Help us improve
Share bugs, ideas, or general feedback.
From tooluniverse
Provides evidence-tiered cancer treatment recommendations from molecular profiles, using CIViC, ClinVar, OpenTargets, and ClinicalTrials.gov for tumor-board-style therapy selection.
npx claudepluginhub mims-harvard/tooluniverse --plugin tooluniverseHow this skill is triggered — by the user, by Claude, or both
Slash command
/tooluniverse:tooluniverse-precision-oncologyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Provide actionable treatment recommendations for cancer patients based on their molecular profile using CIViC, ClinVar, OpenTargets, ClinicalTrials.gov, and structure-based analysis.
Transforms a gene + variant + cancer-type into an actionable precision oncology report with evidence tiers, therapeutic options, resistance mechanisms, and clinical trials for tumor-board variant interpretation.
Query COSMIC REST API v3.1 for somatic cancer mutations by gene/sample/variant, cancer gene census, mutational signatures, and drug resistance variants. Requires free registration.
Queries cBioPortal for cancer genomics data including somatic mutations, copy number alterations, gene expression, and survival analysis across hundreds of cancer studies.
Share bugs, ideas, or general feedback.
Provide actionable treatment recommendations for cancer patients based on their molecular profile using CIViC, ClinVar, OpenTargets, ClinicalTrials.gov, and structure-based analysis.
Treatment selection follows a strict evidence hierarchy: FDA-approved for this specific mutation in this cancer type ranks highest, followed by approval for this mutation in any cancer (tumor-agnostic), then active clinical trials, and finally off-label use. Skipping this hierarchy to recommend off-label therapies when an approved option exists is a clinical error. Always check current NCCN guidelines and recent literature, as approvals change rapidly — a drug that was investigational last year may now be first-line.
When looking up treatment for a specific mutation, search CIViC and OncoKB FIRST, not PubMed. These databases have curated evidence levels. PubMed is for when curated databases don't have the answer.
Biomarker-to-drug logic — When a biomarker is identified, the first-line targeted therapy follows established mappings. Always verify current approval status via OncoKB/CIViC, but use this as a starting framework:
Resistance mechanism reasoning — When a patient progresses on targeted therapy, distinguish primary resistance (never responded — check if the mutation was truly the driver, or if co-mutations like TP53/RB1 abrogate response) from acquired resistance (responded then progressed — on-target mutations or bypass activation). Common patterns:
civic_search_evidence_items with the drug name + "resistance", then PubMed_search_articles for recent mechanisms.OncoKB_annotate_variant and civic_search_variants; never assume approval status from memory.search_clinical_trials with the specific condition and mutation; do not cite trials from memory.civic_search_evidence_items and PubMed_search_articles; do not assume resistance pathways.GDC_get_mutation_frequency or cBioPortal_get_mutations; do not estimate prevalence.KEY PRINCIPLES:
| Tool | WRONG | CORRECT |
|---|---|---|
civic_get_variant | variant_name | variant_id (numeric, e.g., 4170) |
civic_get_evidence_item | variant_id | id (numeric) |
OpenTargets_* | ensemblID | ensemblId (camelCase) |
search_clinical_trials | disease | condition |
Input: Cancer type + Molecular profile (mutations, fusions, amplifications)
Phase 1: Profile Validation -> Resolve gene IDs (Ensembl, UniProt, ChEMBL)
Phase 2: Variant Interpretation -> CIViC, ClinVar, COSMIC, GDC/TCGA, DepMap, OncoKB, cBioPortal, HPA
Phase 2.5: Tumor Expression -> CELLxGENE cell-type expression, ChIPAtlas regulatory context
Phase 3: Treatment Options -> OpenTargets + DailyMed (approved), ChEMBL (off-label)
