End-to-end orientation estimation from 2D cryo-EM images

被引:5
作者
Lian, Ruyi [1 ]
Huang, Bingyao [1 ]
Wang, Liguo [2 ]
Liu, Qun [3 ]
Lin, Yuewei [4 ]
Ling, Haibin [1 ]
机构
[1] SUNY Stony Brook, Dept Comp Sci, Stony Brook, NY 11794 USA
[2] Brookhaven Natl Lab, Lab Biomol Struct, Upton, NY 11973 USA
[3] Brookhaven Natl Lab, Biol Dept, NSLS II, Upton, NY 11973 USA
[4] Brookhaven Natl Lab, Computat Sci Initiat, Upton, NY 11973 USA
来源
ACTA CRYSTALLOGRAPHICA SECTION D-STRUCTURAL BIOLOGY | 2022年 / 78卷
基金
美国国家科学基金会;
关键词
3D reconstruction; image processing; single-particle cryo-EM; RECONSTRUCTION;
D O I
10.1107/S2059798321011761
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Cryo-electron microscopy (cryo-EM) is a Nobel Prize-winning technique for determining high-resolution 3D structures of biological macromolecules. A 3D structure is reconstructed from hundreds of thousands of noisy 2D projection images. However, existing 3D reconstruction methods are still time-consuming, and one of the major computational bottlenecks is recovering the unknown orientation of the particle in each 2D image. The dominant methods typically exploit an expensive global search on each image to estimate the missing orientations. Here, a novel end-to-end supervised learning method is introduced to directly recover the missing orientations from 2D cryo-EM images. A neural network is used to approximate the mapping from images to orientations. A robust loss function is proposed for optimizing the parameters of the network, which can handle both asymmetric and symmetric 3D structures. Experiments on synthetic data sets with various symmetry types confirm that the neural network is capable of recovering orientations from 2D cryo-EM images, and the results on a real cryo-EM data set further demonstrate its potential under more challenging imaging conditions.
引用
收藏
页码:174 / 186
页数:13
相关论文
共 44 条
[1]   A Super-Clustering Approach for Fully Automated Single Particle Picking in Cryo-EM [J].
Al-Azzawi, Adil ;
Ouadou, Anes ;
Tanner, John J. ;
Cheng, Jianlin .
GENES, 2019, 10 (09)
[2]  
Banjac J., 2021, ARXIV210406237
[3]   2.2 Å resolution cryo-EM structure of β-galactosidase in complex with a cell-permeant inhibitor [J].
Bartesaghi, Alberto ;
Merk, Alan ;
Banerjee, Soojay ;
Matthies, Doreen ;
Wu, Xiongwu ;
Milne, Jacqueline L. S. ;
Subramaniam, Sriram .
SCIENCE, 2015, 348 (6239) :1147-1151
[4]  
Bendory T, 2020, IEEE SIGNAL PROC MAG, V37, P58, DOI [10.1109/MSP.2019.2957822, 10.1109/msp.2019.2957822]
[5]  
Bepler T., 2019, ARXIV190911663
[6]   Topaz-Denoise: general deep denoising models for cryoEM and cryoET [J].
Bepler, Tristan ;
Kelley, Kotaro ;
Noble, Alex J. ;
Berger, Bonnie .
NATURE COMMUNICATIONS, 2020, 11 (01)
[7]   Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs [J].
Bepler, Tristan ;
Morin, Andrew ;
Rapp, Micah ;
Brasch, Julia ;
Shapiro, Lawrence ;
Noble, Alex J. ;
Berger, Bonnie .
NATURE METHODS, 2019, 16 (11) :1153-+
[8]  
Bibas K., 2021, ARXIV210103549
[9]  
Bracewell R. N., 1956, AUST J PHYS, V9, P198, DOI [DOI 10.1071/PH560198, 10.1071/PH560198]
[10]   2.8 Å resolution reconstruction of the Thermoplasma acidophilum 20S proteasome using cryo-electron microscopy [J].
Campbell, Melody G. ;
Veesler, David ;
Cheng, Anchi ;
Potter, Clinton S. ;
Carragher, Bridget .
ELIFE, 2015, 4 :1-22