datamol

Wrap RDKit with Pythonic defaults for molecular informatics tasks.

22|4|Updated May 25, 2026
One-click install
npx skills add https://github.com/crazymsn/academic-skills --skill datamol-crazymsn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/datamol
Command: npx skills add https://github.com/crazymsn/academic-skills --skill datamol-crazymsn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Datamol provides a Pythonic wrapper around RDKit to simplify standard cheminformatics tasks, enabling researchers to perform molecule handling, descriptor calculations, fingerprint generation, conformer analysis, and batch processing with sane defaults.

Core Features & Use Cases

  • RDKit integration with a high-level API for conversions, standardization, and I/O
  • Descriptor and fingerprint computations for rapid data-driven analysis
  • 3D conformer generation and clustering to explore conformational space
  • Batch processing and parallelization to scale workflows across datasets

Quick Start

Install and start using datamol to process a small molecule quickly: convert SMILES to a Mol, compute descriptors, and generate fingerprints.

Frequently Asked Questions about datamol

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

FAQPage Schema
How do I calculate molecular descriptors and fingerprints using RDKit in Python?

Molecular descriptors and fingerprints are calculated by wrapping RDKit with a high-level Pythonic API, applying sensible defaults to compute chemical properties directly from SMILES or Mol objects. Datamol simplifies this process by handling standardization and I/O automatically.

What is the best way to batch process small molecule datasets for cheminformatics?

Batch processing for cheminformatics is handled via parallel execution across small to medium datasets, enabling scalable molecular conversions, descriptor calculations, and data pipelines. The datamol namespace processes molecules concurrently while handling errors gracefully.

Can I generate 3D conformers and cluster molecules with RDKit?

3D conformers and clustering are generated by exploring conformational space through a Pythonic RDKit wrapper. This allows researchers to compute 3D structures and group molecules efficiently for drug discovery workflows.

Does datamol support standardization and error handling for SMILES conversions?

SMILES standardization and error handling are supported by providing a Pythonic wrapper around RDKit with sane defaults. It gracefully manages errors during molecular conversions and I/O operations across data pipelines.

Are there limitations when scaling cheminformatics batch processing to large datasets?

Cheminformatics batch processing is optimized for small to medium datasets, which may present limitations when scaling to very large datasets. Parallel execution via the datamol namespace helps, but massive scale requires careful workflow management.