RMDGCN: Prediction of RNA methylation and disease associations based on graph convolutional network with attention mechanism.

RNA modification is a post transcriptional modification that occurs in all organisms and plays a crucial role in the stages of RNA life, closely related to many life processes. As one of the newly discovered modifications, N1-methyladenosine (m¹A) plays an important role in gene expression regulation, closely related to the occurrence and development of diseases. However, due to the low abundance of m¹A, verifying the associations between m¹As and diseases through wet experiments requires a great quantity of manpower and resources. In this study, we proposed a computational method for predicting the associations of RNA methylation and disease based on graph convolutional network (RMDGCN) with attention mechanism. We build an adjacency matrix through the collected m¹As and diseases associations, and use positive-unlabeled learning to increase the number of positive samples. By extracting the features of m¹As and diseases, a heterogeneous network is constructed, and a GCN with attention mechanism is adopted to predict the associations between m¹As and diseases. The experimental results indicate that under a 5-fold cross validation, RMDGCN is superior to other methods (AUC = 0.9892 and AUPR = 0.8682). In addition, case studies indicate that RMDGCN can predict the relationships between unknown m¹As and diseases. In summary, RMDGCN is an effective method for predicting the associations between m¹As and diseases. Author summary: As a new epitranscriptomic modification, m¹A plays an important role in the gene expression regulation, closely related to the occurrence and development of diseases. However, due to the low abundance of m¹A, verifying the associations between m¹As and diseases through wet experiments requires a great quantity of manpower and resources. It is especially important to develop computational methods for predicting the associations between m¹A modifications and diseases. We developed a deep learning model to predict the associations of m¹As and diseases, namely RMDGCN. RMDGCN increases the number of known relationships between m¹As and diseases through PU learning, and combines m¹A similarity network and disease similarity network to construct heterogeneous networks. It adopts GCN with layered attention mechanism to predict the associations between methylations and diseases. The results of the 5-fold cross validation show that the performance of RMDGCN is superior to other comparison algorithms. Through case study analysis of breast cancer, RMDGCN can effectively predict the relationships between unknown m¹As and diseases. [ABSTRACT FROM AUTHOR]