undefined

undefined

from rdkit import Chem
from rdkit.Chem import AllChem, Descriptors, Draw, Lipinski
from rdkit.Chem import rdFingerprintGenerator
from rdkit import DataStructs
import numpy as np
import pandas as pd

from rdkit import Chem

undefined

from rdkit import Chem
from rdkit.Chem import Descriptors, Lipinski

mol = Chem.MolFromSmiles("CC(=O)OC1=CC=CC=C1C(=O)O")

undefined

from rdkit import Chem
from rdkit.Chem import AllChem

undefined

from rdkit import Chem

undefined

from rdkit import Chem

smiles = Chem.MolToSmiles(mol)
print(f"SMILES: {smiles}")

# Access SDF properties
if mol.HasProp("_Name"):
    name = mol.GetProp("_Name")
    print(f"Name: {name}")

undefined

from rdkit import Chem

undefined

from rdkit import Chem

mol = Chem.MolFromSmiles("CC(=O)OC1=CC=CC=C1C(=O)O")  # Aspirin

undefined

from rdkit import Chem
from rdkit.Chem import Descriptors, Lipinski, Crippen

mol = Chem.MolFromSmiles("CC(=O)OC1=CC=CC=C1C(=O)O")  # Aspirin

undefined

from rdkit import Chem
from rdkit.Chem import Descriptors

mol = Chem.MolFromSmiles("CCO")

undefined

from rdkit import Chem
from rdkit.Chem import Descriptors, Lipinski

def check_lipinski(mol):
    """Check Lipinski's Rule of Five."""
    mw = Descriptors.MolWt(mol)
    logp = Descriptors.MolLogP(mol)
    hbd = Lipinski.NumHDonors(mol)
    hba = Lipinski.NumHAcceptors(mol)
    
    rules = {
        'MW <= 500': mw <= 500,
        'LogP <= 5': logp <= 5,
        'HBD <= 5': hbd <= 5,
        'HBA <= 10': hba <= 10
    }
    
    passed = all(rules.values())
    return passed, rules

def check_veber(mol):
    """Check Veber's rules for oral bioavailability."""
    rotatable = Lipinski.NumRotatableBonds(mol)
    tpsa = Descriptors.TPSA(mol)
    
    rules = {
        'Rotatable bonds <= 10': rotatable <= 10,
        'TPSA <= 140': tpsa <= 140
    }
    
    passed = all(rules.values())
    return passed, rules

undefined

from rdkit import Chem
from rdkit.Chem import AllChem
from rdkit import DataStructs

undefined

from rdkit import Chem
from rdkit.Chem import AllChem
from rdkit import DataStructs

undefined

from rdkit import Chem
from rdkit.Chem import AllChem, RDKFingerprint

mol = Chem.MolFromSmiles("CCO")

undefined

from rdkit import Chem

undefined

from rdkit import Chem

undefined

from rdkit import Chem
from rdkit.Chem import AllChem

undefined

from rdkit import Chem
from rdkit.Chem import AllChem

undefined

from rdkit import Chem
from rdkit.Chem import AllChem

mol = Chem.MolFromSmiles("CCCC")  # Butane
mol = Chem.AddHs(mol)

undefined

from rdkit import Chem
from rdkit.Chem import AllChem

undefined

from rdkit import Chem
from rdkit.Chem import Draw
import matplotlib.pyplot as plt

undefined

from rdkit import Chem
from rdkit.Chem import Draw

mol = Chem.MolFromSmiles("CC(=O)OC1=CC=CC=C1C(=O)O")  # Aspirin

undefined

from rdkit import Chem
from rdkit.Chem import Draw

mol = Chem.MolFromSmiles("CCO")

undefined

from rdkit import Chem
from rdkit.Chem import AllChem, Descriptors, Lipinski
from rdkit import DataStructs
import pandas as pd

def screen_library(library_file, reference_smiles, similarity_threshold=0.7):
    """Screen compound library for similar, drug-like molecules."""
    
