Overlap matrix completion for predicting drug-associated indications

Identification of potential drug–associated indications is critical for either approved or novel drugs in drug repositioning. Current computational methods based on drug similarity and disease similarity have been developed to predict drug–disease associations. When more reliable drug- or disease-related information becomes available and is integrated, the prediction precision can be continuously improved. However, it is a challenging problem to effectively incorporate multiple types of prior information, representing different characteristics of drugs and diseases, to identify promising drug–disease associations. In this study, we propose an overlap matrix completion (OMC) for bilayer networks (OMC2) and tri-layer networks (OMC3) to predict potential drug-associated indications, respectively. OMC is able to efficiently exploit the underlying low-rank structures of the drug–disease association matrices. In OMC2, first of all, we construct one bilayer network from drug-side aspect and one from disease-side aspect, and then obtain their corresponding block adjacency matrices. We then propose the OMC2 algorithm to fill out the values of the missing entries in these two adjacency matrices, and predict the scores of unknown drug–disease pairs. Moreover, we further extend OMC2 to OMC3 to handle tri-layer networks. Computational experiments on various datasets indicate that our OMC methods can effectively predict the potential drug–disease associations. Compared with the other state-of-the-art approaches, our methods yield higher prediction accuracy in 10-fold cross-validation and de novo experiments. In addition, case studies also confirm the effectiveness of our methods in identifying promising indications for existing drugs in practical applications.Author summary: This work introduces a computational approach, namely overlap matrix completion (OMC), to predict potential associations between drugs and diseases. The novelty of OMC lies in constructing an efficient framework of incorporating multiple types of prior information in bilayer and tri-layer networks. OMC for bilayer networks (OMC2) can approximate the low-rank structures of the drug–disease association matrices from both drug-side and disease-side. In addition, we further improve the prediction accuracy by extending OMC to handle tri-layer networks and develop its corresponding algorithm (OMC3). To evaluate the performance of OMC2 and OMC3, we conduct 10-fold cross-validation and de novo experiments on three datasets. Our computational results demonstrate that both OMC2 and OMC3 generally outperform five state-of-the-art methods in terms of ROC curve, PR curve, and top-ranked predictions.