Pubchem Compound Search

https://pubchem.ncbi.nlm.nih.gov/rest/pug/<input>/<operation>/<output>

pip install requests pandas

import requests

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

# name → CID
cid = requests.get(f"{BASE}/compound/name/aspirin/cids/JSON").json()["IdentifierList"]["CID"][0]

# CID → properties (single call, many fields)
r = requests.get(
    f"{BASE}/compound/cid/{cid}/property/"
    "MolecularWeight,XLogP,TPSA,HBondDonorCount,HBondAcceptorCount,SMILES,IUPACName/JSON")
p = r.json()["PropertyTable"]["Properties"][0]
print(f"CID {cid} — {p['IUPACName']}")
print(f"  MW={p['MolecularWeight']}  XLogP={p['XLogP']}  TPSA={p['TPSA']}")
print(f"  HBD={p['HBondDonorCount']}  HBA={p['HBondAcceptorCount']}")
print(f"  SMILES={p['SMILES']}")

import requests
from urllib.parse import quote

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

# By name (returns all matching CIDs as a list)
cids = requests.get(f"{BASE}/compound/name/caffeine/cids/JSON").json()["IdentifierList"]["CID"]
print(f"caffeine CIDs: {cids}")

# By canonical SMILES (URL-encode!)
smi = quote("CC(=O)OC1=CC=CC=C1C(=O)O", safe="")
cid = requests.get(f"{BASE}/compound/smiles/{smi}/cids/JSON").json()["IdentifierList"]["CID"][0]
print(f"aspirin SMILES → CID {cid}")

# By InChIKey (exact match, fastest if you already have one)
ikey = "BSYNRYMUTXBXSQ-UHFFFAOYSA-N"
cid = requests.get(f"{BASE}/compound/inchikey/{ikey}/cids/JSON").json()["IdentifierList"]["CID"][0]
print(f"InChIKey → CID {cid}")

import requests

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

# Full property set for a single compound (ibuprofen CID 3672)
url = (f"{BASE}/compound/cid/3672/property/"
       "MolecularWeight,XLogP,TPSA,HBondDonorCount,HBondAcceptorCount,"
       "RotatableBondCount,SMILES,InChIKey,IUPACName,MolecularFormula/JSON")
p = requests.get(url).json()["PropertyTable"]["Properties"][0]
print(f"{p['IUPACName']}  formula={p['MolecularFormula']}")
print(f"  MW={p['MolecularWeight']} XLogP={p['XLogP']} TPSA={p['TPSA']}")
print(f"  HBD={p['HBondDonorCount']} HBA={p['HBondAcceptorCount']} RotB={p['RotatableBondCount']}")

import requests, pandas as pd

# Batch: 4 CIDs, 3 properties — one request, one round trip
cids = "2244,3672,2157,2662"   # aspirin, ibuprofen, naproxen, celecoxib
r = requests.get(
    f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cids}/property/"
    "MolecularWeight,XLogP,TPSA/JSON")
df = pd.DataFrame(r.json()["PropertyTable"]["Properties"])
print(df.to_string(index=False))

import requests

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

# Full synonym list (aspirin has ~700)
info = requests.get(f"{BASE}/compound/cid/2244/synonyms/JSON").json()["InformationList"]["Information"][0]
print(f"aspirin synonyms: {len(info['Synonym'])}")
for s in info["Synonym"][:8]:
    print(f"  {s}")

import requests

# Curated descriptions (NCBI MeSH, CAMEO, etc.)
r = requests.get("https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/aspirin/description/JSON")
for item in r.json()["InformationList"]["Information"]:
    if "Description" in item:
        print(f"[{item.get('DescriptionSourceName','?')}]")
        print(f"  {item['Description'][:200]}…")
        print()

import requests, time
from urllib.parse import quote

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

def poll_listkey(listkey, max_polls=10, interval=2.0):
    """Block until PubChem finishes async search; return CID list."""
    for _ in range(max_polls):
        time.sleep(interval)
        j = requests.get(f"{BASE}/compound/listkey/{listkey}/cids/JSON", timeout=20).json()
        if "IdentifierList" in j:
            return j["IdentifierList"]["CID"]
    raise TimeoutError(f"ListKey {listkey} did not complete")

# Tanimoto similarity (90% threshold, max 20 hits) — starting from aspirin SMILES
smi = quote("CC(=O)OC1=CC=CC=C1C(=O)O", safe="")
init = requests.get(
    f"{BASE}/compound/similarity/smiles/{smi}/JSON?Threshold=90&MaxRecords=20").json()
cids = poll_listkey(init["Waiting"]["ListKey"]) if "Waiting" in init \
       else init["IdentifierList"]["CID"]
print(f"aspirin @90% similarity: {len(cids)} hits, sample={cids[:5]}")

import requests
from urllib.parse import quote

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

# Substructure search — all compounds containing a sulfonamide group
smi = quote("S(=O)(=O)N", safe="")
init = requests.get(
    f"{BASE}/compound/substructure/smiles/{smi}/JSON?MaxRecords=20").json()
cids = poll_listkey(init["Waiting"]["ListKey"]) if "Waiting" in init \
       else init["IdentifierList"]["CID"]
print(f"sulfonamide-containing CIDs: {len(cids)}, sample={cids[:5]}")

import requests, pandas as pd

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

r = requests.get(f"{BASE}/compound/cid/2244/assaysummary/JSON", timeout=30)
rows = r.json().get("Table", {}).get("Row", [])
cols = r.json().get("Table", {}).get("Columns", {}).get("Column", [])
print(f"aspirin appears in {len(rows)} bioassays")

# First few columns + rows as a DataFrame
df = pd.DataFrame([row["Cell"] for row in rows[:5]], columns=cols)
print(df.iloc[:, :6].to_string(index=False))

import requests

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"
cid = 2519   # caffeine

# 2D SDF for downstream RDKit / OpenBabel
sdf = requests.get(f"{BASE}/compound/cid/{cid}/SDF", timeout=15).text
with open("caffeine.sdf", "w") as f:
    f.write(sdf)
print(f"caffeine.sdf: {len(sdf)} chars, ends with M  END={'M  END' in sdf}")

# PNG structure image
png = requests.get(f"{BASE}/compound/cid/{cid}/PNG?image_size=large", timeout=15).content
with open("caffeine.png", "wb") as f:
    f.write(png)
print(f"caffeine.png: {len(png)} bytes")

import requests, pandas as pd, time
from urllib.parse import quote

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

drugs = ["aspirin", "ibuprofen", "naproxen", "celecoxib"]

# Resolve names → CIDs in a loop (rate-limited)
cids = []
for d in drugs:
    cid = requests.get(f"{BASE}/compound/name/{quote(d)}/cids/JSON",
                       timeout=15).json()["IdentifierList"]["CID"][0]
    cids.append(cid)
    time.sleep(0.25)

# Single batched property pull
cid_csv = ",".join(str(c) for c in cids)
r = requests.get(
    f"{BASE}/compound/cid/{cid_csv}/property/"
    "MolecularWeight,XLogP,TPSA,HBondDonorCount,HBondAcceptorCount/JSON")
df = pd.DataFrame(r.json()["PropertyTable"]["Properties"])
df["Name"] = drugs
df = df[["Name", "CID", "MolecularWeight", "XLogP", "TPSA",
         "HBondDonorCount", "HBondAcceptorCount"]]
print(df.to_string(index=False))

import requests, time
from urllib.parse import quote

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

def poll_listkey(listkey, max_polls=10, interval=2.0):
    for _ in range(max_polls):
        time.sleep(interval)
        j = requests.get(f"{BASE}/compound/listkey/{listkey}/cids/JSON",
                         timeout=20).json()
        if "IdentifierList" in j:
            return j["IdentifierList"]["CID"]
    raise TimeoutError("listkey timeout")

# 1. lead → CID → canonical SMILES
ref_cid = requests.get(
    f"{BASE}/compound/name/gefitinib/cids/JSON").json()["IdentifierList"]["CID"][0]
ref_smi = requests.get(
    f"{BASE}/compound/cid/{ref_cid}/property/SMILES/JSON"
    ).json()["PropertyTable"]["Properties"][0]["SMILES"]
print(f"gefitinib CID={ref_cid}  SMILES={ref_smi}")

# 2. similarity search
smi_q = quote(ref_smi, safe="")
init = requests.get(
    f"{BASE}/compound/similarity/smiles/{smi_q}/JSON?Threshold=85&MaxRecords=15"
    ).json()
sim_cids = poll_listkey(init["Waiting"]["ListKey"]) if "Waiting" in init \
           else init["IdentifierList"]["CID"]
print(f"  {len(sim_cids)} analogs @85% Tanimoto")

# 3. batch-pull properties for top 5 analogs
cid_csv = ",".join(str(c) for c in sim_cids[:5])
r = requests.get(
    f"{BASE}/compound/cid/{cid_csv}/property/"
    "MolecularWeight,XLogP,TPSA,RotatableBondCount/JSON")
for row in r.json()["PropertyTable"]["Properties"]:
    print(f"  CID {row['CID']}: MW={row['MolecularWeight']} XLogP={row['XLogP']}")

import requests, time
from urllib.parse import quote

BASE = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"

def poll_listkey(listkey, max_polls=10, interval=2.0):
    for _ in range(max_polls):
        time.sleep(interval)
        j = requests.get(f"{BASE}/compound/listkey/{listkey}/cids/JSON",
                         timeout=20).json()
        if "IdentifierList" in j:
            return j["IdentifierList"]["CID"]
    raise TimeoutError("listkey timeout")

smi = quote("S(=O)(=O)N", safe="")
init = requests.get(
    f"{BASE}/compound/substructure/smiles/{smi}/JSON?MaxRecords=10").json()
cids = poll_listkey(init["Waiting"]["ListKey"]) if "Waiting" in init \
       else init["IdentifierList"]["CID"]
print(f"sulfonamide CIDs: {cids}")

# Bioactivity row counts for the first few hits
for cid in cids[:3]:
    rows = requests.get(f"{BASE}/compound/cid/{cid}/assaysummary/JSON",
                        timeout=30).json().get("Table", {}).get("Row", [])
    print(f"  CID {cid}: {len(rows)} assay rows")
    time.sleep(0.3)