---
id: datamol
version: "0.12.5"
license: Apache
license_treatment: permissive
maintenance: active
---

# datamol — A python library to work with molecules. Built on top of RDKit.

License: permissive · Maintenance: active · Downloads: 104.0K/mo

## What it is and what it does

Datamol is a Python library that wraps RDKit to simplify molecular cheminformatics workflows. It exposes RDKit's core Mol objects through a more intuitive API, handling common tasks like SMILES parsing, molecular fingerprinting, conformer generation, and format conversion with sensible defaults. The library emphasizes ease of use while maintaining direct access to underlying RDKit objects, so you can drop down to RDKit when needed.

It includes built-in parallelization via joblib, remote file support through fsspec for reading and writing SDF, CSV, and other formats from cloud storage, and visualization tools. The package targets chemists and computational biologists working with small-molecule datasets, offering both batch operations on DataFrames and single-molecule transformations.

Use it for:

- Convert SMILES strings to molecular objects and compute fingerprints for machine learning pipelines.
- Standardize and sanitize molecular structures in bulk from CSV or SDF files stored locally or on cloud storage.
- Generate 3D conformers and compute solvent-accessible surface area for molecular dynamics or docking studies.
- Batch-process large molecular datasets with automatic parallelization and progress tracking.
- Visualize molecular structures and conformers in Jupyter notebooks with built-in 2D and 3D rendering.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Datamol provides a pythonic layer on top of RDKit for molecular manipulation, offering simplified APIs for converting between molecular formats, standardizing molecules, and performing common cheminformatics operations.

Yes. Datamol is actively maintained, has no known vulnerabilities, and offers genuine convenience for RDKit-based workflows. Install it if you work with molecular structures and want a more ergonomic API than raw RDKit; the Apache-2.0 license poses no barrier. The main gotcha is rdkit's dependency chain—use conda-forge for a smooth install.

## Install

pip install datamol
uv add datamol
poetry add datamol

## Installing datamol

Before you install: Low install friction with a pure-wheel distribution. Actively maintained with recent commits and passing CI across Windows, OSX, and Linux. Requires rdkit as a dependency, which is typically installed via conda-forge; pip installation may require pre-built wheels.

License in practice: Apache-2.0 permissive license allows commercial and private use with minimal restrictions; you must include a copy of the license and state significant changes.

Quickstart:

import datamol as dm

mol = dm.to_mol("O=C(C)Oc1ccccc1C(=O)O", sanitize=True)
fp = dm.to_fp(mol)
smiles = dm.to_smiles(mol)

Requires rdkit, which is best installed via conda-forge; pip installation may require pre-built wheels or a working C++ compiler.

Verify before relying:

- Whether rdkit can be reliably installed via pip in all environments, or if conda-forge is strongly recommended.
- Performance characteristics and scalability limits for large molecular datasets or batch operations.

## Package facts

- License: Apache (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 104.0K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

molecular structure manipulation, rdkit wrapper library, cheminformatics python, smiles to molecule conversion, molecular fingerprints, conformer generation, molecule standardization, cheminformatics, rdkit-wrapper, molecular-io

[View on SkillFed](https://skillfed.io/packages/datamol) · [View on PyPI](https://pypi.org/project/datamol/)