tooluniverse-drug-target-validation
Comprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ ToolUniverse tools. Produces a quantitative Target Validation Score (0-100) with GO/NO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or "is X a good drug target for Y?
npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-drug-target-validation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
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.
How it works
- Phase 0: Target Disambiguation & ID Resolution (ALWAYS FIRST): Resolve the target to all necessary identifiers using tools to obtain gene symbols, Ensembl IDs (including versioned forms), UniProt IDs, and cross-references. It then maps to OpenTargets, ChEMBL, UniProt function, and alternative names. Outputs a consolidated identity table for the target.
- Phase 1: Disease Association Evidence (0-30): Collects OpenTargets disease associations, GWAS genetic evidence, constraint scores (gnomAD), and literature evidence (PubMed and OpenTargets publications). Applies a scoring scheme across Genetic Evidence, Literature Evidence, and Pathway Evidence to derive disease association points.
- Phase 2: Druggability Assessment (0-25): Assesses tractability across modalities via OpenTargets, target class/family via OpenTargets and Pharos, DGIdb druggability, structural tractability (PDB availability, AlphaFold predictions, pocket detection with ProteinsPlus), and chemical matter via known probes/TEPs.
- Phase 3: Known Modulators & Chemical Matter: Identifies chemical starting points through ChEMBL bioactivity, BindingDB ligands, PubChem assays, and OpenTargets known drugs; compiles drug mechanisms and DGIdb data to contextualize chemical matter.
When to use it
Apply when users ask is a target a good drug target for a disease, need target validation or druggability assessment, or want a comprehensive target dossier for investment decisions. Not for general target biology overview, disease research, or pure compound profiling.
What it can touch
The workflow relies on the following inputs and tools (as listed in the skill): gene/protein identifiers, OpenTargets queries, ChEMBL searches, UniProt data, PubMed, gnomAD, Pharos, DGIdb, AlphaFold, PDB analyses, ProteinsPlus, ChEMBL activities, BindingDB, PubChem, and OpenTargets drug associations. The target identity resolution outputs include EnsemblId, Ensembl (versioned), UniProt, Entrez, ChEMBL, and HGNC mappings.
Caveats
The skill defines scoring rules (0-30 for disease association, 0-25 for druggability, 0-20 for safety, 0-15 for clinical precedent, and 0-10 for validation evidence) and tier-based recommendations, but these depend on the availability and quality of external data sources cited in the tool calls. It requires English-first queries and cites tool/database sources for statements. License is NOASSERTION. The description notes target disambiguation, evidence grading (T1–T4), and mandatory completeness checks; empty sections are treated as failures.
# 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. **KEY PRINCIPLES**: 1. **Report-first approach** - Create report file FIRST, then populate progressively 2. **Target disambiguation FIRST** - Resolve all identifiers before analysis 3. **Evidence grading** - Grade all evidence as T1 (experimental) to T4 (computational) 4. **Disease-specific** - Tailor analysis to disease context when provided 5. **Modality-aware** - Consider small molecule vs biologics tractability 6. **Safety-first** - Prominently flag safety concerns early 7. **Quantitative scoring** - Every dimension scored numerically (0-100 composite) 8. **Negative results documented** - "No data" is data; empty sections are failures 9. **Source references** - Every statement must cite tool/database 10. **Completeness checklist** - Mandatory section showing analysis coverage 11. **English-first queries** - Always use English terms in tool calls. Respond in user's language --- ## When to Use This Skill Apply when us
- When to Use This Skill
- Input Parameters
- Target Validation Scoring System
- Score Components (Total: 0-100)
- Priority Tiers
- Evidence Grading System
- Phase 0: Target Disambiguation & ID Resolution (ALWAYS FIRST)
- Resolution Strategy
- Identifier Resolution Output
- Known Parameter Corrections
- Phase 1: Disease Association Evidence (0-30 points)
- 1A. OpenTargets Disease Associations (Primary)
- 1B. GWAS Genetic Evidence
- 1C. Constraint Scores (gnomAD)
What does the tooluniverse-drug-target-validation skill do?
Comprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ ToolUniverse tools. Produces a quantitative Target Validation Score (0-100) with GO/NO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or "is X a good drug target for Y?
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-drug-target-validation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.