---
OA_place: publisher
OA_type: hybrid
PlanS_conform: '1'
_id: '19443'
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/.
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.
article_processing_charge: Yes (in subscription journal)
article_type: original
author:
- first_name: Pavol
  full_name: Harar, Pavol
  id: e03d953a-6e8c-11ef-99e4-f0717d385cd5
  last_name: Harar
  orcid: 0000-0001-5206-1794
- first_name: Lukas
  full_name: Herrmann, Lukas
  last_name: Herrmann
- first_name: Philipp
  full_name: Grohs, Philipp
  last_name: Grohs
- first_name: David
  full_name: Haselbach, David
  last_name: Haselbach
citation:
  ama: 'Harar P, Herrmann L, Grohs P, Haselbach D. FakET: Simulating cryo-electron
    tomograms with neural style transfer. <i>Structure</i>. 2025;33(4):820-827.e4.
    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. (2025). 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>'
  chicago: 'Harar, Pavol, Lukas Herrmann, Philipp Grohs, and David Haselbach. “FakET:
    Simulating Cryo-Electron Tomograms with Neural Style Transfer.” <i>Structure</i>.
    Elsevier, 2025. <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>, vol. 33, no. 4. Elsevier,
    p. 820–827.e4, 2025.'
  ista: 'Harar P, Herrmann L, Grohs P, Haselbach D. 2025. FakET: Simulating cryo-electron
    tomograms with neural style transfer. Structure. 33(4), 820–827.e4.'
  mla: 'Harar, Pavol, et al. “FakET: Simulating Cryo-Electron Tomograms with Neural
    Style Transfer.” <i>Structure</i>, vol. 33, no. 4, Elsevier, 2025, p. 820–827.e4,
    doi:<a href="https://doi.org/10.1016/j.str.2025.01.020">10.1016/j.str.2025.01.020</a>.'
  short: P. Harar, L. Herrmann, P. Grohs, D. Haselbach, Structure 33 (2025) 820–827.e4.
corr_author: '1'
date_created: 2025-03-23T23:01:27Z
date_published: 2025-04-03T00:00:00Z
date_updated: 2025-09-30T11:13:02Z
day: '03'
ddc:
- '570'
department:
- _id: AlMi
doi: 10.1016/j.str.2025.01.020
external_id:
  isi:
  - '001463196100001'
  pmid:
  - '39947174'
file:
- access_level: open_access
  checksum: f346bc357a66a88cca3d0eb95793fb73
  content_type: application/pdf
  creator: dernst
  date_created: 2025-08-05T12:15:13Z
  date_updated: 2025-08-05T12:15:13Z
  file_id: '20130'
  file_name: 2025_Structure_Harar.pdf
  file_size: 4367530
  relation: main_file
  success: 1
file_date_updated: 2025-08-05T12:15:13Z
has_accepted_license: '1'
intvolume: '        33'
isi: 1
issue: '4'
language:
- iso: eng
month: '04'
oa: 1
oa_version: Published Version
page: 820-827.e4
pmid: 1
publication: Structure
publication_identifier:
  eissn:
  - 1878-4186
  issn:
  - 0969-2126
publication_status: published
publisher: Elsevier
quality_controlled: '1'
related_material:
  link:
  - relation: software
    url: https://github.com/paloha/faket/
scopus_import: '1'
status: public
title: 'FakET: Simulating cryo-electron tomograms with neural style transfer'
tmp:
  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)
  short: CC BY (4.0)
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 33
year: '2025'
...