Skip to content
Skills Library
Science & research · Research

open-targets

/open-targets

Query the Open Targets Platform GraphQL API for gene-drug-disease associations, evidence scores, and therapeutic target validation. Use when the user needs disease associations for a gene, drug evidence for a target, or target prioritization for a disease. NOT for compound property lookup (use pubchem-compound), NOT for bioactivity measurements (use chembl-drug), NOT for protein 3D structures (use pdb-structure).

Repository
scienceclaw ↗
Licence
MIT
Last repository change
07.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
10
Deprecation

No signals detected. Repository changed on 07.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Query the Open Targets Platform GraphQL API for gene-drug-disease associations, evidence scores, and therapeutic target validation. Use when the user needs disease associations for a gene, drug evidence for a target, or target prioritization for a disease. NOT for compound property lookup (use pubchem-compound), NOT for bioactivity measurements (use chembl-drug), NOT for protein 3D structures (use pdb-structure).

Original author description

Query the Open Targets Platform GraphQL API for gene-drug-disease associations, evidence scores, and therapeutic target validation. Use when the user needs disease associations for a gene, drug evidence for a target, or target prioritization for a disease. NOT for compound property lookup (use pubchem-compound), NOT for bioactivity measurements (use chembl-drug), NOT for protein 3D structures (use pdb-structure).

How it works

  1. API Base URL
  2. API Endpoints
  3. Evidence Types
  4. Common Queries
  5. Best Practices
  6. Data Integrity Rule
Original SKILL.md headings · 128 lines, 810 words
SKILL.md preview
---
name: open-targets
description: "Query the Open Targets Platform GraphQL API for gene-drug-disease associations, evidence scores, and therapeutic target validation. Use when the user needs disease associations for a gene, drug evidence for a target, or target prioritization for a disease. NOT for compound property lookup (use pubchem-compound), NOT for bioactivity measurements (use chembl-drug), NOT for protein 3D structures (use pdb-structure)."
metadata: { "openclaw": { "emoji": "\ud83c\udfaf", "requires": { "bins": ["curl"] } } }
---

# Open Targets Platform Lookup

Query the Open Targets Platform GraphQL API to explore gene-drug-disease associations, evidence from genetic studies, known drugs, pathway data, and overall target validation scores.

## API Base URL

```
https://api.platform.opentargets.org/api/v4/graphql
```

All requests use HTTP POST with a JSON body containing `query` and optionally `variables`.

## API Endpoints

### Search Targets by Gene Symbol

```bash
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query { search(queryString: \"BRAF\", entityNames: [\"target\"], page: {size: 5, index: 0}) { total hits { id name entity description } } }"
  }' | python3 -m json.tool | head -40
```

### Get Target Details

Retrieve detailed information about a specific target by Ensembl gene ID:

```bash
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query { target(ensemblId: \"ENSG00000157764\") { id approvedSymbol approvedName biotype functionDescriptions subcellularLocations { location } } }"
  }' | python3 -m json.tool
```

### Get Disease Associations for a Target

Find diseases associated with a gene/target, ranked by overall association score:

```bash
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query { target(ensemblId: \"ENSG00000157764\") { approvedSymbol associatedDiseases(page: {size: 10, index: 0}) { count rows { disease { id name } score datatypeScores { id score } } } } }"
  }' | python3 -m json.tool | head -60
```

### Get Target Associations for a Disease

Find targets associated with a specific disease by EFO ID:

```bash
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query { disease(efoId: \"EFO_0000616\") { id name associatedTargets(page: {size: 10, index: 0}) { count rows { target { id approvedSymbol } score datatypeScores { id score } } } } }"
  }' | python3 -m json.tool | head -60
```

### Get Drug Evidence for a Target

Retrieve known drugs and clinical evidence for a target-disease pair:

```bash
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query { target(ensemblId: \"ENSG00000157764\") { approvedSymbol knownDrugs(page: {size: 10, index: 0}) { count rows { drug { id name mechanismsOfAction { rows { mechanismOfAction } } } phase status diseaseFromSource } } } }"
  }' | python3 -m json.tool | head -80
```

