EigenFold: Generative Protein Structure Prediction with Diffusion Models

TL;DR

EigenFold introduces a diffusion-based generative framework for protein structure modeling that captures conformational ensembles and heterogeneity, advancing understanding of protein flexibility beyond single-structure predictions.

Contribution

The paper presents EigenFold, a novel diffusion model that generates diverse protein structures and models conformational heterogeneity, addressing limitations of existing single-structure prediction methods.

Findings

Median TMScore of 0.84 on CAMEO targets

Provides ensemble of structures for uncertainty estimation

Effectively models conformational heterogeneity in proteins

Abstract

Protein structure prediction has reached revolutionary levels of accuracy on single structures, yet distributional modeling paradigms are needed to capture the conformational ensembles and flexibility that underlie biological function. Towards this goal, we develop EigenFold, a diffusion generative modeling framework for sampling a distribution of structures from a given protein sequence. We define a diffusion process that models the structure as a system of harmonic oscillators and which naturally induces a cascading-resolution generative process along the eigenmodes of the system. On recent CAMEO targets, EigenFold achieves a median TMScore of 0.84, while providing a more comprehensive picture of model uncertainty via the ensemble of sampled structures relative to existing methods. We then assess EigenFold's ability to model and predict conformational heterogeneity for fold-switching proteins and ligand-induced conformational change. Code is available at https://github.com/bjing2016/EigenFold.