Recently, an increasing number of studies have demonstrated that miRNAs are involved in human diseases, indicating that miRNAs might be a potential pathogenic factor for various diseases. Therefore, figuring out the relationship between miRNAs and diseases plays a critical role in not only the development of new drugs, but also the formulation of individualized diagnosis and treatment. As the prediction of miRNA-disease association via biological experiments is expensive and time-consuming, computational methods have a positive effect on revealing the association. In this study, a novel prediction model integrating GCN, CNN and Squeeze-and-Excitation Networks (GCSENet) was constructed for the identification of miRNA-disease association. The model first captured features by GCN based on a heterogeneous graph including diseases, genes and miRNAs. Then, considering the different effects of genes on each type of miRNA and disease, as well as the different effects of the miRNA-gene and disease-gene relationships on miRNA-disease association, a feature weight was set and a combination of miRNA-gene and disease-gene associations was added as feature input for the convolution operation in CNN. Furthermore, the squeeze and excitation blocks of SENet were applied to determine the importance of each feature channel and enhance useful features by means of the attention mechanism, thus achieving a satisfactory prediction of miRNA-disease association. The proposed method was compared against other state-of-the-art methods. It achieved an AUROC score of 95.02% and an AUPR score of 95.55% in a 10-fold cross-validation, which led to the finding that the proposed method is superior to these popular methods on most of the performance evaluation indexes.
We propose a new method to analyse the similarity of protein CPK models. In the proposed method we first construct the skeleton of protein models by an improved L1-medial skeleton extraction. The skeleton information is then used to form a local radius descriptor. Finally, the shape similarity of protein models is compared by using the local radius descriptor based on the absolute degree of grey incidence. Experimental results show that the improved L1-medial skeleton of protein models can describe the shapes of the protein models well. The local descriptor based on the skeleton combined with the absolute degree of grey incidence shows satisfactory performance for comparing the shape similarity of protein CPK models.
The paper proposed a problem that the network topology impacts on the repair cost over a distributed storage system with network coding. Contrary to the general network model, the tandem network model exists a link between the adjacent nodes. To repair one failed node over the two network models, it might cost a small price over the tandem network model compared to the general network model. The paper concluded that the optimal repair cost in the tandem network is obtained no matter where the position of the failed node is. Meanwhile, the minimum repair cost was obtained over the tandem network and the general network model. Finally, the experiments of minimum repair cost over one type of real world network model (such as WSNs) showed that the network topology has a significant impact on the repair cost as well as the theoretical support in the paper.
The 3D structure of a protein is closely related to its function, and the similarity analysis between their structures can help reveal the function of proteins. However, there exist two problems arising from the analysis of 3D structures of proteins. The proteins with a similar sequence may have different structures, while the proteins with a similar structure may have different sequences. In the analysis of similarity in 3D structures of proteins, it remains difficult for the traditional methods using the spatial feature distribution and geometry or topology features of proteins to solve these problems. In this paper, a Tile-CNN network is proposed to analyze the similarity of proteins in 3D structure. In order to capture the overall and the local features as exhibited by the 3D structures of proteins, it projects 3D protein models into 2D protein images from different views and then cuts these 2D projected images using the tile strategy. After the training of proteins with these images in the Tile-CNN, the test protein model can be expressed by an analysis matrix, and then the similarity between 3D structures of proteins is computed using the root mean square distance (RMSD) for the benchmark matrix and the analysis matrix. As revealed by the experimental results, the proposed algorithm is more robust in analyzing the similarity of 3D structures of proteins and produces a satisfactory performance in solving the two aforementioned problems.