iGRLCDA: identifying circRNA–disease association based on graph representation learning

• Published in: Briefings in bioinformatics 2022-05, Vol.23 (3)
• Main Authors: Zhang, Han-Yuan, Wang, Lei, You, Zhu-Hong, Hu, Lun, Zhao, Bo-Wei, Li, Zheng-Wei, Li, Yang-Ming
• Format: Article
• Language: English
• Subjects: Algorithms; Circular RNA; Competitiveness; Computational Biology - methods; Computer applications; Deep learning; Feature extraction; Gene regulation; Graph representations; Graphical representations; Medical research; MicroRNAs - genetics; miRNA; Nucleotide sequence; Prediction models; Predictions; Ribonucleic acid; RNA; RNA, Circular; ROC Curve; Standard data; Topology
• ISSN: 1467-5463; 1477-4054
• DOI: 10.1093/bib/bbac083

Abstract While the technologies of ribonucleic acid-sequence (RNA-seq) and transcript assembly analysis have continued to improve, a novel topology of RNA transcript was uncovered in the last decade and is called circular RNA (circRNA). Recently, researchers have revealed that they compete with messenger RNA (mRNA) and long noncoding for combining with microRNA in gene regulation. Therefore, circRNA was assumed to be associated with complex disease and discovering the relationship between them would contribute to medical research. However, the work of identifying the association between circRNA and disease in vitro takes a long time and usually without direction. During these years, more and more associations were verified by experiments. Hence, we proposed a computational method named identifying circRNA–disease association based on graph representation learning (iGRLCDA) for the prediction of the potential association of circRNA and disease, which utilized a deep learning model of graph convolution network (GCN) and graph factorization (GF). In detail, iGRLCDA first derived the hidden feature of known associations between circRNA and disease using the Gaussian interaction profile (GIP) kernel combined with disease semantic information to form a numeric descriptor. After that, it further used the deep learning model of GCN and GF to extract hidden features from the descriptor. Finally, the random forest classifier is introduced to identify the potential circRNA–disease association. The five-fold cross-validation of iGRLCDA shows strong competitiveness in comparison with other excellent prediction models at the gold standard data and achieved an average area under the receiver operating characteristic curve of 0.9289 and an area under the precision-recall curve of 0.9377. On reviewing the prediction results from the relevant literature, 22 of the top 30 predicted circRNA–disease associations were noted in recent published papers. These exceptional results make us believe that iGRLCDA can provide reliable circRNA–disease associations for medical research and reduce the blindness of wet-lab experiments.