molfeat

Name: molfeat
Availability: InStock
Author: robinbarvaag

Convert molecular structures into numerical features using over 100 featurizers.

Updated Jan 10, 2026

Search Tags:#machine learning #deep learning #cheminformatics #fingerprints #descriptors #molecular featurization

Ready to run

npx skills add https://github.com/robinbarvaag/poynt --skill molfeat-robinbarvaag

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: molfeat
Source: https://github.com/robinbarvaag/poynt/tree/main/.github/skills/molfeat
Command: npx skills add https://github.com/robinbarvaag/poynt --skill molfeat-robinbarvaag

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies and standardizes the process of converting molecular structures into numerical features required for machine learning models.

Core Features & Use Cases

100+ Featurizers: Access a vast library of fingerprints, descriptors, and deep learning embeddings.
Batch Processing: Efficiently featurize large datasets in parallel.
Use Case: Convert thousands of SMILES strings into ECFP fingerprints for use in a QSAR modeling pipeline.

Quick Start

Use the molfeat skill to convert the SMILES string 'CCO' into ECFP features.

Frequently Asked Questions about molfeat

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert SMILES strings into molecular fingerprints for machine learning?▼

To convert SMILES strings into molecular fingerprints for machine learning, you can use a unified featurization interface that transforms molecular structures into numerical features like ECFP for ML pipelines. This Skill supports batch processing of thousands of molecules efficiently.

What is molecular featurization and when do I need it for cheminformatics?▼

Molecular featurization is the process of converting molecular structures into numerical features for ML models. You need it for cheminformatics tasks like QSAR modeling, virtual screening, and similarity searching, using pre-trained featurizers like descriptors or deep learning embeddings.

Can I use scikit-learn with molecular descriptors for QSAR modeling?▼

Yes, you can use scikit-learn with molecular descriptors for QSAR modeling. This featurization interface is scikit-learn compatible, allowing seamless integration of over 100 pre-trained fingerprints and descriptors into your existing ML frameworks and QSAR pipelines.

Does batch processing work for large datasets of deep learning embeddings?▼

Batch processing works for large datasets of deep learning embeddings by featurizing molecules in parallel. This allows you to efficiently convert thousands of molecular structures into deep learning embeddings or fingerprints required for your machine learning models.

What's the best way to standardize molecular featurization across different ML models?▼

The best way to standardize molecular featurization across ML models is using a unified interface offering over 100 pre-trained featurizers, including fingerprints, descriptors, and deep learning embeddings, ensuring consistent numerical feature generation for various ML frameworks.

How does virtual screening benefit from pre-trained molecular descriptors?▼

Virtual screening benefits from pre-trained molecular descriptors by quickly converting large libraries of molecular structures into numerical features for similarity searching. Using over 100 available featurizers, you can efficiently batch process molecules and feed them directly into ML models.