mims-harvard-tooluniverse

Automatically discover life science APIs online, create ToolUniverse tools, validate them, and prepare integration PRs. Performs gap analysis to identify missing tool categories, web searches for APIs, automated tool creation using devtu-create-tool patterns, validation with devtu-fix-tool, and git workflow management. Use when expanding ToolUniverse coverage, adding new API integrations, or systematically discovering scientific resources.

Code quality patterns and guidelines for ToolUniverse tool development. Apply when writing, fixing, or refactoring tool Python code in the ToolUniverse project. Encodes lessons from 80+ debug rounds. Use alongside devtu-fix-tool and devtu-self-evolve. Triggers: implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug fixes.

Retrieves chemical compound information from PubChem and ChEMBL with disambiguation, cross-referencing, and quality assessment. Creates comprehensive compound profiles with identifiers, properties, bioactivity, and drug information. Use when users need chemical data, drug information, or mention PubChem CID, ChEMBL ID, SMILES, InChI, or compound names.

Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology. Integrates tools from ToolUniverse's 1,264+ tool library, creates missing tools when needed, tests thoroughly, and produces skills with Python SDK + MCP support.

Cross-species gene and sequence comparison, ortholog analysis, and evolutionary conservation assessment using ToolUniverse tools. Use when comparing genes across species, finding orthologs, analyzing evolutionary conservation, or performing comparative functional annotation.

Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases/services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.

TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code execution, (A) automated validation, (B) ToolUniverse audit, (E) less-is-more simplification. Core philosophy: each concept appears exactly once; remove don't add; no emojis; single setup entry point. Use when reviewing docs, before releases, after API changes, or when asked to audit, fix, or simplify documentation.

Fix failing ToolUniverse tools by diagnosing test failures, identifying root causes, implementing fixes, and validating solutions. Use when ToolUniverse tools fail tests, return errors, have schema validation issues, or when asked to debug or fix tools in the ToolUniverse framework.

GitHub workflow for ToolUniverse - push code safely by moving temp files, activating pre-commit hooks, running tests, and cleaning staged files. Use when pushing to GitHub, fixing CI failures, or cleaning up before commits.

Optimize tool descriptions in ToolUniverse JSON configs for clarity and usability. Reviews descriptions for missing prerequisites, unexpanded abbreviations, unclear parameters, and missing usage guidance. Use when reviewing tool descriptions, improving API documentation, or when user asks to check if tools are easy to understand.

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.

Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/find/info/run/test/status/build/serve), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".

Systematic ACMG/AMP variant classification using ToolUniverse tools. Given a genetic variant (HGVS, rsID, or gene+change), applies all 28 ACMG criteria (PVS1, PS1-4, PM1-6, PP1-5, BA1, BS1-4, BP1-7) through automated database queries and computational predictions. Produces a final 5-tier classification (Pathogenic / Likely Pathogenic / VUS / Likely Benign / Benign) with evidence summary. Use when asked to classify a variant, interpret a VUS, apply ACMG criteria, assess pathogenicity, or determine clinical significance of a germline variant.

Comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiling of drug candidates using ADMETAI predictions, SwissADME drug-likeness, PubChemTox experimental toxicity, ChEMBL clinical data, and PubChem properties. Generates a structured ADMET scorecard with pass/fail verdicts per category. Use when asked about drug-likeness, ADMET properties, bioavailability, toxicity prediction, BBB penetration, CYP interactions, pharmacokinetic profiling, Lipinski rule of five, or ADME/PK assessment of a compound.

Detect and analyze adverse drug event signals using FDA FAERS data, drug labels, disproportionality analysis (PRR, ROR, IC), and biomedical evidence. Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, adverse event investigation, and regulatory decision support.

Map environmental/industrial chemicals to mechanistic adverse outcome pathways (AOPs) using AOPWiki, quantify toxicological hazard (PubChemTox GHS/carcinogen classification, LD50 values), and link chemical stressors to gene targets and disease endpoints via CTD for regulatory risk assessment. Use when asked about AOP stressor mapping, GHS hazard categories, LD50 data, IARC carcinogen classification, or mechanism-based risk assessment for non-drug chemicals.

Research aging biology, cellular senescence, and longevity using ToolUniverse. Covers senescence markers and pathways, age-related disease genetics, telomere biology, senolytic drug discovery, epigenetic aging clocks, and longevity gene analysis. Integrates GWAS data, gene expression (GTEx age effects), pathway databases, drug repurposing, and literature. Use when asked about aging mechanisms, senescence, senolytics, longevity genes, age-related diseases, or epigenetic clocks.

Interpret results from CRISPR/shRNA genetic screens using DepMap essentiality data, constraint scores, pathway enrichment, protein networks, druggability assessment, and clinical evidence. Use for screen hit validation, gene essentiality analysis, DepMap exploration, functional genomics interpretation, and screen-to-target prioritization.

Comprehensive antibody engineering and optimization for therapeutic development. Covers humanization, affinity maturation, developability assessment, and immunogenicity prediction. Use when asked to optimize antibodies, humanize sequences, or engineer therapeutic antibodies from lead to clinical candidate.

Discover novel small molecule binders for protein targets using structure-based and ligand-based approaches. Creates actionable reports with candidate compounds, ADMET profiles, and synthesis feasibility. Use when users ask to find small molecules for a target, identify novel binders, perform virtual screening, or need hit-to-lead compound identification.

Translate free-text tumor descriptions to OncoTree codes, look up cancer subtypes and tissue hierarchies, resolve UMLS/NCI cross-references, and obtain OncoKB-compatible tumor type codes for variant annotation. Use when asked to find the OncoTree code for a tumor type, enumerate subtypes of a cancer, list cancers by tissue of origin, or standardize tumor nomenclature for downstream precision oncology analysis.

TCGA/GDC cancer genomics analysis -- cohort construction, clinical metadata retrieval, somatic mutation profiling, copy number variation analysis, survival analysis, and clinical variant interpretation. Use when users ask about TCGA data, GDC cancer cohorts, somatic mutation frequencies, Kaplan-Meier survival, CNV profiles in cancer, or OncoKB interpretation of cancer variants.

