DeepR2cov: deep representation learning on heterogeneous drug networks to discover anti-inflammatory agents for COVID-19.

Recent studies have demonstrated that the excessive inflammatory response is an important factor of death in coronavirus disease 2019 (COVID-19) patients. In this study, we propose a deep representation on heterogeneous drug networks, termed DeepR2cov, to discover potential agents for treating the excessive inflammatory response in COVID-19 patients. This work explores the multi-hub characteristic of a heterogeneous drug network integrating eight unique networks. Inspired by the multi-hub characteristic, we design 3 billion special meta paths to train a deep representation model for learning low-dimensional vectors that integrate long-range structure dependency and complex semantic relation among network nodes. Based on the representation vectors and transcriptomics data, we predict 22 drugs that bind to tumor necrosis factor-α or interleukin-6, whose therapeutic associations with the inflammation storm in COVID-19 patients, and molecular binding model are further validated via data from PubMed publications, ongoing clinical trials and a docking program. In addition, the results on five biomedical applications suggest that DeepR2cov significantly outperforms five existing representation approaches. In summary, DeepR2cov is a powerful network representation approach and holds the potential to accelerate treatment of the inflammatory responses in COVID-19 patients. The source code and data can be downloaded from https://github.com/pengsl-lab/DeepR2cov.git.

A geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure.

Modeling the dynamics of glassy systems has been challenging in physics for several decades. Recent studies have shown the efficacy of Graph Neural Networks (GNNs) in capturing particle dynamics from the graph structure of glassy systems. However, current GNN methods do not take the dynamic patterns established by neighboring particles explicitly into account. In contrast to these approaches, this paper introduces a novel dynamical parameter termed "smoothness" based on the theory of graph signal processing, which explores the dynamic patterns from a graph perspective. Present graph-based approaches encode structural features without considering smoothness constraints, leading to a weakened correlation between structure and dynamics, particularly on short timescales. To address this limitation, we propose a Geometry-enhanced Graph Neural Network (Geo-GNN) to learn the smoothness of dynamics. Results demonstrate that our method outperforms state-of-the-art baselines in predicting glassy dynamics. Ablation studies validate the effectiveness of each proposed component in capturing smoothness within dynamics. These findings contribute to a deeper understanding of the interplay between glassy dynamics and static structure.

Interlayer Transition Induced Infrared Response in ReS2/2D Perovskite van der Waals Heterostructure Photodetector.

The emerging Ruddlesden-Popper two-dimensional perovskite (2D PVK) has recently joined the family of 2D semiconductors as a potential competitor for building van der Waals (vdW) heterostructures in future optoelectronics. However, to date, most of the reported heterostructures based on 2D PVKs suffer from poor spectral response that is caused by intrinsic wide bandgap of constituting materials. Herein, a direct heterointerface bandgap (∼0.4 eV) between 2D PVK and ReS2 is demonstrated. The strong interlayer coupling reduces the energy interval at the heterojunction region so that the heterostructure shows high sensitivity with the spectral response expanding to 2000 nm. The large type-II band offsets exceeding 1.1 eV ensure fast photogenerated carriers separation at the heterointerface. When this heterostructure is used as a self-driven photodetector, it exhibits a record high detectivity up to 1.8 × 1014 Jones, surpassing any reported 2D self-driven devices, and an impressive external quantum efficiency of 68%.

BioERP: biomedical heterogeneous network-based self-supervised representation learning approach for entity relationship predictions.

MOTIVATION: Predicting entity relationship can greatly benefit important biomedical problems. Recently, a large amount of biomedical heterogeneous networks (BioHNs) are generated and offer opportunities for developing network-based learning approaches to predict relationships among entities. However, current researches slightly explored BioHNs-based self-supervised representation learning methods, and are hard to simultaneously capturing local- and global-level association information among entities. RESULTS: In this study, we propose a BioHN-based self-supervised representation learning approach for entity relationship predictions, termed BioERP. A self-supervised meta path detection mechanism is proposed to train a deep Transformer encoder model that can capture the global structure and semantic feature in BioHNs. Meanwhile, a biomedical entity mask learning strategy is designed to reflect local associations of vertices. Finally, the representations from different task models are concatenated to generate two-level representation vectors for predicting relationships among entities. The results on eight datasets show BioERP outperforms 30 state-of-the-art methods. In particular, BioERP reveals great performance with results close to 1 in terms of AUC and AUPR on the drug-target interaction predictions. In summary, BioERP is a promising bio-entity relationship prediction approach. AVAILABILITY AND IMPLEMENTATION: Source code and data can be downloaded from https://github.com/pengsl-lab/BioERP.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Thickness-induced band-gap engineering in lead-free double perovskite Cs2AgBiBr6 for highly efficient photocatalysis.

