runchuan-bu/bioclaw/query-geo

from Bio import Entrez
import json
Entrez.email = "bioclaw@example.com"
# 1. Search GEO datasets
def search_geo(query, max_results=10, db="gds"):
    handle = Entrez.esearch(db=db, term=query, retmax=max_results, sort="relevance")
    record = Entrez.read(handle)
    handle.close()
    return record
# 2. Get dataset summaries
def geo_summary(id_list, db="gds"):
    ids = ",".join(str(i) for i in id_list)
    handle = Entrez.esummary(db=db, id=ids, retmode="json")
    result = json.loads(handle.read())
    handle.close()
    return result
# 3. Search for Series (GSE)
def search_gse(keyword, organism="Homo sapiens", max_results=10):
    query = f'"{keyword}" AND "{organism}"[Organism] AND gse[ETYP]'
    return search_geo(query, max_results)
# Example: Find breast cancer RNA-seq datasets
search = search_gse("breast cancer RNA-seq", max_results=5)
print(f"Found {search['Count']} datasets")
if search['IdList']:
    summaries = geo_summary(search['IdList'])
    for uid in search['IdList']:
        info = summaries['result'].get(str(uid), {})
        title = info.get('title', 'N/A')
        gse = info.get('accession', 'N/A')
        gpl = info.get('gpl', 'N/A')
        n_samples = info.get('n_samples', 'N/A')
        summary = info.get('summary', 'N/A')[:200]
        print(f"\n{gse}: {title}")
        print(f"  Platform: {gpl}, Samples: {n_samples}")
        print(f"  Summary: {summary}...")
        print(f"  URL: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc={gse}")