skills.rest
mims-harvard
mims-harvardOFFICIAL
Explore all skills by this author →
Website𝕏@marinkazitnikGitHub

tooluniverse-clinical-trial-matching

Matches patient molecular profiles to ranked clinical trials with evidence-graded scoring.

1.7k|254|Updated Mar 3, 2025
Search Tags:#precision oncology#clinical trials#clinicaltrials.gov#evidence grading#trial eligibility#biomarker matching#patient recruitment
One-click install
npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-clinical-trial-matching
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tooluniverse-clinical-trial-matching
Source: https://github.com/mims-harvard/ToolUniverse/tree/main/plugins/tooluniverse/skills/tooluniverse-clinical-trial-matching
Command: npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-clinical-trial-matching

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Finding the right clinical trial for a patient with a specific cancer type and molecular profile requires manually searching registries, parsing eligibility criteria, and cross-referencing drug-biomarker evidence across many databases. This Skill automates that workflow, turning a patient profile into a scored, ranked list of trial recommendations.

Core Features & Use Cases

  • Molecular-first trial matching: Standardizes disease names to EFO ontology IDs and genes to Ensembl/Entrez IDs, then searches ClinicalTrials.gov, the EU CTIS register, and the ISRCTN registry by disease, biomarker, and intervention.
  • Quantitative scoring and evidence grading: Computes a 0-100 Trial Match Score (molecular match, eligibility, evidence strength, phase, geography) and assigns evidence tiers T1-T4 based on FDA approvals, CIViC, ChEMBL, OpenTargets, and PubMed data.
  • Structured report generation: Produces a markdown report with an executive summary, ranked trials, drug-biomarker alignment, alternative options (basket trials, expanded access), and a completeness checklist.
  • Use Case: Given "Stage IV NSCLC with EGFR L858R, failed platinum chemotherapy," the skill resolves the biomarker, searches three trial registries, parses eligibility text for EGFR requirements, and returns top trials such as EGFR TKI studies with scores and site locations.

Quick Start

Ask the agent to find clinical trials for a patient by describing the disease, biomarker, stage, prior treatments, and optionally a preferred location, for example: find clinical trials for a patient with BRAF V600E melanoma who failed ipilimumab.

Frequently Asked Questions about tooluniverse-clinical-trial-matching

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I match a patient to clinical trials by mutation?▼

Provide the disease type, specific biomarker (e.g., EGFR L858R or KRAS G12C), stage, and prior treatments. The skill standardizes these to ontology and gene IDs, searches trial registries by disease, biomarker, and intervention, then ranks matches with a 0-100 score.

What databases does clinical trial matching search?▼

It searches ClinicalTrials.gov, the EU CTIS register for European trials, and the ISRCTN registry for UK and international trials. Results are deduplicated using cross-reference identifiers, and evidence is drawn from CIViC, OpenTargets, ChEMBL, FDA, PharmGKB, and PubMed.

How is the Trial Match Score calculated?▼

The score totals 100 points: molecular match (0-40), clinical eligibility (0-25), evidence strength (0-20), trial phase (0-10), and geographic feasibility (0-5). Scores map to tiers: Optimal (80-100), Good (60-79), Possible (40-59), and Exploratory (0-39).

Can I find trials outside the United States?▼

Yes. In addition to ClinicalTrials.gov, the skill queries the EU CTIS register for EEA trials and the ISRCTN registry for UK and international studies, then merges results across all three registries for broader geographic coverage.

What happens when no trials match a rare biomarker?▼

The skill broadens the search from variant-level to gene-level and pathway-level queries, checks basket and tumor-agnostic trials, consults CIViC for variant evidence, and suggests additional biomarker testing or expanded access options in the report.

Are the trial eligibility results definitive for enrollment?▼

No. Eligibility assessment is approximate and based on parsing public criteria text. Final eligibility is determined by trial investigators, and trial status should be verified at ClinicalTrials.gov since availability changes frequently.

Related Skills

Explore More Education & Research Skills→
nahisahonahisaho
3

scientific-clinical-decision-support

Generate evidence-based treatment recommendations and clinical pathways from patient biomarker profiles.

Community
Advanced
mims-harvardmims-harvard
1.6k

tooluniverse-precision-oncology

Integrate CIViC, ClinVar, OpenTargets, and ClinicalTrials.gov to generate evidence-graded cancer treatment options.

Official
Advanced
QSong-githubQSong-github
130

faers-query

Query FDA FAERS adverse-event data via the openFDA Drug Event API.

Community
Advanced
felixboehmfelixboehm

clinvar-database

Query NCBI ClinVar for genetic variant clinical significance and pathogenicity.

Community
Intermediate