liugangcode/torch-molecule

torch-molecule is a deep learning package for molecular discovery, designed with an sklearn-style interface for property prediction, inverse design and representation learning.

54
/ 100
Established

This package helps scientists and researchers in chemistry, biology, and materials science quickly build and deploy deep learning models for molecular discovery. You input molecular structures (like SMILES strings) and the system helps predict their properties, generate new molecules, or learn their fundamental characteristics. It's designed for anyone working with molecular data who needs to leverage advanced AI without deep machine learning expertise.

314 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a scientist or researcher looking to apply deep learning to molecular data for tasks like predicting drug properties, designing new materials, or understanding chemical reactions.

Not ideal if you need a no-code solution or if your primary focus is on fundamental research in deep learning model architectures rather than molecular applications.

drug-discovery materials-science cheminformatics molecular-design bioinformatics
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

314

Forks

38

Language

Python

License

MIT

Last pushed

Oct 08, 2025

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/liugangcode/torch-molecule"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.