "IPR055922", "known_evidence_count": null, "matches": 23, "name": "Family of unknown function (DUF7499)", "partial_evidence_count": null, "pfam_id": "PF24330", "proteins": 23, "proteomes": 22, "short_name": "DUF7499", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24330", "structures": 1, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found in uncharacterised sequences from Plasmodium and related sequences from Plasmodiidae.", "domain_architectures": 3, "interpro_id": "IPR056045", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF7628)", "partial_evidence_count": null, "pfam_id": "PF24631", "proteins": 23, "proteomes": 22, "short_name": "DUF7628", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24631", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an Ig-like domain found at the N-terminal of proteins from Plasmodium falciparum and related sequences from Plasmodiidae. The function of these protein is unknown.", "domain_architectures": 3, "interpro_id": "IPR056046", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF7629)", "partial_evidence_count": null, "pfam_id": "PF24632", "proteins": 23, "proteomes": 22, "short_name": "DUF7629", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24632", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found at the C-terminal of uncharacterised sequences from diatoms, which is usually associated with a beta-solenoid at the N-terminal. This domain may adopt a beta-sandwich fold.", "domain_architectures": 6, "interpro_id": "IPR056050", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF7633)", "partial_evidence_count": null, "pfam_id": "PF24636", "proteins": 23, "proteomes": 4, "short_name": "DUF7633", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24636", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed beta-sandwich domain found near the central region of uncharacterised sequences from Plasmodium falciparum (SwissProt:Q8IBR8) and similar sequences from Apicomplexa.", "domain_architectures": 3, "interpro_id": "IPR056051", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF7634)", "partial_evidence_count": null, "pfam_id": "PF24639", "proteins": 23, "proteomes": 22, "short_name": "DUF7634", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24639", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins predominantly found in halophilic archaea. The proteins in this family are primarily distributed among the Halobacteria class, including genera such as Natronomonas and Haloarcula. Additionally, some members are found in viruses infecting these archaea. The proteins are relatively short, with lengths ranging from approximately 113 to 131 amino acids.", "domain_architectures": 1, "interpro_id": "IPR058422", "known_evidence_count": null, "matches": 23, "name": "Family of unknown function (DUF8109)", "partial_evidence_count": null, "pfam_id": "PF26414", "proteins": 23, "proteomes": 22, "short_name": "DUF8109", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26414", "structures": 0, "taxa": 59, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 23, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It contains three cysteine and a histidine residues that are highly conserved. It is predicted to fold into a structure that resembles a circularly permuted zinc-ribbon domains.", "domain_architectures": 1, "interpro_id": "IPR059331", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF8287)", "partial_evidence_count": null, "pfam_id": "PF26936", "proteins": 23, "proteomes": 23, "short_name": "DUF8287", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26936", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Actinomycetes lineage. It contains a semi-conserved WGYxGxG sequence motif. It is predicted to fold into an alpha/beta structure composed of antiparallel beta-sheet and alpha-helices packed on one side.", "domain_architectures": 2, "interpro_id": "IPR059351", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF8307)", "partial_evidence_count": null, "pfam_id": "PF26974", "proteins": 23, "proteomes": 22, "short_name": "DUF8307", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26974", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Campylobacterales. It is predicted to adopt an alpha/beta structure composed of a four stranded antiparallel beta-sheet and array of alpha-helices packed on it. It contains several conserved negatively charged residues that may be essential for function.", "domain_architectures": 1, "interpro_id": "IPR059359", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF8315)", "partial_evidence_count": null, "pfam_id": "PF26989", "proteins": 23, "proteomes": 23, "short_name": "DUF8315", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26989", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains conserved RxDxDxxYY sequence motif which may be important for function.", "domain_architectures": 15, "interpro_id": "IPR059453", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF8409)", "partial_evidence_count": null, "pfam_id": "PF28468", "proteins": 23, "proteomes": 21, "short_name": "DUF8409", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28468", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found at the N-terminal of a group of uncharacterised bacterial sequences, which mostly adopts an helical fold with two beta-strands at its C-terminal that seem to contribute to [pfam:PF27477] structure.", "domain_architectures": 4, "interpro_id": "IPR061661", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF8600)", "partial_evidence_count": null, "pfam_id": "PF29886", "proteins": 23, "proteomes": 23, "short_name": "DUF8600", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29886", "structures": 0, "taxa": 95, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is an alpha-helical domain found in a group of uncharacterised sequences from bacteria, that is usually associated with [pfam:PF00078] at the N-terminal and [pfam:PF18732] at the C-terminal.", "domain_architectures": 3, "interpro_id": "IPR061670", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF8609)", "partial_evidence_count": null, "pfam_id": "PF30173", "proteins": 23, "proteomes": 21, "short_name": "DUF8609", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30173", "structures": 1, "taxa": 83, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 50 residues found in Cyanobacteriota and in cyanophages (Kyanoviridae). Structural analysis indicates this domain adopts a ubiquitin-like fold. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061708", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF8647)", "partial_evidence_count": null, "pfam_id": "PF30581", "proteins": 23, "proteomes": 21, "short_name": "DUF8647", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30581", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised hypothetical proteins of unknown function from Xylella fastidiosa, the organism that causes Pierce's disease in plants.", "domain_architectures": 3, "interpro_id": "IPR008487", "known_evidence_count": null, "matches": 23, "name": "Xylella fastidiosa protein of unknown function (DUF769)", "partial_evidence_count": null, "pfam_id": "PF05590", "proteins": 22, "proteomes": 5, "short_name": "DUF769", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05590", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of conserved Schizosaccharomyces pombe proteins with unknown function.", "domain_architectures": 1, "interpro_id": "IPR009340", "known_evidence_count": null, "matches": 22, "name": "Protein of unknown function (DUF999)", "partial_evidence_count": null, "pfam_id": "PF06198", "proteins": 22, "proteomes": 3, "short_name": "DUF999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06198", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 50 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025053", "known_evidence_count": null, "matches": 22, "name": "Protein of unknown function (DUF3985)", "partial_evidence_count": null, "pfam_id": "PF13153", "proteins": 22, "proteomes": 22, "short_name": "DUF3985", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13153", "structures": 0, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins from Bacteroidetes. This entry adopts a 6-bladed beta propeller structure.", "domain_architectures": 1, "interpro_id": "IPR031978", "known_evidence_count": null, "matches": 22, "name": "DUF4784 WD40-like domain", "partial_evidence_count": null, "pfam_id": "PF16023", "proteins": 22, "proteomes": 22, "short_name": "DUF4784", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16023", "structures": 1, "taxa": 46, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 310 residues in length and found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032318", "known_evidence_count": null, "matches": 22, "name": "Domain of unknown function (DUF4848)", "partial_evidence_count": null, "pfam_id": "PF16140", "proteins": 22, "proteomes": 21, "short_name": "DUF4848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16140", "structures": 1, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 200 residues in length and is mainly found in various Clostridiales species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032219", "known_evidence_count": null, "matches": 22, "name": "Domain of unknown function (DUF5038)", "partial_evidence_count": null, "pfam_id": "PF16441", "proteins": 22, "proteomes": 21, "short_name": "DUF5038", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16441", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycoplasma.", "domain_architectures": 3, "interpro_id": "IPR035158", "known_evidence_count": null, "matches": 34, "name": "Family of unknown function (DUF5396)", "partial_evidence_count": null, "pfam_id": "PF17374", "proteins": 22, "proteomes": 10, "short_name": "DUF5396", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17374", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Human adenovirus.", "domain_architectures": 1, "interpro_id": "IPR035153", "known_evidence_count": null, "matches": 22, "name": "Family of unknown function (DUF5473)", "partial_evidence_count": null, "pfam_id": "PF17567", "proteins": 22, "proteomes": 8, "short_name": "DUF5473", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17567", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040904", "known_evidence_count": null, "matches": 22, "name": "Family of unknown function (DUF5557)", "partial_evidence_count": null, "pfam_id": "PF17712", "proteins": 22, "proteomes": 21, "short_name": "DUF5557", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17712", "structures": 0, "taxa": 85, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043923", "known_evidence_count": null, "matches": 22, "name": "Family of unknown function (DUF5774)", "partial_evidence_count": null, "pfam_id": "PF19083", "proteins": 22, "proteomes": 8, "short_name": "DUF5774", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19083", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the C-terminal of sequences from Gammaproteobacteria. According to structure predictions it may have an alpha/beta fold.", "domain_architectures": 2, "interpro_id": "IPR055485", "known_evidence_count": null, "matches": 22, "name": "Domain of unknown function (DUF7057)", "partial_evidence_count": null, "pfam_id": "PF23167", "proteins": 22, "proteomes": 22, "short_name": "DUF7057", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23167", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterized protein family found in mycobacteriophages. The function of this protein is currently unknown. The family is approximately 147 amino acids long. These proteins contain two small domains. The most N-terminal one contains a CXXC and HXXC motif that likely bind to zinc.", "domain_architectures": 1, "interpro_id": "IPR055868", "known_evidence_count": null, "matches": 22, "name": "Family of unknown function (DUF7445)", "partial_evidence_count": null, "pfam_id": "PF24232", "proteins": 22, "proteomes": 22, "short_name": "DUF7445", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24232", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed helical domain found at the C-terminal of a group of uncharacterised sequences from Plasmodium falciparum and related sequences from Apicomplexa.", "domain_architectures": 3, "interpro_id": "IPR056049", "known_evidence_count": null, "matches": 22, "name": "Domain of unknown function (DUF7632)", "partial_evidence_count": null, "pfam_id": "PF24635", "proteins": 22, "proteomes": 21, "short_name": "DUF7632", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24635", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to adopt a globular structure composed of four stranded antiparallel beta sheet and alpha helices packed on one side of it. It contains a number of positively charged residues which may be essential for function.", "domain_architectures": 1, "interpro_id": "IPR059355", "known_evidence_count": null, "matches": 22, "name": "Domain of unknown function (DUF8311)", "partial_evidence_count": null, "pfam_id": "PF26982", "proteins": 22, "proteomes": 22, "short_name": "DUF8311", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26982", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function in uncharacterised proteins mostly found in Sar organisms. These proteins contain a SNARE-like fold. They are characterised by their tetrameric coiled-coil structures that facilitate membrane fusion processes. SNARE proteins are present in synaptic terminals, endoplasmic reticulum, and Golgi apparatus where the coiled-coil structure is important for membrane targeting and fusion specificity. The conserved coiled-coil architecture enables these proteins to function in vesicle trafficking and membrane fusion events [[cite:PUB00161918]].", "domain_architectures": 2, "interpro_id": "IPR059378", "known_evidence_count": null, "matches": 22, "name": "Domain of unknown function (DUF8334)", "partial_evidence_count": null, "pfam_id": "PF27014", "proteins": 22, "proteomes": 22, "short_name": "DUF8334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27014", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 22, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains three cysteine and histidine residues which are highly conserved. They are predicted to come close in space and probably form a metal coordination site.", "domain_architectures": 3, "interpro_id": "IPR059426", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF8382)", "partial_evidence_count": null, "pfam_id": "PF28346", "proteins": 22, "proteomes": 3, "short_name": "DUF8382", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28346", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 21, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents the C-terminal domain found in a family of uncharacterised hypothetical prokaryotic proteins.", "domain_architectures": 2, "interpro_id": "IPR063034", "known_evidence_count": null, "matches": 22, "name": "DUF499 6th domain", "partial_evidence_count": null, "pfam_id": "PF30801", "proteins": 22, "proteomes": 22, "short_name": "DUF499_6th", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30801", "structures": 0, "taxa": 73, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function has a highly conserved sequence.", "domain_architectures": 1, "interpro_id": "IPR022626", "known_evidence_count": null, "matches": 21, "name": "Protein of unknown function (DUF2740)", "partial_evidence_count": null, "pfam_id": "PF10872", "proteins": 21, "proteomes": 19, "short_name": "DUF2740", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10872", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function. Some members in this family of proteins are annotated as TTHA0547 however this cannot be confirmed.", "domain_architectures": 1, "interpro_id": "IPR021628", "known_evidence_count": null, "matches": 21, "name": "Protein of unknown function (DUF3234)", "partial_evidence_count": null, "pfam_id": "PF11572", "proteins": 21, "proteomes": 21, "short_name": "DUF3234", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11572", "structures": 1, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in bacteroides. Proteins in this family are around 600 amino acids in length.", "domain_architectures": 3, "interpro_id": "IPR032170", "known_evidence_count": null, "matches": 21, "name": "Domain of unknown function (DUF5006)", "partial_evidence_count": null, "pfam_id": "PF16397", "proteins": 21, "proteomes": 15, "short_name": "DUF5006", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16397", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family found in Chlamydia includes CT296 from Chlamydia trachomatis, which show structural features typical of non-heme Fe(II) 2-oxoglutarate-dependent enzymes [[cite:PUB00100851]]. The specific function of these proteins is not known.", "domain_architectures": 1, "interpro_id": "IPR031839", "known_evidence_count": null, "matches": 21, "name": "Domain of unknown function (DUF5070)", "partial_evidence_count": null, "pfam_id": "PF16802", "proteins": 21, "proteomes": 19, "short_name": "DUF5070", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16802", "structures": 2, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Campylobacteria.", "domain_architectures": 1, "interpro_id": "IPR035393", "known_evidence_count": null, "matches": 21, "name": "Family of unknown function (DUF5416)", "partial_evidence_count": null, "pfam_id": "PF17437", "proteins": 21, "proteomes": 21, "short_name": "DUF5416", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17437", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001916) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the lavendiol biosynthetic gene cluster from Streptomyces lavendulae [[cite:PUB00098885]].", "domain_architectures": 1, "interpro_id": "IPR046307", "known_evidence_count": null, "matches": 21, "name": "Family of unknown function (DUF6422)", "partial_evidence_count": null, "pfam_id": "PF19986", "proteins": 21, "proteomes": 17, "short_name": "DUF6422", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19986", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes NMB0500 from Neisseria meningitidis and similar bacterial uncharacterised proteins. NMB0500 has an all-alpha structure. Its function is unknown.", "domain_architectures": 1, "interpro_id": "IPR049276", "known_evidence_count": null, "matches": 21, "name": "Family of unknown function (DUF6853)", "partial_evidence_count": null, "pfam_id": "PF21593", "proteins": 21, "proteomes": 14, "short_name": "DUF6853", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21593", "structures": 1, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found towards the N-terminal of a group of proteins from nematodes such as Trichuris suis and Trichinella britovi, members of the BPI/LBP/Plunc family of proteins which share homology with cholesterol ester transfer protein (CETP) and phospholipid transfer protein (PLTP). The exact function of these proteins is unknown, however, according to their structure predictions and homology to CEPT/PLTP, they may be involved in lipid binding.", "domain_architectures": 4, "interpro_id": "IPR055489", "known_evidence_count": null, "matches": 22, "name": "Domain of unknown function (DUF7061)", "partial_evidence_count": null, "pfam_id": "PF23200", "proteins": 21, "proteomes": 13, "short_name": "DUF7061", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23200", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of protein of unknown function found in phage. The protein are predicted to be largely disordered, with a C-terminal small beta barrel domain.", "domain_architectures": 2, "interpro_id": "IPR055675", "known_evidence_count": null, "matches": 22, "name": "Family of unknown function (DUF7251)", "partial_evidence_count": null, "pfam_id": "PF23909", "proteins": 21, "proteomes": 21, "short_name": "DUF7251", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23909", "structures": 0, "taxa": 60, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised mycobacterial phage proteins. Structure prediction suggests that this protein forms a single alpha helix. It is quite hydrophobic with a negatively charged C-terminus. Some proteins are annotated as RDF proteins but there does not appear to be any evidence to support their function as recombination directionality factors.", "domain_architectures": 1, "interpro_id": "IPR055857", "known_evidence_count": null, "matches": 21, "name": "Family of unknown function (DUF7434)", "partial_evidence_count": null, "pfam_id": "PF24213", "proteins": 21, "proteomes": 21, "short_name": "DUF7434", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24213", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins from bacteria that, according to structure predictions (SwissProt:A0A7C3HQW7 or SwissProt:A0A5C6D6K5), they may contain novel repeats that fold into twisted long beta-hairpins different from typical beta-barrel hairpins and they do not exhibit homology to any beta-barrel.", "domain_architectures": 1, "interpro_id": "IPR055873", "known_evidence_count": null, "matches": 21, "name": "Repeat of unknown function (DUF7450)", "partial_evidence_count": null, "pfam_id": "PF24247", "proteins": 21, "proteomes": 21, "short_name": "DUF7450", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24247", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised enterobacterial phage proteins. These proteins adopt a compact domain composed of a small three stranded beta sheet, with an alpha helix inserted between the first and second strand.", "domain_architectures": 1, "interpro_id": "IPR055962", "known_evidence_count": null, "matches": 21, "name": "Domain of unknown function (DUF7540)", "partial_evidence_count": null, "pfam_id": "PF24386", "proteins": 21, "proteomes": 21, "short_name": "DUF7540", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24386", "structures": 0, "taxa": 81, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in bacteria (Bacteroidota and Chloroflexi). Proteins in this family are approximately 80 amino acids in length. The proteins are likely to be integral membrane proteins with two transmembrane alpha helices. Structural modelling suggests that these proteins form a dimeric arrangement with the pairs of alpha helices tilted at close to 45 degrees angle compared to the lipid membrane. Based on the positive inside rule it is likely that the N and C-terminii of the proteins have a cytoplasmic location. Given the geometry of the protein complex it may not span the entire membrane.", "domain_architectures": 1, "interpro_id": "IPR056089", "known_evidence_count": null, "matches": 21, "name": "Family of unknown function (DUF7672)", "partial_evidence_count": null, "pfam_id": "PF24717", "proteins": 21, "proteomes": 21, "short_name": "DUF7672", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24717", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Actinomycetes. It is predicted to fold into an unique alpha/beta structure. In some proteins it is found inserted into a transmembrane domain.", "domain_architectures": 2, "interpro_id": "IPR059363", "known_evidence_count": null, "matches": 21, "name": "Domain of unknown function (DUF8319)", "partial_evidence_count": null, "pfam_id": "PF26993", "proteins": 21, "proteomes": 21, "short_name": "DUF8319", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26993", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 100 residues that adopts an NTF2-like fold. This domain is often found in tandem repeats within proteins. Members are found in diverse eukaryotes including Stramenopiles and Haptophyta, as well as in some Cyanobacteriota. The function of this domain remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061713", "known_evidence_count": null, "matches": 27, "name": "Domain of unknown function (DUF8652)", "partial_evidence_count": null, "pfam_id": "PF30588", "proteins": 21, "proteomes": 10, "short_name": "DUF8652", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30588", "structures": 0, "taxa": 61, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 85 residues found in Cyanobacteriota. Several members of this family are annotated as 4Fe-4S iron-sulfur cluster binding proteins, though this has not been experimentally verified. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061714", "known_evidence_count": null, "matches": 21, "name": "Domain of unknown function (DUF8653)", "partial_evidence_count": null, "pfam_id": "PF30589", "proteins": 21, "proteomes": 20, "short_name": "DUF8653", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30589", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein from Thermotoga maritima is a hypothetical ORFan protein, TM1622, whose structure has been determined. The protein is composed of seven beta strands and three alpha helices [[cite:PUB00037978]].", "domain_architectures": 1, "interpro_id": "IPR021636", "known_evidence_count": null, "matches": 20, "name": "Protein of unknown function (DUF3242)", "partial_evidence_count": null, "pfam_id": "PF11586", "proteins": 20, "proteomes": 20, "short_name": "DUF3242", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11586", "structures": 1, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This protein is found in viruses. Proteins in this family are typically between 209 and 248 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR021982", "known_evidence_count": null, "matches": 21, "name": "Protein of unknown function (DUF3587)", "partial_evidence_count": null, "pfam_id": "PF12132", "proteins": 20, "proteomes": 10, "short_name": "DUF3587", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12132", "structures": 0, "taxa": 71, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Chlamydia.", "domain_architectures": 1, "interpro_id": "IPR035359", "known_evidence_count": null, "matches": 20, "name": "Family of unknown function (DUF5421)", "partial_evidence_count": null, "pfam_id": "PF17458", "proteins": 20, "proteomes": 19, "short_name": "DUF5421", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17458", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043875", "known_evidence_count": null, "matches": 20, "name": "Family of unknown function (DUF5857)", "partial_evidence_count": null, "pfam_id": "PF19175", "proteins": 20, "proteomes": 11, "short_name": "DUF5857", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19175", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 2, "interpro_id": "IPR045413", "known_evidence_count": null, "matches": 20, "name": "Family of unknown function (DUF5894)", "partial_evidence_count": null, "pfam_id": "PF19246", "proteins": 20, "proteomes": 9, "short_name": "DUF5894", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19246", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000320) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This family includes a protein from the cereulide biosynthetic gene cluster from Bacillus cereus and appears to be predominantly found in Bacilli [[cite:PUB00099383],[cite:PUB00099443]].", "domain_architectures": 1, "interpro_id": "IPR046060", "known_evidence_count": null, "matches": 20, "name": "Family of unknown function (DUF6018)", "partial_evidence_count": null, "pfam_id": "PF19482", "proteins": 20, "proteomes": 18, "short_name": "DUF6018", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19482", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000078) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the incednine biosynthetic gene cluster from Streptomyces sp. ML694-90F3 [[cite:PUB00098990]].", "domain_architectures": 1, "interpro_id": "IPR045779", "known_evidence_count": null, "matches": 20, "name": "Family of unknown function (DUF6205)", "partial_evidence_count": null, "pfam_id": "PF19708", "proteins": 20, "proteomes": 20, "short_name": "DUF6205", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19708", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is functionally uncharacterised and is found in proteins from bacteria and archaea. This domain is found in Protein LicC (swiss:P14183), a CTP:phosphocholine cytidylyltransferase involved in LPS biosynthesis. Members containing this domain are annotated as nucleotidyltransferases. It is probable that this domain has a Rossmann like fold.", "domain_architectures": 3, "interpro_id": "IPR046694", "known_evidence_count": null, "matches": 20, "name": "Domain of unknown function (DUF6564)", "partial_evidence_count": null, "pfam_id": "PF20202", "proteins": 20, "proteomes": 19, "short_name": "DUF6564", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20202", "structures": 0, "taxa": 89, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the N-terminal of phage sequences, which also have a FN3-like domain ([pfam:PF21470]) at the C-terminal.", "domain_architectures": 4, "interpro_id": "IPR054279", "known_evidence_count": null, "matches": 20, "name": "Domain of unknown function (DUF7013)", "partial_evidence_count": null, "pfam_id": "PF22793", "proteins": 20, "proteomes": 15, "short_name": "DUF7013", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22793", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found at the C-terminal of a group of proteins from nematodes, members of the BPI/LBP/Plunc family of proteins which share homology with cholesterol ester transfer protein (CETP) and phospholipid transfer protein (PLTP). The exact function of these proteins is unknown, however, according to their structure predictions and homology to CEPT/PLTP, they may play a role in lipid binding.", "domain_architectures": 3, "interpro_id": "IPR055488", "known_evidence_count": null, "matches": 24, "name": "Domain of unknown function (DUF7060)", "partial_evidence_count": null, "pfam_id": "PF23199", "proteins": 20, "proteomes": 12, "short_name": "DUF7060", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23199", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised phage family. A structure prediction suggests that the proteins consist of a three stranded beta meander followed by a C-terminal Alpha helix.", "domain_architectures": 1, "interpro_id": "IPR055656", "known_evidence_count": null, "matches": 20, "name": "Family of unknown function (DUF7232)", "partial_evidence_count": null, "pfam_id": "PF23879", "proteins": 20, "proteomes": 20, "short_name": "DUF7232", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23879", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised mycobacterial phage proteins. The family includes Phage Bxb1 gene 76. These proteins are short around 40 residues in length.", "domain_architectures": 1, "interpro_id": "IPR055885", "known_evidence_count": null, "matches": 20, "name": "Family of unknown function (DUF7462)", "partial_evidence_count": null, "pfam_id": "PF24261", "proteins": 20, "proteomes": 19, "short_name": "DUF7462", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24261", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised sequences from bacteria. They may consist on repeats with a novel fold which is organised in three units with twisted beta-strands each.", "domain_architectures": 3, "interpro_id": "IPR055904", "known_evidence_count": null, "matches": 24, "name": "Family of unknown function (DUF7481)", "partial_evidence_count": null, "pfam_id": "PF24297", "proteins": 20, "proteomes": 9, "short_name": "DUF7481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24297", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes uncharacterised sequences from Plasmodium sp. and similar sequences from Apicomplexa. This entry may represent transmembrane helices.", "domain_architectures": 2, "interpro_id": "IPR056058", "known_evidence_count": null, "matches": 21, "name": "Domain of unknown function (DUF7641)", "partial_evidence_count": null, "pfam_id": "PF24648", "proteins": 20, "proteomes": 20, "short_name": "DUF7641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24648", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 20, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Mycoplasma lineage. It is predicted to fold into a beta-sandwich. It contains two pairs of conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 1, "interpro_id": "IPR059341", "known_evidence_count": null, "matches": 20, "name": "Domain of unknown function (DUF8297)", "partial_evidence_count": null, "pfam_id": "PF26949", "proteins": 20, "proteomes": 1, "short_name": "DUF8297", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26949", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins specific to Chlamydia species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010564", "known_evidence_count": null, "matches": 19, "name": "Protein of unknown function (DUF1137)", "partial_evidence_count": null, "pfam_id": "PF06587", "proteins": 19, "proteomes": 19, "short_name": "DUF1137", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06587", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins of around 610 residues in length. Members of this family are highly conserved and seem to be specific to Chlamydia species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR010764", "known_evidence_count": null, "matches": 19, "name": "Protein of unknown function (DUF1347)", "partial_evidence_count": null, "pfam_id": "PF07079", "proteins": 19, "proteomes": 19, "short_name": "DUF1347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07079", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry consists of several hypothetical putative lipoproteins which seem to be found specifically in the bacterium Leptospira interrogans. This entry represents the N-terminal domain which may adopt a GT-C-like fold.", "domain_architectures": 4, "interpro_id": "IPR010818", "known_evidence_count": null, "matches": 22, "name": "DUF1420 N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF07220", "proteins": 19, "proteomes": 13, "short_name": "DUF1420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07220", "structures": 0, "taxa": 37, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several bacterial proteins of around 175 residues in length. Members of this family seem to be found exclusively in Chlamydia species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009968", "known_evidence_count": null, "matches": 19, "name": "Protein of unknown function (DUF1494)", "partial_evidence_count": null, "pfam_id": "PF07379", "proteins": 19, "proteomes": 19, "short_name": "DUF1494", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07379", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A family of hypothetical proteins in Rhodopirellula baltica.", "domain_architectures": 1, "interpro_id": "IPR011476", "known_evidence_count": null, "matches": 19, "name": "Protein of unknown function (DUF1582)", "partial_evidence_count": null, "pfam_id": "PF07621", "proteins": 19, "proteomes": 3, "short_name": "DUF1582", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07621", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as TrbD however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR024396", "known_evidence_count": null, "matches": 19, "name": "Protein of unknown function (DUF2689)", "partial_evidence_count": null, "pfam_id": "PF10894", "proteins": 19, "proteomes": 9, "short_name": "DUF2689", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10894", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in viruses. Proteins in this family are typically between 25 and 211 amino acids in length.", "domain_architectures": 4, "interpro_id": "IPR022101", "known_evidence_count": null, "matches": 19, "name": "Protein of unknown function (DUF3640)", "partial_evidence_count": null, "pfam_id": "PF12342", "proteins": 19, "proteomes": 2, "short_name": "DUF3640", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12342", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are typically between 89 and 101 amino acids in length. AlphaFold 3 prediction shows these proteins form a confident homodimer structure which adopts a dimeric Alpha/Beta barrel structure.", "domain_architectures": 1, "interpro_id": "IPR022240", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF3764)", "partial_evidence_count": null, "pfam_id": "PF12594", "proteins": 19, "proteomes": 9, "short_name": "DUF3764", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12594", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 150 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR028113", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF4624)", "partial_evidence_count": null, "pfam_id": "PF15417", "proteins": 19, "proteomes": 17, "short_name": "DUF4624", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15417", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chlamydia. Members of this family have 1-4 predicted trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035358", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF5422)", "partial_evidence_count": null, "pfam_id": "PF17459", "proteins": 19, "proteomes": 19, "short_name": "DUF5422", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17459", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Chlamydia. Family members have 4 predicted trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035355", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF5423)", "partial_evidence_count": null, "pfam_id": "PF17461", "proteins": 19, "proteomes": 19, "short_name": "DUF5423", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17461", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR020151", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF5478)", "partial_evidence_count": null, "pfam_id": "PF17572", "proteins": 19, "proteomes": 19, "short_name": "DUF5478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17572", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR020221", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF5505)", "partial_evidence_count": null, "pfam_id": "PF17610", "proteins": 19, "proteomes": 18, "short_name": "DUF5505", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17610", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 1, "interpro_id": "IPR043840", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF5868)", "partial_evidence_count": null, "pfam_id": "PF19186", "proteins": 19, "proteomes": 10, "short_name": "DUF5868", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19186", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR045327", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF5881)", "partial_evidence_count": null, "pfam_id": "PF19228", "proteins": 19, "proteomes": 16, "short_name": "DUF5881", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19228", "structures": 0, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001142) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member of the tryptoquialanine biosynthetic gene cluster from Penicillium aethiopicum [[cite:PUB00099397]]. This family appears to be predominantly found in fungi.", "domain_architectures": 2, "interpro_id": "IPR046189", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF6217)", "partial_evidence_count": null, "pfam_id": "PF19724", "proteins": 19, "proteomes": 18, "short_name": "DUF6217", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19724", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000084) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the laidlomycin biosynthetic gene cluster from Streptomyces sp. CS684 [[cite:PUB00098975]].", "domain_architectures": 1, "interpro_id": "IPR045771", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF6224)", "partial_evidence_count": null, "pfam_id": "PF19734", "proteins": 19, "proteomes": 19, "short_name": "DUF6224", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19734", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001214) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). It includes a member from the marformycin A biosynthetic gene cluster from Streptomyces drozdowiczii [[cite:PUB00099469]].", "domain_architectures": 2, "interpro_id": "IPR046204", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF6237)", "partial_evidence_count": null, "pfam_id": "PF19750", "proteins": 19, "proteomes": 18, "short_name": "DUF6237", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19750", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins exclusively found in S. japonicus. It contains a highly conserved PLLLP motif at the C-terminal.", "domain_architectures": 2, "interpro_id": "IPR046614", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF6727)", "partial_evidence_count": null, "pfam_id": "PF20495", "proteins": 19, "proteomes": 3, "short_name": "DUF6727", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20495", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain family is functionally uncharacterised. This domain is found in eukaryotes and is around 40 amino acids in length.", "domain_architectures": 8, "interpro_id": "IPR046630", "known_evidence_count": null, "matches": 33, "name": "Domain of unknown function (DUF6742)", "partial_evidence_count": null, "pfam_id": "PF20527", "proteins": 19, "proteomes": 1, "short_name": "DUF6742", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20527", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Methanobacteriati. It is predicted to fold into unusual alpha/beta structure. AlphaFold predicts that it may form a swapped dimer.", "domain_architectures": 1, "interpro_id": "IPR059277", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF8233)", "partial_evidence_count": null, "pfam_id": "PF26694", "proteins": 19, "proteomes": 16, "short_name": "DUF8233", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26694", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a beta-sandwich structure consisting of two pairs of swapped beta-hairpins. This domain is found in combination with TauE ([pfam:PF01925]) suggesting it may be associated with the membrane.", "domain_architectures": 2, "interpro_id": "IPR059313", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF8269)", "partial_evidence_count": null, "pfam_id": "PF26800", "proteins": 19, "proteomes": 18, "short_name": "DUF8269", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26800", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into a beta-barrel structure. It contains several highly conserved positively charged residues that may be functionally important.", "domain_architectures": 1, "interpro_id": "IPR059354", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF8310)", "partial_evidence_count": null, "pfam_id": "PF26979", "proteins": 19, "proteomes": 19, "short_name": "DUF8310", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26979", "structures": 0, "taxa": 67, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 125 residues found in putative transcriptional regulators from Cyanobacteriota. The proteins containing this domain are annotated as XRE family or HTH Cro/C1-type regulators. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061705", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF8644)", "partial_evidence_count": null, "pfam_id": "PF30577", "proteins": 19, "proteomes": 17, "short_name": "DUF8644", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30577", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 275 residues found in Cyanobacteriota. The proteins containing this domain also possess an N-terminal domain of approximately 200 residues. Some proteins containing this domain are annotated as histidine ammonia-lyase, though this has not been experimentally verified. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061709", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF8648)", "partial_evidence_count": null, "pfam_id": "PF30582", "proteins": 19, "proteomes": 18, "short_name": "DUF8648", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30582", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 70 residues found in cyanobacterial LysM-containing proteins. The proteins containing this domain typically have multiple N-terminal LysM domains ([pfam:PF01476]) which bind peptidoglycan. The specific function of this C-terminal domain remains to be determined.", "domain_architectures": 6, "interpro_id": "IPR061715", "known_evidence_count": null, "matches": 19, "name": "Domain of unknown function (DUF8654)", "partial_evidence_count": null, "pfam_id": "PF30590", "proteins": 19, "proteomes": 16, "short_name": "DUF8654", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30590", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised archaeal proteins.", "domain_architectures": 1, "interpro_id": "IPR061779", "known_evidence_count": null, "matches": 19, "name": "Family of unknown function (DUF8718)", "partial_evidence_count": null, "pfam_id": "PF30741", "proteins": 19, "proteomes": 19, "short_name": "DUF8718", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30741", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Lactococcus lactis bacteriophage and Lactococcus lactis proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009376", "known_evidence_count": null, "matches": 18, "name": "Protein of unknown function (DUF1031)", "partial_evidence_count": null, "pfam_id": "PF06275", "proteins": 18, "proteomes": 10, "short_name": "DUF1031", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06275", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a small family of fungal proteins one of whose members, [swissprot:A3LUS4] from Pichia stipitis is described as being an extremely serine rich protein-mucin-like protein.", "domain_architectures": 2, "interpro_id": "IPR021642", "known_evidence_count": null, "matches": 21, "name": "Protein of unknown function (DUF3246)", "partial_evidence_count": null, "pfam_id": "PF11596", "proteins": 18, "proteomes": 16, "short_name": "DUF3246", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11596", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 67 and 93 amino acids in length. There are two conserved sequence motifs: IVKI and YVKKWF.", "domain_architectures": 1, "interpro_id": "IPR025106", "known_evidence_count": null, "matches": 18, "name": "Protein of unknown function (DUF4028)", "partial_evidence_count": null, "pfam_id": "PF13220", "proteins": 18, "proteomes": 18, "short_name": "DUF4028", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13220", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of uncharacterized proteins around 180 residues in length and found in various Thermotoga species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032607", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF4894)", "partial_evidence_count": null, "pfam_id": "PF16235", "proteins": 18, "proteomes": 18, "short_name": "DUF4894", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16235", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 75 residues locates in the N-terminal of F5/8 type C domain proteins and some uncharacterized proteins in various Bacteroides species. The function of this family remains unknown.", "domain_architectures": 5, "interpro_id": "IPR032163", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function", "partial_evidence_count": null, "pfam_id": "PF16390", "proteins": 18, "proteomes": 16, "short_name": "DUF4999", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16390", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 150 or 200 in length and is mainly found in various Bacteroides and Parabacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032205", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF5024)", "partial_evidence_count": null, "pfam_id": "PF16427", "proteins": 18, "proteomes": 18, "short_name": "DUF5024", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16427", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043911", "known_evidence_count": null, "matches": 18, "name": "Family of unknown function (DUF5766)", "partial_evidence_count": null, "pfam_id": "PF19070", "proteins": 18, "proteomes": 12, "short_name": "DUF5766", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19070", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 1, "interpro_id": "IPR043878", "known_evidence_count": null, "matches": 18, "name": "Family of unknown function (DUF5854)", "partial_evidence_count": null, "pfam_id": "PF19172", "proteins": 18, "proteomes": 9, "short_name": "DUF5854", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19172", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 2, "interpro_id": "IPR045373", "known_evidence_count": null, "matches": 18, "name": "Family of unknown function (DUF5889)", "partial_evidence_count": null, "pfam_id": "PF19237", "proteins": 18, "proteomes": 13, "short_name": "DUF5889", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19237", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Minor capsid protein P2 from Paramecium bursaria Chlorella virus 1 and related sequences from Mimiviridae and Phycodnaviridae. Minor capsid protein P2 is one of the minor capsid proteins that constitute a network internal to the major capsid proteins and outside the lipid membrane [[cite:PUB00154526]]. The minor capsid proteins glue and stabilize the capsomers [[cite:PUB00154526]]. It also acts as a molecular tape measure protein that determines the size of the viral capsid [[cite:PUB00154526]].", "domain_architectures": 1, "interpro_id": "IPR045418", "known_evidence_count": null, "matches": 18, "name": "Minor capsid protein P2, DUF5899", "partial_evidence_count": null, "pfam_id": "PF19251", "proteins": 18, "proteomes": 14, "short_name": "DUF5899", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19251", "structures": 2, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001517) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the asperphenamate biosynthetic gene cluster from Aspergillus terreus NIH2624 [[cite:PUB00099475]].", "domain_architectures": 1, "interpro_id": "IPR045953", "known_evidence_count": null, "matches": 18, "name": "Family of unknown function (DUF6373)", "partial_evidence_count": null, "pfam_id": "PF19900", "proteins": 18, "proteomes": 18, "short_name": "DUF6373", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19900", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins.", "domain_architectures": 1, "interpro_id": "IPR055758", "known_evidence_count": null, "matches": 18, "name": "Family of unknown function (DUF7334)", "partial_evidence_count": null, "pfam_id": "PF24022", "proteins": 18, "proteomes": 18, "short_name": "DUF7334", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24022", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain found in a family of Trichinella HMG family proteins.", "domain_architectures": 2, "interpro_id": "IPR058391", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8078)", "partial_evidence_count": null, "pfam_id": "PF26287", "proteins": 18, "proteomes": 14, "short_name": "DUF8078", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26287", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 18, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins mainly from Stramenopiles lineages. It contains two pair of highly conserved cysteine residues that may be involved in metal coordination.", "domain_architectures": 2, "interpro_id": "IPR059326", "known_evidence_count": null, "matches": 20, "name": "Domain of unknown function (DUF8282)", "partial_evidence_count": null, "pfam_id": "PF26931", "proteins": 18, "proteomes": 15, "short_name": "DUF8282", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26931", "structures": 0, "taxa": 56, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It contains a semi-conserved PVxVP sequence motif. In some proteins it is found in combination with eCIS core domain ([pfam:PF13699]).", "domain_architectures": 2, "interpro_id": "IPR059347", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8303)", "partial_evidence_count": null, "pfam_id": "PF26963", "proteins": 18, "proteomes": 12, "short_name": "DUF8303", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26963", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Actinomycetes. It is predicted to adopt a globular structure in which two alpha-helices are sandwiched between two four-stranded beta-sheets. Besides a conserved RxF sequence motif, this domain contains several conserved positively charged residues which may be essential for function.", "domain_architectures": 1, "interpro_id": "IPR059408", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8364)", "partial_evidence_count": null, "pfam_id": "PF27965", "proteins": 18, "proteomes": 18, "short_name": "DUF8364", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27965", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 200 residues found in Cyanobacteriota. The proteins containing this domain also possess a C-terminal domain of approximately 275 residues. Some proteins containing this domain are annotated as histidine ammonia-lyase, though this has not been experimentally verified. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061710", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8649)", "partial_evidence_count": null, "pfam_id": "PF30583", "proteins": 18, "proteomes": 18, "short_name": "DUF8649", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30583", "structures": 0, "taxa": 66, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 85 residues found in Cyanobacteriota, predominantly in Synechococcales. The proteins containing this domain also possess a smaller C-terminal domain of approximately 40 residues. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061716", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8655)", "partial_evidence_count": null, "pfam_id": "PF30591", "proteins": 18, "proteomes": 18, "short_name": "DUF8655", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30591", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 40 residues found in Cyanobacteriota, predominantly in Synechococcales. The proteins containing this domain also possess a larger N-terminal domain of approximately 85 residues. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061717", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8656)", "partial_evidence_count": null, "pfam_id": "PF30592", "proteins": 18, "proteomes": 18, "short_name": "DUF8656", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30592", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 120 residues found in Cyanobacteriota, predominantly in Synechococcales. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061720", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8659)", "partial_evidence_count": null, "pfam_id": "PF30595", "proteins": 18, "proteomes": 17, "short_name": "DUF8659", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30595", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 110 residues. The family is restricted to marine picocyanobacteria, specifically Prochlorococcus and Synechococcus species (Synechococcales). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061724", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8663)", "partial_evidence_count": null, "pfam_id": "PF30601", "proteins": 18, "proteomes": 18, "short_name": "DUF8663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30601", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 48 residues. Some family members are annotated as translation initiation factors, although the basis for this annotation is unclear. The family is restricted to marine picocyanobacteria, specifically Prochlorococcus and Synechococcus species (Synechococcales). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061729", "known_evidence_count": null, "matches": 18, "name": "Family of unknown function (DUF8668)", "partial_evidence_count": null, "pfam_id": "PF30607", "proteins": 18, "proteomes": 18, "short_name": "DUF8668", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30607", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Orthopoxvirus specific proteins predominantly of around 340 residues in length. This family contains both B17 and B15 proteins, the function of which are unknown.", "domain_architectures": 1, "interpro_id": "IPR009633", "known_evidence_count": null, "matches": 17, "name": "Protein of unknown function (DUF1231)", "partial_evidence_count": null, "pfam_id": "PF06802", "proteins": 17, "proteomes": 14, "short_name": "DUF1231", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06802", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family of short hypothetical proteins in Leptospira interrogans.", "domain_architectures": 2, "interpro_id": "IPR011457", "known_evidence_count": null, "matches": 17, "name": "Protein of unknown function (DUF1563)", "partial_evidence_count": null, "pfam_id": "PF07599", "proteins": 17, "proteomes": 12, "short_name": "DUF1563", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07599", "structures": 0, "taxa": 78, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family is composed of uncharacterized proteins expressed by Methanopyrus kandleri, a hyperthermophilic archaebacterium.", "domain_architectures": 1, "interpro_id": "IPR012465", "known_evidence_count": null, "matches": 17, "name": "Protein of unknown function (DUF1678)", "partial_evidence_count": null, "pfam_id": "PF07913", "proteins": 17, "proteomes": 2, "short_name": "DUF1678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07913", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as yjfZ however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR021220", "known_evidence_count": null, "matches": 17, "name": "Protein of unknown function (DUF2686)", "partial_evidence_count": null, "pfam_id": "PF10887", "proteins": 17, "proteomes": 10, "short_name": "DUF2686", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10887", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This viral family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR020356", "known_evidence_count": null, "matches": 17, "name": "Protein of unknown function (DUF2718)", "partial_evidence_count": null, "pfam_id": "PF10918", "proteins": 17, "proteomes": 7, "short_name": "DUF2718", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10918", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Member PDB:3GF6 has statistically significant similarity to TNF-like jelly roll fold may indicate an immunomodulatory function[[cite:PUB00055998]] or a bioadhesion role[[cite:PUB00055999]]", "domain_architectures": 1, "interpro_id": "IPR024328", "known_evidence_count": null, "matches": 17, "name": "Domain of Unknown Function with PDB structure", "partial_evidence_count": null, "pfam_id": "PF12956", "proteins": 17, "proteomes": 17, "short_name": "DUF3845", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12956", "structures": 1, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR025068", "known_evidence_count": null, "matches": 17, "name": "Protein of unknown function (DUF3937)", "partial_evidence_count": null, "pfam_id": "PF13073", "proteins": 17, "proteomes": 16, "short_name": "DUF3937", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13073", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 42 and 85 amino acids in length. There is a conserved DIQKW sequence motif.", "domain_architectures": 1, "interpro_id": "IPR025011", "known_evidence_count": null, "matches": 17, "name": "Protein of unknown function (DUF3963)", "partial_evidence_count": null, "pfam_id": "PF13124", "proteins": 17, "proteomes": 16, "short_name": "DUF3963", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13124", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of uncharacterised proteins around 540 residues in length and is mainly found in various Bacteroides and Prevotella species. Several proteins in this family are annotated as Glycoside hydrolases, but the function of this protein is unknown.", "domain_architectures": 10, "interpro_id": "IPR032504", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF4978)", "partial_evidence_count": null, "pfam_id": "PF16349", "proteins": 17, "proteomes": 15, "short_name": "DUF4978", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16349", "structures": 0, "taxa": 70, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Strongyloides.", "domain_architectures": 2, "interpro_id": "IPR035539", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF5387)", "partial_evidence_count": null, "pfam_id": "PF17361", "proteins": 17, "proteomes": 15, "short_name": "DUF5387", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17361", "structures": 0, "taxa": 52, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 1, "interpro_id": "IPR043881", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF5851)", "partial_evidence_count": null, "pfam_id": "PF19169", "proteins": 17, "proteomes": 9, "short_name": "DUF5851", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19169", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043849", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF5859)", "partial_evidence_count": null, "pfam_id": "PF19177", "proteins": 17, "proteomes": 12, "short_name": "DUF5859", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19177", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 1, "interpro_id": "IPR043842", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF5866)", "partial_evidence_count": null, "pfam_id": "PF19184", "proteins": 17, "proteomes": 6, "short_name": "DUF5866", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19184", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Mimiviridae.", "domain_architectures": 1, "interpro_id": "IPR045368", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF5886)", "partial_evidence_count": null, "pfam_id": "PF19233", "proteins": 17, "proteomes": 11, "short_name": "DUF5886", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19233", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses. This family includes proteins that are thought to have acetyltransferase activity.", "domain_architectures": 1, "interpro_id": "IPR045369", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF5887)", "partial_evidence_count": null, "pfam_id": "PF19234", "proteins": 17, "proteomes": 17, "short_name": "DUF5887", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19234", "structures": 1, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001797) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR045988", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF5944)", "partial_evidence_count": null, "pfam_id": "PF19369", "proteins": 17, "proteomes": 15, "short_name": "DUF5944", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19369", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001062) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the TLN-05220 biosynthetic gene cluster from Micromonospora echinospora subsp. challisensis [[cite:PUB00098881]].", "domain_architectures": 1, "interpro_id": "IPR045637", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF6410)", "partial_evidence_count": null, "pfam_id": "PF19948", "proteins": 17, "proteomes": 16, "short_name": "DUF6410", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19948", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001396) is described by MIBiG as an example of the following biosynthetic class, polyketide, in particular the aldgamycin J biosynthetic gene cluster from Streptomyces sp. A1(2016) [[cite:PUB00099444]].", "domain_architectures": 1, "interpro_id": "IPR046311", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF6426)", "partial_evidence_count": null, "pfam_id": "PF19990", "proteins": 17, "proteomes": 17, "short_name": "DUF6426", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19990", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a highly conserved domain of unknown function found in bacteria from the phylum Chloroflexi. This domain contains the motifs ExRFY and WxEG.", "domain_architectures": 1, "interpro_id": "IPR049216", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF6810)", "partial_evidence_count": null, "pfam_id": "PF20650", "proteins": 17, "proteomes": 1, "short_name": "DUF6810", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20650", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a bacterial protein of unknown function.", "domain_architectures": 1, "interpro_id": "IPR054194", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF6899)", "partial_evidence_count": null, "pfam_id": "PF21840", "proteins": 17, "proteomes": 17, "short_name": "DUF6899", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21840", "structures": 0, "taxa": 84, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in SPbeta prophage-derived uncharacterized protein (YomG) from Bacillus subtilis (strain 168). This domain may adopt a FN3-like fold and can be found in association with a prophage endopeptidase tail domain ([pfam:PF06605]).", "domain_architectures": 10, "interpro_id": "IPR055783", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF7359)", "partial_evidence_count": null, "pfam_id": "PF24058", "proteins": 17, "proteomes": 17, "short_name": "DUF7359", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24058", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. Structure prediction shows the proteins form a compact globular domain composed of a four stranded beta sheet, with a strand order of 4-1-2-3 with an alpha helix between strands 3 and 4.", "domain_architectures": 1, "interpro_id": "IPR055796", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF7372)", "partial_evidence_count": null, "pfam_id": "PF24087", "proteins": 17, "proteomes": 17, "short_name": "DUF7372", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24087", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family includes a group of proteins from nematodes.", "domain_architectures": 3, "interpro_id": "IPR055899", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF7476)", "partial_evidence_count": null, "pfam_id": "PF24288", "proteins": 17, "proteomes": 12, "short_name": "DUF7476", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24288", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins. One of these is ORFg found in retron Ec67.", "domain_architectures": 1, "interpro_id": "IPR058400", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8087)", "partial_evidence_count": null, "pfam_id": "PF26332", "proteins": 17, "proteomes": 15, "short_name": "DUF8087", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26332", "structures": 0, "taxa": 68, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins exclusively from Vitrellaceae. It is predicted to adopt an unique alpha/beta structure featuring antiparallel beta-sheet and an alpha-helix nearly orthogonal to the former.", "domain_architectures": 2, "interpro_id": "IPR059318", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8274)", "partial_evidence_count": null, "pfam_id": "PF26910", "proteins": 17, "proteomes": 1, "short_name": "DUF8274", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26910", "structures": 0, "taxa": 9, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Ochrophyta lineage. It is predicted to fold into a structure with a shape of a double barrel. It contains a highly conserved APQFxSxGVGYxRLGDD sequence motif that probably defines an interaction interface. In some proteins, it is found in combination with SAM domain [pfam:PF00536].", "domain_architectures": 3, "interpro_id": "IPR059410", "known_evidence_count": null, "matches": 18, "name": "Domain of unknown function (DUF8366)", "partial_evidence_count": null, "pfam_id": "PF28039", "proteins": 17, "proteomes": 16, "short_name": "DUF8366", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28039", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein found predominantly in Clostridium species. The family is also found in Bacillus phage PBS1, suggesting horizontal gene transfer between bacteria and phage. The function of this protein remains to be determined.", "domain_architectures": 3, "interpro_id": "IPR061617", "known_evidence_count": null, "matches": 25, "name": "Family of unknown function (DUF8547)", "partial_evidence_count": null, "pfam_id": "PF29424", "proteins": 17, "proteomes": 16, "short_name": "DUF8547", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29424", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 100 residues found in Cyanobacteriota, predominantly in Synechococcales. One member of this family has been detected in the exoproteome of Synechococcus, suggesting these proteins may be secreted. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061711", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8650)", "partial_evidence_count": null, "pfam_id": "PF30585", "proteins": 17, "proteomes": 15, "short_name": "DUF8650", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30585", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 70 residues found in Cyanobacteriota, predominantly in Synechococcales. One member is also found in Paulinella, a cercozoan amoeba that possesses a cyanobacterium-derived chromatophore. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061719", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8658)", "partial_evidence_count": null, "pfam_id": "PF30594", "proteins": 17, "proteomes": 17, "short_name": "DUF8658", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30594", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small proteins of approximately 67 residues found in Cyanobacteriota, predominantly in Synechococcales. One member is also found in Paulinella, a cercozoan amoeba that possesses a cyanobacterium-derived chromatophore. Structural analysis indicates these proteins adopt an SH3 barrel-like fold. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061721", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8660)", "partial_evidence_count": null, "pfam_id": "PF30596", "proteins": 17, "proteomes": 17, "short_name": "DUF8660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30596", "structures": 0, "taxa": 54, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 65 residues. The family is restricted to marine picocyanobacteria, including Prochlorococcus, Synechococcus, and Cyanobium species (Synechococcales). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061723", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8662)", "partial_evidence_count": null, "pfam_id": "PF30600", "proteins": 17, "proteomes": 17, "short_name": "DUF8662", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30600", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 60 residues. The family is restricted to marine picocyanobacteria, including Prochlorococcus, Synechococcus, and Cyanobium species (Synechococcales). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061725", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8664)", "partial_evidence_count": null, "pfam_id": "PF30602", "proteins": 17, "proteomes": 17, "short_name": "DUF8664", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30602", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small helical hairpin domain of approximately 48 residues. The family is restricted to marine picocyanobacteria, including Prochlorococcus, Synechococcus, and Cyanobium species (Synechococcales). The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061727", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8666)", "partial_evidence_count": null, "pfam_id": "PF30605", "proteins": 17, "proteomes": 17, "short_name": "DUF8666", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30605", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 67 residues. Some family members are annotated as containing NIF11 or DUF1292 domains, although the functional significance of this is unclear as the family is restricted to marine picocyanobacteria (Prochlorococcus, Synechococcus, and Cyanobium species in Synechococcales), which are not nitrogen-fixing organisms. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061728", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8667)", "partial_evidence_count": null, "pfam_id": "PF30606", "proteins": 17, "proteomes": 17, "short_name": "DUF8667", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30606", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 55 residues found in cyanobacteria, particularly in marine Prochlorococcus species. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061742", "known_evidence_count": null, "matches": 17, "name": "Family of unknown function (DUF8681)", "partial_evidence_count": null, "pfam_id": "PF30631", "proteins": 17, "proteomes": 10, "short_name": "DUF8681", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30631", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal transmembrane domain of approximately 160 residues found in a subset of glycosyltransferase family 2 (GT2) proteins. The domain is predicted to contain four transmembrane helices and is located C-terminal to the catalytic GT2 domain ([pfam:PF00535]). This domain architecture is characteristic of multi-component transmembrane glycosylation systems involved in cell wall polymer modification. This family is found in bacteria, predominantly Bacteroidota, Cyanobacteriota, and Bacillota. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061813", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8752)", "partial_evidence_count": null, "pfam_id": "PF30883", "proteins": 17, "proteomes": 17, "short_name": "DUF8752", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30883", "structures": 0, "taxa": 77, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several repeats of around 30 residues in length which are found specifically in mature-parasite-infected erythrocyte surface antigen proteins from Plasmodium falciparum. This family often found in conjunction with [pfam:PF00226].", "domain_architectures": 5, "interpro_id": "IPR009484", "known_evidence_count": null, "matches": 24, "name": "Repeat of unknown function (DUF1103)", "partial_evidence_count": null, "pfam_id": "PF06513", "proteins": 16, "proteomes": 9, "short_name": "DUF1103", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06513", "structures": 0, "taxa": 114, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as KleB however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR024392", "known_evidence_count": null, "matches": 16, "name": "Protein of unknown function (DUF2688)", "partial_evidence_count": null, "pfam_id": "PF10892", "proteins": 16, "proteomes": 11, "short_name": "DUF2688", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10892", "structures": 0, "taxa": 65, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This protein is found in bacteria. Proteins in this family are typically between 117 to 1154 amino acids in length. This protein has a single completely conserved residue Q that may be functionally important.", "domain_architectures": 4, "interpro_id": "IPR021907", "known_evidence_count": null, "matches": 16, "name": "Protein of unknown function (DUF3519)", "partial_evidence_count": null, "pfam_id": "PF12033", "proteins": 16, "proteomes": 4, "short_name": "DUF3519", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12033", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 50 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR022142", "known_evidence_count": null, "matches": 16, "name": "Protein of unknown function (DUF3673)", "partial_evidence_count": null, "pfam_id": "PF12425", "proteins": 16, "proteomes": 4, "short_name": "DUF3673", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12425", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a bacterial and viral family of uncharacterised proteins.", "domain_architectures": 1, "interpro_id": "IPR025096", "known_evidence_count": null, "matches": 16, "name": "Protein of unknown function (DUF4014)", "partial_evidence_count": null, "pfam_id": "PF13198", "proteins": 16, "proteomes": 15, "short_name": "DUF4014", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13198", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 220 residues in length and is mainly found in various Clostridiales species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032243", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF5044)", "partial_evidence_count": null, "pfam_id": "PF16447", "proteins": 16, "proteomes": 14, "short_name": "DUF5044", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16447", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of Bacteroidetes proteins. The domain lies upstream of a Fasciclin family, [pfam:PF02469].", "domain_architectures": 3, "interpro_id": "IPR033401", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF5108)", "partial_evidence_count": null, "pfam_id": "PF17133", "proteins": 16, "proteomes": 14, "short_name": "DUF5108", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17133", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR035259", "known_evidence_count": null, "matches": 16, "name": "Family of unknown function (DUF5437)", "partial_evidence_count": null, "pfam_id": "PF17505", "proteins": 16, "proteomes": 16, "short_name": "DUF5437", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17505", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of proteins of unknown function found in viruses which appears to contain transmembrane proteins inferred from homology.", "domain_architectures": 1, "interpro_id": "IPR043921", "known_evidence_count": null, "matches": 16, "name": "Family of unknown function (DUF5772)", "partial_evidence_count": null, "pfam_id": "PF19080", "proteins": 16, "proteomes": 14, "short_name": "DUF5772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19080", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000791) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the O-antigen biosynthetic gene cluster from Cronobacter sakazakii [[cite:PUB00099382]].", "domain_architectures": 1, "interpro_id": "IPR045918", "known_evidence_count": null, "matches": 16, "name": "Family of unknown function (DUF6337)", "partial_evidence_count": null, "pfam_id": "PF19863", "proteins": 16, "proteomes": 15, "short_name": "DUF6337", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19863", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in Cyanobacteria. Proteins in this family are typically between 131 and 150 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046684", "known_evidence_count": null, "matches": 16, "name": "Family of unknown function (DUF6554)", "partial_evidence_count": null, "pfam_id": "PF20191", "proteins": 16, "proteomes": 16, "short_name": "DUF6554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20191", "structures": 0, "taxa": 56, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins mainly from Trypanosoma sp. According to structural predictions, this domain is likely to adopt a beta-propeller fold.", "domain_architectures": 3, "interpro_id": "IPR055476", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF7048)", "partial_evidence_count": null, "pfam_id": "PF23126", "proteins": 16, "proteomes": 14, "short_name": "DUF7048", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23126", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small uncharacterised mycobacterial phage domain composed of two alpha helices and three beta strands. The family includes Phage Bxb1 gene 81.", "domain_architectures": 1, "interpro_id": "IPR055883", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF7460)", "partial_evidence_count": null, "pfam_id": "PF24259", "proteins": 16, "proteomes": 16, "short_name": "DUF7460", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24259", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 16, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Saprolegniales lineage. It contains several conserved cysteine residues which are predicted to form disulfide bonds. This domain is frequently found in combination with [pfam:PF00652].", "domain_architectures": 3, "interpro_id": "IPR059332", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF8288)", "partial_evidence_count": null, "pfam_id": "PF26937", "proteins": 16, "proteomes": 8, "short_name": "DUF8288", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26937", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 55 residues found in Cyanobacteriota, predominantly in Synechococcales. Structural analysis indicates this domain adopts an SH3-like barrel fold. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061718", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF8657)", "partial_evidence_count": null, "pfam_id": "PF30593", "proteins": 16, "proteomes": 15, "short_name": "DUF8657", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30593", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 80 to 110 residues. The family is restricted to marine picocyanobacteria, including Prochlorococcus, Synechococcus, and Cyanobium species (Synechococcales). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061722", "known_evidence_count": null, "matches": 16, "name": "Family of unknown function (DUF8661)", "partial_evidence_count": null, "pfam_id": "PF30599", "proteins": 16, "proteomes": 16, "short_name": "DUF8661", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30599", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 58 residues. The family is restricted to marine picocyanobacteria, including Prochlorococcus, Synechococcus, and Cyanobium species (Synechococcales). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061731", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF8670)", "partial_evidence_count": null, "pfam_id": "PF30614", "proteins": 16, "proteomes": 16, "short_name": "DUF8670", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30614", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 80-100 residues found in uncharacterised proteins from marine cyanobacteria, including Prochlorococcus, Synechococcus and Cyanobium species. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061732", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF8671)", "partial_evidence_count": null, "pfam_id": "PF30617", "proteins": 16, "proteomes": 16, "short_name": "DUF8671", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30617", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 140 residues found in cyanobacteria, including Prochlorococcus, Synechococcus and Cyanobium species. It is also found in Paulinella, a eukaryote with a cyanobacterial chromatophore. This domain is consistently found at the N-terminus of proteins containing an Rce1-like domain ([pfam:PF02517]). The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061736", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF8675)", "partial_evidence_count": null, "pfam_id": "PF30621", "proteins": 16, "proteomes": 16, "short_name": "DUF8675", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30621", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an N-terminal domain of approximately 75 residues found in cyanobacteria, including Prochlorococcus, Synechococcus and Cyanobium species. This domain is consistently found at the N-terminus of proteins containing an Rce1-like domain ([pfam:PF02517]). The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061737", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF8676)", "partial_evidence_count": null, "pfam_id": "PF30622", "proteins": 16, "proteomes": 16, "short_name": "DUF8676", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30622", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in proteins mainly from Chlamydomonadales lineage.", "domain_architectures": 3, "interpro_id": "IPR061759", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF8698)", "partial_evidence_count": null, "pfam_id": "PF30708", "proteins": 16, "proteomes": 14, "short_name": "DUF8698", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30708", "structures": 2, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in mycoplasma. It is found at the C-terminal region.", "domain_architectures": 2, "interpro_id": "IPR004306", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF237)", "partial_evidence_count": null, "pfam_id": "PF03072", "proteins": 15, "proteomes": 3, "short_name": "DUF237", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03072", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 4, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in mycoplasma. It is found at the N-terminal region.", "domain_architectures": 2, "interpro_id": "IPR004319", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF240)", "partial_evidence_count": null, "pfam_id": "PF03086", "proteins": 15, "proteomes": 3, "short_name": "DUF240", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03086", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "These conserved ORFs probably are probably not translated into protein [Personal communication, Val Wood].", "domain_architectures": 1, "interpro_id": "IPR007414", "known_evidence_count": null, "matches": 15, "name": "Protein of unknown function (DUF468)", "partial_evidence_count": null, "pfam_id": "PF04318", "proteins": 15, "proteomes": 3, "short_name": "DUF468", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04318", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Fijivirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR010521", "known_evidence_count": null, "matches": 15, "name": "Protein of unknown function (DUF1101)", "partial_evidence_count": null, "pfam_id": "PF06503", "proteins": 15, "proteomes": 7, "short_name": "DUF1101", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06503", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 3 } }, "demotion_reasons": [], "description": "This family of proteins includes the uncharacterized protein MJ0366 from Methanocaldococcus jannaschii and similar proteins predominantly found in Methanococci. This protein adopts the 3-1 trefoil knot conformation [[cite:PUB00100668]].", "domain_architectures": 1, "interpro_id": "IPR024254", "known_evidence_count": null, "matches": 15, "name": "Protein of unknown function (DUF2540)", "partial_evidence_count": null, "pfam_id": "PF10802", "proteins": 15, "proteomes": 10, "short_name": "DUF2540", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10802", "structures": 1, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Rhodopseudomonas.", "domain_architectures": 1, "interpro_id": "IPR021599", "known_evidence_count": null, "matches": 15, "name": "Protein of unknown function (DUF3222)", "partial_evidence_count": null, "pfam_id": "PF11519", "proteins": 15, "proteomes": 14, "short_name": "DUF3222", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11519", "structures": 1, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 240 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032220", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF5039)", "partial_evidence_count": null, "pfam_id": "PF16442", "proteins": 15, "proteomes": 15, "short_name": "DUF5039", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16442", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of C-terminal of several uncharacterized proteins around 500 residues in length and is mainly found in various Faecalibacterium species. The function of this family is unknown. This family has distant similarity to WD40 repeats.", "domain_architectures": 1, "interpro_id": "IPR032491", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF5046)", "partial_evidence_count": null, "pfam_id": "PF16465", "proteins": 15, "proteomes": 15, "short_name": "DUF5046", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16465", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Human papillomavirus.", "domain_architectures": 1, "interpro_id": "IPR035154", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF5472)", "partial_evidence_count": null, "pfam_id": "PF17566", "proteins": 15, "proteomes": 2, "short_name": "DUF5472", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17566", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040864", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF5553)", "partial_evidence_count": null, "pfam_id": "PF17707", "proteins": 15, "proteomes": 12, "short_name": "DUF5553", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17707", "structures": 0, "taxa": 76, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a highly conserved domain found in various Platyhelminthes. Its function is currently unknown.", "domain_architectures": 3, "interpro_id": "IPR044040", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF5744)", "partial_evidence_count": null, "pfam_id": "PF19015", "proteins": 15, "proteomes": 4, "short_name": "DUF5744", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19015", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001130) is described by MIBiG as an example of the following biosynthetic classes, NRP (non-ribosomal peptide) and polyketide, in particular the fabclavine Ia biosynthetic gene cluster from Xenorhabdus budapestensis [[cite:PUB00099452]].", "domain_architectures": 1, "interpro_id": "IPR045928", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF6347)", "partial_evidence_count": null, "pfam_id": "PF19874", "proteins": 15, "proteomes": 15, "short_name": "DUF6347", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19874", "structures": 0, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000385) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide), in particular the lysobactin biosynthetic gene cluster from Lysobacter sp. ATCC 53042 [[cite:PUB00098898]].", "domain_architectures": 2, "interpro_id": "IPR045656", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF6393)", "partial_evidence_count": null, "pfam_id": "PF19930", "proteins": 15, "proteomes": 14, "short_name": "DUF6393", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19930", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in a group of uncharacterised sequences from bacteria. According to structure predictions, this domain is found towards the C-terminal, after a glycosyltransferase domain ([pfam:PF13231]), and it may adopt an alpha/beta structure. In some instances, this domain is followed by and all-beta domain at the very C-terminal of the sequences ([pfam:PF23157]). The function of this domain is unknown.", "domain_architectures": 4, "interpro_id": "IPR055484", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF7056)", "partial_evidence_count": null, "pfam_id": "PF23158", "proteins": 15, "proteomes": 15, "short_name": "DUF7056", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23158", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small uncharacterised family of mycobacterial phage proteins. The family includes gene 71 from phage Bxb1 [swissprot:Q9B050]. Structure prediction suggests this protein may form a pair of alpha helices that form a helical hairpin structure.", "domain_architectures": 1, "interpro_id": "IPR055884", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF7461)", "partial_evidence_count": null, "pfam_id": "PF24260", "proteins": 15, "proteomes": 15, "short_name": "DUF7461", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24260", "structures": 0, "taxa": 56, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised bacterial proteins.", "domain_architectures": 1, "interpro_id": "IPR056129", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF7712)", "partial_evidence_count": null, "pfam_id": "PF24822", "proteins": 15, "proteomes": 15, "short_name": "DUF7712", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24822", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain found in a family of uncharacterised halobacterial species. The predicted structure shows structural similarity to ribonuclease HII suggesting it may act as a nuclease enzyme.", "domain_architectures": 1, "interpro_id": "IPR058516", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8203)", "partial_evidence_count": null, "pfam_id": "PF26630", "proteins": 15, "proteomes": 14, "short_name": "DUF8203", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26630", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found exclusively in uncharacterised proteins from Legionellales species. It contains several highly conserved cysteine residues which are predicted to form disulfide bonds. It is composed of two repeats predicted to consist of a small three-stranded antiparallel beta-sheet and an alpha-helix packed on it.", "domain_architectures": 1, "interpro_id": "IPR059305", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8261)", "partial_evidence_count": null, "pfam_id": "PF26789", "proteins": 15, "proteomes": 14, "short_name": "DUF8261", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26789", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Spragueidae lineage. It contains conserved GYIYY sequence motif that may be related to function.", "domain_architectures": 1, "interpro_id": "IPR059333", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8289)", "partial_evidence_count": null, "pfam_id": "PF26938", "proteins": 15, "proteomes": 1, "short_name": "DUF8289", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26938", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised archaeal proteins. It is predicted to fold into a beta-sandwich structure decorated with alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR059406", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8362)", "partial_evidence_count": null, "pfam_id": "PF27819", "proteins": 15, "proteomes": 14, "short_name": "DUF8362", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27819", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of approximately 90 residues found in putative transcriptional regulators from Cyanobacteriota. The proteins containing this domain are annotated as XRE family or HTH Cro/C1-type regulators. The function of this domain remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061706", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8645)", "partial_evidence_count": null, "pfam_id": "PF30578", "proteins": 15, "proteomes": 15, "short_name": "DUF8645", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30578", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 58 residues. The family is restricted to marine picocyanobacteria, including Prochlorococcus, Synechococcus, and Cyanobium species (Synechococcales). The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061726", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8665)", "partial_evidence_count": null, "pfam_id": "PF30603", "proteins": 15, "proteomes": 15, "short_name": "DUF8665", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30603", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins of approximately 150 residues found in marine cyanobacteria, including Prochlorococcus, Synechococcus and Cyanobium species. Some members are predicted to be membrane-associated. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061733", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF8672)", "partial_evidence_count": null, "pfam_id": "PF30618", "proteins": 15, "proteomes": 15, "short_name": "DUF8672", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30618", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 75 residues found in marine cyanobacteria, including Prochlorococcus and Cyanobium species. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061734", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF8673)", "partial_evidence_count": null, "pfam_id": "PF30619", "proteins": 15, "proteomes": 14, "short_name": "DUF8673", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30619", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 80 residues found in marine cyanobacteria, including Prochlorococcus, Synechococcus and Cyanobium species. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061735", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8674)", "partial_evidence_count": null, "pfam_id": "PF30620", "proteins": 15, "proteomes": 15, "short_name": "DUF8674", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30620", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 50 residues found in marine cyanobacteria, including Prochlorococcus, Synechococcus and Cyanobium species. It is also found in Paulinella, a eukaryote with a cyanobacterial chromatophore. Some members are predicted to be membrane-associated. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061738", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF8677)", "partial_evidence_count": null, "pfam_id": "PF30623", "proteins": 15, "proteomes": 15, "short_name": "DUF8677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30623", "structures": 0, "taxa": 50, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 80 residues found in cyanobacteria, particularly in marine Prochlorococcus species. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061739", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF8678)", "partial_evidence_count": null, "pfam_id": "PF30628", "proteins": 15, "proteomes": 14, "short_name": "DUF8678", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30628", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 42 residues found in cyanobacteria, particularly in marine Prochlorococcus species. This domain is typically located in the C-terminal region of proteins. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061740", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8679)", "partial_evidence_count": null, "pfam_id": "PF30629", "proteins": 15, "proteomes": 15, "short_name": "DUF8679", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30629", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a conserved domain of approximately 125 residues found in cyanobacteria, particularly in marine Prochlorococcus species. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061741", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8680)", "partial_evidence_count": null, "pfam_id": "PF30630", "proteins": 15, "proteomes": 15, "short_name": "DUF8680", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30630", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of approximately 45 residues found in cyanobacteria, particularly in marine Prochlorococcus species. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061743", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8682)", "partial_evidence_count": null, "pfam_id": "PF30633", "proteins": 15, "proteomes": 15, "short_name": "DUF8682", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30633", "structures": 0, "taxa": 43, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins.", "domain_architectures": 8, "interpro_id": "IPR061795", "known_evidence_count": null, "matches": 15, "name": "Domain of unknown function (DUF8734)", "partial_evidence_count": null, "pfam_id": "PF30781", "proteins": 15, "proteomes": 11, "short_name": "DUF8734", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30781", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Protein of unknown function found in Lactococcus lactis bacteriophages.", "domain_architectures": 2, "interpro_id": "IPR007020", "known_evidence_count": null, "matches": 15, "name": "Protein of unknown function (DUF658)", "partial_evidence_count": null, "pfam_id": "PF04936", "proteins": 14, "proteomes": 10, "short_name": "DUF658", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04936", "structures": 0, "taxa": 72, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain, approximately 130 residues in length, is mainly found in several uncharacterized proteins around 340 residues in Actinobacteria, Cyanobacteria and Metazoa species. It is mainly composed of antiparallel beta sheets and has a cystatin-like fold, but the specific function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032596", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF4904)", "partial_evidence_count": null, "pfam_id": "PF16247", "proteins": 14, "proteomes": 13, "short_name": "DUF4904", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16247", "structures": 1, "taxa": 64, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 250 residues in length and is mainly found in various Thermotoga species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032548", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF4940)", "partial_evidence_count": null, "pfam_id": "PF16298", "proteins": 14, "proteomes": 14, "short_name": "DUF4940", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16298", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 200 in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032214", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF5033)", "partial_evidence_count": null, "pfam_id": "PF16436", "proteins": 14, "proteomes": 14, "short_name": "DUF5033", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16436", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a domain of unknown function found in Gammaproteobacteria such as Haemophilus influenzae.", "domain_architectures": 1, "interpro_id": "IPR035360", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF5420)", "partial_evidence_count": null, "pfam_id": "PF17457", "proteins": 14, "proteomes": 14, "short_name": "DUF5420", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17457", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR020261", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF5493)", "partial_evidence_count": null, "pfam_id": "PF17597", "proteins": 14, "proteomes": 13, "short_name": "DUF5493", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17597", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses which apparently has N-acetyltransferase activity.", "domain_architectures": 1, "interpro_id": "IPR043905", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF5771)", "partial_evidence_count": null, "pfam_id": "PF19075", "proteins": 14, "proteomes": 14, "short_name": "DUF5771", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19075", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000616) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046013", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF5970)", "partial_evidence_count": null, "pfam_id": "PF19395", "proteins": 14, "proteomes": 14, "short_name": "DUF5970", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19395", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000332) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide). This family includes a protein from the cyanopeptolin biosynthetic gene cluster from Microcystis sp. NIVA-CYA 172/5 and appears to be predominantly found in Cyanobacteria [[cite:PUB00099392]].", "domain_architectures": 1, "interpro_id": "IPR046056", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF6014)", "partial_evidence_count": null, "pfam_id": "PF19477", "proteins": 14, "proteomes": 13, "short_name": "DUF6014", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19477", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a WH-like domain (PDB:4ro3) found at the N-terminal of an uncharacterised protein from Vibrio cholerae ([swissprot:M1RHE3]), whose function is unknown. This domain is also found in phage proteins.", "domain_architectures": 2, "interpro_id": "IPR054027", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF6945)", "partial_evidence_count": null, "pfam_id": "PF22182", "proteins": 14, "proteomes": 13, "short_name": "DUF6945", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22182", "structures": 1, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a C-terminal domain of a functionally unknown conserved protein from Bacillus anthracis (PDB:4fca).", "domain_architectures": 6, "interpro_id": "IPR054260", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF6991)", "partial_evidence_count": null, "pfam_id": "PF22501", "proteins": 14, "proteomes": 12, "short_name": "DUF6991", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22501", "structures": 2, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function mostly found in organisms within the Trypanosoma genus. This domain adopt a multiple helical bundle fold.", "domain_architectures": 3, "interpro_id": "IPR055479", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF7051)", "partial_evidence_count": null, "pfam_id": "PF23136", "proteins": 14, "proteomes": 13, "short_name": "DUF7051", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23136", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. Structure prediction suggests that this protein dimerises.", "domain_architectures": 1, "interpro_id": "IPR055798", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF7374)", "partial_evidence_count": null, "pfam_id": "PF24089", "proteins": 14, "proteomes": 14, "short_name": "DUF7374", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24089", "structures": 0, "taxa": 51, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins from a set of mycobacterial phage including phage Bxb1 (gene 86). The members of the family range in length from 50 to 90 residues. Structurally, the domain shows some weak similarity to the N-terminal domain of IF5, which adopts an SH3 like barrel fold.", "domain_architectures": 1, "interpro_id": "IPR055877", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF7454)", "partial_evidence_count": null, "pfam_id": "PF24253", "proteins": 14, "proteomes": 14, "short_name": "DUF7454", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24253", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt a three alpha-helical bundle. It is usually found in combination with [pfam:PF23916].", "domain_architectures": 4, "interpro_id": "IPR057677", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF7917)", "partial_evidence_count": null, "pfam_id": "PF25528", "proteins": 14, "proteomes": 12, "short_name": "DUF7917", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25528", "structures": 2, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea. The proteins are predominantly found in the Halobacteria class, including genera such as Halostagnicola, Natrialbaceae, and Halobacteriales. The domain is approximately 100-130 amino acids in length. This domain is a small putative zinc binding domain that is found C-terminal to a putative toxin-like domain [pfam:PF26442].", "domain_architectures": 2, "interpro_id": "IPR058435", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF8122)", "partial_evidence_count": null, "pfam_id": "PF26443", "proteins": 14, "proteomes": 13, "short_name": "DUF8122", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26443", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in uncharacterised proteins from beta-proteobacteria. It is predicted to fold into a beta-barrel-like structure. This domain is frequently found associated with [pfam:PF07589] (PEP-CTERM).", "domain_architectures": 1, "interpro_id": "IPR058500", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF8187)", "partial_evidence_count": null, "pfam_id": "PF26598", "proteins": 14, "proteomes": 14, "short_name": "DUF8187", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26598", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from proteobacteria. It is predicted to fold into a mainly alpha-helical structure and is frequently found in combination with PKD or GEVED domains.", "domain_architectures": 6, "interpro_id": "IPR059344", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF8300)", "partial_evidence_count": null, "pfam_id": "PF26952", "proteins": 14, "proteomes": 12, "short_name": "DUF8300", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26952", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an unique alpha/beta structure composed of a curved beta-sheet that wraps around a central alpha-helix.", "domain_architectures": 1, "interpro_id": "IPR059371", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF8327)", "partial_evidence_count": null, "pfam_id": "PF27006", "proteins": 14, "proteomes": 14, "short_name": "DUF8327", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27006", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Agaricales lineage. It is predicted to fold into an alpha/beta structure composed of a small three-stranded beta-sheet and array of alpha-helices. This domain contains a highly conserved FGCWY sequence motif that may be important for function.", "domain_architectures": 1, "interpro_id": "IPR059402", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF8358)", "partial_evidence_count": null, "pfam_id": "PF27625", "proteins": 14, "proteomes": 2, "short_name": "DUF8358", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27625", "structures": 0, "taxa": 19, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 14, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from Methanobacteria.", "domain_architectures": 2, "interpro_id": "IPR061662", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF8601)", "partial_evidence_count": null, "pfam_id": "PF29890", "proteins": 14, "proteomes": 14, "short_name": "DUF8601", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29890", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of small uncharacterised proteins of approximately 60 residues. Some family members are annotated as containing NIF11 domains, although the functional significance of this is unclear as the family is restricted to marine picocyanobacteria (Prochlorococcus, Synechococcus, and Cyanobium species in Synechococcales), which are not nitrogen-fixing organisms. The function of this family remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061730", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF8669)", "partial_evidence_count": null, "pfam_id": "PF30608", "proteins": 14, "proteomes": 14, "short_name": "DUF8669", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30608", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins of around 120 residues in length which are found specifically in Trypanosoma brucei. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009566", "known_evidence_count": null, "matches": 13, "name": "Protein of unknown function (DUF1181)", "partial_evidence_count": null, "pfam_id": "PF06680", "proteins": 13, "proteomes": 1, "short_name": "DUF1181", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06680", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Cyanobacteria.", "domain_architectures": 1, "interpro_id": "IPR021453", "known_evidence_count": null, "matches": 13, "name": "Protein of unknown function (DUF3104)", "partial_evidence_count": null, "pfam_id": "PF11302", "proteins": 13, "proteomes": 10, "short_name": "DUF3104", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11302", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Based on Bacteroides thetaiotaomicron gene BT_0594, a putative uncharacterised protein. As seen in gene expression experiments (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE2231), it appears to be upregulated in the presence of host or vs when in culture [[cite:PUB00056011],[cite:PUB00056012]]", "domain_architectures": 1, "interpro_id": "IPR025186", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function, B. Theta Gene description (DUF4119)", "partial_evidence_count": null, "pfam_id": "PF13494", "proteins": 13, "proteomes": 12, "short_name": "DUF4119", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13494", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 300 residues in length and is mainly found in various Thermotoga species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032547", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function (DUF4941)", "partial_evidence_count": null, "pfam_id": "PF16299", "proteins": 13, "proteomes": 13, "short_name": "DUF4941", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16299", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR031990", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function (DUF5066)", "partial_evidence_count": null, "pfam_id": "PF16728", "proteins": 13, "proteomes": 13, "short_name": "DUF5066", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16728", "structures": 1, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Varicellovirus.", "domain_architectures": 1, "interpro_id": "IPR035264", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF5434)", "partial_evidence_count": null, "pfam_id": "PF17502", "proteins": 13, "proteomes": 8, "short_name": "DUF5434", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17502", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterobacterales.", "domain_architectures": 1, "interpro_id": "IPR020298", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF5444)", "partial_evidence_count": null, "pfam_id": "PF17519", "proteins": 13, "proteomes": 12, "short_name": "DUF5444", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17519", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterobacteria phage T7.", "domain_architectures": 1, "interpro_id": "IPR035178", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF5466)", "partial_evidence_count": null, "pfam_id": "PF17554", "proteins": 13, "proteomes": 11, "short_name": "DUF5466", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17554", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 2, "interpro_id": "IPR040863", "known_evidence_count": null, "matches": 15, "name": "Family of unknown function (DUF5554)", "partial_evidence_count": null, "pfam_id": "PF17709", "proteins": 13, "proteomes": 12, "short_name": "DUF5554", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17709", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Homo sapiens.", "domain_architectures": 1, "interpro_id": "IPR041059", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF5558)", "partial_evidence_count": null, "pfam_id": "PF17713", "proteins": 13, "proteomes": 11, "short_name": "DUF5558", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17713", "structures": 0, "taxa": 62, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function appears to be primarily restricted to mimiviridae and phycodnaviridae. This entry may be found at the N terminus of longer proteins, which contain a C-terminal DNA polymerase family domain and a DNA polymerase family B exonuclease domain.", "domain_architectures": 3, "interpro_id": "IPR043929", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF5755)", "partial_evidence_count": null, "pfam_id": "PF19059", "proteins": 13, "proteomes": 11, "short_name": "DUF5755", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19059", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 200 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046602", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF6661)", "partial_evidence_count": null, "pfam_id": "PF20366", "proteins": 13, "proteomes": 13, "short_name": "DUF6661", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20366", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This presumed domain is found at the C terminus of Uncharacterized protein AF_2093 from Archaeoglobus fulgidus and similar proteins of unknown function from archaea.", "domain_architectures": 2, "interpro_id": "IPR049265", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function (DUF6834), C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20755", "proteins": 13, "proteomes": 13, "short_name": "DUF6834_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20755", "structures": 1, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Enterobacterales. It is predicted to fold into a beta-barrel.", "domain_architectures": 1, "interpro_id": "IPR056667", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function (DUF7765)", "partial_evidence_count": null, "pfam_id": "PF24958", "proteins": 13, "proteomes": 13, "short_name": "DUF7765", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24958", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Parachela species. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds.", "domain_architectures": 2, "interpro_id": "IPR059325", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function (DUF8281)", "partial_evidence_count": null, "pfam_id": "PF26930", "proteins": 13, "proteomes": 2, "short_name": "DUF8281", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26930", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Clostridia lineage. It is predicted to fold into a globular structure with a beta-sandwich topology.", "domain_architectures": 1, "interpro_id": "IPR059349", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function (DUF8305)", "partial_evidence_count": null, "pfam_id": "PF26969", "proteins": 13, "proteomes": 13, "short_name": "DUF8305", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26969", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small protein found in bacteriophages that infect Firmicutes, particularly Clostridium species. Members of this family are approximately 85 amino acids in length and appear to be single domain proteins. The family is also found in some bacterial genomes, likely derived from integrated prophages. The function of this protein remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061615", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF8545)", "partial_evidence_count": null, "pfam_id": "PF29421", "proteins": 13, "proteomes": 13, "short_name": "DUF8545", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29421", "structures": 0, "taxa": 49, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain of approximately 35 residues found in cyanobacteria, including Prochlorococcus and Synechococcus species. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061744", "known_evidence_count": null, "matches": 13, "name": "Domain of unknown function (DUF8683)", "partial_evidence_count": null, "pfam_id": "PF30634", "proteins": 13, "proteomes": 13, "short_name": "DUF8683", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30634", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a group of uncharacterised proteins from proteobacteria. Members are annotated as lipoproteins.", "domain_architectures": 1, "interpro_id": "IPR061778", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF8717)", "partial_evidence_count": null, "pfam_id": "PF30740", "proteins": 13, "proteomes": 12, "short_name": "DUF8717", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30740", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a number of repeats of around 34 residues in length. Members of this family seem to be found exclusively in three hypothetical Murid herpesvirus 4 proteins. The function of this family is unknown.", "domain_architectures": 3, "interpro_id": "IPR010871", "known_evidence_count": null, "matches": 31, "name": "Repeat of unknown function (DUF1502)", "partial_evidence_count": null, "pfam_id": "PF07397", "proteins": 12, "proteomes": 9, "short_name": "DUF1502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07397", "structures": 0, "taxa": 105, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several uncharacterised viral proteins from the Marek's disease-like viruses. Members of this family are typically around 400 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010883", "known_evidence_count": null, "matches": 12, "name": "Protein of unknown function (DUF1509)", "partial_evidence_count": null, "pfam_id": "PF07420", "proteins": 12, "proteomes": 6, "short_name": "DUF1509", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07420", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as YxeF however no function is currently known. The family appears to be restricted to Bacillus.", "domain_architectures": 1, "interpro_id": "IPR021664", "known_evidence_count": null, "matches": 12, "name": "Protein of unknown function (DUF3255)", "partial_evidence_count": null, "pfam_id": "PF11631", "proteins": 12, "proteomes": 12, "short_name": "DUF3255", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11631", "structures": 1, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 30 amino acids in length.", "domain_architectures": 9, "interpro_id": "IPR028033", "known_evidence_count": null, "matches": 70, "name": "Domain of unknown function (DUF4462)", "partial_evidence_count": null, "pfam_id": "PF14692", "proteins": 12, "proteomes": 1, "short_name": "DUF4462", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14692", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A small family consists of several uncharacterized proteins around 300 residues in length and is mainly found in various Chloroflexus, Comamonas, Delfitia, Rubrivivax and Roseiflexus species. Several members are annotated as cyanophycin synthetases, but the function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032554", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF4938)", "partial_evidence_count": null, "pfam_id": "PF16292", "proteins": 12, "proteomes": 12, "short_name": "DUF4938", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16292", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of uncharacterised proteins around 370 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 3, "interpro_id": "IPR032511", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF4971)", "partial_evidence_count": null, "pfam_id": "PF16341", "proteins": 12, "proteomes": 12, "short_name": "DUF4971", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16341", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in Bacteroides. Proteins in this family are typically between 500 and 650 amino acids in length.", "domain_architectures": 2, "interpro_id": "IPR032167", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF5003)", "partial_evidence_count": null, "pfam_id": "PF16394", "proteins": 12, "proteomes": 11, "short_name": "DUF5003", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16394", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 100 residues in length and is mainly found in butyrate-producing bacteriums. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032481", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF5055)", "partial_evidence_count": null, "pfam_id": "PF16478", "proteins": 12, "proteomes": 12, "short_name": "DUF5055", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16478", "structures": 0, "taxa": 47, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycoplasmataceae.", "domain_architectures": 1, "interpro_id": "IPR035219", "known_evidence_count": null, "matches": 12, "name": "Family of unknown function (DUF5452)", "partial_evidence_count": null, "pfam_id": "PF17533", "proteins": 12, "proteomes": 12, "short_name": "DUF5452", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17533", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Podoviridae.", "domain_architectures": 1, "interpro_id": "IPR020148", "known_evidence_count": null, "matches": 12, "name": "Family of unknown function (DUF5477)", "partial_evidence_count": null, "pfam_id": "PF17571", "proteins": 12, "proteomes": 10, "short_name": "DUF5477", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17571", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Baculoviridae.", "domain_architectures": 2, "interpro_id": "IPR035120", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF5509)", "partial_evidence_count": null, "pfam_id": "PF17625", "proteins": 12, "proteomes": 12, "short_name": "DUF5509", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17625", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000576) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046017", "known_evidence_count": null, "matches": 12, "name": "Family of unknown function (DUF5974)", "partial_evidence_count": null, "pfam_id": "PF19399", "proteins": 12, "proteomes": 11, "short_name": "DUF5974", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19399", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is found as highly identical tandem repeats in bacterial cell surface proteins associated with Bact_lectin.", "domain_architectures": 12, "interpro_id": "IPR046021", "known_evidence_count": null, "matches": 107, "name": "Family of unknown function (DUF5978)", "partial_evidence_count": null, "pfam_id": "PF19405", "proteins": 12, "proteomes": 7, "short_name": "DUF5978", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19405", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000728) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the capsular polysaccharide biosynthetic gene cluster from Klebsiella pneumoniae subsp. ozaenae [[cite:PUB00099368]].", "domain_architectures": 2, "interpro_id": "IPR045949", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF6369)", "partial_evidence_count": null, "pfam_id": "PF19896", "proteins": 12, "proteomes": 10, "short_name": "DUF6369", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19896", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain predominantly is found in sequences from tailed bacteriophages and proteobacterial prophages, including Pseudomonas phage LUZ7. Its function is unknown.", "domain_architectures": 1, "interpro_id": "IPR049263", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF6833)", "partial_evidence_count": null, "pfam_id": "PF20749", "proteins": 12, "proteomes": 12, "short_name": "DUF6833", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20749", "structures": 1, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found usually twice in a group of uncharacterised bacterial proteins. It shows a four-stranded beta-sheet and two alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR049275", "known_evidence_count": null, "matches": 23, "name": "Domain of unknown function (DUF6854)", "partial_evidence_count": null, "pfam_id": "PF21614", "proteins": 12, "proteomes": 11, "short_name": "DUF6854", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21614", "structures": 1, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. This family includes gene 78 from Phage Bxb1.", "domain_architectures": 1, "interpro_id": "IPR055880", "known_evidence_count": null, "matches": 12, "name": "Family of unknown function (DUF7457)", "partial_evidence_count": null, "pfam_id": "PF24256", "proteins": 12, "proteomes": 12, "short_name": "DUF7457", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24256", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised eukaryotic proteins. It is predicted to fold into Ig-like beta-sandwich.", "domain_architectures": 5, "interpro_id": "IPR055919", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF7496)", "partial_evidence_count": null, "pfam_id": "PF24326", "proteins": 12, "proteomes": 8, "short_name": "DUF7496", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24326", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from a family of uncharacterised proteins in archaea, specifically within the Halobacteria class. The proteins in this family are typically around 116 amino acids in length. They are predicted to be integral membrane proteins, as suggested by the presence of four predicted transmembrane helices.", "domain_architectures": 1, "interpro_id": "IPR058529", "known_evidence_count": null, "matches": 12, "name": "Family of unknown function (DUF8216)", "partial_evidence_count": null, "pfam_id": "PF26651", "proteins": 12, "proteomes": 12, "short_name": "DUF8216", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26651", "structures": 0, "taxa": 39, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Desulfobacterales lineage. It is predicted to fold into an open barrel structure decorated with alpha-helices. It contains a conserved DGRxF sequence motif which may be important for function.", "domain_architectures": 2, "interpro_id": "IPR059338", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF8294)", "partial_evidence_count": null, "pfam_id": "PF26943", "proteins": 12, "proteomes": 12, "short_name": "DUF8294", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26943", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group of uncharacterised sequences from bacteria. It may adopt a Ig-like fold.", "domain_architectures": 2, "interpro_id": "IPR061546", "known_evidence_count": null, "matches": 12, "name": "Domain of unknown function (DUF8476)", "partial_evidence_count": null, "pfam_id": "PF28890", "proteins": 12, "proteomes": 11, "short_name": "DUF8476", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28890", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein domain found in tailed bacteriophages (Caudoviricetes). The domain is approximately 67-87 amino acids in length and can occur as a single copy or be repeated within proteins. The family is also found in the Deinococcus bacterial genome, likely derived from an integrated prophage. The function of this domain remains to be determined.", "domain_architectures": 1, "interpro_id": "IPR061616", "known_evidence_count": null, "matches": 12, "name": "Family of unknown function (DUF8546)", "partial_evidence_count": null, "pfam_id": "PF29423", "proteins": 12, "proteomes": 11, "short_name": "DUF8546", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29423", "structures": 0, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry consists of several hypothetical putative lipoproteins which seem to be found specifically in the bacterium Leptospira interrogans. This entry represents the C-terminal domain which may adopt an alpha/beta fold consisting of four beta-strands decorated with four alpha-helices.", "domain_architectures": 2, "interpro_id": "IPR063026", "known_evidence_count": null, "matches": 12, "name": "DUF1420 C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF29472", "proteins": 12, "proteomes": 7, "short_name": "DUF1420_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29472", "structures": 0, "taxa": 24, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in proteins mainly from Chlamydomonadales lineage.", "domain_architectures": 3, "interpro_id": "IPR061758", "known_evidence_count": null, "matches": 16, "name": "Domain of unknown function (DUF8697)", "partial_evidence_count": null, "pfam_id": "PF30707", "proteins": 12, "proteomes": 11, "short_name": "DUF8697", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF30707", "structures": 2, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Fijivirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009519", "known_evidence_count": null, "matches": 11, "name": "Protein of unknown function (DUF1139)", "partial_evidence_count": null, "pfam_id": "PF06599", "proteins": 11, "proteomes": 5, "short_name": "DUF1139", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06599", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical Lactococcus lactis and related phage proteins of around 75 residues in length. