Isotropic reconstruction for electron tomography with deep learning.
Liu YT, Zhang H, Wang H, Tao CL, Bi GQ, Zhou ZH. · 2022
Read Isotropic reconstruction for electron tomography with deep learning. by Liu YT, Zhang H, Wang H, Tao CL, Bi GQ, Zhou ZH. (2022) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc9617606.txt.
Description
Liu and co-authors build IsoNet, a deep learning package for isotropic reconstruction in electron tomography. Cryo electron tomography shows cell structures in their native place. A missing wedge of data blurs views along one axis. That blur has long blocked clear reading of tomograms.
IsoNet learns from the raw tomograms themselves in loops. Each round rebuilds part of the missing wedge data. The rounds also lift the signal over the noise. No sub-tomogram averaging is needed for the gain. The team tested the tool on three data types. It resolved lattice faults in immature HIV particles. It set out the layout of a flagellar rod in fine detail. It also spotted heptagon bearing clathrin cages in a synapse. The authors say the tool frees cell tomograms for direct study.
Catalog record
| CREATOR | Liu YT, Zhang H, Wang H, Tao CL, Bi GQ, Zhou ZH. |
|---|---|
| YEAR | 2022 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |