Convert SMILES or RDKit molecules into numerical feature vectors for machine learning.
npx skills add https://github.com/shushuzn/Rairos --skill molfeat-shushuzn
Please help me install this Agent Skill. Skill: molfeat Source: https://github.com/shushuzn/Rairos/tree/main/skills/molfeat Command: npx skills add https://github.com/shushuzn/Rairos --skill molfeat-shushuzn
This Skill removes the heavy lifting required to convert chemical structures into numeric features, so you can focus on modeling instead of featurization plumbing.
Featurize a list of SMILES into an ECFP representation using molfeat’s MoleculeTransformer for parallel batch processing.
High-intent search queries and answers about installing and using this skill.
Converting SMILES strings into molecular fingerprints for QSAR modeling is done by using molfeat's MoleculeTransformer, which transforms chemical structures into fixed-length numerical vectors. It applies scikit-learn compatible batch featurization to support parallel processing across large molecular datasets.
Yes, you can generate pretrained molecular embeddings like ChemBERTa for virtual screening. The Skill supports extracting embeddings from pretrained models like ChemGPT and graph-based GNNs, providing numerical feature vectors for downstream similarity searching, ranking, and QSAR tasks.
The best way to batch featurize large molecular datasets with scikit-learn is using molfeat's parallelized transformers. These transformers wrap 100+ calculators, including ECFP and Mordred descriptors, enabling dataset-wide transformations that integrate directly into existing scikit-learn pipelines.
Yes, this molecular featurization approach supports both 2D and 3D chemical descriptors. The unified catalog includes RDKit and Mordred descriptors alongside pharmacophore and shape features, allowing you to convert RDKit molecules into diverse numerical feature vectors for chemical space analysis.
You need to handle errors when converting SMILES to numerical feature vectors because invalid molecular structures can disrupt batch featurization. The Skill includes built-in error handling and caching to manage invalid inputs gracefully, ensuring machine learning pipelines remain robust across large datasets.
Yezez9Convert SMILES strings and RDKit molecules into ML-ready feature representations.
fuzzy-dynamicsConvert SMILES or RDKit molecules into numerical feature vectors for ML pipelines.
pradyumnasagarAutomate QSAR/QSPR model construction for bioassay and ADMET prediction.
SologaConvert SMILES strings into over 100 molecular fingerprints and descriptors.
