Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery

TL;DR

CryoSPIRE is a new 3D reconstruction method for cryo-EM that models heterogeneous biomolecules using hierarchical Gaussian mixtures, effectively handling conformational flexibility and missing parts, and achieves state-of-the-art results.

Contribution

Introduces CryoSPIRE, a hierarchical Gaussian mixture-based framework for cryo-EM that incorporates part segmentation to improve modeling of flexible and variable structures.

Findings

Reveals biologically meaningful structures on complex datasets

Establishes new state-of-the-art on CryoBench benchmark

Handles conformational and compositional variability effectively

Abstract

Cryo-EM is a transformational paradigm in molecular biology where computational methods are used to infer 3D molecular structure at atomic resolution from extremely noisy 2D electron microscope images. At the forefront of research is how to model the structure when the imaged particles exhibit non-rigid conformational flexibility and compositional variation where parts are sometimes missing. We introduce a novel 3D reconstruction framework with a hierarchical Gaussian mixture model, inspired in part by Gaussian Splatting for 4D scene reconstruction. In particular, the structure of the model is grounded in an initial process that infers a part-based segmentation of the particle, providing essential inductive bias in order to handle both conformational and compositional variability. The framework, called CryoSPIRE, is shown to reveal biologically meaningful structures on complex experimental datasets, and establishes a new state-of-the-art on CryoBench, a benchmark for cryo-EM heterogeneity methods.