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

TL;DR

This paper introduces a novel deep learning method using recurrent graph neural networks to predict drug side-effects directly from molecular graph structures, improving accuracy over existing predictors.

Contribution

It presents a new approach that leverages molecular graph encoding and recurrent GNNs for side-effect prediction, outperforming previous methods.

Findings

Improved classification accuracy across multiple metrics

Effective use of molecular graph structures in side-effect prediction

Developed a new dataset from accessible data sources

Abstract

Predicting drug side-effects before they occur is a key task in keeping the number of drug-related hospitalizations low and to improve 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.