School of Computer, Electronic and Information, Guangxi University, Nanning, China; Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning, China.
School of Computer, Electronic and Information, Guangxi University, Nanning, China.
Methods. 2022 Dec;208:35-41. doi: 10.1016/j.ymeth.2022.10.002. Epub 2022 Oct 21.
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.
新兴研究表明，环状 RNA（circRNA）在人类疾病的诊断和预后中发挥着重要作用。已经提出了一些计算方法来预测 circRNA-疾病关联。然而，一些方法仅使用 circRNA-疾病关联，而忽略了其他生物实体的关联。此外，这些方法没有考虑不同种类的 circRNA 和疾病的潜在因素。为了解决现有计算模型的这些局限性，我们提出了一种基于解缠关系图卷积网络的新计算模型（DRGCNCDA）。通过收集 circRNA、疾病、miRNA 和 lncRNA 之间的多种关系数据来构建 circRNA-疾病多关系图。然后，使用解缠关系图卷积网络获取 circRNA 和疾病的特征向量。最后，基于 circRNA 和疾病的嵌入，应用知识图模型来预测 circRNA-疾病关联的亲和度分数。利用 5 折交叉验证来评估该方法的性能。实验结果表明，DRGCNCDA 优于其他现有模型。此外，案例研究表明，DRGCNCDA 可有效预测 circRNA-疾病关联，并为生物实验提供可靠的候选对象。
