Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Weijie, Wang, Yuhang, Yao, Lin
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911849397616640
author Chen, Weijie
Wang, Yuhang
Yao, Lin
author_facet Chen, Weijie
Wang, Yuhang
Yao, Lin
contents Due to the extremely low signal-to-noise ratio (SNR) and unknown poses (projection angles and image shifts) in cryo-electron microscopy (cryo-EM) experiments, reconstructing 3D volumes from 2D images is very challenging. In addition to these challenges, heterogeneous cryo-EM reconstruction requires conformational classification. In popular cryo-EM reconstruction algorithms, poses and conformation classification labels must be predicted for every input cryo-EM image, which can be computationally costly for large datasets. An emerging class of methods adopted the amortized inference approach. In these methods, only a subset of the input dataset is needed to train neural networks for the estimation of poses and conformations. Once trained, these neural networks can make pose/conformation predictions and 3D reconstructions at low cost for the entire dataset during inference. Unfortunately, when facing heterogeneous reconstruction tasks, it is hard for current amortized-inference-based methods to effectively estimate the conformational distribution and poses from entangled latent variables. Here, we propose a self-supervised variational autoencoder architecture called "HetACUMN" based on amortized inference. We employed an auxiliary conditional pose prediction task by inverting the order of encoder-decoder to explicitly enforce the disentanglement of conformation and pose predictions. Results on simulated datasets show that HetACUMN generated more accurate conformational classifications than other amortized or non-amortized methods. Furthermore, we show that HetACUMN is capable of performing heterogeneous 3D reconstructions of a real experimental dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2308_04956
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement
Chen, Weijie
Wang, Yuhang
Yao, Lin
Image and Video Processing
Computer Vision and Pattern Recognition
Biomolecules
Quantitative Methods
J.2; J.3; I.4.5
Due to the extremely low signal-to-noise ratio (SNR) and unknown poses (projection angles and image shifts) in cryo-electron microscopy (cryo-EM) experiments, reconstructing 3D volumes from 2D images is very challenging. In addition to these challenges, heterogeneous cryo-EM reconstruction requires conformational classification. In popular cryo-EM reconstruction algorithms, poses and conformation classification labels must be predicted for every input cryo-EM image, which can be computationally costly for large datasets. An emerging class of methods adopted the amortized inference approach. In these methods, only a subset of the input dataset is needed to train neural networks for the estimation of poses and conformations. Once trained, these neural networks can make pose/conformation predictions and 3D reconstructions at low cost for the entire dataset during inference. Unfortunately, when facing heterogeneous reconstruction tasks, it is hard for current amortized-inference-based methods to effectively estimate the conformational distribution and poses from entangled latent variables. Here, we propose a self-supervised variational autoencoder architecture called "HetACUMN" based on amortized inference. We employed an auxiliary conditional pose prediction task by inverting the order of encoder-decoder to explicitly enforce the disentanglement of conformation and pose predictions. Results on simulated datasets show that HetACUMN generated more accurate conformational classifications than other amortized or non-amortized methods. Furthermore, we show that HetACUMN is capable of performing heterogeneous 3D reconstructions of a real experimental dataset.
title Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement
topic Image and Video Processing
Computer Vision and Pattern Recognition
Biomolecules
Quantitative Methods
J.2; J.3; I.4.5
url https://arxiv.org/abs/2308.04956