Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms

AITom: AI-guided cryo-electron tomography image analyses toolkit

Cryo-electron tomography (cryo-ET) is an essential tool in structural biology, uniquely capable of visualizing three-dimensional macromolecular complexes within their native cellular environments, thereby providing profound molecular-level insights. Despite its significant promise, cryo-ET faces persistent challenges in the systematic localization, identification, segmentation, and structural recovery of three-dimensional subcellular components, necessitating the development of efficient and accurate large-scale image analysis methods. In response to these complexities, this paper introduces AITom, an open-source artificial intelligence platform tailored for cryo-ET researchers. AITom integrates a comprehensive suite of public and proprietary algorithms, supporting both traditional template-based and template-free approaches, alongside state-of-the-art deep learning methodologies for cryo-ET data analysis. By incorporating diverse computational strategies, AITom enables researchers to more effectively tackle the complexities inherent in cryo-ET, facilitating precise analysis and interpretation of complex biological structures. Furthermore, AITom provides extensive tutorials for each analysis module, offering valuable guidance to users in utilizing its comprehensive functionalities.

A noise-robust classification method for cryo-ET subtomograms with out-of-distribution detection

MOTIVATION

Cryogenic electron tomography (cryo-ET) enables high-resolution 3D reconstruction of biological samples, with accurate subtomogram classification critical for structural analysis. However, current subtomogram classification methods often struggle with out-of-distribution (OOD) data issue, causing misclassification and mismatched structures.

RESULTS

To solve this problem, we propose a unified subtomogram classification framework that incorporates OOD detection to distinguish unknown (OOD) from known (in-distribution, ID) classes and predict labels for ID data, thereby enhancing existing subtomogram classification methods. Within this framework, we develop a noise-robust classification method that integrates a 3D discrete wavelet transform-based encoder to reduce high-frequency noise and extract robust features. Additionally, we incorporate a Mahalanobis distance-based OOD detector with a reliable metric for 3D subtomograms and introduce an adaptive classifier that adjusts to accommodate datasets of varying scales. The experimental and visualization results demonstrate that our noise-robust method improves subtomogram classification accuracy and effectively models features while enhancing OOD detection.

AVAILABILITY AND IMPLEMENTATION

Our code is available at https://github.com/yxs1137/Subtomo-Classification-with-OOD.git. The real data used in this study can be accessed through CryoET Data Portal.

Few-shot classification of Cryo-ET subvolumes with deep Brownian distance covariance

Few-shot learning is a crucial approach for macromolecule classification of the cryo-electron tomography (Cryo-ET) subvolumes, enabling rapid adaptation to novel tasks with a small support set of labeled data. However, existing few-shot classification methods for macromolecules in Cryo-ET consider only marginal distributions and overlook joint distributions, failing to capture feature dependencies fully. To address this issue, we propose a method for macromolecular few-shot classification using deep Brownian Distance Covariance (BDC). Our method models the joint distribution within a transfer learning framework, enhancing the modeling capabilities. We insert the BDC module after the feature extractor and only train the feature extractor during the training phase. Then, we enhance the model's generalization capability with self-distillation techniques. In the adaptation phase, we fine-tune the classifier with minimal labeled data. We conduct experiments on publicly available SHREC datasets and a small-scale synthetic dataset to evaluate our method. Results show that our method improves the classification capabilities by introducing the joint distribution.

Computational methods for in situ structural studies with cryogenic electron tomography

Cryo-electron tomography (cryo-ET) plays a critical role in imaging microorganisms in situ in terms of further analyzing the working mechanisms of viruses and drug exploitation, among others. A data processing workflow for cryo-ET has been developed to reconstruct three-dimensional density maps and further build atomic models from a tilt series of two-dimensional projections. Low signal-to-noise ratio (SNR) and missing wedge are two major factors that make the reconstruction procedure challenging. Because only few near-atomic resolution structures have been reconstructed in cryo-ET, there is still much room to design new approaches to improve universal reconstruction resolutions. This review summarizes classical mathematical models and deep learning methods among general reconstruction steps. Moreover, we also discuss current limitations and prospects. This review can provide software and methods for each step of the entire procedure from tilt series by cryo-ET to 3D atomic structures. In addition, it can also help more experts in various fields comprehend a recent research trend in cryo-ET. Furthermore, we hope that more researchers can collaborate in developing computational methods and mathematical models for high-resolution three-dimensional structures from cryo-ET datasets.