Provide comprehensive clinical interpretation of somatic mutations in cancer. Given a gene symbol + variant (e.g., EGFR L858R, BRAF V600E) and optional cancer type, performs multi-database analysis covering clinical evidence (CIViC), mutation prevalence (cBioPortal), therapeutic associations (OpenTargets, ChEMBL, FDA), resistance mechanisms, clinical trials, prognostic impact, and pathway context. Generates an evidence-graded markdown report with actionable recommendations for precision oncology. Use when oncologists, molecular tumor boards, or researchers ask about treatment options for specific cancer mutations, resistance mechanisms, or clinical trial matching.

Help researchers select and characterize cancer cell lines for experiments. Given a cancer type, gene of interest, or cell line name, profiles molecular features (mutations, expression, CNV), gene dependencies (CRISPR screens), drug sensitivities (IC50/AUC), and genetic backgrounds using DepMap, Cellosaurus, PharmacoDB, COSMIC, CellMarker, CLUE, and SYNERGxDB. Generates a decision-support report for cell line selection. Use when researchers ask about which cell line to use, cell line characterization, DepMap dependencies, drug sensitivity profiles, or cancer model selection.

Comprehensive chemical safety and toxicology assessment integrating ADMET-AI predictions, CTD toxicogenomics, FDA label safety data, DrugBank safety profiles, and STITCH chemical-protein interactions. Performs predictive toxicology (AMES, DILI, LD50, carcinogenicity), organ/system toxicity profiling, chemical-gene-disease relationship mapping, regulatory safety extraction, and environmental hazard assessment. Use when asked about chemical toxicity, drug safety profiling, ADMET properties, environmental health risks, chemical hazard assessment, or toxicogenomic analysis.

Find commercial sources for chemical compounds using ZINC, Enamine, eMolecules, and Mcule. Covers compound identification, vendor search, pricing, analog discovery, and order preparation. Use when buying compounds, checking commercial availability, comparing vendors, or finding purchasable analogs.

Comprehensive drug safety review integrating FDA labels, FAERS adverse event reports, disproportionality analysis, pharmacogenomics, clinical trials, and literature. Use for regulatory assessments, post-market surveillance, drug safety reviews, adverse event investigation, and pharmacovigilance.

Search and retrieve clinical practice guidelines across 12+ authoritative sources including NICE, WHO, ADA, AHA/ACC, NCCN, SIGN, CPIC, CMA, CTFPHC, GIN, MAGICapp, PubMed, EuropePMC, TRIP, and OpenAlex. Use when users ask about clinical guidelines, treatment recommendations, standard of care, evidence-based medicine, or drug-gene dosing recommendations.

Strategic clinical trial design feasibility assessment using ToolUniverse. Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways. Creates comprehensive feasibility reports with evidence grading, enrollment projections, and trial design recommendations. Use when planning Phase 1/2 trials, assessing trial feasibility, or designing biomarker-driven studies.

AI-driven patient-to-trial matching for precision medicine and oncology. Given a patient profile (disease, molecular alterations, stage, prior treatments), discovers and ranks clinical trials from ClinicalTrials.gov using multi-dimensional matching across molecular eligibility, clinical criteria, drug-biomarker alignment, evidence strength, and geographic feasibility. Produces a quantitative Trial Match Score (0-100) per trial with tiered recommendations and a comprehensive markdown report. Use when oncologists, molecular tumor boards, or patients ask about clinical trial options for specific cancer types, biomarker profiles, or post-progression scenarios.

Solve quantitative problems in biophysics, pharmacokinetics, epidemiology, toxicology, population genetics, and statistical mechanics. Provides reasoning strategies and Python templates for calculations alongside ToolUniverse data lookups. Use when users ask about drug dosing, half-life decay, radioactive tracers, R0, herd immunity, diffusion, Hardy-Weinberg, binding equilibria, or any computation-heavy biology/chemistry question.

Comprehensive CRISPR screen analysis for functional genomics. Analyze pooled or arrayed CRISPR screens (knockout, activation, interference) to identify essential genes, synthetic lethal interactions, and drug targets. Perform sgRNA count processing, gene-level scoring (MAGeCK, BAGEL), quality control, pathway enrichment, and drug target prioritization. Use for CRISPR screen analysis, gene essentiality studies, synthetic lethality detection, functional genomics, drug target validation, or identifying genetic vulnerabilities.

Add custom local tools to ToolUniverse and use them alongside the 1000+ built-in tools. Use this skill when a user wants to: create their own tool for a private or custom API, add a local tool to their workspace, integrate an internal service with ToolUniverse, or use a custom tool via the MCP server or Python API. Covers both the JSON config approach (easiest, no Python needed) and the Python class approach (full control). Also covers how to verify tools loaded correctly and how to call them. Also covers the plugin package approach for reusable, shareable, pip-installable tool sets.

Integrate statistical analysis results with biological knowledge from ToolUniverse tools. After computing associations or differential expression, use pathway analysis, literature search, drug-target databases, and variant annotation to interpret findings biologically. Use when statistical results need biological context, when users want to go beyond p-values to understand mechanisms, or when combining data analysis with literature evidence.

Universal data access reference for scientific research. Teaches how to download bulk data, parse any scientific file format (VCF, h5ad, mzML, PDB, FASTA, XPT, NIfTI, and 30+ more), paginate REST APIs, and handle authentication. Covers 24 domain API patterns across ALL life science data sources — genomics, proteomics, clinical, imaging, ecology, and more. Use this skill whenever you need to download raw data, parse a file format, access a bulk API, write a multi-step data retrieval workflow, or when a ToolUniverse tool returns metadata but you need the actual data. Also use when the data source has no ToolUniverse tool at all. Even if the user doesn't say "data wrangling" — if their task requires getting data from a scientific database or parsing a scientific file format, this is the skill to use.

Find and evaluate research datasets for any scientific question. Teaches how to reason about data needs, search across public repositories, evaluate dataset fitness, and identify access requirements. Use whenever users ask to find data, search for datasets, identify cohort studies, or need data for analysis. Also use when users ask about a specific survey or cohort (NHANES, HRS, UK Biobank, TCGA, etc.), when they want to know what data exists for a research question, or when they need to compare available data sources. If the user mentions "where can I get data" or "is there a dataset for X", this is the right skill.

Generate comprehensive disease research reports using 100+ ToolUniverse tools. Creates a detailed markdown report file and progressively updates it with findings from 10 research dimensions. All information includes source references. Use when users ask about diseases, syndromes, or need systematic disease analysis.

