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.
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
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.
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:
Report-first approach - Create report file FIRST, then populate progressively
Patient-centric - Every recommendation considers the individual patient's profile
Molecular-first matching - Prioritize trials targeting patient's specific biomarkers
Evidence-graded - Every recommendation has an evidence tier (T1-T4)
Quantitative scoring - Trial Match Score (0-100) for every trial
Eligibility-aware - Parse and evaluate inclusion/exclusion criteria
Actionable output - Clear next steps, contact info, enrollment status
Source-referenced - Every statement cites the tool/database source
defresolve_gene(tu, gene_symbol):
"""Resolve gene symbol to cross-database IDs."""# Normalize common aliases
alias_map = {
'HER2': 'ERBB2', 'HER-2': 'ERBB2',
'PD-L1': 'CD274', 'PDL1': 'CD274',
'PD-1': 'PDCD1', 'PD1': 'PDCD1',
'VEGF': 'VEGFA',
}
normalized = alias_map.get(gene_symbol.upper(), gene_symbol)
# MyGene resolution
result = tu.tools.MyGene_query_genes(query=normalized, species='human')
hits = result.get('hits', [])
gene_hit = Nonefor hit in hits:
if hit.get('symbol', '').upper() == normalized.upper():
gene_hit = hit
breakifnot gene_hit and hits:
gene_hit = hits[0]
if gene_hit:
ensembl = gene_hit.get('ensembl', {})
ensembl_id = ensembl.get('gene') ifisinstance(ensembl, dict) else (ensembl[0].get('gene') ifisinstance(ensembl, list) and ensembl elseNone)
return {
'symbol': gene_hit.get('symbol'),
'entrez_id': gene_hit.get('entrezgene'),
'ensembl_id': ensembl_id,
'name': gene_hit.get('name'),
'original_input': gene_symbol
}
return {'symbol': gene_symbol, 'entrez_id': None, 'ensembl_id': None, 'name': None, 'original_input': gene_symbol}
1.3 Biomarker Actionability Classification
Classify each biomarker using FDA pharmacogenomic biomarkers list:
defclassify_biomarker_actionability(tu, gene_symbol, alteration):
"""Classify biomarker as FDA-approved, guideline, or investigational."""# Check FDA pharmacogenomic biomarkers
fda_result = tu.tools.fda_pharmacogenomic_biomarkers()
fda_biomarkers = fda_result.get('results', [])
fda_match = [b for b in fda_biomarkers if gene_symbol.upper() instr(b.get('Biomarker', '')).upper()]
if fda_match:
return {
'level': 'FDA-approved',
'drugs': [b.get('Drug') for b in fda_match],
'labeling_sections': [b.get('LabelingSection') for b in fda_match]
}
# Check OpenTargets for drugs targeting this gene# (done in Phase 5)return {'level': 'investigational', 'drugs': [], 'labeling_sections': []}
defsearch_trials_by_intervention(tu, drug_name, disease_name=None, page_size=10):
"""Search trials by intervention/drug name."""
result = tu.tools.search_clinical_trials(
condition=disease_name if disease_name else'',
intervention=drug_name,
query_term=drug_name,
pageSize=page_size
)
ifisinstance(result, str):
return []
return result.get('studies', [])
2.4 Alternative Search (clinical_trials_search)
Use as a complement to the main search:
defsearch_trials_alternative(tu, condition, intervention=None, limit=10):
"""Alternative trial search with different API endpoint."""
params = {
'action': 'search_studies',
'condition': condition,
'limit': limit
}
if intervention:
params['intervention'] = intervention
result = tu.tools.clinical_trials_search(**params)
return result.get('studies', [])
2.5 Deduplication
defdeduplicate_trials(trial_lists):
"""Merge and deduplicate trials from multiple searches."""
seen_ncts = set()
unique_trials = []
for trials in trial_lists:
for trial in trials:
nct = trial.get('NCT ID') or trial.get('nctId', '')
if nct and nct notin seen_ncts:
seen_ncts.add(nct)
unique_trials.append(trial)
return unique_trials
Phase 3: Trial Characterization
Goal: Get detailed information for the top candidate trials.