Phase 3.5: Pathway & Network -> KEGG/Reactome pathways, IntAct interactions
Phase 4: Resistance Analysis -> CIViC + PubMed + NvidiaNIM structure analysis
Phase 5: Clinical Trials -> ClinicalTrials.gov search + eligibility
Phase 5.5: Literature -> PubMed, BioRxiv/MedRxiv preprints, OpenAlex citations
Phase 6: Report Synthesis -> Executive summary + prioritized recommendations
MyGene_query_genes - Resolve gene to Ensembl IDUniProt_search - Get UniProt accessionChEMBL_search_targets - Get ChEMBL target IDcivic_search_variants / civic_get_variant - CIViC evidenceCOSMIC_get_mutations_by_gene / COSMIC_search_mutations - Somatic mutationsGDC_get_mutation_frequency / GDC_get_ssm_by_gene - TCGA patient dataGDC_get_gene_expression / GDC_get_cnv_data - Expression and CNVGDC_get_survival - Kaplan-Meier survival data by project and optional gene mutation filterGDC_get_clinical_data - TCGA clinical metadata (stage, vital status, treatment, demographics)Progenetix_cnv_search - Copy number variation biosamples by genomic region and cancer type (NCIt code)DepMap_get_gene_dependencies / PharmacoDB_get_experiments - Target essentialityOncoKB_annotate_variant / OncoKB_get_gene_info - ActionabilitycBioPortal_get_mutations / cBioPortal_get_cancer_studies - Cross-study dataHPA_search_genes_by_query / HPA_get_comparative_expression_by_gene_and_cellline - ExpressionCELLxGENE_get_expression_data / CELLxGENE_get_cell_metadata - Cell-type expressionOpenTargets_get_associated_drugs_by_target_ensemblID - Approved drugs (param: ensemblId, camelCase)DGIdb_get_drug_gene_interactions - Drug-gene interactions (param: genes as array, e.g., ["EGFR"]). Comprehensive; covers inhibitors, antibodies, and investigational agents.DailyMed_search_spls - FDA label detailsChEMBL_get_drug_mechanisms - Drug mechanismkegg_find_genes / kegg_get_gene_info - KEGG pathwaysreactome_disease_target_score - Reactome disease relevanceintact_get_interaction_network - Protein interactionscivic_search_evidence_items - Search by known resistance mutations individually (e.g., molecular_profile="EGFR C797S", molecular_profile="MET Amplification"). The significance field in results indicates Resistance/Sensitivity — filter on it after retrieval.PubMed_search_articles - Resistance literature (e.g., "osimertinib resistance C797S combination therapy")alphafold_get_prediction / get_diffdock_info - Structure-based analysis (AlphaFold for structure, DiffDock for docking)search_clinical_trials - Find trials (param: condition, NOT disease)get_clinical_trial_eligibility_criteria - Eligibility detailsYou MUST call FAERS for the leading approved drug before finalizing the report. A clinical brief without real-world adverse-event data is incomplete.
FAERS_search_adverse_event_reports — REQUIRED: call with medicinalproduct="<drug_name>" for at least the top 1-2 approved drugs. Report top 10 serious AEs + death count.FDA_get_warnings_and_cautions_by_drug_name — REQUIRED: boxed warnings + key precautions.FAERS_count_death_related_by_drug - Mortality signal for a drugCPIC_list_guidelines - Check for relevant PGx guidelines (e.g., DPYD for fluoropyrimidines in chemo regimens, UGT1A1 for irinotecan). No CPIC guidelines exist for EGFR TKIs.fda_pharmacogenomic_biomarkers - FDA-labeled PGx biomarkers for the drugOncoKB demo mode: Without
ONCOKB_API_TOKENenv var, OncoKB only covers BRAF, TP53, ROS1. For other genes (EGFR, KRAS, ALK, etc.), set the API key or use CIViC as the primary evidence source.
PubMed_search_articles - Published evidence (use limit, mindate, maxdate for date filtering)BioRxiv_list_recent_preprints / MedRxiv_get_preprint - Preprints (flag as NOT peer-reviewed)openalex_search_works - Citation analysisFor CYP interaction with cancer drugs, run: python3 skills/tooluniverse-drug-drug-interaction/scripts/pharmacology_ref.py --type cyp_substrate --drug drugname