datamol

Wrap RDKit with a Pythonic API for cheminformatics tasks like SMILES parsing and standardization.

16|7|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/jackspace/ClaudeSkillz --skill datamol
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-pkg-datamol
Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill datamol

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Datamol offers a Pythonic wrapper around RDKit to simplify common cheminformatics tasks, including SMILES handling, standardization, descriptors, fingerprints, conformers, and batch processing.

Core Features & Use Cases

  • Molecule handling from SMILES, conversions, and standardization
  • Read/write SDF/SMI/CSV with cloud storage support
  • Descriptors, fingerprints, clustering, and 3D conformers
  • Batch processing with parallelization

Quick Start

  • Install via conda or pip and start with a few molecules to compute descriptors

Frequently Asked Questions about datamol

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

FAQPage Schema
How do I parse and standardize SMILES strings for cheminformatics workflows?

Datamol provides a Pythonic wrapper around RDKit that simplifies SMILES parsing and standardization. It handles molecule conversions, applies sensible defaults for routine operations, and returns native rdkit.Chem.Mol objects for downstream analysis.

Can I compute molecular descriptors and fingerprints without writing complex RDKit code?

Datamol wraps RDKit to simplify descriptor and fingerprint generation. It abstracts away boilerplate, supports batch processing with parallelization, and integrates seamlessly into drug-discovery pipelines for rapid molecular property analysis.

How do I handle SDF and SMI files with cloud storage support?

Datamol enables reading and writing SDF, SMI, and CSV files with built-in fsspec integration for cloud storage access. This eliminates manual I/O handling and scales across local and cloud workflows in batch operations.

What's the best way to generate 3D conformers and perform molecular clustering?

Datamol streamlines 3D conformer generation and clustering through a clean Python interface over RDKit. It handles the underlying complexity while maintaining access to native RDKit objects for advanced customization when needed.

Can I parallelize molecule processing across multiple cores or cloud infrastructure?

Datamol supports parallel batch processing across local and cloud environments. It abstracts parallelization complexity while preserving full compatibility with RDKit, enabling scalable drug-discovery workflows without rewriting core logic.

Do I need to be an expert in RDKit to work with molecular data?

Datamol is designed for users familiar with Python but not necessarily RDKit internals. It provides sensible defaults for common cheminformatics tasks—SMILES handling, descriptors, fingerprints, conformers—while remaining accessible through a Pythonic API.