skills.rest
felixboehm
felixboehmCOMMUNITY
Explore all skills by this author →
GitHub

molfeat

Convert chemical structures into machine learning-ready numerical formats.

Updated Mar 10, 2026
Search Tags:#machine learning#drug discovery#cheminformatics#featurization#fingerprints#molecular descriptors
One-click install
npx skills add https://github.com/felixboehm/biochem-allergy --skill molfeat-felixboehm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: molfeat
Source: https://github.com/felixboehm/biochem-allergy/tree/main/.claude/skills/molfeat
Command: npx skills add https://github.com/felixboehm/biochem-allergy --skill molfeat-felixboehm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires datamol, rdkit-pypi, torch, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the conversion of molecular structures into numerical representations essential for machine learning tasks in chemistry and drug discovery.

Core Features & Use Cases

  • Diverse Featurizers: Access over 100 featurizers including fingerprints (ECFP, MACCS), descriptors (RDKit, Mordred), and deep learning embeddings (ChemBERTa, GIN).
  • ML Integration: Seamlessly integrates with scikit-learn and PyTorch pipelines for QSAR, virtual screening, and similarity searching.
  • Use Case: You need to build a predictive model for drug toxicity. Use this Skill to generate ECFP fingerprints for your dataset and feed them into a Random Forest classifier.

Quick Start

Use the molfeat skill to generate ECFP fingerprints for the SMILES string 'CCO'.

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 to molecular fingerprints for machine learning?▼

This Skill provides over 100 featurizers to convert chemical structures into machine learning-ready numerical formats, supporting QSAR, virtual screening, and similarity analysis with deep learning embeddings like ChemBERTa.

Can I use RDKit molecular descriptors in a PyTorch pipeline?▼

Yes, this Skill integrates with PyTorch pipelines and supports calculating RDKit and Mordred descriptors, allowing you to feed molecular numerical representations directly into deep learning models.

What's the best way to generate molecular embeddings for virtual screening?▼

Generating deep learning embeddings like ChemBERTa or GIN through this Skill is an effective way to prepare molecular structures for numerical virtual screening and similarity searching tasks.

Do I need datamol and rdkit to calculate molecular descriptors?▼

Yes, datamol and rdkit are required dependencies for core functionality, providing the foundational cheminformatics operations needed to calculate molecular descriptors and structural fingerprints.

How do I build a QSAR model for drug toxicity prediction?▼

To build a predictive model for drug toxicity, use this Skill to generate ECFP fingerprints for your dataset and feed those numerical features into a scikit-learn Random Forest classifier.

Related Skills

Explore More Software Engineering Skills→
omar-A-hassanomar-A-hassan
18

datamol

Parse, standardize, and analyze molecular structures using datamol.

Community
Intermediate
sanand0sanand0
8

molfeat

Convert chemical structures into machine learning-ready numerical representations.

Community
Intermediate
SologaSologa
1

torchdrug

Create and apply PyTorch-native Graph Neural Networks for molecular and protein data analysis.

Community
Advanced
robotlearning123robotlearning123

rdkit

Analyze and manipulate molecular structures with RDKit for cheminformatics operations.

Community
Advanced