Chembl Database Bioactivity

pip install requests
# Optional, for DataFrame work:
pip install pandas

import requests

BASE = "https://www.ebi.ac.uk/chembl/api/data"

# Retrieve a molecule by ChEMBL ID
r = requests.get(f"{BASE}/molecule/CHEMBL25.json", timeout=15)
r.raise_for_status()
aspirin = r.json()
print(f"{aspirin['pref_name']}: MW={aspirin['molecule_properties']['mw_freebase']}")
# ASPIRIN: MW=180.16

# Search targets by full name (acronyms like 'EGFR' don't match pref_name — use full term)
r = requests.get(
    f"{BASE}/target.json",
    params={"pref_name__icontains": "epidermal growth factor receptor",
            "target_type": "SINGLE PROTEIN", "limit": 5},
    timeout=15,
)
targets = r.json()["targets"]
print(f"EGFR-like targets: {len(targets)}, first={targets[0]['target_chembl_id']}")

# Potent bioactivities: EGFR (CHEMBL203) IC50 <= 100 nM
r = requests.get(
    f"{BASE}/activity.json",
    params={"target_chembl_id": "CHEMBL203",
            "standard_type": "IC50",
            "standard_value__lte": 100,
            "standard_units": "nM",
            "limit": 5},
    timeout=30,
)
data = r.json()
print(f"EGFR IC50 ≤ 100 nM records: {data['page_meta']['total_count']}")

{
  "page_meta": {
    "limit": 20,
    "offset": 0,
    "total_count": 12145,
    "next": "/chembl/api/data/activity.json?...&offset=20",
    "previous": null
  },
  "activities": [ /* or molecules[], targets[], etc. */ ]
}

import requests
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# By ChEMBL ID
r = requests.get(f"{BASE}/molecule/CHEMBL25.json", timeout=15)
aspirin = r.json()
print(f"{aspirin['pref_name']}: MW={aspirin['molecule_properties']['mw_freebase']}")

# By name (case-insensitive substring)
r = requests.get(f"{BASE}/molecule.json",
                 params={"pref_name__icontains": "imatinib", "limit": 5},
                 timeout=15)
for mol in r.json()["molecules"]:
    print(f"  {mol['molecule_chembl_id']}  {mol.get('pref_name')!r}")

# By Lipinski-compliant property ranges
r = requests.get(f"{BASE}/molecule.json",
                 params={"molecule_properties__mw_freebase__range": "300,500",
                         "molecule_properties__alogp__lte": 5,
                         "molecule_properties__hba__lte": 10,
                         "molecule_properties__hbd__lte": 5,
                         "limit": 3},
                 timeout=15)
print(f"Lipinski-compliant total: {r.json()['page_meta']['total_count']}")

import requests
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# By ChEMBL ID
r = requests.get(f"{BASE}/target/CHEMBL203.json", timeout=15)
egfr = r.json()
print(f"{egfr['pref_name']} ({egfr['organism']}) — type={egfr['target_type']}")

# Search by full name (NOT acronym) + type
r = requests.get(f"{BASE}/target.json",
                 params={"pref_name__icontains": "kinase",
                         "target_type": "SINGLE PROTEIN", "limit": 5},
                 timeout=15)
d = r.json()
print(f"Kinase SINGLE_PROTEIN targets: total={d['page_meta']['total_count']}")
for t in d["targets"][:5]:
    print(f"  {t['target_chembl_id']:12s} {t.get('pref_name')!r}  ({t['organism']})")

# By organism
r = requests.get(f"{BASE}/target.json",
                 params={"organism": "Homo sapiens", "limit": 3},
                 timeout=15)
print(f"Human targets: total={r.json()['page_meta']['total_count']}")

import requests
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# Potent inhibitors for a target (EGFR = CHEMBL203)
r = requests.get(f"{BASE}/activity.json",
                 params={"target_chembl_id": "CHEMBL203",
                         "standard_type": "IC50",
                         "standard_value__lte": 100,
                         "standard_units": "nM",
                         "limit": 5},
                 timeout=30)
data = r.json()
print(f"EGFR IC50≤100nM: total={data['page_meta']['total_count']}")
for act in data["activities"][:5]:
    print(f"  {act['molecule_chembl_id']:14s} IC50={act['standard_value']} nM "
          f"pChEMBL={act.get('pchembl_value')}")

# All pChEMBL-tagged activities for a compound
r = requests.get(f"{BASE}/activity.json",
                 params={"molecule_chembl_id": "CHEMBL25",
                         "pchembl_value__isnull": "False",
                         "limit": 5},
                 timeout=30)
print(f"Aspirin pChEMBL activities: total={r.json()['page_meta']['total_count']}")

