MultiGML: Multimodal Graph Machine Learning for Prediction of Adverse Drug Events

Abstract

SummaryAdverse drug events constitute a major challenge for the success of clinical trials. Several computational strategies have been suggested to estimate the risk of adverse drug events in preclinical drug development. While these approaches have demonstrated high utility in practice, they are at the same time limited to specific information sources and thus neglect a wealth of information that is uncovered by fusion of different data sources, including biological protein function, gene expression, chemical compound structure, cell-based imaging, etc. In this work we propose an integrative and explainable Graph Machine Learning approach (MultiGML), which fuses knowledge graphs with multiple further data modalities to predict drug related adverse events. MultiGML demonstrates excellent prediction performance compared to alternative algorithms, including various knowledge graph embedding techniques. MultiGML distinguishes itself from alternative techniques by providing in-depth explanations of model predictions, which point towards biological mechanisms associated with predictions of an adverse drug event.MotivationAdverse drug events are a major risk for failure of late-stage clinical trials. Attempts to prevent adverse drug events in preclinical drug development include experimental procedures for measuring liver-toxicity, cardio-toxicity, etc. Yet these procedures are costly and cannot fully guarantee success in later clinical studies, specifically in situations without a reliable animal model. Computational approaches developed for adverse event prediction have shown to be valuable, but are mostly limited to single data sources. Our approach successfully integrates various data sources on protein functions, gene expression, chemical compound structures and more, into the prediction of adverse events. A main distinguishing characteristic is the explainability of our model predictions which allow further insight into biological mechanisms.