SHREC 2020: Classification in cryo-electron tomograms

doi:10.1016/j.cag.2020.07.010

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	SHREC 2020: Classification in cryo-electron tomograms
	Gubins, Ilja 1; Chaillet, Marten L.2; van der Schot, Gijs 2; Veltkamp, Remco C.1; Forster, Friedrich 2; Hao, Yu 3; Wan, Xiaohua 3; Cui, Xuefeng 4; Zhang, Fa 3; Moebel, Emmanuel 5
刊名	COMPUTERS & GRAPHICS-UK
	2020-10-01
卷号	91 页码:279-289
关键词	Cryo-electron tomography Computer vision Pattern recognition Protein classification Benchmark
ISSN号	0097-8493
DOI	10.1016/j.cag.2020.07.010
英文摘要	Cryo-electron tomography (cryo-ET) is an imaging technique that allows us to three-dimensionally visualize both the structural details of macro-molecular assemblies under near-native conditions and its cellular context. Electrons strongly interact with biological samples, limiting electron dose. The latter limits the signal-to-noise ratio and hence resolution of an individual tomogram to about 50 (5 nm). Biological molecules can be obtained by averaging volumes, each depicting copies of the molecule, allowing for resolutions beyond 4 (0.4 nm). To this end, the ability to localize and classify components is crucial, but challenging due to the low signal-to-noise ratio. Computational innovation is key to mine biological information from cryo-electron tomography. To promote such innovation, we provide a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in cryo-electron tomograms. Our publicly available dataset contains ten tomographic reconstructions of simulated cell-like volumes. Each volume contains twelve different types of complexes, varying in size, function and structure. In this paper, we have evaluated seven different methods of finding and classifying proteins. Six research groups present results obtained with learning-based methods and trained on the simulated dataset, as well as a baseline template matching, a traditional method widely used in cryo-ET research. We find that method performance correlates with particle size, especially noticeable for template matching which performance degrades rapidly as the size decreases. We learn that neural networks can achieve significantly better localization and classification performance, in particular convolutional networks with focus on high-resolution details such as those based on U-Net architecture. (C) 2020 Elsevier Ltd. All rights reserved.
资助项目	European Research Council under the European Union[724425 - BENDER] ; Nederlandse Organisatie voor Wetenschappelijke Onderzoek[Vici 724.016.001] ; Nederlandse Organisatie voor Wetenschappelijke Onderzoek[741.018.201]
WOS研究方向	Computer Science
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:000577434300023
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/15678]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gubins, Ilja
作者单位	1.Univ Utrecht, Dept Informat & Comp Sci, Utrecht, Netherlands 2.Univ Utrecht, Dept Chem, Utrecht, Netherlands 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 4.Shandong Univ, Sch Comp Sci & Technol, Jinan, Peoples R China 5.Inria Rennes Bretagne Atlantique, Rennes, France 6.Purdue Univ, Dept Comp Sci, W Lafayette, IN 47907 USA 7.Purdue Univ, Computat Biol Dept, W Lafayette, IN 47907 USA 8.Carnegie Mellon Univ, Computat Biol Dept, Pittsburgh, PA 15213 USA 9.Univ Missouri, Dept Elect Engn & Comp Sci, Columbia, MO 65211 USA 10.Univ Missouri, Dept Biochem, Columbia, MO USA
推荐引用方式 GB/T 7714	Gubins, Ilja,Chaillet, Marten L.,van der Schot, Gijs,et al. SHREC 2020: Classification in cryo-electron tomograms[J]. COMPUTERS & GRAPHICS-UK,2020,91:279-289.
APA	Gubins, Ilja.,Chaillet, Marten L..,van der Schot, Gijs.,Veltkamp, Remco C..,Forster, Friedrich.,...&Bunyak, Filiz.(2020).SHREC 2020: Classification in cryo-electron tomograms.COMPUTERS & GRAPHICS-UK,91,279-289.
MLA	Gubins, Ilja,et al."SHREC 2020: Classification in cryo-electron tomograms".COMPUTERS & GRAPHICS-UK 91(2020):279-289.