A Deep Learning Approach to the Prediction of Drug Side–Effects on Molecular Graphs

Predicting drug side effects before they occur is a critical task for keeping the number of drug–related hospitalizations low and for improving drug discovery processes. Automatic predictors of side–effects generally are not able to process the structure of the drug, resulting in a loss of information. Graph neural networks have seen great success in recent years, thanks to their ability of exploiting the information conveyed by the graph structure and labels. These models have been used in a wide variety of biological applications, among which the prediction of drug side–effects on a large knowledge graph. Exploiting the molecular graph encoding the structure of the drug represents a novel approach, in which the problem is formulated as a multi–class multi–label graph–focused classification. We developed a methodology to carry out this task, using recurrent Graph Neural Networks, and building a dataset from freely accessible and well established data sources. The results show that our method has an improved classification capability, under many parameters and metrics, with respect to previously available predictors. The method is not ready for clinical tests yet, as the specificity is still below the preliminary 25% threshold. Future efforts will aim at improving this aspect.

I. Introduction

Drug discovery is a fundamental but expensive process to make new pharmacological products available for healthcare [1]. Detecting and identifying Drug Side–Effects (DSEs) is mandatory to ensure that only safe drugs enter the market. DSEs have high costs for public health [2], and cause a significant number of hospitalizations every year [3], a constantly increasing trend, also due to the growing use of prescription drugs [4]. Predicting DSEs automatically in silico, before submitting drug candidates to clinical trials, would represent a fundamental improvement for drug discovery processes, cutting their costs in terms of time and money [5].