Simplifies molecular cheminformatics and drug discovery workflows using a Pythonic interface for RDKit.
Datamol provides a lightweight, high-level abstraction layer over RDKit, making complex molecular operations accessible through sensible defaults and modern Python patterns. It enables researchers and developers to handle SMILES parsing, structure standardization, 3D conformer generation, and parallelized molecular descriptor computation with minimal boilerplate. By returning native RDKit objects, it ensures seamless integration with the broader scientific computing ecosystem while significantly accelerating common tasks in drug discovery and chemical data analysis.
주요 기능
01Molecular format conversion for SMILES, InChI, and SELFIES
02Advanced scaffold analysis and molecular fragmentation
033D conformer generation with UFF force field minimization
04Batch processing with built-in parallelization and progress tracking
05Structure standardization and sanitization for high-quality datasets
061 GitHub stars
사용 사례
01Identifying lead compounds through structural clustering and scaffold analysis
02Generating 3D molecular structures for docking and simulation workflows
03Preparing and cleaning large chemical datasets for machine learning models
