iCDA-CGR: Identification of circRNA-disease associations based on Chaos Game Representation

• DOI: 10.1371/journal.pcbi.1007872
• Publication Date: 2020-05-18T18:49:43Z
• Authors: Kai Zheng; Zhu-Hong You; Jian-Qiang Li; Lei Wang; Zhen-Hao Guo; Yu-An Huang
• Keywords: Sequence (biology)

Found in recent research, tumor cell invasion, proliferation, or other biological processes are controlled by circular RNA. Understanding the association between circRNAs and diseases is an important way to explore pathogenesis of complex promote disease-targeted therapy. Most methods, such as k-mer PSSM, based on analysis high-throughput expression data have tendency think functionally similar nucleic acid lack direct linear homology regardless positional information only quantify nonlinear sequence relationships. However, many diseases, relationship pathogenic ordinary not much different. Therefore, can help predict associations circRNA disease. To fill up this gap, we propose a new method, named iCDA-CGR, circRNA-disease associations. In particular, introduce quantifies Chaos Game Representation (CGR) technology position for first time prediction model. cross-validation experiment, our method achieved 0.8533 AUC, which was significantly higher than existing methods. validation independent sets including circ2Disease, circRNADisease CRDD, accuracy iCDA-CGR reached 95.18%, 90.64% 95.89%. Moreover, case studies, 19 top 30 predicted circRDisease dataset were confirmed newly published literature. These results demonstrated that has outstanding robustness stability, provide highly credible candidates experiments.