What problem does it solve?
Genome-wide association studies produce thousands of disease-linked loci, but translating those statistical signals into actionable drug targets requires connecting variants to causal genes, assessing druggability, and finding existing compounds. This Skill automates that GWAS-to-drug pipeline so genetic evidence directly informs target discovery and repurposing decisions.
Core Features & Use Cases
- GWAS Gene Discovery: Query GWAS Catalog and Open Targets for disease associations, map variants to genes via fine-mapping, eQTL, and L2G scores.
- Druggability & Prioritization: Score targets using a composite formula (GWAS evidence 40%, druggability 30%, clinical evidence 20%, novelty 10%) with tractability data from Open Targets.
- Drug Repurposing: Match approved drugs from ChEMBL and DGIdb to new disease indications, with safety profiles from FDA adverse event data.
- Use Case: Given Alzheimer's disease, retrieve GWAS hits (APOE, TREM2, CLU), rank them by genetic evidence and druggability, then surface repurposing candidates like Anakinra with mechanistic rationale and clinical phase.
Quick Start
Ask the AI to discover and rank druggable gene targets for type 2 diabetes using GWAS associations, then list any approved drugs that could be repurposed for it.