iCircDA-ENR: identification of circRNA-disease associations based on ensemble network representation

Abstract

Circular RNAs (circRNAs) are severing as important regulators for various physiological and pathological life activities. Identifying associations between circRNAs and diseases can help uncover the disease mechanism, and promote the diagnosis and treatment of human diseases. To provide assisting guidance and optimize biological experiments, some computational methods have been proposed to predict circRNA-disease associations. However, most predictors focus on identifying missing associations for known circRNA and diseases. It is still challenging to effectively detect potential circRNA-disease association pattern because of their limited generation ability and insufficient pair representation. In this regard, we propose a novel computational method named iCircDA-ENR for identifying circRNA-disease associations based on ensemble network representation. Different from other predictors, iCircDA-ENR is a ranking method. Multiple biological information and meta-paths are introduced to construct heterogeneous relation network, and then different network representation algorithms are incorporated into ranking framework to capture informative network features. The learned ranking predictor prioritizes the candidate diseases for query circRNAs according to their relevance degree. Experimental results illustrate that iCircDA-ENR achieves better performance and wider applicability, benefited from its sufficient representation and effective learning.