Learning to recover orientations from projections in single-particle cryo-EM

TL;DR

This paper introduces a learning-based method to determine 3D particle orientations from 2D cryo-EM projections by estimating pairwise distances with a neural network and recovering orientations through optimization, showing promising results on synthetic data.

Contribution

The paper presents a novel two-step approach combining neural network-based distance estimation and optimization for orientation recovery in cryo-EM, not previously explored in this context.

Findings

Accurate orientation recovery from noisy, shifted projections in synthetic datasets.

The method's success depends on the accuracy of the distance estimator.

Potential for application in real cryo-EM data with further development.

Abstract

A major challenge in single-particle cryo-electron microscopy (cryo-EM) is that the orientations adopted by the 3D particles prior to imaging are unknown; yet, this knowledge is essential for high-resolution reconstruction. We present a method to recover these orientations directly from the acquired set of 2D projections. Our approach consists of two steps: (i) the estimation of distances between pairs of projections, and (ii) the recovery of the orientation of each projection from these distances. In step (i), pairwise distances are estimated by a Siamese neural network trained on synthetic cryo-EM projections from resolved bio-structures. In step (ii), orientations are recovered by minimizing the difference between the distances estimated from the projections and the distances induced by the recovered orientations. We evaluated the method on synthetic cryo-EM datasets. Current results demonstrate that orientations can be accurately recovered from projections that are shifted and corrupted with a high level of noise. The accuracy of the recovery depends on the accuracy of the distance estimator. While not yet deployed in a real experimental setup, the proposed method offers a novel learning-based take on orientation recovery in SPA. Our code is available at https://github.com/JelenaBanjac/protein-reconstruction