| name | open-targets |
| description | Query the Open Targets Platform GraphQL API for target-disease associations, genetic and clinical evidence, tractability and safety liabilities, target prioritisation metrics, known drugs and mechanisms of action, and disease ontology. Use this skill for target identification and validation, target-disease evidence review, druggability assessment, drug repurposing, and resolving gene, disease, and drug names to Ensembl, MONDO, and ChEMBL identifiers. Also trigger when a query mentions Open Targets, platform.opentargets.org, association scores, tractability buckets, or api.platform.opentargets.org. |
| license | MIT |
| allowed-tools | Read Write Edit Bash |
| compatibility | Requires Python 3.10+ and outbound HTTPS access to api.platform.opentargets.org. The bundled client uses only the Python standard library and needs no API key or account. Data is CC0; the API is a shared public resource, so batch requests rather than looping. |
| metadata | {"version":"1.1","skill-author":"K-Dense Inc.","openclaw":{"emoji":"🎯","homepage":"https://platform.opentargets.org"},"hermes":{"category":"research"}} |
Open Targets Platform
Open Targets aggregates genetic, somatic, clinical, pathway, expression, animal-model, and
literature evidence into scored target–disease associations, and attaches druggability and safety
annotation to every target. It answers the question that comes before any modelling work: is
this target worth working on for this disease, and what is already known about it?
Endpoint: https://api.platform.opentargets.org/api/v4/graphql — POST, JSON, no key.
Docs: platform-docs.opentargets.org ·
playground
Checked against: the live API, August 2026 — meta reports API 26.6.3, data release 26.06.
Read references/graphql-schema.md before writing a query by hand,
references/datasources.md before interpreting or filtering a score,
and references/query-cookbook.md for tested documents to adapt.
Start here: three identifier rules
Everything else fails downstream of getting these wrong.
- Targets are Ensembl gene ids (
ENSG00000146648) — never symbols, UniProt accessions, or
transcript ids.
- Diseases are MONDO ids (
MONDO_0005233) in almost all cases, even though the argument is
still named efoId. Most EFO_* ids from older tutorials now return null silently.
A few nodes legitimately keep EFO_, HP_, or OTAR_ ids, so you cannot rewrite the prefix —
resolve the name and use what comes back.
- Drugs are ChEMBL molecule ids (
CHEMBL939).
Always resolve first:
python skills/open-targets/scripts/ot_query.py resolve EGFR "non-small cell lung carcinoma" gefitinib
term id name entity score
EGFR ENSG00000146648 EGFR target 1
non-small cell lung carcinoma MONDO_0005233 non-small cell lung carcinoma disease 1
gefitinib CHEMBL2087361 ICOTINIB drug 1
gefitinib CHEMBL553 ERLOTINIB drug 1
gefitinib CHEMBL939 GEFITINIB drug 1
