What molecular formats does Molfeat support?

Molfeat primarily handles SMILES strings and RDKit molecule objects, enabling easy conversion from common chemical data formats into numerical vectors.

How does Molfeat handle large chemical datasets?

It utilizes multi-core parallel processing (via n_jobs) and efficient caching mechanisms to process thousands of molecules quickly and reliably.

Can I save my featurization settings for later use?

Yes, Molfeat allows you to export your transformer's state to a YAML file, ensuring your featurization process is consistent and reproducible across different sessions.

Which deep learning models are available in Molfeat?

It supports several pre-trained models including ChemBERTa, ChemGPT, MolT5, and various Graph Neural Networks (GNNs) like GIN and Graphormer.

Is Molfeat compatible with Scikit-learn?

Yes, Molfeat's MoleculeTransformer is designed to be fully compatible with Scikit-learn's API, allowing it to be used directly in ML pipelines.

Molfeat Molecular Featurization

Name: Molfeat Molecular Featurization
Author: Activer007

byActiver007

数据科学与机器学习

Converts chemical structures into numerical representations for molecular machine learning and drug discovery workflows.

关于

Molfeat is a comprehensive Python library integrated as a Claude Code skill that unifies over 100 pre-trained embeddings and hand-crafted featurizers into a single interface. It allows users to effortlessly convert molecular representations like SMILES strings or RDKit molecules into ML-ready feature vectors using fingerprints, descriptors, or state-of-the-art deep learning models such as ChemBERTa and Graphormer. Designed for research and production, it features scikit-learn compatibility, parallel processing, and configuration persistence, making it an essential tool for QSAR modeling, virtual screening, and chemical space exploration.

主要功能

Access to 100+ featurizers including ECFP, MACCS, and RDKit descriptors
Scikit-learn compatible transformers for seamless ML pipeline integration
Pre-trained deep learning embeddings from ChemBERTa, ChemGPT, and MolT5
High-performance parallel processing for large-scale molecular datasets
Configuration management via YAML for reproducible scientific workflows
0 GitHub stars

使用场景

Analyzing chemical space through clustering, visualization, and similarity searching
Executing large-scale virtual screening to identify potential drug candidates
Developing QSAR/QSPR models to predict chemical properties and biological activities

关于

主要功能

Access to 100+ featurizers including ECFP, MACCS, and RDKit descriptors
Scikit-learn compatible transformers for seamless ML pipeline integration
Pre-trained deep learning embeddings from ChemBERTa, ChemGPT, and MolT5
High-performance parallel processing for large-scale molecular datasets
Configuration management via YAML for reproducible scientific workflows
0 GitHub stars

使用场景

Analyzing chemical space through clustering, visualization, and similarity searching
Executing large-scale virtual screening to identify potential drug candidates
Developing QSAR/QSPR models to predict chemical properties and biological activities