In recent years, two-dimensional (2D) lead-free double perovskites have been attracting much attention because of their unique performance in photovoltaic solar cells and photocatalysis. Nonetheless, how thickness affects the photoelectric properties of lead-free double perovskite remains unclear. In this work, by means of density functional theory (DFT) with a spin orbit coupling (SOC) effect, we have investigated the electronic and optical properties systemically, including band structures, carrier mobility, optical absorption spectra, exciton-binding energies, band edges alignment and molecule adsorption performance of Cs2AgBiBr6 with different thicknesses. The calculated results revealed the thickness-induced band gap and optical performance for Cs2AgBiBr6. It shows a low band gap and outstanding optical absorption of visible and ultraviolet light. When the thickness is reduced to a monolayer, Cs2AgBiBr6 moves from an indirect band gap to a direct band gap. Moreover, the carrier mobility of Cs2AgBiBr6 is excellent and the exciton-binding energy increases with the decreased thickness. Importantly, an analysis of molecule adsorption and band edge alignment indicates that Cs2AgBiBr6 is prone to H2O adsorption and H2 desorption theoretically, which is conducive to the photocatalytic water splitting for hydrogen generation and other photovatalytic reactions. Our work suggests that Cs2AgBiBr6 is a potential candidate as a solar cell or a photocatalyst, and we provide theoretical explorations into reducing the layers of lead-free double perovskite materials to 2D atomic thickness for a better photocatalytic application, which can serve as guidelines for the design of excellent photocatalysts.

iProX: an integrated proteome resource.

Sharing of research data in public repositories has become best practice in academia. With the accumulation of massive data, network bandwidth and storage requirements are rapidly increasing. The ProteomeXchange (PX) consortium implements a mode of centralized metadata and distributed raw data management, which promotes effective data sharing. To facilitate open access of proteome data worldwide, we have developed the integrated proteome resource iProX (http://www.iprox.org) as a public platform for collecting and sharing raw data, analysis results and metadata obtained from proteomics experiments. The iProX repository employs a web-based proteome data submission process and open sharing of mass spectrometry-based proteomics datasets. Also, it deploys extensive controlled vocabularies and ontologies to annotate proteomics datasets. Users can use a GUI to provide and access data through a fast Aspera-based transfer tool. iProX is a full member of the PX consortium; all released datasets are freely accessible to the public. iProX is based on a high availability architecture and has been deployed as part of the proteomics infrastructure of China, ensuring long-term and stable resource support. iProX will facilitate worldwide data analysis and sharing of proteomics experiments.

Improving biomedical named entity recognition with syntactic information.

BACKGROUND: Biomedical named entity recognition (BioNER) is an important task for understanding biomedical texts, which can be challenging due to the lack of large-scale labeled training data and domain knowledge. To address the challenge, in addition to using powerful encoders (e.g., biLSTM and BioBERT), one possible method is to leverage extra knowledge that is easy to obtain. Previous studies have shown that auto-processed syntactic information can be a useful resource to improve model performance, but their approaches are limited to directly concatenating the embeddings of syntactic information to the input word embeddings. Therefore, such syntactic information is leveraged in an inflexible way, where inaccurate one may hurt model performance. RESULTS: In this paper, we propose BIOKMNER, a BioNER model for biomedical texts with key-value memory networks (KVMN) to incorporate auto-processed syntactic information. We evaluate BIOKMNER on six English biomedical datasets, where our method with KVMN outperforms the strong baseline method, namely, BioBERT, from the previous study on all datasets. Specifically, the F1 scores of our best performing model are 85.29% on BC2GM, 77.83% on JNLPBA, 94.22% on BC5CDR-chemical, 90.08% on NCBI-disease, 89.24% on LINNAEUS, and 76.33% on Species-800, where state-of-the-art performance is obtained on four of them (i.e., BC2GM, BC5CDR-chemical, NCBI-disease, and Species-800). CONCLUSION: The experimental results on six English benchmark datasets demonstrate that auto-processed syntactic information can be a useful resource for BioNER and our method with KVMN can appropriately leverage such information to improve model performance.

Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.

There have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19.

SW-Tandem: a highly efficient tool for large-scale peptide identification with parallel spectrum dot product on Sunway TaihuLight.

