Hyperbolic multivariate feature learning in higher-order heterogeneous networks for drug–disease prediction

Abstract

New drug discovery has always been a costly, time-consuming process with a high failure rate. Repurposing existing drugs offers a valuable alternative and reduces the risks associated with developing new drugs. Various experimental methods have been employed to facilitate drug repositioning; however, associations prediction between drugs and diseases through biological experiments is both expensive and time-consuming. Consequently, it is imperative to develop efficient and highly precise computational methods for predicting these associations. Based on this, we propose a drug–disease associations prediction method based on $H$yperbolic $M$ultivariate feature $L$earning in $H$igh-order $H$eterogeneous Networks for Drug–Disease Prediction, called $H$³ML. Our approach begins by mining high-order information from protein–disease and drug–protein networks to construct high-order heterogeneous networks. Subsequently, we employ multivariate feature learning to create hyperbolic representations, and then enhance the features of the heterogeneous network. Finally, we utilize a hyperbolic graph attention network in the hyperbolic space to aggregate neighbor information and perform the final prediction task. In addition, we evaluate the performance of $H$³ML by comparing it with some state-of-the-art methods across different datasets. The case study further validate the effectiveness of $H$³ML. Our implementation will be publicly available at: https://github.com/jianruichen/H-3ML.