Tooluniverse Drug Target Validation

This is a computational go/no-go framework for drug targets before you commit resources to medichem. It runs a gated validation across genetic evidence, druggability, safety, and competitive landscape, then outputs a 0-100 score with a tier classification. The pipeline enforces an evidence hierarchy: genetic links first (OpenTargets, GWAS), then structural tractability (PDB, AlphaFold), tissue safety (GTEx), and existing compounds (ChEMBL, ClinicalTrials.gov). It's opinionated about running ML models even when you have database evidence, and it makes you compute rather than describe. Use this when you need a defensible rationale for target prioritization or deselection, not for general target biology exploration.

skills.sh installs: 384
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-drug-target-validation --agent claude-code

Installs into .claude/skills of the current project.

Files

Drug Target Validation Pipeline

Validate drug target hypotheses using multi-dimensional computational evidence before committing to wet-lab work. Produces a quantitative Target Validation Score (0-100) with priority tier classification and GO/NO-GO recommendation.