ClawBio
- 116 skills
- 0 followers
- 1.2k repo stars
- yesterday last updated
- ▌ Vcf Annotator 2 · clawbio bundleAnnotate VCF variants with Ensembl VEP, ClinVar, and gnomAD. Ranks variants by impact (HIGH/MODERATE/LOW/MODIFIER) and generates a reproducible report.
- ▌ Mendelian Randomisation 2 · clawbio bundleTwo-sample Mendelian Randomisation from GWAS summary statistics with IVW, MR-Egger, weighted median/mode, and full sensitivity analysis (Cochran Q, Egger intercept, Steiger, F-statistic, leave-one-out).
- ▌ Prs Abstain · clawbio bundleGates polygenic risk score percentiles on trait applicability, score integrity and ancestry transferability, withholding the percentile when it would be uninterpretable and attributing the error to individual SNPs.
- ▌ Fine Mapping · clawbio bundleStatistical 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.
- ▌ Claw Ancestry Pca · clawbio bundleAncestry decomposition PCA against the Simons Genome Diversity Project
- ▌ Organ Aging Studio · clawbio bundleInteractive Goeminne proteomic aging clock with organ filters and per-protein contribution breakdown (protein NPX × coefficient). Agent- and demo-friendly.
- ▌ Affinity Proteomics · clawbio bundleUnified 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.
- ▌ Rare Disease Rnaseq · clawbio bundleBlood RNA-seq expression-outlier detection for rare-disease diagnostics. Cases scored against a control reference panel; outliers ranked and filtered by a haploinsufficient disease-gene panel.
- ▌ Dnasp · clawbio bundlePopulation genetics of pre-aligned DNA sequences or multi-sample VCFs using selected DnaSP 6 methods. Use for diversity, neutrality statistics, linkage disequilibrium, InDel polymorphism, divergence, MK, Ka/Ks and codon usage; not alignment, phasing or clinical interpretation.
- ▌ Nutrigx 2 · clawbio bundlePersonalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant SNPs and generates actionable dietary guidance, all computed locally.
- ▌ Gwas Prs 2 · clawbio bundleCalculate polygenic risk scores from DTC genetic data using the PGS Catalog
- ▌ Gi Expression 2 · clawbio bundlePredict tissue / cell-type expression (log TPM + TPM) from 9,198–500,000 bp of DNA around a TSS, at least 4,599 bp each side (anything but exactly 9,198 bp needs --tss-index) using the Genomic Intelligence G0 Expression model, via the hosted /v1/tasks/expression/predict API. The model is conditioned on a free-text cell-type / assay description.
- ▌ Skill Builder 2 · clawbio bundleScaffold a new ClawBio skill from a spec file (JSON/YAML) or interactively — generates SKILL.md, Python skeleton, tests, and updates catalog.json
- ▌ Clinical Variant Reporter · clawbio bundleClassify 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.
- ▌ Gwas Catalog Region Fetch · clawbio bundleFetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP. Use when an agent needs GWAS beta / SE / p-value for every variant in a window for one specific study (GCST accession). Input: accession, chromosome, start, end. Output: harmonised TSV slice in canonical format.
- ▌ Rare High Impact Variants · clawbio bundleCount rare, high-impact loss-of-function variants carried in a VCF, annotated with molecular consequence and population allele frequency
- ▌ Locuscompare Region Render · clawbio bundleRender a 4-panel regional LocusCompare diagnostic for one (lead variant, exposure study, outcome study) tuple - overlays GWAS Manhattan, QTL Manhattan, GENCODE gene track, and cross-trait scatter colored by LD r². Use when an agent needs visual confirmation that two GWAS / QTL signals share the same causal variant (the Liu 2019 LocusCompare convention). Inputs: lead variant + two pre-fetched harmonised sumstats slices (or eQTL Catalogue / GWAS Catalog identifiers for bundled fetch). Output: PNG + JSON manifest.
- ▌ Eqtl Catalogue Region Fetch · clawbio bundleFetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP. Use when an agent needs eQTL beta / SE / p-value for every variant in a window around a gene's TSS for one specific dataset (study × tissue × quantification method). Input: dataset_id, chromosome, start, end, optional molecular_trait_id. Output: harmonised TSV slice.
