Datamol

uv pip install datamol

import datamol as dm

import datamol as dm

# Single molecule
mol = dm.to_mol("CCO")  # Ethanol

# From list of SMILES
smiles_list = ["CCO", "c1ccccc1", "CC(=O)O"]
mols = [dm.to_mol(smi) for smi in smiles_list]

# Error handling
mol = dm.to_mol("invalid_smiles")  # Returns None
if mol is None:
    print("Failed to parse SMILES")

# Canonical SMILES
smiles = dm.to_smiles(mol)

# Isomeric SMILES (includes stereochemistry)
smiles = dm.to_smiles(mol, isomeric=True)

# Other formats
inchi = dm.to_inchi(mol)
inchikey = dm.to_inchikey(mol)
selfies = dm.to_selfies(mol)

# Sanitize molecule
mol = dm.sanitize_mol(mol)

# Full standardization (recommended for datasets)
mol = dm.standardize_mol(
    mol,
    disconnect_metals=True,
    normalize=True,
    reionize=True
)

# For SMILES strings directly
clean_smiles = dm.standardize_smiles(smiles)

# SDF files (most common in chemistry)
df = dm.read_sdf("compounds.sdf", mol_column='mol')

# SMILES files
df = dm.read_smi("molecules.smi", smiles_column='smiles', mol_column='mol')

# CSV with SMILES column
df = dm.read_csv("data.csv", smiles_column="SMILES", mol_column="mol")

# Excel files
df = dm.read_excel("compounds.xlsx", sheet_name=0, mol_column="mol")

# Universal reader (auto-detects format)
df = dm.open_df("file.sdf")  # Works with .sdf, .csv, .xlsx, .parquet, .json

# Save as SDF
dm.to_sdf(mols, "output.sdf")
# Or from DataFrame
dm.to_sdf(df, "output.sdf", mol_column="mol")

# Save as SMILES file
dm.to_smi(mols, "output.smi")

# Excel with rendered molecule images
dm.to_xlsx(df, "output.xlsx", mol_columns=["mol"])

# Read from cloud storage
df = dm.read_sdf("s3://bucket/compounds.sdf")
df = dm.read_csv("https://example.com/data.csv")

# Write to cloud storage
dm.to_sdf(mols, "s3://bucket/output.sdf")

# Get standard descriptor set
descriptors = dm.descriptors.compute_many_descriptors(mol)
# Returns: {'mw': 46.07, 'logp': -0.03, 'hbd': 1, 'hba': 1,
#           'tpsa': 20.23, 'n_aromatic_atoms': 0, ...}

# Compute for all molecules in parallel
desc_df = dm.descriptors.batch_compute_many_descriptors(
    mols,
    n_jobs=-1,      # Use all CPU cores
    progress=True   # Show progress bar
)

# Aromaticity
n_aromatic = dm.descriptors.n_aromatic_atoms(mol)
aromatic_ratio = dm.descriptors.n_aromatic_atoms_proportion(mol)

# Stereochemistry
n_stereo = dm.descriptors.n_stereo_centers(mol)
n_unspec = dm.descriptors.n_stereo_centers_unspecified(mol)

# Flexibility
n_rigid = dm.descriptors.n_rigid_bonds(mol)

# Filter compounds
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_mols = [mol for mol in mols if is_druglike(mol)]

# ECFP (Extended Connectivity Fingerprint, default)
fp = dm.to_fp(mol, fp_type='ecfp', radius=2, n_bits=2048)

# Other fingerprint types
fp_maccs = dm.to_fp(mol, fp_type='maccs')
fp_topological = dm.to_fp(mol, fp_type='topological')
fp_atompair = dm.to_fp(mol, fp_type='atompair')

# Pairwise distances within a set
distance_matrix = dm.pdist(mols, n_jobs=-1)

# Distances between two sets
distances = dm.cdist(query_mols, library_mols, n_jobs=-1)

# Find most similar molecules
from scipy.spatial.distance import squareform
dist_matrix = squareform(dm.pdist(mols))
# Lower distance = higher similarity (Tanimoto distance = 1 - Tanimoto similarity)

# Cluster molecules by structural similarity
clusters = dm.cluster_mols(
    mols,
    cutoff=0.2,    # Tanimoto distance threshold (0=identical, 1=completely different)
    n_jobs=-1      # Parallel processing
)

# Each cluster is a list of molecule indices
for i, cluster in enumerate(clusters):
    print(f"Cluster {i}: {len(cluster)} molecules")
    cluster_mols = [mols[idx] for idx in cluster]

# Pick diverse subset
diverse_mols = dm.pick_diverse(
    mols,
    npick=100  # Select 100 diverse molecules
)

# Pick cluster centroids
centroids = dm.pick_centroids(
    mols,
    npick=50   # Select 50 representative molecules
)

# Get Bemis-Murcko scaffold (core structure)
scaffold = dm.to_scaffold_murcko(mol)
scaffold_smiles = dm.to_smiles(scaffold)

# Group compounds by scaffold
from collections import Counter

scaffolds = [dm.to_scaffold_murcko(mol) for mol in mols]
scaffold_smiles = [dm.to_smiles(s) for s in scaffolds]

# Count scaffold frequency
scaffold_counts = Counter(scaffold_smiles)
most_common = scaffold_counts.most_common(10)

# Create scaffold-to-molecules mapping
scaffold_groups = {}
for mol, scaf_smi in zip(mols, scaffold_smiles):
    if scaf_smi not in scaffold_groups:
        scaffold_groups[scaf_smi] = []
    scaffold_groups[scaf_smi].append(mol)

# Ensure train and test sets have different scaffolds
scaffold_to_mols = {}
for mol, scaf in zip(mols, scaffold_smiles):
    if scaf not in scaffold_to_mols:
        scaffold_to_mols[scaf] = []
    scaffold_to_mols[scaf].append(mol)

