Learning from Hetero Density for Cryo-EM Protein Reconstruction

2026-10-08

AI Summary

This study addresses the underutilization of heterogeneous density information in cryo-electron microscopy (cryo-EM) protein reconstruction by proposing CryoCue, a novel framework that pioneers the use of heterogeneous densities as supervisory signals. Specifically, it guides protein structure reconstruction through an anchor-supervised detector and multi-scale feature extraction, while integrating geometric constraints with a confidence-driven strategy to optimize backbone tracing and structural refinement. Experimental results demonstrate that this approach significantly improves backbone localization accuracy near heterogeneous regions, thereby achieving more precise three-dimensional protein structure reconstruction from cryo-EM data.

Abstract

Reconstructing protein structures from cryo-electron microscopy (cryo-EM) maps is essential for understanding macromolecular assemblies. Although learning-based methods have improved protein reconstruction, information from hetero components remains underused. Our analysis finds both false predictions and reference protein sites near hetero components; filtering nearby candidates can improve or impair chain construction. We introduce CryoCue, a framework that uses hetero information to guide protein reconstruction. An anchor-supervised detector learns hetero representations across five component classes. Multiscale hetero features guide backbone localization, while predicted hetero candidates condition structure refinement through their class, confidence, and frame-relative geometry. Experiments show that CryoCue improves backbone localization near hetero components and achieves more accurate protein structure reconstruction.

Problem

• Cryo-EM
• Protein reconstruction
• Hetero components
• Backbone localization
• Macromolecular assemblies

Innovation

• Cryo-EM
• Protein Reconstruction
• Hetero Density
• Anchor-supervised Detector
• Multiscale Features