A review of methodologies in detecting drug-drug interactions
Jizhou Tian · AIP conference proceedings · 2022
Drug-drug interactions (DDIs) are a leading cause of adverse drug reactions. It is a critical process to identify DDIs in drug administration. Compared to biomedical experiments, there exists urgent demand to predict DDIs through computational approaches. In this review, both traditional and advanced DDI prediction methodologies are discussed. Classical approaches based on frequency and Bayes are illustrated. Studies on the latest statistical techniques such as machine learning, network and deep learning for the DDI prediction are elaborated. On account of superiorities and limitations in current models, we also prospect the future development of computational approaches. This review shall provide a whole picture of innovation in DDI prediction methodologies and facilitate drug interaction research.