Unsupervised particle sorting for cryo-EM using probabilistic PCA

TL;DR

This paper introduces an unsupervised probabilistic PCA-based algorithm to automatically distinguish true particle images from noise and contamination in cryo-EM data, reducing manual sorting effort.

Contribution

It presents a novel extension of probabilistic PCA to model union of subspaces for cryo-EM particle image filtering, enabling automatic removal of false detections.

Findings

Effective removal of non-particle images demonstrated in experiments

Reduces need for manual intervention in cryo-EM data processing

Flexible modeling of cryo-EM data with union of subspaces

Abstract

Single-particle cryo-electron microscopy (cryo-EM) is a leading technology to resolve the structure of molecules. Early in the process, the user detects potential particle images in the raw data. Typically, there are many false detections as a result of high levels of noise and contamination. Currently, removing the false detections requires human intervention to sort the hundred thousands of images. We propose a statistically-established unsupervised algorithm to remove non-particle images. We model the particle images as a union of low-dimensional subspaces, assuming non-particle images are arbitrarily scattered in the high-dimensional space. The algorithm is based on an extension of the probabilistic PCA framework to robustly learn a non-linear model of union of subspaces. This provides a flexible model for cryo-EM data, and allows to automatically remove images that correspond to pure noise and contamination. Numerical experiments corroborate the effectiveness of the sorting algorithm.