- ▌ Xena Tcga Gene Query · clawbio bundleQuery TCGA tumor biology through the ucscxenatoolspy API. Supports tumor-vs-normal differential expression, gene-gene correlation, survival association, and cancer catalogue browsing across 30+ TCGA cancer types.
- ▌ Archaic Introgression · clawbio bundleDetect Neanderthal and Denisovan introgression segments from modern human genomes
- ▌ Nfcore Rnaseq Wrapper · clawbio bundleWrapper skill for running nf-core/rnaseq bulk RNA-seq preprocessing from FASTQ or BAM inputs with strict preflight, reproducibility outputs, and downstream handoff to ClawBio bulk RNA-seq DE skills.
- ▌ Phylogenetics Builder · clawbio bundleEnd-to-end ML phylogenetic tree inference — MSA, trimming, ModelFinder, IQ-TREE2/RAxML-NG.
- ▌ Ancestry Risk Profiler · clawbio bundleInfers 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.
- ▌ Claw Methylation Cycle · clawbio bundleMethylation cycle analysis — enzymatic activity profiles, Net Methylation Capacity, BH4 axis estimates, compound heterozygosity detection from SNP genotype data.
- ▌ Drug Repurposing Screen · clawbio bundleObjective-driven pooled viability screen analysis: QC, hit calling, context-selectivity, biomarker sweep, and ranked repurposing candidates. Format-agnostic via schema.yaml + objective.yaml; includes offline demo.
- ▌ Ld 1000g Region Compute · clawbio bundleCompute pairwise r² between a lead variant and every variant in a window using the 1000 Genomes Phase 3 GRCh38 reference panel, ancestry-stratified. Use when an agent needs LD coloring for a regional plot or LD pruning around a candidate causal variant. Single client (on-demand region fetch from EBI 1000G FTP); no multi-GB cold-start.
- ▌ Marker Dominance Mapper · clawbio bundleDeterministic marker-dominance region mapping from local spot-count CSVs
- ▌ Mendelian Randomisation · clawbio bundleTwo-sample Mendelian Randomisation from GWAS summary statistics with IVW, MR-Egger, weighted median/mode, and full sensitivity analysis (Cochran Q, Egger intercept, Steiger, F-statistic, leave-one-out).
- ▌ Nfcore Scrnaseq Wrapper · clawbio bundleWrapper skill for running nf-core/scrnaseq 4.1.0 upstream single-cell RNA-seq preprocessing from FASTQ with strict preflight, reproducibility outputs, and downstream handoff to ClawBio scRNA skills.
- ▌ Variant Annotation · clawbio bundleAnnotate VCF variants with Ensembl VEP REST, ClinVar significance, gnomAD/population frequency context, and prioritized variant ranking.
- ▌ Bioconductor Bridge · clawbio bundleBioconductor package discovery, workflow recommendation, setup inspection, and starter code generation grounded in official Bioconductor containers and BiocManager.
- ▌ Clinical Trial Finder · clawbio bundleFind clinical trials for a gene, variant, or condition from ClinicalTrials.gov + EUCTR, with FHIR R4 output
- ▌ Target Validation Scorer · clawbio bundleEvidence-grounded target validation scoring with GO/NO-GO decisions for drug discovery campaigns
- ▌ Omics Target Evidence Mapper · clawbio bundleAggregate public target-level evidence across omics and translational sources for research triage.
- ▌ Bigquery Public · clawbio bundleRun read-only SQL against BigQuery public datasets with local result capture, cost safeguards, and reproducibility outputs.
- ▌ Sample Qc Triage · clawbio bundleDeterministic multi-sample QC triage for identity, sex, contamination, and batch-shift outliers
- ▌ Article Data Fetcher · clawbio bundleGiven 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.
- ▌ Crispr Screen Triage · clawbio bundleDeterministic CRISPR screen hit ranking from local guide-level count tables
- ▌ Nfcore Sarek Wrapper · clawbio bundleClawBio wrapper around nf-core/sarek 3.8.1 covering mapping through annotation for germline, tumor-only, and somatic paired analyses.