# Multiple activity types (CHEMBL240 = D2 dopamine receptor)
r = requests.get(f"{BASE}/activity.json",
                 params={"target_chembl_id": "CHEMBL240",
                         "standard_type__in": "IC50,Ki,Kd",
                         "limit": 5},
                 timeout=30)
print(f"D2 receptor IC50/Ki/Kd: total={r.json()['page_meta']['total_count']}")

import requests
from urllib.parse import quote
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# Similarity search (Tanimoto ≥ 85%)
# Path-style endpoint: /similarity/{smiles}/{threshold}
# The SMILES MUST be URL-encoded (it contains '/', '(', ')' etc.)
aspirin_smiles = quote("CC(=O)Oc1ccccc1C(=O)O", safe="")
r = requests.get(f"{BASE}/similarity/{aspirin_smiles}/85.json",
                 params={"limit": 5}, timeout=30)
data = r.json()
print(f"Similar to aspirin (≥85% Tanimoto): total={data['page_meta']['total_count']}")
for m in data["molecules"][:5]:
    print(f"  {m['molecule_chembl_id']}  similarity={m.get('similarity')}")

# Substructure search
benzimidazole = quote("c1ccc2[nH]cnc2c1", safe="")
r = requests.get(f"{BASE}/substructure/{benzimidazole}.json",
                 params={"limit": 3}, timeout=30)
print(f"Benzimidazole substructure total: {r.json()['page_meta']['total_count']}")

import requests
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# Drug record (max clinical phase, ATC class, etc.)
r = requests.get(f"{BASE}/drug/CHEMBL941.json", timeout=15)   # imatinib
drug = r.json()
print(f"Imatinib max_phase={drug.get('max_phase')}")

# Mechanisms of action — note: not every drug has mechanism records.
# Imatinib (CHEMBL941) returns 0 mechanism rows; sunitinib (CHEMBL535) has many.
r = requests.get(f"{BASE}/mechanism.json",
                 params={"molecule_chembl_id": "CHEMBL535"}, timeout=15)
for m in r.json()["mechanisms"]:
    print(f"  {m['mechanism_of_action']} → target {m.get('target_chembl_id')}")

# Therapeutic indications
r = requests.get(f"{BASE}/drug_indication.json",
                 params={"molecule_chembl_id": "CHEMBL941", "limit": 5},
                 timeout=15)
for ind in r.json()["drug_indications"]:
    print(f"  {ind.get('mesh_heading')!r}  max_phase_for_ind={ind.get('max_phase_for_ind')}")

# SVG molecular structure image — direct binary response, NOT JSON
# Do NOT call /image/{cid}.json — that endpoint raises JSONDecodeError.
r = requests.get(f"{BASE}/image/CHEMBL25.svg", timeout=15)
r.raise_for_status()
with open("aspirin.svg", "w") as f:
    f.write(r.text)
print(f"Saved aspirin.svg ({len(r.text)} bytes, looks_svg={'<svg' in r.text})")

import requests, pandas as pd, time
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# Step 1: Resolve the target by full name
r = requests.get(f"{BASE}/target.json",
                 params={"pref_name__icontains": "B-raf",
                         "target_type": "SINGLE PROTEIN", "limit": 5},
                 timeout=15)
targets = r.json()["targets"]
human_braf = next(t for t in targets if t["organism"] == "Homo sapiens")
target_id = human_braf["target_chembl_id"]
print(f"Using {target_id} — {human_braf['pref_name']}")

# Step 2: Paginate all potent IC50 activities (cap at 500 for demo)
url = (f"{BASE}/activity.json"
       f"?target_chembl_id={target_id}"
       f"&standard_type=IC50"
       f"&standard_value__lte=100"
       f"&standard_units=nM"
       f"&pchembl_value__isnull=False"
       f"&limit=200")
records = []
while url and len(records) < 500:
    r = requests.get(url, timeout=30)
    r.raise_for_status()
    data = r.json()
    records.extend(data["activities"])
    nxt = data["page_meta"].get("next")
    url = f"https://www.ebi.ac.uk{nxt}" if nxt else None
    time.sleep(0.2)

df = pd.DataFrame(records)
df["standard_value"] = pd.to_numeric(df["standard_value"])
print(f"Retrieved {len(df)} potent {target_id} compounds")
print(df[["molecule_chembl_id", "standard_value", "pchembl_value"]].head(10))

import requests
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# Sunitinib (CHEMBL535) — has documented mechanisms + indications.
# Imatinib (CHEMBL941) sometimes returns 0 mechanism rows depending on ChEMBL release.
chembl_id = "CHEMBL535"

# Molecule record
m = requests.get(f"{BASE}/molecule/{chembl_id}.json", timeout=15).json()
print(f"Name: {m['pref_name']}")
print(f"MW  : {m['molecule_properties']['mw_freebase']}")

