ClawBio

Local scVI/scANVI-based single-cell latent embedding and batch-aware integration from raw-count .h5ad or 10x Matrix Market input, with stable integrated AnnData export for downstream latent analysis.

Differential expression analysis for bulk RNA-seq and pseudo-bulk count matrices with QC, PCA, and contrast testing.

Genomic coordinates of introgressed segments

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

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

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

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.

Ancestry analysis report with population assignments and statistics

Classify germline variants from VCF/BCF files according to the ACMG/AMP 2015 28-criteria evidence framework and generate clinical-grade interpretation reports with per-variant evidence audit trails and ACMG SF v3.2 secondary findings screening.

Compute HEIM diversity and equity metrics from VCF or ancestry data. Generates heterozygosity, FST, PCA plots, and a composite HEIM Equity Score with markdown reports.

Statistical fine-mapping of GWAS loci using SuSiE, SuSiE-inf, and Approximate Bayes Factors to identify credible sets and posterior inclusion probabilities (PIPs) for causal variant discovery. SuSiE-inf adds an infinitesimal polygenic component for improved calibration at well-powered loci.

Unified personal genomic profile report — reads a PatientProfile JSON and synthesizes all skill results into a single "Your Genomic Profile" document.

30 synthetic BMI->T2D instruments for offline demo

List all available ClawBio bioinformatics skills with their status and capabilities

Pre-generated demo report for 5 clinically relevant variants

Professional clinical report in Spanish with interpretation, tables, and disclaimer

commands.sh, environment.yml, checksums.sha256

Extract numerical data from scientific figure images using Claude vision + OpenCV calibration. Supports 26+ plot types including bar charts, scatter plots, forest plots, Kaplan-Meier curves, box plots, and more.

Rich downstream visualisation and reporting for bulk RNA-seq differential expression and scRNA marker/contrast outputs.

Structured paper data with 25+ fields per result

Semantic Similarity Index for disease research literature using PubMedBERT embeddings

Compare your genome to George Church (PGP-1) and estimate ancestry composition via IBS and EM admixture

Search PubMed for a gene name or disease term and generate a structured research briefing of the top recent English-language papers.

Produce offspring genomes from parent pairs via meiotic recombination, mutation, and clinical evaluation

Search, browse, and retrieve scientific protocols from protocols.io via REST API. Client token authentication for private protocols. Use when user mentions protocols.io, lab protocols, DOI lookup, protocol search, protocol steps, or scientific methods.

Local Scanpy pipeline for single-cell RNA-seq QC, optional doublet detection, clustering, marker discovery, optional CellTypist annotation, optional latent downstream mode from integrated.h5ad/X_scvi, and optional dataset-level plus within-cluster contrastive marker analysis from raw-count .h5ad or 10x Matrix Market input.

Pre-generated demo report for two synthetic samples

Run a ClawBio skill demo with built-in sample data

Query the ClinPGx API for pharmacogenomic gene-drug data, clinical annotations, CPIC guidelines, and FDA drug labels

Synthetic test data

Galaxy tool discovery, intelligent recommendation, and execution — 8,000+ bioinformatics tools from usegalaxy.org with multi-signal scoring and workflow suggestions

Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.

Aggregate public target-level evidence across omics and translational sources for research triage.

Bundled synthetic 20-variant VCF used for demo mode

Professional clinical report with interpretation, tables, and disclaimer

Calculate polygenic risk scores from DTC genetic data using the PGS Catalog

Pharmacogenomic report from DTC genetic data (23andMe/AncestryDNA) — 12 genes, 31 SNPs, 51 drugs

Query and display Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy. Supports offline demo mode with synthetic biology data.

Protein structure prediction with Boltz-2. Accepts YAML inputs (single protein or multi-chain complex), runs boltz predict, extracts per-residue pLDDT and PAE confidence, and writes a markdown report with figures.

commands.sh, environment.yml, checksums.sha256

Compile SOUL.md character profiles into synthetic diploid genomes (.genome.json) via trait-to-allele mapping

Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance

Compute epigenetic age from DNA methylation arrays using PyAging clocks from GEO accessions or local files.

Synthetic target validation query for TGFBR1/IPF with pre-cached evidence

Personalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant SNPs and generates actionable dietary guidance, all computed locally.

Pre-generated demo report for CRISPR genome editing query

Synthetic query for BRCA1 breast cancer trials — exercises recruiting and completed status paths

Differential expression analysis for label-free quantitative (LFQ) intensity data with standard MaxQuant and DIA-NN output. Workflow includes preprocessing, imputation, and statistical testing.

Import DRAGEN-exported Illumina result bundles into ClawBio for local tertiary analysis and downstream routing.

Semantic search across UK Biobank's 12,000+ data fields and publications — find the right variables for your research question.

Score genetic compatibility across all male-female pairings in a Genomebook generation

Synthetic FastQC output for 3 samples (generated at runtime into a tempdir)

Export any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.

Run a ClawBio bioinformatics analysis on user-provided genetic data