- ▌ Ukb Ppp Region Fetch · clawbio bundleFetch a regional slice of plasma pQTL summary statistics from the UK Biobank Pharma Proteomics Project (UKB-PPP; Sun 2023 Nature) for a specific (protein, ancestry) measurement. Use when an agent needs per-variant beta / SE / p-value around a coloc-lead variant for downstream colocalisation, Mendelian randomisation, or regional plotting against a pQTL exposure. The canonical use case is the cis-window around the protein's coding gene TSS, but UKB-PPP releases full-genome summary stats per protein so any GRCh38 window (including trans loci) is supported when the user supplies an explicit (chromosome, start_bp, end_bp). Input: protein_label (HGNC or UniProt), ancestry, chromosome, start_bp, end_bp. Output: harmonised TSV slice + manifest + human-readable report.
- ▌ Profile Report · clawbio bundleUnified personal genomic profile report — reads a PatientProfile JSON and synthesizes all skill results into a single "Your Genomic Profile" document.
- ▌ Repro Enforcer · clawbioExport any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.
- ▌ Diff Visualizer · clawbio bundleRich downstream visualisation and reporting for bulk RNA-seq differential expression and scRNA marker/contrast outputs.
- ▌ Illumina Bridge · clawbio bundleImport DRAGEN-exported Illumina result bundles into ClawBio for local tertiary analysis and downstream routing.
- ▌ Lit Synthesizer · clawbio bundleSearch PubMed and bioRxiv for bioinformatics literature, synthesise results into a structured report, and build a citation graph — all locally, with a reproducibility bundle.
- ▌ Scrna Embedding · clawbio bundleLocal 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.
- ▌ Bio Orchestrator · clawbio bundleMeta-agent that routes bioinformatics requests to specialised sub-skills. Handles file type detection, analysis planning, report generation, and reproducibility export.
- ▌ Pharmgx Reporter · clawbio bundlePharmacogenomic report from DTC genetic data (23andMe/AncestryDNA) — 12 genes, 31 SNPs, 51 drugs
- ▌ Struct Predictor · clawbio bundleProtein structure prediction with Boltz-2 (default) or OpenFold3. Accepts YAML inputs (single protein or multi-chain complex), runs the chosen backend offline, extracts per-residue pLDDT and PAE confidence, and writes a markdown report with figures.
- ▌ Claw Semantic Sim · clawbioSemantic Similarity Index for disease research literature using PubMedBERT embeddings
- ▌ Methylation Clock · clawbio bundleCompute epigenetic age from DNA methylation arrays using PyAging clocks from GEO accessions or local files.
- ▌ Pubmed Summariser · clawbio bundleSearch PubMed, preserve complete abstracts and sections, and produce research briefings with abstract openings or optional OpenAI/Ollama summaries.
- ▌ Scrna Orchestrator · clawbio bundleLocal 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.
- ▌ Proteomics De · clawbio bundleDifferential expression analysis for label-free quantitative (LFQ) intensity data with standard MaxQuant and DIA-NN output. Workflow includes preprocessing, imputation, and statistical testing.
- ▌ Ukb Navigator · clawbio bundleSemantic search across UK Biobank's 12,000+ data fields and publications — find the right variables for your research question.
- ▌ Vcf Annotator · clawbio bundleAnnotate VCF variants with Ensembl VEP, ClinVar, and gnomAD. Ranks variants by impact (HIGH/MODERATE/LOW/MODIFIER) and generates a reproducible report.
- ▌ Data Extractor · clawbio bundleExtract 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.
- ▌ Genome Compare · clawbio bundleCompare your genome to George Church (PGP-1) and estimate ancestry composition via IBS and EM admixture
- ▌ Drug Photo · clawbio bundleMedication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance
- ▌ Gwas Lookup · clawbio bundleFederated variant lookup across 8 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, and more.
- ▌ Genome Match · clawbio bundleScore genetic compatibility across all male-female pairings in a Genomebook generation
- ▌ Protocols Io · clawbio bundleSearch, 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.
- ▌ Recombinator · clawbio bundleProduce offspring genomes from parent pairs via meiotic recombination, mutation, and clinical evaluation
- ▌ Seq Wrangler · clawbio bundleNGS read QC, alignment, and BAM processing pipeline. Wraps FastQC, BWA/Bowtie2/Minimap2, SAMtools, and MultiQC for automated read-to-BAM workflows.
- ▌ Equity Scorer · clawbio bundleCompute HEIM diversity and equity metrics from VCF or ancestry data. Generates heterozygosity, FST, PCA plots, and a composite HEIM Equity Score with markdown reports.
