DRGCNCDA: Predicting circRNA-disease interactions based on knowledge graph and disentangled relational graph convolutional network.

Abstract

Emerging studies have shown that circular RNA (circRNA) plays a significant role in the diagnosis and prognosis of human disease. Some computational methods have been proposed to predict circRNA-disease associations. However, some methods only use circRNA-disease association and ignore the associations of other biological entities. In addition, these methods do not take into account the latent factors of different kinds of circRNAs and diseases. To solve these limitations of existing computational models, we propose a new computational model (DRGCNCDA) based on disentangled relational graph convolutional network. The circRNA-disease multi-relational graphs are constructed by collecting multiple relational data among circRNA, disease, miRNA and lncRNA. Then, the disentangled relational graph convolutional network is employed to obtain the feature vectors of circRNA and disease. Finally, knowledge graph model is applied to predict the affinity scores of circRNA-disease associations based on the embeddings of circRNA and disease. The 5-fold cross validation is utilized to evaluate the performance of the method. The experimental results show that the DRGCNCDA outperforms other existing models. Moreover, the case study demonstrates that the DRGCNCDA is effective to predict the circRNA-disease association and can provide reliable candidates for biological experiments.