MinkaiXu/GeoDiff

Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).

49
/ 100
Emerging

This project helps chemists and drug designers generate diverse and realistic 3D atomic structures (conformations) for molecules. You input a molecule's basic chemical structure, and it outputs multiple possible 3D shapes the molecule could adopt. This is ideal for researchers in drug discovery, materials science, or computational chemistry who need to explore molecular geometry.

406 stars. No commits in the last 6 months.

Use this if you need to computationally predict a variety of stable 3D arrangements for a given molecule to understand its behavior or design new compounds.

Not ideal if you are looking for a tool to simulate molecular dynamics or predict specific interactions between molecules.

computational chemistry drug design molecular modeling materials science cheminformatics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

406

Forks

87

Language

Python

License

MIT

Last pushed

May 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MinkaiXu/GeoDiff"

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