ADicksonLab/AGDIFF

Implementation of AGDIFF: Attention-Enhanced Diffusion for Molecular Geometry Prediction

24
/ 100
Experimental

This project helps computational chemists and materials scientists predict the 3D shapes (molecular geometries) of molecules. You input a molecule's basic structure, and it outputs a set of likely 3D arrangements of its atoms. This is useful for researchers who need to understand how molecules behave and interact.

No commits in the last 6 months.

Use this if you need to accurately generate or predict the stable 3D conformations of various molecules for research or design purposes.

Not ideal if you need to simulate complex molecular dynamics or interactions over time, as this focuses on static geometry prediction.

computational-chemistry materials-science drug-discovery molecular-modeling conformer-generation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Jun 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ADicksonLab/AGDIFF"

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