    # Reference molecule and fingerprint
    ref_mol = Chem.MolFromSmiles(reference_smiles)
    ref_fp = AllChem.GetMorganFingerprintAsBitVect(ref_mol, radius=2)
    
    # Results
    hits = []
    
    # Read library
    suppl = Chem.SDMolSupplier(library_file)
    
    for i, mol in enumerate(suppl):
        if mol is None:
            continue
        
        # Step 1: Drug-likeness filter (Lipinski)
        mw = Descriptors.MolWt(mol)
        logp = Descriptors.MolLogP(mol)
        hbd = Lipinski.NumHDonors(mol)
        hba = Lipinski.NumHAcceptors(mol)
        
        if not (mw <= 500 and logp <= 5 and hbd <= 5 and hba <= 10):
            continue
        
        # Step 2: Similarity filter
        fp = AllChem.GetMorganFingerprintAsBitVect(mol, radius=2)
        similarity = DataStructs.TanimotoSimilarity(ref_fp, fp)
        
        if similarity < similarity_threshold:
            continue
        
        # Step 3: PAINS filter (Pan-Assay Interference Compounds)
        from rdkit.Chem import FilterCatalog
        params = FilterCatalog.FilterCatalogParams()
        params.AddCatalog(FilterCatalog.FilterCatalogParams.FilterCatalogs.PAINS)
        catalog = FilterCatalog.FilterCatalog(params)
        
        if catalog.HasMatch(mol):
            continue
        
        # Passed all filters
        hits.append({
            'id': i,
            'smiles': Chem.MolToSmiles(mol),
            'similarity': similarity,
            'mw': mw,
            'logp': logp
        })
    
    # Convert to DataFrame
    df_hits = pd.DataFrame(hits)
    df_hits = df_hits.sort_values('similarity', ascending=False)
    
    return df_hits

undefined

from rdkit import Chem
from rdkit.Chem import AllChem
from rdkit import DataStructs
import numpy as np

def select_diverse_set(smiles_list, n_select=100):
    """Select diverse subset using MaxMin algorithm."""
    
    # Generate fingerprints
    mols = [Chem.MolFromSmiles(s) for s in smiles_list]
    fps = [AllChem.GetMorganFingerprintAsBitVect(m, radius=2) for m in mols if m]
    
    if len(fps) < n_select:
        return list(range(len(fps)))
    
    # MaxMin diversity picking
    from rdkit.SimDivFilters import MaxMinPicker
    
    def distance_function(i, j):
        return 1 - DataStructs.TanimotoSimilarity(fps[i], fps[j])
    
    picker = MaxMinPicker()
    picks = picker.LazyPick(
        distance_function,
        len(fps),
        n_select,
        seed=42
    )
    
    return list(picks)

undefined

from rdkit import Chem
from rdkit.Chem import AllChem, Descriptors
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score, mean_squared_error
import numpy as np

def build_qsar_model(smiles_list, activities):
    """Build QSAR model from SMILES and activities."""
    
    # Generate fingerprints
    fps = []
    valid_activities = []
    
    for smi, act in zip(smiles_list, activities):
        mol = Chem.MolFromSmiles(smi)
        if mol is not None:
            # Morgan fingerprint as features
            fp = AllChem.GetMorganFingerprintAsBitVect(mol, radius=2, nBits=2048)
            arr = np.zeros((1,))
            DataStructs.ConvertToNumpyArray(fp, arr)
            fps.append(arr)
            valid_activities.append(act)
    
    X = np.array(fps)
    y = np.array(valid_activities)
    
    # Split data
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, random_state=42
    )
    
    # Train model
    model = RandomForestRegressor(n_estimators=100, random_state=42)
    model.fit(X_train, y_train)
    
    # Evaluate
    y_pred_train = model.predict(X_train)
    y_pred_test = model.predict(X_test)
    
    print(f"Train R²: {r2_score(y_train, y_pred_train):.3f}")
    print(f"Test R²: {r2_score(y_test, y_pred_test):.3f}")
    print(f"Test RMSE: {mean_squared_error(y_test, y_pred_test, squared=False):.3f}")
    
    return model

undefined

from rdkit import Chem
from rdkit.Chem.Scaffolds import MurckoScaffold
from collections import Counter

def analyze_scaffolds(smiles_list):
    """Analyze Murcko scaffolds in compound set."""
    
    scaffolds = []
    
    for smi in smiles_list:
        mol = Chem.MolFromSmiles(smi)
        if mol is not None:
            # Get Murcko scaffold
            scaffold = MurckoScaffold.GetScaffoldForMol(mol)
            scaffold_smi = Chem.MolToSmiles(scaffold)
            scaffolds.append(scaffold_smi)
    
    # Count scaffolds
    scaffold_counts = Counter(scaffolds)
    
    print(f"Unique scaffolds: {len(scaffold_counts)}")
    print("\nTop 5 scaffolds:")
    for scaffold, count in scaffold_counts.most_common(5):
        print(f"{scaffold}: {count}")
    
    return scaffold_counts

undefined

from rdkit import Chem
from rdkit.Chem import AllChem

def enumerate_amide_coupling(acids, amines):
    """Enumerate all possible amide products."""
    
    # Define reaction SMARTS
    rxn = AllChem.ReactionFromSmarts('[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]')
    
    products = []
    
    for acid_smi in acids:
        for amine_smi in amines:
            acid = Chem.MolFromSmiles(acid_smi)
            amine = Chem.MolFromSmiles(amine_smi)
            
            if acid is None or amine is None:
                continue
            
            # Run reaction
            products_tuple = rxn.RunReactants((acid, amine))
            
            if products_tuple:
                product = products_tuple[0][0]
                Chem.SanitizeMol(product)
                product_smi = Chem.MolToSmiles(product)
                products.append({
                    'acid': acid_smi,
                    'amine': amine_smi,
                    'product': product_smi
                })
    
    return products

undefined

from rdkit import Chem
from rdkit.Chem import AllChem
import pandas as pd

undefined

from rdkit import Chem
from rdkit.Chem import AllChem
from multiprocessing import Pool
import pandas as pd

def process_molecule(smiles):
    """Process single molecule."""
    mol = Chem.MolFromSmiles(smiles)
    if mol is None:
        return None
    
    return {
        'smiles': smiles,
        'mw': Descriptors.MolWt(mol),
        'logp': Descriptors.MolLogP(mol),
        'fp': AllChem.GetMorganFingerprintAsBitVect(mol, 2)
    }

def process_library_parallel(smiles_list, n_jobs=4):
    """Process library in parallel."""
    with Pool(n_jobs) as pool:
        results = pool.map(process_molecule, smiles_list)
    
    # Filter None results
    results = [r for r in results if r is not None]
    return pd.DataFrame(results)

undefined

from functools import lru_cache
from rdkit import Chem
from rdkit.Chem import Descriptors

@lru_cache(maxsize=10000)
def get_mol_properties(smiles):
    """Calculate properties with caching."""
    mol = Chem.MolFromSmiles(smiles)
    if mol is None:
        return None
    
    return {
        'mw': Descriptors.MolWt(mol),
        'logp': Descriptors.MolLogP(mol),
        'tpsa': Descriptors.TPSA(mol)
    }

undefined

undefined

undefined

from rdkit import Chem

undefined

from rdkit import Chem
from rdkit.Chem import AllChem

mol = Chem.MolFromSmiles("CCO")

undefined

from rdkit import Chem
from rdkit.Chem import AllChem, MACCSkeys
from rdkit import DataStructs

mol1 = Chem.MolFromSmiles("CCO")
mol2 = Chem.MolFromSmiles("CCCO")

undefined

undefined

for mol in suppl:
    if mol is not None:
        batch.append(mol)
    
    if len(batch) >= batch_size:
        # Process batch
        yield batch
        batch = []

# Process remaining
if batch:
    yield batch

RDKit is the cornerstone of computational drug discovery and cheminformatics. Its comprehensive toolkit for molecular manipulation, descriptor calculation, and similarity searching makes it indispensable for pharmaceutical research, virtual screening, and chemical data analysis. Master RDKit, and you'll have the power to computationally explore vast chemical spaces and accelerate drug discovery.