SUMMARY: Tandem mass spectrometry based database searching is a widely acknowledged and adopted method that identifies peptide sequence in shotgun proteomics. However, database searching is extremely computationally expensive, which can take days even weeks to process a large spectra dataset. To address this critical issue, this paper presents SW-Tandem, a new tool for large-scale peptide sequencing. SW-Tandem parallelizes the spectrum dot product scoring algorithm and leverages the advantages of Sunway TaihuLight, the No. 1 supercomputer in the world in 2017. Sunway TaihuLight is powered by the brand new many-core SW26010 processors and provides a peak computation performance greater than 100PFlops. To fully utilize the Sunway TaihuLights capacity, SW-Tandem employs three mechanisms to accelerate large-scale peptide identification, memory-access optimizations, double buffering and vectorization. The results of experiments conducted on multiple datasets demonstrate the performance of SW-Tandem against three state-of-the-art tools for peptide identification, including X!! Tandem, MR-Tandem and MSFragger. In addition, it shows high scalability in the experiments on extremely large datasets sized up to 12 GB. AVAILABILITY AND IMPLEMENTATION: SW-Tandem is an open source software tool implemented in C++. The source code and the parameter settings are available at https://github.com/Logic09/SW-Tandem. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Secure Key Establishment Mechanism for Smart Sensing System Based Robots Network.

The smart robot is playing an increasingly important role in the social economy, and multi-robot systems will be an important development in robotics. With smart sensing systems, the communications between sensors, actuators, and edge computing systems and robots are prone to be attacked due to the highly dynamic and distributed environment. Since smart robots are often distributed in open environments, as well as due to their limited hardware resources and security protection capabilities, the security requirements of their keys cannot be met with traditional key distribution algorithms. In this paper, we propose a new mechanism of key establishment based on high-order polynomials to ensure the safe key generation and key distribution. Experiments show that the key establishment mechanism proposed in this paper guarantees the security of keys; its storage cost and communication cost are smaller than state-of-the-art mechanisms; and it allows robot components to join and leave the network dynamically, which is more suitable for multi-robot systems.

MCtandem: an efficient tool for large-scale peptide identification on many integrated core (MIC) architecture.

BACKGROUND: Tandem mass spectrometry (MS/MS)-based database searching is a widely acknowledged and widely used method for peptide identification in shotgun proteomics. However, due to the rapid growth of spectra data produced by advanced mass spectrometry and the greatly increased number of modified and digested peptides identified in recent years, the current methods for peptide database searching cannot rapidly and thoroughly process large MS/MS spectra datasets. A breakthrough in efficient database search algorithms is crucial for peptide identification in computational proteomics. RESULTS: This paper presents MCtandem, an efficient tool for large-scale peptide identification on Intel Many Integrated Core (MIC) architecture. To support big data processing capability, a novel parallel match scoring algorithm, named MIC-SDP (spectrum dot product), and its two-level parallelization are presented in MCtandem's design. In addition, a series of optimization strategies on both the host CPU side and the MIC side, which includes pre-fetching, optimized communication overlapping scheme, multithreading and hyper-threading, are exploited to improve the execution performance. CONCLUSIONS: For fair comparisons, we first set up experiments and verified the 28 fold times speedup on a single MIC against the original CPU-based implementation. We then execute the MCtandem for a very large dataset on an MIC cluster (a component of the Tianhe-2 supercomputer) and achieved much higher scalability than in a benchmark MapReduce-based programs, MR-Tandem. MCtandem is an open-source software tool implemented in C++. The source code and the parameter settings are available at https://github.com/LogicZY/MCtandem .

Low-Cost Image Compressive Sensing with Multiple Measurement Rates for Object Detection.

When measurement rates grow, most Compressive Sensing (CS) methods suffer from an increase in overheads of transmission and storage of CS measurements, while reconstruction quality degrades appreciably when measurement rates reduce. To solve these problems in real scenarios such as large-scale distributed surveillance systems, we propose a low-cost image CS approach called MRCS for object detection. It predicts key objects using the proposed MYOLO3 detector, and then samples the regions of the key objects as well as other regions using multiple measurement rates to reduce the size of sampled CS measurements. It also stores and transmits half-precision CS measurements to further reduce the required transmission bandwidth and storage space. Comprehensive evaluations demonstrate that MYOLO3 is a smaller and improved object detector for resource-limited hardware devices such as surveillance cameras and aerial drones. They also suggest that MRCS significantly reduces the required transmission bandwidth and storage space by declining the size of CS measurements, e.g., mean Compression Ratios (mCR) achieves 1.43-22.92 on the VOC-pbc dataset. Notably, MRCS further reduces the size of CS measurements by half-precision representations. Subsequently, the required transmission bandwidth and storage space are reduced by one half as compared to the counterparts represented with single-precision floats. Moreover, it also substantially enhances the usability of object detection on reconstructed images with half-precision CS measurements and multiple measurement rates as compared to its counterpart, using a single low measurement rate.

