An improved computational method for prediction of lncRNA-disease associations based on collaborative filtering and resource allocation

Various lncRNAs have been proved to play vital roles in a lot of biological processes. Finding and verifying lncRNA-disease associations contributes to understand human complex disease at molecular level and support the diagnosis, treatment and prevention of complex diseases. It is laboratory, time-consuming and expensive to find and verify lncRNA-disease associations by biological experiments. Therefore, it is urgent to develop a computational method to predict lncRNA-disease associations to save time and resources. In this paper, we proposed an improved computational method for prediction of lncRNA-disease associations based on collaborative filtering and resource allocation. It achieves a reliable prediction performance with both best AUC and AUPR values of 0.983 under 5-fold cross-validation. Additionally, the experimental results show that it is superior to other previous related methods. It could be acknowledged as a forceful and valuable tool to predict lncRNA-disease associations.