Gene Database

pip install requests pandas

import requests

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

def gene_search(query, retmax=5):
    r = requests.get(f"{BASE}/esearch.fcgi",
                     params={"db": "gene", "term": query,
                             "retmax": retmax, "retmode": "json", "email": EMAIL})
    r.raise_for_status()
    return r.json()["esearchresult"]["idlist"]

# Find human BRCA1 gene ID
ids = gene_search("BRCA1[sym] AND Homo sapiens[orgn]")
print(f"Gene IDs for BRCA1: {ids}")  # → ['672']

import requests

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

# Exact symbol match for human gene
r = requests.get(f"{BASE}/esearch.fcgi",
                 params={"db": "gene", "email": EMAIL, "retmode": "json",
                         "term": "TP53[sym] AND Homo sapiens[orgn] AND alive[prop]"})
ids = r.json()["esearchresult"]["idlist"]
print(f"TP53 Gene ID: {ids}")  # → ['7157']

# Search by function keyword
r = requests.get(f"{BASE}/esearch.fcgi",
                 params={"db": "gene", "email": EMAIL, "retmode": "json",
                         "term": "CRISPR[title] AND Homo sapiens[orgn]", "retmax": 5})
ids = r.json()["esearchresult"]["idlist"]
print(f"CRISPR-related gene IDs: {ids}")

import requests

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

def esummary_gene(gene_ids):
    r = requests.post(f"{BASE}/esummary.fcgi",
                      data={"db": "gene", "id": ",".join(gene_ids),
                            "retmode": "json", "email": EMAIL})
    r.raise_for_status()
    return r.json()["result"]

result = esummary_gene(["672", "675", "7157"])  # BRCA1, BRCA2, TP53

for uid in result.get("uids", []):
    g = result[uid]
    print(f"\n{g.get('name')} (ID {uid})")
    print(f"  Official symbol : {g.get('nomenclaturesymbol', g.get('name'))}")
    print(f"  Chr location    : {g.get('maplocation')}")
    print(f"  Summary (first 100): {g.get('summary', '')[:100]}...")
    print(f"  Aliases: {g.get('otheraliases', 'none')}")

import requests
import xml.etree.ElementTree as ET

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

def efetch_gene_xml(gene_id):
    r = requests.get(f"{BASE}/efetch.fcgi",
                     params={"db": "gene", "id": gene_id,
                             "rettype": "gene_table", "retmode": "text", "email": EMAIL})
    r.raise_for_status()
    return r.text

# Get gene table (tab-delimited overview)
table = efetch_gene_xml("672")
print(table[:500])

# XML for RefSeq accession extraction
r = requests.get(f"{BASE}/efetch.fcgi",
                 params={"db": "gene", "id": "672",
                         "rettype": "xml", "retmode": "xml", "email": EMAIL})
root = ET.fromstring(r.text)

# Extract RefSeq mRNA accessions
for ref in root.iter("Gene-commentary"):
    acc = ref.find("Gene-commentary_accession")
    ver = ref.find("Gene-commentary_version")
    typ = ref.find("Gene-commentary_type")
    if acc is not None and acc.text and acc.text.startswith("NM_"):
        print(f"RefSeq mRNA: {acc.text}.{ver.text if ver is not None else ''}")

import requests, time

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

def symbols_to_ids(symbols, organism="Homo sapiens"):
    """Map gene symbols to NCBI Gene IDs. Returns dict {symbol: gene_id}."""
    mapping = {}
    for sym in symbols:
        r = requests.get(f"{BASE}/esearch.fcgi",
                         params={"db": "gene", "email": EMAIL, "retmode": "json",
                                 "term": f"{sym}[sym] AND {organism}[orgn] AND alive[prop]"})
        ids = r.json()["esearchresult"]["idlist"]
        mapping[sym] = ids[0] if ids else None
        time.sleep(0.1)
    return mapping

genes = ["EGFR", "KRAS", "BRAF", "PIK3CA", "PTEN"]
id_map = symbols_to_ids(genes)
for sym, gid in id_map.items():
    print(f"{sym:10s} → Gene ID {gid}")

import requests
import xml.etree.ElementTree as ET

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

r = requests.get(f"{BASE}/efetch.fcgi",
                 params={"db": "gene", "id": "7157",
                         "rettype": "xml", "retmode": "xml", "email": EMAIL})
root = ET.fromstring(r.text)