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009848", "known_evidence_count": null, "matches": 11, "name": "Protein of unknown function (DUF1408)", "partial_evidence_count": null, "pfam_id": "PF07193", "proteins": 11, "proteomes": 6, "short_name": "DUF1408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07193", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a hypothetical protein family homologous to Lmo2305 in Bacteriophage A118 systems.", "domain_architectures": 1, "interpro_id": "IPR018916", "known_evidence_count": null, "matches": 11, "name": "Protein of unknown function (DUF2481)", "partial_evidence_count": null, "pfam_id": "PF10654", "proteins": 11, "proteomes": 11, "short_name": "DUF2481", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10654", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This viral family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR022586", "known_evidence_count": null, "matches": 11, "name": "Protein of unknown function (DUF2701)", "partial_evidence_count": null, "pfam_id": "PF10857", "proteins": 11, "proteomes": 10, "short_name": "DUF2701", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10857", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Some members in this family of proteins are annotated as membrane proteins however this cannot be confirmed. Currently, this archaeal family has no known function.", "domain_architectures": 1, "interpro_id": "IPR024504", "known_evidence_count": null, "matches": 11, "name": "Protein of unknown function (DUF3198)", "partial_evidence_count": null, "pfam_id": "PF11433", "proteins": 11, "proteomes": 11, "short_name": "DUF3198", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11433", "structures": 1, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This viral family are possible phage integrase proteins however this cannot be confirmed.", "domain_architectures": 3, "interpro_id": "IPR021672", "known_evidence_count": null, "matches": 11, "name": "Protein of unknown function DUF3258", "partial_evidence_count": null, "pfam_id": "PF11646", "proteins": 11, "proteomes": 11, "short_name": "DUF3258", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11646", "structures": 5, "taxa": 55, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This C-terminal domain is found only on a small subgroup of proteins from Gram-positive Clostridiales that also carry a YARHG domain, [pfam:PF13308].", "domain_architectures": 1, "interpro_id": "IPR028080", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF4454)", "partial_evidence_count": null, "pfam_id": "PF14628", "proteins": 11, "proteomes": 10, "short_name": "DUF4454", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14628", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR031860", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF4754)", "partial_evidence_count": null, "pfam_id": "PF15946", "proteins": 11, "proteomes": 10, "short_name": "DUF4754", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15946", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 300 in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032211", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF5030)", "partial_evidence_count": null, "pfam_id": "PF16433", "proteins": 11, "proteomes": 7, "short_name": "DUF5030", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16433", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 270 in length and is mainly found in various Bacteroides and Parabacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032213", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF5032)", "partial_evidence_count": null, "pfam_id": "PF16435", "proteins": 11, "proteomes": 11, "short_name": "DUF5032", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16435", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This domain of unknown function is found in Poxviridae.", "domain_architectures": 1, "interpro_id": "IPR020320", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5409)", "partial_evidence_count": null, "pfam_id": "PF17421", "proteins": 11, "proteomes": 9, "short_name": "DUF5409", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17421", "structures": 0, "taxa": 38, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR020312", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5497)", "partial_evidence_count": null, "pfam_id": "PF17601", "proteins": 11, "proteomes": 11, "short_name": "DUF5497", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17601", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR040670", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5556)", "partial_evidence_count": null, "pfam_id": "PF17711", "proteins": 11, "proteomes": 11, "short_name": "DUF5556", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17711", "structures": 0, "taxa": 58, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a highly conserved domain of unknown function found in Platyhelminthes, with many of the sequences annotated as being the small conductance calcium-activated potassium channel protein. However, the location suggests that this domain belongs to the intracellular amino terminus of these transmembrane proteins, near the calcium-activated SK potassium channel.", "domain_architectures": 5, "interpro_id": "IPR043787", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5729)", "partial_evidence_count": null, "pfam_id": "PF19000", "proteins": 11, "proteomes": 11, "short_name": "DUF5729", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19000", "structures": 0, "taxa": 41, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in pandoraviruses.", "domain_architectures": 2, "interpro_id": "IPR043884", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5848)", "partial_evidence_count": null, "pfam_id": "PF19166", "proteins": 11, "proteomes": 1, "short_name": "DUF5848", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19166", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Marseillevirus.", "domain_architectures": 1, "interpro_id": "IPR043873", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5858)", "partial_evidence_count": null, "pfam_id": "PF19176", "proteins": 11, "proteomes": 3, "short_name": "DUF5858", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19176", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in Marseillevirus.", "domain_architectures": 1, "interpro_id": "IPR043807", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5869)", "partial_evidence_count": null, "pfam_id": "PF19194", "proteins": 11, "proteomes": 6, "short_name": "DUF5869", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19194", "structures": 0, "taxa": 45, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000178) is described by MIBiG as an example of the following biosynthetic class, polyketide.", "domain_architectures": 1, "interpro_id": "IPR045996", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5952)", "partial_evidence_count": null, "pfam_id": "PF19377", "proteins": 11, "proteomes": 7, "short_name": "DUF5952", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19377", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000571) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046011", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF5967)", "partial_evidence_count": null, "pfam_id": "PF19392", "proteins": 11, "proteomes": 6, "short_name": "DUF5967", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19392", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000700) is described by MIBiG as an example of the following biosynthetic class, saccharide, in particular the istamycin biosynthetic gene cluster from Streptomyces tenjimariensis [[cite:PUB00098957]].", "domain_architectures": 1, "interpro_id": "IPR045952", "known_evidence_count": null, "matches": 11, "name": "Family of unknown function (DUF6372)", "partial_evidence_count": null, "pfam_id": "PF19899", "proteins": 11, "proteomes": 10, "short_name": "DUF6372", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19899", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in a group of uncharacterised sequences from bacteria. According to structure predictions, this domain is found at the C-terminal and may adopt an all-beta structure consisting of eight anti-parallel beta-sheets.. These proteins also have a glycosyltransferase domain at the N-terminal ([pfam:PF13231]).", "domain_architectures": 2, "interpro_id": "IPR055483", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF7055)", "partial_evidence_count": null, "pfam_id": "PF23157", "proteins": 11, "proteomes": 11, "short_name": "DUF7055", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23157", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an uncharacterised protein domain found in a mycobacterial phage proteins. These domains form a zinc binding cluster where 8 cysteine and histidine residues bind two zinc ions according to structure prediction (iPTM=0.87).", "domain_architectures": 1, "interpro_id": "IPR055882", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF7459)", "partial_evidence_count": null, "pfam_id": "PF24258", "proteins": 11, "proteomes": 11, "short_name": "DUF7459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24258", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found in sequences from Strongyloides stercoralis and similar worms. It may adopt a beta-sandwich fold related to MATh domains.", "domain_architectures": 3, "interpro_id": "IPR056658", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF7756)", "partial_evidence_count": null, "pfam_id": "PF24939", "proteins": 11, "proteomes": 5, "short_name": "DUF7756", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24939", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function largely found in the order Bacteroidales. Proteins in this family have a signal peptide or a lipoprotein attachment motif. The domain has an Ig-like fold.", "domain_architectures": 1, "interpro_id": "IPR058490", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF8177)", "partial_evidence_count": null, "pfam_id": "PF26538", "proteins": 11, "proteomes": 11, "short_name": "DUF8177", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26538", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins. Contains several chlamydial members.", "domain_architectures": 2, "interpro_id": "IPR006835", "known_evidence_count": null, "matches": 10, "name": "Protein of unknown function (DUF575)", "partial_evidence_count": null, "pfam_id": "PF04746", "proteins": 10, "proteomes": 3, "short_name": "DUF575", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04746", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family of uncharacterised proteins.", "domain_architectures": 2, "interpro_id": "IPR006850", "known_evidence_count": null, "matches": 10, "name": "Protein of unknown function (DUF562)", "partial_evidence_count": null, "pfam_id": "PF04763", "proteins": 10, "proteomes": 3, "short_name": "DUF562", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04763", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short (27-30aa) porcine and bovine circovirus ORF6 proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR008484", "known_evidence_count": null, "matches": 10, "name": "Circovirus protein of unknown function (DUF765)", "partial_evidence_count": null, "pfam_id": "PF05570", "proteins": 10, "proteomes": 0, "short_name": "DUF765", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05570", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region located towards the C-terminus of a number proteins of unknown function that seem to be specific to Oryza sativa.", "domain_architectures": 3, "interpro_id": "IPR010685", "known_evidence_count": null, "matches": 10, "name": "Protein of unknown function (DUF1263)", "partial_evidence_count": null, "pfam_id": "PF06882", "proteins": 10, "proteomes": 4, "short_name": "DUF1263", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06882", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is found in some prophages found in Lactobacillales lactis ([[cite:PUB00016516]]).", "domain_architectures": 2, "interpro_id": "IPR012450", "known_evidence_count": null, "matches": 10, "name": "Protein of unknown function (DUF1655)", "partial_evidence_count": null, "pfam_id": "PF07868", "proteins": 10, "proteomes": 9, "short_name": "DUF1655", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07868", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family adopt a secondary structure consisting of six alpha helices, with four long helices (alpha1, alpha2, alpha5, alpha6) form a left-handed, antiparallel alpha helical bundle. The function of this family of Archaeal hypothetical proteins has not, as yet, been defined [[cite:PUB00035391]].", "domain_architectures": 1, "interpro_id": "IPR015238", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF1940)", "partial_evidence_count": null, "pfam_id": "PF09155", "proteins": 10, "proteomes": 10, "short_name": "DUF1940", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09155", "structures": 1, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of proteins with unknown function. The structure of one of the proteins in this family has revealed a novel alpha-beta fold [[cite:PUB00039229]].", "domain_architectures": 1, "interpro_id": "IPR018546", "known_evidence_count": null, "matches": 10, "name": "Protein of unknown function (DUF2004)", "partial_evidence_count": null, "pfam_id": "PF09406", "proteins": 10, "proteomes": 9, "short_name": "DUF2004", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09406", "structures": 1, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members in this family of proteins are annotated as UL121 however currently no function is known.", "domain_architectures": 1, "interpro_id": "IPR022545", "known_evidence_count": null, "matches": 10, "name": "Protein of unknown function (DUF2677)", "partial_evidence_count": null, "pfam_id": "PF10838", "proteins": 10, "proteomes": 8, "short_name": "DUF2677", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10838", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This bacterial family of proteins has no known function.", "domain_architectures": 2, "interpro_id": "IPR021571", "known_evidence_count": null, "matches": 10, "name": "Protein of unknown function (DUF3206)", "partial_evidence_count": null, "pfam_id": "PF11472", "proteins": 10, "proteomes": 10, "short_name": "DUF3206", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11472", "structures": 1, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is typically between 310 and 324 amino acids in length. According to structure prediction and comparison (DALI server) it is suggested that it may adopt a metallo-dependent phosphatase fold.", "domain_architectures": 2, "interpro_id": "IPR025123", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF4049)", "partial_evidence_count": null, "pfam_id": "PF13258", "proteins": 10, "proteomes": 5, "short_name": "DUF4049", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13258", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 250 residues in length and is mainly found in various Enterococcus faecalis species. The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR032539", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF4950)", "partial_evidence_count": null, "pfam_id": "PF16308", "proteins": 10, "proteomes": 9, "short_name": "DUF4950", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16308", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family around 300 residues locates in the N-terminal of some uncharacterized proteins in various Bacteroides and Alistipes species. The function of this family remains unknown. This entry contains a duplication of a DUF1735-like domain.", "domain_architectures": 2, "interpro_id": "IPR032152", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF4989)", "partial_evidence_count": null, "pfam_id": "PF16379", "proteins": 10, "proteomes": 10, "short_name": "DUF4989", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16379", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphafusellovirus.", "domain_architectures": 1, "interpro_id": "IPR020142", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF5489)", "partial_evidence_count": null, "pfam_id": "PF17592", "proteins": 10, "proteomes": 10, "short_name": "DUF5489", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17592", "structures": 0, "taxa": 36, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Fuselloviridae. Structure analysis suggest a role in viral assembly.", "domain_architectures": 1, "interpro_id": "IPR020507", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF5517)", "partial_evidence_count": null, "pfam_id": "PF17639", "proteins": 10, "proteomes": 9, "short_name": "DUF5517", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17639", "structures": 1, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 3, "interpro_id": "IPR041435", "known_evidence_count": null, "matches": 14, "name": "Family of unknown function (DUF5552)", "partial_evidence_count": null, "pfam_id": "PF17706", "proteins": 10, "proteomes": 10, "short_name": "DUF5552", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17706", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 2, "interpro_id": "IPR040620", "known_evidence_count": null, "matches": 13, "name": "Family of unknown function (DUF5560)", "partial_evidence_count": null, "pfam_id": "PF17715", "proteins": 10, "proteomes": 10, "short_name": "DUF5560", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17715", "structures": 0, "taxa": 63, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function predicted to be a carbohydrate binding module [[cite:PUB00091246]].", "domain_architectures": 5, "interpro_id": "IPR040753", "known_evidence_count": null, "matches": 17, "name": "Domain of unknown function (DUF5620)", "partial_evidence_count": null, "pfam_id": "PF18522", "proteins": 10, "proteomes": 4, "short_name": "DUF5620", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18522", "structures": 3, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a highly conserved domain of unknown function found in Platyhelminthes, with many of the sequences annotated as being the small conductance calcium-activated potassium channel protein. However, the location suggests that this domain belongs to the intracellular amino terminus of these transmembrane proteins, immediately next to the calcium-activated SK potassium channel.", "domain_architectures": 4, "interpro_id": "IPR043786", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF5728)", "partial_evidence_count": null, "pfam_id": "PF18999", "proteins": 10, "proteomes": 10, "short_name": "DUF5728", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18999", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function is associated with the biosynthetic gene cluster for enterocin A.", "domain_architectures": 1, "interpro_id": "IPR043892", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF5841)", "partial_evidence_count": null, "pfam_id": "PF19159", "proteins": 10, "proteomes": 6, "short_name": "DUF5841", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19159", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins predominantly found in viruses which is apparently a Putative RNA methyltransferase.", "domain_architectures": 1, "interpro_id": "IPR045409", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF5891)", "partial_evidence_count": null, "pfam_id": "PF19241", "proteins": 10, "proteomes": 10, "short_name": "DUF5891", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19241", "structures": 0, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR045421", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF5902)", "partial_evidence_count": null, "pfam_id": "PF19255", "proteins": 10, "proteomes": 1, "short_name": "DUF5902", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19255", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000069) is described by MIBiG as an example of the following biosynthetic class, polyketide. It includes a member from the gephyronic acid biosynthetic gene cluster from Archangium violaceum Cb vi76 and appears to be predominantly found in bacteria [[cite:PUB00099412]].", "domain_architectures": 1, "interpro_id": "IPR046091", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF6109)", "partial_evidence_count": null, "pfam_id": "PF19604", "proteins": 10, "proteomes": 9, "short_name": "DUF6109", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19604", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an alpha helical bundle domain found at the N-terminus of a small group of putative bacterial toxins. The function of this domain is unknown.", "domain_architectures": 2, "interpro_id": "IPR049196", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF6863)", "partial_evidence_count": null, "pfam_id": "PF21727", "proteins": 10, "proteomes": 10, "short_name": "DUF6863", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21727", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised mycobacterial phage proteins. The family includes gene 82 from mycobacterial phage Bxb1.", "domain_architectures": 1, "interpro_id": "IPR055886", "known_evidence_count": null, "matches": 10, "name": "Family of unknown function (DUF7463)", "partial_evidence_count": null, "pfam_id": "PF24262", "proteins": 10, "proteomes": 10, "short_name": "DUF7463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24262", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents the N-terminal domain found in a small family of uncharacterised bacillus proteins. Structure prediction suggest this domain might mediate homodimerisation. It is composed of a small three stranded beta sheet with an alpha helix found between strands 1 and 2.", "domain_architectures": 1, "interpro_id": "IPR058401", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF8088)", "partial_evidence_count": null, "pfam_id": "PF26338", "proteins": 10, "proteomes": 9, "short_name": "DUF8088", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26338", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to adopt mainly alpha-helical structure flanked with a beta-hairpin.", "domain_architectures": 3, "interpro_id": "IPR059350", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF8306)", "partial_evidence_count": null, "pfam_id": "PF26972", "proteins": 10, "proteomes": 10, "short_name": "DUF8306", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26972", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Planctomycetia. It contains four invariant cysteine residues which may be involved in metal coordination.", "domain_architectures": 2, "interpro_id": "IPR059396", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF8352)", "partial_evidence_count": null, "pfam_id": "PF27617", "proteins": 10, "proteomes": 9, "short_name": "DUF8352", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27617", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from double-stranded DNA viruses. It is predicted to fold into a globular structure with a complex topology.", "domain_architectures": 2, "interpro_id": "IPR059404", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF8360)", "partial_evidence_count": null, "pfam_id": "PF27647", "proteins": 10, "proteomes": 10, "short_name": "DUF8360", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27647", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Actinomycetes. It contains highly conserved cysteine and histidine residues that may be involved in metal coordination.", "domain_architectures": 1, "interpro_id": "IPR059452", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF8408)", "partial_evidence_count": null, "pfam_id": "PF28467", "proteins": 10, "proteomes": 10, "short_name": "DUF8408", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28467", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial proteins found in Escherichia coli and Citrobacter rodentium. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009490", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF1106)", "partial_evidence_count": null, "pfam_id": "PF06523", "proteins": 9, "proteomes": 3, "short_name": "DUF1106", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06523", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short Lactococcus lactis and bacteriophage proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009503", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF1125)", "partial_evidence_count": null, "pfam_id": "PF06563", "proteins": 9, "proteomes": 3, "short_name": "DUF1125", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06563", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This viral family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR024322", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF2682)", "partial_evidence_count": null, "pfam_id": "PF10909", "proteins": 9, "proteomes": 9, "short_name": "DUF2682", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10909", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins have no known function but appear to be restricted to phage.", "domain_architectures": 1, "interpro_id": "IPR020112", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF2883)", "partial_evidence_count": null, "pfam_id": "PF11097", "proteins": 9, "proteomes": 9, "short_name": "DUF2883", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11097", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This viral family of proteins has no known function.", "domain_architectures": 1, "interpro_id": "IPR021411", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF3051)", "partial_evidence_count": null, "pfam_id": "PF11252", "proteins": 9, "proteomes": 3, "short_name": "DUF3051", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11252", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This archaeal family of proteins has no known function. This entry represents the N-terminal ferredoxin-like domain.", "domain_architectures": 2, "interpro_id": "IPR021540", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF3195) N-terminal domain", "partial_evidence_count": null, "pfam_id": "PF11424", "proteins": 9, "proteomes": 9, "short_name": "DUF3195", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11424", "structures": 1, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Mycoplasma and Ruminococcus spp. The structure of Uncharacterized protein MG376 homolog from Mycoplasma pneumoniae shows an OB fold with six beta-strands and three loops forming a beta-barrel that is capped by one alpha-helix [[cite:PUB00041476]]. Its specific function is still unknown.", "domain_architectures": 1, "interpro_id": "IPR024506", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF3217)", "partial_evidence_count": null, "pfam_id": "PF11506", "proteins": 9, "proteomes": 9, "short_name": "DUF3217", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11506", "structures": 1, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR031773", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF4741)", "partial_evidence_count": null, "pfam_id": "PF15897", "proteins": 9, "proteomes": 9, "short_name": "DUF4741", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15897", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins is functionally uncharacterised. This family is found in various Bacteroides species. Proteins in this family are around 630 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR032182", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF5014)", "partial_evidence_count": null, "pfam_id": "PF16406", "proteins": 9, "proteomes": 7, "short_name": "DUF5014", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16406", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in primates.", "domain_architectures": 1, "interpro_id": "IPR041422", "known_evidence_count": null, "matches": 9, "name": "Family of unknown function (DUF5545)", "partial_evidence_count": null, "pfam_id": "PF17699", "proteins": 9, "proteomes": 6, "short_name": "DUF5545", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17699", "structures": 0, "taxa": 46, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in Iridoviridae.", "domain_architectures": 1, "interpro_id": "IPR043888", "known_evidence_count": null, "matches": 9, "name": "Family of unknown function (DUF5844)", "partial_evidence_count": null, "pfam_id": "PF19162", "proteins": 9, "proteomes": 9, "short_name": "DUF5844", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19162", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000604) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046012", "known_evidence_count": null, "matches": 9, "name": "Family of unknown function (DUF5969)", "partial_evidence_count": null, "pfam_id": "PF19394", "proteins": 9, "proteomes": 6, "short_name": "DUF5969", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19394", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain of unknown function found at the N-terminal end.", "domain_architectures": 1, "interpro_id": "IPR054244", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF6971)", "partial_evidence_count": null, "pfam_id": "PF22318", "proteins": 9, "proteomes": 9, "short_name": "DUF6971", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22318", "structures": 1, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found N-terminal in a group of uncharacterised proteins from Trypanosomes. It has a very weak similarity to the vWA-like domain of the SSL1 subunit of general transcription and DNA repair factor IIH and it is predicted to adopt a structure with similarity to known vWA-like domains.", "domain_architectures": 1, "interpro_id": "IPR055587", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF7163)", "partial_evidence_count": null, "pfam_id": "PF23734", "proteins": 9, "proteomes": 8, "short_name": "DUF7163", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23734", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found at the C-terminal of SPbeta prophage-derived uncharacterized protein YomG from Bacillus subtilis (strain 168). This domain may be found in association with a prophage endopeptidase tail domain ([pfam:PF06605]).", "domain_architectures": 3, "interpro_id": "IPR055785", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF7361)", "partial_evidence_count": null, "pfam_id": "PF24060", "proteins": 9, "proteomes": 9, "short_name": "DUF7361", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24060", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. The family includes the gene 83 from the mycobacterial phage Bxb1 [swissprot:Q9B038]. This family shows structural similarity to [pfam:PF09926]. These proteins have an SH3 like barrel structure.", "domain_architectures": 2, "interpro_id": "IPR055887", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF7464)", "partial_evidence_count": null, "pfam_id": "PF24263", "proteins": 9, "proteomes": 9, "short_name": "DUF7464", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24263", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry found in a small number of phage is uncharacterised. There is some evidence form AlphaFold 3 prediction that these proteins may form homodimers.", "domain_architectures": 1, "interpro_id": "IPR057698", "known_evidence_count": null, "matches": 9, "name": "Phage family of unknown function (DUF7938)", "partial_evidence_count": null, "pfam_id": "PF25604", "proteins": 9, "proteomes": 7, "short_name": "DUF7938", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25604", "structures": 0, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Piroplasmida lineage. It is predicted to fold into alpha helical structure and it is frequently found in combination with [pfam:PF03588].", "domain_architectures": 2, "interpro_id": "IPR059342", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF8298)", "partial_evidence_count": null, "pfam_id": "PF26950", "proteins": 9, "proteomes": 9, "short_name": "DUF8298", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26950", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds. Some proteins contains two copies of this domain.", "domain_architectures": 2, "interpro_id": "IPR059357", "known_evidence_count": null, "matches": 14, "name": "Domain of unknown function (DUF8313)", "partial_evidence_count": null, "pfam_id": "PF26985", "proteins": 9, "proteomes": 2, "short_name": "DUF8313", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26985", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Alveolata lineage. It is predicted to adopt an alpha-helical structure. It contains several conserved positively charged residues predicted to be at the surface.", "domain_architectures": 3, "interpro_id": "IPR059369", "known_evidence_count": null, "matches": 11, "name": "Domain of unknown function (DUF8325)", "partial_evidence_count": null, "pfam_id": "PF27004", "proteins": 9, "proteomes": 9, "short_name": "DUF8325", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27004", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. This domain ids predicted to fold into an alpha/beta structure composed of an antiparallel beta-sheet with array of alpha-helices packed on it.", "domain_architectures": 1, "interpro_id": "IPR059373", "known_evidence_count": null, "matches": 9, "name": "Domain of unknown function (DUF8329)", "partial_evidence_count": null, "pfam_id": "PF27009", "proteins": 9, "proteomes": 8, "short_name": "DUF8329", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27009", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is predicted to fold into an alpha/beta structure composed of a curved beta-sheet with alpha helices on one side. Some proteins contain two copies of this domain.", "domain_architectures": 3, "interpro_id": "IPR059374", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF8330)", "partial_evidence_count": null, "pfam_id": "PF27010", "proteins": 9, "proteomes": 6, "short_name": "DUF8330", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27010", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Family of chloroplast proteins of unknown function. Some members have two copies of the conserved region.", "domain_architectures": 2, "interpro_id": "IPR006851", "known_evidence_count": null, "matches": 11, "name": "Protein of unknown function (DUF613)", "partial_evidence_count": null, "pfam_id": "PF04764", "proteins": 8, "proteomes": 1, "short_name": "DUF613", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04764", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical proteins from Neisseria meningitidis. