chao1224/GeoSSL
GeoSSL: Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching, ICLR'23 (https://openreview.net/forum?id=CjTHVo1dvR)
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.
Stars
47
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
MinkaiXu/GeoDiff
Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).
MinkaiXu/GeoLDM
Geometric Latent Diffusion Models for 3D Molecule Generation
caio-freitas/GraphARM
An implementation of the Autoregressive Diffusion Model for Graph Generation from [Kong et al. 2023]
microsoft/foldingdiff
Diffusion models of protein structure; trigonometry and attention are all you need!
Membrizard/ml_conformer_generator
Shape-constrained molecule generation via Equivariant Diffusion and GCN