microsoft/foldingdiff
Diffusion models of protein structure; trigonometry and attention are all you need!
This tool helps computational biologists and protein engineers generate novel protein backbone structures. You provide desired length ranges, and it outputs 3D atomic coordinates (.pdb files) of entirely new protein structures, as well as plots comparing generated and known structures. It's designed for researchers exploring new protein designs or validating computational protein generation methods.
565 stars. No commits in the last 6 months.
Use this if you need to computationally generate diverse, realistic protein backbone structures for research or design purposes.
Not ideal if you need to predict the structure of an existing protein sequence or evaluate the functional properties of generated proteins.
Stars
565
Forks
73
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/microsoft/foldingdiff"
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]
Membrizard/ml_conformer_generator
Shape-constrained molecule generation via Equivariant Diffusion and GCN
aqlaboratory/genie
De Novo Protein Design by Equivariantly Diffusing Oriented Residue Clouds