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009509", "known_evidence_count": null, "matches": 8, "name": "Protein of unknown function (DUF1132)", "partial_evidence_count": null, "pfam_id": "PF06575", "proteins": 8, "proteomes": 6, "short_name": "DUF1132", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06575", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins from Melanoplus sanguinipes entomopoxvirus (MsEPV). The function of this family is unknown.", "domain_architectures": 2, "interpro_id": "IPR010587", "known_evidence_count": null, "matches": 8, "name": "Protein of unknown function (DUF1157)", "partial_evidence_count": null, "pfam_id": "PF06636", "proteins": 8, "proteomes": 4, "short_name": "DUF1157", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06636", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Circovirus proteins of around 35 residues in length. Members of this family are described as ORF-10 proteins and their function is unknown.", "domain_architectures": 1, "interpro_id": "IPR009762", "known_evidence_count": null, "matches": 8, "name": "Protein of unknown function (DUF1331)", "partial_evidence_count": null, "pfam_id": "PF07048", "proteins": 8, "proteomes": 0, "short_name": "DUF1331", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07048", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 270 residues in length and is mainly found in various Clostridiales species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032218", "known_evidence_count": null, "matches": 8, "name": "Domain of unknown function (DUF5037)", "partial_evidence_count": null, "pfam_id": "PF16440", "proteins": 8, "proteomes": 6, "short_name": "DUF5037", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16440", "structures": 1, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is believed to be involved in the type VII secretion system.", "domain_architectures": 2, "interpro_id": "IPR031666", "known_evidence_count": null, "matches": 8, "name": "Domain of unknown function (DUF5084)", "partial_evidence_count": null, "pfam_id": "PF16894", "proteins": 8, "proteomes": 7, "short_name": "DUF5084", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16894", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteria.", "domain_architectures": 1, "interpro_id": "IPR035389", "known_evidence_count": null, "matches": 8, "name": "Domain of unknown function (DUF5411)", "partial_evidence_count": null, "pfam_id": "PF17424", "proteins": 8, "proteomes": 7, "short_name": "DUF5411", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17424", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycoplasma.", "domain_architectures": 1, "interpro_id": "IPR035233", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5443)", "partial_evidence_count": null, "pfam_id": "PF17518", "proteins": 8, "proteomes": 8, "short_name": "DUF5443", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17518", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Epstein-Barr virus.", "domain_architectures": 1, "interpro_id": "IPR035221", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5451)", "partial_evidence_count": null, "pfam_id": "PF17532", "proteins": 8, "proteomes": 5, "short_name": "DUF5451", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17532", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycoplasma. Family members have 4 predicted trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035217", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5453)", "partial_evidence_count": null, "pfam_id": "PF17534", "proteins": 8, "proteomes": 8, "short_name": "DUF5453", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17534", "structures": 0, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Saccharomycetales.", "domain_architectures": 1, "interpro_id": "IPR035145", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5482)", "partial_evidence_count": null, "pfam_id": "PF17579", "proteins": 8, "proteomes": 4, "short_name": "DUF5482", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17579", "structures": 0, "taxa": 48, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR020249", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5492)", "partial_evidence_count": null, "pfam_id": "PF17596", "proteins": 8, "proteomes": 7, "short_name": "DUF5492", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17596", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Herpesvirus.", "domain_architectures": 1, "interpro_id": "IPR020504", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5500)", "partial_evidence_count": null, "pfam_id": "PF17604", "proteins": 8, "proteomes": 7, "short_name": "DUF5500", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17604", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 8, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function. Family members include the archaeal homolog the bacterial RelB, a toxin-antitoxin system which is activated during amino acid starvation. This family is mostly found in thermococcus archaea [[cite:PUB00038109]].", "domain_architectures": 1, "interpro_id": "IPR043706", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5646)", "partial_evidence_count": null, "pfam_id": "PF18881", "proteins": 8, "proteomes": 8, "short_name": "DUF5646", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18881", "structures": 1, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "The function of this family of euryarchaeal proteins is unknown. The structure of this protein forms a beta barrel.", "domain_architectures": 1, "interpro_id": "IPR043961", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5749)", "partial_evidence_count": null, "pfam_id": "PF19023", "proteins": 8, "proteomes": 8, "short_name": "DUF5749", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19023", "structures": 1, "taxa": 30, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Marseillevirus.", "domain_architectures": 1, "interpro_id": "IPR045415", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5896)", "partial_evidence_count": null, "pfam_id": "PF19248", "proteins": 8, "proteomes": 3, "short_name": "DUF5896", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19248", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000624) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046019", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF5976)", "partial_evidence_count": null, "pfam_id": "PF19401", "proteins": 8, "proteomes": 4, "short_name": "DUF5976", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19401", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria, and is approximately 100 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046727", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF6619)", "partial_evidence_count": null, "pfam_id": "PF20324", "proteins": 8, "proteomes": 8, "short_name": "DUF6619", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20324", "structures": 0, "taxa": 35, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 358 and 460 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR046608", "known_evidence_count": null, "matches": 8, "name": "Family of unknown function (DUF6667)", "partial_evidence_count": null, "pfam_id": "PF20372", "proteins": 8, "proteomes": 8, "short_name": "DUF6667", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20372", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 10 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in SPbeta prophage-derived uncharacterized protein YomG from Bacillus subtilis (strain 168). This domain may can be found in association with a prophage endopeptidase tail domain ([pfam:PF06605]).", "domain_architectures": 2, "interpro_id": "IPR055784", "known_evidence_count": null, "matches": 8, "name": "Domain of unknown function (DUF7360)", "partial_evidence_count": null, "pfam_id": "PF24059", "proteins": 8, "proteomes": 8, "short_name": "DUF7360", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24059", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists several of several uncharacterised proteins from the bacterium Coxiella burnetii. Coxiella burnetii is the causative agent of the Q fever disease.", "domain_architectures": 2, "interpro_id": "IPR008481", "known_evidence_count": null, "matches": 7, "name": "Coxiella burnetii protein of unknown function (DUF762)", "partial_evidence_count": null, "pfam_id": "PF05555", "proteins": 7, "proteomes": 2, "short_name": "DUF762", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05555", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several proteins of unknown function from Coxiella burnetii (the causative agent of a zoonotic disease called Q fever).", "domain_architectures": 2, "interpro_id": "IPR008525", "known_evidence_count": null, "matches": 7, "name": "Coxiella burnetii protein of unknown function (DUF807)", "partial_evidence_count": null, "pfam_id": "PF05660", "proteins": 7, "proteomes": 4, "short_name": "DUF807", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05660", "structures": 0, "taxa": 27, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several short Circovirus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009373", "known_evidence_count": null, "matches": 7, "name": "Protein of unknown function (DUF1030)", "partial_evidence_count": null, "pfam_id": "PF06270", "proteins": 7, "proteomes": 0, "short_name": "DUF1030", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06270", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several Barley yellow dwarf virus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009426", "known_evidence_count": null, "matches": 7, "name": "Protein of unknown function (DUF1072)", "partial_evidence_count": null, "pfam_id": "PF06380", "proteins": 7, "proteomes": 3, "short_name": "DUF1072", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06380", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several phage and bacterial proteins of around 59 residues in length. Members of this family seem to be found exclusively in Lactococcus lactis and the bacteriophages that infect this organism. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009972", "known_evidence_count": null, "matches": 7, "name": "Protein of unknown function (DUF1497)", "partial_evidence_count": null, "pfam_id": "PF07384", "proteins": 7, "proteomes": 6, "short_name": "DUF1497", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07384", "structures": 0, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "The members of this family are hypothetical proteins expressed by Trypanosoma cruzi, a eukaryotic parasite that causes Chagas' disease in humans. This region is found as multiple copies per protein.", "domain_architectures": 2, "interpro_id": "IPR012457", "known_evidence_count": null, "matches": 9, "name": "Protein of unknown function (DUF1663)", "partial_evidence_count": null, "pfam_id": "PF07909", "proteins": 7, "proteomes": 7, "short_name": "DUF1663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07909", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of Mycoplasma hypothetical proteins adopt a helical structure, with a buried central helix. Their function has not, as yet, been determined.", "domain_architectures": 1, "interpro_id": "IPR015271", "known_evidence_count": null, "matches": 7, "name": "Domain of unknown function (DUF1951)", "partial_evidence_count": null, "pfam_id": "PF09188", "proteins": 7, "proteomes": 7, "short_name": "DUF1951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09188", "structures": 1, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Enterobacteriaceae. This entry may represent a pseudogene [[cite:PUB00159757]].", "domain_architectures": 1, "interpro_id": "IPR020404", "known_evidence_count": null, "matches": 7, "name": "Protein of unknown function (DUF2713)", "partial_evidence_count": null, "pfam_id": "PF10897", "proteins": 7, "proteomes": 7, "short_name": "DUF2713", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10897", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Bordetella.", "domain_architectures": 1, "interpro_id": "IPR021597", "known_evidence_count": null, "matches": 7, "name": "Protein of unknown function (DUF3220)", "partial_evidence_count": null, "pfam_id": "PF11516", "proteins": 7, "proteomes": 5, "short_name": "DUF3220", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11516", "structures": 1, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family consists of several uncharacterised proteins around 540 residues in length and is mainly found in various Bacteroides species. The function of this protein is unknown.", "domain_architectures": 3, "interpro_id": "IPR032512", "known_evidence_count": null, "matches": 7, "name": "Domain of unknown function (DUF4969)", "partial_evidence_count": null, "pfam_id": "PF16339", "proteins": 7, "proteomes": 7, "short_name": "DUF4969", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16339", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 380 in length and is mainly found in Bacteroides fragilis and sp. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032212", "known_evidence_count": null, "matches": 7, "name": "Domain of unknown function (DUF5031)", "partial_evidence_count": null, "pfam_id": "PF16434", "proteins": 7, "proteomes": 7, "short_name": "DUF5031", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16434", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Betanecrovirus.", "domain_architectures": 1, "interpro_id": "IPR035284", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5428)", "partial_evidence_count": null, "pfam_id": "PF17493", "proteins": 7, "proteomes": 3, "short_name": "DUF5428", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17493", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Varicellovirus.", "domain_architectures": 1, "interpro_id": "IPR035262", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5435)", "partial_evidence_count": null, "pfam_id": "PF17503", "proteins": 7, "proteomes": 6, "short_name": "DUF5435", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17503", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Gammaproteobacteria.", "domain_architectures": 1, "interpro_id": "IPR020379", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5448)", "partial_evidence_count": null, "pfam_id": "PF17526", "proteins": 7, "proteomes": 7, "short_name": "DUF5448", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17526", "structures": 0, "taxa": 33, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycoplasma.", "domain_architectures": 1, "interpro_id": "IPR035215", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5454)", "partial_evidence_count": null, "pfam_id": "PF17535", "proteins": 7, "proteomes": 7, "short_name": "DUF5454", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17535", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacteriophages.", "domain_architectures": 1, "interpro_id": "IPR035180", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5464)", "partial_evidence_count": null, "pfam_id": "PF17552", "proteins": 7, "proteomes": 5, "short_name": "DUF5464", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17552", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Saccharomycetaceae.", "domain_architectures": 1, "interpro_id": "IPR035143", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5483)", "partial_evidence_count": null, "pfam_id": "PF17581", "proteins": 7, "proteomes": 3, "short_name": "DUF5483", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17581", "structures": 0, "taxa": 44, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 7, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR035132", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5501)", "partial_evidence_count": null, "pfam_id": "PF17605", "proteins": 7, "proteomes": 7, "short_name": "DUF5501", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17605", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillus.", "domain_architectures": 1, "interpro_id": "IPR020239", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5511)", "partial_evidence_count": null, "pfam_id": "PF17630", "proteins": 7, "proteomes": 5, "short_name": "DUF5511", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17630", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000807) is described by MIBiG as an example of the following biosynthetic class, saccharide. It includes a member of the phosphonoglycans biosynthetic gene cluster from Stackebrandtia nassauensis DSM 44728 [[cite:PUB00098921]].", "domain_architectures": 1, "interpro_id": "IPR045686", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF6189)", "partial_evidence_count": null, "pfam_id": "PF19688", "proteins": 7, "proteomes": 7, "short_name": "DUF6189", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19688", "structures": 0, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in a range of bacteria and phage.", "domain_architectures": 1, "interpro_id": "IPR049289", "known_evidence_count": null, "matches": 7, "name": "Domain of unknown function (DUF6839)", "partial_evidence_count": null, "pfam_id": "PF20767", "proteins": 7, "proteomes": 5, "short_name": "DUF6839", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20767", "structures": 1, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised bacterial proteins. It is frequently found in combination with [pfam:PF21818]. It is predicted to adopt a complex alpha/beta structure composed of a curved beta-sheet that encloses an alpha-helix and a number of helices packed on its exterior.", "domain_architectures": 2, "interpro_id": "IPR056080", "known_evidence_count": null, "matches": 7, "name": "Domain of unknown function (DUF7663)", "partial_evidence_count": null, "pfam_id": "PF24699", "proteins": 7, "proteomes": 7, "short_name": "DUF7663", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24699", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain found in streptococcal phage proteins. Structurally the domain is composed of a three stranded beta sheet followed by an alpha helix.", "domain_architectures": 1, "interpro_id": "IPR056137", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF7720)", "partial_evidence_count": null, "pfam_id": "PF24843", "proteins": 7, "proteomes": 7, "short_name": "DUF7720", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24843", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function (DUF8092) found exclusively in members of the Mycobacterium tuberculosis complex. The domain is approximately 54 amino acids in length and is highly conserved across all known members. The function of this domain has not been experimentally determined.", "domain_architectures": 1, "interpro_id": "IPR058405", "known_evidence_count": null, "matches": 7, "name": "Domain of unknown function (DUF8092)", "partial_evidence_count": null, "pfam_id": "PF26357", "proteins": 7, "proteomes": 7, "short_name": "DUF8092", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26357", "structures": 0, "taxa": 19, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised phage proteins. It is predicted to fold into an alpha-helical structure. It has several highly conserved cysteine residues some of which may coordinate a metal ion.", "domain_architectures": 1, "interpro_id": "IPR059356", "known_evidence_count": null, "matches": 7, "name": "Domain of unknown function (DUF8312)", "partial_evidence_count": null, "pfam_id": "PF26983", "proteins": 7, "proteomes": 7, "short_name": "DUF8312", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26983", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several proteins of unknown function Raphanus sativus (Radish) and Brassica napus (Rape).", "domain_architectures": 1, "interpro_id": "IPR008527", "known_evidence_count": null, "matches": 6, "name": "Protein of unknown function (DUF809)", "partial_evidence_count": null, "pfam_id": "PF05663", "proteins": 6, "proteomes": 1, "short_name": "DUF809", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05663", "structures": 0, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Trypanosoma brucei putative variant specific antigen proteins of around 80 residues in length.", "domain_architectures": 1, "interpro_id": "IPR009795", "known_evidence_count": null, "matches": 6, "name": "Protein of unknown function (DUF1363)", "partial_evidence_count": null, "pfam_id": "PF07101", "proteins": 6, "proteomes": 0, "short_name": "DUF1363", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07101", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical putative outer membrane proteins which appear to be specific to Anaplasma marginale and Anaplasma ovis.", "domain_architectures": 1, "interpro_id": "IPR009919", "known_evidence_count": null, "matches": 6, "name": "Protein of unknown function (DUF1455)", "partial_evidence_count": null, "pfam_id": "PF07306", "proteins": 6, "proteomes": 2, "short_name": "DUF1455", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07306", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in the Archaeal protein maltooligosyl trehalose synthase produced by Sulfolobus spp. Its function has not, as yet, been defined.", "domain_architectures": 1, "interpro_id": "IPR015279", "known_evidence_count": null, "matches": 6, "name": "Domain of unknown function (DUF1953)", "partial_evidence_count": null, "pfam_id": "PF09196", "proteins": 6, "proteomes": 5, "short_name": "DUF1953", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09196", "structures": 2, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is found in bacteria. Proteins in this family are approximately 160 amino acids in length. Several members are associated with vancomycin virulence in Staph. aureus in some way [[cite:PUB00076539]]. These proteins are all lipoproteins, carrying the characteristic prokaryotic membrane-attachment site at their N-termini.", "domain_architectures": 1, "interpro_id": "IPR032590", "known_evidence_count": null, "matches": 6, "name": "Domain of unknown function (DUF4909)", "partial_evidence_count": null, "pfam_id": "PF16253", "proteins": 6, "proteomes": 5, "short_name": "DUF4909", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16253", "structures": 1, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 550 in length and is mainly found in Bacteroides fragilis and sp. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032210", "known_evidence_count": null, "matches": 6, "name": "Domain of unknown function (DUF5029)", "partial_evidence_count": null, "pfam_id": "PF16432", "proteins": 6, "proteomes": 4, "short_name": "DUF5029", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16432", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 2, "interpro_id": "IPR033426", "known_evidence_count": null, "matches": 6, "name": "Domain of unknown function (DUF5124)", "partial_evidence_count": null, "pfam_id": "PF17160", "proteins": 6, "proteomes": 6, "short_name": "DUF5124", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17160", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterococcus.", "domain_architectures": 1, "interpro_id": "IPR035395", "known_evidence_count": null, "matches": 6, "name": "Family of unknown function (DUF5415)", "partial_evidence_count": null, "pfam_id": "PF17436", "proteins": 6, "proteomes": 6, "short_name": "DUF5415", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17436", "structures": 0, "taxa": 24, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Chironomus.", "domain_architectures": 1, "interpro_id": "IPR035241", "known_evidence_count": null, "matches": 6, "name": "Family of unknown function (DUF5442)", "partial_evidence_count": null, "pfam_id": "PF17514", "proteins": 6, "proteomes": 2, "short_name": "DUF5442", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17514", "structures": 0, "taxa": 40, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Giardia intestinalis.", "domain_architectures": 1, "interpro_id": "IPR035226", "known_evidence_count": null, "matches": 6, "name": "Family of unknown function (DUF5450)", "partial_evidence_count": null, "pfam_id": "PF17529", "proteins": 6, "proteomes": 1, "short_name": "DUF5450", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17529", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillus.", "domain_architectures": 1, "interpro_id": "IPR020265", "known_evidence_count": null, "matches": 6, "name": "Family of unknown function (DUF5513)", "partial_evidence_count": null, "pfam_id": "PF17632", "proteins": 6, "proteomes": 4, "short_name": "DUF5513", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17632", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043883", "known_evidence_count": null, "matches": 6, "name": "Family of unknown function (DUF5849)", "partial_evidence_count": null, "pfam_id": "PF19167", "proteins": 6, "proteomes": 2, "short_name": "DUF5849", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19167", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043848", "known_evidence_count": null, "matches": 6, "name": "Family of unknown function (DUF5860)", "partial_evidence_count": null, "pfam_id": "PF19178", "proteins": 6, "proteomes": 3, "short_name": "DUF5860", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19178", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 2 } }, "demotion_reasons": [], "description": "This domain is found at the N-terminal end of Uncharacterized protein AF_2093 from Archaeoglobus fulgidus and similar proteins from archaea. Its function is unknown.", "domain_architectures": 1, "interpro_id": "IPR049264", "known_evidence_count": null, "matches": 6, "name": "Domain of unknown function (DUF6846)", "partial_evidence_count": null, "pfam_id": "PF20897", "proteins": 6, "proteomes": 6, "short_name": "DUF6846", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20897", "structures": 1, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a presumed domain found at the N-terminal of a set of sequences from Strongyloides stercoralis and similar worms. It may adopt a beta-sandwich fold, related to MATH domains.", "domain_architectures": 1, "interpro_id": "IPR056659", "known_evidence_count": null, "matches": 6, "name": "Domain of unknown function (DUF7757)", "partial_evidence_count": null, "pfam_id": "PF24941", "proteins": 6, "proteomes": 5, "short_name": "DUF7757", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24941", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 6, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a group of uncharacterised proteins from arthropod-infecting viruses.", "domain_architectures": 1, "interpro_id": "IPR056688", "known_evidence_count": null, "matches": 6, "name": "Family of unknown function (DUF7786)", "partial_evidence_count": null, "pfam_id": "PF25012", "proteins": 6, "proteomes": 6, "short_name": "DUF7786", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25012", "structures": 0, "taxa": 57, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region in a number of uncharacterised plant proteins.", "domain_architectures": 1, "interpro_id": "IPR007649", "known_evidence_count": null, "matches": 5, "name": "Protein of unknown function", "partial_evidence_count": null, "pfam_id": "PF04569", "proteins": 5, "proteomes": 3, "short_name": "DUF591", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04569", "structures": 0, "taxa": 26, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Cucumber mosaic virus ORF IIB proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009536", "known_evidence_count": null, "matches": 5, "name": "Protein of unknown function (DUF1155)", "partial_evidence_count": null, "pfam_id": "PF06633", "proteins": 5, "proteomes": 0, "short_name": "DUF1155", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06633", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a conserved region approximately 50 residues long within a number of proteins of unknown function that seem to be specific to Arabidopsis thaliana. Note that many family members contain multiple copies of this region.", "domain_architectures": 3, "interpro_id": "IPR010725", "known_evidence_count": null, "matches": 8, "name": "Protein of unknown function (DUF1299)", "partial_evidence_count": null, "pfam_id": "PF06975", "proteins": 5, "proteomes": 3, "short_name": "DUF1299", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06975", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several hypothetical bacterial and phage proteins of around 100 residues in length. Members of this family seem to be found exclusively in Lactococcus lactis and the bacteriophages that infect this species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR010772", "known_evidence_count": null, "matches": 5, "name": "Protein of unknown function (DUF1359)", "partial_evidence_count": null, "pfam_id": "PF07097", "proteins": 5, "proteomes": 2, "short_name": "DUF1359", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07097", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Members of this family are found in maltosyltransferases, and adopt a secondary structure consisting of eight antiparallel beta-strands, which form an open-sided 'jelly roll' Greek key beta-barrel. Their exact function is, as yet, unknown [[cite:PUB00025274]].", "domain_architectures": 2, "interpro_id": "IPR015167", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF1923)", "partial_evidence_count": null, "pfam_id": "PF09083", "proteins": 5, "proteomes": 4, "short_name": "DUF1923", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09083", "structures": 2, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a set of hypothetical Archaeal proteins. Its exact function has not, as yet, been defined. It possesses a zinc ribbon fold.", "domain_architectures": 2, "interpro_id": "IPR015234", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF1936)", "partial_evidence_count": null, "pfam_id": "PF09151", "proteins": 5, "proteomes": 4, "short_name": "DUF1936", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09151", "structures": 2, "taxa": 31, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family appears only on sequences from Salmonella spp. These sequences also all carry a YARHG domain, [pfam:PF13308].", "domain_architectures": 3, "interpro_id": "IPR028007", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF4459)", "partial_evidence_count": null, "pfam_id": "PF14673", "proteins": 5, "proteomes": 5, "short_name": "DUF4459", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14673", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family of uncharacterised proteins is found in eukaryotes.", "domain_architectures": 1, "interpro_id": "IPR029363", "known_evidence_count": null, "matches": 10, "name": "Domain of unknown function (DUF4575)", "partial_evidence_count": null, "pfam_id": "PF15143", "proteins": 5, "proteomes": 2, "short_name": "DUF4575", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15143", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 100 residues in length and is mainly found in various Clostridiales species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032207", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF5026)", "partial_evidence_count": null, "pfam_id": "PF16429", "proteins": 5, "proteomes": 5, "short_name": "DUF5026", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16429", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Methanocaldococcus jannaschii. Family members have three predicted trans-membrane regions.", "domain_architectures": 1, "interpro_id": "IPR035582", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5418)", "partial_evidence_count": null, "pfam_id": "PF17439", "proteins": 5, "proteomes": 3, "short_name": "DUF5418", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17439", "structures": 0, "taxa": 37, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mycoplasma.", "domain_architectures": 1, "interpro_id": "IPR035339", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5426)", "partial_evidence_count": null, "pfam_id": "PF17473", "proteins": 5, "proteomes": 2, "short_name": "DUF5426", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17473", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Mastadenoviruses.", "domain_architectures": 1, "interpro_id": "IPR035249", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5441)", "partial_evidence_count": null, "pfam_id": "PF17513", "proteins": 5, "proteomes": 1, "short_name": "DUF5441", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17513", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Saccharomycetales.", "domain_architectures": 1, "interpro_id": "IPR020120", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5474)", "partial_evidence_count": null, "pfam_id": "PF17568", "proteins": 5, "proteomes": 2, "short_name": "DUF5474", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17568", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Kappa-papillomavirus.", "domain_architectures": 1, "interpro_id": "IPR035149", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5479)", "partial_evidence_count": null, "pfam_id": "PF17575", "proteins": 5, "proteomes": 2, "short_name": "DUF5479", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17575", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Alphabaculovirus.", "domain_architectures": 1, "interpro_id": "IPR035138", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5485)", "partial_evidence_count": null, "pfam_id": "PF17586", "proteins": 5, "proteomes": 5, "short_name": "DUF5485", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17586", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR020272", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5494)", "partial_evidence_count": null, "pfam_id": "PF17598", "proteins": 5, "proteomes": 5, "short_name": "DUF5494", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17598", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Listeria.", "domain_architectures": 1, "interpro_id": "IPR035131", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5502)", "partial_evidence_count": null, "pfam_id": "PF17606", "proteins": 5, "proteomes": 3, "short_name": "DUF5502", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17606", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents YpjCB family of proteins found in Escherichia coli.", "domain_architectures": 2, "interpro_id": "IPR035124", "known_evidence_count": null, "matches": 7, "name": "YpjCB family", "partial_evidence_count": null, "pfam_id": "PF17621", "proteins": 5, "proteomes": 4, "short_name": "DUF5508", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17621", "structures": 0, "taxa": 24, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillus.", "domain_architectures": 1, "interpro_id": "IPR035115", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5514)", "partial_evidence_count": null, "pfam_id": "PF17633", "proteins": 5, "proteomes": 3, "short_name": "DUF5514", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17633", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a domain of unknown function, which is predominantly found in Phycodnaviridae and Caudovirale viruses.", "domain_architectures": 1, "interpro_id": "IPR043862", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5824)", "partial_evidence_count": null, "pfam_id": "PF19141", "proteins": 5, "proteomes": 5, "short_name": "DUF5824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19141", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Marseillevirus.", "domain_architectures": 2, "interpro_id": "IPR045412", "known_evidence_count": null, "matches": 7, "name": "Family of unknown function (DUF5893)", "partial_evidence_count": null, "pfam_id": "PF19245", "proteins": 5, "proteomes": 3, "short_name": "DUF5893", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19245", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses. These proteins are thought to include F-box domain containing proteins, a conserved domain present in numerous proteins, involved in protein- protein interaction.", "domain_architectures": 1, "interpro_id": "IPR045419", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5900)", "partial_evidence_count": null, "pfam_id": "PF19253", "proteins": 5, "proteomes": 2, "short_name": "DUF5900", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19253", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 4 } }, "demotion_reasons": [], "description": "This is the N-terminal domain of uncharacterised proteins such as YhiJ from E.coli. According to AlphaFold model, this domain may have an alpha/beta structure consisting of five beta-sheets and three short alpha-helices.", "domain_architectures": 1, "interpro_id": "IPR049206", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF6860)", "partial_evidence_count": null, "pfam_id": "PF21661", "proteins": 5, "proteomes": 5, "short_name": "DUF6860", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF21661", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain containing a novel repeat fold, according to structure predictions. It may comprise six repeats, each of them consisting of two antiparallel beta-strands and a short alpha-helix.", "domain_architectures": 1, "interpro_id": "IPR055901", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF7478)", "partial_evidence_count": null, "pfam_id": "PF24290", "proteins": 5, "proteomes": 5, "short_name": "DUF7478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24290", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to fold into an alpha-helical structure capped with a beta-hairpin. It contains a conserved CFVxxR motif at the N-termini.", "domain_architectures": 1, "interpro_id": "IPR059365", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF8321)", "partial_evidence_count": null, "pfam_id": "PF26995", "proteins": 5, "proteomes": 5, "short_name": "DUF8321", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26995", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 5, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins. It is predicted to fold into a beta-barrel with topology reminiscent to PH domains but with circular permutation. It contains two conserved sequence motifs YDPN and YFxGG.", "domain_architectures": 1, "interpro_id": "IPR059366", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF8322)", "partial_evidence_count": null, "pfam_id": "PF26997", "proteins": 5, "proteomes": 5, "short_name": "DUF8322", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26997", "structures": 0, "taxa": 42, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in a group of uncharacterised proteins mainly from Alveolata lineage. It contains several highly conserved cysteine residues that are predicted to form disulfide bonds. In many proteins this domain is followed by a helix which is predicted as a transmembrane.", "domain_architectures": 1, "interpro_id": "IPR059382", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF8338)", "partial_evidence_count": null, "pfam_id": "PF27029", "proteins": 5, "proteomes": 5, "short_name": "DUF8338", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27029", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found at the C-terminal of uncharacterised bacterial sequences. It may adopt a Ig-like domain and it is found associated with [pfam:PF27477].", "domain_architectures": 2, "interpro_id": "IPR061658", "known_evidence_count": null, "matches": 5, "name": "Domain of unknown function (DUF8597)", "partial_evidence_count": null, "pfam_id": "PF29883", "proteins": 5, "proteomes": 5, "short_name": "DUF8597", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29883", "structures": 0, "taxa": 28, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family consists of several hypothetical Feline immunodeficiency virus (FIV) proteins. Members of this family are typically around 67 residues long and are often annotated as ORF3 proteins. