ovachiever/droid-tings/pubchem-database

import pubchempy as pcp
compounds = pcp.get_compounds('aspirin', 'name')
compound = compounds[0]

compound = pcp.Compound.from_cid(2244)  # Aspirin

compound = pcp.get_compounds('CC(=O)OC1=CC=CC=C1C(=O)O', 'smiles')[0]

compound = pcp.get_compounds('InChI=1S/C9H8O4/...', 'inchi')[0]

compounds = pcp.get_compounds('C9H8O4', 'formula')
# Returns all compounds matching this formula

import pubchempy as pcp
# Get compound object with all properties
compound = pcp.get_compounds('caffeine', 'name')[0]
# Access individual properties
molecular_formula = compound.molecular_formula
molecular_weight = compound.molecular_weight
iupac_name = compound.iupac_name
smiles = compound.canonical_smiles
inchi = compound.inchi
xlogp = compound.xlogp  # Partition coefficient
tpsa = compound.tpsa    # Topological polar surface area

# Request only specific properties
properties = pcp.get_properties(
    ['MolecularFormula', 'MolecularWeight', 'CanonicalSMILES', 'XLogP'],
    'aspirin',
    'name'
)
# Returns list of dictionaries

import pandas as pd
compound_names = ['aspirin', 'ibuprofen', 'paracetamol']
all_properties = []
for name in compound_names:
    props = pcp.get_properties(
        ['MolecularFormula', 'MolecularWeight', 'XLogP'],
        name,
        'name'
    )
    all_properties.extend(props)
df = pd.DataFrame(all_properties)

import pubchempy as pcp
# Start with a query compound
query_compound = pcp.get_compounds('gefitinib', 'name')[0]
query_smiles = query_compound.canonical_smiles
# Perform similarity search
similar_compounds = pcp.get_compounds(
    query_smiles,
    'smiles',
    searchtype='similarity',
    Threshold=85,  # Similarity threshold (0-100)
    MaxRecords=50
)
# Process results
for compound in similar_compounds[:10]:
    print(f"CID {compound.cid}: {compound.iupac_name}")
    print(f"  MW: {compound.molecular_weight}")

import pubchempy as pcp
# Search for compounds containing pyridine ring
pyridine_smiles = 'c1ccncc1'
matches = pcp.get_compounds(
    pyridine_smiles,
    'smiles',
    searchtype='substructure',
    MaxRecords=100
)
print(f"Found {len(matches)} compounds containing pyridine")

import pubchempy as pcp
compound = pcp.get_compounds('aspirin', 'name')[0]
# Convert to different formats
smiles = compound.canonical_smiles
inchi = compound.inchi
inchikey = compound.inchikey
cid = compound.cid
# Download structure files
pcp.download('SDF', 'aspirin', 'name', 'aspirin.sdf', overwrite=True)
pcp.download('JSON', '2244', 'cid', 'aspirin.json', overwrite=True)

import pubchempy as pcp
# Download compound structure as PNG
pcp.download('PNG', 'caffeine', 'name', 'caffeine.png', overwrite=True)
# Using direct URL (via requests)
import requests
cid = 2244  # Aspirin
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/PNG?image_size=large"
response = requests.get(url)
with open('structure.png', 'wb') as f:
    f.write(response.content)

import pubchempy as pcp
synonyms_data = pcp.get_synonyms('aspirin', 'name')
if synonyms_data:
    cid = synonyms_data[0]['CID']
    synonyms = synonyms_data[0]['Synonym']
    print(f"CID {cid} has {len(synonyms)} synonyms:")
    for syn in synonyms[:10]:  # First 10
        print(f"  - {syn}")

import requests
import json
# Get bioassay summary for a compound
cid = 2244  # Aspirin
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/assaysummary/JSON"
response = requests.get(url)
if response.status_code == 200:
    data = response.json()
    # Process bioassay information
    table = data.get('Table', {})
    rows = table.get('Row', [])
    print(f"Found {len(rows)} bioassay records")

import requests
cid = 2244
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON"
response = requests.get(url)
if response.status_code == 200:
    annotations = response.json()
    # Contains extensive data including:
    # - Chemical and Physical Properties
    # - Drug and Medication Information
    # - Pharmacology and Biochemistry
    # - Safety and Hazards
    # - Toxicity
    # - Literature references
    # - Patents

# Get only drug information
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON?heading=Drug and Medication Information"

uv pip install pubchempy

uv pip install requests

uv pip install pandas

from scripts.compound_search import search_by_name, get_compound_properties
# Search for a compound
compounds = search_by_name('ibuprofen')
# Get specific properties
props = get_compound_properties('aspirin', 'name', ['MolecularWeight', 'XLogP'])

from scripts.bioactivity_query import get_bioassay_summary, summarize_bioactivities
# Get bioactivity summary
summary = summarize_bioactivities(2244)  # Aspirin
print(f"Total assays: {summary['total_assays']}")
print(f"Active: {summary['active']}, Inactive: {summary['inactive']}")

from pubchempy import BadRequestError, NotFoundError, TimeoutError
try:
    compound = pcp.get_compounds('query', 'name')[0]
except NotFoundError:
    print("Compound not found")
except BadRequestError:
    print("Invalid request format")
except TimeoutError:
    print("Request timed out - try reducing scope")
except IndexError:
    print("No results returned")

import pubchempy as pcp
# Start with any identifier type
compound = pcp.get_compounds('caffeine', 'name')[0]
# Extract all identifier formats
identifiers = {
    'CID': compound.cid,
    'Name': compound.iupac_name,
    'SMILES': compound.canonical_smiles,
    'InChI': compound.inchi,
    'InChIKey': compound.inchikey,
    'Formula': compound.molecular_formula
}

import pubchempy as pcp
def check_drug_likeness(compound_name):
    compound = pcp.get_compounds(compound_name, 'name')[0]
    # Lipinski's Rule of Five
    rules = {
        'MW <= 500': compound.molecular_weight <= 500,
        'LogP <= 5': compound.xlogp <= 5 if compound.xlogp else None,
        'HBD <= 5': compound.h_bond_donor_count <= 5,
        'HBA <= 10': compound.h_bond_acceptor_count <= 10
    }