Find in Library

Accurate identification of microRNA regulatory modules can give insights to understand microRNA synergistical regulatory mechanism. However, the identification accuracy suffers from incomplete biological data. In this paper, we proposed a learning-based framework called MicroRNA regulatory module dentification with Convolutional Autoencoders (MICA). Firstly, the framework applied convolutional autoencoders to extract significant features of microRNA and their target-genes. Then they were clustered into microRNA clusters and target-gene clusters. Finally, the two types of clusters were combined into modules by known microRNA–target interactions. Compared with three existing methods on three cancer data sets, the modules detected by the proposed method exhibited better overall performance.