Boosted ab initio Cryo-EM 3D Reconstruction with ACE-EM

TL;DR

This paper introduces ACE-EM, an improved autoencoder-based method for cryo-EM 3D reconstruction that achieves Nyquist resolution and better pose estimation compared to previous approaches.

Contribution

The paper presents ACE-EM, a novel autoencoder architecture that enhances pose estimation and reconstruction quality in cryo-EM, reaching Nyquist resolution.

Findings

Achieved Nyquist resolution in simulated and experimental datasets

Higher pose space coverage within same training time

Outperformed previous autoencoder-based methods in reconstruction quality

Abstract

The central problem in cryo-electron microscopy (cryo-EM) is to recover the 3D structure from noisy 2D projection images which requires estimating the missing projection angles (poses). Recent methods attempted to solve the 3D reconstruction problem with the autoencoder architecture, which suffers from the latent vector space sampling problem and frequently produces suboptimal pose inferences and inferior 3D reconstructions. Here we present an improved autoencoder architecture called ACE (Asymmetric Complementary autoEncoder), based on which we designed the ACE-EM method for cryo-EM 3D reconstructions. Compared to previous methods, ACE-EM reached higher pose space coverage within the same training time and boosted the reconstruction performance regardless of the choice of decoders. With this method, the Nyquist resolution (highest possible resolution) was reached for 3D reconstructions of both simulated and experimental cryo-EM datasets. Furthermore, ACE-EM is the only amortized inference method that reached the Nyquist resolution.