# Mechanisms
mechs = requests.get(f"{BASE}/mechanism.json",
                     params={"molecule_chembl_id": chembl_id},
                     timeout=15).json()["mechanisms"]
for mc in mechs:
    print(f"  Mechanism: {mc['mechanism_of_action']}")

# Indications
inds = requests.get(f"{BASE}/drug_indication.json",
                    params={"molecule_chembl_id": chembl_id, "limit": 5},
                    timeout=15).json()["drug_indications"]
for ind in inds:
    print(f"  Indication: {ind.get('mesh_heading')}  "
          f"(Phase {ind.get('max_phase_for_ind')})")

# Bioactivity record count
total = requests.get(f"{BASE}/activity.json",
                     params={"molecule_chembl_id": chembl_id,
                             "pchembl_value__isnull": "False",
                             "limit": 1},
                     timeout=30).json()["page_meta"]["total_count"]
print(f"Total bioactivity records (pChEMBL-tagged): {total}")

import requests, pandas as pd, time
from urllib.parse import quote
BASE = "https://www.ebi.ac.uk/chembl/api/data"

# Step 1: Similar compounds to a lead (e.g., quinoline scaffold)
lead_smiles = "c1ccc2c(c1)cc(nc2N)c3ccc(cc3)NC(=O)c4ccccc4"
r = requests.get(f"{BASE}/similarity/{quote(lead_smiles, safe='')}/80.json",
                 params={"limit": 20}, timeout=30)
analogs = r.json()["molecules"]
print(f"Analogs found: {len(analogs)}")

# Step 2: Collect bioactivities for each analog
records = []
for compound in analogs[:20]:
    cid = compound["molecule_chembl_id"]
    acts = requests.get(f"{BASE}/activity.json",
                        params={"molecule_chembl_id": cid,
                                "standard_type": "IC50",
                                "pchembl_value__isnull": "False",
                                "limit": 20},
                        timeout=30).json()["activities"]
    for act in acts:
        records.append({
            "chembl_id": cid,
            "target": act.get("target_pref_name"),
            "IC50_nM": act.get("standard_value"),
            "pchembl": act.get("pchembl_value"),
            "mw":    (compound.get("molecule_properties") or {}).get("mw_freebase"),
            "alogp": (compound.get("molecule_properties") or {}).get("alogp"),
        })
    time.sleep(0.2)

df = pd.DataFrame(records)
if not df.empty:
    df["IC50_nM"] = pd.to_numeric(df["IC50_nM"])
    print(df.groupby("target")["IC50_nM"].describe())

import requests
BASE = "https://www.ebi.ac.uk/chembl/api/data"
r = requests.get(f"{BASE}/molecule.json",
                 params={"molecule_properties__mw_freebase__range": "300,500",
                         "molecule_properties__alogp__lte": 5,
                         "molecule_properties__hba__lte": 10,
                         "molecule_properties__hbd__lte": 5,
                         "molecule_properties__num_ro5_violations": 0,
                         "limit": 1},
                 timeout=15)
print(f"Drug-like candidates: {r.json()['page_meta']['total_count']}")

import requests, pandas as pd, time
BASE = "https://www.ebi.ac.uk/chembl/api/data"

url = (f"{BASE}/activity.json"
       f"?target_chembl_id=CHEMBL203"
       f"&standard_type=IC50"
       f"&pchembl_value__isnull=False"
       f"&limit=500")
all_acts = []
while url:
    r = requests.get(url, timeout=60)
    r.raise_for_status()
    data = r.json()
    all_acts.extend(data["activities"])
    nxt = data["page_meta"].get("next")
    url = f"https://www.ebi.ac.uk{nxt}" if nxt else None
    time.sleep(0.3)

df = pd.DataFrame(all_acts)
df.to_csv("egfr_activities.csv", index=False)
print(f"Exported {len(df)} records → egfr_activities.csv")

import requests
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry

def chembl_session(retries=3, backoff=1.0):
    s = requests.Session()
    s.headers.update({"Accept": "application/json"})
    s.mount("https://", HTTPAdapter(max_retries=Retry(
        total=retries, backoff_factor=backoff,
        status_forcelist=[429, 500, 502, 503, 504],
        allowed_methods=["GET"])))
    return s

session = chembl_session()
r = session.get("https://www.ebi.ac.uk/chembl/api/data/molecule/CHEMBL25.json", timeout=15)
print(r.json()["pref_name"])

import requests
r = requests.get("https://www.ebi.ac.uk/chembl/api/data/image/CHEMBL25.svg", timeout=15)
r.raise_for_status()
with open("aspirin.svg", "w") as f:
    f.write(r.text)