AI-driven patient-to-trial matching for precision oncology and rare-disease care. Transforms a patient's molecular profile (mutations, biomarkers, expression) and clinical state into ranked clinical-trial recommendations with evidence tiers. Searches ClinicalTrials.gov, the EU CTIS register (Europea

Clinical Trial Matching for Precision Medicine 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. KEY PRINCIPLES : 1. Report first approach Create report file FIRST, then populate progressively 2. Patient centric Every recommendation considers the individual patient's profile 3. Molecular first matching Prioritize trials targeting patient's specific biomarkers Molecular Matching Priority Match patients to trials by molecular profile FIRST (specific mutations), then by disease stage, then by prior treatments. A patient with EGFR L858R should match to EGFR targeted trials regardless of other factors. 4. Evidence graded Every recommendation has an evidence tier (T1 T4) 5. Quantitative scoring Trial Match Score (0 100) for every trial 6. Eligibility aware Parse and evaluate inclusion/exclusion criteria 7. Actionable output Clear next steps, contact info, enrollment status 8. Source referenced Every statement cites the tool/database source 9. Completeness checklist Mandatory section showing analysis coverage 10. English first queries Always use English terms in tool calls. Respond in user's language LOOK UP, DON'T GUESS When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database verified answer is always more reliable than a guess. COMPUTE, DON'T DESCRIBE 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. When to Use Apply when user asks: "What clinical trials are available for my NSCLC with EGFR L858R?" "Patient has BRAF V600E melanoma, failed ipilimumab what trials?" "Find basket trials for NTRK fusion" "Breast cancer with HER2 amplification, post CDK4/6 inhibitor trials" "KRAS G12C colorectal cancer clinical trials" "Immunotherapy trials for TMB high solid tumors" "Clinical trials near Boston for lung cancer" "What are my options after failing osimertinib for EGFR+ NSCLC?" NOT for (use other skills instead): Single variant interpretation without trial focus Use tooluniverse cancer variant interpretation Drug safety profiling Use tooluniverse adverse event detection Target validation Use tooluniverse drug target validation General disease research Use tooluniverse disease research Input Parsing Required Input Disease/cancer type : Free text disease name (e.g., "non small cell lung cancer", "melanoma") Strongly Recommended Molecular alterations : One or more biomarkers (e.g., "EGFR L858R", "KRAS G12C", "PD L1 50%", "TMB high") Stage/grade : Disease stage (e.g., "Stage IV", "metastatic", "locally advanced") Prior treatments : Previous therapies and outcomes (e.g., "failed platinum chemotherapy", "progressed on osimertinib") Optional Performance status : ECOG or Karnofsky score Geographic location : City/state for proximity filtering Trial phase preference : I, II, III, IV, or "any" Intervention type : drug, biological, device, etc. Recruiting status preference : recruiting, not yet recruiting, active For biomarker parsing rules and gene symbol normalization, see [MATCHING ALGORITHMS.md](./MATCHING ALGORITHMS.md). Workflow Overview Critical Tool Parameters Clinical Trial Search Tools Tool Key Parameters Notes search clinical trials query term (REQ), condition , intervention , pageSize Main search (ClinicalTrials.gov, U.S./global) search clinical trials action="search studies" (REQ), condition , intervention , limit Alternative search get clinical trial descriptions action="get study details" (REQ), nct id (REQ) Full trial details CTIS search trials query (REQ), limit , page EU/EEA trials (EU CTIS register, since 2022) — complements ClinicalTrials.gov CTIS get trial ct number (REQ, e.g. 2022 503001 38 01 ) Full EU trial detail (Part I/II, member states, results) ISRCTN search trials query (REQ), limit ISRCTN registry (UK based, WHO primary, international) — a third source ISRCTN get trial isrctn id (REQ, e.g. ISRCTN12336055 ) Full ISRCTN trial detail + cross ref ids (DOI/EudraCT/NCT) Geographic coverage : ClinicalTrials.gov is U.S. centric but global; many EU/EEA only trials appear only in the EU CTIS register, and UK/international trials in ISRCTN . For a comprehensive search — or any patient who could enroll outside the U.S. — query search clinical trials , CTIS search trials , and ISRCTN search trials , then merge (the three registers list largely disjoint trials; ISRCTN records carry DOI/EudraCT/NCT cross refs you can use to dedupe against