Comprehensive drug-drug interaction (DDI) prediction and risk assessment. Analyzes interaction mechanisms (CYP450, transporters, pharmacodynamic), severity classification, clinical evidence grading, and provides management strategies. Supports single drug pairs, polypharmacy analysis (3+ drugs), and alternative drug recommendations. Use when users ask about drug interactions, medication safety, polypharmacy risks, or need DDI assessment for clinical decision support.

Drug mechanism of action investigation -- systematic strategy to trace a drug from its primary target through pathways to clinical outcomes, identify off-target effects, and combine regulatory labels with literature evidence for a complete mechanism picture.

Drug regulatory and approval research -- FDA substance registry lookup, drug classification by ATC/EPC/MoA via RxClass, Orange Book generic availability and patent status, DailyMed label parsing (adverse reactions, dosing, contraindications), and clinical trial search. Use when users ask about FDA-approved drugs, drug regulatory status, generic availability, patent expiration, drug class membership, drug labeling, or substance identification.

Identify drug repurposing candidates using ToolUniverse for target-based, compound-based, and disease-driven strategies. Searches existing drugs for new therapeutic indications by analyzing targets, bioactivity, safety profiles, and literature evidence. Use when exploring drug repurposing opportunities, finding new indications for approved drugs, or when users mention drug repositioning, off-label uses, or therapeutic alternatives.

Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.

Find and compare gene-disease associations across multiple databases (DisGeNET, OpenTargets, Monarch Initiative, OMIM, GenCC, Orphanet, ClinVar). Produces a unified evidence table with confidence levels and cross-database concordance. Use when users ask about gene-disease links, disease genes, genetic basis of disease, or want to compare association evidence across sources.

Comprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ ToolUniverse tools. Produces a quantitative Target Validation Score (0-100) with GO/NO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or "is X a good drug target for Y?"

Ecology, biodiversity, and conservation biology research — species identification, invasive species assessment, pollinator ecology, population dynamics, food webs, trophic interactions, community ecology, island biogeography. Use for ANY ecology question including species distributions, invasive impacts, pollination biology, predator-prey dynamics, or conservation assessment.

Search and analyze cryo-EM maps, single particle structures, tomography datasets, and raw micrograph data from EMDB, EMPIAR, and CryoET Data Portal. Cross-reference with PDB structures and AlphaFold predictions. Use for cryo-EM map discovery, structure fitting analysis, raw data access, and tomography exploration.

End-to-end epidemiological data analysis — from research question to statistical report. Covers study design assessment, dataset discovery and download, data wrangling, confounder adjustment, regression modeling, sensitivity analysis, visualization, and biological interpretation. Integrates ToolUniverse tools for dataset discovery, literature search, and biological context with Python code execution for data analysis. Use whenever users ask to analyze health data, study disease risk factors, assess exposure-outcome relationships, or conduct observational epidemiology. Also use when users want to run regression on clinical/survey data, calculate odds ratios or hazard ratios from a dataset, adjust for confounders, or produce a Table 1. If the task involves downloading a health dataset and running statistical analysis on it, this is the right skill.

Epigenomics and chromatin accessibility research -- histone modification ChIP-seq data from ENCODE, CTCF binding and chromatin architecture, eQTL analysis connecting variants to gene regulation, gene expression correlation with chromatin marks, regulatory element identification via SCREEN/UCSC cCREs, transcription factor binding motifs via JASPAR/ReMap, and variant regulatory scoring via RegulomeDB. Use when users ask about histone marks, chromatin states, CTCF binding, eQTLs, cis-regulatory elements, enhancer/promoter annotation, or chromatin accessibility in specific cell types.

Production-ready genomics and epigenomics data processing for BixBench questions. Handles methylation array analysis (CpG filtering, differential methylation, age-related CpG detection, chromosome-level density), ChIP-seq peak analysis (peak calling, motif enrichment, coverage stats), ATAC-seq chromatin accessibility, multi-omics integration (expression + methylation correlation), and genome-wide statistics. Pure Python computation (pandas, scipy, numpy, pysam, statsmodels) plus ToolUniverse annotation tools (Ensembl, ENCODE, SCREEN, JASPAR, ReMap, RegulomeDB, ChIPAtlas). Supports BED, BigWig, methylation beta-value matrices, Illumina manifest files, and multi-sample clinical data. Use when processing methylation data, ChIP-seq peaks, ATAC-seq signals, or answering questions about CpG sites, differential methylation, chromatin accessibility, histone marks, or epigenomic statistics.

Retrieves gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation, experiment quality assessment, and structured reports. Creates comprehensive dataset profiles with metadata, sample information, and download links. Use when users need expression data, omics datasets, or mention ArrayExpress (E-MTAB, E-GEOD) or BioStudies (S-BSST) accessions.

Perform comprehensive gene enrichment and pathway analysis using gseapy (ORA and GSEA), PANTHER, STRING, Reactome, and 40+ ToolUniverse tools. Supports GO enrichment (BP, MF, CC), KEGG, Reactome, WikiPathways, MSigDB Hallmark, and 220+ Enrichr libraries. Handles multiple ID types (gene symbols, Ensembl, Entrez, UniProt), multiple organisms (human, mouse, rat, fly, worm, yeast), customizable backgrounds, and multiple testing correction (BH, Bonferroni). Use when users ask about gene enrichment, pathway analysis, GO term enrichment, KEGG pathway analysis, GSEA, over-representation analysis, functional annotation, or gene set analysis.

**GRN inference starts with: which TF regulates which gene?** Direct evidence (ChIP-seq binding) is stronger than indirect (co-expression correlation). A TF binding near a gene doesn't prove regulation — check if expression changes when the TF is perturbed. JASPAR provides binding motifs but motif presence in a promoter is only computational evidence (T3); ENCODE ChIP-seq data that places the TF at the locus in the relevant cell type is stronger (T1). eQTLs from GTEx show which variants affect expression but don't identify the upstream regulator — combine with TF motif disruption analysis for mechanistic insight.

Research GPCR receptors, antibody structures, and protein interface analysis using GPCRdb, SAbDab, and PDBePISA. Retrieves receptor families, known ligands (agonists/antagonists/biased), mutations, crystal/cryo-EM structures, antibody CDR annotations, and protein-protein interface geometry. Use when asked about GPCR drug targets, receptor-ligand interactions, antibody structural data, or protein assembly interfaces.

