MinkaiXu/GeoDiff
Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).
Applies diffusion-based sampling in 3D geometric space using equivariant graph neural networks to generate diverse molecular conformations from molecular graphs. Supports end-to-end training on GEOM datasets with PyTorch Geometric, offering evaluation metrics for both conformation quality (COV/MAT scores) and downstream property prediction tasks. Includes pretrained checkpoints for QM9 and drug-like molecules with configurable sampling strategies.
406 stars. No commits in the last 6 months.
Stars
406
Forks
87
Language
Python
License
MIT
Category
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.
Related models
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!
aqlaboratory/genie
De Novo Protein Design by Equivariantly Diffusing Oriented Residue Clouds
pengxingang/MolDiff
MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation