Recent Deep Learning Methods Research Articles

CNN-Based Detector for Spectrum Sensing With General Noise Models

In this paper, we consider spectrum sensing (SS) problems with various general noise models such as Middleton class A (MCA), isometric complex symmetric <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> -stable ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{S}\alpha \text{S}$ </tex-math></inline-formula> ), and isometric complex generalized Gaussian distribution (CGGD). This approach enables us to examine the effect of practical phenomena such as impulsive noise on SS problems. In this general framework, we propose a detector based on convolutional neural networks (CNNs) with favorable performance under various noise models. The proposed model-free and data-driven CNN offers robustness in diverse noise scenarios. Thus, it can be utilized in environments with different physical behaviors. We demonstrate this method outperforms the highly regarded likelihood ratio test (LRT) in most cases. For all impulsive cases, the proposed CNN is the superior detector, providing a near-optimum performance for the conventional Gaussian noise. We indicate the proposed data-driven CNN offers an appropriate alternative solution to LRT. However, it requires more computational operations, a rich training dataset, and a training process, instead. Furthermore, the main rationale for proposing this CNN is that it enables the network to generalize its effective performance to various noise models and cases. To this end, quantitative simulations confirm superiority of the proposed CNN compared to other recent deep-learning methods.

Classification of benign and malignant subtypes of breast cancer histopathology imaging using hybrid CNN-LSTM based transfer learning

BackgroundGrading of cancer histopathology slides requires more pathologists and expert clinicians as well as it is time consuming to look manually into whole-slide images. Hence, an automated classification of histopathological breast cancer sub-type is useful for clinical diagnosis and therapeutic responses. Recent deep learning methods for medical image analysis suggest the utility of automated radiologic imaging classification for relating disease characteristics or diagnosis and patient stratification.MethodsTo develop a hybrid model using the convolutional neural network (CNN) and the long short-term memory recurrent neural network (LSTM RNN) to classify four benign and four malignant breast cancer subtypes. The proposed CNN-LSTM leveraging on ImageNet uses a transfer learning approach in classifying and predicting four subtypes of each. The proposed model was evaluated on the BreakHis dataset comprises 2480 benign and 5429 malignant cancer images acquired at magnifications of 40×, 100×, 200× and 400×.ResultsThe proposed hybrid CNN-LSTM model was compared with the existing CNN models used for breast histopathological image classification such as VGG-16, ResNet50, and Inception models. All the models were built using three different optimizers such as adaptive moment estimator (Adam), root mean square propagation (RMSProp), and stochastic gradient descent (SGD) optimizers by varying numbers of epochs. From the results, we noticed that the Adam optimizer was the best optimizer with maximum accuracy and minimum model loss for both the training and validation sets. The proposed hybrid CNN-LSTM model showed the highest overall accuracy of 99% for binary classification of benign and malignant cancer, and, whereas, 92.5% for multi-class classifier of benign and malignant cancer subtypes, respectively.ConclusionTo conclude, the proposed transfer learning approach outperformed the state-of-the-art machine and deep learning models in classifying benign and malignant cancer subtypes. The proposed method is feasible in classification of other cancers as well as diseases.

