HDN-DDI: a novel framework for predicting drug-drug interactions using hierarchical molecular graphs and enhanced dual-view representation learning.

Journal: BMC bioinformatics
PMID:

Abstract

BACKGROUND: Drug-drug interactions (DDIs) especially antagonistic ones present significant risks to patient safety, underscoring the urgent need for reliable prediction methods. Recently, substructure-based DDI prediction has garnered much attention due to the dominant influence of functional groups and substructures on drug properties. However, existing approaches face challenges regarding the insufficient interpretability of identified substructures and the isolation of chemical substructures.

Authors

  • Jinchen Sun
    School of Computer Science and Technology, University of Science and Technology of China, 443 Huangshan Road, Hefei, 230027, China.
  • Haoran Zheng
    School of Computer Science and Technology, University of Science and Technology of China, Huangshan Road, Hefei, 230026, People's Republic of China. zhulx@mail.ustc.edu.cn.