pfizer-opensource/symmetry-induced-score-matching

Official implementation of the NeurIPS 25 Paper: "Diffusion Generative Modeling on Lie Group Representations"

24
/ 100
Experimental

This project offers a new way to create complex molecular structures and model how molecules interact, like in drug discovery. It takes in existing molecular data and generates new, plausible molecular conformers or predicts how ligands bind to proteins. Chemists and computational biologists who design new drugs or study molecular behavior would find this useful.

Use this if you need to generate realistic 3D molecular structures or predict precise molecular docking poses with higher accuracy and efficiency than current methods.

Not ideal if your work doesn't involve complex molecular transformations or you are working with simpler, non-geometric data.

molecular-design drug-discovery computational-chemistry protein-ligand-docking conformer-generation
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Jupyter Notebook

License

Last pushed

Dec 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/pfizer-opensource/symmetry-induced-score-matching"

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