cryoSPHERE: Single-particle heterogeneous reconstruction from cryo EM

2024-05-29

bioRxiv

AI Summary

This work addresses the challenge of reconstructing continuous conformational distributions of proteins from single-particle cryo-electron microscopy (cryo-EM) data—a longstanding limitation of conventional methods that yield only discrete consensus structures. We propose the first end-to-end differentiable framework that integrates AlphaFold-derived structural priors, automatically partitions the protein into near-rigid fragments, and parameterizes their continuous rigid-body motions. Coupling differentiable electron-optical rendering with geometric constraint optimization, the method directly learns the full conformational distribution from noisy 2D projections. Our approach establishes the first structural-prior-driven continuous conformational modeling paradigm for cryo-EM. Evaluated on three real-world datasets, it significantly outperforms state-of-the-art methods, yielding high-resolution, structurally interpretable, and physically consistent conformational manifolds—thereby enabling a new paradigm for dynamic structural biology.

Technology Category

• Machine Learning: Structured Learning
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Security and Privacy: Data transparency and provenance

Abstract

The three-dimensional structure of a protein plays a key role in determining its function. Methods like AlphaFold have revolutionized protein structure prediction based only on the amino-acid sequence. However, proteins often appear in multiple different conformations, and it is highly relevant to resolve the full conformational distribution. Single-particle cryo-electron microscopy (cryo EM) is a powerful tool for capturing a large number of images of a given protein, frequently in different conformations (referred to as particles). The images are, however, very noisy projections of the protein, and traditional methods for cryo EM reconstruction are limited to recovering a single, or a few, conformations. In this paper, we introduce cryoSPHERE, a deep learning method that takes as input a nominal protein structure, e.g. from AlphaFold, learns how to divide it into segments, and how to move these as approximately rigid bodies to fit the different conformations present in the cryo EM dataset. This formulation is shown to provide enough constraints to recover meaningful reconstructions of single protein structures. This is illustrated in three examples where we show consistent improvements over the current state-of-the-art for heterogeneous reconstruction.

Problem

• Resolves conformational heterogeneity in protein structures.
• Improves reconstruction of large protein complexes from cryo-EM data.
• Handles high noise levels in experimental cryo-EM datasets.

Innovation

• Deep learning for cryo-EM conformational heterogeneity
• Segmentation and rigid-body movement of protein structures
• Resilient to high noise in experimental datasets