molfeat - Molecular featurization for machine learning
Converts SMILES strings or RDKit molecules into fingerprints, descriptors, and pretrained embeddings for molecular machine learning.
Tags
Updated: 2026-09-29Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Convert molecular structures to features
- Process molecular batches in parallel
- Load pretrained molecular embeddings
- Combine multiple featurizers
- Save featurizer configurations
- Handle invalid molecular inputs
- Search available featurizers
Inputs
- SMILES strings
- RDKit molecules
- Molecular datasets
- Featurizer configurations
- Pretrained model names
Outputs
- Molecular feature arrays
- Pretrained molecular embeddings
- Similarity scores
- Saved YAML configuration files
- Available model listings
Requirements
- Python environment
- molfeat package
- Optional featurizer dependencies
- scikit-learn for pipeline integration