datamol

What this skill does

# Datamol Cheminformatics Skill

## Overview

Datamol is a Python library that provides a lightweight, Pythonic abstraction layer over RDKit for molecular cheminformatics. Simplify complex molecular operations with sensible defaults, efficient parallelization, and modern I/O capabilities. All molecular objects are native `rdkit.Chem.Mol` instances, ensuring full compatibility with the RDKit ecosystem.

**Version note:** Examples target **datamol 0.12.x** (PyPI stable: **0.12.5**, June 2024). Since 0.10.0, modules are lazy-loaded by default (set `DATAMOL_DISABLE_LAZY_LOADING=1` to disable). Since 0.12.2, RDKit is a direct PyPI dependency of datamol. Fingerprints use RDKit's `rdFingerprintGenerator` API (0.12.5+).

**Key capabilities**:
- Molecular format conversion (SMILES, SELFIES, InChI)
- Structure standardization and sanitization
- Molecular descriptors and fingerprints
- 3D conformer generation and analysis
- Clustering and diversity selection
- Scaffold and fragment analysis
- Chemical reaction application
- Visualization and alignment
- Batch processing with parallelization
- Cloud storage support via fsspec

## Installation and Setup

Guide users to install datamol:

```bash
uv pip install datamol
```

RDKit is installed automatically with datamol. For remote file paths (S3, GCS, HTTP), install the matching fsspec backend:

```bash
uv pip install s3fs   # AWS S3
uv pip install gcsfs  # Google Cloud Storage
```

**Import convention**:
```python
import datamol as dm
```

## Core Workflows

### 1. Basic Molecule Handling

**Creating molecules from SMILES**:
```python
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")
```

**Converting molecules to SMILES**:
```python
# 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)
```

**Standardization and sanitization** (always recommend for user-provided molecules):
```python
# 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)
```

### 2. Reading and Writing Molecular Files

Refer to `references/io_module.md` for comprehensive I/O documentation.

**Reading files**:
```python
# 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/writer (auto-detects format; supports compression)
df = dm.open_df("file.sdf")  # .sdf, .csv, .xlsx, .parquet, .json, .gz, etc.
dm.save_df(df, "output.parquet")
```

**Writing files**:
```python
# 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"])
```

**Remote file support** (S3, GCS, HTTP via fsspec):

Only use cloud paths when the user explicitly requests them. Confirm the destination before writing.

```python
# Read from cloud storage or HTTPS (user-provided URLs only)
df = dm.read_sdf("s3://bucket/compounds.sdf")
df = dm.read_csv("https://example.com/data.csv")

# Write to cloud storage — confirm path with user first
dm.to_sdf(mols, "s3://bucket/output.sdf")
```

Cloud backends read credentials from the standard provider environment (for example `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION`, or `GOOGLE_APPLICATION_CREDENTIALS`). Datamol passes these to fsspec locally; it does not collect or transmit environment variables to third-party endpoints. Scope credential access to the named provider variables only.

### 3. Molecular Descriptors and Properties

Refer to `references/descriptors_viz.md` for detailed descriptor documentation.

**Computing descriptors for a single molecule**:
```python
# 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, ...}
```

**Batch descriptor computation** (recommended for datasets):
```python
# 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
)
```

**Specific descriptors**:
```python
# 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)
```

**Drug-likeness filtering (Lipinski's Rule of Five)**:
```python
# 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)]
```

### 4. Molecular Fingerprints and Similarity

**Generating fingerprints**:

Datamol defaults to ECFP6 (`radius=3`, `n_bits=2048`). Pass `radius=2` explicitly for ECFP4.

```python
# ECFP4 (common in similarity screening)
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')
fp_rdkit = dm.to_fp(mol, fp_type='rdkit')
```

**Similarity calculations**:
```python
# 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 (scipy is a PyPI package, not a file in this skill)
from scipy.spatial.distance import squareform  # third-party library
dist_matrix = squareform(dm.pdist(mols))
# Lower distance = higher similarity (Tanimoto distance = 1 - Tanimoto similarity)
```

### 5. Clustering and Diversity Selection

Refer to `references/core_api.md` for clustering details.

**Butina clustering**:
```python
# 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]
```

**Important**: Butina clustering builds a full distance matrix - suitable for ~1000 molecules, not for 10,000+.

**Diversity selection**:
```python
# 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
)
```

### 6. Scaffold Analysis

Refer to `references/fragments_scaffolds.md` for complete scaffold documentation.

**Extracting Murcko scaffolds**:
```python
# Get Bemis-Murcko scaffold (core structure)
scaffold = dm.to_scaffold_murcko(mol)
scaffold_smiles = dm.to_smiles(scaffold)
```

**Scaffold-based analysis**:
```python
# Group compounds by scaffold
from col