kiharalab/DiffModeler
DiffModeler: a diffusion model based protein complex structure modeling tool.
DiffModeler helps structural biologists and biochemists automatically build complete protein complex structures from cryo-electron microscopy (cryo-EM) data. You input a cryo-EM map (an image representing electron density) and, optionally, individual protein chain structures or sequences. The tool then outputs a high-accuracy 3D model of the assembled protein complex, even when the cryo-EM data is at challenging intermediate to low resolutions.
Use this if you need to accurately model the 3D structure of multi-chain protein complexes from cryo-EM maps, especially at intermediate (5-10 Å) or even lower (10-20 Å) resolutions where traditional methods struggle.
Not ideal if you are working with extremely high-resolution cryo-EM maps (better than 2 Å) where diffusion model-based backbone tracing might not be necessary, or if you lack access to GPU hardware.
Stars
58
Forks
5
Language
Python
License
—
Category
Last pushed
Jan 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kiharalab/DiffModeler"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gcorso/DiffDock
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
arneschneuing/DiffSBDD
A Euclidean diffusion model for structure-based drug design.
gcorso/torsional-diffusion
Implementation of Torsional Diffusion for Molecular Conformer Generation (NeurIPS 2022)
igashov/DiffLinker
DiffLinker: Equivariant 3D-Conditional Diffusion Model for Molecular Linker Design
BioinfoMachineLearning/bio-diffusion
A geometry-complete diffusion generative model (GCDM) for 3D molecule generation and...