Convert SMILES or RDKit molecules into fixed-length numerical vectors for ML tasks.
npx skills add https://github.com/OwnLabAI/ownlab --skill molfeat-ownlabai
Please help me install this Agent Skill. Skill: molfeat Source: https://github.com/OwnLabAI/ownlab/tree/main/mart/skills/scientific-skills/molfeat Command: npx skills add https://github.com/OwnLabAI/ownlab --skill molfeat-ownlabai
Molfeat unifies 100+ molecular featurizers to transform chemical structures (SMILES or RDKit molecules) into machine-learning-ready vectors, accelerating cheminformatics workflows and model development.
Install molfeat, create a calculator with FPCalculator, wrap it in MoleculeTransformer, and featurize a list of SMILES.
High-intent search queries and answers about installing and using this skill.
To convert SMILES strings into numerical vectors for machine learning, use molecular featurization tools like FPCalculator and MoleculeTransformer to map chemical structures into fixed-length numeric representations ready for ML models.
For QSAR and virtual screening workflows, available molecular descriptors include ECFP, MACCS, MAP4, Mordred, RDKit descriptors, and pretrained embeddings like ChemBERTa, ChemGPT, and MolT5 for downstream model training.
Yes, you can use pretrained transformer models like ChemGPT to extract molecular embeddings by unlocking advanced featurizers through optional dependencies, enabling numeric vector generation for downstream ML tasks.
Batch processing of molecular featurizers works with sklearn pipelines by wrapping calculators in a MoleculeTransformer, enabling you to featurize large lists of SMILES and integrate them into end-to-end ML workflows.
You can combine multiple molecular featurizers into a single numeric vector by using FeatConcat, which concatenates outputs from different calculators to create unified representations for similarity searching and QSAR modeling.
To unlock graph-based featurizers like Graphormer, you need to install optional dependencies such as molfeat[graphormer] or molfeat[dgl], which extend the core library to support advanced graph neural network representations.
SologaConvert SMILES strings into over 100 molecular fingerprints and descriptors.
shushuznConvert SMILES or RDKit molecules into numerical feature vectors for machine learning.
Yezez9Convert SMILES strings and RDKit molecules into ML-ready feature representations.
rubenslivConvert chemical structures into machine-learning-ready feature vectors for ML workflows.