- ▌ Galaxy Bridge · clawbio bundleGalaxy tool discovery, intelligent recommendation, and execution — 8,000+ bioinformatics tools from usegalaxy.org with multi-signal scoring and workflow suggestions
- ▌ Nutrigx · clawbio bundlePersonalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant SNPs and generates actionable dietary guidance, all computed locally.
- ▌ Gwas Prs · clawbio bundleCalculate polygenic risk scores from DTC genetic data using the PGS Catalog
- ▌ Gi Splice · clawbio bundleDetect splice donor and acceptor sites in DNA sequences using the Genomic Intelligence G0 BigBird transformer, via the hosted /v1/tasks/splice/predict API. Returns per-position site probabilities and called sites.
- ▌ Gi Enhancer · clawbio bundlePredict enhancer activity in DNA sequences using the Genomic Intelligence G0 DeepSTARR model, via the hosted /v1/tasks/enhancer/predict API. Returns per-window activity scores.
- ▌ Gi Promoter · clawbio bundleDetect promoter regions in DNA sequences using the Genomic Intelligence G0 transformer (GENA-LM BERT Large), via the hosted /v1/tasks/promoter/predict API. Returns per-window promoter probabilities and called regions.
- ▌ Gi Chromatin · clawbio bundlePredict chromatin state — histone marks, DNase, TF binding — across 919 tracks (DeepSEA-style) for DNA sequences, via the hosted Genomic Intelligence /v1/tasks/chromatin/predict API.
- ▌ Gi Annotation · clawbio bundlePredict gene and transcript structure (intervals, exons, strand) from a DNA sequence using the Genomic Intelligence DNA Annotation model, via the hosted /v1/tasks/annotation/predict API. Submitted asynchronously — the pipeline takes ~20 s for ~20 kbp.
- ▌ Gi Expression · clawbio bundlePredict tissue / cell-type expression (log TPM + TPM) from 9,198–500,000 bp of DNA around a TSS, at least 4,599 bp each side (anything but exactly 9,198 bp needs --tss-index) using the Genomic Intelligence G0 Expression model, via the hosted /v1/tasks/expression/predict API. The model is conditioned on a free-text cell-type / assay description.
- ▌ Skill Builder · clawbio bundleScaffold a new ClawBio skill from a spec file (JSON/YAML) or interactively — generates SKILL.md, Python skeleton, tests, and updates catalog.json
- ▌ Rnaseq De · clawbio bundleDifferential expression analysis for bulk RNA-seq and pseudo-bulk count matrices with QC, PCA, and contrast testing.
- ▌ Nfcore Rnastructurome Wrapper · clawbio bundleWrapper skill for running nf-core/rnastructurome — chemical-probing RNA structure analysis (SHAPE/DMS, RT-stop/MaP readout) from FASTQ to per-base reactivity, secondary-structure predictions, and 2D diagrams.
- ▌ Gwas Sumstats Harmonize · clawbio bundleHarmonize GWAS summary statistics from any common format (GWAS-Catalog SSF, PLINK 1.9/2, REGENIE, METAL, BOLT, SAIGE) to one canonical table (SNP CHR BP EA NEA EAF BETA SE P N): column detection, BETA/SE/P derivation, QC with drop reasons, and allele alignment to a reference panel, run as a Snakemake workflow.
- ▌ Spatial Transcriptomics · clawbio bundleAnalyse 10x Visium spatial transcriptomics: SpaceRanger outs or spatial h5ad in, then QC, Leiden clustering, Wilcoxon markers, Moran's I, neighbourhood enrichment and co-occurrence in one local report.
- ▌ Prs Applicability Gate · clawbio bundleDeterministic gate for ONE already-computed polygenic score result and ONE person: returns SUPPORTED (raw score, standardised score and reference percentile may be shown), RAW_ONLY (raw score only) or ABSTAIN (nothing), with reason codes, a full rule trace and what would change the result. Never produces absolute risk.
- ▌ Arrayexpress Fetch · clawbio bundleQuery 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.
- ▌ Biostudies Fetch · clawbio bundleQuery 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.
- ▌ Seqtk Downsample · clawbio bundleRandomly downsample FASTQ files to N reads or a fraction with `seqtk sample`, single-end or paired-end, fixed seed (default 12345), gzip in and out.
- ▌ Igv Validator · clawbio bundleRead-level validation of variant calls from any VCF, tumor/normal or tumor-only: counts read support in the BAMs (SNVs, indels, SV breakpoints), compares it with the caller's reported counts, flags artifact patterns, takes one IGV screenshot per variant and writes a report.
