Patient stratification for precision medicine — integrate genomic, clinical, and therapeutic data to split patients into responder/non-responder groups, risk tiers, or treatment-decision groups. Use for stratification-by-biomarker, treatment-selection logic, and personalized therapeutic strategy rep

Precision Medicine Patient Stratification Transform patient genomic and clinical profiles into actionable risk stratification, treatment recommendations, and personalized therapeutic strategies. Reasoning Before Searching Stratification means splitting patients into groups that respond differently to a treatment or have different prognoses. Ask these questions before running any tools: 1. What molecular feature predicts response? Candidates: somatic mutation (e.g., EGFR L858R), germline variant (e.g., BRCA1 LoF), expression level (e.g., HER2 overexpression), germline pharmacogenomic variant (e.g., CYP2C19 PM), or composite biomarker (e.g., TMB H + MSI H). 2. Is the predictive feature actionable? Knowing it must change treatment — either the drug choice, dose, or monitoring plan. A variant with prognostic value but no therapeutic consequence is not a stratification biomarker. 3. What is the evidence level for the stratifier? FDA approved companion diagnostic (T1) vs. exploratory (T4) changes how much weight to place on the finding. Route to the correct Phase 3 path BEFORE running Phase 2 tools — cancer, metabolic, CVD, rare disease, and autoimmune pipelines require different stratifiers. LOOK UP DON'T GUESS : Never assume a variant is pathogenic, never assume a gene is relevant to a disease, never assign metabolizer status without PharmGKB or CPIC evidence. KEY PRINCIPLES : 1. Report first Create report file FIRST, then populate progressively 2. Disease specific logic Cancer vs metabolic vs rare disease pipelines diverge at Phase 3 3. Multi level integration Germline + somatic + expression + clinical data layers 4. Evidence graded Every finding has an evidence tier (T1 T4) 5. Quantitative output Precision Medicine Risk Score (0 100) 6. Source referenced Every statement cites the tool/database source 7. English first queries Always use English terms in tool calls Reference files (same directory): TOOLS REFERENCE.md Tool parameters, response formats, phase by phase tool lists SCORING REFERENCE.md Scoring matrices, risk tiers, pathogenicity tables, PGx tables REPORT TEMPLATE.md Output report template, treatment algorithms, completeness requirements EXAMPLES.md Six worked examples (cancer, metabolic, NSCLC, CVD, rare, neuro) QUICK START.md Sample prompts and output summary 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 about patient risk stratification, treatment selection, prognosis prediction, or personalized therapeutic strategy for any disease with genomic/clinical data. NOT for (use other skills instead): Single variant interpretation tooluniverse variant interpretation Immunotherapy specific prediction tooluniverse immunotherapy response prediction Drug safety profiling only tooluniverse adverse event detection Target validation tooluniverse drug target validation Clinical trial search only tooluniverse clinical trial matching Drug drug interaction only tooluniverse drug drug interaction PRS calculation only tooluniverse polygenic risk score Input Parsing Required Disease/condition : Free text disease name At least one of : Germline variants, somatic mutations, gene list, or clinical biomarkers Optional (improves stratification) Age, sex, ethnicity, disease stage, comorbidities, prior treatments, family history Current medications (for DDI and PGx), stratification goal Disease Type Classification Classify into one category (determines Phase 3 routing): Category Examples CANCER Breast, lung, colorectal, melanoma METABOLIC Type 2 diabetes, obesity, NAFLD CARDIOVASCULAR CAD, heart failure, AF NEUROLOGICAL Alzheimer, Parkinson, epilepsy RARE/MONOGENIC Marfan, CF, sickle cell, Huntington AUTOIMMUNE RA, lupus, MS, Crohn's Critical Tool Parameter Notes See TOOLS REFERENCE.md for full details. Key gotchas: MyGene query genes : param is query (NOT q ) EnsemblVEP annotate rsid : param is variant id (NOT rsid ) ensembl lookup gene : REQUIRES species='homo sapiens' DrugBank tools : ALL require 4 params: query , case sensitive , exact match , limit cBioPortal get mutations : gene list is a STRING (space separated), not array PubMed search articles : Returns a plain list of dicts, NOT {articles: [...]} fda pharmacogenomic biomarkers : Use limit=1000 for all results gnomAD : May return "Service overloaded" skip gracefully OpenTargets : Always nested {data: {entity: {field: ...