Search

Abstract Network embedding aspires to learn a low‐dimensional vector of each node in networks, which can apply to diverse data mining tasks. In real‐life, many networks include rich attributes and temporal information. However, most existing embedding approaches ignore either temporal information or network attributes. A self‐attention based architecture using higher‐order weights and node attributes for both static and temporal attributed network embedding is presented in this article. A random walk sampling algorithm based on higher‐order weights and node attributes to capture network topological features is presented. For static attributed networks, the algorithm incorporates first‐order to k‐order weights, and node attribute similarities into one weighted graph to preserve topological features of networks. For temporal attribute networks, the algorithm incorporates previous snapshots of networks containing first‐order to k‐order weights, and nodes attribute similarities into one weighted graph. In addition, the algorithm utilises a damping factor to ensure that the more recent snapshots allocate a greater weight. Attribute features are then incorporated into topological features. Next, the authors adopt the most advanced architecture, Self‐Attention Networks, to learn node representations. Experimental results on node classification of static attributed networks and link prediction of temporal attributed networks reveal that our proposed approach is competitive against diverse state‐of‐the‐art baseline approaches.

BackgroundThere are many similarities in the clinical manifestations of human norovirus and SARS-CoV-2 infections, and nucleic acid detection is the gold standard for diagnosing both diseases. In order to expedite the identification of norovirus and SARS-CoV-2, a quantitative one-step triplex reverse transcription PCR (RT-qPCR) method was designed in this paper.MethodsA one-step triplex RT-qPCR assay was developed for simultaneous detection and differentiation of human norovirus GI (NoV-GI), GII (NoV-GII) and SARS-CoV-2 from fecal specimens.ResultsThe triplex RT-qPCR assay had high detection reproducibility (CV

Nickel serves as an essential micronutrient for the human body, playing a vital role in various enzymatic processes. However, excessive nickel entering the environment can cause pollution and pose serious risks to animals, plants, and human health. High concentrations of nickel ions in the human body increase the risk of various diseases, highlighting the need for accurate measurement of nickel ions levels. In this study, we designed a sequence-specific cleavage probe for nickel (II) ion called SSC-Ni. Similar to the TaqMan probe, SSC-Ni is an off-on fluorescent probe with an exceptionally low background fluorescence signal. It exhibits high detection specificity, making it highly selective for nickel ions, and the detection limit of the probe towards Ni2+ is as low as 82 nM. The SSC-Ni probe can be utilized for convenient and cost-effective high-throughput quantitative detection of nickel ions in serum. Its user-friendly operation and affordability make it a practical solution. By addressing the lack of simple and effective nickel ion detection methods, this probe has the potential to contribute significantly to environmental monitoring and the protection of human health.

Cyclin‐dependent kinase 1 (CDK1) plays a significant role in certain malignancies. However, it remains unclear whether CDK1 plays a role in esophageal squamous cell carcinoma (ESCC). The aim of this study was to analyze the expression and clinical value of CDK1 in ESCC. CDK1 protein in 151 ESCC tissues and 138 normal esophageal tissues was detected by immunohistochemistry. RNA‐seq of eight pairs of ESCC and adjacent esophageal specimens was performed to evaluate the levels of CDK1 mRNA. Microarray and external RNA‐seq data from 664 cases of ESCC and 1733 cases of control tissues were used to verify the difference in CDK1 expression between the two groups. A comprehensive analysis of all data was performed to evaluate the difference in CDK1 between ESCC tissues and control tissues. Further, functional enrichment analyses were performed based on differentially expressed genes (DEGs) of ESCC and co‐expressed genes (CEGs) of CDK1. In addition, a lncRNA‐miRNA‐CDK1 network was constructed. The expression of CDK1 protein was obviously increased in ESCC tissues (3.540 ± 2.923 vs. 1.040 ± 1.632, P

For children and adolescents, there is a high risk of developing post-traumatic stress disorder (PTSD) after suffering from catastrophic events. Previous studies have identified brain functionally and subcortical brain volumes structurally abnormalities in this population. However, up till now, researches exploring alterations of regional cortical thickness (CTh) and brain interregional structural covariance networks (SCNs) are scarce. In this cross-sectional study, CTh measures are derived from 3-Tesla Tl-weighted MRI imaging data in a well-characterized combined group of children and adolescents with PTSD after an earthquake (N = 35) and a traumatized healthy control group (N = 24). By using surface-based morphometry (SBM) techniques, the regional CTh analysis was conducted. To map interregional SCNs derived from CTh, twenty-five altered brain regions reported in the PTSD population were selected as seeds. Whole-brain SBM analysis discovered a significant thickness reduction in the left medial orbitofrontal cortex for the subjects with PTSD. Similarly, analysis of SCNs associated with “seed” regions primarily located in default mode network (DMN), midline cortex structures, motor cortex, auditory association cortex, limbic system, and visual cortex demonstrated that children and adolescents with PTSD are associated with altered structural covariance with six key regions. This study provides evidence for distinct CTh correlates of PTSD that are present across children and adolescents, suggesting that brain cortical abnormalities related to trauma exposure are present in this population, probably by driving specific symptom clusters associated with disrupted extinction recall mechanisms for fear, episodic memory network and visuospatial attention.

Network embedding has shown its effectiveness in many tasks, such as link prediction, node classification, and community detection. Most attributed network embedding methods consider topological features and attribute features to obtain a node embedding but ignore its implicit information behavior features, including information inquiry, interaction, and sharing. These can potentially lead to ineffective performance for downstream applications. In this article, we propose a novel network embedding framework, named information behavior extraction (IBE), that incorporates nodes’ topological features, attribute features, and information behavior features within a joint embedding framework. To design IBE, we use an existing embedding method (e.g., SDNE, CANE, or CENE) to extract a node’s topological features and attribute features into a basic vector. Then, we propose a topic-sensitive network embedding (TNE) model to extract a node’s information behavior features and eventually generate information behavior feature vectors. In our TNE model, we design an importance score rating algorithm (ISR), which considers both effects of the topic-based community of a node and its interaction with adjacent nodes to capture the node’s information behavior features. Eventually, we concatenate a node’s information behavior feature vector with its basic vector to get its ultimate joint embedding vector. Extensive experiments demonstrate that our method achieves significant and consistent improvements compared to several state-of-the-art embedding methods on link prediction.