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

tooluniverse-cancer-variant-interpretation

Generates evidence-graded clinical interpretation reports for somatic cancer mutations using genomic databases.

1.7k|254|Updated Mar 3, 2025
Search Tags:#precision oncology#cbioportal#civic#clinical interpretation#mutation analysis#targeted therapy#cancer variant
One-click install
npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-cancer-variant-interpretation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tooluniverse-cancer-variant-interpretation
Source: https://github.com/mims-harvard/ToolUniverse/tree/main/plugins/tooluniverse/skills/tooluniverse-cancer-variant-interpretation
Command: npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-cancer-variant-interpretation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Interpreting a somatic cancer mutation (e.g., EGFR L858R) for treatment decisions requires manually querying a dozen databases—CIViC, cBioPortal, OpenTargets, FDA, ClinicalTrials.gov—and synthesizing the evidence into an actionable report. This Skill automates that entire workflow, producing a structured precision-oncology report with evidence tiers.

Core Features & Use Cases

  • Gene & Variant Resolution: Resolves gene symbols to Ensembl, UniProt, Entrez, and CIViC IDs, with alias normalization (HER2 → ERBB2) and verified tool parameters.
  • Evidence-Graded Reports: Produces a markdown report covering clinical evidence (CIViC), mutation prevalence (cBioPortal), FDA-approved and investigational therapies, resistance mechanisms, clinical trials, and prognostic impact—each finding tagged T1–T4.
  • Clinical Actionability Scoring: Assigns HIGH/MODERATE/LOW/UNKNOWN actionability with prioritized treatment recommendations and fallback chains when primary data sources return no results.
  • Use Case: A molecular tumor board receives "BRAF V600E in colorectal cancer" and gets a complete report showing encorafenib + cetuximab combination therapy [T1], resistance patterns, and recruiting trials.

Quick Start

Ask the agent to interpret a cancer variant, for example: "Interpret EGFR L858R for lung adenocarcinoma and list FDA-approved therapies and active clinical trials."

Frequently Asked Questions about tooluniverse-cancer-variant-interpretation

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

FAQPage Schema
How do I interpret a cancer mutation like EGFR L858R for treatment options?▼

Provide the gene symbol, variant notation, and optionally the cancer type. The skill resolves gene IDs, queries CIViC and OpenTargets for clinical evidence and drugs, checks cBioPortal for prevalence, and outputs a report with prioritized, evidence-tiered therapy recommendations.

What databases does cancer variant interpretation query?▼

It queries CIViC for clinical evidence, cBioPortal for mutation prevalence, OpenTargets and ChEMBL for drug associations, FDA and DrugBank for drug labels, ClinicalTrials.gov for trials, and PubMed, Reactome, and GTEx for literature, pathways, and expression.

How are treatment recommendations prioritized in the report?▼

Recommendations use a T1–T4 evidence tier system: T1 for FDA-approved therapies matching the mutation and cancer type, T2 for approvals in other cancer types or phase 2-3 trial data, T3 for preclinical evidence, and T4 for computational rationale.

What input formats are accepted for variant notation?▼

Accepted formats include amino acid changes (EGFR L858R), HGVS protein notation (BRAF p.V600E), exon-level events (EGFR exon 19 deletion), fusions (EML4-ALK), and amplifications (HER2 amplification). Common aliases like HER2 are normalized to ERBB2.

What happens when CIViC has no data for a variant?▼

The skill applies fallback chains rather than reporting no data: it searches PubMed for clinical evidence literature, uses ChEMBL when OpenTargets lacks drug hits, and tries pan-cancer cBioPortal studies when a specific study is unavailable.

Can it analyze resistance mechanisms after therapy failure?▼

Yes. It identifies on-target resistance mutations (e.g., EGFR T790M, C797S), bypass pathway activation via Reactome, and searches PubMed for resistance literature, then suggests next-line strategies such as later-generation inhibitors or combination trials.

Related Skills

Explore More Education & Research Skills→
stellaromicsstellaromics

bio-clinical-databases-tumor-mutational-burden

Calculate tumor mutational burden from somatic VCFs with panel-aware normalization.

Official
Advanced
patsnappatsnap
33

precision-oncology

Analyze cancer and tumor intelligence to build precision oncology reports.

Official
Advanced
TianGzlabTianGzlab
155

genomics-cnv-calling

Detect copy number variants from exome or whole-genome sequencing data using CNVkit, GATK gCNV, or Control-FREEC.

Official
Advanced
jey3dayojey3dayo

cross-research

Route research tasks across web, GitHub, and social media sources.

Community
Advanced