Rapid coarse-grained simulation of whole cryo-tomograms.

Abstract

Cryo-electron tomography is a rapidly expanding field of microscopy investigation, from subtomogram averaging to cellular tomography. This range of applications leads to highly varied data which can be difficult to analyze systematically. Multiple deep-learning techniques have been successfully applied to automate object classification, aiding in particle averaging or structural analysis. However, these neural networks typically rely on large training datasets that are painstakingly generated by hand based on a subset of the data. A method that does not require detailed hand-segmentation by an expert is needed to allow high-throughput application of deep-learning tools to varied datasets. Here we present CTS, a toolbox for modeling vitreous fields of randomized proteins and other organic structures and simulating these fields as complete tomograms. Crucially, CTS also generates a molecular atlas that provides efficient inputs to deep learning tools. This simple-to-use program can generate a complete simulation and atlas in minutes, and accepts a wide range of structure files to generate independent training data. The simulation replicates imaging processes to produce a realistic level of CTF aberration, resolution, contrast, and noise to best provide high-quality training data that is still representative of target data. CTS can model multiple structural organizations, such as bundled fibers, uniform and non-uniform protein complexes, and particle clusters in addition to modeling carbon gridholes, vitreous ice, and vesicular membranes. These simulations have proven to be capable of training highly accurate deep-learning segmentations of acellular tomograms with no further human input. Complex cellular tomograms are segmented more reliably and with less manual training required when paired with simulated training datasets, in addition to improving accuracy especially with fine-grained structural differences that can be difficult to discern and segment by hand. This tool therefore lowers the barrier for broad and novel deep-learning applications in cryo-ET.