Joint contrastive triple-learning for deep multi-view clustering

Deep multi-view clustering (MVC) is to mine and employ the complex relationships among views to learn the compact data clusters with deep neural networks in an unsupervised manner. The more recent deep contrastive learning (CL) methods have shown promising performance in MVC by learning cluster-oriented deep feature representations, which is realized by contrasting the positive and negative sample pairs. However, most existing deep contrastive MVC methods only focus on the one-side contrastive learning, such as feature-level or cluster-level contrast, failing to integrating the two sides together or bringing in more important aspects of contrast. Additionally, most of them work in a separate two-stage manner, i.e., first feature learning and then data clustering, failing to mutually benefit each other. To fix the above challenges, in this paper we propose a novel joint contrastive triple-learning framework to learn multi-view discriminative feature representation for deep clustering, which is threefold, i.e., feature-level alignment-oriented and commonality-oriented CL, and cluster-level consistency-oriented CL. The former two submodules aim to contrast the encoded feature representations of data samples in different feature levels, while the last contrasts the data samples in the cluster-level representations. Benefiting from the triple contrast, the more discriminative representations of views can be obtained. Meanwhile, a view weight learning module is designed to learn and exploit the quantitative complementary information across the learned discriminative features of each view. Thus, the contrastive triple-learning module, the view weight learning module and the data clustering module with these fused features are jointly performed, so that these modules are mutually beneficial. The extensive experiments on several challenging multi-view datasets show the superiority of the proposed method over many state-of-the-art methods, especially the large improvement of 15.5% and 8.1% on Caltech-4V and CCV in terms of accuracy. Due to the promising performance on visual datasets, the proposed method can be applied into many practical visual applications such as visual recognition and analysis. The source code of the proposed method is provided at https://github.com/ShizheHu/Joint-Contrastive-Triple-learning.

Time Series Prediction Using Deep Learning Methods in Healthcare

Traditional machine learning methods face unique challenges when applied to healthcare predictive analytics. The high-dimensional nature of healthcare data necessitates labor-intensive and time-consuming processes when selecting an appropriate set of features for each new task. Furthermore, machine learning methods depend heavily on feature engineering to capture the sequential nature of patient data, oftentimes failing to adequately leverage the temporal patterns of medical events and their dependencies. In contrast, recent deep learning (DL) methods have shown promising performance for various healthcare prediction tasks by specifically addressing the high-dimensional and temporal challenges of medical data. DL techniques excel at learning useful representations of medical concepts and patient clinical data as well as their nonlinear interactions from high-dimensional raw or minimally processed healthcare data. In this article, we systematically reviewed research works that focused on advancing deep neural networks to leverage patient structured time series data for healthcare prediction tasks. To identify relevant studies, we searched MEDLINE, IEEE, Scopus, and ACM Digital Library for relevant publications through November 4, 2021. Overall, we found that researchers have contributed to deep time series prediction literature in 10 identifiable research streams: DL models, missing value handling, addressing temporal irregularity, patient representation, static data inclusion, attention mechanisms, interpretation, incorporation of medical ontologies, learning strategies, and scalability. This study summarizes research insights from these literature streams, identifies several critical research gaps, and suggests future research opportunities for DL applications using patient time series data.

Smart Contract Vulnerability Detection Based on Hybrid Attention Mechanism Model

A smart contract, as an important part of blockchain technology, has attracted considerable interest from both industry and academia. It provides the basis for the realization of a variety of practical blockchain applications and plays a crucial role in the blockchain ecosystem. While it also holds a large number of digital assets, the frequent occurrence of smart contract vulnerabilities have caused huge economic losses and destroyed the blockchain-based credit system. Currently, the security and reliability of smart contracts have become a new focus of research, and there are a number of smart contract vulnerability detection methods, such as traditional detection tools based on static or dynamic analysis. However, most of them often rely on expert rules, and therefore have poor scalability and high false negative and false positive rates. Recent deep learning methods alleviate this issue, but without considering the semantic information and context of source code. To this end, we propose a hybrid attention mechanism (HAM) model to detect security vulnerabilities in smart contracts. We extract code fragments from the source code, which focus on key points of vulnerability. We conduct extensive experiments on two public smart contract datasets (a total of 24,957 contracts). Empirical results show remarkable accuracy improvement over the state-of-the art methods on five kinds of vulnerabilities, where the detection accuracy could achieve 93.36%, 80.85%, 82.56%, 85.62%, and 82.19% for reentrancy, arithmetic vulnerability, unchecked return value, timestamp dependency, and tx.origin, respectively.

Progressive DeepSSM: Training Methodology for Image-To-Shape Deep Models.

