Clinvar Database

pip install requests
# No additional packages required; xml.etree is part of Python stdlib

import requests

EMAIL = "your@email.com"  # required by NCBI policy

def clinvar_search(query, retmax=10):
    """Search ClinVar and return a list of ClinVar Variation IDs."""
    r = requests.get(
        "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi",
        params={"db": "clinvar", "term": query, "retmax": retmax,
                "retmode": "json", "email": EMAIL}
    )
    r.raise_for_status()
    return r.json()["esearchresult"]["idlist"]

# Find pathogenic BRCA1 variants
ids = clinvar_search("BRCA1[gene] AND pathogenic[clinsig]", retmax=5)
print(f"Found variation IDs: {ids}")

import requests

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

def esearch(query, retmax=200):
    r = requests.get(f"{BASE}/esearch.fcgi",
                     params={"db": "clinvar", "term": query,
                             "retmax": retmax, "retmode": "json", "email": EMAIL})
    r.raise_for_status()
    result = r.json()["esearchresult"]
    return result["idlist"], int(result["count"])

# Gene-specific pathogenic variants
ids, total = esearch("BRCA2[gene] AND (pathogenic[clinsig] OR likely pathogenic[clinsig])")
print(f"Pathogenic/LP BRCA2 variants: {total} total, retrieved {len(ids)}")
print(f"First 5 IDs: {ids[:5]}")

# By rsID
ids, _ = esearch("rs80357906[rs]")
print(f"Variant IDs for rs80357906: {ids}")

# By condition name
ids, total = esearch("breast cancer[dis] AND pathogenic[clinsig]")
print(f"Pathogenic variants for breast cancer: {total}")

import requests, json

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

def esummary(ids):
    """Fetch ESummary records for a list of ClinVar variation IDs."""
    r = requests.post(f"{BASE}/esummary.fcgi",
                      data={"db": "clinvar", "id": ",".join(ids),
                            "retmode": "json", "email": EMAIL})
    r.raise_for_status()
    return r.json()["result"]

ids, _ = esearch_func = lambda q: requests.get(
    f"{BASE}/esearch.fcgi",
    params={"db": "clinvar", "term": q, "retmax": 5, "retmode": "json", "email": EMAIL}
).json()["esearchresult"]["idlist"]

# Manual example with known IDs
sample_ids = ["12375", "17684", "54270"]
result = esummary(sample_ids)

for vid in result.get("uids", []):
    rec = result[vid]
    # ClinVar 2024 schema: clinical_significance was replaced by germline_classification
    # (also: clinical_impact_classification, oncogenicity_classification — same shape, often empty)
    gc = rec.get("germline_classification", {})
    print(f"\nVariation {vid}: {rec.get('title')}")
    print(f"  ClinSig  : {gc.get('description')}")
    print(f"  Review   : {gc.get('review_status')}")
    print(f"  Gene     : {rec.get('genes', [{}])[0].get('symbol')}")

import requests
import xml.etree.ElementTree as ET

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

def efetch_xml(variation_ids):
    # ClinVar 2024 XML overhaul: "clinvarset" rettype returns an empty stub.
    # Use rettype="vcv" + is_variationid="true" to get the new <VariationArchive> records.
    r = requests.post(f"{BASE}/efetch.fcgi",
                      data={"db": "clinvar", "id": ",".join(variation_ids),
                            "rettype": "vcv", "is_variationid": "true",
                            "retmode": "xml", "email": EMAIL})
    r.raise_for_status()
    return ET.fromstring(r.text)

root = efetch_xml(["17677"])  # BRCA1 c.5266dupC (rs80357906)

# Aggregate (germline) classification — one per VariationArchive
for va in root.iter("VariationArchive"):
    name = va.get("VariationName")
    gc = va.find("./ClassifiedRecord/Classifications/GermlineClassification")
    desc = gc.find("Description") if gc is not None else None
    rstat = gc.find("ReviewStatus") if gc is not None else None
    print(f"{name}: {desc.text if desc is not None else 'n/a'} "
          f"({rstat.text if rstat is not None else 'n/a'})")

    # Per-submitter assertions
    for ca in va.iter("ClinicalAssertion"):
        acc = ca.find("ClinVarAccession")
        cls = ca.find("Classification/GermlineClassification")
        if acc is not None and cls is not None:
            print(f"  {acc.get('SubmitterName', '?')}: {cls.text}")

import urllib.request
import gzip, csv, io

# Full summary (tab-separated, ~300 MB compressed)
URL = "https://ftp.ncbi.nlm.nih.gov/pub/clinvar/tab_delimited/variant_summary.txt.gz"

