datamol - Perform Pythonic cheminformatics with Datamol
Provides a simplified Python interface to RDKit for molecular formats, standardization, descriptors, fingerprints, conformers, clustering, and cheminformatics workflows.
Tags
Updated: 2026-10-07Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Parse molecular formats
- Standardize molecular structures
- Compute descriptors and fingerprints
- Generate and analyze conformers
- Cluster molecules and select diversity
- Analyze scaffolds and fragments
- Apply chemical reactions
- Visualize and align molecules
- Process batches in parallel
- Read and write molecular files
- Support cloud storage via fsspec
Inputs
- Molecular strings
- Molecular files
- Molecule datasets
- Query and library molecules
- Output paths
- Cloud storage URLs
- Processing parameters
Outputs
- Native RDKit Mol objects
- Converted molecular representations
- Standardized molecules
- Descriptor and fingerprint results
- Conformer data
- Clusters and diverse selections
- Scaffold and fragment analyses
- Chemical reaction results
- Molecular visualizations and alignments
- Written molecular files
Requirements
- Python 3.8 or newer
- datamol installed
- RDKit dependency
- s3fs or gcsfs for cloud I/O