Predicting LncRNA-disease Association by Autoencoder and Rotation Forest

In the past few years, most disease-related lncRNAs have been identified, but the experimental identification is cost-consuming and time-consuming. It is therefore very important to develop a reliable computational model to predict lncRNA-disease association. In this paper, we propose a method based on similarity, combining autoencoder and rotation forest to predict lncRNA-disease association (SARLDA). This method not only makes use of disease and lncRNA similarities, but also extracts latent low-dimension features and expand the gap between samples to make it easier to predict the associations. To evaluate our method, we conducted several experiments. Sufficient validations show that this method has significantly improved the prediction performance.