APRILE: Exploring the Molecular Mechanisms of Drug Side Effects with Explainable Graph Neural Networks

Abstract

The majority of people over the age of 65 take two or more medications. While many individual drug side effects are known, polypharmacy side effects due to novel drug combinations poses great risk. Here, we present APRILE: an explainable artificial intelligence (XAI) framework that uses graph neural networks to explore the molecular mechanisms underlying polypharmacy side effects. Given a list of side effects and the pairs of drugs causing them, APRILE identifies a set of proteins (drug targets or non-targets) and associated Gene Ontology (GO) terms as mechanistic explanations of associated side effects. Using APRILE, we generate such explanations for 843,318 (learned) and 93,966 (novel) side effect-drug pair events, spanning 861 side effects (472 diseases, 485 symptoms and 9 mental disorders) and 20 disease cate-gories. We show that our two new metrics--pharmacogenomic information utilization and protein-protein interaction information utilization--provide quantitative estimates of mechanism complexity. Explanations were significantly consistent with state of the art disease-gene associations for 232/239 (97%) side effects. Further, APRILE generated new insights into molecular mechanisms of four diverse categories of adverse drug reactions: infection, metabolic diseases, gastrointestinal diseases, and mental disorders, including paradoxical side effects. We demonstrate the viability of discovering polypharmacy side effect mechanisms by training an XAI framework on massive biomedical data. Consequently, it facilitates wider and more reliable use of AI in healthcare.