- ▌ Pride Fetch · clawbio bundleQuery metadata and download data from the PRIDE Archive, EMBL-EBI's proteomics identifications database, via the PRIDE Archive REST API v3. Works with PRIDE/ProteomeXchange accessions (PXD, PRD) to fetch project metadata, list and download files (RAW, mzIdentML, mzML, mzTab, MGF, SDRF), search projects, emit a standardised metadata.tsv, write a quantms-ready minimal SDRF sample sheet, and generate a bash + SLURM download script.
- ▌ Analyze Fasta · clawbio bundleAnalyze 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.
- ▌ Labstep · clawbio bundleQuery and display Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy. Supports offline demo mode with synthetic biology data.
- ▌ Fastreer · clawbio bundlePhylogenetic distance matrices and trees from VCF or FASTA data using the fastreeR hybrid Java/Python toolkit (VCF2TREE, VCF2DIST, DIST2TREE, FASTA2DIST).
- ▌ Flow Bio · clawbio bundleFlow.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance.
- ▌ Ena Fetch · clawbio bundleQuery metadata and download sequencing data from the European Nucleotide Archive (ENA) via the Portal and Browser APIs. Works with ENA/SRA accessions (PRJEB/PRJNA studies, ERR/SRR/DRR runs, ERX/SRX experiments, SAMEA/SAMN samples), listing runs and FASTQ links, building custom file reports, running advanced metadata searches, and emitting a standardised metadata.tsv plus a pipeline-ready nf-core/rnaseq or nf-core/scrnaseq samplesheet.csv.
- ▌ Geo Fetch · clawbio bundleQuery metadata and download data from the NCBI Gene Expression Omnibus (GEO). Works with GEO accessions (GSE series, GSM samples, GPL platforms, GDS datasets) to search GEO DataSets, fetch series and sample metadata, list and download series matrix / SOFT / MINiML / supplementary files, fetch the SRA Run Selector files, and emit a standardised metadata.tsv plus a pipeline-ready nf-core/rnaseq or nf-core/scrnaseq samplesheet.csv.
- ▌
- ▌ Snp Phewas · clawbio bundleVariant PheWAS across three curated biobanks, Pan-UK Biobank, FinnGen R12 and the Million Veteran Program: one variant in, beta / SE / p / allele frequency for every outcome each biobank tested (nulls included), on one effect allele, every untested or unreadable outcome kept as a row with a reason, outcomes harmonized across the biobanks, and a replication verdict per shared outcome for every biobank pair and across all three.
- ▌ Clinpgx · clawbio bundleQuery the ClinPGx API for pharmacogenomic gene-drug data, clinical annotations, CPIC guidelines, and FDA drug labels
- ▌ Gi Splice 2 · clawbio bundleDetect splice donor and acceptor sites in DNA sequences using the Genomic Intelligence G0 BigBird transformer, via the hosted /v1/tasks/splice/predict API. Returns per-position site probabilities and called sites.
- ▌ Gi Enhancer 2 · clawbio bundlePredict enhancer activity in DNA sequences using the Genomic Intelligence G0 DeepSTARR model, via the hosted /v1/tasks/enhancer/predict API. Returns per-window activity scores.
- ▌ Gi Promoter 2 · clawbio bundleDetect promoter regions in DNA sequences using the Genomic Intelligence G0 transformer (GENA-LM BERT Large), via the hosted /v1/tasks/promoter/predict API. Returns per-window promoter probabilities and called regions.
- ▌ Gi Chromatin 2 · clawbio bundlePredict chromatin state — histone marks, DNase, TF binding — across 919 tracks (DeepSEA-style) for DNA sequences, via the hosted Genomic Intelligence /v1/tasks/chromatin/predict API.
- ▌ Equity Scorer 2 · clawbio bundleCompute HEIM diversity and equity metrics from VCF or ancestry data. Generates heterozygosity, FST, PCA plots, and a composite HEIM Equity Score with markdown reports.
- ▌ Gi Annotation 2 · clawbio bundlePredict gene and transcript structure (intervals, exons, strand) from a DNA sequence using the Genomic Intelligence DNA Annotation model, via the hosted /v1/tasks/annotation/predict API. Submitted asynchronously — the pipeline takes ~20 s for ~20 kbp.