molfeat

Convert SMILES strings or RDKit molecules into numerical molecular features.

Updated Dec 17, 2025
One-click install
npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill molfeat-robotlearning123
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: molfeat
Source: https://github.com/robotlearning123/claude-scientific-skills/tree/main/scientific-skills/molfeat
Command: npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill molfeat-robotlearning123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires molfeat, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Molfeat solves the problem of converting chemical structures into numerical representations suitable for machine learning tasks like QSAR modeling, virtual screening, and deep learning.

Core Features & Use Cases

  • Molecular Featurization: Convert SMILES strings or RDKit molecules into numerical features.
  • 100+ Featurizers: Offers a comprehensive library of pre-trained embeddings and hand-crafted featurizers.
  • Deep Learning Ready: Provides state-of-the-art molecular embeddings for deep learning applications.
  • Use Case: Imagine you are developing a QSAR model for predicting drug activity. Use Molfeat to generate molecular features for your machine learning model.

Quick Start

Load your molecular data and use the molfeat skill to generate features for a molecule:

molfeat --smiles "CCO" --feature "ecfp"

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 numerical features for QSAR modeling?

To convert SMILES strings to numerical features for QSAR modeling, you can use molecular featurization to transform chemical structures into numerical representations suitable for machine learning tasks.

What is the best way to generate molecular embeddings for deep learning?

Generating molecular embeddings for deep learning involves converting chemical structures into numerical vectors. This Skill provides state-of-the-art pretrained embeddings and hand-crafted featurizers to transform SMILES strings into deep learning ready representations.

Can I use RDKit molecules as input for virtual screening featurization?

Yes, virtual screening featurization supports RDKit molecules as input. It converts RDKit molecule objects directly into numerical features using various featurization techniques and pretrained models for similarity searching.

Does molecular featurization support pretrained models for chemical structure conversion?

Molecular featurization supports pretrained models for chemical structure conversion. It offers a comprehensive library of pre-trained embeddings alongside hand-crafted featurizers to generate numerical representations from SMILES strings.

Do I need the molfeat package to compute ECFP features from SMILES?

Yes, you need the molfeat package installed to compute ECFP features from SMILES strings. The package provides the featurization techniques and pretrained models required to generate numerical representations for machine learning tasks.

Why use pretrained molecular embeddings instead of hand-crafted featurizers for similarity searching?

Pretrained molecular embeddings capture learned chemical structure representations for similarity searching, while hand-crafted featurizers use predefined rules. Pretrained models often provide state-of-the-art numerical representations suited for deep learning applications.

Related Skills