A Method Based On Dual-Network Information Fusion to Predict MiRNA-Disease Associations

MicroRNAs (miRNAs) are single-stranded small RNAs. An increasing number of studies have shown thatmiRNAs play a vital role inmany important biological processes. However, some experimental methods to predict unknownmiRNA-disease associations (MDAs) are time-consuming and costly. Only a small percentage ofMDAs are verified by researchers. Therefore, there is a great need for high-speed and efficient methods to predict novelMDAs. In this paper, a new computational method based on Dual-Network Information Fusion (DNIF) is developed to predict potentialMDAs. Specifically, on the one hand, two enhanced sub-models are integrated to reconstruct an effective prediction framework; on the other hand, the prediction performance of the algorithm is improved by fully fusingmultiple omics data information, including validatedmiRNA-disease associations network, miRNA functional similarity, disease semantic similarity and Gaussian interaction profile (GIP) kernel network associations. As a result, DNIF achieves the excellent performance under situation of 5fold cross validation (average AUC of 0.9571). In the cases study of three important human diseases, our model has achieved satisfactory performance in predicting potential miRNAs for certain diseases. The reliable experimental results demonstrate thatDNIF could serve as an effective calculationmethod to accelerate the identification ofMDAs.