Network Diffusion Approach to Predict LncRNA Disease Associations Using Multi-Type Biological Networks: LION

The scarcity of information about the link between lncRNA and diseases in a multi-level complex network prevents us from better rationalizing about the roles lncRNAs play in cellular processes and diseases. Current approaches often use known lncRNA-disease associations to predict potential lncRNA-disease links. In this work, we exploited the topology of the protein interactome and multi-layer networks to propose the lncRNA rankIng by NetwOrk DiffusioN (LION) approach to identify lncRNA-disease associations. We first built a multi-level complex network (tripartite network) consisting of lncRNA-protein, protein-protein interactions, and protein-disease associations. Next, we apply the random walk network diffusion algorithm to predict the lncRNAs disease associations in the multi-level network. LION achieved an AUC value of 91.8% for cardiovascular diseases, 91.9% for cancer and 90.2% for neurological diseases by using experimentally verified lncRNAs associated with diseases. Furthermore, compared to a similar approach, LION performed better for cardiovascular diseases and cancer. Given the versatile role played by lncRNAs in different biological mechanisms that are perturbed in diseases, LION’s accurate prediction of lncRNA-disease associations helps in ranking LncRNAs that could function as potential biomarkers and potential drug targets.