A novel computational method for inferring competing endogenous interactions

Posttranscriptional cross talk and communication between genes mediated by microRNA response element (MREs) yieldlarge regulatory competing endogenous RNA (ceRNA) networks. Their inference may improve the understanding of pathologies and shed new light on biological mechanisms. A variety of RNA: messenger RNA, transcribed pseudogenes, noncodingRNA, circular RNA and proteins related to RNA-induced silencing complex complex interacting with RNA transfer and ribosomal RNA have been experimentally proved to be ceRNAs. We retrace the ceRNA hypothesis of post-transcriptional regulation from its original formulation [Salmena L, Poliseno L, Tay Y, et al. Cell 2011;146:353–8] to the most recent experi- mental and computational validations. We experimentally analyze the methods in literature [Li J-H, Liu S, Zhou H, et al. Nucleic Acids Res 2013;42:D92–7; Sumazin P, Yang X, Chiu H-S, et al. Cell 2011;147:370–81; Sarver AL, Subramanian S. Bioinformation 2012;8:731–3] comparing them with a general machine learning approach, called ceRNA predIction Algorithm, evaluating the performance in predicting novel MRE-based ceRNAs.