ABSTRACT
Heterogeneous graph neural networks play a crucial role in discovering discriminative node embeddings and relations from multi-relational networks. One of the key challenges in heterogeneous graph learning lies in designing learnable meta-paths, which significantly impact the quality of learned embeddings. In this paper, we propose an Attributed Multi-Order Graph Convolutional Network (AMOGCN), which automatically explores meta-paths that involve multi-hop neighbors by aggregating multi-order adjacency matrices. The proposed model first constructs different orders of adjacency matrices from manually designed node connections. Next, AMOGCN fuses these various orders of adjacency matrices to create an intact multi-order adjacency matrix. This process is supervised by the node semantic information, which is extracted from the node homophily evaluated by attributes. Eventually, we employ a one-layer simplifying graph convolutional network with the learned multi-order adjacency matrix, which is equivalent to the cross-hop node information propagation with multi-layer graph neural networks. Substantial experiments reveal that AMOGCN achieves superior semi-supervised classification performance compared with state-of-the-art competitors.
Subject(s)
Learning , Neural Networks, Computer , SemanticsABSTRACT
Zinc (Zn) is a vital micronutrient that strengthens the immune system, aids cellular activities, and treats infectious diseases. A deficiency in Zn can lead to an imbalance in the immune system. This imbalance is particularly evident in severe deficiency cases, where there is a high susceptibility to various viral infections, including COVID-19 caused by SARS-CoV-2. This review article examines the nutritional roles of Zn in human health, the maintenance of Zn concentration, and Zn uptake. As Zn is an essential trace element that plays a critical role in the immune system and is necessary for immune cell function and cell signaling, the roles of Zn in the human immune system, immune cells, interleukins, and its role in SARS-CoV-2 infection are further discussed. In summary, this review paper encapsulates the nutritional role of Zn in the human immune system, with the hope of providing specific insights into Zn research.
ABSTRACT
Graph convolutional network (GCN) has gained widespread attention in semisupervised classification tasks. Recent studies show that GCN-based methods have achieved decent performance in numerous fields. However, most of the existing methods generally adopted a fixed graph that cannot dynamically capture both local and global relationships. This is because the hidden and important relationships may not be directed exhibited in the fixed structure, causing the degraded performance of semisupervised classification tasks. Moreover, the missing and noisy data yielded by the fixed graph may result in wrong connections, thereby disturbing the representation learning process. To cope with these issues, this article proposes a learnable GCN-based framework, aiming to obtain the optimal graph structures by jointly integrating graph learning and feature propagation in a unified network. Besides, to capture the optimal graph representations, this article designs dual-GCN-based meta-channels to simultaneously explore local and global relations during the training process. To minimize the interference of the noisy data, a semisupervised graph information bottleneck (SGIB) is introduced to conduct the graph structural learning (GSL) for acquiring the minimal sufficient representations. Concretely, SGIB aims to maximize the mutual information of both the same and different meta-channels by designing the constraints between them, thereby improving the node classification performance in the downstream tasks. Extensive experimental results on real-world datasets demonstrate the robustness of the proposed model, which outperforms state-of-the-art methods with fixed-structure graphs.
ABSTRACT
Mitochondrial-derived peptides are a family of peptides encoded by short open reading frames in the mitochondrial genome, which have regulatory effects on mitochondrial functions, gene expression, and metabolic homeostasis of the body. As a new member of the mitochondrial-derived peptide family, mitochondrial open reading frame of the 12S rRNA-c (MOTS-c) is regarding a peptide hormone that could reduce insulin resistance, prevent obesity, improve muscle function, promote bone metabolism, enhance immune regulation, and postpone aging. MOTS-c plays these physiological functions mainly through activating the AICAR-AMPK signaling pathways by disrupting the folate-methionine cycle in cells. Recent studies have shown that the above hormonal effect can be achieved through MOTS-c regulating the expression of genes such as GLUT4, STAT3, and IL-10. However, there is a lack of articles summarizing the genes and pathways involved in the physiological activity of MOTS-c. This article aims to summarize and interpret the interesting and updated findings of MOTS-c-associated genes and pathways involved in pathological metabolic processes. Finally, it is expected to develop novel diagnostic markers and treatment approaches with MOTS-c to prevent and treat metabolic disorders in the future.