Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

Abstract

Construction of a scaffold structure that supports a desired motif, conferring protein function, shows promise for the design of vaccines and enzymes. But a general solution to this motif-scaffolding problem remains open. Current machine-learning techniques for scaffold design are either limited to unrealistically small scaffolds (up to length 20) or struggle to produce multiple diverse scaffolds. We propose to learn a distribution over diverse and longer protein backbone structures via an E(3)-equivariant graph neural network. We develop SMCDiff to efficiently sample scaffolds from this distribution conditioned on a given motif; our algorithm is the first to theoretically guarantee conditional samples from a diffusion model in the large-compute limit. We evaluate our designed backbones by how well they align with AlphaFold2-predicted structures. We show that our method can (1) sample scaffolds up to 80 residues and (2) achieve structurally diverse scaffolds for a fixed motif.

Appearing in ICLR 2023. Code available: github.com/blt2114/ProtDiff_SMCDiff

Cited by in corpus (4)

• Time Series Diffusion Method: A Denoising Diffusion Probabilistic Model for Vibration Signal Generation
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Monte Carlo guided Diffusion for Bayesian linear inverse problems
• ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model