GRAPH-0/JODO
Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation
This project helps chemists and materials scientists generate novel drug-like molecules with specific desired properties. By taking existing molecular data (like QM9 or GEOM-Drugs) as input, it creates new, stable 2D bond graphs and 3D atomic structures. The output is a list of RDKit molecule objects, which are widely used for molecular analysis and drug discovery workflows.
No commits in the last 6 months.
Use this if you need to computationally design new chemical compounds or drug candidates with precise structural and quantum chemical characteristics.
Not ideal if you are looking for a simple, off-the-shelf application to visualize existing molecules or perform basic property calculations without generating new structures.
Stars
52
Forks
9
Language
Python
License
MIT
Category
Last pushed
Nov 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/GRAPH-0/JODO"
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