Curtis-Wu/Equivariant-Graph-Transformer

A deep neural network with hybrid architecture (EGNN + Transformer) for molecular properties prediction.

25
/ 100
Experimental

This project helps chemists and materials scientists predict molecular potential energy. You provide molecular structures, including atom types and their coordinates, and it outputs an estimated potential energy for that molecule. It's designed for researchers working with molecular simulations or drug discovery who need to quickly assess molecular stability and reactivity.

No commits in the last 6 months.

Use this if you need to accurately predict the potential energy of molecules based on their atomic structure to understand their behavior.

Not ideal if you are looking for a general-purpose graph transformer that operates on arbitrary graph data, as this is specifically tailored for molecular potential prediction.

molecular-modeling computational-chemistry materials-science drug-discovery quantum-chemistry
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

23

Forks

3

Language

Jupyter Notebook

License

Last pushed

Dec 09, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Curtis-Wu/Equivariant-Graph-Transformer"

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