Solving Inverse Problems in Protein Space Using Diffusion-Based Priors

TL;DR

This paper presents a versatile diffusion-based framework that transforms biophysical measurements like cryo-EM maps into detailed 3D protein structures, outperforming existing methods and enabling new applications.

Contribution

It introduces the first diffusion-based approach for refining atomic models from cryo-EM data and constructing structures from sparse distance matrices, integrating physics-based models with pretrained generative priors.

Findings

Outperforms posterior sampling baselines on inverse problems

First diffusion-based method for cryo-EM atomic model refinement

Enables structure building from sparse distance matrices

Abstract

The interaction of a protein with its environment can be understood and controlled via its 3D structure. Experimental methods for protein structure determination, such as X-ray crystallography or cryogenic electron microscopy, shed light on biological processes but introduce challenging inverse problems. Learning-based approaches have emerged as accurate and efficient methods to solve these inverse problems for 3D structure determination, but are specialized for a predefined type of measurement. Here, we introduce a versatile framework to turn biophysical measurements, such as cryo-EM density maps, into 3D atomic models. Our method combines a physics-based forward model of the measurement process with a pretrained generative model providing a task-agnostic, data-driven prior. Our method outperforms posterior sampling baselines on linear and non-linear inverse problems. In particular, it is the first diffusion-based method for refining atomic models from cryo-EM maps and building atomic models from sparse distance matrices.