In cryo-electron microscopy, accurate particle localization and classification are imperative. Recent deep learning solutions, though successful, require extensive training datasets. The protracted generation time of physics-based models, often employed to produce these datasets, limits their broad applicability. We introduce FakET, a method based on neural style transfer, capable of simulating the forward operator of any cryo transmission electron microscope. It can be used to adapt a synthetic training dataset according to reference data producing high-quality simulated micrographs or tilt-series. To assess the quality of our generated data, we used it to train a state-of-the-art localization and classification architecture and compared its performance with a counterpart trained on benchmark data. Remarkably, our technique matches the performance, boosts data generation speed 750×, uses 33× less memory, and scales well to typical transmission electron microscope detector sizes. It leverages GPU acceleration and parallel processing. The source code is available at https://github.com/paloha/faket/.

Haselbach Lab Research Institute of Molecular Pathology Vienna Austria

Johann Radon Institute for Computational and Applied Mathematics Austrian Academy of Sciences Linz Austria

Mathematical Data Science Faculty of Mathematics University of Vienna Vienna Austria; Research Network Data Science University of Vienna Vienna Austria; Johann Radon Institute for Computational and Applied Mathematics Austrian Academy of Sciences Linz Austria

Mathematical Data Science Klosterneuburg Austria

References provided by Crossref.org