mims-harvard/tooluniverse▌

Toxicity assessment: identify the chemical, check known hazards (GHS, IARC), then look for ADMET predictions. Dose makes the poison — always consider exposure level, as a compound that is toxic at high doses may be safe at relevant exposures. Distinguish between acute toxicity (LD50, GHS category) and chronic hazards (carcinogenicity, endocrine disruption) — they require different risk management approaches. Computational predictions (ADMETAI) are T3 evidence and must be anchored by experimental

Systematic discovery of novel small molecule binders using 60+ ToolUniverse tools across druggability assessment, known ligand mining, similarity expansion, ADMET filtering, and synthesis feasibility.

Guide the user step-by-step through setting up ToolUniverse.

Transform genome-wide association studies (GWAS) into actionable drug targets and repurposing opportunities.

Production-ready VCF processing and variant annotation skill combining local bioinformatics computation with ToolUniverse database integration. Designed to answer bioinformatics analysis questions about VCF data, mutation classification, variant filtering, and clinical annotation.

Systematic variant interpretation using ToolUniverse - from raw variant calls to ACMG-classified clinical recommendations with structural impact analysis.

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Build and interpret polygenic risk scores for complex diseases using genome-wide association study (GWAS) data.

Comprehensive metabolomics research skill that identifies metabolites, analyzes studies, and searches metabolomics databases. Generates structured research reports with annotated metabolite information, study details, and database statistics.

Comprehensive protein interaction network analysis using ToolUniverse tools. Analyzes protein networks through a 4-phase workflow: identifier mapping, network retrieval, enrichment analysis, and optional structural data.

SNP interpretation: a GWAS hit is a REGION, not a single causal variant. The lead SNP may not be causal — it may be in LD with the causal variant. Always check LD structure and functional annotation before concluding a specific SNP is mechanistically responsible. Fine-mapping (SuSiE, FINEMAP credible sets) narrows the causal set but rarely identifies a single variant with certainty. L2G scores integrate eQTL, chromatin interaction, and distance data to predict the causal gene — a lead SNP mappin

Comprehensive skill for analyzing T-cell receptor (TCR) and B-cell receptor (BCR) repertoire sequencing data to characterize adaptive immune responses, clonal expansion, and antigen specificity.

Compare GWAS studies, perform meta-analyses, and assess replication across cohorts

Coordinate and integrate multiple omics datasets for comprehensive systems biology analysis. Orchestrates specialized ToolUniverse skills to perform cross-omics correlation, multi-omics clustering, pathway-level integration, and unified interpretation.

Nearest gene is often wrong. Use L2G (locus-to-gene) scores from Open Targets which integrate eQTL, chromatin interaction, and distance data. L2G > 0.5 is a strong prediction; positional mapping alone should not be used to claim a causal gene. A single GWAS study with p < 5e-8 is suggestive — replication across independent cohorts is required for high confidence. GWAS hits are associations in the studied population; effect sizes and even the implicated gene can differ across ancestries due

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Differential expression analysis of RNA-seq count data using PyDESeq2, with enrichment analysis (gseapy) and gene annotation via ToolUniverse.

Comprehensive statistical modeling skill for fitting regression models, survival models, and mixed-effects models to biomedical data. Produces publication-quality statistical summaries with odds ratios, hazard ratios, confidence intervals, and p-values.

Comprehensive clinical interpretation of somatic mutations in cancer. Transforms a gene + variant input into an actionable precision oncology report covering clinical evidence, therapeutic options, resistance mechanisms, clinical trials, and prognostic implications.

Not all guidelines carry equal weight. Evaluate sources in this order:

Validate drug target hypotheses using multi-dimensional computational evidence before committing to wet-lab work. Produces a quantitative Target Validation Score (0-100) with priority tier classification and GO/NO-GO recommendation.

Comprehensive analysis of metabolomics data from metabolite identification through quantification, statistical analysis, pathway interpretation, and integration with other omics layers.

Comprehensive analysis of spatially-resolved transcriptomics data to understand gene expression patterns in tissue architecture context. Combines expression profiling with spatial coordinates to reveal tissue organization, cell-cell interactions, and spatially variable genes.

Comprehensive skill for analyzing CRISPR-Cas9 genetic screens to identify essential genes, synthetic lethal interactions, and therapeutic targets through robust statistical analysis and pathway enrichment.

Safely push ToolUniverse code to GitHub by enforcing pre-push cleanup, pre-commit hooks, and test validation.