the others). Each register has its own id namespace and detail tool: NCT→ get clinical trial , CT number→ CTIS get trial , ISRCTN id→ ISRCTN get trial . Batch Trial Detail Tools (all take nct ids array) Tool Second Required Param Returns get clinical trial eligibility criteria eligibility criteria="all" Eligibility text get clinical trial locations location="all" Site locations get clinical trial conditions and interventions condition and intervention="all" Arms/interventions get clinical trial status and dates status and date="all" Status/dates get clinical trial descriptions description type="brief" or "full" Titles/summaries get clinical trial outcome measures outcome measures="all" Outcomes Gene/Disease Resolution Tool Key Parameters MyGene query genes query , species OpenTargets get disease id description by name diseaseName OpenTargets get target id description by name targetName ols search efo terms query , limit Drug Information Tool Key Parameters Notes OpenTargets get drug id description by name drugName Resolve drug to ChEMBL ID OpenTargets get drug mechanisms of action by chemblId chemblId Drug MoA and targets OpenTargets get associated drugs by target ensemblID ensemblId , size Drugs for a target drugbank get targets by drug name or drugbank id query , case sensitive , exact match , limit (ALL REQ) Drug targets fda pharmacogenomic biomarkers (none) FDA biomarker drug list FDA get indications by drug name drug name , limit FDA indications Evidence Tools Tool Key Parameters PubMed search articles query , max results civic get variants by gene gene id (CIViC int ID), limit PharmGKB search genes query Known CIViC Gene IDs EGFR=19, BRAF=5, ALK=1, ABL1=4, KRAS=30, TP53=45, ERBB2=20, NTRK1=197, NTRK2=560, NTRK3=561, PIK3CA=37, MET=52, ROS1=118, RET=122, BRCA1=2370, BRCA2=2371 Critical Parameter Notes 1. DrugBank tools : ALL 4 parameters ( query , case sensitive , exact match , limit ) are REQUIRED 2. search clinical trials : query term is REQUIRED even for disease only searches 3. search clinical trials : action must be exactly "search studies" 4. CIViC civic search variants : Does NOT filter by query returns alphabetically 5. CIViC civic get variants by gene : Takes CIViC gene ID (integer), NOT gene symbol 6. Batch clinical trial tools : Accept arrays of NCT IDs, process in batches of 10 Scoring Summary Trial Match Score (0 100) : Molecular Match: 0 40 pts (exact variant=40, gene level=30, pathway=20, none=10, excluded=0) Clinical Eligibility: 0 25 pts (all met=25, most=18, some=10, ineligible=0) Evidence Strength: 0 20 pts (FDA approved=20, Phase III=15, Phase II=10, Phase I=5) Trial Phase: 0 10 pts (III=10, II=8, I/II=6, I=4) Geographic: 0 5 pts (local=5, same country=3, international=1) Recommendation Tiers : Optimal (80 100), Good (60 79), Possible (40 59), Exploratory (0 39) Evidence Tiers : T1 (FDA/guideline), T2 (Phase III), T3 (Phase I/II), T4 (computational) For detailed scoring logic, see [SCORING CRITERIA.md](./SCORING CRITERIA.md). Parallelization Strategy Group 1 (Phase 1 simultaneous): MyGene query genes per gene, OpenTargets disease search, ols search efo terms , fda pharmacogenomic biomarkers Group 2 (Phase 2 simultaneous): search clinical trials by disease, biomarker, and intervention; search clinical trials alternative Group 3 (Phase 3 simultaneous): All batch detail tools (eligibility, interventions, locations, status, descriptions) Group 4 (Phases 5 6 per drug): Drug resolution, MoA, FDA indications, PubMed evidence Error Handling 1. Wrap every tool call in try/except 2. Check for empty results and string error responses 3. Use fallback tools when primary fails (e.g., OLS if OpenTargets fails) 4. Document failures in completeness checklist 5. Never let one failure block the entire analysis Reference Files File Contents [TOOLS REFERENCE.md](./TOOLS REFERENCE.md) Full tool inventory with parameters and response structures [MATCHING ALGORITHMS.md](./MATCHING ALGORITHMS.md) Patient profile standardization, biomarker parsing, molecular eligibility matching, drug biomarker alignment code [SCORING CRITERIA.md](./SCORING CRITERIA.md) Detailed scoring tables, molecular match logic, drug biomarker alignment scoring [REPORT TEMPLATE.md](./REPORT TEMPLATE.md) Full markdown report template with all sections [TRIAL SEARCH PATTERNS.md](./TRIAL SEARCH PATTERNS.md) Search functions, batch retrieval, parallelization, common use patterns, edge cases [EXAMPLES.md](./EXAMPLES.md) Worked examples for different matching scenarios [QUICK START.md](./QUICK START.md) Quick start guide for common workflows

tooluniverse-clinical-trial-matching