# Extract GO annotations
go_terms = []
for ref in root.iter("Gene-commentary"):
    heading = ref.find("Gene-commentary_heading")
    label = ref.find("Gene-commentary_label")
    if heading is not None and "Gene Ontology" in heading.text:
        if label is not None:
            go_terms.append(label.text)

print(f"TP53 GO terms ({len(go_terms)} found):")
for term in go_terms[:10]:
    print(f"  {term}")

import requests, time

DATASETS_BASE = "https://api.ncbi.nlm.nih.gov/datasets/v2"

def get_orthologs(gene_id, taxon_filter=None):
    """Return ortholog Gene reports for a given NCBI Gene ID.
    taxon_filter: optional tax_id (int) or list of tax_ids to narrow species."""
    params = {}
    if taxon_filter is not None:
        # tax_ids: human=9606, mouse=10090, rat=10116, zebrafish=7955, fly=7227
        ids = taxon_filter if isinstance(taxon_filter, (list, tuple)) else [taxon_filter]
        params["taxon_filter"] = [str(t) for t in ids]
    r = requests.get(f"{DATASETS_BASE}/gene/id/{gene_id}/orthologs",
                     params=params, timeout=30)
    r.raise_for_status()
    return r.json().get("reports", [])

# Mouse ortholog of human TP53 (Gene ID 7157)
reports = get_orthologs("7157", taxon_filter=10090)
for rep in reports[:5]:
    g = rep.get("gene", {})
    print(f"  {g.get('symbol'):8s} (tax {g.get('tax_id')}, gene_id {g.get('gene_id')}): "
          f"{g.get('description', '')[:60]}")
# Expect:  Trp53    (tax 10090, gene_id 22059): transformation related protein 53

time.sleep(0.34)
# All orthologs (every species in the orthology group)
all_orthologs = get_orthologs("7157")
print(f"\nTotal TP53 orthologs across species: {len(all_orthologs)}")

import requests, time, pandas as pd

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

def search_gene(sym, organism="Homo sapiens"):
    r = requests.get(f"{BASE}/esearch.fcgi",
                     params={"db": "gene", "email": EMAIL, "retmode": "json",
                             "term": f"{sym}[sym] AND {organism}[orgn] AND alive[prop]"})
    ids = r.json()["esearchresult"]["idlist"]
    return ids[0] if ids else None

def batch_summary(gene_ids):
    r = requests.post(f"{BASE}/esummary.fcgi",
                      data={"db": "gene", "id": ",".join(gene_ids),
                            "retmode": "json", "email": EMAIL})
    return r.json()["result"]

symbols = ["BRCA1", "BRCA2", "TP53", "EGFR", "MYC", "KRAS", "PTEN"]

# Step 1: Symbol → Gene ID
id_map = {}
for sym in symbols:
    gid = search_gene(sym)
    id_map[sym] = gid
    time.sleep(0.12)

# Step 2: Batch summary
valid_ids = [v for v in id_map.values() if v]
result = batch_summary(valid_ids)

rows = []
sym_to_id = {v: k for k, v in id_map.items() if v}
for uid in result.get("uids", []):
    g = result[uid]
    rows.append({
        "symbol": sym_to_id.get(uid, g.get("name")),
        "gene_id": uid,
        "full_name": g.get("description"),
        "chr_location": g.get("maplocation"),
        "summary": g.get("summary", "")[:200],
    })

df = pd.DataFrame(rows)
df.to_csv("gene_annotations.csv", index=False)
print(df[["symbol", "gene_id", "full_name", "chr_location"]].to_string(index=False))

import requests, time, pandas as pd

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

keyword = "DNA mismatch repair"
r = requests.get(f"{BASE}/esearch.fcgi",
                 params={"db": "gene", "email": EMAIL, "retmode": "json",
                         "retmax": 50,
                         "term": f"{keyword}[title/abstract] AND Homo sapiens[orgn] AND alive[prop]"})
ids = r.json()["esearchresult"]["idlist"]
print(f"Found {len(ids)} genes related to '{keyword}'")

# Fetch summaries
r2 = requests.post(f"{BASE}/esummary.fcgi",
                   data={"db": "gene", "id": ",".join(ids), "retmode": "json", "email": EMAIL})
result = r2.json()["result"]

rows = []
for uid in result.get("uids", []):
    g = result[uid]
    rows.append({"gene_id": uid, "symbol": g.get("name"),
                 "description": g.get("description"),
                 "location": g.get("maplocation")})

df = pd.DataFrame(rows)
print(df.to_string(index=False))
df.to_csv(f"{keyword.replace(' ', '_')}_genes.csv", index=False)