Can this skill handle large molecular datasets?

Yes, the skill provides patterns for parallel processing and batch computation using Datamol's built-in performance optimizations for handling large compound libraries.

Is Datamol compatible with existing RDKit objects?

Yes, Datamol functions return native rdkit.Chem.Mol objects, ensuring full compatibility with the standard RDKit ecosystem and existing scripts.

What is the Datamol skill for Claude Code?

The Datamol skill provides Claude with the specialized knowledge and implementation patterns to perform molecular cheminformatics tasks using the Datamol library, which is a simplified wrapper for RDKit.

Does Datamol support 3D conformer generation?

Yes, it includes high-level workflows for generating 3D conformers, energy minimization, and clustering based on RMSD thresholds.

Datamol Cheminformatics

Name: Datamol Cheminformatics
Author: K-Dense-AI

byK-Dense-AI

•

2,188

データサイエンスとML

Simplifies molecular cheminformatics workflows by providing a Pythonic wrapper for RDKit with sensible defaults and parallel processing.

概要

Datamol acts as a high-level abstraction layer for RDKit, making complex molecular operations accessible and efficient for scientific computing. It streamlines tasks essential for drug discovery and chemical data analysis, such as SMILES parsing, structure standardization, 3D conformer generation, and molecular descriptor computation. By returning native RDKit objects and supporting cloud storage, it integrates seamlessly into modern scientific data pipelines while maintaining full compatibility with the broader cheminformatics ecosystem.

主な機能

Molecular format conversion for SMILES, SELFIES, and InChI
High-performance batch computation of descriptors and fingerprints
Scaffold analysis and diverse subset selection for chemical libraries
2,188 GitHub stars
Automated structure standardization and chemical sanitization
Efficient 3D conformer generation with RMSD clustering

ユースケース

Performing scaffold-based partitioning for machine learning training and test sets
Generating 3D molecular structures and solvent accessible surface area (SASA) for modeling
Cleaning and standardizing large chemical datasets for drug discovery

概要

主な機能

Molecular format conversion for SMILES, SELFIES, and InChI
High-performance batch computation of descriptors and fingerprints
Scaffold analysis and diverse subset selection for chemical libraries
2,188 GitHub stars
Automated structure standardization and chemical sanitization
Efficient 3D conformer generation with RMSD clustering

ユースケース

Performing scaffold-based partitioning for machine learning training and test sets
Generating 3D molecular structures and solvent accessible surface area (SASA) for modeling
Cleaning and standardizing large chemical datasets for drug discovery