Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
Datamol is a specialized Python library designed to provide a simplified interface over RDKit, catering specifically to the needs of chemoinformatics and drug discovery. By abstracting away the complexities of molecular operations, Datamol empowers users to efficiently perform tasks such as SMILES parsing, structure standardization, and descriptor calculations with sensible defaults. This skill alleviates the burden on chemists and data scientists who seek to manipulate molecular data without delving into the intricacies of RDKit directly, allowing them to focus on their research and analyses instead.
Datamol serves as a Pythonic wrapper around RDKit, offering a simplified interface for molecular cheminformatics operations.
Datamol is designed to work with the RDKit ecosystem, but users should ensure they are using compatible versions for optimal functionality.
Datamol supports various molecular formats including SMILES, SELFIES, InChI, and can read/write files in SDF, CSV, and Excel formats.
Yes, Datamol offers support for reading from and writing to cloud storage solutions like S3 and GCS.
While Datamol simplifies many operations, for advanced control or custom parameters, users may need to utilize RDKit directly.
Quick Setup:
.claude/skills/Repository
K-Dense-AI/claude-scientific-skills