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR009588", "known_evidence_count": null, "matches": 4, "name": "Protein of unknown function (DUF1199)", "partial_evidence_count": null, "pfam_id": "PF06712", "proteins": 4, "proteomes": 1, "short_name": "DUF1199", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06712", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family consist of various uncharacterised viral hypothetical proteins.", "domain_architectures": 2, "interpro_id": "", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF1970)", "partial_evidence_count": null, "pfam_id": "PF09301", "proteins": 4, "proteomes": 3, "short_name": "DUF1970", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09301", "structures": 2, "taxa": 25, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of short, 111 residue, proteins found in S. pombe. The function is not known.", "domain_architectures": 1, "interpro_id": "IPR019445", "known_evidence_count": null, "matches": 4, "name": "Protein of unknown function (DUF2430)", "partial_evidence_count": null, "pfam_id": "PF10353", "proteins": 4, "proteomes": 2, "short_name": "DUF2430", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF10353", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "Family based on orphan protein (TM0875) from Thermotoga maritima that has been structurally determined as PDB:1022. The TM0875 gene of Thermotoga maritima encodes a hypothetical protein NP_228683 [[cite:PUB00029305]] of unknown function. Analysis of TM0875 genomic context reveals the presence of MMT1 (a predicted Co/Zn/Cd cation transporter) and an inactive homolog of metal-dependent proteases. 1O22 shows weak structural similarity with the phosphoribosylformylglycinamidine synthase 1t4a (Dali Z-scr=4.6), the yggU protein (PDB structure:1n91; with DALI Z-scr=3), and with the thioesterase superfamily member (PDB structure 2cy9 - found using FATCAT), even though they have very low sequence identity.", "domain_architectures": 1, "interpro_id": "IPR024482", "known_evidence_count": null, "matches": 4, "name": "Domain of Unknown Function with PDB structure (DUF3855)", "partial_evidence_count": null, "pfam_id": "PF12967", "proteins": 4, "proteomes": 4, "short_name": "DUF3855", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12967", "structures": 1, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are approximately 350 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR027977", "known_evidence_count": null, "matches": 4, "name": "Protein of unknown function (DUF4621)", "partial_evidence_count": null, "pfam_id": "PF15414", "proteins": 4, "proteomes": 4, "short_name": "DUF4621", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15414", "structures": 1, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 460 residues in length and is mainly found in various Bacteroides species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032241", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF5042)", "partial_evidence_count": null, "pfam_id": "PF16445", "proteins": 4, "proteomes": 4, "short_name": "DUF5042", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16445", "structures": 0, "taxa": 19, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein is believed to be involved in the type VII secretion system.", "domain_architectures": 1, "interpro_id": "IPR031676", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF5083)", "partial_evidence_count": null, "pfam_id": "PF16890", "proteins": 4, "proteomes": 4, "short_name": "DUF5083", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16890", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This small family of proteins found in Clostridiales is functionally uncharacterized. Proteins in this family are around 130 amino acids in length. Based on NMR structure 2MCA, it forms a beta-sandwich structure consisting of two 4-stranded antiparallel b-strands. The structure is very similar to glutamine glutamyltransferases (1l9n) and peptide transporters (5a9h).", "domain_architectures": 1, "interpro_id": "IPR033779", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF5300)", "partial_evidence_count": null, "pfam_id": "PF17224", "proteins": 4, "proteomes": 4, "short_name": "DUF5300", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17224", "structures": 1, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function.", "domain_architectures": 1, "interpro_id": "IPR035282", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5429)", "partial_evidence_count": null, "pfam_id": "PF17494", "proteins": 4, "proteomes": 1, "short_name": "DUF5429", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17494", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR020099", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5445)", "partial_evidence_count": null, "pfam_id": "PF17520", "proteins": 4, "proteomes": 4, "short_name": "DUF5445", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17520", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR035194", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5461)", "partial_evidence_count": null, "pfam_id": "PF17545", "proteins": 4, "proteomes": 4, "short_name": "DUF5461", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17545", "structures": 0, "taxa": 29, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 3, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Yersinia pestis.", "domain_architectures": 1, "interpro_id": "IPR035181", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5463)", "partial_evidence_count": null, "pfam_id": "PF17551", "proteins": 4, "proteomes": 2, "short_name": "DUF5463", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17551", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Orthopoxvirus.", "domain_architectures": 1, "interpro_id": "IPR020125", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5488)", "partial_evidence_count": null, "pfam_id": "PF17590", "proteins": 4, "proteomes": 3, "short_name": "DUF5488", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17590", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents an uncharacterised protein that is associated with the thiocillin biosynthetic gene cluster.", "domain_architectures": 1, "interpro_id": "IPR043874", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5834)", "partial_evidence_count": null, "pfam_id": "PF19152", "proteins": 4, "proteomes": 4, "short_name": "DUF5834", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19152", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phycodnaviridae.", "domain_architectures": 2, "interpro_id": "IPR043879", "known_evidence_count": null, "matches": 5, "name": "Family of unknown function (DUF5853)", "partial_evidence_count": null, "pfam_id": "PF19171", "proteins": 4, "proteomes": 4, "short_name": "DUF5853", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19171", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043844", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5865)", "partial_evidence_count": null, "pfam_id": "PF19183", "proteins": 4, "proteomes": 1, "short_name": "DUF5865", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19183", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Marseilleviridae.", "domain_architectures": 1, "interpro_id": "IPR045366", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5905)", "partial_evidence_count": null, "pfam_id": "PF19262", "proteins": 4, "proteomes": 3, "short_name": "DUF5905", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19262", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001805) is described by MIBiG as an example of the following biosynthetic class, NRP (non-ribosomal peptide).", "domain_architectures": 1, "interpro_id": "IPR045995", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF5951)", "partial_evidence_count": null, "pfam_id": "PF19376", "proteins": 4, "proteomes": 3, "short_name": "DUF5951", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19376", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in bacteria. Proteins in this family are typically between 454 and 596 amino acids in length. There are two highly conserved residues, a Tyr and an Asp.", "domain_architectures": 1, "interpro_id": "IPR046490", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF6583)", "partial_evidence_count": null, "pfam_id": "PF20224", "proteins": 4, "proteomes": 4, "short_name": "DUF6583", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20224", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This archaeal family of proteins has no known function. This entry represents the C-terminal THUMP-like domain.", "domain_architectures": 1, "interpro_id": "IPR048305", "known_evidence_count": null, "matches": 4, "name": "Protein of unknown function (DUF3195) C-terminal domain", "partial_evidence_count": null, "pfam_id": "PF20997", "proteins": 4, "proteomes": 4, "short_name": "DUF3195_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20997", "structures": 1, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This short helical domain is found in a small set of ribosomal S1 proteins. It's function is unknown.", "domain_architectures": 2, "interpro_id": "IPR054237", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF6964)", "partial_evidence_count": null, "pfam_id": "PF22291", "proteins": 4, "proteomes": 3, "short_name": "DUF6964", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22291", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents an alpha-lytic protease prodomain-like domain present in a protein of unknown function from Desulfovibrio piger. It structure has been characterized (PDB:4HLB).", "domain_architectures": 1, "interpro_id": "IPR054250", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF6981)", "partial_evidence_count": null, "pfam_id": "PF22403", "proteins": 4, "proteomes": 3, "short_name": "DUF6981", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22403", "structures": 1, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised phage proteins. The family includes Phage Bxb1 protein 85 [swissprot:Q9B036].", "domain_architectures": 1, "interpro_id": "IPR055888", "known_evidence_count": null, "matches": 4, "name": "Family of unknown function (DUF7465)", "partial_evidence_count": null, "pfam_id": "PF24264", "proteins": 4, "proteomes": 4, "short_name": "DUF7465", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24264", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 4, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry includes uncharacterised sequences mainly from actinobacteria. According to structure predictions, they may form a beta-propeller-like fold consisting of four repeated units containing three (in one of them) and four (on the other three units) beta-strands. There is an additional unit which is slightly different that resembles a seven stranded beta-sandwich.", "domain_architectures": 1, "interpro_id": "IPR055908", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF7485)", "partial_evidence_count": null, "pfam_id": "PF24303", "proteins": 4, "proteomes": 4, "short_name": "DUF7485", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24303", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group of uncharacterised sequences from bacteria. It may adopt a Ig-like fold.", "domain_architectures": 1, "interpro_id": "IPR061544", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF8474)", "partial_evidence_count": null, "pfam_id": "PF28888", "proteins": 4, "proteomes": 4, "short_name": "DUF8474", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28888", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group of uncharacterised sequences from bacteria. It may adopt a Ig-like fold.", "domain_architectures": 1, "interpro_id": "IPR061545", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF8475)", "partial_evidence_count": null, "pfam_id": "PF28889", "proteins": 4, "proteomes": 4, "short_name": "DUF8475", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28889", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found mainly in proteins from Bacillota lineage. It is found C-terminal to a lipoprotein lipid attachment site suggesting that it may be associated with the membrane.", "domain_architectures": 1, "interpro_id": "IPR061885", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF8824)", "partial_evidence_count": null, "pfam_id": "PF31152", "proteins": 4, "proteomes": 4, "short_name": "DUF8824", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF31152", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several Maize streak virus proteins of unknown function.", "domain_architectures": 1, "interpro_id": "IPR009529", "known_evidence_count": null, "matches": 3, "name": "Protein of unknown function (DUF1148)", "partial_evidence_count": null, "pfam_id": "PF06618", "proteins": 3, "proteomes": 1, "short_name": "DUF1148", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06618", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain found in several proteins that seem to be specific to red algae plasmids.", "domain_architectures": 1, "interpro_id": "IPR010778", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF1368)", "partial_evidence_count": null, "pfam_id": "PF07112", "proteins": 3, "proteomes": 1, "short_name": "DUF1368", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF07112", "structures": 0, "taxa": 23, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "Members of this family of Mycoplasma hypothetical proteins adopt a helical structure, with one central alpha-helix surrounded by five others, in a NusB-like fold. Their function has not, as yet, been determined [[cite:PUB00030162]].", "domain_architectures": 1, "interpro_id": "IPR015268", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF1948)", "partial_evidence_count": null, "pfam_id": "PF09185", "proteins": 3, "proteomes": 3, "short_name": "DUF1948", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF09185", "structures": 1, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "this domain is found on the N-terminal of several uncharacterize proteins found in various Bacteroides species. Solved structure of one of them (BACOVA_00967) from Bacteroides ovatus shows a small beta barrel with an immunoglobulin-like fold. DUF4841 domain shows weak overlap with the DUF4114 family, suggesting a possible distant relation. Function of this domain is unknown.", "domain_architectures": 1, "interpro_id": "IPR032294", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF4841)", "partial_evidence_count": null, "pfam_id": "PF16129", "proteins": 3, "proteomes": 3, "short_name": "DUF4841", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16129", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterized proteins around 350 in length and is mainly found in various Firmicutes species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "IPR032203", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF5022)", "partial_evidence_count": null, "pfam_id": "PF16425", "proteins": 3, "proteomes": 3, "short_name": "DUF5022", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16425", "structures": 0, "taxa": 20, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Enterobacteriaceae.", "domain_architectures": 1, "interpro_id": "IPR020484", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF5503)", "partial_evidence_count": null, "pfam_id": "PF17607", "proteins": 3, "proteomes": 2, "short_name": "DUF5503", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17607", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Bacillus.", "domain_architectures": 1, "interpro_id": "IPR020257", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF5512)", "partial_evidence_count": null, "pfam_id": "PF17631", "proteins": 3, "proteomes": 2, "short_name": "DUF5512", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17631", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This presumed domain is functionally uncharacterised. This domain family is found in bacteria and fungi, and is approximately 110 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR043719", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF5660)", "partial_evidence_count": null, "pfam_id": "PF18904", "proteins": 3, "proteomes": 3, "short_name": "DUF5660", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18904", "structures": 0, "taxa": 34, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043909", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF5768)", "partial_evidence_count": null, "pfam_id": "PF19072", "proteins": 3, "proteomes": 1, "short_name": "DUF5768", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19072", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in Phycodnaviridae.", "domain_architectures": 1, "interpro_id": "IPR043922", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF5773)", "partial_evidence_count": null, "pfam_id": "PF19082", "proteins": 3, "proteomes": 2, "short_name": "DUF5773", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19082", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phyconaviridae.", "domain_architectures": 1, "interpro_id": "IPR043660", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF5873)", "partial_evidence_count": null, "pfam_id": "PF19201", "proteins": 3, "proteomes": 3, "short_name": "DUF5873", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19201", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Marseillevirus.", "domain_architectures": 1, "interpro_id": "IPR045356", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF5882)", "partial_evidence_count": null, "pfam_id": "PF19229", "proteins": 3, "proteomes": 3, "short_name": "DUF5882", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19229", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phycodnavirus.", "domain_architectures": 1, "interpro_id": "IPR045364", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF5883)", "partial_evidence_count": null, "pfam_id": "PF19230", "proteins": 3, "proteomes": 3, "short_name": "DUF5883", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19230", "structures": 0, "taxa": 15, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents a domain of unknown function that is found in Phycodnaviridae. This entry is likely to represent membrane proteins with four transmembrane regions.", "domain_architectures": 1, "interpro_id": "IPR045360", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF5904)", "partial_evidence_count": null, "pfam_id": "PF19261", "proteins": 3, "proteomes": 3, "short_name": "DUF5904", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19261", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0001410) is described by MIBiG as an example of the following biosynthetic class, saccharide. This family includes a protein from the polysaccharide A biosynthetic gene cluster from Bacteroides fragilis [[cite:PUB00099396]].", "domain_architectures": 1, "interpro_id": "IPR046073", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF6032)", "partial_evidence_count": null, "pfam_id": "PF19497", "proteins": 3, "proteomes": 2, "short_name": "DUF6032", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19497", "structures": 0, "taxa": 21, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This uncharacterised protein family is predominantly found in Leptospirillum sp. Its function is unknown. There are some conserved motifs: SRD, AGGL and some highly conserved Y, H and W residues.", "domain_architectures": 1, "interpro_id": "IPR049291", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF6840)", "partial_evidence_count": null, "pfam_id": "PF20786", "proteins": 3, "proteomes": 3, "short_name": "DUF6840", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20786", "structures": 1, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group of uncharacterised bacterial sequences whose function is unknown. This domain adopts a galactose-binding-like structure (PDBe:4lr4).", "domain_architectures": 1, "interpro_id": "IPR054225", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF6947)", "partial_evidence_count": null, "pfam_id": "PF22239", "proteins": 3, "proteomes": 3, "short_name": "DUF6947", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22239", "structures": 1, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This protein family includes a group of uncharacterised short sequences from actinobacteria.", "domain_architectures": 1, "interpro_id": "IPR055584", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF7160)", "partial_evidence_count": null, "pfam_id": "PF23718", "proteins": 3, "proteomes": 3, "short_name": "DUF7160", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23718", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in phage proteins, approximately 100 residues in length. The domain is found in Microbacterium phages.", "domain_architectures": 1, "interpro_id": "IPR055674", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF7250)", "partial_evidence_count": null, "pfam_id": "PF23908", "proteins": 3, "proteomes": 3, "short_name": "DUF7250", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23908", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain of unknown function found in bacteriophage proteins. The domain is around 115-125 residues long composed of a four stranded beta sheet with helices packed on one side. There is evidence for a confident dimer from structure prediction. In addition the dimer shows a strong electrostatic polarity possibly suggesting a nucleic acid binding function.", "domain_architectures": 1, "interpro_id": "IPR055676", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF7252)", "partial_evidence_count": null, "pfam_id": "PF23910", "proteins": 3, "proteomes": 3, "short_name": "DUF7252", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF23910", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small accessory domain found at the N-terminus of a small family of archaeal AGOG proteins. These proteins have 8-oxoguanine DNA glycosylase activity.", "domain_architectures": 2, "interpro_id": "IPR056081", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF7664)", "partial_evidence_count": null, "pfam_id": "PF24701", "proteins": 3, "proteomes": 3, "short_name": "DUF7664", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24701", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This entry represents a small family of uncharacterised proteins that have a 6 stranded beta barrel fold. This domain is usually found next to a C-terminal PilZ domain. This domain appears to share structural similarity to the PilZ domain suggesting this may be a divergent PilZ domain.", "domain_architectures": 2, "interpro_id": "IPR058402", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF8089)", "partial_evidence_count": null, "pfam_id": "PF26339", "proteins": 3, "proteomes": 3, "short_name": "DUF8089", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26339", "structures": 0, "taxa": 16, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins mainly from Planctomycetia. It contains four pairs of highly conserved cysteine residues that are probably involved in zinc coordination. This domain is predicted to contain two zinc ribbon domains inserted one into the other.", "domain_architectures": 1, "interpro_id": "IPR059303", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF8259)", "partial_evidence_count": null, "pfam_id": "PF26787", "proteins": 3, "proteomes": 3, "short_name": "DUF8259", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF26787", "structures": 0, "taxa": 18, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharcterised proteins from gram negative bacteria. It is predicted to fold into alpha/beta structure comprising a curved beta-sheet and an alpha helix packed on it. It has a number of conserved negatively charged residues that are predicted to cluster on the protein domain surface.", "domain_architectures": 1, "interpro_id": "IPR059395", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF8351)", "partial_evidence_count": null, "pfam_id": "PF27616", "proteins": 3, "proteomes": 3, "short_name": "DUF8351", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF27616", "structures": 0, "taxa": 22, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents uncharacterised proteins from Methanobacteriati lineage. They are predicted to adopt a non-compact alpha-helical structure which is likely to assemble in a higher order oligomer.", "domain_architectures": 1, "interpro_id": "IPR059467", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF8423)", "partial_evidence_count": null, "pfam_id": "PF28524", "proteins": 3, "proteomes": 3, "short_name": "DUF8423", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28524", "structures": 0, "taxa": 17, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a protein family found in bacteriophages, specifically within Takahashivirus (Caudoviricetes). The function of this protein family remains to be determined.", "domain_architectures": 2, "interpro_id": "IPR061634", "known_evidence_count": null, "matches": 3, "name": "Family of unknown function (DUF8567)", "partial_evidence_count": null, "pfam_id": "PF29562", "proteins": 3, "proteomes": 1, "short_name": "DUF8567", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29562", "structures": 0, "taxa": 10, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a small domain found in a group of uncharacterised sequences from fungi. It is found associated with [pfam:PF17019] at the C-terminal.", "domain_architectures": 1, "interpro_id": "IPR061645", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF8584)", "partial_evidence_count": null, "pfam_id": "PF29767", "proteins": 3, "proteomes": 3, "short_name": "DUF8584", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29767", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 3, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a domain found in a group of uncharacterised bacterial sequences, found at the N-terminal of [pfam:PF27477]. It may adopt an helical bundle fold.", "domain_architectures": 1, "interpro_id": "IPR061659", "known_evidence_count": null, "matches": 3, "name": "Domain of unknown function (DUF8598)", "partial_evidence_count": null, "pfam_id": "PF29884", "proteins": 3, "proteomes": 3, "short_name": "DUF8598", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF29884", "structures": 0, "taxa": 19, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 2, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This family contains uncharacterised protein encoded on Trypanosoma kinetoplast minicircles.", "domain_architectures": 1, "interpro_id": "IPR007429", "known_evidence_count": null, "matches": 2, "name": "Protein of unknown function (DUF478)", "partial_evidence_count": null, "pfam_id": "PF04334", "proteins": 2, "proteomes": 0, "short_name": "DUF478", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04334", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins with unknown function appears to be restricted to Pseudomonas.", "domain_architectures": 1, "interpro_id": "IPR021593", "known_evidence_count": null, "matches": 2, "name": "Protein of unknown function (DUF3218)", "partial_evidence_count": null, "pfam_id": "PF11508", "proteins": 2, "proteomes": 2, "short_name": "DUF3218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF11508", "structures": 1, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. This family of proteins is found in some mammals.", "domain_architectures": 1, "interpro_id": "IPR027906", "known_evidence_count": null, "matches": 2, "name": "Domain of unknown function (DUF4567)", "partial_evidence_count": null, "pfam_id": "PF15131", "proteins": 2, "proteomes": 2, "short_name": "DUF4567", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF15131", "structures": 0, "taxa": 53, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in bacteria.", "domain_architectures": 1, "interpro_id": "IPR020497", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5440)", "partial_evidence_count": null, "pfam_id": "PF17509", "proteins": 2, "proteomes": 1, "short_name": "DUF5440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17509", "structures": 0, "taxa": 14, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function, found in phycodnaviruses. The protein contains a predicted N-terminal transmembrane helix.", "domain_architectures": 1, "interpro_id": "IPR043924", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5775)", "partial_evidence_count": null, "pfam_id": "PF19084", "proteins": 2, "proteomes": 2, "short_name": "DUF5775", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19084", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family contains a domain of unknown function found in prasinoviruses.", "domain_architectures": 1, "interpro_id": "IPR043810", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5792)", "partial_evidence_count": null, "pfam_id": "PF19105", "proteins": 2, "proteomes": 2, "short_name": "DUF5792", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19105", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function is found mostly in prasinoviruses.", "domain_architectures": 1, "interpro_id": "IPR043871", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5831)", "partial_evidence_count": null, "pfam_id": "PF19149", "proteins": 2, "proteomes": 2, "short_name": "DUF5831", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19149", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "", "domain_architectures": 1, "interpro_id": "IPR043897", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5835)", "partial_evidence_count": null, "pfam_id": "PF19153", "proteins": 2, "proteomes": 1, "short_name": "DUF5835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19153", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family represents the induction peptide AbpIP, which regulates the biosynthesis of the bacteriocin ABP-118 in Lactobacillus salivarius subsp. salivarius UCC118 [[cite:PUB00094618],[cite:PUB00094619]].", "domain_architectures": 1, "interpro_id": "IPR043896", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5836)", "partial_evidence_count": null, "pfam_id": "PF19154", "proteins": 2, "proteomes": 1, "short_name": "DUF5836", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19154", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043889", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5843)", "partial_evidence_count": null, "pfam_id": "PF19161", "proteins": 2, "proteomes": 1, "short_name": "DUF5843", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19161", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in Phycodnaviridae.", "domain_architectures": 1, "interpro_id": "IPR043877", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5855)", "partial_evidence_count": null, "pfam_id": "PF19173", "proteins": 2, "proteomes": 2, "short_name": "DUF5855", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19173", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043806", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5870)", "partial_evidence_count": null, "pfam_id": "PF19195", "proteins": 2, "proteomes": 1, "short_name": "DUF5870", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19195", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043655", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5878)", "partial_evidence_count": null, "pfam_id": "PF19206", "proteins": 2, "proteomes": 1, "short_name": "DUF5878", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19206", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043654", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5879)", "partial_evidence_count": null, "pfam_id": "PF19207", "proteins": 2, "proteomes": 1, "short_name": "DUF5879", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19207", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR045367", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5885)", "partial_evidence_count": null, "pfam_id": "PF19232", "proteins": 2, "proteomes": 1, "short_name": "DUF5885", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19232", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function mostly found in Prasinoviruses.", "domain_architectures": 1, "interpro_id": "IPR045359", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5903)", "partial_evidence_count": null, "pfam_id": "PF19260", "proteins": 2, "proteomes": 1, "short_name": "DUF5903", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19260", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a member of a biosynthetic gene cluster (BGC). This BGC (BGC0000486) is described by MIBiG as an example of the following biosynthetic class, RiPP (ribosomally synthesised and post-translationally modified peptide).", "domain_architectures": 1, "interpro_id": "IPR046018", "known_evidence_count": null, "matches": 2, "name": "Family of unknown function (DUF5975)", "partial_evidence_count": null, "pfam_id": "PF19400", "proteins": 2, "proteomes": 1, "short_name": "DUF5975", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19400", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 2, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is predominantly found in proteins from bacteria, including CLOLEP_02462 from Clostridium leptum. The function of this protein is unknown.", "domain_architectures": 1, "interpro_id": "IPR049269", "known_evidence_count": null, "matches": 4, "name": "Domain of unknown function (DUF6836)", "partial_evidence_count": null, "pfam_id": "PF20762", "proteins": 2, "proteomes": 1, "short_name": "DUF6836", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20762", "structures": 1, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of a series of 12 repeats of 35 amino acids in length which are found exclusively in Herpesvirus-7. