Zhou Bo, Yu Haisu, Zeng Xiangrui, Yang Xiaoyan, Zhang Jing, Xu Min
Department of Biomedical Engineering, Yale University, New Haven, CT, United States.
Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, United States.
Front Mol Biosci. 2021 Jan 12;7:613347. doi: 10.3389/fmolb.2020.613347. eCollection 2020.
Cryo-electron Tomography (cryo-ET) generates 3D visualization of cellular organization that allows biologists to analyze cellular structures in a near-native state with nano resolution. Recently, deep learning methods have demonstrated promising performance in classification and segmentation of macromolecule structures captured by cryo-ET, but training individual deep learning models requires large amounts of manually labeled and segmented data from previously observed classes. To perform classification and segmentation in the wild (i.e., with limited training data and with unseen classes), novel deep learning model needs to be developed to classify and segment unseen macromolecules captured by cryo-ET. In this paper, we develop a one-shot learning framework, called cryo-ET one-shot network (COS-Net), for simultaneous classification of macromolecular structure and generation of the voxel-level 3D segmentation, using only one training sample per class. Our experimental results on 22 macromolecule classes demonstrated that our COS-Net could efficiently classify macromolecular structures with small amounts of samples and produce accurate 3D segmentation at the same time.
冷冻电子断层扫描（cryo-ET）可生成细胞组织的三维可视化图像，使生物学家能够以纳米分辨率分析近天然状态下的细胞结构。最近，深度学习方法在冷冻电子断层扫描捕获的大分子结构分类和分割方面展现出了良好的性能，但训练单个深度学习模型需要大量来自先前观察类别的手动标记和分割数据。为了在实际场景中进行分类和分割（即训练数据有限且存在未见类别的情况），需要开发新的深度学习模型来对冷冻电子断层扫描捕获的未见大分子进行分类和分割。在本文中，我们开发了一种一次性学习框架，称为冷冻电子断层扫描一次性网络（COS-Net），用于同时对大分子结构进行分类并生成体素级别的三维分割，每个类别仅使用一个训练样本。我们在22个大分子类别上的实验结果表明，我们的COS-Net能够使用少量样本高效地对大分子结构进行分类，并同时生成准确的三维分割。
