SE(3) diffusion model with application to protein backbone generation

By Jason Yim, Brian L. Trippe, Valentin De Bortoli, Emile Mathieu, Arnaud Doucet, Regina Barzilay, Tommi S. Jaakkola. 2023

343 citations recorded by the source corpus.

The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry. In this line of work, a diffusion model over rigid bodies in 3D (referred to as frames) has shown success in generating novel, functional protein backbones that have not been observed in nature. However, there exists no principled methodological framework for diffusion on SE(3), the space of orientation preserving rigid motions in R3, that operates on frames and confers the group invariance. We address these shortcomings by developing theoretical foundations of SE(3) invariant diffusion models on multiple frames followed by a novel framework, FrameDiff, for learning the SE(3) equivariant score over multiple frames. We apply FrameDiff on monomer backbone generation and find it can generate designable monomers up to 500 amino acids without relying on a pretrained protein structure prediction network that has been integral to previous methods. We find our samples are capable of generalizing beyond any known protein structure.

Subfields: Molecular Biology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (2022, background): “Journal of chemical information and modeling , 62(5):1308–1317, 2022.”
Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds (2023, methodology): “Nearly contemporaneous with this work, three other methods reported performant DDPMs for protein design inspired by similar ideas (Ingraham et al., 2022; Watson et al., 2022; Yim et al., 2023), although their architectural details and training procedures are distinct from Genie’s.”
Practical and Asymptotically Exact Conditional Sampling in Diffusion Models (2023, unknown): “Next, 1 − ᾱt = Var[x | x] and σ̄(2) t is the time of the Brownian motion associated with the forward process at step t [34].”