Clinpgx Database

pip install requests pandas

import requests

CLINPGX = "https://api.clinpgx.org/v1"
CPIC    = "https://api.cpicpgx.org/v1"

# CPIC genotype → recommendation: clopidogrel + CYP2C19 Poor Metabolizer
drug = requests.get(f"{CPIC}/drug", params={"name": "eq.clopidogrel"}).json()[0]
recs = requests.get(f"{CPIC}/recommendation",
                    params={"drugid": f"eq.{drug['drugid']}",
                            "phenotypes": 'cs.{"CYP2C19":"Poor Metabolizer"}'}).json()
print(f"clopidogrel CYP2C19=PM: {len(recs)} recommendation(s)")
for rec in recs[:2]:
    print(f"  [{rec['classification']}] {rec['drugrecommendation'][:80]}…")

# ClinPGx side: how many CPIC guideline annotations cover CYP2C19?
glines = requests.get(f"{CLINPGX}/data/guidelineAnnotation",
                      params={"relatedGenes.symbol": "CYP2C19",
                              "source": "CPIC", "view": "base"}).json()["data"]
print(f"CYP2C19 CPIC guidelines: {len(glines)}")

import requests

CLINPGX = "https://api.clinpgx.org/v1"

r = requests.post(f"{CLINPGX}/site/search",
                  json={"query": "rs4149056"}, timeout=15)
r.raise_for_status()
hits = r.json()["data"]["hits"]
print(f"Total hits: {r.json()['data']['total']}")
for h in hits[:5]:
    print(f"  id={h.get('id')}  name={h.get('name')[:80]}")

# Broader concept search
r = requests.post(f"{CLINPGX}/site/search",
                  json={"query": "TPMT azathioprine"}, timeout=15)
hits = r.json()["data"]["hits"]
print(f"TPMT+azathioprine hits: {len(hits)}")
for h in hits[:5]:
    print(f"  {h.get('id'):>15}  {h.get('name','')[:80]}")

import requests

CLINPGX = "https://api.clinpgx.org/v1"

# Gene by HGNC symbol
gene = requests.get(f"{CLINPGX}/data/gene",
                    params={"symbol": "CYP2D6", "view": "base"}).json()["data"][0]
print(f"{gene['symbol']}  id={gene['id']}  {gene['name']}")

# Drug by name (lowercase generic preferred)
drug = requests.get(f"{CLINPGX}/data/drug",
                    params={"name": "warfarin", "view": "base"}).json()["data"][0]
print(f"{drug['name']}  id={drug['id']}")

# Variant by rsID
var = requests.get(f"{CLINPGX}/data/variant",
                   params={"name": "rs4149056", "view": "base"}).json()["data"][0]
print(f"{var['name']}  id={var['id']}  significance={var.get('clinicalSignificance')}")

# Direct record fetch when you already have a PA ID
r = requests.get(f"{CLINPGX}/data/drug/PA449088", params={"view": "max"}).json()
d = r["data"]
print(f"PA449088 → {d['name']}  (objCls={d['objCls']})")

import requests, pandas as pd

CLINPGX = "https://api.clinpgx.org/v1"

# All clinical annotations for clopidogrel
data = requests.get(f"{CLINPGX}/data/clinicalAnnotation",
                    params={"relatedChemicals.name": "clopidogrel",
                            "view": "base"}).json()["data"]
print(f"clopidogrel annotations: {len(data)}")

rows = []
for ann in data[:10]:
    loc = ann.get("location") or {}
    drugs = ", ".join(c.get("name", "") for c in ann.get("relatedChemicals", []))
    rows.append({
        "id": ann["id"],
        "variant": loc.get("displayName"),
        "gene": (loc.get("genes") or [{}])[0].get("symbol"),
        "drug": drugs,
        "level": (ann.get("levelOfEvidence") or {}).get("term"),
        "score": ann.get("score"),
    })
print(pd.DataFrame(rows).to_string(index=False))

# All Level 1A clinical annotations (highest evidence)
data = requests.get(f"{CLINPGX}/data/clinicalAnnotation",
                    params={"levelOfEvidence.term": "1A",
                            "view": "base"}).json()["data"]
print(f"Level 1A annotations: {len(data)}")

drug_to_count = {}
for ann in data:
    for c in ann.get("relatedChemicals") or []:
        drug_to_count[c["name"]] = drug_to_count.get(c["name"], 0) + 1
top = sorted(drug_to_count.items(), key=lambda x: -x[1])[:10]
for d, n in top:
    print(f"  {n:3}  {d}")

import requests

CLINPGX = "https://api.clinpgx.org/v1"

# All CPIC guidelines mentioning CYP2C19
data = requests.get(f"{CLINPGX}/data/guidelineAnnotation",
                    params={"relatedGenes.symbol": "CYP2C19",
                            "source": "CPIC",
                            "view": "base"}).json()["data"]
print(f"CYP2C19 CPIC guidelines: {len(data)}")
for g in data[:5]:
    print(f"  PA{g['id']}: {g['name'][:80]}")

