Is Datamol compatible with existing RDKit code?

Yes, Datamol returns native rdkit.Chem.Mol objects, ensuring full compatibility with the existing RDKit ecosystem while providing more readable code.

Can Datamol handle large-scale molecular datasets?

Absolutely. It features built-in parallel processing and specialized I/O modules to handle batch descriptor computation and large molecular files efficiently.

Can I use Datamol for machine learning preparation?

Yes, it is specifically designed for feature engineering, generating fingerprints, and performing scaffold-based splitting for robust ML models.

What is the Datamol skill used for?

The Datamol skill is used for molecular cheminformatics, providing a simplified interface for RDKit to handle chemical structures, descriptors, and 3D modeling within Claude Code.

Does it support 3D structure generation?

Yes, Datamol includes comprehensive modules for generating 3D conformers using methods like ETKDGv3, including energy minimization and clustering.

Datamol Cheminformatics

Name: Datamol Cheminformatics
Author: henriquescastilho

byhenriquescastilho

•

Data Science & ML

Simplifies molecular cheminformatics and drug discovery workflows with a Pythonic wrapper around RDKit.

Datamol is a specialized Claude Code skill designed to streamline molecular modeling and cheminformatics tasks. It provides a high-level, Pythonic interface for RDKit, enabling users to perform complex operations like SMILES parsing, structure standardization, 3D conformer generation, and scaffold analysis with sensible defaults. By abstracting the complexities of RDKit while maintaining native object compatibility, it accelerates drug discovery pipelines, enables efficient batch processing with parallelization, and supports modern data formats including cloud storage via fsspec.

Key Features

01Molecular format conversion for SMILES, SELFIES, InChI, and InChIKey

02Batch computation of molecular descriptors and fingerprints for ML

03High-performance 3D conformer generation and energy minimization

041 GitHub stars

05Automated structure standardization and sanitization for chemical datasets

06Scaffold analysis and fragmentation using BRICS and RECAP methods

Use Cases

01Preparing and cleaning molecular datasets for machine learning property prediction

02Conducting scaffold-based library analysis and diversity selection for drug discovery

03Generating 3D conformations and performing spatial analysis of chemical structures

Key Features

01Molecular format conversion for SMILES, SELFIES, InChI, and InChIKey

02Batch computation of molecular descriptors and fingerprints for ML

03High-performance 3D conformer generation and energy minimization

041 GitHub stars

05Automated structure standardization and sanitization for chemical datasets

06Scaffold analysis and fragmentation using BRICS and RECAP methods

Use Cases

01Preparing and cleaning molecular datasets for machine learning property prediction

02Conducting scaffold-based library analysis and diversity selection for drug discovery

03Generating 3D conformations and performing spatial analysis of chemical structures