Accumulating evidence demonstrates that miRNAs serve as critical biomarkers in various complex human diseases. Thus, identifying potential miRNA-disease associations have become a hot research topic for providing better understanding of disease pathology, including cell carcinoma, cell proliferation and mevalonate pathway. Recently, based on various biological datasets, more and more computational prediction methods have been designed to uncover disease-related miRNAs for further experimental validation. Due to the fact that different limitations exist in previous computational methods, we proposed the model of Decision Template-based MiRNA-Disease Association prediction (DTMDA) to prioritize potential related miRNAs for diseases of interest. By integrating miRNA functional similarity network, miRNA Gaussian interaction profile kernel similarity network, two disease semantic similarity networks and disease Gaussian interaction profile kernel similarity network, we trained five multi-label K nearest neighbors-based core classifiers.