Statistical shape modeling (SSM) is an enabling quantitative tool to study anatomical shapes in various medical applications. However, directly using 3D images in these applications still has a long way to go. Recent deep learning methods have paved the way for reducing the substantial preprocessing steps to construct SSMs directly from unsegmented images. Nevertheless, the performance of these models is not up to the mark. Inspired by multiscale/multiresolution learning, we propose a new training strategy, progressive DeepSSM, to train image-to-shape deep learning models. The training is performed in multiple scales, and each scale utilizes the output from the previous scale. This strategy enables the model to learn coarse shape features in the first scales and gradually learn detailed fine shape features in the later scales. We leverage shape priors via segmentation-guided multi-task learning and employ deep supervision loss to ensure learning at each scale. Experiments show the superiority of models trained by the proposed strategy from both quantitative and qualitative perspectives. This training methodology can be employed to improve the stability and accuracy of any deep learning method for inferring statistical representations of anatomies from medical images and can be adopted by existing deep learning methods to improve model accuracy and training stability.

Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing.

In this paper, we introduce a new algorithm based on archetypal analysis for blind hyperspectral unmixing, assuming linear mixing of endmembers. Archetypal analysis is a natural formulation for this task. This method does not require the presence of pure pixels (i.e., pixels containing a single material) but instead represents endmembers as convex combinations of a few pixels present in the original hyperspectral image. Our approach leverages an entropic gradient descent strategy, which (i) provides better solutions for hyperspectral unmixing than traditional archetypal analysis algorithms, and (ii) leads to efficient GPU implementations. Since running a single instance of our algorithm is fast, we also propose an ensembling mechanism along with an appropriate model selection procedure that make our method robust to hyper-parameter choices while keeping the computational complexity reasonable. By using six standard real datasets, we show that our approach outperforms state-of-the-art matrix factorization and recent deep learning methods. We also provide an open-source PyTorch implementation: https://github.com/inria-thoth/EDAA.

Cosmic-CoNN: A Cosmic-Ray Detection Deep-learning Framework, Data Set, and Toolkit

Rejecting cosmic rays (CRs) is essential for the scientific interpretation of CCD-captured data, but detecting CRs in single-exposure images has remained challenging. Conventional CR detectors require experimental parameter tuning for different instruments, and recent deep-learning methods only produce instrument-specific models that suffer from performance loss on telescopes not included in the training data. We present Cosmic-CoNN, a generic CR detector deployed for 24 telescopes at the Las Cumbres Observatory, which has been made possible by the three contributions in this work: (1) We build a large and diverse ground-based CR data set leveraging thousands of images from a global telescope network. (2) We propose a novel loss function and a neural network optimized for telescope imaging data to train generic CR-detection models. At 95% recall, our model achieves a precision of 93.70% on Las Cumbres imaging data and maintains a consistent performance on new ground-based instruments never used for training. Specifically, the Cosmic-CoNN model trained on the Las Cumbres CR data set maintains high precisions of 92.03% and 96.69% on Gemini GMOS-N/S 1 × 1 and 2 × 2 binning images, respectively. (3) We build a suite of tools including an interactive CR mask visualization and editing interface, console commands, and Python APIs to make automatic, robust CR detection widely accessible by the community of astronomers. Our data set, open-source code base, and trained models are available at https://github.com/cy-xu/cosmic-conn.

