Predict patient response to immune checkpoint inhibitors (ICIs) by integrating tumor mutational burden (TMB), microsatellite instability (MSI), PD-L1 expression, HLA status, and immune-related gene expression. Outputs ICI Response Score with drug-specific recommendations and resistance-risk assessme

Immunotherapy Response Prediction 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. Reasoning Before Searching Not all tumors respond to checkpoint inhibitors. Reason through the biology before running tools: TMB (tumor mutational burden) : More somatic mutations produce more neoantigens, which are recognized by T cells. High TMB ( =10 mut/Mb, FDA approved threshold for pembrolizumab) generally predicts better response — but this varies by cancer type (e.g., RCC responds despite low TMB). MSI H (microsatellite instability high) : Caused by defective DNA mismatch repair (MMR). MSI H tumors have very high TMB and are pan cancer approved for pembrolizumab. Check MLH1, MSH2, MSH6, PMS2 mutations. PD L1 expression : The direct target of pembrolizumab/atezolizumab. High PD L1 (TPS =50% or CPS =10 depending on cancer) predicts response in some cancers (NSCLC) but not all (melanoma, where TMB is more predictive). Resistance factors are equally important: STK11, KEAP1, JAK1/2 loss, B2M mutations can render an otherwise TMB high tumor non responsive. Before calling any tool, determine which biomarkers are available for this patient and which are unknown. This determines which phases can be scored with data vs. must use cancer type priors. Do not default to "moderate" for unknowns — flag them explicitly as missing. LOOK UP DON'T GUESS : Never assume FDA approval for a biomarker ICI combination — always verify with fda pharmacogenomic biomarkers or FDA get indications by drug name . Cancer specific thresholds differ from pan cancer approvals. KEY PRINCIPLES : 1. Report first approach Create report file FIRST, then populate progressively 2. Evidence graded Every finding has an evidence tier (T1 T4) 3. Quantitative output ICI Response Score (0 100) with transparent component breakdown 4. Cancer specific All thresholds and predictions are cancer type adjusted 5. Multi biomarker Integrate TMB + MSI + PD L1 + neoantigen + mutations 6. Resistance aware Always check for known resistance mutations (STK11, PTEN, JAK1/2, B2M) 7. Drug specific Recommend specific ICI agents with evidence 8. Source referenced Every statement cites the tool/database source 9. English first queries Always use English terms in tool calls 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: "Will this patient respond to immunotherapy?" "Should I give pembrolizumab to this melanoma patient?" "Patient has NSCLC with TMB 25, PD L1 80% predict ICI response" "MSI high colorectal cancer which checkpoint inhibitor?" "Patient has BRAF V600E melanoma, TMB 15 immunotherapy or targeted?" "Compare pembrolizumab vs nivolumab for this patient profile" Input Parsing Required : Cancer type + at least one of: mutation list OR TMB value Optional : PD L1 expression, MSI status, immune infiltration data, HLA type, prior treatments, intended ICI See [INPUT REFERENCE.md](INPUT REFERENCE.md) for input format examples, cancer type normalization, and gene symbol normalization tables. Workflow Overview Phase 1: Input Standardization & Cancer Context 1. Resolve cancer type to EFO ID via OpenTargets get disease id description by name 2. Parse mutations into structured format: {gene, variant, type} 3. Resolve gene IDs via MyGene query genes 4. Look up cancer specific ICI baseline ORR from the cancer context table (see [SCORING TABLES.md](SCORING TABLES.md)) Phase 2: TMB Analysis 1. Classify TMB: Very Low (<5), Low (5 9.9), Intermediate (10 19.9), High ( =20) 2. Check FDA TMB H biomarker via fda pharmacogenomic biomarkers(drug name='pembrolizumab') 3. Apply cancer specific TMB thresholds (see [SCORING TABLES.md](SCORING TABLES.md)) 4. Note: RCC responds to ICIs despite low TMB; TMB is less predictive in some cancers Phase 3: Neoantigen Analysis 1. Estimate neoantigen burden: missense count 0.3 + frameshift count 