Isotropic reconstruction for electron tomography with deep learning

Yun-Tao Liu; Heng Zhang; Hui Wang; Chang-Lu Tao; Guo-Qiang Bi; Z Hong Zhou

doi:10.1038/s41467-022-33957-8

Isotropic reconstruction for electron tomography with deep learning

Nat Commun. 2022 Oct 29;13(1):6482. doi: 10.1038/s41467-022-33957-8.

Authors

Yun-Tao Liu^#^{1

2

3}, Heng Zhang^#^{1

4}, Hui Wang^{2

3

5}, Chang-Lu Tao^{1

6

7}, Guo-Qiang Bi^{8

9

10}, Z Hong Zhou^{11

12

13}

Affiliations

¹ Center for Integrative Imaging, Hefei National Research Center for Physical Sciences at the Microscale, School of Life Sciences, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230026, China.
² California NanoSystems Institute, University of California, Los Angeles (UCLA), Los Angeles, CA, 90095, USA.
³ Department of Microbiology, Immunology and Molecular Genetics, UCLA, Los Angeles, CA, 90095, USA.
⁴ Department of Physics, University of Science and Technology of China, Hefei, Anhui, 230026, China.
⁵ Department of Bioengineering, UCLA, Los Angeles, CA, 90095, USA.
⁶ Interdisciplinary Center for Brain Information, Brain Cognition and Brain Disease Institute, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.
⁷ Faculty of Life and Health Sciences, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.
⁸ Center for Integrative Imaging, Hefei National Research Center for Physical Sciences at the Microscale, School of Life Sciences, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230026, China. gqbi@ustc.edu.cn.
⁹ Interdisciplinary Center for Brain Information, Brain Cognition and Brain Disease Institute, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China. gqbi@ustc.edu.cn.
¹⁰ Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China. gqbi@ustc.edu.cn.
¹¹ California NanoSystems Institute, University of California, Los Angeles (UCLA), Los Angeles, CA, 90095, USA. Hong.Zhou@UCLA.edu.
¹² Department of Microbiology, Immunology and Molecular Genetics, UCLA, Los Angeles, CA, 90095, USA. Hong.Zhou@UCLA.edu.
¹³ Department of Bioengineering, UCLA, Los Angeles, CA, 90095, USA. Hong.Zhou@UCLA.edu.

^# Contributed equally.

Abstract

Cryogenic electron tomography (cryoET) allows visualization of cellular structures in situ. However, anisotropic resolution arising from the intrinsic "missing-wedge" problem has presented major challenges in visualization and interpretation of tomograms. Here, we have developed IsoNet, a deep learning-based software package that iteratively reconstructs the missing-wedge information and increases signal-to-noise ratio, using the knowledge learned from raw tomograms. Without the need for sub-tomogram averaging, IsoNet generates tomograms with significantly reduced resolution anisotropy. Applications of IsoNet to three representative types of cryoET data demonstrate greatly improved structural interpretability: resolving lattice defects in immature HIV particles, establishing architecture of the paraflagellar rod in Eukaryotic flagella, and identifying heptagon-containing clathrin cages inside a neuronal synapse of cultured cells. Therefore, by overcoming two fundamental limitations of cryoET, IsoNet enables functional interpretation of cellular tomograms without sub-tomogram averaging. Its application to high-resolution cellular tomograms should also help identify differently oriented complexes of the same kind for sub-tomogram averaging.

Publication types

Research Support, U.S. Gov't, Non-P.H.S.
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

Cryoelectron Microscopy / methods
Deep Learning*
Electron Microscope Tomography* / methods
Image Processing, Computer-Assisted / methods
Software

Abstract

Publication types

MeSH terms

Grants and funding