molfeat
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
Security Assessment
About molfeat
Molfeat is a powerful Python library designed for molecular featurization, enabling users to convert chemical structures—represented as SMILES strings or RDKit molecules—into numerical feature representations suitable for machine learning applications. This skill addresses the challenges faced in molecular machine learning by providing over 100 pre-trained embeddings and handcrafted featurizers, streamlining the process of feature extraction for tasks such as QSAR modeling, virtual screening, and similarity searching. By offering a unified platform for various featurization techniques, Molfeat enhances the efficiency and accuracy of molecular data analysis.
FAQ
How do I install Molfeat?
You can install Molfeat using pip: `pip install molfeat` or with optional dependencies using `pip install 'molfeat[all]'`.
Can I use Molfeat for batch processing of molecular data?
Yes, Molfeat provides Scikit-learn compatible transformers that allow for batch processing and parallelization.
What types of molecular representations does Molfeat support?
Molfeat supports SMILES strings and RDKit `Chem.Mol` objects for molecular representation.
Is there support for deep learning models in Molfeat?
Yes, Molfeat includes pretrained transformers for state-of-the-art molecular embeddings and transfer learning.
Are there any specific dependencies required for certain features?
Yes, optional dependencies are available for specific featurizers, such as GNN models and ChemBERTa.
Install molfeat
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
davila7/claude-code-templates