1.5 2. Check mutation impact via UniProt get function by accession 3. Query known epitopes via iedb search epitopes 4. POLE/POLD1 mutations indicate ultra high neoantigen load Phase 4: MSI/MMR Status Assessment 1. Integrate MSI status if provided (MSI H = 25 pts, MSS = 5 pts) 2. Check mutations in MMR genes: MLH1, MSH2, MSH6, PMS2, EPCAM 3. Check FDA MSI H approvals via fda pharmacogenomic biomarkers(biomarker='Microsatellite Instability') Phase 5: PD L1 Expression Analysis 1. Classify PD L1: High ( =50%), Positive (1 49%), Negative (<1%) 2. Apply cancer specific PD L1 thresholds and scoring methods (TPS vs CPS) 3. Get baseline expression via HPA get cancer prognostics by gene(gene name='CD274') Phase 6: Immune Microenvironment Profiling 1. Query immune checkpoint gene expression for: CD274, PDCD1, CTLA4, LAG3, HAVCR2, TIGIT, CD8A, CD8B, GZMA, GZMB, PRF1, IFNG 2. Classify tumor: Hot (T cell inflamed), Cold (immune desert), Immune excluded, Immune suppressed 3. Run immune pathway enrichment via enrichr gene enrichment analysis Phase 7: Mutation Based Predictors 1. Resistance mutations (apply PENALTIES): STK11 ( 10), PTEN ( 5), JAK1/2 ( 10 each), B2M ( 15), KEAP1 ( 5), MDM2/4 ( 5), EGFR ( 5) 2. Sensitivity mutations (apply BONUSES): POLE (+10), POLD1 (+5), BRCA1/2 (+3), ARID1A (+3), PBRM1 (+5 RCC only) 3. Check CIViC and OpenTargets for driver mutation ICI context 4. Check DDR pathway genes: ATM, ATR, CHEK1/2, BRCA1/2, PALB2, RAD50, MRE11 Phase 8: Clinical Evidence & ICI Options 1. Query FDA indications for ICI drugs via FDA get indications by drug name 2. Search clinical trials via search clinical trials (params: condition , intervention , query term ) 3. Search PubMed for biomarker specific response data 4. Get drug mechanisms via OpenTargets get drug mechanisms of action by chemblId See [SCORING TABLES.md](SCORING TABLES.md) for ICI drug profiles and ChEMBL IDs. Phase 9: Resistance Risk Assessment 1. Check CIViC for resistance evidence via civic search evidence items 2. Assess pathway level resistance: IFN g signaling, antigen presentation, WNT/b catenin, MAPK, PI3K/AKT/mTOR 3. Summarize risk: Low / Moderate / High Phase 10: Multi Biomarker Score Integration Response Likelihood Tiers : 70 100 HIGH (50 80% ORR): Strong ICI candidate 40 69 MODERATE (20 50% ORR): Consider ICI, combo preferred 0 39 LOW (<20% ORR): ICI alone unlikely effective Confidence : HIGH (all 4 biomarkers), MODERATE HIGH (3/4), MODERATE (2/4), LOW (1), VERY LOW (cancer only) Phase 11: Clinical Recommendations 1. ICI drug selection using cancer specific algorithm (see [SCORING TABLES.md](SCORING TABLES.md)) 2. Monitoring plan : CT/MRI q8 12wk, ctDNA at 4 6wk, thyroid/liver function, irAEs 3. Alternative strategies if LOW response: targeted therapy, chemotherapy, ICI+chemo combo, ICI+anti angiogenic, ICI+CTLA 4 combo, clinical trials Output Report Save as immunotherapy response prediction {cancer type}.md . See [REPORT TEMPLATE.md](REPORT TEMPLATE.md) for the full report structure. Tool Parameter Reference BEFORE calling ANY tool , verify parameters. See [TOOLS REFERENCE.md](TOOLS REFERENCE.md) for verified tool parameters table. Key reminders: MyGene query genes : use query (NOT q ) EnsemblVEP annotate rsid : use variant id (NOT rsid ) drugbank tools: ALL 4 params required ( query , case sensitive , exact match , limit ) cBioPortal get mutations : gene list is a STRING not array ensembl lookup gene : REQUIRES species='homo sapiens' Evidence Tiers Tier Description Source Examples T1 FDA approved biomarker/indication FDA labels, NCCN guidelines T2 Phase 2 3 clinical trial evidence Published trial data, PubMed T3 Preclinical/computational evidence Pathway analysis, in vitro data T4 Expert opinion/case reports Case series, reviews References OpenTargets: https://platform.opentargets.org CIViC: https://civicdb.org FDA Drug Labels: https://dailymed.nlm.nih.gov DrugBank: https://go.drugbank.com PubMed: https://pubmed.ncbi.nlm.nih.gov IEDB: https://www.iedb.org HPA: https://www.proteinatlas.org cBioPortal: https://www.cbioportal.org

tooluniverse-immunotherapy-response-prediction