Convert SMILES and RDKit molecules into numerical feature vectors.
npx skills add https://github.com/dralkh/seerai --skill molfeat-dralkh
Please help me install this Agent Skill. Skill: molfeat Source: https://github.com/dralkh/seerai/tree/main/skills/molfeat Command: npx skills add https://github.com/dralkh/seerai --skill molfeat-dralkh
Molfeat turns molecular structures into consistent numerical features, removing the friction of manual featurization for machine learning, similarity search, and chemistry workflows.
Ask the molfeat skill to convert your SMILES list into the most appropriate molecular features for your model and explain which calculator or pretrained transformer to use.
High-intent search queries and answers about installing and using this skill.
Molecular featurization transforms SMILES strings into numerical vectors using fingerprints, descriptors, or pretrained embeddings. This Skill handles batch SMILES processing with parallel execution to produce ML-ready features for QSAR modeling and virtual screening.
Generating ECFP and MACCS fingerprints for virtual screening requires a featurization calculator that processes molecular structures into bit vectors. This Skill supports multiple fingerprint formats and parallel batch processing for fast similarity ranking and screening workflows.
Yes, pretrained molecular embeddings like ChemBERTa, ChemGPT, and Graphormer can be loaded for QSAR modeling. This Skill integrates pretrained transformer models to generate learned molecular representations that capture structural semantics for property prediction tasks.
This molecular featurization tool supports both SMILES strings and RDKit molecule objects as input formats. It processes these structures through calculators and transformers to output numerical feature vectors suitable for clustering and similarity search applications.
Featurizing large SMILES collections with parallel batch processing involves passing molecular lists through a configured pipeline with caching and error handling. This Skill executes batch featurization while maintaining reproducible saved configurations for research pipeline consistency.
Molecular descriptors provide interpretable 2D and 3D property sets for QSAR and scaffold analysis, while fingerprints like ECFP offer fast structural screening. Use descriptors when you need explainable physicochemical properties and fingerprints for rapid similarity ranking workflows.
robotlearning123Convert SMILES strings or RDKit molecules into numerical molecular features.
crazymsnConvert molecular structures into ML-ready feature vectors across hundreds of featurizers.
jaechang-hitsCalculate molecular descriptors and assess drug-likeness with RDKit.
rubenslivConvert chemical structures into machine-learning-ready feature vectors for ML workflows.