Transform GWAS signals into actionable drug targets and repurposing opportunities. Performs locus-to-gene mapping, target druggability assessment, existing drug identification, safety profile evaluation, and clinical trial matching. Use when discovering drug targets from GWAS data, finding drug repurposing opportunities from genetic associations, or translating GWAS findings into therapeutic leads.

Identify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions. Computes posterior probabilities for causal variants, links variants to genes via L2G predictions, annotates functional consequences, and suggests validation strategies. Use when asked to fine-map GWAS loci, prioritize causal variants, identify credible sets, or link GWAS signals to causal genes.

Immunology research workflows using ToolUniverse tools. Covers antibody-antigen structural analysis (SAbDab, TheraSAbDab), immune protein interactions (IntAct, BioGRID), epitope and T-cell/B-cell assay data (IEDB), immunoglobulin gene databases (IMGT), cytokine/receptor signaling (OpenTargets, GWAS), clinical safety data for immune diseases (FAERS, clinical trials), autoimmune disease genetics (Orphanet), and immune pathway analysis (KEGG, Reactome). Use when researchers ask about antibody targets, immune signaling networks, autoimmune genetics, immunotherapy safety, epitope discovery, or immune pathway enrichment.

Interpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple databases (GWAS Catalog, Open Targets Genetics, ClinVar). Retrieves variant annotations, GWAS trait associations, fine-mapping evidence, locus-to-gene predictions, and clinical significance. Use when asked to interpret a SNP by rsID, find disease associations for a variant, assess clinical significance, or answer questions like "What diseases is rs429358 associated with?" or "Interpret rs7903146".

Compare GWAS studies, perform meta-analyses, and assess replication across cohorts. Integrates NHGRI-EBI GWAS Catalog and Open Targets Genetics to compare study designs, effect sizes, ancestry diversity, and heterogeneity statistics. Use when comparing GWAS studies for a trait, performing meta-analysis of genetic loci, assessing replication across cohorts, or exploring the genetic architecture of complex diseases.

Discover genes associated with diseases and traits using GWAS data from the GWAS Catalog (500,000+ associations) and Open Targets Genetics (L2G predictions). Identifies genetic risk factors, prioritizes causal genes via locus-to-gene scoring, and assesses druggability. Use when asked to find genes associated with a disease or trait, discover genetic risk factors, translate GWAS signals to gene targets, or answer questions like "What genes are associated with type 2 diabetes?"

Analyze HLA genes, MHC binding, epitope-MHC associations, and immunogenomics for transplant compatibility, vaccine design, and immunotherapy. Integrates IMGT, IEDB, BVBRC, UniProt, and DGIdb. Use for HLA typing interpretation, antigen presentation analysis, MHC restriction, neoantigen prediction context, and transplant immunology.

Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ/CellProfiler output (area, circularity, intensity, cell counts), performs Dunnett's test, Cohen's d effect size, power analysis, Shapiro-Wilk normality tests, two-way ANOVA, polynomial regression, natural spline regression with confidence intervals, and comparative morphometry. Supports CSV/TSV measurement tables, multi-channel fluorescence data, colony swarming assays, and neuron counting datasets. Use when analyzing microscopy measurement data, colony area/circularity, cell count statistics, swarming assays, co-culture ratio optimization, or answering questions about imaging-derived quantitative data.

Comprehensive immune repertoire analysis for T-cell and B-cell receptor sequencing data. Analyze TCR/BCR repertoires to assess clonality, diversity, V(D)J gene usage, CDR3 characteristics, convergence, and predict epitope specificity. Integrate with single-cell data for clonotype-phenotype associations. Use for adaptive immune response profiling, cancer immunotherapy research, vaccine response assessment, autoimmune disease studies, or repertoire diversity analysis in immunology research.

Predict patient response to immune checkpoint inhibitors (ICIs) using multi-biomarker integration. Given a cancer type, somatic mutations, and optional biomarkers (TMB, PD-L1, MSI status), performs systematic analysis across 11 phases covering TMB classification, neoantigen burden estimation, MSI/MMR assessment, PD-L1 evaluation, immune microenvironment profiling, mutation-based resistance/sensitivity prediction, clinical evidence retrieval, and multi-biomarker score integration. Generates a quantitative ICI Response Score (0-100), response likelihood tier, specific ICI drug recommendations with evidence, resistance risk factors, and a monitoring plan. Use when oncologists ask about immunotherapy eligibility, checkpoint inhibitor selection, or biomarker-guided ICI treatment decisions.

Rapid pathogen characterization and drug repurposing analysis for infectious disease outbreaks. Identifies pathogen taxonomy, essential proteins, predicts structures, and screens existing drugs via docking. Use when facing novel pathogens, emerging infections, or needing rapid therapeutic options during outbreaks.

Inorganic chemistry, physical chemistry, and materials science — crystal structures, coordination chemistry, bonding theory (covalency, orbital mixing), symmetry/point groups, thermodynamics, kinetics, spectroscopy interpretation, noble gas compounds, lanthanide/actinide chemistry. Use for questions about crystal systems, unit cells, density calculations, metal complexes, solid-state chemistry, or physical chemistry calculations.

Detect and auto-install missing ToolUniverse research skills by checking common client skill directories and cloning from GitHub if absent. Use when ToolUniverse specialized skills are not installed, when setting up a new project, or when the tooluniverse router skill needs to bootstrap its sub-skills before routing.

KEGG-based disease-drug-variant research using KEGG Disease, Drug, Network, and Variant databases. Covers disease gene lookup, drug-target analysis, disease-gene-drug network exploration, and variant annotation. Use when users ask about KEGG disease entries, KEGG drug targets, disease-variant-drug relationships, or KEGG network analysis.

Analyze lipids, lipid metabolism, and lipid-disease associations using LIPID MAPS, HMDB, PubChem, KEGG, and CTD. Covers lipid identification, classification, pathway mapping, biomarker discovery, and disease links. Distinct from general metabolomics — focuses on lipid-specific biology (membrane composition, signaling lipids, lipoproteins, sphingolipids, eicosanoids). Use when asked about lipid profiling, lipidomics data interpretation, lipid biomarkers, lipid metabolism disorders, or lipid-disease connections.

