1. Isotropic reconstruction for electron tomography with deep learning
- Author
-
Liu, Yun-Tao, Zhang, Heng, Wang, Hui, Tao, Chang-Lu, Bi, Guo-Qiang, and Zhou, Z Hong
- Subjects
Information and Computing Sciences ,Physical Sciences ,Condensed Matter Physics ,1.1 Normal biological development and functioning ,Underpinning research ,Electron Microscope Tomography ,Cryoelectron Microscopy ,Deep Learning ,Image Processing ,Computer-Assisted ,Software - 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.
- Published
- 2022