Overcoming the Preferred-Orientation Problem in Cryo-EM with Self-Supervised Deep Learning. Liu, Y., Fan, H., Hu, J. J., & Zhou, Z. H. Nature Methods, 22(1):113–123, Nature Publishing Group, January, 2025.
doi  abstract   bibtex   
While advances in single-particle cryo-EM have enabled the structural determination of macromolecular complexes at atomic resolution, particle orientation bias (the `preferred' orientation problem) remains a complication for most specimens. Existing solutions have relied on biochemical and physical strategies applied to the specimen and are often complex and challenging. Here, we develop spIsoNet, an end-to-end self-supervised deep learning-based software to address map anisotropy and particle misalignment caused by the preferred-orientation problem. Using preferred-orientation views to recover molecular information in under-sampled views, spIsoNet improves both angular isotropy and particle alignment accuracy during 3D reconstruction. We demonstrate spIsoNet's ability to generate near-isotropic reconstructions from representative biological systems with limited views, including ribosomes, $β$-galactosidases and a previously intractable hemagglutinin trimer dataset. spIsoNet can also be generalized to improve map isotropy and particle alignment of preferentially oriented molecules in subtomogram averaging. Therefore, without additional specimen-preparation procedures, spIsoNet provides a general computational solution to the preferred-orientation problem.
@article{liuOvercomingPreferredorientationProblem2025,
  title = {Overcoming the Preferred-Orientation Problem in Cryo-{{EM}} with Self-Supervised Deep Learning},
  author = {Liu, Yun-Tao and Fan, Hongcheng and Hu, Jason J. and Zhou, Z. Hong},
  year = {2025},
  month = jan,
  journal = {Nature Methods},
  volume = {22},
  number = {1},
  pages = {113--123},
  publisher = {Nature Publishing Group},
  issn = {1548-7105},
  doi = {10.1038/s41592-024-02505-1},
  urldate = {2025-04-04},
  abstract = {While advances in single-particle cryo-EM have enabled the structural determination of macromolecular complexes at atomic resolution, particle orientation bias (the `preferred' orientation problem) remains a complication for most specimens. Existing solutions have relied on biochemical and physical strategies applied to the specimen and are often complex and challenging. Here, we develop spIsoNet, an end-to-end self-supervised deep learning-based software to address map anisotropy and particle misalignment caused by the preferred-orientation problem. Using preferred-orientation views to recover molecular information in under-sampled views, spIsoNet improves both angular isotropy and particle alignment accuracy during 3D reconstruction. We demonstrate spIsoNet's ability to generate near-isotropic reconstructions from representative biological systems with limited views, including ribosomes, {$\beta$}-galactosidases and a previously intractable hemagglutinin trimer dataset. spIsoNet can also be generalized to improve map isotropy and particle alignment of preferentially oriented molecules in subtomogram averaging. Therefore, without additional specimen-preparation procedures, spIsoNet provides a general computational solution to the preferred-orientation problem.},
  copyright = {2024 The Author(s), under exclusive licence to Springer Nature America, Inc.},
  langid = {english},
  keywords = {Cryoelectron microscopy,Cryoelectron tomography,Machine learning,Software},
  file = {C:\Users\shervinnia\Zotero\storage\2WR59ZWV\Liu et al. - 2025 - Overcoming the preferred-orientation problem in cryo-EM with self-supervised deep learning.pdf}
}

Downloads: 0