# Split scaffolds into train/test
import random
scaffolds = list(scaffold_to_mols.keys())
random.shuffle(scaffolds)
split_idx = int(0.8 * len(scaffolds))
train_scaffolds = scaffolds[:split_idx]
test_scaffolds = scaffolds[split_idx:]

# Get molecules for each split
train_mols = [mol for scaf in train_scaffolds for mol in scaffold_to_mols[scaf]]
test_mols = [mol for scaf in test_scaffolds for mol in scaffold_to_mols[scaf]]

# Fragment molecule
fragments = dm.fragment.brics(mol)
# Returns: set of fragment SMILES with attachment points like '[1*]CCN'

fragments = dm.fragment.recap(mol)

# Find common fragments across compound library
from collections import Counter

all_fragments = []
for mol in mols:
    frags = dm.fragment.brics(mol)
    all_fragments.extend(frags)

fragment_counts = Counter(all_fragments)
common_frags = fragment_counts.most_common(20)

# Fragment-based scoring
def fragment_score(mol, reference_fragments):
    mol_frags = dm.fragment.brics(mol)
    overlap = mol_frags.intersection(reference_fragments)
    return len(overlap) / len(mol_frags) if mol_frags else 0

# Generate 3D conformers
mol_3d = dm.conformers.generate(
    mol,
    n_confs=50,           # Number to generate (auto if None)
    rms_cutoff=0.5,       # Filter similar conformers (Ångströms)
    minimize_energy=True,  # Minimize with UFF force field
    method='ETKDGv3'      # Embedding method (recommended)
)

# Access conformers
n_conformers = mol_3d.GetNumConformers()
conf = mol_3d.GetConformer(0)  # Get first conformer
positions = conf.GetPositions()  # Nx3 array of atom coordinates

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

# Get representative conformers
centroids = dm.conformers.return_centroids(mol_3d, clusters)

# Calculate solvent accessible surface area
sasa_values = dm.conformers.sasa(mol_3d, n_jobs=-1)

# Access SASA from conformer properties
conf = mol_3d.GetConformer(0)
sasa = conf.GetDoubleProp('rdkit_free_sasa')

# Visualize molecules
dm.viz.to_image(
    mols[:20],
    legends=[dm.to_smiles(m) for m in mols[:20]],
    n_cols=5,
    mol_size=(300, 300)
)

# Save to file
dm.viz.to_image(mols, outfile="molecules.png")

# SVG for publications
dm.viz.to_image(mols, outfile="molecules.svg", use_svg=True)

# Align molecules by common substructure
dm.viz.to_image(
    similar_mols,
    align=True,  # Enable MCS alignment
    legends=activity_labels,
    n_cols=4
)

# Highlight specific atoms and bonds
dm.viz.to_image(
    mol,
    highlight_atom=[0, 1, 2, 3],  # Atom indices
    highlight_bond=[0, 1, 2]      # Bond indices
)

# Display multiple conformers
dm.viz.conformers(
    mol_3d,
    n_confs=10,
    align_conf=True,
    n_cols=3
)

from rdkit.Chem import rdChemReactions

# Define reaction from SMARTS
rxn_smarts = '[C:1](=[O:2])[OH:3]>>[C:1](=[O:2])[Cl:3]'
rxn = rdChemReactions.ReactionFromSmarts(rxn_smarts)

# Apply to molecule
reactant = dm.to_mol("CC(=O)O")  # Acetic acid
product = dm.reactions.apply_reaction(
    rxn,
    (reactant,),
    sanitize=True
)

# Convert to SMILES
product_smiles = dm.to_smiles(product)

# Apply reaction to library
products = []
for mol in reactant_mols:
    try:
        prod = dm.reactions.apply_reaction(rxn, (mol,))
        if prod is not None:
            products.append(prod)
    except Exception as e:
        print(f"Reaction failed: {e}")

import datamol as dm
import pandas as pd

# 1. Load molecules
df = dm.read_sdf("compounds.sdf")

# 2. Standardize
df['mol'] = df['mol'].apply(lambda m: dm.standardize_mol(m) if m else None)
df = df[df['mol'].notna()]  # Remove failed molecules

# 3. Compute descriptors
desc_df = dm.descriptors.batch_compute_many_descriptors(
    df['mol'].tolist(),
    n_jobs=-1,
    progress=True
)

# 4. Filter by drug-likeness
druglike = (
    (desc_df['mw'] <= 500) &
    (desc_df['logp'] <= 5) &
    (desc_df['hbd'] <= 5) &
    (desc_df['hba'] <= 10)
)
filtered_df = df[druglike]

# 5. Cluster and select diverse subset
diverse_mols = dm.pick_diverse(
    filtered_df['mol'].tolist(),
    npick=100
)

# 6. Visualize results
dm.viz.to_image(
    diverse_mols,
    legends=[dm.to_smiles(m) for m in diverse_mols],
    outfile="diverse_compounds.png",
    n_cols=10
)

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

# Create DataFrame with activities
sar_df = pd.DataFrame({
    'mol': mols,
    'scaffold': scaffold_smiles,
    'activity': activities  # User-provided activity data
})

# Analyze each scaffold series
for scaffold, group in sar_df.groupby('scaffold'):
    if len(group) >= 3:  # Need multiple examples
        print(f"\nScaffold: {scaffold}")
        print(f"Count: {len(group)}")
        print(f"Activity range: {group['activity'].min():.2f} - {group['activity'].max():.2f}")

        # Visualize with activities as legends
        dm.viz.to_image(
            group['mol'].tolist(),
            legends=[f"Activity: {act:.2f}" for act in group['activity']],
            align=True  # Align by common substructure
        )