}}} structure Workflow Overview Phase 1: Disease Disambiguation & Profile Standardization 1. Resolve disease to EFO ID using OpenTargets get disease id description by name 2. Classify disease type (CANCER/METABOLIC/CVD/NEUROLOGICAL/RARE/AUTOIMMUNE) 3. Parse genomic data into structured format (gene, variant, type) 4. Resolve gene IDs using MyGene query genes to get Ensembl/Entrez IDs Phase 2: Genetic Risk Assessment 1. Germline variant pathogenicity : ClinVar search variants , EnsemblVEP annotate rsid / hgvs 2. Gene disease association : OpenTargets target disease evidence 3. GWAS polygenic risk : gwas get associations for trait , OpenTargets search gwas studies by disease 4. Population frequency : gnomad get variant 5. Gene constraint : gnomad get gene constraints (pLI, LOEUF scores) Scoring: See SCORING REFERENCE.md for genetic risk score component (0 35 points). Phase 3: Disease Specific Molecular Stratification CANCER PATH 1. Molecular subtyping : cBioPortal get mutations , HPA get cancer prognostics by gene 2. TMB/MSI/HRD : fda pharmacogenomic biomarkers for FDA cutoffs 3. Prognostic stratification : Combine stage + molecular features METABOLIC PATH 1. Genetic risk integration : GWAS search associations by gene , OpenTargets target disease evidence 2. Complication risk : Based on HbA1c, duration, existing complications CVD PATH 1. FH gene check : ClinVar search variants for LDLR, APOB, PCSK9 2. Statin PGx : PharmGKB get clinical annotations for SLCO1B1 RARE DISEASE PATH 1. Causal variant identification : ClinVar search variants 2. Genotype phenotype : UniProt get disease variants by accession Scoring: See SCORING REFERENCE.md for disease specific tables. Phase 4: Pharmacogenomic Profiling 1. Drug metabolizing enzymes : PharmGKB get clinical annotations , PharmGKB get dosing guidelines 2. FDA PGx biomarkers : fda pharmacogenomic biomarkers (use limit=1000 ) 3. Treatment specific PGx : PharmGKB get drug details Scoring: See SCORING REFERENCE.md for PGx risk score (0 10 points). Phase 5: Comorbidity & Drug Interaction Risk 1. Disease overlap : OpenTargets get associated targets by disease efoId 2. DDI check : drugbank get drug interactions by drug name or id , FDA get drug interactions by drug name 3. PGx amplified DDI : If PM genotype + CYP inhibitor, flag compounded risk Phase 6: Molecular Pathway Analysis 1. Pathway enrichment : enrichr gene enrichment analysis (libs: KEGG 2021 Human , Reactome 2022 , GO Biological Process 2023 ) 2. Reactome mapping : ReactomeAnalysis pathway enrichment , Reactome map uniprot to pathways 3. Network analysis : STRING get interaction partners , STRING functional enrichment 4. Druggable targets : OpenTargets get target tractability by ensemblID Phase 7: Clinical Evidence & Guidelines 1. Guidelines search : PubMed Guidelines Search (fallback: PubMed search articles ) 2. FDA approved therapies : OpenTargets get associated drugs by disease efoId , FDA get indications by drug name 3. Biomarker drug evidence : civic search evidence items , civic search assertions Phase 8: Clinical Trial Matching 1. Biomarker driven trials : search clinical trials with condition + intervention 2. Precision medicine trials : search clinical trials for basket/umbrella trials Phase 9: Integrated Scoring & Recommendations Score Components (total 0 100) Genetic Risk (0 35): Pathogenicity + gene disease association + PRS Clinical Risk (0 30): Stage/biomarkers/comorbidities Molecular Features (0 25): Driver mutations, subtypes, actionable targets Pharmacogenomic Risk (0 10): Metabolizer status, HLA alleles Risk Tiers Score Tier Management 75 100 VERY HIGH Intensive treatment, subspecialty referral, clinical trial 50 74 HIGH Aggressive treatment, close monitoring 25 49 INTERMEDIATE Standard guideline based care, PGx guided dosing 0 24 LOW Surveillance, prevention, risk factor modification Output Generate report per REPORT TEMPLATE.md . See SCORING REFERENCE.md for detailed scoring matrices. Common Use Patterns See EXAMPLES.md for six detailed worked examples: 1. Cancer + actionable mutation : Breast cancer, BRCA1, ER+/HER2 Score ~55 65 (HIGH) 2. Metabolic + PGx concern : T2D, CYP2C19 PM on clopidogrel Score ~55 65 (HIGH) 3. NSCLC comprehensive : EGFR L858R, TMB 25, PD L1 80% Score ~75 85 (VERY HIGH) 4. CVD risk : LDL 190, SLCO1B1 5, family hx MI Score ~50 60 (HIGH) 5. Rare disease : Marfan, FBN1 variant Score ~55 65 (HIGH) 6. Neurological risk : APOE e4/e4, family hx Alzheimer's Score ~60 72 (HIGH)

tooluniverse-precision-medicine-stratification