Background: Long non-coding RNAs play an important role in human complex diseases. Identification of lncRNAdisease\nassociations will gain insight into disease-related lncRNAs and benefit disease diagnoses and treatment.\nHowever, using experiments to explore the lncRNA-disease associations is expensive and time consuming.\nResults: In this study, we developed a novel method to identify potential lncRNA-disease associations by\nIntegrating Diverse Heterogeneous Information sources with positive pointwise Mutual Information and Random\nWalk with restart algorithm (namely IDHI-MIRW). IDHI-MIRW first constructs multiple lncRNA similarity networks and\ndisease similarity networks from diverse lncRNA-related and disease-related datasets, then implements the random\nwalk with restart algorithm on these similarity networks for extracting the topological similarities which are fused\nwith positive pointwise mutual information to build a large-scale lncRNA-disease heterogeneous network. Finally,\nIDHI-MIRW implemented random walk with restart algorithm on the lncRNA-disease heterogeneous network to\ninfer potential lncRNA-disease associations.\nConclusions: Compared with other state-of-the-art methods, IDHI-MIRW achieves the best prediction performance.\nIn case studies of breast cancer, stomach cancer, and colorectal cancer, 36/45 (80%) novel lncRNA-disease\nassociations predicted by IDHI-MIRW are supported by recent literatures. Furthermore, we found lncRNA LINC01816\nis associated with the survival of colorectal cancer patients. IDHI-MIRW is freely available at https://github.com/\nNWPU-903PR/IDHI-MIRW.
Loading....