Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms.
Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms.
复制标题
DOI：
10.1093/bioinformatics/btx230
复制
发表时间：
2017-07-15
期刊：
影响因子：
--
通讯作者：
Xing EP
中科院分区：
文献类型：
--
作者：
Xu M;Chai X;Muthakana H;Liang X;Yang G;Zeev-Ben-Mordehai T;Xing EP
细胞电子冷冻断层扫描（CECT）能够在近天然状态和亚分子分辨率下对细胞组织进行3D可视化，使其成为分析单细胞内大分子复合物结构及其空间组织的有力工具。然而，高度的结构复杂性以及实际成像的限制使得细胞内结构的系统性从头发现具有挑战性。它可能需要平均和分类数以百万计的子断层图像可能包含数百个高度异质性的结构类。尽管由于数据采集自动化的进步，采集包含这样数量的子断层图像的CECT数据不再困难，但是现有的计算方法具有非常有限的可扩展性或辨别能力，使得它们不能处理这样数量的数据。为了补充现有的方法，在这篇文章中，我们提出了一种新的方法细分subtomographs成较小的，但相对均匀的子集。然后，可以使用现有的计算密集型方法分别恢复这些子集中的结构。我们的方法基于使用深度学习的监督结构特征提取，结合无监督聚类和无参考分类。实验结果表明，与现有的基于无监督旋转不变特征和姿态归一化的方法相比，该方法在识别能力和可扩展性方面都有了显著的提高.更重要的是，我们的新方法能够发现新的结构类，并恢复训练数据中不存在的结构。源代码可在http：//www.cs.cmu.edu/software上免费获得。 补充数据可在Bioinformatics在线获得。
Cellular Electron CryoTomography (CECT) enables 3D visualization of cellular organization at near-native state and in sub-molecular resolution, making it a powerful tool for analyzing structures of macromolecular complexes and their spatial organizations inside single cells. However, high degree of structural complexity together with practical imaging limitations makes the systematic de novo discovery of structures within cells challenging. It would likely require averaging and classifying millions of subtomograms potentially containing hundreds of highly heterogeneous structural classes. Although it is no longer difficult to acquire CECT data containing such amount of subtomograms due to advances in data acquisition automation, existing computational approaches have very limited scalability or discrimination ability, making them incapable of processing such amount of data. To complement existing approaches, in this article we propose a new approach for subdividing subtomograms into smaller but relatively homogeneous subsets. The structures in these subsets can then be separately recovered using existing computation intensive methods. Our approach is based on supervised structural feature extraction using deep learning, in combination with unsupervised clustering and reference-free classification. Our experiments show that, compared with existing unsupervised rotation invariant feature and pose-normalization based approaches, our new approach achieves significant improvements in both discrimination ability and scalability. More importantly, our new approach is able to discover new structural classes and recover structures that do not exist in training data. Source code freely available at http://www.cs.cmu.edu/∼mxu1/software. Supplementary data are available at Bioinformatics online.
登录
查看更多内容
影响因子：
48
作者：
Beck, Martin;Malmstroem, Johan A.;Lange, Vinzenz;Schmidt, Alexander;Deutsch, Eric W.;Aebersold, Ruedi
通讯作者：
Aebersold, Ruedi
影响因子：
6.8
作者：
Briggs, John A. G.
通讯作者：
Briggs, John A. G.
影响因子：
3.8
作者：
Grünewald, K;Medalia, O;Baumeister, W
通讯作者：
Baumeister, W
影响因子：
3
作者：
Bartesaghi, A.;Sprechmann, P.;Subramaniam, S.
通讯作者：
Subramaniam, S.
影响因子：
56.9
作者：
Asano, Shoh;Fukuda, Yoshiyuki;Baumeister, Wolfgang
通讯作者：
Baumeister, Wolfgang