Ensembl Database

pip install requests

import requests

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

def ensembl_get(endpoint, params=None):
    r = requests.get(f"{BASE}{endpoint}", headers=HEADERS, params=params)
    r.raise_for_status()
    return r.json()

# Look up human BRCA1
gene = ensembl_get("/lookup/symbol/homo_sapiens/BRCA1", params={"expand": 1})
print(f"ID: {gene['id']}, Chr: {gene['seq_region_name']}:{gene['start']}-{gene['end']}")
print(f"Transcripts: {len(gene.get('Transcript', []))}")

import requests

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

# By gene symbol
r = requests.get(
    f"{BASE}/lookup/symbol/homo_sapiens/TP53",
    headers=HEADERS,
    params={"expand": 1}
)
gene = r.json()
print(f"Ensembl ID : {gene['id']}")
print(f"Location   : {gene['seq_region_name']}:{gene['start']}-{gene['end']} ({gene['strand']})")
print(f"Biotype    : {gene['biotype']}")
print(f"Transcripts: {len(gene.get('Transcript', []))}")

# By stable ID (works for genes, transcripts, proteins)
r = requests.get(
    f"{BASE}/lookup/id/ENSG00000141510",
    headers=HEADERS,
    params={"expand": 0}
)
obj = r.json()
print(f"Symbol: {obj.get('display_name')}, Species: {obj.get('species')}")

import requests, json

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

# Batch lookup by symbols
symbols = ["BRCA1", "BRCA2", "TP53", "EGFR", "MYC"]
r = requests.post(
    f"{BASE}/lookup/symbol/homo_sapiens",
    headers=HEADERS,
    data=json.dumps({"symbols": symbols})
)
results = r.json()
for sym, data in results.items():
    if data:
        print(f"{sym}: {data['id']} ({data['seq_region_name']}:{data['start']}-{data['end']})")

import requests

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "text/plain"}

# Protein sequence for canonical transcript
r = requests.get(
    f"{BASE}/sequence/id/ENST00000269305",
    headers=HEADERS,
    params={"type": "protein"}
)
seq = r.text
print(f"Protein sequence ({len(seq)} aa): {seq[:60]}...")

# Genomic region sequence
HEADERS_JSON = {"Content-Type": "application/json"}
r = requests.get(
    f"{BASE}/sequence/region/human/17:43044295..43125364",
    headers=HEADERS_JSON,
    params={"coord_system_version": "GRCh38"}
)
result = r.json()
print(f"Retrieved {len(result['seq'])} bp of genomic sequence")

import requests

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

# All xrefs for a gene
r = requests.get(
    f"{BASE}/xrefs/id/ENSG00000141510",
    headers=HEADERS
)
xrefs = r.json()

# Group by database
from collections import defaultdict
by_db = defaultdict(list)
for x in xrefs:
    by_db[x["dbname"]].append(x["primary_id"])

for db in ["HGNC", "RefSeq_gene_name", "Uniprot_gn", "MIM_gene"]:
    if db in by_db:
        print(f"{db}: {by_db[db]}")

import requests, json

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

# Annotate a list of hgvs notations
variants = ["17:g.43094692C>T", "13:g.32929387C>T"]
r = requests.post(
    f"{BASE}/vep/human/hgvs",
    headers=HEADERS,
    data=json.dumps({"hgvs_notations": variants})
)
for v in r.json():
    print(f"\nVariant: {v.get('input')}")
    for tc in v.get("transcript_consequences", [])[:2]:
        print(f"  Gene: {tc.get('gene_symbol')}, Impact: {tc.get('impact')}, Consequence: {tc.get('consequence_terms')}")

# Annotate by rsID
r = requests.get(
    f"{BASE}/vep/human/id/rs699",
    headers=HEADERS
)
v = r.json()[0]
print(f"rsID rs699 in gene: {v['transcript_consequences'][0]['gene_symbol']}")
print(f"Consequence: {v['transcript_consequences'][0]['consequence_terms']}")

import requests

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

# Regulatory features in BRCA1 region
r = requests.get(
    f"{BASE}/overlap/region/human/17:43044000-43126000",
    headers=HEADERS,
    params={"feature": "regulatory"}
)
features = r.json()
print(f"Found {len(features)} regulatory features")
for f in features[:5]:
    print(f"  {f.get('feature_type')}: {f.get('start')}-{f.get('end')} ({f.get('description', 'n/a')})")

import requests

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

# Get mouse ortholog for human TP53
r = requests.get(
    f"{BASE}/homology/symbol/human/TP53",
    headers=HEADERS,
    params={"target_species": "mus_musculus", "type": "orthologues"}
)
data = r.json()
for homo in data["data"][0]["homologies"][:3]:
    tgt = homo["target"]
    print(f"Mouse ortholog: {tgt['id']} ({tgt.get('perc_id', 'n/a')}% identity)")

import requests, json, time

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

def batch_lookup(symbols, species="homo_sapiens"):
    r = requests.post(
        f"{BASE}/lookup/symbol/{species}",
        headers=HEADERS,
        data=json.dumps({"symbols": symbols, "expand": 1})
    )
    return r.json()

def canonical_transcript(gene_data):
    """Return the ID of the canonical (longest CDS) transcript."""
    transcripts = gene_data.get("Transcript", [])
    coding = [t for t in transcripts if t.get("biotype") == "protein_coding"]
    if not coding:
        return None
    return max(coding, key=lambda t: t.get("Translation", {}).get("length", 0))

genes = ["BRCA1", "BRCA2", "TP53"]
lookup = batch_lookup(genes)

for sym in genes:
    g = lookup.get(sym)
    if not g:
        print(f"{sym}: not found")
        continue
    canon = canonical_transcript(g)
    print(f"\n{sym} ({g['id']})")
    print(f"  Location: {g['seq_region_name']}:{g['start']}-{g['end']}")
    if canon:
        prot_len = canon.get("Translation", {}).get("length", "n/a")
        print(f"  Canonical transcript: {canon['id']} ({prot_len} aa)")
    time.sleep(0.1)  # be polite

import requests, json, pandas as pd

BASE = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json"}

# Input: list of hgvs notations
hgvs_list = [
    "17:g.43094692C>T",
    "17:g.43063873A>G",
    "13:g.32929387C>T",
]

# Annotate in batches of 200
def vep_batch(hgvs_batch):
    r = requests.post(
        f"{BASE}/vep/human/hgvs",
        headers=HEADERS,
        data=json.dumps({"hgvs_notations": hgvs_batch})
    )
    r.raise_for_status()
    return r.json()

records = []
for ann in vep_batch(hgvs_list):
    for tc in ann.get("transcript_consequences", []):
        if tc.get("canonical") == 1:
            records.append({
                "variant": ann["input"],
                "gene": tc.get("gene_symbol"),
                "consequence": ",".join(tc.get("consequence_terms", [])),
                "impact": tc.get("impact"),
                "biotype": tc.get("biotype"),
            })

df = pd.DataFrame(records)
print(df.to_string(index=False))
df.to_csv("vep_results.csv", index=False)
print(f"\nSaved {len(df)} variant annotations → vep_results.csv")