Isotropic reconstruction for electron tomography with deep learning

Cryogenic electron tomography (cryoET) allows visualization of cellular structures in situ. However, anisotropic resolution arising from the intrinsic "missing-wedge" problem has presented major challenges in visualization and interpretation of tomograms. Here, we have developed IsoNet, a deep learning-based software package that iteratively reconstructs the missing-wedge information and increases signal-to-noise ratio, using the knowledge learned from raw tomograms. Without the need for sub-tomogram averaging, IsoNet generates tomograms with significantly reduced resolution anisotropy. Applications of IsoNet to three representative types of cryoET data demonstrate greatly improved structural interpretability: resolving lattice defects in immature HIV particles, establishing architecture of the paraflagellar rod in Eukaryotic flagella, and identifying heptagon-containing clathrin cages inside a neuronal synapse of cultured cells. Therefore, by overcoming two fundamental limitations of cryoET, IsoNet enables functional interpretation of cellular tomograms without sub-tomogram averaging. Its application to high-resolution cellular tomograms should also help identify differently oriented complexes of the same kind for sub-tomogram averaging.

Volumetric macromolecule identification in cryo-electron tomograms using capsule networks

Background

Despite recent advances in cellular cryo-electron tomography (CET), developing automated tools for macromolecule identification in submolecular resolution remains challenging due to the lack of annotated data and high structural complexities. To date, the extent of the deep learning methods constructed for this problem is limited to conventional Convolutional Neural Networks (CNNs). Identifying macromolecules of different types and sizes is a tedious and time-consuming task. In this paper, we employ a capsule-based architecture to automate the task of macromolecule identification, that we refer to as 3D-UCaps. In particular, the architecture is composed of three components: feature extractor, capsule encoder, and CNN decoder. The feature extractor converts voxel intensities of input sub-tomograms to activities of local features. The encoder is a 3D Capsule Network (CapsNet) that takes local features to generate a low-dimensional representation of the input. Then, a 3D CNN decoder reconstructs the sub-tomograms from the given representation by upsampling.

Results

We performed binary and multi-class localization and identification tasks on synthetic and experimental data. We observed that the 3D-UNet and the 3D-UCaps had an \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1-$$\end{document}F1-score mostly above 60% and 70%, respectively, on the test data. In both network architectures, we observed degradation of at least 40% in the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score when identifying very small particles (PDB entry 3GL1) compared to a large particle (PDB entry 4D8Q). In the multi-class identification task of experimental data, 3D-UCaps had an \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score of 91% on the test data in contrast to 64% of the 3D-UNet. The better \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score of 3D-UCaps compared to 3D-UNet is obtained by a higher precision score. We speculate this to be due to the capsule network employed in the encoder. To study the effect of the CapsNet-based encoder architecture further, we performed an ablation study and perceived that the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score is boosted as network depth is increased which is in contrast to the previously reported results for the 3D-UNet. To present a reproducible work, source code, trained models, data as well as visualization results are made publicly available.

Conclusion

Quantitative and qualitative results show that 3D-UCaps successfully perform various downstream tasks including identification and localization of macromolecules and can at least compete with CNN architectures for this task. Given that the capsule layers extract both the existence probability and the orientation of the molecules, this architecture has the potential to lead to representations of the data that are better interpretable than those of 3D-UNet.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04901-w.

Applications of deep learning in electron microscopy

We review the growing use of machine learning in electron microscopy (EM) driven in part by the availability of fast detectors operating at kiloHertz frame rates leading to large data sets that cannot be processed using manually implemented algorithms. We summarize the various network architectures and error metrics that have been applied to a range of EM-related problems including denoising and inpainting. We then provide a review of the application of these in both physical and life sciences, highlighting how conventional networks and training data have been specifically modified for EM.

Cryo-shift: reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization

MOTIVATION

Cryo-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.

RESULTS

In 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 IMPLEMENTATION

https://github.com/xulabs/aitom.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography

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.

Few shot domain adaptation for in situ macromolecule structural classification in cryoelectron tomograms

MOTIVATION

Cryoelectron tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at submolecular resolution. Such information is critical for the accurate understanding of cellular processes. However, subtomogram classification remains one of the major challenges for the systematic recognition and recovery of the macromolecule structures in cryo-ET because of imaging limits and data quantity. Recently, deep learning has significantly improved the throughput and accuracy of large-scale subtomogram classification. However, often it is difficult to get enough high-quality annotated subtomogram data for supervised training due to the enormous expense of labeling. To tackle this problem, it is beneficial to utilize another already annotated dataset to assist the training process. However, due to the discrepancy of image intensity distribution between source domain and target domain, the model trained on subtomograms in source domain may perform poorly in predicting subtomogram classes in the target domain.