Physics-Driven Probabilistic Deep Learning for the Inversion of Physical Models With Application to Phenological Parameter Retrieval From Satellite Times Series

Recent Sentinel satellite constellations and deep learning methods offer great possibilities for estimating the states and dynamics of physical parameters on a global scale. Such parameters and their corresponding uncertainties can be retrieved by machine learning methods solving probabilistic inverse problems. Nevertheless, the scarcity of reference data to train supervised methodologies is a well-known constraint for remote sensing applications. To address such limitations, this work presents a new generic physics-guided probabilistic deep learning methodology to invert physical models. The presented methodology proposes a new strategy to combine probabilistic deep learning methods and physical models avoiding simulation-driven machine learning. The inverse problem is addressed through a Bayesian inference framework by proposing a new physically-constrained self-supervised representation learning methodology. To show the interest of the proposed strategy, the methodology is applied to the retrieval of phenological parameters from NDVI time series. As a result, the probability distributions of the intrinsic phenological model parameters are inferred. The feasibility of the method is evaluated on both simulated and real Sentinel-2 data and compared with different standard algorithms. Promising results show satisfactory accuracy predictions and low inference times for real applications.

CFNet: An Eigenvalue Preserved Approach to Multiscale Building Segmentation in High-Resolution Remote Sensing Images

In recent years, AI and Deep Learning (DL) methods have been widely used for object classification, recognition, and segmentation of high-resolution multispectral remote sensing images. These DL-based solutions perform better compare to traditional spectral algorithms but still suffer from insufficient optimization of global and local features of object context. In addition, failure of code-data isolation and/or disclosure of detailed eigenvalues causes serious privacy and even secret leakage due to the sensitivity of high-resolution remote sensing data and their processing mechanisms. In this paper, Class Feature (CF) modules have been presented in the decoder part of an attention-based CNN network to distinguish between building and non-building (background) area. In this way, context features of a focused object can be extracted with more details being processed, whilst the resolution of images is maintained. The reconstructed local and global feature values and dependencies in the proposed model are maintained by reconfiguring multiple effective attention modules with contextual dependencies to achieve better results for the eigenvalue. According to quantitative results and their visualization, the proposed model has depicted better performance over others' work using two large-scale building remote sensing datasets. The F1-score of this model reached 87.91 and 89.58 on WHU Buildings Dataset and Massachusetts Buildings Dataset, respectively, which exceeded the other semantic segmentation models.

TRNR: Task-Driven Image Rain and Noise Removal with a Few Images Based on Patch Analysis.

The recent success of learning-based image rain and noise removal can be attributed primarily to well-designed neural network architectures and large labeled datasets. However, we discover that current image rain and noise removal methods result in low utilization of images. To alleviate the reliance of deep models on large labeled datasets, we propose the task-driven image rain and noise removal (TRNR) based on a patch analysis strategy. The patch analysis strategy samples image patches with various spatial and statistical properties for training and can increase image utilization. Furthermore, the patch analysis strategy encourages us to introduce the N-frequency-K-shot learning task for the task-driven approach TRNR. TRNR allows neural networks to learn from numerous N-frequency-K-shot learning tasks, rather than from a large amount of data. To verify the effectiveness of TRNR, we build a Multi-Scale Residual Network (MSResNet) for both image rain removal and Gaussian noise removal. Specifically, we train MSResNet for image rain removal and noise removal with a few images (for example, 20.0% train-set of Rain100H). Experimental results demonstrate that TRNR enables MSResNet to learn more effectively when data is scarce. TRNR has also been shown in experiments to improve the performance of existing methods. Furthermore, MSResNet trained with a few images using TRNR outperforms most recent deep learning methods trained data-driven on large labeled datasets. These experimental results have confirmed the effectiveness and superiority of the proposed TRNR. The source code is available on https://github.com/Schizophreni/MSResNet-TRNR.

