中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography

文献类型：期刊论文

作者Gao, Shan1,2; Han, Renmin3; Zeng, Xiangrui4; Liu, Zhiyong5; Xu, Min4; Zhang, Fa5
刊名IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
出版日期2022
卷号19期号:1页码:209-219
关键词Cryo-electron tomography image classification convolution neural network
ISSN号1545-5963
DOI10.1109/TCBB.2021.3065986
英文摘要Cryo-electron tomography, combined with subtomogram averaging (STA), can reveal three-dimensional (3D) macromolecule structures in the near-native state from cells and other biological samples. In STA, to get a high-resolution 3D view of macromolecule structures, diverse macromolecules captured by the cellular tomograms need to be accurately classified. However, due to the poor signal-to-noise-ratio (SNR) and severe ray artifacts in the tomogram, it remains a major challenge to classify macromolecules with high accuracy. In this paper, we propose a new convolutional neural network, named 3D-Dilated-DenseNet, to improve the performance of macromolecule classification. In 3D-Dilated-DenseNet, there are two key strategies to guarantee macromolecule classification accuracy: 1) Using dense connections to enhance feature map utilization (corresponding to the baseline 3D-C-DenseNet); 2) Adopting dilated convolution to enrich multi-level information in feature maps. We tested 3D-Dilated-DenseNet and 3D-C-DenseNet both on synthetic data and experimental data. The results show that, on synthetic data, compared with the state-of-the-art method in the SHREC contest (SHREC-CNN), both 3D-C-DenseNet and 3D-Dilated-DenseNet outperform SHREC-CNN. In particular, 3D-Dilated-DenseNet improves 0.393 of F1 metric on tiny-size macromolecules and 0.213 on small-size macromolecules. On experimental data, compared with 3D-C-DenseNet, 3D-Dilated-DenseNet can increase classification performance by 2.1 percent.
资助项目National Key Research and Development Program of China[2017YFA0504702] ; National Key Research and Development Program of China[2017YFE0103900] ; NSFC[61932018] ; NSFC[62072441] ; NSFC[62072280] ; NSFC[62072283] ; Beijing Municipal Natural Science Foundation[L182053] ; Postgraduate Study Abroad Program of National Construction on High-level Universities - China Scholarship Council
WOS研究方向Biochemistry & Molecular Biology ; Computer Science ; Mathematics
语种英语
WOS记录号WOS:000752015800024
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/19000]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Gao, Shan
作者单位1.Chinese Acad Sci, Performance Comp Res Ctr, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
3.Shandong Univ, Res Ctr Math & Interdisciplinary Sci, Qingdao 266237, Peoples R China
4.Carnegie Mellon Univ, Sch Comp Sci, Computat Biol Dept, Pittsburgh, PA 15213 USA
5.Chinese Acad Sci, High Performance Comp Res Ctr, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Gao, Shan,Han, Renmin,Zeng, Xiangrui,et al. Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography[J]. IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS,2022,19(1):209-219.
APA Gao, Shan,Han, Renmin,Zeng, Xiangrui,Liu, Zhiyong,Xu, Min,&Zhang, Fa.(2022).Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography.IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS,19(1),209-219.
MLA Gao, Shan,et al."Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography".IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 19.1(2022):209-219.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。