Prediction of lncRNA–Disease Associations via Closest Node Weight Graphs of the Spatial Neighborhood Based on the Edge Attention Graph Convolutional Network

Accumulated evidence of biological clinical trials has shown that long non-coding RNAs (lncRNAs) are closely related to the occurrence and development of various complex human diseases. Research works on lncRNA–disease relations will benefit to further understand the pathogenesis of human complex diseases at the molecular level, but only a small proportion of lncRNA–disease associations has been confirmed. Considering the high cost of biological experiments, exploring potential lncRNA–disease associations with computational approaches has become very urgent. In this study, a model based on closest node weight graph of the spatial neighborhood (CNWGSN) and edge attention graph convolutional network (EAGCN), LDA-EAGCN, was developed to uncover potential lncRNA–disease associations by integrating disease semantic similarity, lncRNA functional similarity, and known lncRNA–disease associations. Inspired by the great success of the EAGCN method on the chemical molecule property recognition problem, the prediction of lncRNA–disease associations could be regarded as a component recognition problem of lncRNA–disease characteristic graphs. The CNWGSN features of lncRNA–disease associations combined with known lncRNA–disease associations were introduced to train EAGCN, and correlation scores of input data were predicted with EAGCN for judging whether the input lncRNAs would be associated with the input diseases. LDA-EAGCN achieved a reliable AUC value of 0.9853 in the ten-fold cross-over experiments, which was the highest among five state-of-the-art models. Furthermore, case studies of renal cancer, laryngeal carcinoma, and liver cancer were implemented, and most of the top-ranking lncRNA–disease associations have been proven by recently published experimental literature works. It can be seen that LDA-EAGCN is an effective model for predicting potential lncRNA–disease associations. Its source code and experimental data are available at https://github.com/HGDKMF/LDA-EAGCN.

Detecting Overlapping Communities in Modularity Optimization by Reweighting Vertices

On the purpose of detecting communities, many algorithms have been proposed for the disjointed community sets. The major challenge of detecting communities from the real-world problems is to determine the overlapped communities. The overlapped vertices belong to some communities, so it is difficult to be detected using the modularity maximization approach. The major problem is that the overlapping structure barely be found by maximizing the fuzzy modularity function. In this paper, we firstly introduce a node weight allocation problem to formulate the overlapping property in the community detection. We propose an extension of modularity, which is a better measure for overlapping communities based on reweighting nodes, to design the proposed algorithm. We use the genetic algorithm for solving the node weight allocation problem and detecting the overlapping communities. To fit the properties of various instances, we introduce three refinement strategies to increase the solution quality. In the experiments, the proposed method is applied on both synthetic and real networks, and the results show that the proposed solution can detect the nontrivial valuable overlapping nodes which might be ignored by other algorithms.

A New Complex Network Model with Multiweights and Its Synchronization Control

Based on the weighted complex network model, this paper establishes a multiweight complex network model, which possesses several different weights on the one edge. According to the method of network split, the complex network with multiweights is split into several different complex networks with single weight. Some new static characteristics, such as node weight, node degree, node weight strength, node weight distribution, edge weight distribution, and diversity of weight distribution are defined. Then, by using Lyapunov stability theory, the adaptive feedback synchronization controller is designed, and the complete synchronization of the new complex network model is investigated. Two numerical examples of a triweight network model with the same and diverse structure are given to demonstrate the effectiveness of the control strategies. The synchronization design can achieve good results in the same and diverse structure network models with multiweights, which enrich complex network and control theory, so has certain theoretical and practical significance.

Sika deer (Cervus nippon) velvet antler ameliorates 2,4-dinitrochlorobenzene-induced atopic dermatitis-like clinical signs in a rodent model

Context Deer velvet is a rarely used component in traditional Chinese medicine and has beneficial effects against several diseases. As a substance that covers the bone and cartilage of immature antlers, deer velvet is a natural cytokine ‘storeroom’ that is rich in protein and proteoglycans. Recently, proteoglycans have been shown to have beneficial effects against inflammation. Aims To determine whether antler extract possesses therapeutic effects in a mouse model of atopic dermatitis (AD) and to explore the underlying mechanisms of action. Methods BALB/c mice were randomly divided into the following groups: control, AD, and AD + antler groups. We established an in vivo AD model by repeatedly exposing the ears of mice to Dermatophagoides farinae extract (house dust-mite extract) and 2,4-dinitrochlorobenzene once per week for 4 weeks. On the day after induction, ear thickness was measured. Antler extract (100 mg/kg) was administered orally once a day for 26 days. After 4 weeks of treatment with antler extract, the epidermal and dermal ear thickness, mast-cell infiltration, spleen weight, and lymph-node weight were measured. In addition, the mRNA levels of several pathogenic cytokines in the ears were measured. The concentrations of IL-4, IL-5, IL-10, IL-31 and IL-17 mRNA in the skin lesions of each group were measured by quantitative polymerase chain reaction. Key results Epidermal and dermal ear thickness, mast-cell infiltration, lymph-node weight, and gene expression levels of pathogenic cytokines in ear tissue were diminished following oral administration of antler extract, unlike in the control group. Conclusions The results of the present study strongly suggest that antler extract exhibits therapeutic activity against atopic dermatitis via regulation of inflammatory response. Implications Further exploration of the mechanisms of action of antler extract will be important for clinical application.