An AI co-scientist and research observatory for BERDL-scale microbial discovery — powered by reusable skills, shared memory, and scalable data.
A human-in-the-loop AI research workflow that plans analyses, executes them on BERDL, synthesizes findings with literature context, and captures lessons learned for future projects. Each project produces reusable skills, memory, and data products.
Explore curated data collections across the BERDL lakehouse, browse completed research projects with full reports, and discover findings documented with figures, citations, and reproducible notebooks.
Knowledge compounds across projects. Each analysis adds to a growing base of skills, memory, and discoveries that accelerates future research.
20 reusable tools for querying BERDL, searching literature, synthesizing findings, and more.
Pitfalls, performance tips, and query patterns captured from real analyses to avoid repeating mistakes.
143 curated research findings documented with statistical evidence and biological context.
M22 Sankoff parsimony attribution of 17M gain events on the GTDB-r214 species tree, classified into 5 acquisition-depth bins (recent / older_recent / mid / older / ancient), produces clean signatures ...
Family-rank Cohen's d for Mycobacteriaceae × mycolic-acid (NB12) was d=0.31 producer-side, supporting H2 Innovator-Isolated. The leaf_consistency layer (NB28e: per-(rank × clade × KO) species-prevalen...
For each pre-registered atlas finding (NB12 mycolic, NB16 PSII, Phase 1B Bacteroidota PUL), three independent measurement substrates produced convergent evidence: (1) atlas Cohen's d on Sankoff-derive...
How does sequential enrichment on lignin, with or without labile carbon supplementation, shape bacterial and fungal community composition — and does e...
Across the BERDL lakehouse, the label "NMDC" is attached to tenants, databases, and tables whose provenance, depth, breadth, completeness, and added v...
Across the 293K-genome BERDL pangenome, how are seven of the major anti-phage defense system families (CRISPR-Cas, restriction-modification, CBASS, Ga...
kbase_all_the_bacteria
Discovered BERDL database. Add curated description as this collection is used.
kbase_genomes
Structural genomics data including contigs, features, and protein sequences from the KBase genome repository.
kbase_ke_pangenome
Pangenome data for 293,059 genomes across 27,690 microbial species derived from GTDB r214. Includes core/accessory gene classification, functional annotations, and ANI relationships.