Heterogeneous network model to infer human disease-long intergenic non-coding RNA associations

With the knowledge of molecular biology it is highlighting that long non-coding RNAs (lncRNAs) play a critical role in many important biological processes, such as imprinting control, cell differentiation, immune responses, human diseases, tumorigenesis and other biological processes. This study proposes a novel computational method, named KRWRH, to infer disease-lincRNA associations with the influence of phenotype information and tissue expression details of lincRNA. Gaussian interaction profile kernel is calculated for diseases and lincRNAs and random walk with restart method is used for final prediction. The proposed method KRWRH is compared with four existing methods: LRLSLDA, TslncRNA, NRWRH, and RWRH. The experimental results based on the leave-one-out cross validation, ROC curves, and mean enrichment show that the proposed method KRWRH is able to predict known and unknown disease-lincRNA associations more effectively.