Integrate and analyze multiple omics datasets (transcriptomics, proteomics, epigenomics, genomics, metabolomics) for systems biology and precision medicine. Performs cross-omics correlation, multi-omics clustering (MOFA+, NMF), pathway-level integration, and sample matching. Coordinates ToolUniverse skills for expression data (RNA-seq), epigenomics (methylation, ChIP-seq), variants (SNVs, CNVs), protein interactions, and pathway enrichment. Use when analyzing multi-omics datasets, performing integrative analysis, discovering multi-omics biomarkers, studying disease mechanisms across molecular layers, or conducting systems biology research that requires coordinated analysis of transcriptome, genome, epigenome, proteome, and metabolome data.

Comprehensive literature deep research across any academic domain using 120+ ToolUniverse tools. Conducts subject disambiguation, systematic literature search with citation network expansion, evidence grading (T1-T4), and structured theme extraction. Produces detailed reports with mandatory completeness checklists, integrated models, and testable hypotheses. Use when users need thorough literature reviews, target/drug/disease profiles, topic deep-dives, claim verification, or systematic evidence synthesis. Supports biomedical (genes, proteins, drugs, diseases), computer science, social science, and general academic topics. For single factoid questions, uses a fast verification mode with inline answer.

Analyze metabolomics data including metabolite identification, quantification, pathway analysis, and metabolic flux. Processes LC-MS, GC-MS, NMR data from targeted and untargeted experiments. Performs normalization, statistical analysis, pathway enrichment, metabolite-enzyme integration, and biomarker discovery. Use when analyzing metabolomics datasets, identifying differential metabolites, studying metabolic pathways, integrating with transcriptomics/proteomics, discovering metabolic biomarkers, performing flux balance analysis, or characterizing metabolic phenotypes in disease, drug response, or physiological conditions.

Metabolomics pathway analysis -- metabolite identification, pathway mapping, disease associations, cross-database enrichment, and enzyme/gene linkage. Connects PubChem, HMDB, MetaCyc, CTD, KEGG, Reactome, MetabolomicsWorkbench, and BridgeDb. Use when users ask about metabolite identification, metabolic pathways, metabolite-disease links, metabolomics data interpretation, or pathway enrichment from metabolite lists.

Comprehensive metabolomics research skill for identifying metabolites, analyzing studies, and searching metabolomics databases. Integrates HMDB (220k+ metabolites), MetaboLights, Metabolomics Workbench, and PubChem. Use when asked to identify or annotate metabolites (HMDB IDs, chemical properties, pathways), retrieve metabolomics study information from MetaboLights (MTBLS*) or Metabolomics Workbench (ST*), search for studies by keywords or disease, or generate comprehensive metabolomics research reports.

Analyze microbiome and metagenomics data using MGnify, GTDB, ENA, and literature tools. Search studies by biome/keyword, retrieve taxonomic profiles and functional annotations, classify genomes with GTDB taxonomy, and find related publications. Use for human gut microbiome, soil/ocean metagenomics, and environmental microbiology research.

Analyze microbiome and metagenomics data using MGnify, GTDB, ENA, and literature tools. Search studies by biome/keyword, retrieve taxonomic profiles and functional annotations, classify genomes with GTDB taxonomy, and find related publications. Use for human gut microbiome, soil/ocean metagenomics, and environmental microbiology research.

Cross-species genetic analysis using model organism databases. Maps human genes to orthologs in mouse, fly, worm, zebrafish, yeast, and frog, then retrieves phenotypes, expression, and functional data from MGI, FlyBase, WormBase, ZFIN, SGD, and Xenbase. Use when users ask about model organisms, gene orthologs, mouse phenotypes, fly genetics, worm RNAi, zebrafish morphants, cross-species comparison, animal models for human disease, or conservation of gene function.

Comprehensive multi-omics disease characterization integrating genomics, transcriptomics, proteomics, pathway, and therapeutic layers for systems-level understanding. Produces a detailed multi-omics report with quantitative confidence scoring (0-100), cross-layer gene concordance analysis, biomarker candidates, therapeutic opportunities, and mechanistic hypotheses. Uses 80+ ToolUniverse tools across 8 analysis layers. Use when users ask about disease mechanisms, multi-omics analysis, systems biology of disease, biomarker discovery, or therapeutic target identification from a disease perspective.

Construct and analyze compound-target-disease networks for drug repurposing, polypharmacology discovery, and systems pharmacology. Builds multi-layer networks from ChEMBL, OpenTargets, STRING, DrugBank, Reactome, FAERS, and 60+ other ToolUniverse tools. Calculates Network Pharmacology Scores (0-100), identifies repurposing candidates, predicts mechanisms, and analyzes polypharmacology. Use when users ask about drug repurposing via network analysis, multi-target drug effects, compound-target-disease networks, systems pharmacology, or polypharmacology.

Neuroscience research and reasoning workflows using ToolUniverse tools. Covers computational neuroscience (rate models, integrate-and-fire neurons, synaptic plasticity, network dynamics), neuroanatomy (cortical regions, basal ganglia, cerebellum, brainstem, model organism connectomes), neurophysiology (ion channels, action potentials, synaptic transmission), neural circuits (E/I balance, oscillations, central pattern generators), synaptic dynamics (STDP, short-term plasticity, neuromodulation), neurodegenerative diseases (Alzheimer's, Parkinson's, ALS, Huntington's), and clinical neurology (cranial nerves, stroke localization, neuromuscular disorders). Use when researchers ask about brain regions, neural computation, firing rates, synaptic plasticity, connectomics, neurodegeneration, or clinical neurological questions.

Analyze non-coding RNAs (miRNAs, lncRNAs, circRNAs) using miRBase, LNCipedia, RNAcentral, Rfam, and target prediction databases. Covers ncRNA identification, target prediction, disease associations, expression profiling, and functional annotation. Use when asked about microRNAs, long non-coding RNAs, RNA interference, miRNA targets, lncRNA function, or ncRNA-disease associations.

Teaches reasoning strategies for organic chemistry problems — reaction product prediction, spectroscopy interpretation, stereochemistry, and quantitative calculations. Use when users ask about reaction products, spectra, mechanisms, stereochemistry, or molecular formulas.

Connect GWAS variants to biological pathways for drug target discovery. Maps disease-associated SNPs to causal genes via eQTL colocalization (GTEx), links genes to enriched pathways (Reactome, KEGG, MetaCyc), and identifies druggable targets within disease-relevant pathways. Use when asked to translate GWAS findings into mechanistic insights, find pathways enriched for disease genes, discover drug targets from genetic evidence, or answer questions like "What pathways are disrupted in type 2 diabetes based on GWAS data?"