MRUniNovo: an efficient tool for de novo peptide sequencing utilizing the hadoop distributed computing framework.

Summary: Tandem mass spectrometry-based de novo peptide sequencing is a complex and time-consuming process. The current algorithms for de novo peptide sequencing cannot rapidly and thoroughly process large mass spectrometry datasets. In this paper, we propose MRUniNovo, a novel tool for parallel de novo peptide sequencing. MRUniNovo parallelizes UniNovo based on the Hadoop compute platform. Our experimental results demonstrate that MRUniNovo significantly reduces the computation time of de novo peptide sequencing without sacrificing the correctness and accuracy of the results, and thus can process very large datasets that UniNovo cannot. Availability and Implementation: MRUniNovo is an open source software tool implemented in java. The source code and the parameter settings are available at http://bioinfo.hupo.org.cn/MRUniNovo/index.php. Contact: s131020002@hnu.edu.cn ; taochen1019@163.com. Supplementary information: Supplementary data are available at Bioinformatics online.

cooccurNet: an R package for co-occurrence network construction and analysis.

MOTIVATION: Previously, we developed a computational model to identify genomic co-occurrence networks that was applied to capture the coevolution patterns within genomes of influenza viruses. To facilitate easy public use of this model, an R package 'cooccurNet' is presented here. RESULTS: 'cooccurNet' includes functionalities of construction and analysis of residues (e.g. nucleotides, amino acids and SNPs) co-occurrence network. In addition, a new method for measuring residues coevolution, defined as residue co-occurrence score (RCOS), is proposed and implemented in 'cooccurNet' based on the co-occurrence network. AVAILABILITY AND IMPLEMENTATION: 'cooccurNet' is publicly available on CRAN repositories under the GPL-3 Open Source License ( http://cran.r-project.org/package=cooccurNet ). CONTACT: taijiao@ibms.pumc.edu.cn or pys2013@hnu.edu.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Analyzing the impact of storage shortage on data availability in decentralized online social networks.

Maintaining data availability is one of the biggest challenges in decentralized online social networks (DOSNs). The existing work often assumes that the friends of a user can always contribute to the sufficient storage capacity to store all data. However, this assumption is not always true in today's online social networks (OSNs) due to the fact that nowadays the users often use the smart mobile devices to access the OSNs. The limitation of the storage capacity in mobile devices may jeopardize the data availability. Therefore, it is desired to know the relation between the storage capacity contributed by the OSN users and the level of data availability that the OSNs can achieve. This paper addresses this issue. In this paper, the data availability model over storage capacity is established. Further, a novel method is proposed to predict the data availability on the fly. Extensive simulation experiments have been conducted to evaluate the effectiveness of the data availability model and the on-the-fly prediction.

Toward Interpreting the Thermally Activated ß Dynamics in Metallic Glass Using the Structural Constraint Neural Network.

It is crucial to unravel the structural factors influencing the dynamics of the amorphous solids. Deep learning aids in navigating these complexities, while transparency issues persist. Drawing inspiration from the successful application of prototype neural networks in image analysis, this study introduces a novel machine learning approach to address interpretability challenges in glassy research. Distinguishing from traditional machine learning models, the proposed neural network tries to learn distant structural motifs for solid-like atoms and liquid-like atoms. Such learned structural motifs constrain the underlying structural space and thus can serve as a breakthrough in explaining how structural differences impact dynamics. We further used the proposed model to explore the correlation between the local structure and activation energy in the CuZr alloys. Building upon this interpretable model, we demonstrated significant structural differences among atoms with different activation energies. Our interpretable model is a data-driven solution that provides a pathway to reveal the origin of structural heterogeneity in amorphous alloys.

A knowledge-interpretable multi-task learning framework for automated thyroid nodule diagnosis in ultrasound videos.

Ultrasound has become the most widely used modality for thyroid nodule diagnosis, due to its portability, real-time feedback, lack of toxicity, and low cost. Recently, the computer-aided diagnosis (CAD) of thyroid nodules has attracted significant attention. However, most existing techniques can only be applied to either static images with prominent features (manually selected from scanning videos) or rely on 'black boxes' that cannot provide interpretable results. In this study, we develop a user-friendly framework for the automated diagnosis of thyroid nodules in ultrasound videos, by simulating the typical diagnostic workflow used by radiologists. This process consists of two orderly part-to-whole tasks. The first interprets the characteristics of each image using prior knowledge, to obtain corresponding frame-wise TI-RADS scores. Associated embedded representations not only provide diagnostic information for radiologists but also reduce computational costs. The second task models temporal contextual information in an embedding vector sequence and selectively enhances important information to distinguish benign and malignant thyroid nodules, thereby improving the efficiency and generalizability of the proposed framework. Experimental results demonstrated this approach outperformed other state-of-the-art video classification methods. In addition to assisting radiologists in understanding model predictions, these CAD results could further ease diagnostic workloads and improve patient care.

