PIXER: an automated particle-selection method based on segmentation using a deep neural network

doi:10.1186/s12859-019-2614-y

	PIXER: an automated particle-selection method based on segmentation using a deep neural network
	Zhang, Jingrong 1,2; Wang, Zihao 1,2; Chen, Yu 1,2; Han, Renmin 3; Liu, Zhiyong 1; Sun, Fei 2,4,5; Zhang, Fa 1
	2019-01-18
发表期刊	BMC BIOINFORMATICS
ISSN	1471-2105
卷号	20 页码:14
摘要	BackgroundCryo-electron microscopy (cryo-EM) has become a widely used tool for determining the structures of proteins and macromolecular complexes. To acquire the input for single-particle cryo-EM reconstruction, researchers must select hundreds of thousands of particles from micrographs. As the signal-to-noise ratio (SNR) of micrographs is extremely low, the performance of automated particle-selection methods is still unable to meet research requirements. To free researchers from this laborious work and to acquire a large number of high-quality particles, we propose an automated particle-selection method (PIXER) based on the idea of segmentation using a deep neural network.ResultsFirst, to accommodate low-SNR conditions, we convert micrographs into probability density maps using a segmentation network. These probability density maps indicate the likelihood that each pixel of a micrograph is part of a particle instead of just background noise. Particles selected from density maps have a more robust signal than do those directly selected from the original noisy micrographs. Second, at present, there is no segmentation-training dataset for cryo-EM. To enable our plan, we present an automated method to generate a training dataset for segmentation using real-world data. Third, we propose a grid-based, local-maximum method to locate the particles from the probability density maps. We tested our method on simulated and real-world experimental datasets and compared PIXER with the mainstream methods RELION, DeepEM and DeepPicker to demonstrate its performance. The results indicate that, as a fully automated method, PIXER can acquire results as good as the semi-automated methods RELION and DeepEM.ConclusionTo our knowledge, our work is the first to address the particle-selection problem using the segmentation network concept. As a fully automated particle-selection method, PIXER can free researchers from laborious particle-selection work. Based on the results of experiments, PIXER can acquire accurate results under low-SNR conditions within minutes.
关键词	Cryo-electron microscope Single-particle analysis Deep learning Particle selection Segmentation
DOI	10.1186/s12859-019-2614-y
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFE0103900] ; National Key Research and Development Program of China[2017YFA0504702] ; NSFC[U1611263] ; NSFC[U1611261] ; NSFC[61472397] ; NSFC[61502455] ; NSFC[61672493] ; Special Program for Applied Research on Super Computation of the NSFC-Guangdong Joint Fund
WOS研究方向	Biochemistry & Molecular Biology ; Biotechnology & Applied Microbiology ; Mathematical & Computational Biology
WOS类目	Biochemical Research Methods ; Biotechnology & Applied Microbiology ; Mathematical & Computational Biology
WOS记录号	WOS:000456152300002
出版者	BMC
引用统计	被引频次：30[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/3465
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Fa
作者单位	1.Chinese Acad Sci, Inst Comp Technol, High Performance Comp Res Ctr, 6 Kexueyuan South Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.KAUST, CBRC, Comp Elect & Math Sci & Engn CEMSE Div, Thuwal 239556900, Saudi Arabia 4.Chinese Acad Sci, Inst Biophys, CAS Ctr Excellence Biomacromol, Natl Lab Biomacromol, 15 Datun Rd, Beijing 100101, Peoples R China 5.Chinese Acad Sci, Inst Biophys, Ctr Biol Imaging, 15 Datun Rd, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Jingrong,Wang, Zihao,Chen, Yu,et al. PIXER: an automated particle-selection method based on segmentation using a deep neural network[J]. BMC BIOINFORMATICS,2019,20:14.
APA	Zhang, Jingrong.,Wang, Zihao.,Chen, Yu.,Han, Renmin.,Liu, Zhiyong.,...&Zhang, Fa.(2019).PIXER: an automated particle-selection method based on segmentation using a deep neural network.BMC BIOINFORMATICS,20,14.
MLA	Zhang, Jingrong,et al."PIXER: an automated particle-selection method based on segmentation using a deep neural network".BMC BIOINFORMATICS 20(2019):14.