3.1 Get Eligibility Criteria (Batch)
defget_trial_eligibility(tu, nct_ids):
"""Get eligibility criteria for multiple trials."""# Process in batches of 10
all_criteria = []
for i inrange(0, len(nct_ids), 10):
batch = nct_ids[i:i+10]
result = tu.tools.get_clinical_trial_eligibility_criteria(
nct_ids=batch,
eligibility_criteria='all'
)
ifisinstance(result, list):
all_criteria.extend(result)
return all_criteria
# Returns: [{NCT ID, eligibility_criteria: "Inclusion Criteria:\n...\nExclusion Criteria:\n..."}]
3.2 Get Conditions and Interventions (Batch)
defget_trial_interventions(tu, nct_ids):
"""Get conditions, arm groups, and interventions for multiple trials."""
all_interventions = []
for i inrange(0, len(nct_ids), 10):
batch = nct_ids[i:i+10]
result = tu.tools.get_clinical_trial_conditions_and_interventions(
nct_ids=batch,
condition_and_intervention='all'
)
ifisinstance(result, list):
all_interventions.extend(result)
return all_interventions
# Returns: [{NCT ID, condition, arm_groups: [{label, type, description, interventionNames}], interventions: [{type, name, description}]}]
3.3 Get Locations (Batch)
defget_trial_locations(tu, nct_ids):
"""Get trial site locations."""
all_locations = []
for i inrange(0, len(nct_ids), 10):
batch = nct_ids[i:i+10]
result = tu.tools.get_clinical_trial_locations(
nct_ids=batch,
location='all'
)
ifisinstance(result, list):
all_locations.extend(result)
return all_locations
# Returns: [{NCT ID, locations: [{facility, city, state, country}]}]
3.4 Get Status and Dates (Batch)
defget_trial_status(tu, nct_ids):
"""Get enrollment status and key dates."""
all_status = []
for i inrange(0, len(nct_ids), 10):
batch = nct_ids[i:i+10]
result = tu.tools.get_clinical_trial_status_and_dates(
nct_ids=batch,
status_and_date='all'
)
ifisinstance(result, list):
all_status.extend(result)
return all_status
# Returns: [{NCT ID, overall_status, start_date, primary_completion_date, completion_date}]
Goal: Determine how well the patient's molecular profile matches each trial's requirements.
4.1 Parse Eligibility Text for Biomarker Requirements
defextract_biomarker_requirements(eligibility_text):
"""Extract biomarker requirements from eligibility criteria text."""import re
requirements = {
'required_biomarkers': [],
'excluded_biomarkers': [],
'biomarker_agnostic': False
}
ifnot eligibility_text:
return requirements
text_upper = eligibility_text.upper()
# Common biomarker patterns in eligibility text# Required biomarkers (in inclusion criteria)
inclusion_section = eligibility_text.split('Exclusion Criteria')[0] if'Exclusion Criteria'in eligibility_text else eligibility_text
exclusion_section = eligibility_text.split('Exclusion Criteria')[1] if'Exclusion Criteria'in eligibility_text else''# Look for gene mutation requirements
gene_patterns = [
r'(?:EGFR|KRAS|BRAF|ALK|ROS1|RET|MET|NTRK|HER2|ERBB2|PIK3CA|BRCA|PD-?L1|MSI|TMB|dMMR)',
]
for pattern in gene_patterns:
# In inclusion sectionformatchin re.finditer(pattern, inclusion_section, re.IGNORECASE):
gene = match.group(0).upper()
context = inclusion_section[max(0, match.start()-100):match.end()+100]
requirements['required_biomarkers'].append({
'gene': gene,
'context': context.strip()
})
# In exclusion sectionformatchin re.finditer(pattern, exclusion_section, re.IGNORECASE):
gene = match.group(0).upper()
context = exclusion_section[max(0, match.start()-100):match.end()+100]
requirements['excluded_biomarkers'].append({
'gene': gene,
'context': context.strip()
})
# Check for biomarker-agnostic / basket trial language
basket_terms = ['tumor-agnostic', 'histology-independent', 'basket', 'any solid tumor', 'all comers', 'biomarker-selected']
ifany(term in text_upper.lower() for term in basket_terms):
requirements['biomarker_agnostic'] = Truereturn requirements
4.2 Score Molecular Match
defscore_molecular_match(patient_biomarkers, trial_requirements):
"""Score molecular match between patient and trial (0-40 points)."""ifnot trial_requirements['required_biomarkers'] andnot trial_requirements['excluded_biomarkers']:
# No molecular criteria - could be open to anyreturn10, 'No specific molecular criteria (general trial)'
patient_genes = {b['gene'].upper() for b in patient_biomarkers}
required_genes = {b['gene'].upper() for b in trial_requirements['required_biomarkers']}
excluded_genes = {b['gene'].upper() for b in trial_requirements['excluded_biomarkers']}
# Check exclusions first
excluded_match = patient_genes & excluded_genes
if excluded_match:
return0, f'Patient biomarker(s) {excluded_match} are in exclusion criteria'ifnot required_genes:
return10, 'No specific biomarker requirements found'# Check for exact gene match
matched_genes = patient_genes & required_genes
if matched_genes:
# Check for specific variant match# Look for specific mutation mentions in context
exact_variant_match = Falsefor req in trial_requirements['required_biomarkers']:
for pb in patient_biomarkers:
if pb['gene'].upper() == req['gene'].upper():
alt = pb.get('alteration', '').upper()
if alt and alt in req.get('context', '').upper():
exact_variant_match = Truebreakif exact_variant_match:
return40, f'Exact biomarker match: {matched_genes} with specific variant'else:
return30, f'Gene-level match: {matched_genes} (specific variant match unclear)'# Check for pathway-level match (e.g., trial targets EGFR pathway, patient has EGFR mutation)# This requires domain knowledge mappingreturn5, 'No direct biomarker match found'
Phase 5: Drug-Biomarker Alignment
Goal: Verify that trial drugs actually target the patient's biomarkers.
5.1 Identify Trial Drugs and Mechanisms
defget_drug_mechanism_info(tu, drug_name):
"""Get drug mechanism, targets, and approval status."""# Step 1: Resolve drug in OpenTargets
result = tu.tools.OpenTargets_get_drug_id_description_by_name(drugName=drug_name)
hits = result.get('data', {}).get('search', {}).get('hits', [])
ifnot hits:
return {'drug_name': drug_name, 'chembl_id': None, 'mechanisms': [], 'is_approved': False}
drug_info = hits[0]
chembl_id = drug_info.get('id')
# Step 2: Get mechanisms of action
moa_result = tu.tools.OpenTargets_get_drug_mechanisms_of_action_by_chemblId(chemblId=chembl_id)
moa_rows = moa_result.get('data', {}).get('drug', {}).get('mechanismsOfAction', {}).get('rows', [])
mechanisms = []
for row in moa_rows:
targets = row.get('targets', [])
mechanisms.append({
'mechanism': row.get('mechanismOfAction'),
'action_type': row.get('actionType'),
'target_name': row.get('targetName'),
'target_genes': [t.get('approvedSymbol') for t in targets]
})
# Step 3: Check approval
approval_result = tu.tools.OpenTargets_get_drug_approval_status_by_chemblId(chemblId=chembl_id)
return {
'drug_name': drug_name,
'chembl_id': chembl_id,
'description': drug_info.get('description'),
'mechanisms': mechanisms,
'is_approved': 'approved'in drug_info.get('description', '').lower()
}
5.2 Score Drug-Biomarker Alignment
defscore_drug_biomarker_alignment(patient_gene_symbols, drug_mechanisms):
"""Check if trial drug targets patient's biomarkers."""
patient_genes_upper = {g.upper() for g in patient_gene_symbols}
for mech in drug_mechanisms:
target_genes = {g.upper() for g in mech.get('target_genes', [])}
if patient_genes_upper & target_genes:
returnTrue, f"Drug targets {patient_genes_upper & target_genes} via {mech.get('mechanism')}"returnFalse, "No direct target overlap with patient biomarkers"
Phase 6: Evidence Assessment
Goal: Assess evidence strength for drug efficacy in similar patient populations.