Mining Joint Intraimage and Interimage Context for Remote Sensing Change Detection

Recent deep learning methods for change detection focus on excavating more discriminative context within individual images. However, due to seasonal change, noise, and so on, the appearance of objects tends to be more heterogeneous among various scenes. Consequently, the above intra-image context is inadequate to represent specific-category objects and pseudo changes would be inevitable in detection results. To deal with this issue, we propose a context aggregation network (CANet) to mine inter-image context over all training images for further enhancing intra-image context. Specifically, a Siamese network attached with temporal attention modules is served as a feature encoder to extract multi-scale temporal features from bitemporal images. Then, a context extraction module is devised to capture long-range spatial-channel context within individual images. Meanwhile, context representations of underlying categories in the scene are inferred using all training images in an unsupervised manner. Finally, these two kinds of contextual information are aggregated to one which is subsequently fed into a multi-scale fusion module to produce the detection map. CANet is compared with several state-of-the-art methods on three benchmark datasets, including the season-varying change detection (SVCD) dataset, the Sun Yat-sen University change detection (SYSU-CD) dataset, and the Learning Vision and Remote Sensing Laboratory building change detection (LEVIR-CD) dataset. It is demonstrated that our method outperforms all comparison methods in terms of F1, overall accuracy (OA), and Intersection-of-Union (IoU). The results of CANet on three datasets are available at https://github.com/NuistZF/CANet-for-change-detection and codes will be public soon.

Retinal blood vessel segmentation by using the MS-LSDNet network and geometric skeleton reconnection method

Automatic retinal blood vessel segmentation is a key link in the diagnosis of ophthalmic diseases. Recent deep learning methods have achieved high accuracy in vessel segmentation but still face challenges in maintaining vascular structural connectivity. Therefore, this paper proposes a novel retinal blood vessel segmentation strategy that includes three stages: vessel structure detection, vessel branch extraction and broken vessel segment reconnection. First, we propose a multiscale linear structure detection network (MS-LSDNet), which improves the detection ability of fine blood vessels by learning the types of rich hierarchical features. In addition, to maintain the connectivity of the vascular structure in the process of binarization of the vascular probability map, an adaptive hysteresis threshold method for vascular extraction is proposed. Finally, we propose a vascular tree structure reconstruction algorithm based on a geometric skeleton to connect the broken vessel segments. Experimental results on three publicly available datasets show that compared with current state-of-the-art algorithms, our strategy effectively maintains the connectivity of retinal vascular tree structure.

Dual-Branch Attention-Assisted CNN for Hyperspectral Image Classification

Convolutional neural network (CNN)-based hyperspectral image (HSI) classification models have developed rapidly in recent years due to their superiority. However, recent deep learning methods based on CNN tend to be deep networks with multiple parameters, which inevitably resulted in information redundancy and increased computational cost. We propose a dual-branch attention-assisted CNN (DBAA-CNN) for HSI classification to address these problems. The network consists of spatial-spectral and spectral attention branches. The spatial-spectral branch integrates multi-scale spatial information with cross-channel attention by extracting spatial–spectral information jointly utilizing a 3-D CNN and a pyramid squeeze-and-excitation attention (PSA) module. The spectral branch maps the original features to the spectral interaction space for feature representation and learning by adding an attention module. Finally, the spectral and spatial features are combined and input into the linear layer to generate the sample label. We conducted tests with three common hyperspectral datasets to test the efficacy of the framework. Our method outperformed state-of-the-art HSI classification algorithms based on classification accuracy and processing time.

Ensembled masked graph autoencoders for link anomaly detection in a road network considering spatiotemporal features

Road anomaly detection aims to find a small group of roads that are exceptional with respect to the rest of the physical links in a transportation network, posing great challenges for spatial data mining and urban infrastructure management applications. Road links involve complex features from both spatial and temporal perspectives, but existing detection methods mostly rely on the topological features of road networks because they face difficulty in capturing the spatial and temporal characteristics of road networks. To overcome this difficulty, we constructed an ensembled autoencoder framework for road anomaly detection by combining spatiotemporal graph learning and graph masking methods, and our main focus was to effectively detect the topological and attribute anomalies mapped by spatiotemporal features in a road network based on traffic flow data. To model local contexts, we performed random masking on the input graph to obtain heterogeneous masked subgraphs. On this basis, a spatiotemporal graph learning model was used to extract topological and traffic flow features from masked subgraphs. Then, we carried out feature reconstructions for each subgraph and calculated the anomaly scores for every node in the graph. Finally, an ensemble model was designed to integrate the anomaly detection results from multiple autoencoders that were trained on the subgraphs to improve feature learning. Our experimental results show that the proposed method is superior to traditional topological analysis methods, machine learning methods (DBScan, isolation forest, LOF, and one-class SVM), and recent deep learning methods (GAE and VGAE).

