Opentargets Database

pip install requests

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
query = """
query TargetDiseases($ensgId: String!) {
  target(ensemblId: $ensgId) {
    id
    approvedSymbol
    associatedDiseases(page: {index: 0, size: 5}) {
      rows {
        disease { id name }
        score
      }
    }
  }
}
"""
data = ot_query(query, {"ensgId": "ENSG00000012048"})
target = data["target"]
print(f"Target: {target['approvedSymbol']}")
for row in target["associatedDiseases"]["rows"]:
    print(f"  {row['disease']['name']}: {row['score']:.3f}")

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"]

# Search by gene symbol
query = """
query SearchTarget($sym: String!) {
  search(queryString: $sym, entityNames: ["target"]) {
    hits {
      id
      name
      entity
      object {
        ... on Target {
          approvedSymbol
          approvedName
          biotype
          functionDescriptions
        }
      }
    }
  }
}
"""
data = ot_query(query, {"sym": "BRCA1"})
for hit in data["search"]["hits"][:3]:
    obj = hit.get("object", {})
    print(f"ID: {hit['id']} | {obj.get('approvedSymbol')} | {obj.get('biotype')}")
    descs = obj.get("functionDescriptions", [])
    if descs:
        print(f"  Function: {descs[0][:120]}")

# Direct lookup by Ensembl ID
query2 = """
query Target($ensgId: String!) {
  target(ensemblId: $ensgId) {
    id approvedSymbol approvedName biotype
    tractability { label modality value }
  }
}
"""
data2 = ot_query(query2, {"ensgId": "ENSG00000141510"})  # TP53
t = data2["target"]
print(f"\n{t['approvedSymbol']} ({t['id']}): {t['biotype']}")
print("Tractability:")
for tr in t.get("tractability", [])[:5]:
    print(f"  {tr['modality']} | {tr['label']}: {tr['value']}")

import requests, pandas as pd

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"]

query = """
query Associations($ensgId: String!, $size: Int!) {
  target(ensemblId: $ensgId) {
    approvedSymbol
    associatedDiseases(page: {index: 0, size: $size}, orderByScore: "score") {
      count
      rows {
        disease { id name therapeuticAreas { name } }
        score
        datatypeScores { id score }
      }
    }
  }
}
"""
data = ot_query(query, {"ensgId": "ENSG00000012048", "size": 20})
target = data["target"]
assoc = target["associatedDiseases"]
print(f"{target['approvedSymbol']}: {assoc['count']} associated diseases")

rows = []
for r in assoc["rows"]:
    scores = {d["id"]: d["score"] for d in r.get("datatypeScores", [])}
    rows.append({
        "disease": r["disease"]["name"],
        "disease_id": r["disease"]["id"],
        "overall_score": round(r["score"], 4),
        "genetics": round(scores.get("genetic_association", 0), 3),
        "drugs": round(scores.get("known_drug", 0), 3),
        "literature": round(scores.get("literature", 0), 3),
    })

df = pd.DataFrame(rows)
print(df.head(10).to_string(index=False))

import requests, pandas as pd

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"]

query = """
query DiseaseTargets($efoId: String!, $size: Int!) {
  disease(efoId: $efoId) {
    id name
    associatedTargets(page: {index: 0, size: $size}, orderByScore: "score") {
      count
      rows {
        target { id approvedSymbol biotype }
        score
        datatypeScores { id score }
      }
    }
  }
}
"""
# EFO_0000305 = breast carcinoma
data = ot_query(query, {"efoId": "EFO_0000305", "size": 10})
disease = data["disease"]
print(f"Disease: {disease['name']}")
print(f"Total associated targets: {disease['associatedTargets']['count']}")

for row in disease["associatedTargets"]["rows"][:5]:
    t = row["target"]
    print(f"  {t['approvedSymbol']:12s} score={row['score']:.3f} biotype={t['biotype']}")

import requests, pandas as pd

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"]

query = """
query KnownDrugs($ensgId: String!) {
  target(ensemblId: $ensgId) {
    approvedSymbol
    drugAndClinicalCandidates {
      count
      rows {
        maxClinicalStage
        drug { id name drugType maximumClinicalStage mechanismsOfAction { rows { mechanismOfAction } } }
        diseases { disease { id name } }
      }
    }
  }
}
"""
data = ot_query(query, {"ensgId": "ENSG00000146648"})  # EGFR
target = data["target"]
drugs_data = target["drugAndClinicalCandidates"]
print(f"{target['approvedSymbol']}: {drugs_data['count']} drug-indication pairs")

rows = []
for r in drugs_data["rows"]:
    drug = r["drug"]
    moa = drug.get("mechanismsOfAction") or {}
    moa_first = (moa.get("rows") or [{}])[0].get("mechanismOfAction")
    first_disease = (r.get("diseases") or [{}])[0].get("disease") or {}
    rows.append({
        "drug": drug["name"],
        "type": drug["drugType"],
        "maxClinicalStage": r["maxClinicalStage"],
        "approved": drug["maximumClinicalStage"] == "PHASE_4",
        "indication": first_disease.get("name", "n/a"),
        "mechanism": moa_first,
    })

df = pd.DataFrame(rows).drop_duplicates(subset=["drug", "indication"])
print(df.head(10).to_string(index=False))