6.1 FDA Approval Evidence
defcheck_fda_approval(tu, drug_name, disease_name):
"""Check FDA approval status and labeled indications."""
result = tu.tools.FDA_get_indications_by_drug_name(drug_name=drug_name, limit=3)
indications = result.get('results', [])
for ind in indications:
ind_text = str(ind.get('indications_and_usage', ''))
# Check if disease is mentioned in indicationsifany(term.lower() in ind_text.lower() for term in disease_name.split()):
return {
'approved': True,
'indication_text': ind_text[:500],
'brand_name': ind.get('openfda.brand_name', []),
'evidence_tier': 'T1'
}
return {'approved': False, 'indication_text': '', 'brand_name': [], 'evidence_tier': 'T3'}
6.2 Literature Evidence
defget_literature_evidence(tu, gene, alteration, drug_name, disease_name):
"""Search PubMed for evidence of drug efficacy for this biomarker."""
query = f'{gene}{alteration}{drug_name}{disease_name} clinical trial'
result = tu.tools.PubMed_search_articles(query=query, max_results=5)
articles = result ifisinstance(result, list) else result.get('articles', [])
return articles
Goal: Assess practical feasibility of trial enrollment.
7.1 Location Analysis
defanalyze_trial_locations(locations_data, patient_location=None):
"""Analyze trial site locations and proximity."""ifnot locations_data:
return {'total_sites': 0, 'countries': [], 'us_states': [], 'nearest': None}
locations = locations_data.get('locations', [])
countries = list(set(loc.get('country', '') for loc in locations if loc.get('country')))
us_states = list(set(loc.get('state', '') for loc in locations if loc.get('country') == 'United States'and loc.get('state')))
return {
'total_sites': len(locations),
'countries': countries,
'us_states': us_states,
'has_us_sites': 'United States'in countries,
'locations': locations[:10] # First 10 for display
}
7.2 Geographic Scoring
Criterion
Points
Trial sites in patient's state/city
5
Trial sites within 100 miles
3
Trial sites in same country
1
No location info or far away
0
Phase 8: Alternative Options
Goal: Identify basket trials, expanded access, and related studies.
8.1 Basket Trial Search
IMPORTANT: ClinicalTrials.gov search is sensitive to query complexity. Overly specific queries like "NTRK fusion tumor agnostic" may return zero results. Use simpler queries and combine results.
defsearch_basket_trials(tu, biomarker, page_size=10):
"""Search for basket/biomarker-driven trials.
NOTE: Use simpler queries first (e.g., 'NTRK solid tumor'),
then more specific ones. Complex multi-word queries often fail.
"""# Start with simpler queries (more likely to return results)
query_terms = [
f'{biomarker} solid tumor',
f'{biomarker}',
f'{biomarker} basket',
]
all_trials = []
for query in query_terms:
result = tu.tools.search_clinical_trials(
query_term=query,
pageSize=page_size
)
ifnotisinstance(result, str):
all_trials.extend(result.get('studies', []))
return deduplicate_trials([all_trials])
8.2 Expanded Access Search
defsearch_expanded_access(tu, drug_name):
"""Search for expanded access / compassionate use programs."""
result = tu.tools.search_clinical_trials(
query_term=f'{drug_name} expanded access',
pageSize=5
)
ifisinstance(result, str):
return []
return result.get('studies', [])
Phase 9: Trial Match Scoring System
Score Components (Total: 0-100)
Molecular Match (0-40 points):
Criterion
Points
Description
Exact biomarker match
40
Trial requires patient's specific variant
Gene-level match
30
Trial requires gene mutation, patient has specific variant
Pathway match
20
Trial targets same pathway as patient's biomarker
No molecular criteria
10
General disease trial
Excluded biomarker
0
Patient's biomarker is in exclusion criteria
Clinical Eligibility (0-25 points):
Criterion
Points
Description
All criteria met
25
Disease, stage, prior treatment all match
Most criteria met
18
1-2 criteria unclear
Some criteria met
10
Several criteria unclear
Clearly ineligible
0
Fails major criterion
Evidence Strength (0-20 points):
Criterion
Points
Description
FDA-approved combination
20
T1 evidence
Phase III positive
15
T2 evidence
Phase II promising
10
T3 evidence
Phase I or no results
5
T4 evidence
Trial Phase (0-10 points):
Phase
Points
Phase III
10
Phase II
8
Phase I/II
6
Phase I
4
Geographic Feasibility (0-5 points):
Criterion
Points
Patient's city/state
5
Same country
3
International only
1
Unknown
0
Recommendation Tiers
Score
Tier
Label
Action
80-100
Tier 1
Optimal Match
Strongly recommend - contact site immediately
60-79
Tier 2
Good Match
Recommend - discuss with care team
40-59
Tier 3
Possible Match
Consider - needs further eligibility review
0-39
Tier 4
Exploratory
Backup option - consider if Tier 1-3 unavailable
Phase 10: Report Synthesis
Report Template
The final report should follow this structure:
# Clinical Trial Matching Report**Patient**: [Disease type] with [biomarker(s)]
**Date**: [Current date]
**Trials Analyzed**: [N total] | **Top Matches**: [N with score >= 60]
---
## Executive Summary**Top 3 Trial Recommendations**:
1.**[NCT ID]** - [Brief title] (Score: XX/100, Tier N)
- Phase: [Phase], Status: [Status]
- Why: [Key reason for match]
2.**[NCT ID]** - [Brief title] (Score: XX/100, Tier N)
...