RESULTS

In this article, we adapt a few shot domain adaptation method for deep learning-based cross-domain subtomogram classification. The essential idea of our method consists of two parts: (i) take full advantage of the distribution of plentiful unlabeled target domain data, and (ii) exploit the correlation between the whole source domain dataset and few labeled target domain data. Experiments conducted on simulated and real datasets show that our method achieves significant improvement on cross domain subtomogram classification compared with baseline methods.

AVAILABILITY AND IMPLEMENTATION

Software is available online https://github.com/xulabs/aitom.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography

MOTIVATION

Cryo-Electron Tomography (cryo-ET) is a 3D bioimaging tool that visualizes the structural and spatial organization of macromolecules at a near-native state in single cells, which has broad applications in life science. However, the systematic structural recognition and recovery of macromolecules captured by cryo-ET are difficult due to high structural complexity and imaging limits. Deep learning based subtomogram classification have played critical roles for such tasks. As supervised approaches, however, their performance relies on sufficient and laborious annotation on a large training dataset.

RESULTS

To alleviate this major labeling burden, we proposed a Hybrid Active Learning (HAL) framework for querying subtomograms for labelling from a large unlabeled subtomogram pool. Firstly, HAL adopts uncertainty sampling to select the subtomograms that have the most uncertain predictions. This strategy enforces the model to be aware of the inductive bias during classification and subtomogram selection, which satisfies the discriminativeness principle in AL literature. Moreover, to mitigate the sampling bias caused by such strategy, a discriminator is introduced to judge if a certain subtomogram is labeled or unlabeled and subsequently the model queries the subtomogram that have higher probabilities to be unlabeled. Such query strategy encourages to match the data distribution between the labeled and unlabeled subtomogram samples, which essentially encodes the representativeness criterion into the subtomogram selection process. Additionally, HAL introduces a subset sampling strategy to improve the diversity of the query set, so that the information overlap is decreased between the queried batches and the algorithmic efficiency is improved. Our experiments on subtomogram classification tasks using both simulated and real data demonstrate that we can achieve comparable testing performance (on average only 3% accuracy drop) by using less than 30% of the labeled subtomograms, which shows a very promising result for subtomogram classification task with limited labeling resources.

AVAILABILITY

https://github.com/xulabs/aitom.

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

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.

Few-shot learning for classification of novel macromolecular structures in cryo-electron tomograms

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.

Three-dimensional deconvolution processing for STEM cryotomography

The complex environment of biological cells and tissues has motivated development of three-dimensional (3D) imaging in both light and electron microscopies. To this end, one of the primary tools in fluorescence microscopy is that of computational deconvolution. Wide-field fluorescence images are often corrupted by haze due to out-of-focus light, i.e., to cross-talk between different object planes as represented in the 3D image. Using prior understanding of the image formation mechanism, it is possible to suppress the cross-talk and reassign the unfocused light to its proper source post facto. Electron tomography based on tilted projections also exhibits a cross-talk between distant planes due to the discrete angular sampling and limited tilt range. By use of a suitably synthesized 3D point spread function, we show here that deconvolution leads to similar improvements in volume data reconstructed from cryoscanning transmission electron tomography (CSTET), namely a dramatic in-plane noise reduction and improved representation of features in the axial dimension. Contrast enhancement is demonstrated first with colloidal gold particles and then in representative cryotomograms of intact cells. Deconvolution of CSTET data collected from the periphery of an intact nucleus revealed partially condensed, extended structures in interphase chromatin.

Adversarial domain adaptation for cross data source macromolecule in situ structural classification in cellular electron cryo-tomograms

MOTIVATION

Since 2017, an increasing amount of attention has been paid to the supervised deep learning-based macromolecule in situ structural classification (i.e. subtomogram classification) in cellular electron cryo-tomography (CECT) due to the substantially higher scalability of deep learning. However, the success of such supervised approach relies heavily on the availability of large amounts of labeled training data. For CECT, creating valid training data from the same data source as prediction data is usually laborious and computationally intensive. It would be beneficial to have training data from a separate data source where the annotation is readily available or can be performed in a high-throughput fashion. However, the cross data source prediction is often biased due to the different image intensity distributions (a.k.a. domain shift).

