Convert chemical structures into machine learning-ready numerical representations.
npx skills add https://github.com/sanand0/scientific-research --skill molfeat-sanand0
Please help me install this Agent Skill. Skill: molfeat Source: https://github.com/sanand0/scientific-research/tree/main/.claude/skills/molfeat Command: npx skills add https://github.com/sanand0/scientific-research --skill molfeat-sanand0
This Skill streamlines the process of converting complex molecular structures into numerical representations suitable for machine learning models, accelerating cheminformatics and drug discovery workflows.
Use the molfeat skill to generate ECFP fingerprints for the provided SMILES strings.
High-intent search queries and answers about installing and using this skill.
Molecular featurization converts chemical structures like SMILES strings into numerical representations. This Skill provides a unified interface to generate fingerprints such as ECFP and MACCS, making molecules ready for ML pipelines.
Deep learning embeddings for cheminformatics include ChemBERTa and GIN. This featurization Skill integrates these embeddings alongside traditional descriptors like RDKit and Mordred to support QSAR and virtual screening tasks.
Molecular descriptors and fingerprints can be used directly in scikit-learn and PyTorch pipelines. This Skill seamlessly integrates featurization outputs with these frameworks for predictive modeling and molecular similarity searching.
Featurizing thousands of drug-like molecules for QSAR modeling is streamlined through this Skill. It provides a unified interface to quickly generate numerical representations like ECFP fingerprints for large sets of chemical structures.
Molecular featurization supports both structural fingerprints and physicochemical descriptors. Access over 100 featurizers including ECFP, MACCS, RDKit, and Mordred descriptors to represent chemical structures for diverse machine learning applications.
Deep learning embeddings capture complex molecular representations beyond ECFP fingerprints. This Skill provides both options for virtual screening, allowing you to choose between traditional fingerprints and deep learning embeddings based on model requirements.
jaechang-hitsConvert SMILES strings into numerical representations using over 100 featurizers.
K-Dense-AIConvert molecular structures into fixed-length numerical representations for machine learning.
robinbarvaagConvert molecular structures into numerical features using over 100 featurizers.
SciMate-AIFeaturize SMILES molecules into ML-ready vectors for QSAR modeling.
