{"has_accepted_license":"1","language":[{"iso":"eng"}],"month":"01","date_updated":"2025-03-25T08:42:31Z","status":"public","oa_version":"Published Version","OA_type":"hybrid","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_created":"2025-03-23T23:01:27Z","publication_status":"inpress","department":[{"_id":"AlMi"}],"acknowledgement":"The IMP and D.H. are generously funded by Boehringer Ingelheim. We thank Julius Berner from the Mathematical Data Science group @ UniVie, Ilja Gubins and Marten Chaillet from the SHREC team, and the members of the Haselbach lab for helpful discussions.","license":"https://creativecommons.org/licenses/by/4.0/","author":[{"first_name":"Pavol","id":"e03d953a-6e8c-11ef-99e4-f0717d385cd5","orcid":"0000-0001-5206-1794","full_name":"Harar, Pavol","last_name":"Harar"},{"last_name":"Herrmann","full_name":"Herrmann, Lukas","first_name":"Lukas"},{"first_name":"Philipp","last_name":"Grohs","full_name":"Grohs, Philipp"},{"last_name":"Haselbach","full_name":"Haselbach, David","first_name":"David"}],"publication_identifier":{"issn":["0969-2126"],"eissn":["1878-4186"]},"main_file_link":[{"open_access":"1","url":"https://doi.org/10.1016/j.str.2025.01.020"}],"article_processing_charge":"Yes (in subscription journal)","scopus_import":"1","corr_author":"1","article_type":"original","date_published":"2025-01-01T00:00:00Z","abstract":[{"lang":"eng","text":"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 750x, uses 33x 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/."}],"title":"FakET: Simulating cryo-electron tomograms with neural style transfer","publisher":"Elsevier","_id":"19443","related_material":{"link":[{"relation":"software","url":"https://github.com/paloha/faket/"}]},"oa":1,"doi":"10.1016/j.str.2025.01.020","publication":"Structure","type":"journal_article","quality_controlled":"1","year":"2025","tmp":{"short":"CC BY (4.0)","image":"/images/cc_by.png","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"citation":{"mla":"Harar, Pavol, et al. “FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer.” <i>Structure</i>, Elsevier, doi:<a href=\"https://doi.org/10.1016/j.str.2025.01.020\">10.1016/j.str.2025.01.020</a>.","apa":"Harar, P., Herrmann, L., Grohs, P., &#38; Haselbach, D. (n.d.). FakET: Simulating cryo-electron tomograms with neural style transfer. <i>Structure</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.str.2025.01.020\">https://doi.org/10.1016/j.str.2025.01.020</a>","ieee":"P. Harar, L. Herrmann, P. Grohs, and D. Haselbach, “FakET: Simulating cryo-electron tomograms with neural style transfer,” <i>Structure</i>. Elsevier.","chicago":"Harar, Pavol, Lukas Herrmann, Philipp Grohs, and David Haselbach. “FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer.” <i>Structure</i>. Elsevier, n.d. <a href=\"https://doi.org/10.1016/j.str.2025.01.020\">https://doi.org/10.1016/j.str.2025.01.020</a>.","ista":"Harar P, Herrmann L, Grohs P, Haselbach D. FakET: Simulating cryo-electron tomograms with neural style transfer. Structure.","short":"P. Harar, L. Herrmann, P. Grohs, D. Haselbach, Structure (n.d.).","ama":"Harar P, Herrmann L, Grohs P, Haselbach D. FakET: Simulating cryo-electron tomograms with neural style transfer. <i>Structure</i>. doi:<a href=\"https://doi.org/10.1016/j.str.2025.01.020\">10.1016/j.str.2025.01.020</a>"},"day":"01","OA_place":"publisher"}