NCBI Gene Database

Overview

NCBI Gene is the authoritative curated database for gene-centric information, covering 1M+ genes across hundreds of thousands of taxa. Each gene record includes the official symbol, aliases, full name, functional summary, genomic coordinates (GRCh38/GRCh37), RefSeq accessions, GO annotations, interaction partners, and links to related databases. Access is free via E-utilities REST API (no API key required, though recommended).

When to Use

• Resolving gene aliases and synonyms to the current official HGNC/NCBI symbol
• Fetching the NCBI Gene ID (integer) for a gene symbol for downstream API calls (e.g., dbSNP, ClinVar, GEO)
• Retrieving curated gene summaries and function descriptions programmatically
• Pulling RefSeq mRNA (NM_) and protein (NP_) accessions associated with a gene
• Querying GO functional annotations (Biological Process, Molecular Function, Cellular Component)
• Finding orthologs across species via the NCBI Datasets v2 orthologs endpoint (legacy E-utilities gene_gene_homolog retired with HomoloGene in 2019)
• For expression profiles across conditions use geo-database; for variant annotations use clinvar-database or ensembl-database

Prerequisites

• Python packages: requests, xml.etree.ElementTree (stdlib), pandas (optional)
• Data requirements: gene symbols, NCBI Gene IDs, or tax IDs
• Environment: internet connection; NCBI email required (set email parameter)
• Rate limits: 3 req/s unauthenticated; 10 req/s with free NCBI API key

pip install requests pandas

Quick Start

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']

Core API

Query 1: Search by Symbol, Name, or Function

Use ESearch with field tags for precise queries.

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}")

Query 2: Fetch Gene Summary (JSON/ESummary)

Retrieve key metadata fields for a list of Gene 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')}")

Query 3: Fetch Full Gene Record (XML)

Retrieve the complete gene record in XML for RefSeq accessions, GO terms, and interaction data.

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 ''}")

Query 4: Batch Symbol-to-ID Mapping

Map a list of gene symbols to NCBI Gene IDs efficiently.

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}")

Query 5: GO Annotation Retrieval

Parse GO terms from the gene XML record.

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}")

Query 6: Cross-Species Orthologs (NCBI Datasets v2)

Find orthologs across species. Note: the legacy E-utilities link gene_gene_homolog was retired with HomoloGene in 2019 — the modern path is the NCBI Datasets v2 REST API, which exposes a dedicated orthologs endpoint.

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