Heterogeneous Graph Convolutional Networks and Matrix Completion for miRNA-Disease Association Prediction

摘要

Due to the cost and complexity of biological experiments, many computational methods have been proposed to predict potential miRNA-disease associations by utilizing known miRNA-disease associations and other related information. However, there are some challenges for these computational methods. First, the relationships between miRNAs and diseases are complex. The computational network should consider the local and global influence of neighborhood from the network. Furthermore, predicting the diseases related miRNAs without any known associations is also very important. This study presents a new computational method which constructs a heterogeneous network composed of the miRNA similarity network, disease similarity network, and the known miRNA-disease association network. The miRNA similarity considers the miRNAs and their possible families and clusters. The information of each node in this network is obtained by aggregating neighborhood information with graph convolutional networks (GCNs), which can pass the information of a node to its intermediate and distant neighbors. The diseases related miRNAs with no known associations can be predicted with the reconstructed heterogeneous matrix. We apply 5-fold cross-validation, leave-one-disease-out cross-validation, global and local leave-one-out cross-validation to evaluate our method. The area under curves (AUCs) of them are 0.9616, 0.9946, 0.9656 and 0.9532 respectively, which proves that our approach significantly outperform the state-of-the-art methods. Case studies shows that the approach can effectively predict the new diseases without any known miRNAs.