Overcoming the preferred-orientation problem in cryo-EM with self-supervised deep learning

• Published in: Nature methods Vol. 22; no. 1; pp. 113 - 123
• Main Authors: Liu, Yun-Tao, Fan, Hongcheng, Hu, Jason J., Zhou, Z. Hong
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.01.2025; Nature Publishing Group
• Subjects: 631/114/1305; 631/1647/2258/1258/1259; 631/1647/2258/1258/1260; 631/1647/794; Algorithms; Alignment; Anisotropy; Bioinformatics; Biological Microscopy; Biological Techniques; Biomedical and Life Sciences; Biomedical Engineering/Biotechnology; Cryoelectron Microscopy - methods; Deep Learning; Hemagglutinins; Image Processing, Computer-Assisted - methods; Image reconstruction; Imaging, Three-Dimensional - methods; Isotropy; Life Sciences; Macromolecular Substances - chemistry; Misalignment; Orientation; Proteomics; Ribosomes; Ribosomes - ultrastructure; Software
• ISSN: 1548-7091; 1548-7105; 1548-7105
• DOI: 10.1038/s41592-024-02505-1

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. spIsoNet is an end-to-end self-supervised deep learning-based software to address the reconstruction and misalignment challenge in single-particle cryo-EM caused by the preferred-orientation problem. spIsoNet can also improve map isotropy and particle alignment of preferentially oriented molecules during subtomogram averaging in cryogenic electron tomography.