datamol

Wrap RDKit with a Pythonic API for cheminformatics tasks.

321|26|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/mkurman/tamux --skill datamol-mkurman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/mkurman/tamux/tree/main/skills/scientific-skills/datamol
Command: npx skills add https://github.com/mkurman/tamux --skill datamol-mkurman

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Datamol provides a clean, Pythonic interface that wraps RDKit, reducing boilerplate and accelerating cheminformatics workflows.

Core Features & Use Cases

  • Molecule creation and conversion (SMILES, InChI) with standardization
  • Descriptors, fingerprints, clustering, and 3D conformers
  • Scaffold and fragment analysis, visualization, and simple reaction utilities
  • Lightweight data I/O and batch processing for datasets
  • Cloud storage integration via fsspec for remote datasets

Quick Start

Install datamol, import it as dm, and start by converting a SMILES string to a molecule with to_mol.

Frequently Asked Questions about datamol

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I simplify RDKit cheminformatics workflows in Python?

You can simplify RDKit cheminformatics workflows by using a Pythonic wrapper that reduces boilerplate for molecule creation, standardization, and descriptor calculation across datasets.

What is the best way to calculate molecular descriptors and fingerprints from SMILES strings?

Calculating molecular descriptors and fingerprints from SMILES strings is done by converting the text to a molecule object, then applying modular functions for batch processing and structural feature extraction.

Can I generate 3D conformers and perform scaffold analysis without writing extensive RDKit code?

Generating 3D conformers and performing scaffold analysis is supported natively, allowing you to process fragments and generate spatial configurations without extensive manual RDKit code.

Does this cheminformatics approach support remote dataset I/O and cloud storage integration?

Cloud storage integration for remote datasets is supported via fsspec, enabling lightweight data I/O and batch processing of molecular files directly from remote environments.

How does a Pythonic RDKit wrapper compare to using raw RDKit for molecule standardization?

A Pythonic RDKit wrapper provides a cleaner interface compared to raw RDKit, accelerating molecule standardization and conversion tasks by minimizing boilerplate code in data pipelines.