Comprehensive pathway and systems biology analysis integrating multiple curated databases to provide multi-dimensional view of biological systems, pathway enrichment, and protein-pathway relationships.

AI-guided antibody optimization pipeline from preclinical lead to clinical candidate. Covers sequence humanization, structure modeling, affinity optimization, developability assessment, immunogenicity prediction, and manufacturing feasibility.

Discover, create, validate, and integrate life science APIs into ToolUniverse.

AI-guided de novo protein design using RFdiffusion backbone generation, ProteinMPNN sequence optimization, and structure validation for therapeutic protein development.

Optimize tool descriptions in ToolUniverse JSON configuration files to ensure they are clear, complete, and user-friendly.

Systematically identify and evaluate drug repurposing candidates using multiple computational strategies.

Systematic workflow for creating production-ready ToolUniverse skills.

Best practices for high-quality research skills with evidence grading and source attribution.

Systematic diagnosis support for rare diseases using phenotype matching, gene panel prioritization, and variant interpretation across Orphanet, OMIM, HPO, ClinVar, and structure-based analysis.

3 calling patterns -- start with pattern 1:

Gather complete target intelligence by exploring 9 parallel research paths. Supports targets identified by gene symbol, UniProt accession, Ensembl ID, or gene name.

Retrieve protein structures with disambiguation, quality assessment, and comprehensive metadata.

Retrieve comprehensive chemical compound data with proper disambiguation and cross-database validation.

Generate a comprehensive disease research report with full source citations. The report is created as a markdown file and progressively updated during research.

Route user questions to specialized skills. If no skill matches, use general strategies from references/general-strategies.md.

Systematic literature research: disambiguate, search with collision-aware queries, grade evidence, produce structured reports.

Production-ready skill for analyzing microscopy-derived measurement data using pandas, numpy, scipy, statsmodels, and scikit-image.

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Transform patient molecular profiles and clinical characteristics into prioritized clinical trial recommendations. Searches ClinicalTrials.gov and cross-references with molecular databases (CIViC, OpenTargets, ChEMBL, FDA) to produce evidence-graded, scored trial matches.

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Production-ready skill combining Python computation (pandas, scipy, numpy, pysam, statsmodels) with ToolUniverse annotation tools for epigenomics analysis.

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Comprehensive biological interpretation of spatial omics data. Transforms spatially variable genes (SVGs), domain annotations, and tissue context into actionable biological insights.

Characterize diseases across multiple molecular layers (genomics, transcriptomics, proteomics, pathways) to provide systems-level understanding of disease mechanisms, identify therapeutic opportunities, and discover biomarker candidates.

Predict patient response to immune checkpoint inhibitors (ICIs) using multi-biomarker integration. Transforms a patient tumor profile (cancer type + mutations + biomarkers) into a quantitative ICI Response Score with drug-specific recommendations, resistance risk assessment, and monitoring plan.

PhyKIT, Biopython, and DendroPy for alignment/tree analysis, evolutionary metrics, and comparative genomics.

Comprehensive analysis of mass spectrometry-based proteomics data from protein identification through quantification, differential expression, post-translational modifications, and systems-level interpretation.

Systematic analysis of drug-drug interactions with evidence-based risk scoring, mechanism identification, and clinical management recommendations.

Transform patient genomic and clinical profiles into actionable risk stratification, treatment recommendations, and personalized therapeutic strategies.

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Create new scientific tools following established patterns.

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Systematically assess clinical trial feasibility by analyzing 6 research dimensions. Produces comprehensive feasibility reports with quantitative enrollment projections, endpoint recommendations, and regulatory pathway analysis.

Retrieve gene expression experiments and multi-omics datasets with disambiguation and quality assessment.

Comprehensive drug investigation using 50+ ToolUniverse tools across chemical databases, clinical trials, adverse events, pharmacogenomics, and literature.

Diagnose and fix failing ToolUniverse tools through systematic error identification, targeted fixes, and validation.

Provide actionable treatment recommendations for cancer patients based on their molecular profile using CIViC, ClinVar, OpenTargets, ClinicalTrials.gov, and structure-based analysis.

Retrieve DNA, RNA, and protein sequences from NCBI and ENA with automatic gene disambiguation and cross-database handling. \n \n Searches NCBI Nucleotide by organism, gene name, strain, and sequence type; automatically disambiguates genes across species and resolves accession prefixes to the correct database \n Handles RefSeq (NC_, NM_, NP_) and GenBank accessions with intelligent fallback between NCBI and ENA; never attempts ENA queries on RefSeq-only accessions \n Returns detailed sequence pro