Estimation of Orientation and Camera Parameters from Cryo-Electron Microscopy Images with Variational Autoencoders and Generative Adversarial Networks

TL;DR

This paper introduces a novel deep learning approach combining VAEs and GANs to efficiently estimate orientations and camera parameters in cryo-EM images, enhancing speed and scalability for 3D biomolecule reconstruction.

Contribution

It presents a new unsupervised method leveraging latent space analysis for estimating cryo-EM image parameters, improving computational efficiency over existing techniques.

Findings

Latent space exhibits a Lie group orbit structure.

Proposed method accurately estimates orientations and camera parameters.

Enables faster and scalable cryo-EM 3D reconstructions.

Abstract

Cryo-electron microscopy (cryo-EM) is capable of producing reconstructed 3D images of biomolecules at near-atomic resolution. As such, it represents one of the most promising imaging techniques in structural biology. However, raw cryo-EM images are only highly corrupted - noisy and band-pass filtered - 2D projections of the target 3D biomolecules. Reconstructing the 3D molecular shape starts with the removal of image outliers, the estimation of the orientation of the biomolecule that has produced the given 2D image, and the estimation of camera parameters to correct for intensity defects. Current techniques performing these tasks are often computationally expensive, while the dataset sizes keep growing. There is a need for next-generation algorithms that preserve accuracy while improving speed and scalability. In this paper, we combine variational autoencoders (VAEs) and generative adversarial networks (GANs) to learn a low-dimensional latent representation of cryo-EM images. We perform an exploratory analysis of the obtained latent space, that is shown to have a structure of "orbits", in the sense of Lie group theory, consistent with the acquisition procedure of cryo-EM images. This analysis leads us to design an estimation method for orientation and camera parameters of single-particle cryo-EM images, together with an outliers detection procedure. As such, it opens the door to geometric approaches for unsupervised estimations of orientations and camera parameters, making possible fast cryo-EM biomolecule reconstruction.