SPARSE: a sparse hypergraph neural network for learning multiple types of latent combinations to accurately predict drug-drug interactions.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: Predicting side effects of drug-drug interactions (DDIs) is an important task in pharmacology. The state-of-the-art methods for DDI prediction use hypergraph neural networks to learn latent representations of drugs and side effects to express high-order relationships among two interacting drugs and a side effect. The idea of these methods is that each side effect is caused by a unique combination of latent features of the corresponding interacting drugs. However, in reality, a side effect might have multiple, different mechanisms that cannot be represented by a single combination of latent features of drugs. Moreover, DDI data are sparse, suggesting that using a sparsity regularization would help to learn better latent representations to improve prediction performances.

Authors

  • Duc Anh Nguyen
    Bioinformatics Center in Kyoto University.
  • Canh Hao Nguyen
    Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, Japan.
  • Peter Petschner
    Bioinformatics Center, Institute of Chemical Research, Kyoto University, Uji, Kyoto, 611 - 0011, Japan. petschner.peter@semmelweis.hu.
  • Hiroshi Mamitsuka
    Bioinformatics Center, Institute of Chemical Research, Kyoto University, