Datamol Cheminformatics

uv pip install datamol

import datamol as dm
import numpy as np
import pandas as pd

import datamol as dm

# Parse and standardize
mol = dm.to_mol("CC(=O)Oc1ccccc1C(=O)O")  # Aspirin
mol = dm.standardize_mol(mol)
print(dm.to_smiles(mol))  # Canonical SMILES

# Compute descriptors
desc = dm.descriptors.compute_many_descriptors(mol)
print(f"MW: {desc['mw']:.1f}, LogP: {desc['logp']:.2f}, TPSA: {desc['tpsa']:.1f}")

# Generate fingerprint
fp = dm.to_fp(mol, fp_type='ecfp', radius=2, n_bits=2048)
print(f"Fingerprint shape: {fp.shape}")  # (2048,)

import datamol as dm

# From SMILES (returns None on failure)
mol = dm.to_mol("CCO")
if mol is None:
    print("Invalid SMILES")

# Format conversions
smiles = dm.to_smiles(mol, isomeric=True)  # Canonical SMILES
inchi = dm.to_inchi(mol)
inchikey = dm.to_inchikey(mol)
selfies = dm.to_selfies(mol)

mol = dm.standardize_mol(
    mol,
    disconnect_metals=True,
    normalize=True,
    reionize=True
)
clean_smiles = dm.standardize_smiles("C(C)O")  # From SMILES directly

# Reading (supports local, S3, GCS, HTTP via fsspec)
df = dm.read_sdf("compounds.sdf", mol_column='mol')
df = dm.read_csv("data.csv", smiles_column="SMILES", mol_column="mol")
df = dm.read_excel("compounds.xlsx", sheet_name=0, mol_column="mol")
df = dm.open_df("file.sdf")  # Auto-detect format

# Writing
dm.to_sdf(df, "output.sdf", mol_column="mol")
dm.to_smi(mols, "output.smi")
dm.to_xlsx(df, "output.xlsx", mol_columns=["mol"])  # Renders molecule images

# Remote files
df = dm.read_sdf("s3://bucket/compounds.sdf")
dm.to_sdf(mols, "s3://bucket/output.sdf")

import datamol as dm

mol = dm.to_mol("c1ccc(cc1)CCN")

# Standard descriptor set (single molecule)
desc = dm.descriptors.compute_many_descriptors(mol)
# Returns dict: {'mw': 121.18, 'logp': 1.41, 'hbd': 1, 'hba': 1,
#                'tpsa': 26.02, 'n_aromatic_atoms': 6, ...}

# Batch computation (parallel)
mols = [dm.to_mol(s) for s in ["CCO", "c1ccccc1", "CC(=O)O"]]
desc_df = dm.descriptors.batch_compute_many_descriptors(
    mols, n_jobs=-1, progress=True
)
print(desc_df.head())

# Specific descriptors
n_stereo = dm.descriptors.n_stereo_centers(mol)
n_aromatic = dm.descriptors.n_aromatic_atoms(mol)
aromatic_ratio = dm.descriptors.n_aromatic_atoms_proportion(mol)
n_rigid = dm.descriptors.n_rigid_bonds(mol)

def is_druglike(mol):
    desc = dm.descriptors.compute_many_descriptors(mol)
    return (desc['mw'] <= 500 and desc['logp'] <= 5
            and desc['hbd'] <= 5 and desc['hba'] <= 10)

druglike = [m for m in mols if is_druglike(m)]
print(f"Drug-like: {len(druglike)}/{len(mols)}")

import datamol as dm

mol = dm.to_mol("c1ccc(cc1)CCN")

# Fingerprint types
fp_ecfp = dm.to_fp(mol, fp_type='ecfp', radius=2, n_bits=2048)  # Morgan/ECFP
fp_maccs = dm.to_fp(mol, fp_type='maccs')    # MACCS keys (167 bits)
fp_topo = dm.to_fp(mol, fp_type='topological')  # Topological
fp_ap = dm.to_fp(mol, fp_type='atompair')    # Atom pairs

# Pairwise distances (Tanimoto distance = 1 - similarity)
mols = [dm.to_mol(s) for s in ["CCO", "CCCO", "c1ccccc1"]]
dist_matrix = dm.pdist(mols, n_jobs=-1)
print(f"Distance vector shape: {dist_matrix.shape}")

# Distances between two sets
query = [dm.to_mol("CCO")]
library = [dm.to_mol(s) for s in ["CCCO", "c1ccccc1", "CC(=O)O"]]
distances = dm.cdist(query, library, n_jobs=-1)
print(f"Query-library distances: {distances.shape}")

import datamol as dm

mols = [dm.to_mol(s) for s in smiles_list]  # Assume smiles_list defined

# Butina clustering (suitable for ~1000 molecules, builds full distance matrix)
clusters = dm.cluster_mols(mols, cutoff=0.2, n_jobs=-1)
for i, cluster in enumerate(clusters[:5]):
    print(f"Cluster {i}: {len(cluster)} molecules")

# Diversity selection (works for larger libraries)
diverse_mols = dm.pick_diverse(mols, npick=100)
print(f"Selected {len(diverse_mols)} diverse molecules")

# Cluster centroids
centroids = dm.pick_centroids(mols, npick=50)
print(f"Selected {len(centroids)} centroids")

import datamol as dm
from collections import Counter

mol = dm.to_mol("c1ccc(cc1)CCN")
scaffold = dm.to_scaffold_murcko(mol)
print(f"Scaffold: {dm.to_smiles(scaffold)}")

# Scaffold frequency analysis
scaffolds = [dm.to_scaffold_murcko(m) for m in mols]
scaffold_smiles = [dm.to_smiles(s) for s in scaffolds]
counts = Counter(scaffold_smiles)
print(f"Top scaffolds: {counts.most_common(5)}")

# Scaffold-based train/test split (for ML)
scaffold_to_mols = {}
for mol, scaf in zip(mols, scaffold_smiles):
    scaffold_to_mols.setdefault(scaf, []).append(mol)
scaffolds_list = list(scaffold_to_mols.keys())
split_idx = int(0.8 * len(scaffolds_list))
train_mols = [m for s in scaffolds_list[:split_idx] for m in scaffold_to_mols[s]]
test_mols = [m for s in scaffolds_list[split_idx:] for m in scaffold_to_mols[s]]

mol = dm.to_mol("CC(=O)Oc1ccccc1C(=O)O")  # Aspirin

# BRICS (16 bond types, retrosynthetic)
brics_frags = dm.fragment.brics(mol)
print(f"BRICS fragments: {brics_frags}")  # Set of fragment SMILES with [1*] attachment points

# RECAP (11 bond types, combinatorial)
recap_frags = dm.fragment.recap(mol)

# MMPA (matched molecular pair analysis)
mmpa_frags = dm.fragment.mmpa_frag(mol)

import datamol as dm

mol = dm.to_mol("c1ccc(cc1)CCN")

# Generate conformers
mol_3d = dm.conformers.generate(
    mol,
    n_confs=50,           # Number to generate
    rms_cutoff=0.5,       # Filter similar (Angstroms)
    minimize_energy=True,  # UFF minimization
    method='ETKDGv3'      # Embedding method
)
print(f"Generated {mol_3d.GetNumConformers()} conformers")

# Access coordinates
conf = mol_3d.GetConformer(0)
positions = conf.GetPositions()  # Nx3 array
print(f"Atom positions shape: {positions.shape}")

# Cluster conformers by RMSD
clusters = dm.conformers.cluster(mol_3d, rms_cutoff=1.0)
centroids = dm.conformers.return_centroids(mol_3d, clusters)

# Solvent accessible surface area
sasa = dm.conformers.sasa(mol_3d, n_jobs=-1)
print(f"SASA values: {sasa[:3]}")

import datamol as dm

# 1. Load and standardize
df = dm.read_sdf("compounds.sdf")
df['mol'] = df['mol'].apply(lambda m: dm.standardize_mol(m) if m else None)
df = df[df['mol'].notna()]
print(f"Loaded {len(df)} valid molecules")

# 2. Compute descriptors and filter by drug-likeness
desc_df = dm.descriptors.batch_compute_many_descriptors(
    df['mol'].tolist(), n_jobs=-1, progress=True
)
druglike = (desc_df['mw'] <= 500) & (desc_df['logp'] <= 5) & (desc_df['hbd'] <= 5) & (desc_df['hba'] <= 10)
filtered_df = df[druglike.values].reset_index(drop=True)
print(f"Drug-like compounds: {len(filtered_df)}")

# 3. Select diverse subset
diverse = dm.pick_diverse(filtered_df['mol'].tolist(), npick=100)

# 4. Visualize
dm.viz.to_image(diverse[:20], legends=[dm.to_smiles(m) for m in diverse[:20]],
                n_cols=5, mol_size=(300, 300), outfile="diverse_hits.png")

import datamol as dm
import numpy as np

# Query actives and screening library
actives = [dm.to_mol(s) for s in active_smiles]  # Known actives
library = [dm.to_mol(s) for s in library_smiles]  # Screening library

# Calculate distances (Tanimoto)
distances = dm.cdist(actives, library, n_jobs=-1)
min_distances = distances.min(axis=0)  # Best match to any active
similarities = 1 - min_distances

# Rank and select top hits
top_idx = np.argsort(similarities)[::-1][:100]
top_hits = [library[i] for i in top_idx]
top_scores = [similarities[i] for i in top_idx]
print(f"Top hit similarity: {top_scores[0]:.3f}")

# Visualize top hits
dm.viz.to_image(top_hits[:20],
    legends=[f"Sim: {s:.3f}" for s in top_scores[:20]],
    outfile="screening_hits.png")

import datamol as dm

# Group compounds by scaffold
scaffolds = [dm.to_scaffold_murcko(m) for m in mols]
scaffold_smiles = [dm.to_smiles(s) for s in scaffolds]

sar_df = pd.DataFrame({
    'mol': mols, 'scaffold': scaffold_smiles, 'activity': activities
})

# Analyze each scaffold series
for scaffold, group in sar_df.groupby('scaffold'):
    if len(group) >= 3:
        print(f"Scaffold: {scaffold} | N={len(group)} | "
              f"Activity: {group['activity'].min():.2f}–{group['activity'].max():.2f}")
        dm.viz.to_image(group['mol'].tolist(), align=True,
            legends=[f"Act: {a:.2f}" for a in group['activity']])