Transform SMILES strings into feature vectors using molecular featurizers.
npx skills add https://github.com/tassiovale/claude-code-kit --skill molfeat-tassiovale
Please help me install this Agent Skill. Skill: molfeat Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/molfeat Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill molfeat-tassiovale
Molfeat solves the challenge of transforming complex molecular information from SMILES strings into feature vectors, suitable for a variety of machine learning applications.
Use the molfeat skill to transform the SMILES string 'CCO' into a feature vector.
High-intent search queries and answers about installing and using this skill.
To convert SMILES strings to feature vectors for machine learning, you can use molecular featurization tools that support over 100 featurizers including ECFP, MACCS, and pretrained models like ChemBERTa for QSAR and virtual screening.
Molecular featurizers for QSAR modeling include ECFP, MACCS keys, chemical descriptors, and pretrained transformer models like ChemBERTa, providing diverse numerical representations from SMILES strings.
Yes, you can use ChemBERTa and GNN models for molecular featurization with PyTorch, requiring optional extras installation alongside datamol to support deep learning applications.
Yes, transforming SMILES strings into numerical representations requires Python 3.9 or 3.10, along with datamol and PyTorch dependencies to execute the molecular featurization pipeline.
The best way to generate molecular descriptors for virtual screening is using a featurization library that offers 100+ featurizers, converting chemical structures directly into numerical feature vectors for deep learning and predictive modeling.
When using pretrained models like ChemBERTa for SMILES to features conversion, limitations include requiring optional extras for GNN and transformer models, and strict dependency on Python 3.9–3.10 environments.
jasrajtulsiConvert molecular structures into machine-learning-ready feature vectors for cheminformatics workflows.
AlterLab-IEUConvert SMILES and RDKit molecules into machine-learning-ready feature vectors.
felixboehmConvert chemical structures into machine learning-ready numerical formats.
felixboehmCalculate molecular descriptors and generate fingerprints from SMILES strings using RDKit.