Guide pharmacogenomics (PGx) research -- drug-gene interaction lookup, CPIC guideline retrieval, variant-drug annotation, allele function status, FDA biomarker labeling, and clinical dosing recommendations. Covers the full CPIC-to-PharmGKB-to-clinical-recommendation workflow. Use when users ask about pharmacogenomics, drug-gene interactions, CPIC guidelines, genotype-guided dosing, PGx biomarkers, CYP enzyme phenotypes, or star allele interpretation.

Analyze drug safety signals from FDA adverse event reports, label warnings, and pharmacogenomic data. Calculates disproportionality measures (PRR, ROR), identifies serious adverse events, assesses pharmacogenomic risk variants. Use when asked about drug safety, adverse events, post-market surveillance, or risk-benefit assessment.

Production-ready phylogenetics and sequence analysis skill for alignment processing, tree analysis, and evolutionary metrics. Computes treeness, RCV, treeness/RCV, parsimony informative sites, evolutionary rate, DVMC, tree length, alignment gap statistics, GC content, and bootstrap support using PhyKIT, Biopython, and DendroPy. Performs NJ/UPGMA/parsimony tree construction, Robinson-Foulds distance, Mann-Whitney U tests, and batch analysis across gene families. Integrates with ToolUniverse for sequence retrieval (NCBI, UniProt, Ensembl) and tree annotation. Use when processing FASTA/PHYLIP/Nexus/Newick files, computing phylogenetic metrics, comparing taxa groups, or answering questions about alignments, trees, parsimony, or molecular evolution.

Research plant genes, pathways, and species using PlantReactome, Ensembl Plants, POWO, UniProt, KEGG, and literature tools. Covers plant pathway analysis, gene function annotation, species identification, crop genomics, and comparative plant biology. Use when asked about plant genes, Arabidopsis, crop improvement, plant pathways, plant metabolism, photosynthesis, plant development, or plant species identification.

Build and interpret polygenic risk scores (PRS) for complex diseases using GWAS summary statistics. Calculates genetic risk profiles, interprets PRS percentiles, and assesses disease predisposition across conditions including type 2 diabetes, coronary artery disease, and Alzheimer's disease. Use when asked to calculate polygenic risk scores, interpret genetic risk for complex diseases, build custom PRS from GWAS data, or answer questions like "What is my genetic predisposition to breast cancer?"

Population genetics research using the 1000 Genomes Project (IGSR) -- search populations by superpopulation ancestry (AFR, AMR, EAS, EUR, SAS), retrieve samples by population code, list available data collections, and integrate with GWAS tools for population stratification analysis. Use when users ask about 1000 Genomes populations, sample ancestry, allele frequency variation across continental groups, population-specific GWAS interpretation, or IGSR data collections like the 30x high-coverage resequencing or HGSVC.

**MC Strategy**: Population genetics MC questions often test whether you know a specific theorem or result. COMPUTE the answer first (use popgen_calculator.py or write Python), then match to options. Don't try to reason about which option "sounds right."

Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Given a disease/condition, genomic data (germline variants, somatic mutations, expression), and optional clinical parameters, performs multi-phase analysis covering disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity/DDI risk, pathway analysis, clinical evidence and guideline mapping, clinical trial matching, and integrated outcome prediction. Generates a quantitative Precision Medicine Risk Score (0-100) with risk tier assignment, treatment algorithm, pharmacogenomic guidance, clinical trial matches, and monitoring plan.

Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials. Use when oncologist asks about treatment options for specific mutations (EGFR, KRAS, BRAF, etc.), therapy resistance, or clinical trial eligibility.

Analyze protein-protein interaction networks using STRING, BioGRID, and SASBDB databases. Maps protein identifiers, retrieves interaction networks with confidence scores, performs functional enrichment analysis (GO/KEGG/Reactome), and optionally includes structural data. No API key required for core functionality (STRING). Use when analyzing protein networks, discovering interaction partners, identifying functional modules, or studying protein complexes.

Analyze post-translational modifications (PTMs) of proteins — modification sites, types, proteoforms, functional effects at PTM sites, and PTM-dependent protein interactions. Integrates iPTMnet, ProtVar, UniProt, and STRING databases. Use when asked about protein phosphorylation, ubiquitination, acetylation, glycosylation, methylation, SUMOylation, or other PTMs; proteoform diversity; PTM-regulated interactions; or functional impact of PTM sites.

Predict and analyze protein 3D structure from amino acid sequence using ESMFold and AlphaFold. Covers de novo structure prediction (ESMFold for sequences up to ~800 residues), AlphaFold model retrieval, quality assessment (pLDDT scores), experimental structure comparison (RCSB), variant structural impact (ProtVar), and sequence physicochemical property calculation (ProtParam). Use when asked to predict protein structure from sequence, assess structure quality, compare predictions to experimental structures, or evaluate how mutations affect protein structure.

Retrieves protein structure data from RCSB PDB, PDBe, and AlphaFold with protein disambiguation, quality assessment, and comprehensive structural profiles. Creates detailed structure reports with experimental metadata, ligand information, and download links. Use when users need protein structures, 3D models, crystallography data, or mention PDB IDs (4-character codes like 1ABC) or UniProt accessions.

Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design. Uses RFdiffusion for backbone generation, ProteinMPNN for sequence design, ESMFold/AlphaFold2 for validation. Use when asked to design protein binders, therapeutic proteins, or engineer protein function.

Analyze mass spectrometry proteomics data including protein quantification, differential expression, post-translational modifications (PTMs), and protein-protein interactions. Processes MaxQuant, Spectronaut, DIA-NN, and other MS platform outputs. Performs normalization, statistical analysis, pathway enrichment, and integration with transcriptomics. Use when analyzing proteomics data, comparing protein abundance between conditions, identifying PTM changes, studying protein complexes, integrating protein and RNA data, discovering protein biomarkers, or conducting quantitative proteomics experiments.

Find and retrieve proteomics datasets from public repositories including MassIVE and ProteomeXchange (which aggregates PRIDE, PeptideAtlas, jPOST, and iProX). Search by species, keyword, or accession. Get detailed dataset metadata including instruments, publications, species, modifications, and file counts. Use when asked to find proteomics datasets, search for mass spectrometry data, look up ProteomeXchange or MassIVE accessions, or discover publicly available proteomics experiments for a given organism or topic.