Fusion of tactile and visual information in deep learning models for object recognition

Humans use multimodal sensory information to understand the physical properties of their environment. Intelligent decision-making systems such as the ones used in robotic applications could also utilize the fusion of multimodal information to improve their performance and reliability. In recent years, machine learning and deep learning methods are used at the heart of such intelligent systems. Developing visuo-tactile models is a challenging task due to various problems such as performance, limited datasets, reliability, and computational efficiency. In this research, we propose four efficient models based on dynamic neural network architectures for unimodal and multimodal object recognition. For unimodal object recognition, TactileNet and VisionNet are proposed. For multimodal object recognition, the FusionNet-A and the FusionNet-B are designed to implement early and late fusion strategies, respectively. The proposed models have a flexible structure and are able to change at the train or test phase to accommodate the amount of available information. Model confidence calibration is employed to enhance the reliability and generalization of the models. The proposed models are evaluated on MIT CSAIL large-scale multimodal dataset. Our results demonstrate accurate performance in both unimodal and multimodal scenarios. It has been illustrated that by using different fusion strategies and augmenting the tactile-based models with visual information, the top-1 error rate of the single-frame tactile model was reduced by 78% and the mean average precision was increased by 2.19 times. Although the focus has been on the fusion of tactile and visual modalities, the proposed design methodology can be generalized to include more modalities.

ULD-Net: 3D unsupervised learning by dense similarity learning with equivariant-crop.

Although many recent deep learning methods have achieved good performance in point cloud analysis, most of them are built upon the heavy cost of manual labeling. Unsupervised representation learning methods have attracted increasing attention due to their high label efficiency. How to learn more useful representations from unlabeled 3D point clouds is still a challenging problem. Addressing this problem, we propose a novel unsupervised learning approach for point cloud analysis, named ULD-Net, consisting of an equivariant-crop (equiv-crop) module to achieve dense similarity learning. We propose dense similarity learning that maximizes consistency across two randomly transformed global-local views at both the instance level and the point level. To build feature correspondence between global and local views, an equiv-crop is proposed to transform features from the global scope to the local scope. Unlike previous methods that require complicated designs, such as negative pairs and momentum encoders, our ULD-Net benefits from the simple Siamese network that relies solely on stop-gradient operation preventing the network from collapsing. We also utilize the feature separability constraint for more representative embeddings. Experimental results show that our ULD-Net achieves the best results of context-based unsupervised methods and comparable performances to supervised models in shape classification and segmentation tasks. On the linear support vector machine classification benchmark, our ULD-Net surpasses the best context-based method spatiotemporal self-supervised representation learning (STRL) by 1.1% overall accuracy. On tasks with fine-tuning, our ULD-Net outperforms STRL under fully supervised and semisupervised settings, in particular, 0.1% accuracy gain on the ModelNet40 classification benchmark, and 0.6% medium intersection of union gain on the ShapeNet part segmentation benchmark.

A symmetric prior knowledge based deep learning model for intracerebral hemorrhage lesion segmentation.