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"]

query = """
query Evidence($ensgId: String!, $efoId: String!) {
  disease(efoId: $efoId) {
    evidences(
      ensemblIds: [$ensgId]
      enableIndirect: true
      size: 10
      datasourceIds: ["gwas_catalog", "clinvar", "chembl"]
    ) {
      count
      rows {
        datasourceId
        score
        variantRsId
        studyId
        publicationYear
        clinicalSignificances
      }
    }
  }
}
"""
data = ot_query(query, {"ensgId": "ENSG00000012048", "efoId": "EFO_0000305"})
evidences = data["disease"]["evidences"]
print(f"Evidence records: {evidences['count']}")
for ev in evidences["rows"][:5]:
    print(f"  Source: {ev['datasourceId']:20s} | Score: {ev['score']:.3f}")

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"]

query = """
query Safety($ensgId: String!) {
  target(ensemblId: $ensgId) {
    approvedSymbol
    safetyLiabilities {
      event
      effects { direction dosing }
      biosamples { tissueLabel cellLabel }
      datasource
    }
  }
}
"""
data = ot_query(query, {"ensgId": "ENSG00000146648"})  # EGFR
target = data["target"]
print(f"Safety liabilities for {target['approvedSymbol']}:")
for s in target.get("safetyLiabilities", [])[:5]:
    print(f"  Event: {s['event']}")
    # 2025 schema: `datasource` is a scalar literature-citation string,
    # not the legacy `datasources[{name, pmid}]` list of objects
    print(f"    Source: {s.get('datasource', 'n/a')}")
    for eff in s.get("effects", []) or []:
        print(f"    Effect: direction={eff.get('direction')} dosing={eff.get('dosing')}")

import requests, pandas as pd, time

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"]

def disease_search(name):
    q = 'query S($q:String!){search(queryString:$q,entityNames:["disease"]){hits{id name}}}'
    data = ot_query(q, {"q": name})
    return [(h["id"], h["name"]) for h in data["search"]["hits"][:3]]

def get_top_targets(efo_id, n=50):
    q = """
    query($efoId:String!,$size:Int!){
      disease(efoId:$efoId){
        name
        associatedTargets(page:{index:0,size:$size},orderByScore:"score"){
          count
          rows{
            target{id approvedSymbol biotype}
            score
            datatypeScores { id score }
          }
        }
      }
    }"""
    data = ot_query(q, {"efoId": efo_id, "size": n})
    disease = data["disease"]
    rows = []
    for row in disease["associatedTargets"]["rows"]:
        t = row["target"]
        scores = {d["id"]: round(d["score"], 3) for d in row.get("datatypeScores", [])}
        rows.append({
            "target": t["approvedSymbol"],
            "ensembl_id": t["id"],
            "biotype": t["biotype"],
            "overall_score": round(row["score"], 4),
            **scores
        })
    return disease["name"], pd.DataFrame(rows)

# Step 1: Find EFO ID for disease
candidates = disease_search("non-small cell lung carcinoma")
print("Disease candidates:", candidates)

# Step 2: Get top targets
disease_name, df = get_top_targets("EFO_0003060", n=50)
df.to_csv("target_prioritization.csv", index=False)
print(f"\nTop targets for {disease_name}:")
cols = [c for c in ["target", "overall_score", "genetic_association", "known_drug", "literature", "rna_expression", "somatic_mutation"] if c in df.columns]
print(df[cols].head(10).to_string(index=False))

import requests, pandas as pd

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"]

query = """
query($ensgId:String!){
  target(ensemblId:$ensgId){
    approvedSymbol
    drugAndClinicalCandidates{
      count
      rows{
        maxClinicalStage
        drug{id name drugType maximumClinicalStage mechanismsOfAction { rows { mechanismOfAction } } }
        diseases { disease { id name } }
      }
    }
  }
}"""

targets = {
    "EGFR": "ENSG00000146648",
    "ERBB2": "ENSG00000141736",
}

all_rows = []
for sym, ensg in targets.items():
    data = ot_query(query, {"ensgId": ensg})
    for row in data["target"]["drugAndClinicalCandidates"]["rows"]:
        drug = row["drug"]
        moa = drug.get("mechanismsOfAction") or {}
        moa_first = (moa.get("rows") or [{}])[0].get("mechanismOfAction")
        first_disease = (row.get("diseases") or [{}])[0].get("disease") or {}
        all_rows.append({
            "target": sym,
            "drug": drug["name"],
            "drug_type": drug["drugType"],
            "maxClinicalStage": row["maxClinicalStage"],
            "approved": drug["maximumClinicalStage"] == "PHASE_4",
            "indication": first_disease.get("name", "n/a"),
            "mechanism": moa_first,
        })

df = pd.DataFrame(all_rows)
df.to_csv("drug_target_matrix.csv", index=False)
print(df.head(10).to_string(index=False))