Provide differential diagnosis for patients with suspected rare diseases based on phenotype and genetic data. Matches symptoms to HPO terms, identifies candidate diseases from Orphanet/OMIM, prioritizes genes for testing, interprets variants of uncertain significance. Use when clinician asks about rare disease diagnosis, unexplained phenotypes, or genetic testing interpretation.

Rare disease genomics research -- disease identification via Orphanet, causative gene discovery, gene-disease validity assessment via GenCC, pathogenic variant lookup via ClinVar, HPO phenotype mapping, epidemiology and prevalence data, clinical trial search, and literature review. Use when users ask about rare diseases, orphan diseases, genetic causes of rare conditions, Orphanet codes, HPO phenotypes, gene-disease validity, rare disease prevalence, or treatment options for rare genetic disorders.

Investigate transcription factor binding, cis-regulatory elements, chromatin accessibility, and regulatory variant annotation. Use when asked about TF binding sites, enhancers, promoters, ChIP-seq data, ATAC-seq signals, candidate cis-regulatory elements (cCREs), or the regulatory impact of genomic variants.

Regulatory variant interpretation -- GWAS association lookup, eQTL analysis, chromatin state annotation, regulatory element overlap, and trait ontology resolution. Connects GWAS Catalog, GTEx, ENCODE, RegulomeDB, OpenTargets, OLS ontology, and Ensembl regulatory features. Use when users ask about non-coding variants, GWAS hits, eQTLs, regulatory elements, enhancer/promoter variants, or trait-associated SNPs.

Production-ready RNA-seq differential expression analysis using PyDESeq2. Performs DESeq2 normalization, dispersion estimation, Wald testing, LFC shrinkage, and result filtering. Handles multi-factor designs, multiple contrasts, batch effects, and integrates with gene enrichment (gseapy) and ToolUniverse annotation tools (UniProt, Ensembl, OpenTargets). Supports CSV/TSV/H5AD input formats and any organism. Use when analyzing RNA-seq count matrices, identifying DEGs, performing differential expression with statistical rigor, or answering questions about gene expression changes.

Build AI scientist systems using ToolUniverse Python SDK for scientific research. Use when users need to access 1000++ scientific tools through Python code, create scientific workflows, perform drug discovery, protein analysis, genomics analysis, literature research, or any computational biology task. Triggers include requests to use scientific tools programmatically, build research pipelines, analyze biological data, search literature, predict drug properties, or create AI-powered scientific workflows.

Retrieve and analyze biological sequences -- gene/protein sequences from NCBI, Ensembl, and UniProt. Search nucleotide databases, fetch by accession, find orthologs, get gene summaries. Use when users ask about DNA/RNA/protein sequences, gene lookups, ortholog searches, or sequence retrieval.

Retrieves biological sequences (DNA, RNA, protein) from NCBI and ENA with gene disambiguation, accession type handling, and comprehensive sequence profiles. Creates detailed reports with sequence metadata, cross-database references, and download options. Use when users need nucleotide sequences, protein sequences, genome data, or mention GenBank, RefSeq, EMBL accessions.

Production-ready single-cell and expression matrix analysis using scanpy, anndata, and scipy. Performs scRNA-seq QC, normalization, PCA, UMAP, Leiden/Louvain clustering, differential expression (Wilcoxon, t-test, DESeq2), cell type annotation, per-cell-type statistical analysis, gene-expression correlation, batch correction (Harmony), trajectory inference, and cell-cell communication analysis. NEW: Analyzes ligand-receptor interactions between cell types using OmniPath (CellPhoneDB, CellChatDB), scores communication strength, identifies signaling cascades, and handles multi-subunit receptor complexes. Integrates with ToolUniverse gene annotation tools (HPA, Ensembl, MyGene, UniProt) and enrichment tools (gseapy, PANTHER, STRING). Supports h5ad, 10X, CSV/TSV count matrices, and pre-annotated datasets. Use when analyzing single-cell RNA-seq data, studying cell-cell interactions, performing cell type differential expression, computing gene-expression correlations by cell type, analyzing tumor-immune communication, or answering questions about scRNA-seq datasets.

Find, characterize, and source small molecules for chemical biology and drug discovery. Covers compound identification (PubChem, ChEMBL), structure search, binding affinity data, ADMET/drug-likeness prediction, and commercial availability (eMolecules, Enamine). Use when asked to find compounds, assess drug-likeness, search by structure, retrieve binding affinities, or source chemicals.

Computational analysis framework for spatial multi-omics data integration. Given spatially variable genes (SVGs), spatial domain annotations, tissue type, and disease context from spatial transcriptomics/proteomics experiments (10x Visium, MERFISH, DBiTplus, SLIDE-seq, etc.), performs comprehensive biological interpretation including pathway enrichment, cell-cell interaction inference, druggable target identification, immune microenvironment characterization, and multi-modal integration. Produces a detailed markdown report with Spatial Omics Integration Score (0-100), domain-by-domain characterization, and validation recommendations. Uses 70+ ToolUniverse tools across 9 analysis phases. Use when users ask about spatial transcriptomics analysis, spatial omics interpretation, tissue heterogeneity, spatial gene expression patterns, tumor microenvironment mapping, tissue zonation, or cell-cell communication from spatial data.

Analyze spatial transcriptomics data to map gene expression in tissue architecture. Supports 10x Visium, MERFISH, seqFISH, Slide-seq, and imaging-based platforms. Performs spatial clustering, domain identification, cell-cell proximity analysis, spatial gene expression patterns, tissue architecture mapping, and integration with single-cell data. Use when analyzing spatial transcriptomics datasets, studying tissue organization, identifying spatial expression patterns, mapping cell-cell interactions in tissue context, characterizing tumor microenvironment spatial structure, or integrating spatial and single-cell RNA-seq data for comprehensive tissue analysis.

Perform statistical modeling and regression analysis on biomedical datasets. Supports linear regression, logistic regression (binary/ordinal/multinomial), mixed-effects models, Cox proportional hazards survival analysis, Kaplan-Meier estimation, and comprehensive model diagnostics. Extracts odds ratios, hazard ratios, confidence intervals, p-values, and effect sizes. Designed to solve BixBench statistical reasoning questions involving clinical/experimental data. Use when asked to fit regression models, compute odds ratios, perform survival analysis, run statistical tests, or interpret model coefficients from provided data.