# Guidelines for a specific drug across all bodies (CPIC, DPWG, …)
data = requests.get(f"{CLINPGX}/data/guidelineAnnotation",
                    params={"relatedChemicals.name": "clopidogrel",
                            "view": "base"}).json()["data"]
by_source = {}
for g in data:
    for s in (g.get("crossReferences") or []):
        by_source.setdefault(s.get("resource", "?"), 0)
        by_source[s["resource"]] = by_source.get(s["resource"], 0) + 1
print(f"clopidogrel guidelines: {len(data)} ({list({g.get('source') for g in data})})")

import requests, pandas as pd

CLINPGX = "https://api.clinpgx.org/v1"

data = requests.get(f"{CLINPGX}/data/label",
                    params={"relatedChemicals.name": "warfarin",
                            "source": "FDA",
                            "view": "base"}).json()["data"]
print(f"warfarin FDA labels: {len(data)}")

rows = [{
    "name": d["name"][:60],
    "biomarker_status": d.get("biomarkerStatus"),
    "testing_required": d.get("testingRequired"),
    "alternate_drug": d.get("alternateDrugAvailable"),
} for d in data]
print(pd.DataFrame(rows).to_string(index=False))

import requests

CPIC = "https://api.cpicpgx.org/v1"

# Resolve drug name to drugid (RxNorm-prefixed)
drug = requests.get(f"{CPIC}/drug",
                    params={"name": "eq.clopidogrel"}).json()[0]
print(f"clopidogrel drugid: {drug['drugid']}")

# All phenotype-specific recommendations for clopidogrel
recs = requests.get(f"{CPIC}/recommendation",
                    params={"drugid": f"eq.{drug['drugid']}"}).json()
print(f"Total recommendations: {len(recs)}")
for rec in recs[:3]:
    print(f"  {rec['phenotypes']}  [{rec['classification']}]")
    print(f"    {rec['drugrecommendation'][:90]}…")

# Phenotype filter via jsonb containment (cs.{...})
# The phenotypes column is a jsonb dict; cs. checks that the query is a subset.
recs = requests.get(f"{CPIC}/recommendation",
                    params={"drugid": f"eq.{drug['drugid']}",
                            "phenotypes": 'cs.{"CYP2C19":"Poor Metabolizer"}'}
                    ).json()
for rec in recs:
    print(f"  [{rec['classification']}] {rec['drugrecommendation'][:90]}…")

# Gene-driven: list every drug with a CPIC pair for CYP2C19
pairs = requests.get(f"{CPIC}/pair",
                     params={"genesymbol": "eq.CYP2C19"}).json()
print(f"\nCYP2C19 CPIC pairs: {len(pairs)}")
drug_ids = sorted({p["drugid"] for p in pairs})
print(f"Sample drug IDs: {drug_ids[:5]}")

import requests, pandas as pd, time

CLINPGX = "https://api.clinpgx.org/v1"
pharmacogenes = ["CYP2D6", "CYP2C19", "CYP2C9", "DPYD", "TPMT", "SLCO1B1"]

rows = []
for g in pharmacogenes:
    data = requests.get(f"{CLINPGX}/data/guidelineAnnotation",
                        params={"relatedGenes.symbol": g,
                                "source": "CPIC", "view": "base"},
                        timeout=20).json()["data"]
    drugs = sorted({c["name"] for guideline in data
                                for c in (guideline.get("relatedChemicals") or [])})
    rows.append({"gene": g, "cpic_guidelines": len(data),
                 "n_drugs": len(drugs), "sample": ", ".join(drugs[:3])})
    time.sleep(0.3)

df = pd.DataFrame(rows).sort_values("cpic_guidelines", ascending=False)
print(df.to_string(index=False))
df.to_csv("pharmacogene_cpic_coverage.csv", index=False)

import requests, pandas as pd, time

CPIC = "https://api.cpicpgx.org/v1"
drugs = ["warfarin", "clopidogrel", "codeine", "simvastatin",
         "metoprolol", "omeprazole", "azathioprine", "tacrolimus"]

rows = []
for name in drugs:
    drug = requests.get(f"{CPIC}/drug", params={"name": f"eq.{name}"}, timeout=15).json()
    if not drug:
        rows.append({"drug": name, "in_cpic": False, "n_recs": 0, "phenotypes": ""}); continue
    did = drug[0]["drugid"]
    recs = requests.get(f"{CPIC}/recommendation",
                        params={"drugid": f"eq.{did}"}, timeout=15).json()
    phens = sorted({f"{k}={v}" for rec in recs
                                  for k, v in (rec.get("phenotypes") or {}).items()})
    rows.append({"drug": name, "in_cpic": True, "n_recs": len(recs),
                 "phenotypes": "; ".join(phens[:3])})
    time.sleep(0.3)

df = pd.DataFrame(rows).sort_values(["in_cpic", "n_recs"], ascending=[False, False])
print(df.to_string(index=False))

import requests

CLINPGX = "https://api.clinpgx.org/v1"
rsid = "rs4149056"

hits = requests.post(f"{CLINPGX}/site/search",
                     json={"query": rsid}, timeout=15).json()["data"]["hits"]
print(f"{rsid}: {len(hits)} hits")

# Filter hits that look like clinical annotations
ann_hits = [h for h in hits if h.get("name", "").lower().startswith("clinical annotation")]
print(f"Clinical-annotation hits: {len(ann_hits)}")
for h in ann_hits[:5]:
    print(f"  id={h['id']}  {h['name'][:90]}")

# Dereference one annotation by ID for full detail
if ann_hits:
    ann = requests.get(f"{CLINPGX}/data/clinicalAnnotation/{ann_hits[0]['id']}",
                       params={"view": "max"}, timeout=15).json()["data"]
    drugs = ", ".join(c["name"] for c in (ann.get("relatedChemicals") or []))
    print(f"\nFirst annotation:")
    print(f"  drugs: {drugs}")
    print(f"  level: {(ann.get('levelOfEvidence') or {}).get('term')}")