RESULTS

We adapt a deep learning-based adversarial domain adaptation (3D-ADA) method to timely address the domain shift problem in CECT data analysis. 3D-ADA first uses a source domain feature extractor to extract discriminative features from the training data as the input to a classifier. Then it adversarially trains a target domain feature extractor to reduce the distribution differences of the extracted features between training and prediction data. As a result, the same classifier can be directly applied to the prediction data. We tested 3D-ADA on both experimental and realistically simulated subtomogram datasets under different imaging conditions. 3D-ADA stably improved the cross data source prediction, as well as outperformed two popular domain adaptation methods. Furthermore, we demonstrate that 3D-ADA can improve cross data source recovery of novel macromolecular structures.

AVAILABILITY AND IMPLEMENTATION

https://github.com/xulabs/projects.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

In situ structure determination by subtomogram averaging

Cryo-tomography and subtomogram averaging are increasingly popular techniques for structural determination of macromolecular complexes in situ. They have the potential to achieve high-resolution views of native complexes, together with the details of their location relative to interacting molecules. The subtomogram averaging (StA) pipelines are well-established, with current developments aiming to optimise each step by reducing manual intervention and user decisions, following similar trends in single-particle approaches that have dramatically increased their popularity. Here, we review the main steps of typical StA workflows. We focus on considerations arising from the fact that the objects of study are embedded within unique crowded environments, and we emphasise those steps where careful decisions need to be made by the user.

Subtomogram averaging from cryo-electron tomograms

Cryo-electron tomography (cryo-ET) allows three-dimensional (3D) visualization of frozen-hydrated biological samples, such as protein complexes and cell organelles, in near-native environments at nanometer scale. Protein complexes that are present in multiple copies in a set of tomograms can be extracted, mutually aligned, and averaged to yield a signal-enhanced 3D structure up to sub-nanometer or even near-atomic resolution. This technique, called subtomogram averaging (StA), is powered by improvements in EM hardware and image processing software. Importantly, StA provides unique biological insights into the structure and function of cellular machinery in close-to-native contexts. In this chapter, we describe the principles and key steps of StA. We briefly cover sample preparation and data collection with an emphasis on image processing procedures related to tomographic reconstruction, subtomogram alignment, averaging, and classification. We conclude by summarizing current limitations and future directions of this technique with a focus on high-resolution StA.

De Novo Structural Pattern Mining in Cellular Electron Cryotomograms

Electron cryotomography enables 3D visualization of cells in a near-native state at molecular resolution. The produced cellular tomograms contain detailed information about a plethora of macromolecular complexes, their structures, abundances, and specific spatial locations in the cell. However, extracting this information in a systematic way is very challenging, and current methods usually rely on individual templates of known structures. Here, we propose a framework called "Multi-Pattern Pursuit" for de novo discovery of different complexes from highly heterogeneous sets of particles extracted from entire cellular tomograms without using information of known structures. These initially detected structures can then serve as input for more targeted refinement efforts. Our tests on simulated and experimental tomograms show that our automated method is a promising tool for supporting large-scale template-free visual proteomics analysis.

Feature Decomposition Based Saliency Detection in Electron Cryo-Tomograms

Electron Cryo-Tomography (ECT) allows 3D visualization of subcellular structures at the submolecular resolution in close to the native state. However, due to the high degree of structural complexity and imaging limits, the automatic segmentation of cellular components from ECT images is very difficult. To complement and speed up existing segmentation methods, it is desirable to develop a generic cell component segmentation method that is 1) not specific to particular types of cellular components, 2) able to segment unknown cellular components, 3) fully unsupervised and does not rely on the availability of training data. As an important step towards this goal, in this paper, we propose a saliency detection method that computes the likelihood that a subregion in a tomogram stands out from the background. Our method consists of four steps: supervoxel over-segmentation, feature extraction, feature matrix decomposition, and computation of saliency. The method produces a distribution map that represents the regions' saliency in tomograms. Our experiments show that our method can successfully label most salient regions detected by a human observer, and able to filter out regions not containing cellular components. Therefore, our method can remove the majority of the background region, and significantly speed up the subsequent processing of segmentation and recognition of cellular components captured by ECT.

