Isotropic reconstruction for electron tomography with deep learning
University of Science and Technology of China · California NanoSystems Institute · +9 more institutions
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:…
Citation impact
- FWCI
- 70.48
- Percentile
- 100%
- References
- 74
Authors
6- YLYun-Tao LiuCorresponding
University of Science and Technology of China, California NanoSystems Institute, University of California, Los Angeles, Hefei National Center for Physical Sciences at Nanoscale
- HZHeng Zhang
University of Science and Technology of China, Hefei National Center for Physical Sciences at Nanoscale
- HWHui Wang
California NanoSystems Institute, University of California, Los Angeles, La Jolla Bioengineering Institute
- CTChang-Lu Tao
University of Science and Technology of China, Chinese Academy of Sciences, HKUST Shenzhen Research Institute, Hefei National Center for Physical Sciences at Nanoscale, Shenzhen Institute of Neuroscience, Shenzhen Institutes of Advanced Technology
- GBGuo‐Qiang Bi
University of Science and Technology of China, HKUST Shenzhen Research Institute, Center for Excellence in Brain Science and Intelligence Technology, Hefei National Center for Physical Sciences at Nanoscale, Shenzhen Institutes of Advanced Technology
Topics & keywords
- Tomography
- Electron tomography
- Artificial intelligence
- Computer science
- Interpretability
- Cryo-electron tomography
- Visualization
- Algorithm
Funding
- NSNational Science FoundationAwards: DMR-1548924, 1548924
- NNNational Natural Science Foundation of ChinaAwards: XDB32030200, 31761163006, 31630030, 31621002
- CAChinese Academy of SciencesAwards: XDB32030200, 31621002
- NINational Institutes of HealthAwards: S10OD018111, GM071940, S10RR23057
- DODivision of Materials ResearchAwards: 1548924, DMR-1548924