More Like this

1. One-Shot Learning With Attention-Guided Segmentation in Cryo-Electron Tomography

   https://doi.org/10.3389/fmolb.2020.613347  

   Zhou, Bo; Yu, Haisu; Zeng, Xiangrui; Yang, Xiaoyan; Zhang, Jing; Xu, Min (January 2021, Frontiers in Molecular Biosciences)

   null (Ed.)

   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. 

   more » « less
2. Cryo-shift: reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization

   https://doi.org/10.1093/bioinformatics/btab794  

   Bandyopadhyay, Hmrishav; Deng, Zihao; Ding, Leiting; Liu, Sinuo; Uddin, Mostofa Rafid; Zeng, Xiangrui; Behpour, Sima; Xu, Min; Xu, ed., Jinbo (November 2021, Bioinformatics)

   Abstract MotivationCryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution. Cellular cryo-ET images help in resolving the structures of macromolecules and determining their spatial relationship in a single cell, which has broad significance in cell and structural biology. Subtomogram classification and recognition constitute a primary step in the systematic recovery of these macromolecular structures. Supervised deep learning methods have been proven to be highly accurate and efficient for subtomogram classification, but suffer from limited applicability due to scarcity of annotated data. While generating simulated data for training supervised models is a potential solution, a sizeable difference in the image intensity distribution in generated data as compared with real experimental data will cause the trained models to perform poorly in predicting classes on real subtomograms. ResultsIn this work, we present Cryo-Shift, a fully unsupervised domain adaptation and randomization framework for deep learning-based cross-domain subtomogram classification. We use unsupervised multi-adversarial domain adaption to reduce the domain shift between features of simulated and experimental data. We develop a network-driven domain randomization procedure with ‘warp’ modules to alter the simulated data and help the classifier generalize better on experimental data. We do not use any labeled experimental data to train our model, whereas some of the existing alternative approaches require labeled experimental samples for cross-domain classification. Nevertheless, Cryo-Shift outperforms the existing alternative approaches in cross-domain subtomogram classification in extensive evaluation studies demonstrated herein using both simulated and experimental data. Availabilityand implementationhttps://github.com/xulabs/aitom. Supplementary informationSupplementary data are available at Bioinformatics online. 

   more » « less
3. Beyond X-rays: an overview of emerging structural biology methods

   https://doi.org/10.1042/ETLS20200272  

   Schaffer, Jason E.; Kukshal, Vandna; Miller, Justin J.; Kitainda, Vivian; Jez, Joseph M. (February 2021, Emerging Topics in Life Sciences)

   Jez, Joseph M.; Topp, Christopher N. (Ed.)

   Structural biologists rely on X-ray crystallography as the main technique for determining the three-dimensional structures of macromolecules; however, in recent years, new methods that go beyond X-ray-based technologies are broadening the selection of tools to understand molecular structure and function. Simultaneously, national facilities are developing programming tools and maintaining personnel to aid novice structural biologists in de novo structure determination. The combination of X-ray free electron lasers (XFELs) and serial femtosecond crystallography (SFX) now enable time-resolved structure determination that allows for capture of dynamic processes, such as reaction mechanism and conformational flexibility. XFEL and SFX, along with microcrystal electron diffraction (MicroED), help side-step the need for large crystals for structural studies. Moreover, advances in cryogenic electron microscopy (cryo-EM) as a tool for structure determination is revolutionizing how difficult to crystallize macromolecules and/or complexes can be visualized at the atomic scale. This review aims to provide a broad overview of these new methods and to guide readers to more in-depth literature of these methods. 

   more » « less
4. Electron microscopy for imaging organelles in plants and algae

   https://doi.org/10.1093/plphys/kiab449  

   Weiner, Ethan; Pinskey, Justine M; Nicastro, Daniela; Otegui, Marisa S (September 2021, Plant Physiology)

   Abstract Recent developments in both instrumentation and image analysis algorithms have allowed three-dimensional electron microscopy (3D-EM) to increase automated image collections through large tissue volumes using serial block-face scanning EM (SEM) and to achieve near-atomic resolution of macromolecular complexes using cryo-electron tomography (cryo-ET) and sub-tomogram averaging. In this review, we discuss applications of cryo-ET to cell biology research on plant and algal systems and the special opportunities they offer for understanding the organization of eukaryotic organelles with unprecedently resolution. However, one of the most challenging aspects for cryo-ET is sample preparation, especially for multicellular organisms. We also discuss correlative light and electron microscopy (CLEM) approaches that have been developed for ET at both room and cryogenic temperatures. 

   more » « less
5. Few-shot learning for classification of novel macromolecular structures in cryo-electron tomograms

   https://doi.org/10.1371/journal.pcbi.1008227  

   Li, Ran; Yu, Liangyong; Zhou, Bo; Zeng, Xiangrui; Wang, Zhenyu; Yang, Xiaoyan; Zhang, Jing; Gao, Xin; Jiang, Rui; Xu, Min (November 2020, PLOS Computational Biology)

   Haliloglu, Turkan (Ed.)

   Cryo-electron tomography (cryo-ET) provides 3D visualization of subcellular components in the near-native state and at sub-molecular resolutions in single cells, demonstrating an increasingly important role in structural biology in situ . However, systematic recognition and recovery of macromolecular structures in cryo-ET data remain challenging as a result of low signal-to-noise ratio (SNR), small sizes of macromolecules, and high complexity of the cellular environment. Subtomogram structural classification is an essential step for such task. Although acquisition of large amounts of subtomograms is no longer an obstacle due to advances in automation of data collection, obtaining the same number of structural labels is both computation and labor intensive. On the other hand, existing deep learning based supervised classification approaches are highly demanding on labeled data and have limited ability to learn about new structures rapidly from data containing very few labels of such new structures. In this work, we propose a novel approach for subtomogram classification based on few-shot learning. With our approach, classification of unseen structures in the training data can be conducted given few labeled samples in test data through instance embedding. Experiments were performed on both simulated and real datasets. Our experimental results show that we can make inference on new structures given only five labeled samples for each class with a competitive accuracy (> 0.86 on the simulated dataset with SNR = 0.1), or even one sample with an accuracy of 0.7644. The results on real datasets are also promising with accuracy > 0.9 on both conditions and even up to 1 on one of the real datasets. Our approach achieves significant improvement compared with the baseline method and has strong capabilities of generalizing to other cellular components. 

   more » « less