Prediction of drug–target interaction networks from the integration of chemical and genomic spaces

TLDR

Identifying drug–target interactions is a central challenge in genomic drug discovery. The authors aim to develop statistical methods that predict unknown drug–target interaction networks from chemical structure and genomic sequence data, while characterizing four human network classes and their correlation with drug and target similarities. They formulate the inference as a supervised learning problem on a bipartite graph, integrating chemical and genomic spaces into a unified pharmacological space without requiring 3D protein structures, and apply it at large scale. The approach accurately predicts the four classes of drug–target interaction networks, revealing many potential interactions and enhancing research productivity in genomic drug discovery. Software and all prediction results are available upon request and at http://web.kuicr.kyoto-u.ac.jp/supp/yoshi/drugtarget/.

Abstract

The identification of interactions between drugs and target proteins is a key area in genomic drug discovery. Therefore, there is a strong incentive to develop new methods capable of detecting these potential drug-target interactions efficiently.In this article, we characterize four classes of drug-target interaction networks in humans involving enzymes, ion channels, G-protein-coupled receptors (GPCRs) and nuclear receptors, and reveal significant correlations between drug structure similarity, target sequence similarity and the drug-target interaction network topology. We then develop new statistical methods to predict unknown drug-target interaction networks from chemical structure and genomic sequence information simultaneously on a large scale. The originality of the proposed method lies in the formalization of the drug-target interaction inference as a supervised learning problem for a bipartite graph, the lack of need for 3D structure information of the target proteins, and in the integration of chemical and genomic spaces into a unified space that we call 'pharmacological space'. In the results, we demonstrate the usefulness of our proposed method for the prediction of the four classes of drug-target interaction networks. Our comprehensively predicted drug-target interaction networks enable us to suggest many potential drug-target interactions and to increase research productivity toward genomic drug discovery.Softwares are available upon request.Datasets and all prediction results are available at http://web.kuicr.kyoto-u.ac.jp/supp/yoshi/drugtarget/.