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

TL;DR

This paper introduces FrameDiff, a novel SE(3) invariant diffusion model for protein backbone generation that operates directly on frames, enabling the creation of new, designable protein structures without pretrained networks.

Contribution

The paper develops a theoretical framework for SE(3) invariant diffusion on multiple frames and introduces FrameDiff, a new method for protein backbone generation that is group-equivariant and structure-agnostic.

Findings

Successfully generated monomer backbones up to 500 amino acids.

Samples can generalize beyond known protein structures.

Operates without pretrained structure prediction networks.

Abstract

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.