tooluniverse-drug-target-validation

# 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.

## Reasoning Before Searching

A valid drug target must pass 4 gates in order. Failing an early gate makes later gates irrelevant:

1. **Genetic evidence linking it to disease**: Does human genetic data (GWAS, rare variant studies, Mendelian genetics) support this target's role? Genetic evidence is the strongest predictor of clinical success. Use OpenTargets and GWAS catalog before anything else. If no genetic link exists, the hypothesis is speculative — document this clearly.
2. **Druggability**: Can a molecule reach and modulate the target? Check structure availability (PDB, AlphaFold), binding pocket prediction (ProteinsPlus), target class (kinase, GPCR, nuclear receptor = favorable; transcription factor, scaffold protein = difficult), and existing chemical probes.
3. **Safety — essentiality in normal tissue**: Is the target expressed in critical tissues (heart, liver, bone marrow)? Is knockout lethal in mice? High expression in essential tissue or lethality in mouse models is a strong safety red flag even before any clinical data.
4. **Competitive landscape**: Are other drugs already approved or in late-stage trials for this target? If so, the bar is differentiation, not first-in-class. Check ChEMBL, DrugBank, and ClinicalTrials.gov early.

Do not proceed to Phase 3 (Chemical Matter) before completing Phase 1 (Disease Association). Gate 1 failures should prompt a NO-GO or pivot recommendation.

**LOOK UP DON'T GUESS**: Never assume a target is druggable based on its protein family alone, never assume expression is low in a tissue without checking GTEx or HPA, never assume no competitors without searching ClinicalTrials.gov.

**RUN THE ML MODELS, DON'T SKIP THEM**: When deep-learning predictors are available (ADMET-AI, ESMFold, AlphaFold, DoGSite, DynaMut2, DeepGO), **run them even when database lookups or experimental data already cover the same property**. The ML predictions provide an orthogonal, mechanistically-grounded estimate that's a first-class output of this skill — not a fallback. A target-validation report missing ML predictions is incomplete regardless of how much database evidence is present.

## COMPUTE, DON'T DESCRIBE
When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

## Key Principles

1. **Report-first** - 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. **English-first queries** - Always use English terms in tool calls; respond in user's language

## When to Use

Apply when users ask about:
- "Is [target] a good drug target for [disease]?"
- Target validation, druggability assessment, or target prioritization
- Safety risks of modulating a target
- Chemical starting points for target validation
- GO/NO-GO recommendation for a target

**Not for** (use other skills): general target biology (`tooluniverse-target-research`), drug compound profiling (`tooluniverse-drug-research`), variant interpretation (`tooluniverse-variant-interpretation`), disease research (`tooluniverse-disease-research`).

## Input Parameters

| Parameter | Required | Description | Example |
|-----------|----------|-------------|---------|
| **target** | Yes | Gene symbol, protein name, or UniProt ID | `EGFR`, `P00533` |
| **disease** | No | Disease/indication for context | `Non-small cell lung cancer` |
| **modality** | No | Preferred therapeutic modality | `small molecule`, `antibody`, `PROTAC` |

## Reference Files

- **SCORING_CRITERIA.md** - Detailed scoring matrices, evidence grading, priority tiers, score calculation
- **REPORT_TEMPLATE.md** - Full report template, completeness checklist, section format examples
- **TOOL_REFERENCE.md** - Verified tool parameters, known corrections, fallback chains, modality-specific guidance, phase-by-phase tool lists
- **QUICK_START.md** - Quick start guide

---

## Scoring Overview

**Total: 0-100 points** across 5 dimensions (details in SCORING_CRITERIA.md):

| Dimension | Max | Sub-dimensions |
|-----------|-----|----------------|
| Disease Association | 30 | Genetic (10) + Literature (10) + Pathway (10) |
| Druggability | 25 | Structure (10) + Chemical matter (10) + Target class (5) |
| Safety Profile | 20 | Expression (5) + Genetic validation (10) + ADRs (5) |
| Clinical Precedent | 15 | Based on highest clinical stage achieved |
| Validation Evidence | 10 | Functional studies (5) + Disease models (5) |

**Priority Tiers**: 80-100 = Tier 1 (GO) | 60-79 = Tier 2 (CONDITIONAL GO) | 40-59 = Tier 3 (CAUTION) | 0-39 = Tier 4 (NO-GO)

**Evidence Grades**: T1 (clinical proof) > T2 (functional studies) > T3 (associations) > T4 (predictions)

---

## Pipeline Phases

### Phase 0: Target Disambiguation (ALWAYS FIRST)

Resolve target to ALL identifiers before any analysis.

**Steps**:
1. `MyGene_query_genes` - Get initial IDs (Ensembl, UniProt, Entrez)
2. `ensembl_lookup_gene` - Get versioned Ensembl ID (species="homo_sapiens" REQUIRED)
3. `e