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.
SkillScore86Maintained
Automatic
◆Research pack
Last verified 8/23/2026
What it changes
Passed 18 of 21 test cases with the skill, and 10 of 21 without it.
Without skill45%
With skill86%
Checks it passed that the model alone missed
Queries associatedTargets with orderByScore score
Filters results where maximumClinicalStage equals PHASE_4
Sets enableIndirect parameter to true in the evidences query
and 9 more in the full report
9 fixed10 passed either way3 still failing0 broke
Pass-rate lift
+41 pp
Tokens
+224%
Agent turns
0%
Response time
-32%
Model gemini-3.6-flashMeasured 8/23/2026v119 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
If a target returns an empty list for drugAndClinicalCandidates in Open Targets, what alternative bioactivity database skill should be queried for preclinical small molecule activity data?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends querying ChEMBL via chembl-database-bioactivity for preclinical bioactivity data
Missed
Passed
case-22 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md599 linessingle file
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
Prerequisites
Python packages: requests
Data requirements: gene symbols (HGNC), Ensembl gene IDs, disease EFO IDs, or drug names
Environment: internet connection; no authentication needed
Rate limits: no hard limit stated; use reasonable delays for large queries (>100 targets)
pip install requests
Quick Start
import requests
OT_URL = "https://api.platform.opentargets.org/api/v4/graphql"
def ot_query(gql, variables=None):
r = requests.post(OT_URL, json={"query": gql, "variables": variables or {}})
r.raise_for_status()
return r.json()["data"]
# Top disease associations for BRCA1