Gaussian interaction profile kernels for predicting drug–target interaction

TLDR

In silico prediction of drug–target interactions is crucial for drug discovery, yet only a small fraction of all possible pairs have been experimentally validated. The study develops a computational method that accurately predicts drug–target interactions using only the interaction network. The authors construct Gaussian Interaction Profile kernels from binary interaction profiles and apply regularized least squares to predict interactions, evaluating the approach on four benchmark networks. The method attains an AUPR of up to 92.7, outperforming existing approaches, and adding chemical and genomic kernels further improves accuracy, especially on small datasets. Software, supplementary material, and data are available at the authors’ website and Bioinformatics online.

Abstract

The in silico prediction of potential interactions between drugs and target proteins is of core importance for the identification of new drugs or novel targets for existing drugs. However, only a tiny portion of all drug-target pairs in current datasets are experimentally validated interactions. This motivates the need for developing computational methods that predict true interaction pairs with high accuracy.We show that a simple machine learning method that uses the drug-target network as the only source of information is capable of predicting true interaction pairs with high accuracy. Specifically, we introduce interaction profiles of drugs (and of targets) in a network, which are binary vectors specifying the presence or absence of interaction with every target (drug) in that network. We define a kernel on these profiles, called the Gaussian Interaction Profile (GIP) kernel, and use a simple classifier, (kernel) Regularized Least Squares (RLS), for prediction drug-target interactions. We test comparatively the effectiveness of RLS with the GIP kernel on four drug-target interaction networks used in previous studies. The proposed algorithm achieves area under the precision-recall curve (AUPR) up to 92.7, significantly improving over results of state-of-the-art methods. Moreover, we show that using also kernels based on chemical and genomic information further increases accuracy, with a neat improvement on small datasets. These results substantiate the relevance of the network topology (in the form of interaction profiles) as source of information for predicting drug-target interactions.Software and Supplementary Material are available at http://cs.ru.nl/~tvanlaarhoven/drugtarget2011/[e-mail]; [e-mail] data are available at Bioinformatics online.