ClawBio

Unified analysis pipeline for affinity-based proteomics platforms — Olink (PEA, NPX) and SomaLogic SomaScan (SOMAmer, RFU). Platform-aware QC, normalisation, differential abundance, volcano plots, heatmaps, and PCA.

Analyze a single FASTA file (nucleotide or protein), compute sequence-level metrics (GC, ORFs, MW, pI, GRAVY, secondary-structure fractions) with Biopython, and write a Markdown report plus structured JSON for downstream chaining.

Infers genetic super-population ancestry from a 23andMe/AncestryDNA file and computes ancestry-stratified odds ratios with an exploratory Ancestry Elevation Score (AES) showing where ancestry-specific GWAS effect sizes diverge from European reference estimates. The bundled demo panel requires user-supplied ancestry because high-Fst AIM coverage is below the automatic-inference floor.

Detect Neanderthal and Denisovan introgression segments from modern human genomes

Query metadata and download data from ArrayExpress, EMBL-EBI's functional genomics collection, now hosted inside BioStudies. Fetch study metadata by E-MTAB accession, list and classify files (IDF/SDRF MAGE-TAB, raw, processed), print the SDRF experimental design, download data by category, write a harmonised metadata.tsv, and build an nf-core/rnaseq or nf-core/scrnaseq samplesheet.csv from the SDRF.

Given an article DOI or PubMed ID, discover and download the genomics data files deposited by the authors (VCF, FASTA, H5AD, CSV, JSON, BAM, etc.) from public repositories such as GEO, ENA, Zenodo, Figshare, Dryad, and OSF.

Search scientific papers via the BGPT MCP server and retrieve structured experimental data — methods, results, conclusions, quality scores, and 25+ metadata fields per paper.

Run read-only SQL against BigQuery public datasets with local result capture, cost safeguards, and reproducibility outputs.

Bioconductor package discovery, workflow recommendation, setup inspection, and starter code generation grounded in official Bioconductor containers and BiocManager.

Meta-agent that routes bioinformatics requests to specialised sub-skills. Handles file type detection, analysis planning, report generation, and reproducibility export.

Automated sequencing quality control and advanced visualization wrapping FastQC, MultiQC, and custom chart generation. Exposes an MCP stdio server for live AI integration alongside a ClawBio CLI runner.

Query metadata and download data from EMBL-EBI BioStudies, the database that describes biological studies and links their data across collections (ArrayExpress, BioImages, BioModels, EGA-linked studies and standalone submissions). Fetch study metadata by accession, list and download attached files, search across collections, and write a harmonised metadata.tsv.

Genome, transcriptome, and protein completeness assessment via BUSCO v6. Agentic lineage routing from organism description, all three BUSCO modes, auto-lineage support, and full demo mode without the BUSCO binary.

Cell segmentation in fluorescence microscopy images. Supports Cellpose/cpsam (Cellpose 4.0) with additional backends planned. Produces segmentation masks, per-cell morphology metrics (area, diameter, centroid, eccentricity), overlay figures, and a report.md.

Given a gene and a single-cell atlas, compute how cell-type-specific its expression is — the tau specificity index, Sarle's expression bimodality coefficient, and the cell types that drive the signal; a pure analytic transform that chains downstream of scrna-embedding.

16S/18S rRNA amplicon preprocessing — from raw paired-end FASTQ files through N removal and primer trimming, producing outputs ready for DADA2 quality filtering and denoising. Deliberately stops before quality-filtering decisions that require researcher judgment.

Ancestry decomposition PCA against the Simons Genome Diversity Project

Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways

Methylation cycle analysis — enzymatic activity profiles, Net Methylation Capacity, BH4 axis estimates, compound heterozygosity detection from SNP genotype data.

Eval-driven skill tuning. Given a task and an LLM-judge rubric, iteratively rewrites a SKILL.md until a downstream executor agent performs well against the judge. Low-code: all evaluation is LLM-as-judge, not deterministic Python.