Research

Evidence-grounded target validation scoring with GO/NO-GO decisions for drug discovery campaigns

Count rare, high-impact loss-of-function variants carried in a VCF, annotated with molecular consequence and population allele frequency

Unified personal genomic profile report — reads a PatientProfile JSON and synthesizes all skill results into

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

Personalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant

Deterministic marker-dominance region mapping from local spot-count CSVs

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

HLA allele typing from WGS/WES VCF data

Statistical fine-mapping of GWAS loci using SuSiE, SuSiE-inf, and Approximate Bayes Factors to identify credible

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

Population genetics of pre-aligned DNA sequences or multi-sample VCFs

Transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Scores a 224x224 tile and returns per-gene log1p-CPM values for any HGNC symbols you ask for, with a CSV, a report and a reproducibility bundle.

Deterministic CRISPR screen hit ranking from local guide-level count tables

Classify structural variants / copy-number variants (deletions and duplications) using the ClinGen / ACMG 2019 (Riggs et al. 2020) point framework and return a five-tier classification with a per-section evidence trail. Germline CNV interpretation, not SNV/indel.

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

Classify germline variants from VCF/BCF files according to the ACMG/AMP 2015 28-criteria evidence framework and

Screen a genotype set (array or WGS-derived) against OMIM-morbid, ACMG-SF and Hereditary-Cancer gene panels and prioritise carried variants by ClinVar significance, gnomAD frequency, inheritance model and zygosity, following the pathogenicity-screening method of Corpas et al. 2021 (Whole Genome Interpretation for a Family of Five).

'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

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.

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

Search scientific papers via the BGPT MCP server and retrieve structured experimental data — methods, results,

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.

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.

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.