CultureBotAI — KG-Microbe Knowledge Graph for AI-Driven Microbial Cultivation 🦠

CultureBotAI is a research initiative at Lawrence Berkeley National Laboratory in Berkeley, California, developing AI-driven tools and knowledge graphs for microbial cultivation and computational biology.

Led by Dr. Marcin P. Joachimiak, CultureBotAI focuses on the KG-Microbe knowledge graph and AI-powered solutions for microbial research, cultivation, and analysis.

About Us

CultureBotAI is affiliated with Lawrence Berkeley National Laboratory and develops AI-powered solutions for microbial research, cultivation, and analysis. We create intelligent tools that enhance laboratory workflows, optimize culture conditions, and accelerate microbiological discoveries.

Principal Investigator: Dr. Marcin P. Joachimiak (BBOP) Laboratory: Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory Location: Berkeley, California, USA

Our Focus

Our primary research areas include:

  • Cultivation of isolated and novel organisms
  • Culture optimization through data-driven approaches
  • Growth preference prediction using machine learning and AI methods

Key Resources

🧬 KG-Microbe Knowledge Graph

The comprehensive modular knowledge graph that powers CultureBotAI, developed by Dr. Marcin P. Joachimiak. This resource integrates diverse microbial data to enable AI-driven insights.

📄 KG-Microbe Publication

Read our peer-reviewed GigaScience paper by Dr. Marcin P. Joachimiak detailing the development and applications of the KG-Microbe knowledge graph.

🤖 AI Curation Tools — X-Mech Suite

The X-Mech suite (CultureMech, MediaIngredientMech, CommunityMech, TraitMech, ProteinTraitsMech) provides AI-powered curation of microbial cultivation records, transforming unstructured literature data into standardized knowledge graphs with 10,000+ media recipes, 477 ecophysiological traits, and 400,000+ protein traits.

🧠 MicroGrowAgents

Multi-agent AI system for microbial cultivation and growth media design across 864,363 validated species — GitHub repository (private repository — public release planned) · bioRxiv preprint

🧮 KOGUT Transformer

Relational graph transformer for link prediction over kg-microbe, trained for growth media prediction on 1.3M nodes and 3.0M edges. Registered as DOE CODE 175162; no public repository yet.

📐 Explainable Media Prediction

Human-readable rules that predict cultivation media from microbial traits — the interpretable counterpart to our neural models, published in Computational and Structural Biotechnology Journal. The RuleML/GOBLIN lecture reports accuracy comparable to state-of-the-art, illustrated by a rule of the form if β-galactosidase activity and isolated from a marine environment, then 87% likely to grow on Marine Broth.

📊 METPO Ontology

The Microbial Ecophysiological Trait and Phenotype Ontology, used to standardize growth preference data and to drive text extraction in kg-microbe. Also on BioPortal.

How Our Tools Work Together

CultureBotAI’s projects form an integrated ecosystem built on the kg-microbe knowledge graph:

  • AI curation pipelines (X-Mech suite) transform unstructured cultivation data into standardized knowledge graphs
  • Data processing pipelines prepare chemical, genomic, and literature data
  • AI agent systems combine multiple data sources for intelligent predictions
  • Prediction models range from interpretable rule mining to graph transformers (KOGUT)
  • Specialized applications target specific research domains (PFAS biodegradation, lanthanide bioprocessing)
  • Web services provide API access to prediction models

Explore the complete project ecosystem →

Frequently Asked Questions

What is CultureBotAI?

CultureBotAI is a research initiative at Lawrence Berkeley National Laboratory in Berkeley, California, that develops AI-driven tools and knowledge graphs for microbial cultivation and computational biology.

Who leads CultureBotAI?

CultureBotAI is led by Dr. Marcin P. Joachimiak, a staff researcher specializing in microbiology, knowledge graph development, and computational biology at Lawrence Berkeley National Laboratory.

What does CultureBotAI work on?

CultureBotAI focuses on three main areas: (1) cultivation of isolated and novel organisms, (2) culture optimization through data-driven approaches, and (3) growth preference prediction using machine learning and AI methods.

Where is CultureBotAI based?

CultureBotAI is based at Lawrence Berkeley National Laboratory in Berkeley, California, within the Environmental Genomics and Systems Biology Division.

What is KG-Microbe?

KG-Microbe is a comprehensive modular knowledge graph developed by Dr. Marcin P. Joachimiak that integrates diverse microbial data sources to enable AI-driven insights for growth prediction and culture optimization.

How can I access KG-Microbe?

KG-Microbe is available on GitHub at https://github.com/Knowledge-Graph-Hub/kg-microbe under the BSD-3-Clause license. The publication is available in GigaScience at https://doi.org/10.1093/gigascience/giag077

Bibliography

  1. Santangelo BE, Hegde H, Caufield JH, Reese J, Kliegr T, Hunter LE, Lozupone CA, Mungall CJ, Joachimiak MP. KG-Microbe — Building Modular and Scalable Knowledge Graphs for Microbiome and Microbial Sciences. GigaScience. 2026;giag077. doi:10.1093/gigascience/giag077
  2. Máša P, Kliegr T, Joachimiak MP. Explainable rule-based prediction of cultivation media for microbes. Computational and Structural Biotechnology Journal. 2025;27:5194–5206. doi:10.1016/j.csbj.2025.10.014 · free full text
  3. Naseem S, Miller MA, Martinez-Gomez NC, Sun N, Joachimiak MP. MicroGrowAgents: An Agentic AI System for Microbial Cultivation Engineering. bioRxiv. 2026. doi:10.64898/2026.06.04.729985
  4. Joachimiak MP. Knowledge Oriented Graph Unified Transformer (KOGUT) v0.1 [software]. DOE CODE; 2025. doi:10.11578/dc.20260210.3 · DOE CODE 175162
  5. Joachimiak MP. “RuleML/GOBLIN COST Action Lecture on Data Science: Teaching AI to Teach Humans About Microbiology” [talk]. RuleML / COST GOBLIN Action Seminar; 2026. Recording

Full publication list →

Cultivating the future of microbial research, one algorithm at a time.