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 12, "name": "Herpesvirus-7 repeat of unknown function (DUF865)", "partial_evidence_count": null, "pfam_id": "PF05906", "proteins": 1, "proteomes": 0, "short_name": "DUF865", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05906", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain family is found in eukaryotes, and is approximately 30 amino acids in length.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 1, "name": "Protein of unknown function (DUF3704)", "partial_evidence_count": null, "pfam_id": "PF12488", "proteins": 1, "proteomes": 1, "short_name": "DUF3704", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12488", "structures": 0, "taxa": 13, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of several uncharacterised proteins around 300 residues in length and is mainly found in various Eubacterium species. The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF5023)", "partial_evidence_count": null, "pfam_id": "PF16426", "proteins": 1, "proteomes": 1, "short_name": "DUF5023", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16426", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Orthopoxvirus.", "domain_architectures": 1, "interpro_id": "IPR035271", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5432)", "partial_evidence_count": null, "pfam_id": "PF17497", "proteins": 1, "proteomes": 0, "short_name": "DUF5432", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17497", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Orthopoxviruses.", "domain_architectures": 1, "interpro_id": "IPR035270", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5433)", "partial_evidence_count": null, "pfam_id": "PF17498", "proteins": 1, "proteomes": 0, "short_name": "DUF5433", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17498", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Orthopoxvirus.", "domain_architectures": 1, "interpro_id": "IPR020077", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5436)", "partial_evidence_count": null, "pfam_id": "PF17504", "proteins": 1, "proteomes": 0, "short_name": "DUF5436", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17504", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Orthopoxvirus.", "domain_architectures": 1, "interpro_id": "IPR020104", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5438)", "partial_evidence_count": null, "pfam_id": "PF17506", "proteins": 1, "proteomes": 0, "short_name": "DUF5438", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17506", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Orthopoxvirus.", "domain_architectures": 1, "interpro_id": "IPR020113", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5439)", "partial_evidence_count": null, "pfam_id": "PF17507", "proteins": 1, "proteomes": 0, "short_name": "DUF5439", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17507", "structures": 0, "taxa": 12, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 1, "protein_traits_record": true, "records_by_mech": { "ProteinTraitsMech": 1 } }, "demotion_reasons": [], "description": "This is a family of unknown function found in Hominidae.", "domain_architectures": 1, "interpro_id": "IPR041571", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5576)", "partial_evidence_count": null, "pfam_id": "PF17739", "proteins": 1, "proteomes": 1, "short_name": "DUF5576", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF17739", "structures": 0, "taxa": 32, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from ORF137 from Pyrobaculum spherical virus. This protein contains two domains with Sm-like fold which relative orientation is very similar to the relative orientation of individual subunits in the Sm-like assembly rings.", "domain_architectures": 1, "interpro_id": "IPR041655", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF5607)", "partial_evidence_count": null, "pfam_id": "PF18355", "proteins": 1, "proteomes": 1, "short_name": "DUF5607", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18355", "structures": 1, "taxa": 8, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a domain from ORF137 from Pyrobaculum spherical virus. This protein contains two domains with Sm-like fold which relative orientation is very similar to the relative orientation of individual subunits in the Sm-like assembly rings.", "domain_architectures": 1, "interpro_id": "IPR041574", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF5608)", "partial_evidence_count": null, "pfam_id": "PF18356", "proteins": 1, "proteomes": 1, "short_name": "DUF5608", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18356", "structures": 1, "taxa": 8, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of small integral membrane proteins is found in bacteria. Proteins in this family are approximately 80 amino acids in length.", "domain_architectures": 1, "interpro_id": "IPR043716", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5657)", "partial_evidence_count": null, "pfam_id": "PF18901", "proteins": 1, "proteomes": 1, "short_name": "DUF5657", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18901", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of unknown function is mostly found in prasinoviruses and is likely to represent membrane proteins with two transmembrane regions.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5826)", "partial_evidence_count": null, "pfam_id": "PF19144", "proteins": 1, "proteomes": 1, "short_name": "DUF5826", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19144", "structures": 0, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function predominantly found in viruses.", "domain_architectures": 1, "interpro_id": "IPR043841", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5867)", "partial_evidence_count": null, "pfam_id": "PF19185", "proteins": 1, "proteomes": 1, "short_name": "DUF5867", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19185", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in pandoraviruses and amoeba. The structure of these proteins forms a distorted beta-trefoil fold.", "domain_architectures": 1, "interpro_id": "IPR045370", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF5888)", "partial_evidence_count": null, "pfam_id": "PF19235", "proteins": 1, "proteomes": 1, "short_name": "DUF5888", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19235", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This is a family of uncharacterised proteins of unknown function found in viruses.", "domain_architectures": 1, "interpro_id": "IPR045416", "known_evidence_count": null, "matches": 1, "name": "Family of unknown function (DUF5897)", "partial_evidence_count": null, "pfam_id": "PF19249", "proteins": 1, "proteomes": 1, "short_name": "DUF5897", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19249", "structures": 0, "taxa": 7, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain of unknown function is found in proteins from bacteria, including the product of the gene SO_2669 from Shewanella oneidensis. Its structure has been solved and shows 16 alpha helices ([swissprot:Q8EDS4]).", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF6835)", "partial_evidence_count": null, "pfam_id": "PF20759", "proteins": 1, "proteomes": 1, "short_name": "DUF6835", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20759", "structures": 1, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in proteins from tailed bacteriophages and eukaryotes, including 201phi2-1p060 from Pseudomonas phage 201phi2-1 Its function is unknown.", "domain_architectures": 1, "interpro_id": "IPR049287", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF6837)", "partial_evidence_count": null, "pfam_id": "PF20764", "proteins": 1, "proteomes": 1, "short_name": "DUF6837", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20764", "structures": 1, "taxa": 11, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a dimeric alpha/beta barrel domain from an uncultured marine organism (PDB:2op5). The function of this family is unknown.", "domain_architectures": 1, "interpro_id": "", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF6974)", "partial_evidence_count": null, "pfam_id": "PF22388", "proteins": 1, "proteomes": 1, "short_name": "DUF6974", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22388", "structures": 2, "taxa": 9, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 1, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a pair of OB fold domains found in a group of uncharacterised proteins from bacteria which have a [pfam:PF22707] domain at the C-terminal.", "domain_architectures": 1, "interpro_id": "IPR054282", "known_evidence_count": null, "matches": 1, "name": "Domain of unknown function (DUF7016)", "partial_evidence_count": null, "pfam_id": "PF22858", "proteins": 1, "proteomes": 1, "short_name": "DUF7016", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF22858", "structures": 0, "taxa": 10, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "A protein family created to cover PDB:2OD5. 2OD5 is a hypothetical protein (JCVI_PEP_1096688149193) from an environmental metagenome (unidentified marine microbe).", "domain_architectures": 0, "interpro_id": "", "known_evidence_count": null, "matches": 0, "name": "Domain of Unknown Function with PDB structure (DUF3860)", "partial_evidence_count": null, "pfam_id": "PF12976", "proteins": 0, "proteomes": 0, "short_name": "DUF3860", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF12976", "structures": 0, "taxa": 0, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family consists of Prepilin-type cleavage/methylation N-terminal domain proteins around 200 residues in length and is mainly found in various Eubacterium species. The function of this family is unknown.", "domain_architectures": 0, "interpro_id": "", "known_evidence_count": null, "matches": 0, "name": "Domain of unknown function (DUF5021)", "partial_evidence_count": null, "pfam_id": "PF16424", "proteins": 0, "proteomes": 0, "short_name": "DUF5021", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF16424", "structures": 0, "taxa": 0, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This family of proteins is functionally uncharacterised. However, the contain an N-terminal [pfam:PF07963] suggesting these may be pilin proteins. This family of proteins is found in bacteria. Proteins in this family are typically between 203 and 237 amino acids in length.", "domain_architectures": 0, "interpro_id": "", "known_evidence_count": null, "matches": 0, "name": "Family of unknown function (DUF6613)", "partial_evidence_count": null, "pfam_id": "PF20318", "proteins": 0, "proteomes": 0, "short_name": "DUF6613", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20318", "structures": 0, "taxa": 0, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a presumed domain found in a group of uncharacterised sequences from bacteria. According to structure predictions, this domain may adopt and all-beta configuration with beta-strands of different lengths. This domain is usually associated with DUF7450 ([pfam:PF24247]).", "domain_architectures": 0, "interpro_id": "", "known_evidence_count": null, "matches": 0, "name": "Domain of unknown function (DUF7451)", "partial_evidence_count": null, "pfam_id": "PF24248", "proteins": 0, "proteomes": 0, "short_name": "DUF7451", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF24248", "structures": 0, "taxa": 0, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This entry represents a family of uncharacterised proteins found in Bacillota species. From genomic context it is likely to be a phage derived protein. It contains a helical domain composed of segments from the N-terminus and C-terminus connected by a coiled coil region.", "domain_architectures": 0, "interpro_id": "", "known_evidence_count": null, "matches": 0, "name": "Family of unknown function (DUF7934)", "partial_evidence_count": null, "pfam_id": "PF25588", "proteins": 0, "proteomes": 0, "short_name": "DUF7934", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF25588", "structures": 0, "taxa": 0, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 0, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "cross_mech": { "example_proteins": 0, "protein_traits_record": true, "records_by_mech": {} }, "demotion_reasons": [], "description": "This domain is found in uncharacterised fungal proteins. It is predicted to fold into an open barrel capped with alpha helices. It contains a number of conserved cysteine residues some of which are predicted to form disulfide bonds.", "domain_architectures": 0, "interpro_id": "", "known_evidence_count": null, "matches": 0, "name": "Domain of unknown function (DUF8378)", "partial_evidence_count": null, "pfam_id": "PF28257", "proteins": 0, "proteomes": 0, "short_name": "DUF8378", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF28257", "structures": 0, "taxa": 0, "unknown_status": "UNKNOWN_CANDIDATE" } ], "inputs": { "cross_mech": "cross-mech-duf-examples-2026-10-06", "worklist": "interpro-pfam-duf-2026-10-05" }, "summary": { "by_candidate_reason": { "description_says_unknown_function": 1359, "domain_of_unknown_function": 2832, "name_matches_duf": 155, "name_says_unknown_function": 6115, "short_name_matches_duf": 6371 }, "by_characterization_status": { "UNSCORED": 6532 }, "by_demotion_reason": {}, "by_unknown_status": { "KNOWN_HISTORICAL_DUF": 378, "UNKNOWN_CANDIDATE": 6154 }, "cross_mech": { "families": 1763, "proteins": 3533, "rows": 16298 }, "families": { "interpro_matches": 7529705, "interpro_proteins": 7199293, "missing_match_counts": 0, "missing_protein_counts": 0, "total": 6532, "with_alphafold_models": 6478, "with_domain_architectures": 6526, "with_interpro_id": 6492, "with_structures": 820 }, "top_by_proteins": [ { "alphafold_models": 19000, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "The function of this family is unknown.", "domain_architectures": 25, "interpro_id": "IPR007278", "known_evidence_count": null, "matches": 40691, "name": "Domain of unknown function (DUF397)", "partial_evidence_count": null, "pfam_id": "PF04149", "proteins": 37657, "proteomes": 1831, "short_name": "DUF397", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04149", "structures": 0, "taxa": 2162, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19007, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This entry represents a putative ligand binding domain found in bacterial transcription regulators that have an N-terminal HTH domain [pfam:PF13560].", "domain_architectures": 42, "interpro_id": "IPR043917", "known_evidence_count": null, "matches": 37543, "name": "Domain of unknown function (DUF5753)", "partial_evidence_count": null, "pfam_id": "PF19054", "proteins": 37511, "proteomes": 1857, "short_name": "DUF5753", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF19054", "structures": 0, "taxa": 2194, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 19995, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This family of prokaryotic proteins have no known function. [swissprot:P71138] a protein of unknown function in the family has been misannotated as alpha-dextrin 6-glucanohydrolase.", "domain_architectures": 45, "interpro_id": "IPR002881", "known_evidence_count": null, "matches": 31548, "name": "Protein of unknown function DUF58", "partial_evidence_count": null, "pfam_id": "PF01882", "proteins": 31251, "proteomes": 13552, "short_name": "DUF58", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01882", "structures": 0, "taxa": 18964, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15881, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This domain contains several highly conserved charged amino acids, suggesting this may be an enzymatic domain (Bateman A pers. obs). The entry includes SanA [swissprot:P33017] and Sfix ([swissprot:O33790]) from Salmonella typhimurium which are involved in Vancomycin resistance [[cite:PUB00019464]]. These proteins may be involved in murein synthesis [[cite:PUB00019465]]. This domain is found in Escherichia coli YdcF, which has been shown to bind S-adenosyl-L-methionine (AdoMet), but whose biochemical function has not been identified [[cite:PUB00050945]].", "domain_architectures": 92, "interpro_id": "IPR003848", "known_evidence_count": null, "matches": 25685, "name": "DUF218 domain", "partial_evidence_count": null, "pfam_id": "PF02698", "proteins": 25685, "proteomes": 14217, "short_name": "DUF218", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02698", "structures": 1, "taxa": 20830, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 16566, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This domain is found at the C terminus of the YchF GTP-binding protein ([swissprot:O13998]) and is possibly related to the ubiquitin-like and MoaD/ThiS superfamilies.", "domain_architectures": 137, "interpro_id": "IPR013029", "known_evidence_count": null, "matches": 23716, "name": "Protein of unknown function (DUF933)", "partial_evidence_count": null, "pfam_id": "PF06071", "proteins": 23701, "proteomes": 20956, "short_name": "YchF-GTPase_C", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF06071", "structures": 12, "taxa": 34445, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 17164, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This domain family is found in plants, and is approximately 100 amino acids in length. Considering the very diverse range of other domains it is associated with it is possible that this domain is a binding/guiding region. There are two highly conserved tryptophan residues.", "domain_architectures": 1056, "interpro_id": "IPR025558", "known_evidence_count": null, "matches": 23565, "name": "Domain of unknown function (DUF4283)", "partial_evidence_count": null, "pfam_id": "PF14111", "proteins": 23437, "proteomes": 339, "short_name": "DUF4283", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14111", "structures": 0, "taxa": 984, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 15479, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This entry (ex DUF4371) represents a RNase-like domain in Zinc finger MYM-type protein 1 (ZMYM1), FAM200 and similar proteins mainly found in animals. FAM200 is characterised by its involvement in cellular regulatory processes, its precise function remains to be elucidated.", "domain_architectures": 951, "interpro_id": "IPR025398", "known_evidence_count": null, "matches": 22713, "name": "ZMYM1/FAM200, RNase-like domain", "partial_evidence_count": null, "pfam_id": "PF14291", "proteins": 21818, "proteomes": 1267, "short_name": "DUF4371", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14291", "structures": 0, "taxa": 4275, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 17072, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "The function of the plant proteins constituting this family is unknown.", "domain_architectures": 302, "interpro_id": "IPR004158", "known_evidence_count": null, "matches": 23865, "name": "Plant protein of unknown function", "partial_evidence_count": null, "pfam_id": "PF03140", "proteins": 21663, "proteomes": 386, "short_name": "DUF247", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03140", "structures": 0, "taxa": 1061, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 12110, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This is a family of proteins of unknown function. Most of the members are gag-polyproteins.", "domain_architectures": 1118, "interpro_id": "IPR005312", "known_evidence_count": null, "matches": 21116, "name": "Protein of unknown function (DUF1759)", "partial_evidence_count": null, "pfam_id": "PF03564", "proteins": 20944, "proteomes": 467, "short_name": "DUF1759", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF03564", "structures": 0, "taxa": 1789, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13058, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This domain is found in uncharacterised proteins from bacteria, archaea and eukaryotes, including NTF2-Like SgcJ protein from Streptomyces carzinostaticus, which plays a role in the biosynthesis of the 9-membered enediyne antitumor antibiotic C-1027. It shows a cone-like alpha+beta barrel structure with a long N-terminal alpha- helix, a curved six-stranded antiparallel beta-sheet and two additional shorter alpha-helices. Its specific function is still unkown [[cite:PUB00100883]].", "domain_architectures": 127, "interpro_id": "IPR027843", "known_evidence_count": null, "matches": 21018, "name": "Domain of unknown function (DUF4440)", "partial_evidence_count": null, "pfam_id": "PF14534", "proteins": 20901, "proteomes": 9416, "short_name": "DUF4440", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF14534", "structures": 14, "taxa": 13277, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11735, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This presumed domain is found in a range of retrotransposon polyproteins.", "domain_architectures": 1120, "interpro_id": "IPR040676", "known_evidence_count": null, "matches": 20760, "name": "Family of unknown function (DUF5641)", "partial_evidence_count": null, "pfam_id": "PF18701", "proteins": 20636, "proteomes": 472, "short_name": "DUF5641", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF18701", "structures": 0, "taxa": 1848, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 13291, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This family consists of hypothetical proteins some of which are putative membrane proteins. No functional information or experimental verification of function is known. This domain is around 100 amino acids long.", "domain_architectures": 173, "interpro_id": "IPR003807", "known_evidence_count": null, "matches": 18687, "name": "Domain of unknown function (DUF202)", "partial_evidence_count": null, "pfam_id": "PF02656", "proteins": 18669, "proteomes": 7356, "short_name": "DUF202", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02656", "structures": 3, "taxa": 11815, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11006, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "", "domain_architectures": 113, "interpro_id": "IPR025161", "known_evidence_count": null, "matches": 18631, "name": "Putative transposase of IS4/5 family (DUF4096)", "partial_evidence_count": null, "pfam_id": "PF13340", "proteins": 18629, "proteomes": 5344, "short_name": "DUF4096", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF13340", "structures": 0, "taxa": 8051, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 12676, "candidate_reasons": [ "name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This family includes the DUF34/metal-binding protein/NIF3 proteins, which are widely distributed across superkingdoms. They were previously annotated as GTP cyclohydrolase 1 type 2 [[cite:PUB00070175]] and, recently, through a comprehensive literature review and integrative bioinformatics analyses it was revealed that annotations for these members were misleading as they were based on a single set of in vitro results examining the NIF3 homolog of Helicobacter pylori [[cite:PUB00070175]]. Actually, they have varied phenotypes with the unifying functional role as metal-binding proteins [[cite:PUB00100327]]. This entry contains several NIF3 (NGG1p interacting factor 3) protein homologues. NIF3 interacts with the yeast transcriptional coactivator NGG1p which is part of the ADA complex, the exact function of this interaction is unknown [[cite:PUB00002954],[cite:PUB00019927]].", "domain_architectures": 53, "interpro_id": "IPR002678", "known_evidence_count": null, "matches": 18654, "name": "Duf34/NIF3 (NGG1p interacting factor 3)", "partial_evidence_count": null, "pfam_id": "PF01784", "proteins": 18574, "proteomes": 16807, "short_name": "DUF34_NIF3", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF01784", "structures": 16, "taxa": 26806, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 11207, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This family is often found associated to the N-terminus of the HNH endonuclease domain [pfam:PF01844]. The function of this domain is uncertain. This family has been called the 13E12 repeat family [[cite:PUB00057273]].", "domain_architectures": 37, "interpro_id": "IPR003870", "known_evidence_count": null, "matches": 19420, "name": "Domain of unknown function (DUF222)", "partial_evidence_count": null, "pfam_id": "PF02720", "proteins": 18467, "proteomes": 2216, "short_name": "DUF222", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF02720", "structures": 0, "taxa": 2801, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11286, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function", "domain_of_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This domain is found in the Intracellular iron chaperone frataxin YdhG [[cite:PUB00098100]] and the uncharacterised protein YdeI from Bacillus subtilis.", "domain_architectures": 33, "interpro_id": "IPR014922", "known_evidence_count": null, "matches": 18242, "name": "Domain of unknown function (DU1801)", "partial_evidence_count": null, "pfam_id": "PF08818", "proteins": 18172, "proteomes": 8371, "short_name": "DUF1801", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF08818", "structures": 4, "taxa": 11668, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 11560, "candidate_reasons": [ "short_name_matches_duf" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This presumed domain is found at the N-terminus of many proteins found in transposons.", "domain_architectures": 78, "interpro_id": "IPR008490", "known_evidence_count": null, "matches": 17574, "name": "Transposase domain (DUF772)", "partial_evidence_count": null, "pfam_id": "PF05598", "proteins": 17572, "proteomes": 6555, "short_name": "DUF772", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF05598", "structures": 0, "taxa": 10733, "unknown_status": "KNOWN_HISTORICAL_DUF" }, { "alphafold_models": 14906, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This entry represents a large family of fungal integral membrane proteins.", "domain_architectures": 216, "interpro_id": "IPR045339", "known_evidence_count": null, "matches": 17391, "name": "Family of unknown function (DUF6534)", "partial_evidence_count": null, "pfam_id": "PF20152", "proteins": 17299, "proteomes": 298, "short_name": "DUF6534", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20152", "structures": 0, "taxa": 744, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 9780, "candidate_reasons": [ "short_name_matches_duf", "name_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "This presumed domain is found at the C-terminus of bacterial RNA polymerase ECF sigma factor proteins.", "domain_architectures": 42, "interpro_id": "IPR046531", "known_evidence_count": null, "matches": 16823, "name": "Family of unknown function (DUF6596)", "partial_evidence_count": null, "pfam_id": "PF20239", "proteins": 16812, "proteomes": 6132, "short_name": "DUF6596", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF20239", "structures": 0, "taxa": 8083, "unknown_status": "UNKNOWN_CANDIDATE" }, { "alphafold_models": 10934, "candidate_reasons": [ "name_matches_duf", "name_says_unknown_function", "description_says_unknown_function" ], "characterization_status": "", "context_evidence_count": null, "demotion_reasons": [], "description": "Members of this family have so far been found in bacteria and mouse SwissProt or TrEMBL entries. However possible family members have also been identified in translated rat (Genbank:AW144450) and human (Genbank:AI478629) ESTs. A mouse family member has been named SIMPL (signalling molecule that associates with mouse pelle-like kinase). SIMPL appears to facilitate and/or regulate complex formation between IRAK/mPLK (IL-1 receptor-associated kinase) and IKK (inhibitor of kappa-B kinase) containing complexes, and thus regulate NF-kappa-B activity [[cite:PUB00010115]]. Separate experiments demonstrate that a mouse family member (named LaXp180) binds the Listeria monocytogenes surface protein ActA, which is a virulence factor that induces actin polymerisation. It may also bind stathmin, a protein involved in signal transduction and in the regulation of microtubule dynamics [[cite:PUB00009982]]. In bacteria its function is unknown, but it is thought to be located in the periplasm or outer membrane.", "domain_architectures": 17, "interpro_id": "IPR007497", "known_evidence_count": null, "matches": 16828, "name": "Protein of unknown function (DUF541)", "partial_evidence_count": null, "pfam_id": "PF04402", "proteins": 16767, "proteomes": 13193, "short_name": "SIMPL", "source_url": "https://www.ebi.ac.uk/interpro/api/entry/pfam/PF04402", "structures": 3, "taxa": 20114, "unknown_status": "UNKNOWN_CANDIDATE" } ] } }