Background: Accurate localization and classification of intracerebral hemorrhage (ICH) lesions are of great significance for the treatment and prognosis of patients with ICH. The purpose of this study is to develop a symmetric prior knowledge based deep learning model to segment ICH lesions in computed tomography (CT). Methods: A novel symmetric Transformer network (Sym-TransNet) is designed to segment ICH lesions in CT images. A cohort of 1,157 patients diagnosed with ICH is established to train (n = 857), validate (n = 100), and test (n = 200) the Sym-TransNet. A healthy cohort of 200 subjects is added, establishing a test set with balanced positive and negative cases (n = 400), to further evaluate the accuracy, sensitivity, and specificity of the diagnosis of ICH. The segmentation results are obtained after data pre-processing and Sym-TransNet. The DICE coefficient is used to evaluate the similarity between the segmentation results and the segmentation gold standard. Furthermore, some recent deep learning methods are reproduced to compare with Sym-TransNet, and statistical analysis is performed to prove the statistical significance of the proposed method. Ablation experiments are conducted to prove that each component in Sym-TransNet could effectively improve the DICE coefficient of ICH lesions. Results: For the segmentation of ICH lesions, the DICE coefficient of Sym-TransNet is 0.716 0.031 in the test set which contains 200 CT images of ICH. The DICE coefficients of five subtypes of ICH, including intraparenchymal hemorrhage (IPH), intraventricular hemorrhage (IVH), extradural hemorrhage (EDH), subdural hemorrhage (SDH), and subarachnoid hemorrhage (SAH), are 0.784 0.039, 0.680 0.049, 0.359 0.186, 0.534 0.455, and 0.337 0.044, respectively. Statistical results show that the proposed Sym-TransNet can significantly improve the DICE coefficient of ICH lesions in most cases. In addition, the accuracy, sensitivity, and specificity of Sym-TransNet in the diagnosis of ICH in 400 CT images are 91.25%, 98.50%, and 84.00%, respectively. Conclusion: Compared with recent mainstream deep learning methods, the proposed Sym-TransNet can segment and identify different types of lesions from CT images of ICH patients more effectively. Moreover, the Sym-TransNet can diagnose ICH more stably and efficiently, which has clinical application prospects.

HProteome-BSite: predicted binding sites and ligands in human 3D proteome.

Atomic-level knowledge of protein-ligand interactions allows a detailed understanding of protein functions and provides critical clues to discovering molecules regulating the functions. While recent innovative deep learning methods for protein structure prediction dramatically increased the structural coverage of the human proteome, molecular interactions remain largely unknown. A new database, HProteome-BSite, provides predictions of binding sites and ligands in the enlarged 3D human proteome. The model structures for human proteins from the AlphaFold Protein Structure Database were processed to structural domains of high confidence to maximize the coverage and reliability of interaction prediction. For ligand binding site prediction, an updated version of a template-based method GalaxySite was used. A high-level performance of the updated GalaxySite was confirmed. HProteome-BSite covers 80.74% of the UniProt entries in the AlphaFold human 3D proteome. Predicted binding sites and binding poses of potential ligands are provided for effective applications to further functional studies and drug discovery. The HProteome-BSite database is available at https://galaxy.seoklab.org/hproteome-bsite/database and is free and open to all users.

Traffic-GGNN: Predicting Traffic Flow via Attentional Spatial-Temporal Gated Graph Neural Networks

Recent spatial-temporal graph-based deep learning methods for Traffic Flow Prediction (TFP) problems have shown superior performance in modeling higher-level spatial interactions and temporal correlations. However, most of these methods suffer from post-fusion efficiency difficulty caused by separate explorations of the spatial communications and the temporal dependencies, which could result in delayed and biased predictions. To address that, we propose a Traffic Gated Graph Neural Networks (Traffic-GGNN) for real-time-fused spatial-temporal representation modeling. Firstly, we adopt bidirectional message passing to capture the location-wise spatial interactions. Secondly, we apply a GRU-based module to explore and aggregate the spatial interactions with the temporal correlations in a real-time fusion way. Lastly, we introduce a self-attention mechanism to reweight the location-based importance and produce the final prediction. Moreover, our proposed model allows end-to-end training thus it is easy to scale to diverse types of traffic datasets and yield better efficiency and effectiveness on three real-world datasets (SZ-taxi, Los-loop, and PEMS-BAY).