Computational drug repositioning, designed to identify new indications for existing drugs, significantly reduced the cost and time\ninvolved in drug development. Prediction of drug-disease associations is promising for drug repositioning. Recent years have\nwitnessed an increasing number of machine learning-based methods for calculating drug repositioning. In this paper, a novel\nfeature learning method based on Gaussian interaction profile kernel and autoencoder (GIPAE) is proposed for drug-disease\nassociation. In order to further reduce the computation cost, both batch normalization layer and the full-connected layer are\nintroduced to reduce training complexity. The experimental results of 10-fold cross validation indicate that the proposed method\nachieves superior performance on Fdataset and Cdataset with theAUCs of 93.30% and 96.03%, respectively,whichwere higher than\nmany previous computational models. To further assess the accuracy of GIPAE, we conducted case studies on two complex human\ndiseases. The top 20 drugs predicted, 14 obesity-related drugs, and 11 drugs related to Alzheimer's disease were validated in the\nCTD database.The results of cross validation and case studies indicated that GIPAE is a reliable model for predicting drug-disease\nassociations.
Loading....