# Stream and parse without full download
with urllib.request.urlopen(URL) as resp:
    with gzip.open(resp, "rt", encoding="utf-8") as f:
        reader = csv.DictReader(f, delimiter="\t")
        pathogenic_brca1 = []
        for row in reader:
            if row["GeneSymbol"] == "BRCA1" and "Pathogenic" in row["ClinicalSignificance"]:
                pathogenic_brca1.append({
                    "name": row["Name"],
                    "clinsig": row["ClinicalSignificance"],
                    "condition": row["PhenotypeList"],
                    "rsid": row["RS# (dbSNP)"],
                })
        print(f"Pathogenic BRCA1 variants: {len(pathogenic_brca1)}")
        for v in pathogenic_brca1[:3]:
            print(f"  {v['name']} | {v['clinsig']} | rs{v['rsid']}")

import requests

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

# Stars correspond to review levels:
# 0 = no assertion criteria, 1 = criteria provided (single),
# 2 = criteria provided (multiple), 3 = expert panel, 4 = practice guideline

def search_by_review_stars(gene, min_stars=2):
    """Search for variants with at least min_stars review status."""
    star_terms = {1: "criteria provided, single submitter",
                  2: "criteria provided, multiple submitters, no conflicts",
                  3: "reviewed by expert panel",
                  4: "practice guideline"}
    terms = [f'"{star_terms[s]}"[review status]' for s in range(min_stars, 5) if s in star_terms]
    query = f"{gene}[gene] AND (" + " OR ".join(terms) + ")"
    r = requests.get(f"{BASE}/esearch.fcgi",
                     params={"db": "clinvar", "term": query, "retmax": 100,
                             "retmode": "json", "email": EMAIL})
    return r.json()["esearchresult"]

result = search_by_review_stars("BRCA1", min_stars=3)
print(f"Expert-reviewed BRCA1 variants: {result['count']}")

import requests, json

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

def get_conditions(variation_ids):
    """Return condition data for a list of ClinVar variation IDs."""
    r = requests.post(f"{BASE}/esummary.fcgi",
                      data={"db": "clinvar", "id": ",".join(variation_ids),
                            "retmode": "json", "email": EMAIL})
    r.raise_for_status()
    result = r.json()["result"]
    conditions = {}
    for vid in result.get("uids", []):
        rec = result[vid]
        # trait_set moved under germline_classification in the 2024 ClinVar JSON
        trait_set = rec.get("germline_classification", {}).get("trait_set", [])
        conditions[vid] = [t.get("trait_name") for t in trait_set]
    return conditions

sample_ids = ["12375", "17684", "54270"]
cond_map = get_conditions(sample_ids)
for vid, conds in cond_map.items():
    print(f"Variation {vid}: {', '.join(conds)}")

import requests, json, time, pandas as pd

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

def search_gene_pathogenic(gene, clinsig="pathogenic"):
    query = f"{gene}[gene] AND {clinsig}[clinsig]"
    r = requests.get(f"{BASE}/esearch.fcgi",
                     params={"db": "clinvar", "term": query, "retmax": 500,
                             "retmode": "json", "email": EMAIL})
    return r.json()["esearchresult"]["idlist"]

def fetch_summaries(ids):
    records = []
    for i in range(0, len(ids), 100):
        batch = ids[i:i+100]
        r = requests.post(f"{BASE}/esummary.fcgi",
                          data={"db": "clinvar", "id": ",".join(batch),
                                "retmode": "json", "email": EMAIL})
        result = r.json()["result"]
        for vid in result.get("uids", []):
            rec = result[vid]
            # ClinVar 2024 schema: clinical_significance → germline_classification; trait_set nested inside it
            gc = rec.get("germline_classification", {})
            records.append({
                "variation_id": vid,
                "name": rec.get("title"),
                "clinsig": gc.get("description"),
                "review_status": gc.get("review_status"),
                "gene": ",".join(g.get("symbol", "") for g in rec.get("genes", [])),
                "conditions": "; ".join(t.get("trait_name", "") for t in gc.get("trait_set", [])),
            })
        time.sleep(0.15)
    return records

gene = "BRCA1"
ids = search_gene_pathogenic(gene)
print(f"Found {len(ids)} pathogenic variants in {gene}")

records = fetch_summaries(ids)
df = pd.DataFrame(records)
df.to_csv(f"{gene}_pathogenic_variants.csv", index=False)
print(f"Saved {len(df)} records → {gene}_pathogenic_variants.csv")
print(df[["name", "clinsig", "review_status"]].head())

import requests, time, pandas as pd

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

variants = ["rs80357906", "rs80357220", "rs28897672"]
results = []

for rsid in variants:
    r = requests.get(f"{BASE}/esearch.fcgi",
                     params={"db": "clinvar", "term": f"{rsid}[rs]",
                             "retmax": 5, "retmode": "json", "email": EMAIL})
    ids = r.json()["esearchresult"]["idlist"]
    if not ids:
        results.append({"rsid": rsid, "variation_id": None, "clinsig": "Not in ClinVar"})
        continue

    r2 = requests.post(f"{BASE}/esummary.fcgi",
                       data={"db": "clinvar", "id": ",".join(ids[:1]),
                             "retmode": "json", "email": EMAIL})
    rec = r2.json()["result"][ids[0]]
    gc = rec.get("germline_classification", {})  # 2024 ClinVar JSON
    results.append({
        "rsid": rsid,
        "variation_id": ids[0],
        "clinsig": gc.get("description", "Unknown"),
        "review_status": gc.get("review_status"),
    })
    time.sleep(0.15)

df = pd.DataFrame(results)
print(df.to_string(index=False))