molfeat

Convert SMILES strings into numerical features for machine learning.

3|Updated Apr 17, 2026

Search Tags:#machine learning #virtual screening #featurization #QSAR #molecular

Ready to run

npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill molfeat-ramanebrahimi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: molfeat
Source: https://github.com/RamanEbrahimi/raman-marketplace/tree/main/plugins/agentic-research/skills/scientific-skills/molfeat
Command: npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill molfeat-ramanebrahimi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires molfeat[all], rdkit, numpy, scikit-learn, torch, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Molfeat automates molecular featurization for machine learning tasks, making complex molecular analysis faster and more efficient.

Core Features & Use Cases

Featurization: Converts chemical structures into numerical representations.
Transformers: Handles batch processing with parallelization for scalability.
Deep Learning Embeddings: Pre-trained models for transfer learning in molecular AI.
Use Case: Imagine you have a collection of compounds for virtual screening. Use molfeat to preprocess the data, featurize the molecules, and then apply machine learning models to predict their properties.

Quick Start

Run the molfeat skill to convert a SMILES string to features for machine learning analysis:

uv molfeat "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 numerical features for machine learning?▼

To convert SMILES strings to features, run the molfeat skill with the SMILES string as an argument, such as `uv molfeat "CCO"`. This outputs numerical representations ready for model training.

Can I use scikit-learn and PyTorch with molecular featurization workflows?▼

Yes, molecular featurization workflows are compatible with scikit-learn and PyTorch. The molfeat skill integrates with these libraries to apply machine learning models and deep learning embeddings to chemical data.

What is the best way to preprocess compounds for virtual screening at scale?▼

The best way to preprocess compounds for virtual screening at scale is using transformers that handle batch processing with parallelization. This ensures your molecular featurization remains scalable for large datasets.

Do I need RDKit installed to calculate molecular descriptors?▼

Yes, you need RDKit installed to calculate molecular descriptors. The molfeat skill requires RDKit, numpy, scikit-learn, and torch as dependencies to perform featurization and preprocessing tasks.

Does QSAR modeling require pre-trained deep learning models?▼

QSAR modeling can utilize pre-trained deep learning models for transfer learning in molecular AI. The molfeat skill provides these embeddings to enhance property prediction without training models from scratch.