For a more complete understanding of molecular mechanisms, it is important to study macromolecules and their assemblies in the broader context of the cell. This context can be visualized at nanometer resolution in three dimensions (3D) using electron cryo-tomography, which requires tilt series to be recorded and computationally aligned, currently limiting throughput. Additionally, the high-resolution signal preserved in the raw tomograms is currently limited by a number of technical difficulties, leading to an increased false-positive detection rate when using 3D template matching to find molecular complexes in tomograms. We have recently described a 2D template matching approach that addresses these issues by including high-resolution signal preserved in single-tilt images. A current limitation of this approach is the high computational cost that limits throughput. We describe here a GPU-accelerated implementation of 2D template matching in the image processing software cisTEM that allows for easy scaling and improves the accessibility of this approach. We apply 2D template matching to identify ribosomes in images of frozen-hydrated Mycoplasma pneumoniae cells with high precision and sensitivity, demonstrating that this is a versatile tool for in situ visual proteomics and in situ structure determination. We benchmark the results with 3D template matching of tomograms acquired on identical sample locations and identify strengths and weaknesses of both techniques, which offer complementary information about target localization and identity.

Over the last decade, single-particle electron cryo-microscopy has become one of the main techniques contributing to the growing library of high-resolution structures of macromolecules and their assemblies. For a full understanding of molecular mechanisms, however, it is important to place them into the broader context of a cell. Traditionally, this context can be visualized in 3D by electron cryo-tomography, and more recently, has also been studied by template matching of 2D images of cells and viruses. A current limitation of the latter approach is the high computational cost that limits the throughput and widespread adoption of this method. We describe here a GPU-accelerated implementation of 2D template matching in the image processing software cisTEM that allows for easy scaling and improves the accessibility of this approach. We apply 2D template matching to identify ribosomes in images of frozen-hydrated Mycoplasma pneumoniae cells and demonstrate that it can function as a versatile tool for in situ visual proteomics and in situ structure determination. We compare the results with 3D template matching of tomograms acquired on identical sample locations. We identify strengths and weaknesses of both techniques which offer complementary information about target localization and identity.