What problem does it solve?
Cancer genomics research requires stitching together cohort construction, clinical metadata, somatic mutation profiling, copy number analysis, survival statistics, and variant annotation across multiple databases (GDC, Progenetix, OncoKB). This Skill provides a structured six-phase workflow that prevents common errors like interpreting pan-cancer mutation counts without cohort context.
Core Features & Use Cases
- Cohort & Clinical Data: List GDC projects, search cases, and retrieve demographics, diagnoses, and treatments for any TCGA project (e.g., TCGA-BRCA).
- Mutation & CNV Analysis: Query somatic mutations per gene and project, and search Progenetix for copy number amplifications or deletions by NCIt code and GRCh38 coordinates.
- Survival & Variant Interpretation: Run Kaplan-Meier survival analysis split by mutation status with log-rank p-values, and annotate variants with OncoKB oncogenicity and FDA-level therapy evidence.
- Use Case: Ask "What is the mutation frequency of TP53 in TCGA-LUAD and does it affect survival?" to get per-project mutation records, a survival comparison with p-value, and OncoKB clinical actionability in one workflow.
Quick Start
Ask the agent to analyze TP53 mutation frequency and survival impact in TCGA-BRCA using the cancer genomics workflow.