chao1224/GeoSSL

GeoSSL: Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching, ICLR'23 (https://openreview.net/forum?id=CjTHVo1dvR)

29
/ 100
Experimental

This project helps computational chemists and drug discovery scientists by improving how computers understand complex 3D molecular structures. It takes raw molecular conformation data and produces more accurate and robust representations of these molecules, which can then be used to predict properties or interactions. The end-user is typically someone working with molecular simulations, drug design, or materials science.

No commits in the last 6 months.

Use this if you need to develop more accurate machine learning models for predicting molecular properties or interactions based on their 3D geometry.

Not ideal if your primary interest is 2D molecular graphs, or if you don't have access to 3D conformation data for your molecules.

molecular-modeling drug-discovery materials-science computational-chemistry protein-ligand-binding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

47

Forks

2

Language

Python

License

MIT

Last pushed

Jul 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/chao1224/GeoSSL"

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