FARN: Fetal Anatomy Reasoning Network for Detection with Global Context Semantic and Local Topology Relationship.

Accurate recognition of fetal anatomical structure is a pivotal task in ultrasound (US) image analysis. Sonographers naturally apply anatomical knowledge and clinical expertise to recognizing key anatomical structures in complex US images. However, mainstream object detection approaches usually treat each structure recognition separately, overlooking anatomical correlations between different structures in fetal US planes. In this work, we propose a Fetal Anatomy Reasoning Network (FARN) that incorporates two kinds of relationship forms: a global context semantic block summarized with visual similarity and a local topology relationship block depicting structural pair constraints. Specifically, by designing the Adaptive Relation Graph Reasoning (ARGR) module, anatomical structures are treated as nodes, with two kinds of relationships between nodes modeled as edges. The flexibility of the model is enhanced by constructing the adaptive relationship graph in a data-driven way, enabling adaptation to various data samples without the need for predefined additional constraints. The feature representation is further enhanced by aggregating the outputs of the ARGR module. Comprehensive experimental results demonstrate that FARN achieves promising performance in detecting 37 anatomical structures across key US planes in tertiary obstetric screening. FARN effectively utilizes key relationships to improve detection performance, demonstrates robustness to small-scale, similar, and indistinct structures, and avoids some detection errors that deviate from anatomical norms. Overall, our study serves as a resource for developing efficient and concise approaches to model inter-anatomy relationships.

Neural Network Compression Based on Tensor Ring Decomposition.

Deep neural networks (DNNs) have made great breakthroughs and seen applications in many domains. However, the incomparable accuracy of DNNs is achieved with the cost of considerable memory consumption and high computational complexity, which restricts their deployment on conventional desktops and portable devices. To address this issue, low-rank factorization, which decomposes the neural network parameters into smaller sized matrices or tensors, has emerged as a promising technique for network compression. In this article, we propose leveraging the emerging tensor ring (TR) factorization to compress the neural network. We investigate the impact of both parameter tensor reshaping and TR decomposition (TRD) on the total number of compressed parameters. To achieve the maximal parameter compression, we propose an algorithm based on prime factorization that simultaneously identifies the optimal tensor reshaping and TRD. In addition, we discover that different execution orders of the core tensors result in varying computational complexities. To identify the optimal execution order, we construct a novel tree structure. Based on this structure, we propose a top-to-bottom splitting algorithm to schedule the execution of core tensors, thereby minimizing computational complexity. We have performed extensive experiments using three kinds of neural networks with three different datasets. The experimental results demonstrate that, compared with the three state-of-the-art algorithms for low-rank factorization, our algorithm can achieve better performance with much lower memory consumption and lower computational complexity.

HFSCCD: A Hybrid Neural Network for Fetal Standard Cardiac Cycle Detection in Ultrasound Videos.

In the fetal cardiac ultrasound examination, standard cardiac cycle (SCC) recognition is the essential foundation for diagnosing congenital heart disease. Previous studies have mostly focused on the detection of adult CCs, which may not be applicable to the fetus. In clinical practice, localization of SCCs needs to recognize end-systole (ES) and end-diastole (ED) frames accurately, ensuring that every frame in the cycle is a standard view. Most existing methods are not based on the detection of key anatomical structures, which may not recognize irrelevant views and background frames, results containing non-standard frames, or even it does not work in clinical practice. We propose an end-to-end hybrid neural network based on an object detector to detect SCCs from fetal ultrasound videos efficiently, which consists of 3 modules, namely Anatomical Structure Detection (ASD), Cardiac Cycle Localization (CCL), and Standard Plane Recognition (SPR). Specifically, ASD uses an object detector to identify 9 key anatomical structures, 3 cardiac motion phases, and the corresponding confidence scores from fetal ultrasound videos. On this basis, we propose a joint probability method in the CCL to learn the cardiac motion cycle based on the 3 cardiac motion phases. In SPR, to reduce the impact of structure detection errors on the accuracy of the standard plane recognition, we use XGBoost algorithm to learn the relation knowledge of the detected anatomical structures. We evaluate our method on the test fetal ultrasound video datasets and clinical examination cases and achieve remarkable results. This study may pave the way for clinical practices.