masa-ue/AlignInversePro
Inference-Time Alignment in Protein Diffusion Models
This project helps protein engineers and computational biologists design novel protein sequences that fold into specific desired 3D backbone structures. You provide a protein backbone structure and define desired properties like stability or structural accuracy. The project then generates one or more protein sequences (output as PDB files) that are optimized to meet those criteria, along with performance statistics.
Use this if you need to design protein sequences that accurately fold into a specific backbone structure and exhibit particular biophysical properties, iterating on designs quickly.
Not ideal if you are looking for a tool to predict protein structure from a given sequence, or if you only need a basic inverse folding model without multi-objective optimization.
Stars
56
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/masa-ue/AlignInversePro"
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