Predicting miRNA–Disease Associations by Combining Graph and Hypergraph Convolutional Network

• Published in: Interdisciplinary sciences : computational life sciences Vol. 16; no. 2; pp. 289 - 303
• Main Authors: Liang, Xujun, Guo, Ming, Jiang, Longying, Fu, Ying, Zhang, Pengfei, Chen, Yongheng
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.06.2024
• Subjects: Algorithms; Biomedical and Life Sciences; Computational Biology - methods; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Appl. in Life Sciences; Genetic Predisposition to Disease; Health Sciences; Humans; Life Sciences; Mathematical and Computational Physics; Medicine; MicroRNAs - genetics; Neural Networks, Computer; Original Research Article; Statistics for Life Sciences; Theoretical; Theoretical and Computational Chemistry; miRNA–disease associatons; Graph convolution; Hypergraph convolution; Algorithm
• ISSN: 1913-2751; 1867-1462; 1867-1462
• DOI: 10.1007/s12539-023-00599-3

miRNAs are important regulators for many crucial biological processes. Many recent studies have shown that miRNAs are closely related to various human diseases and can be potential biomarkers or therapeutic targets for some diseases, such as cancers. Therefore, accurately predicting miRNA–disease associations is of great importance for understanding and curing diseases. However, how to efficiently utilize the characteristics of miRNAs and diseases and the information on known miRNA–disease associations for prediction is still not fully explored. In this study, we propose a novel computational method for predicting miRNA–disease associations. The proposed method combines the graph convolutional network and the hypergraph convolutional network. The graph convolutional network is utilized to extract the information from miRNA-similarity data as well as disease-similarity data. Based on the representations of miRNAs and diseases learned by the graph convolutional network, we further use the hypergraph convolutional network to capture the complex high-order interactions in the known miRNA–disease associations. We conduct comprehensive experiments with different datasets and predictive tasks. The results show that the proposed method consistently outperforms several other state-of-the-art methods. We also discuss the influence of hyper-parameters and model structures on the performance of our method. Some case studies also demonstrate that the predictive results of the method can be verified by independent experiments. Graphical Abstract