# PickET: An unsupervised method for localizing macromolecules in cryo-electron tomograms

## TL;DR

PickET is a new method that automatically finds macromolecules in cryo-electron tomograms without needing prior knowledge or manual input.

## Contribution

PickET introduces an unsupervised approach for localizing macromolecules in cryo-ET data without requiring expert annotations or known structures.

## Key findings

- PickET successfully localizes macromolecules of varying shapes, sizes, and abundance in diverse tomograms.
- The method enables 3D classification and de novo structural characterization using predicted particle localizations.
- PickET is efficient, scalable, and suitable for high-throughput analysis of cryo-ET datasets.

## Abstract

Cryo-electron tomography (cryo-ET) datasets are rich sources of information capable of describing the localizations, structures, and interactions of macromolecules. However, most current methods for localizing particles in cryo-electron tomograms are limited to macromolecules with known structures, require extensive manual annotations, and/or are computationally expensive. Here, we present PickET, a method for localizing macromolecules in tomograms that does not rely on expert annotations and prior structures. Its performance is demonstrated on a diverse dataset comprising over a hundred tomograms from publicly available datasets, varying in sample types, sample preparation conditions, microscope hardware, and image processing workflows. We demonstrate that PickET can simultaneously localize macromolecules of various shapes, sizes, and abundance. The predicted particle localizations can be used for 3D classification and de novo structural characterization. Our fully unsupervised approach is efficient and scalable, and enables high-throughput analysis of cryo-ET data.