3.**[NCT ID]** - [Brief title] (Score: XX/100, Tier N)
...
---
## Patient Profile Summary
| Parameter | Value | Standardized |
|-----------|-------|-------------|
| Disease | [input] | [EFO name] (EFO_XXXX) |
| Biomarker(s) | [input] | [gene: variant, type] |
| Stage | [input] | [standardized] |
| Prior Treatment | [input] | [standardized] |
| Performance Status | [input] | [ECOG score] |
| Location | [input] | [city, state] |
### Biomarker Actionability
| Biomarker | Actionability Level | FDA-Approved Drugs | Evidence |
|-----------|--------------------|--------------------|----------|
| [gene variant] | [FDA-approved/investigational] | [drugs] | [T1/T2/T3/T4] |
---
## Ranked Trial Matches
### Trial 1: [NCT ID] - [Title]
**Trial Match Score: XX/100** (Tier N: [Label])
| Component | Score | Details |
|-----------|-------|---------|
| Molecular Match | XX/40 | [explanation] |
| Clinical Eligibility | XX/25 | [explanation] |
| Evidence Strength | XX/20 | [explanation] |
| Trial Phase | XX/10 | [phase] |
| Geographic | XX/5 | [location info] |
**Trial Details**:
- **Phase**: [Phase]
- **Status**: [Recruiting/Active/etc.]
- **Sponsor**: [Sponsor]
- **Start Date**: [Date]
- **Estimated Completion**: [Date]
**Interventions**:
- [Drug name]: [Mechanism] | [Dosing info if available]
- [Comparator]: [Description]
**Molecular Eligibility Match**:
- Required biomarkers: [list]
- Patient match: [Exact/Gene-level/Pathway/None]
- Notes: [details]
**Clinical Eligibility Assessment**:
- Disease type: [Match/Mismatch]
- Stage: [Match/Mismatch/Unclear]
- Prior treatment: [Match/Mismatch/Unclear]
- Performance status: [Match/Mismatch/Unclear]
**Evidence for Efficacy**:
- FDA approval: [Yes/No for this indication]
- Clinical results: [Phase III/II/I data if available]
- Mechanism alignment: [Drug targets patient's biomarker: Yes/No]
- Literature: [Key references]
**Trial Sites** (first 5):
- [City, State, Country]
- ...
