Agent skill · Databases

opentargets-database

Query Open Targets GraphQL API for target-disease associations, evidence, drug links, safety. Search targets by gene, diseases by EFO ID; scores from 20+ sources, drug mechanisms, tractability. For ChEMBL use chembl-database-bioactivity; for trials use clinicaltrials-database-search.

BioTender-maxgithub.com/BioTender-maxGitHub ↗
claude-codeNOASSERTION
Install
npx skills add BioTender-max/awesome-bio-agent-skills --skill opentargets-database --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 20 KB
Bundled scripts: none
Path: skills/sciagent/opentargets-database/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 135
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

It instructs an AI agent to query the Open Targets GraphQL API to access target-disease associations, evidence, and drug links, including safety information. It covers searching targets by gene symbol, retrieving diseases by EFO ID, and obtaining scores from multiple data sources. It also directs use of specific sub-databases for bioactivity and clinical trials when needed.

How it works

  • Establishes GraphQL requests to the OT API at https://api.platform.opentargets.org/api/v4/graphql.
  • Demonstrates query examples for:
    • Target lookup by gene symbol and by Ensembl ID, including metadata and tractability.
    • Target-disease associations with overall scores and datatype-specific scores.
    • Disease-target associations ranked by score.
    • Known drugs for a target with mechanisms and clinical stage.
    • Evidence for a target-disease pair with datasource-specific records.
    • Safety liabilities for a target with events and effects.
  • Uses a helper function ot_query(gql, variables) to send POST requests and parse data.
  • Provides Quick Start and Core API examples, including Python code blocks.
  • Notes prerequisites such as Python package requests and the use of EFO IDs for diseases.

When to use it

  • When ranking therapeutic targets for a disease by overall association score and evidence breakdown.
  • When finding diseases associated with a gene and their confidence scores.
  • When retrieving drugs for a target with mechanisms and clinical phase.
  • When assessing target druggability and tractability.
  • When pulling genetic association evidence and safety data for a target-disease pair.
  • When needing bioactivity data via chembl-database-bioactivity or clinical trial details via clinicaltrials-database-search.

What it can touch

  • Uses the Open Targets GraphQL API via HTTP requests.
  • Exposes data fields such as target, disease, associatedDiseases, drugAndClinicalCandidates, evidences, safetyLiabilities, and datatypeScores as part of responses.
  • Requires internet access; no authentication mentioned.

Caveats

  • License indicated as Apache-2.0 in the skill metadata.
  • Rate limits are not hard-stated; examples emphasize reasonable delays for large queries.
  • Some responses reference fields that may vary across API versions (e.g., safety datasource format); the examples reflect the described structure.
From the SKILL.md

# Open Targets Platform Database ## Overview Open Targets Platform integrates evidence from genetics, genomics, literature, and drug databases to systematically score target-disease associations for 60,000+ targets and 20,000+ diseases/phenotypes. The public GraphQL API (no authentication required) provides access to association scores, evidence from 20+ data sources (GWAS, ClinVar, ChEMBL, drugs, pathways, mouse models, expression), and detailed drug-target-disease triangles. ## When to Use - Ranking therapeutic targets for a disease by overall association score and evidence breakdown - Finding all diseases associated with a gene of interest and their confidence scores - Retrieving approved and investigational drugs for a target, with mechanism of action and clinical phase - Assessing target druggability and tractability (small molecule, antibody, PROTAC likelihood) - Pulling genetic association evidence (GWAS hits, variant-to-gene mappings) for a target-disease pair - Exploring safety/adverse event data for a drug target from FAERS and literature - For bioactivity IC50/Ki data use `chembl-database-bioactivity`; for clinical trial details use `clinicaltrials-database-search` ## Pr

What's inside
Steps it walks through
  1. Overview
  2. When to Use
  3. Prerequisites
  4. Quick Start
  5. Core API
  6. Query 1: Target Lookup by Gene Symbol
  7. Query 2: Target-Disease Associations
  8. Query 3: Disease-Target Associations
  9. Query 4: Known Drugs for a Target
  10. Query 5: Evidence for a Specific Target-Disease Pair
  11. Query 6: Safety and Adverse Events
  12. Key Concepts
  13. Association Scores
  14. EFO IDs for Diseases
Commands it runs
pip install requests
More from awesome-bio-agent-skills
All skills →
About this skill
What does the opentargets-database skill do?

Query Open Targets GraphQL API for target-disease associations, evidence, drug links, safety. Search targets by gene, diseases by EFO ID; scores from 20+ sources, drug mechanisms, tractability. For ChEMBL use chembl-database-bioactivity; for trials use clinicaltrials-database-search.

How do I install it?

Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill opentargets-database --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.

Keep going