Improved deep learning-based macromolecules structure classification from electron cryo-tomograms

Cellular processes are governed by macromolecular complexes inside the cell. Study of the native structures of macromolecular complexes has been extremely difficult due to lack of data. With recent breakthroughs in Cellular Electron Cryo-Tomography (CECT) 3D imaging technology, it is now possible for researchers to gain accesses to fully study and understand the macro-molecular structures single cells. However, systematic recovery of macromolecular structures from CECT is very difficult due to high degree of structural complexity and practical imaging limitations. Specifically, we proposed a deep learning-based image classification approach for large-scale systematic macromolecular structure separation from CECT data. However, our previous work was only a very initial step toward exploration of the full potential of deep learning-based macromolecule separation. In this paper, we focus on improving classification performance by proposing three newly designed individual CNN models: an extended version of (Deep Small Receptive Field) DSRF3D, donated as DSRF3D-v2, a 3D residual block-based neural network, named as RB3D, and a convolutional 3D (C3D)-based model, CB3D. We compare them with our previously developed model (DSRF3D) on 12 datasets with different SNRs and tilt angle ranges. The experiments show that our new models achieved significantly higher classification accuracies. The accuracies are not only higher than 0.9 on normal datasets, but also demonstrate potentials to operate on datasets with high levels of noises and missing wedge effects presented.

Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography

Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured by CECT, methods for several important tasks such as subtomogram classification and semantic segmentation have been developed. However, the recognition and recovery of macromolecular structures are still very difficult due to high molecular structural diversity, crowding molecular environment, and the imaging limitations of CECT. In this paper, we propose a novel multi-task 3D convolutional neural network model for simultaneous classification, segmentation, and coarse structural recovery of macromolecules of interest in subtomograms. In our model, the learned image features of one task are shared and thereby mutually reinforce the learning of other tasks. Evaluated on realistically simulated and experimental CECT data, our multi-task learning model outperformed all single-task learning methods for classification and segmentation. In addition, we demonstrate that our model can generalize to discover, segment and recover novel structures that do not exist in the training data.

Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations

The convolutional neural network (CNN) has become a powerful tool for various biomedical image analysis tasks, but there is a lack of visual explanation for the machinery of CNNs. In this paper, we present a novel algorithm, Respond-weighted Class Activation Mapping (Respond-CAM), for making CNN-based models interpretable by visualizing input regions that are important for predictions, especially for biomedical 3D imaging data inputs. Our method uses the gradients of any target concept (e.g. the score of target class) that flow into a convolutional layer. The weighted feature maps are combined to produce a heatmap that highlights the important regions in the image for predicting the target concept. We prove a preferable sum-to-score property of the Respond-CAM and verify its significant improvement on 3D images from the current state-of-the-art approach. Our tests on Cellular Electron Cryo-Tomography 3D images show that Respond-CAM achieves superior performance on visualizing the CNNs with 3D biomedical image inputs, and is able to get reasonably good results on visualizing the CNNs with natural image inputs. The Respond-CAM is an efficient and reliable approach for visualizing the CNN machinery, and is applicable to a wide variety of CNN model families and image analysis tasks. Our code is available at: https://github.com/xulabs/projects/tree/master/respond_cam.

Model Compression for Faster Structural Separation of Macromolecules Captured by Cellular Electron Cryo-Tomography

Electron Cryo-Tomography (ECT) enables 3D visualization of macromolecule structure inside single cells. Macromolecule classification approaches based on convolutional neural networks (CNN) were developed to separate millions of macromolecules captured from ECT systematically. However, given the fast accumulation of ECT data, it will soon become necessary to use CNN models to efficiently and accurately separate substantially more macromolecules at the prediction stage, which requires additional computational costs. To speed up the prediction, we compress classification models into compact neural networks with little in accuracy for deployment. Specifically, we propose to perform model compression through knowledge distillation. Firstly, a complex teacher network is trained to generate soft labels with better classification feasibility followed by training of customized student networks with simple architectures using the soft label to compress model complexity. Our tests demonstrate that our compressed models significantly reduce the number of parameters and time cost while maintaining similar classification accuracy.

A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation

Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes. In addition, the autoencoder can be used to detect non-cellular features related to sample preparation and data collection, such as carbon edges from the grid and tomogram boundaries. The autoencoder is also able to detect patterns that may indicate spatial interactions between cellular components. Furthermore, we demonstrate that our autoencoder can be used for weakly supervised semantic segmentation of cellular components, requiring a very small amount of manual annotation.

Big data in cryoEM: automated collection, processing and accessibility of EM data

The scope and complexity of cryogenic electron microscopy (cryoEM) data has greatly increased, and will continue to do so, due to recent and ongoing technical breakthroughs that have led to much improved resolutions for macromolecular structures solved using this method. This big data explosion includes single particle data as well as tomographic tilt series, both generally acquired as direct detector movies of ∼10-100 frames per image or per tilt-series. We provide a brief survey of the developments leading to the current status, and describe existing cryoEM pipelines, with an emphasis on the scope of data acquisition, methods for automation, and use of cloud storage and computing.