Integrating molecular models into CryoEM heterogeneity analysis using scalable high-resolution deep Gaussian mixture models

TL;DR

This paper presents a scalable deep Gaussian mixture model approach that integrates molecular models into CryoEM heterogeneity analysis, enabling near-atomic resolution insights into protein conformational variability.

Contribution

It introduces a novel method combining Gaussian mixture models and deep neural networks to improve protein heterogeneity analysis in CryoEM data.

Findings

Resolves complex protein conformations at near-atomic resolution.

Provides more interpretable results by integrating molecular models.

Enhances understanding of protein dynamics from noisy CryoEM micrographs.

Abstract

Resolving the structural variability of proteins is often key to understanding the structure-function relationship of those macromolecular machines. Single particle analysis using Cryogenic electron microscopy (CryoEM), combined with machine learning algorithms, provides a way to reveal the dynamics within the protein system from noisy micrographs. Here, we introduce an improved computational method that uses Gaussian mixture models for protein structure representation and deep neural networks for conformation space embedding. By integrating information from molecular models into the heterogeneity analysis, we can resolve complex protein conformational changes at near atomic resolution and present the results in a more interpretable form.