Abstract
Pregnane X receptor (PXR) is an important nuclear receptor that regulates diverse physiological functions, including drug metabolism. Although PXR activation is potentially involved in adverse events, the full scope of its impact has yet to be elucidated. In this study, we developed a machine learning model to predict the activity of PXR agonists and applied the model to drugs listed in the US Food and Drug Administration Adverse Event Reporting System database. Analysis of the predicted agonist-active drug interactions and adverse event reports revealed statistically significant risks (lnROR > 1 and -logp > 1.3) for multiple cardiac disorders. These findings suggest that PXR activity is involved in cardiovascular adverse effects and may contribute to drug safety through the early identification of risks.