Research stem cells, iPSCs, organoids, and cell differentiation using ToolUniverse tools. Covers pluripotency marker identification, differentiation pathway analysis, organoid model characterization, cell type annotation, and disease modeling. Integrates CellxGene/HCA for single-cell atlas data, CellMarker for cell type markers, GEO for stem cell datasets, and pathway tools for differentiation signaling. Use when asked about stem cells, iPSCs, organoids, cell reprogramming, pluripotency, differentiation protocols, or 3D culture models.

Integrate structural biology data with proteomics for drug target validation. Retrieves protein structures from PDB (RCSB, PDBe), AlphaFold predictions, antibody structures (SAbDab), GPCR data (GPCRdb), binding pocket analysis (ProteinsPlus), and ligand interactions (BindingDB). Use when asked to find structures for a drug target, identify binding site ligands, cross-validate drug binding with structural data, assess structural druggability, or compare experimental vs predicted structures.

Comprehensive structural variant (SV) analysis skill for clinical genomics. Classifies SVs (deletions, duplications, inversions, translocations), assesses pathogenicity using ACMG-adapted criteria, evaluates gene disruption and dosage sensitivity, and provides clinical interpretation with evidence grading. Use when analyzing CNVs, large deletions/duplications, chromosomal rearrangements, or any structural variants requiring clinical interpretation.

Comprehensive systems biology and pathway analysis using multiple pathway databases (Reactome, KEGG, WikiPathways, Pathway Commons, BioModels). Performs pathway enrichment, protein-pathway mapping, keyword searches, and systems-level analysis. Use when analyzing gene sets, exploring biological pathways, or investigating systems-level biology.

Gather comprehensive biological target intelligence from 9 parallel research paths covering protein info, structure, interactions, pathways, expression, variants, drug interactions, and literature. Features collision-aware searches, evidence grading (T1-T4), explicit Open Targets coverage, and mandatory completeness auditing. Use when users ask about drug targets, proteins, genes, or need target validation, druggability assessment, or comprehensive target profiling.

Assess chemical and drug toxicity via adverse outcome pathways, real-world adverse event signals, and toxicogenomic evidence. Integrates AOPWiki (AOPWiki_list_aops, AOPWiki_get_aop) for mechanism- level pathway tracing, FAERS for post-market adverse event quantification, OpenFDA for label mining, and CTD for chemical-gene-disease evidence. Produces structured toxicity reports with evidence grading (T1-T4). Use when asked about toxicity mechanisms, adverse outcome pathways, AOP mapping, FAERS signal detection, or chemical-disease relationships for drugs or environmental chemicals.

Design and evaluate vaccine candidates using computational immunology tools. Covers epitope prediction (MHC-I/II binding via IEDB), population coverage analysis, antigen selection, adjuvant matching, and immunogenicity assessment. Integrates IEDB for epitope prediction, UniProt for antigen sequences, PDB/AlphaFold for structural epitopes, BVBRC for pathogen proteomes, and literature for clinical precedent. Use when asked about vaccine design, epitope prediction, immunogenicity, MHC binding, T-cell epitopes, B-cell epitopes, or population coverage for vaccine candidates.

Production-ready VCF processing, variant annotation, mutation analysis, and structural variant (SV/CNV) interpretation for bioinformatics questions. Parses VCF files (streaming, large files), classifies mutation types (missense, nonsense, synonymous, frameshift, splice, intronic, intergenic) and structural variants (deletions, duplications, inversions, translocations), applies VAF/depth/quality/consequence filters, annotates with ClinVar/dbSNP/gnomAD/CADD via ToolUniverse, interprets SV/CNV clinical significance using ClinGen dosage sensitivity scores, computes variant statistics, and generates reports. Solves questions like "What fraction of variants with VAF < 0.3 are missense?", "How many non-reference variants remain after filtering intronic/intergenic?", "What is the pathogenicity of this deletion affecting BRCA1?", or "Which dosage-sensitive genes overlap this CNV?". Use when processing VCF files, annotating variants, filtering by VAF/depth/consequence, classifying mutations, interpreting structural variants, assessing CNV pathogenicity, comparing cohorts, or answering variant analysis questions.

Comprehensive functional annotation of protein variants — pathogenicity, population frequency, structural context, and clinical significance. Integrates ProtVar (map_variant, get_function, get_population) for protein-level mapping and structural context, ClinVar for clinical classifications, gnomAD for population frequency with ancestry data, CADD for deleteriousness scores, and ClinGen for gene-disease validity. Produces a structured variant annotation report with evidence grading. Use when asked about protein variant impact, missense variant pathogenicity, ProtVar annotation, variant functional context, or combining population and structural evidence for a variant.

Systematic clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Aggregates evidence from ClinVar, gnomAD, CIViC, UniProt, and PDB across ACMG criteria. Produces pathogenicity scores (0-100), clinical recommendations, and treatment implications. Use when interpreting genetic variants, classifying variants of uncertain significance (VUS), performing ACMG variant classification, or translating variant calls to clinical actionability.

End-to-end variant-to-mechanism analysis: given a genetic variant (rsID or coordinates), trace its functional impact from regulatory context (GWAS, eQTL, RegulomeDB, ENCODE) through target gene identification (GTEx, OpenTargets L2G) to downstream pathway and disease biology (STRING, Reactome, GO enrichment, disease associations). Produces an evidence-graded mechanistic narrative linking genotype to phenotype. Use when asked "how does this variant cause disease?", "what is the mechanism of rs7903146?", "trace variant to pathway", or "connect this GWAS hit to biology".

Router skill for ToolUniverse tasks. First checks if specialized tooluniverse skills (105+ skills covering disease/drug/target research, gene-disease associations, clinical decision support, genomics, epigenomics, proteomics, comparative genomics, chemical safety, toxicology, systems biology, and more) can solve the problem, then falls back to general strategies for using 2300+ scientific tools. Covers tool discovery, multi-hop queries, comprehensive research workflows, disambiguation, evidence grading, and report generation. Use when users need to research any scientific topic, find biological data, or explore drug/target/disease relationships. ALSO USE for any biology, medicine, chemistry, pharmacology, or life science question — even simple factoid questions like "how many X in protein Y", "what drug interacts with Z", "what gene causes disease W", or "translate this sequence". These questions benefit from database lookups (UniProt, PubMed, ChEMBL, ClinVar, GWAS Catalog, etc.) rather than answering from memory alone. When in doubt about a scientific fact, USE THIS SKILL to verify against real databases.