### Search Diseases

```bash
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query { search(queryString: \"melanoma\", entityNames: [\"disease\"], page: {size: 5, index: 0}) { total hits { id name entity description } } }"
  }' | python3 -m json.tool | head -40
```

## Evidence Types

The `datatypeScores` array contains scores for each evidence category:

- **genetic_association** -- GWAS and gene-burden analyses linking gene variants to disease
- **known_drug** -- approved or clinical-stage drugs with established target-disease evidence
- **affected_pathway** -- pathway-level evidence from Reactome and other pathway databases
- **somatic_mutation** -- cancer somatic mutation data from COSMIC, IntOGen, and others
- **literature** -- text-mined co-occurrences from Europe PMC literature
- **rna_expression** -- differential expression data from Expression Atlas
- **animal_model** -- phenotype evidence from mouse model knockouts (MGI, IMPC)

## Common Queries

```bash
# Resolve gene symbol to Ensembl ID
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{"query": "query { search(queryString: \"TP53\", entityNames: [\"target\"], page: {size: 1, index: 0}) { hits { id name } } }"}' | python3 -m json.tool

# Resolve disease name to EFO ID
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{"query": "query { search(queryString: \"breast cancer\", entityNames: [\"disease\"], page: {size: 1, index: 0}) { hits { id name } } }"}' | python3 -m json.tool

# Get drug details by ChEMBL ID
curl -s -X POST https://api.platform.opentargets.org/api/v4/graphql \
  -H "Content-Type: application/json" \
  -d '{"query": "query { drug(chemblId: \"CHEMBL941\") { id name drugType maximumClinicalTrialPhase mechanismsOfAction { rows { mechanismOfAction targets { id approvedSymbol } } } } }"}' | python3 -m json.tool
```

## Best Practices

1. Always resolve gene symbols to Ensembl IDs and disease names to EFO IDs before querying associations.
2. Use `page: {size: N, index: 0}` to control result counts; default pages can be large.
3. Filter by `datatypeScores` to focus on specific evidence types relevant to the research question.
4. Scores range from 0 to 1; values above 0.5 indicate strong association evidence.
5. Combine with ChEMBL skill for detailed bioactivity data on drugs found through Open Targets.
6. The API has no authentication requirement but rate limit to 10 requests per second.
7. Request only the fields you need to reduce response size and latency.

## Data Integrity Rule

NEVER fabricate database results from training data. Every protein ID, gene name, compound property, pathway ID, structure detail, and metadata MUST come from an actual API response in this conversation. If the API returns no results, errors, or partial data, report exactly what happened. Do not "fill in" missing data from memory or make up identifiers.

Versions

RepositoryScoreLicence
This page · beita6969/scienceclaw100MIT
K-Dense-AI/drug-discovery-agent-skills100MIT

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 86109cc293a0 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100chembl-drug
    Query the ChEMBL REST API for drug-target interactions, bioactivity data, ADMET properties, and approved drug information. Use when the user needs drug mechanism of action, binding affinity data, target information, or pharmacokinetic properties. NOT for basic compound lookup…
  • 100pubchem-compound
    Search and retrieve chemical compound data from PubChem's PUG REST API (110M+ compounds). Use when the user needs compound properties, molecular structures, similarity searches, substructure searches, or bioactivity data. NOT for protein structures (use pdb-structure), NOT for…
  • 100alterlab-opentargets
    Query the Open Targets Platform GraphQL API for target-disease associations, tractability and safety data, genetics/omics evidence, and known drugs. Use when identifying or prioritizing therapeutic drug targets, assessing target druggability/safety, or gathering target-disease…
  • 95chembl-database
    Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.
  • 100tooluniverse-kegg-disease-drug
    KEGG-based disease-drug-variant network research. Connects diseases to causal genes, drugs to molecular targets, and variants to pathways using KEGG's editorially curated databases (KEGG Disease, Drug, Network, Variant, Pathway). Use for drug repurposing via shared pathways,…
  • 95drug_target_identification
    Drug Target Identification Pipeline - Identify drug targets for a disease by querying OpenTargets for associated targets, then retrieve detailed target info from ChEMBL and protein data from UniProt. Use this skill for drug discovery tasks involving get associated targets by…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.