**Next Steps**: [Contact info, enrollment instructions]
[Repeat for each matched trial]
---
## Trials by Category
### Targeted Therapy Trials
[List trials with targeted agents matching patient's biomarkers]
### Immunotherapy Trials
[List immunotherapy trials, noting PD-L1/TMB/MSI requirements]
### Combination Therapy Trials
[List trials with drug combinations]
### Basket/Platform Trials
[List biomarker-agnostic or multi-arm trials]
---
## Additional Testing Recommendations
If the patient has not been tested for certain biomarkers, these trials would become relevant:
| Biomarker | Test Needed | Trials Unlocked | Priority |
|-----------|-------------|----------------|----------|
| [e.g., TMB] | [NGS panel] | [NCT IDs] | [High/Medium/Low] |
---
## Alternative Options
### Expanded Access Programs
[List any expanded access or compassionate use programs]
### Off-Label Options
[FDA-approved drugs for other indications with same biomarker]
---
## Evidence Grading Summary
| Evidence Tier | Count | Description |
|--------------|-------|-------------|
| T1 (FDA/Guideline) | N | FDA-approved biomarker-drug, clinical guideline |
| T2 (Clinical) | N | Phase III data, robust clinical evidence |
| T3 (Emerging) | N | Phase I/II, preclinical evidence |
| T4 (Exploratory) | N | Computational, mechanism inference |
---
## Completeness Checklist
| Analysis Step | Status | Source |
|--------------|--------|--------|
| Disease standardization | [Done/Partial/Failed] | [OpenTargets/OLS] |
| Gene resolution | [Done/Partial/Failed] | [MyGene] |
| Biomarker actionability | [Done/Partial/Failed] | [FDA biomarkers] |
| Disease trial search | [Done/Partial/Failed] | [ClinicalTrials.gov] |
| Biomarker trial search | [Done/Partial/Failed] | [ClinicalTrials.gov] |
| Intervention trial search | [Done/Partial/Failed] | [ClinicalTrials.gov] |
| Eligibility parsing | [Done/Partial/Failed] | [ClinicalTrials.gov] |
| Drug mechanism analysis | [Done/Partial/Failed] | [OpenTargets/ChEMBL] |
| Evidence assessment | [Done/Partial/Failed] | [FDA/PubMed/CIViC] |
| Location analysis | [Done/Partial/Failed] | [ClinicalTrials.gov] |
| Basket trial search | [Done/Partial/Failed] | [ClinicalTrials.gov] |
| Expanded access search | [Done/Partial/Failed] | [ClinicalTrials.gov] |
| Scoring & ranking | [Done/Partial/Failed] | [Composite] |
---
## Disclaimer
This report is for informational and research purposes only. Clinical trial eligibility is ultimately determined by the trial investigators based on complete medical records. Patients should discuss all options with their healthcare team. Trial availability and status may change; verify current status at [ClinicalTrials.gov](https://clinicaltrials.gov).
## Sources
All data sourced from:
- ClinicalTrials.gov (trial search, eligibility, locations, status)
- OpenTargets Platform (drug-target associations, disease ontology)
- CIViC (clinical variant interpretations)
- ChEMBL (drug mechanisms, targets)
- FDA (approved indications, pharmacogenomic biomarkers, drug labels)
- DrugBank (drug targets, indications)
- PharmGKB (pharmacogenomics)
- PubMed/NCBI (literature evidence)
- OLS/EFO (disease ontology)
- MyGene (gene identifier resolution)
Execution Strategy
Parallelization Opportunities
Many tool calls can be executed in parallel to speed up the workflow:
Parallel Group 1 (Phase 1 - can all run simultaneously):
MyGene_query_genes for each gene
OpenTargets_get_disease_id_description_by_name for disease
ols_search_efo_terms for disease
fda_pharmacogenomic_biomarkers (no params)
Parallel Group 2 (Phase 2 - can all run simultaneously):
search_clinical_trials with disease condition
search_clinical_trials with biomarker query
search_clinical_trials with intervention query
clinical_trials_search as alternative
Parallel Group 3 (Phase 3 - can all run simultaneously):
get_clinical_trial_eligibility_criteria for all NCT IDs
get_clinical_trial_conditions_and_interventions for all NCT IDs
get_clinical_trial_locations for all NCT IDs
get_clinical_trial_status_and_dates for all NCT IDs
get_clinical_trial_descriptions for all NCT IDs
Parallel Group 4 (Phases 5-6 - for each drug):
OpenTargets_get_drug_id_description_by_name for drug
OpenTargets_get_drug_mechanisms_of_action_by_chemblId for drug
FDA_get_indications_by_drug_name for drug
PubMed_search_articles for evidence
Error Handling
For each tool call:
Wrap in try/except
Check for empty results
Use fallback tools when primary fails
Document what failed in completeness checklist
Never let one failure block the entire analysis
Performance Optimization
Batch NCT IDs in groups of 10 for detail tools
Limit initial search to 20-30 trials per search strategy
Focus detailed analysis on top 15-20 candidates after initial filtering
Cache gene/disease resolution results for reuse across phases
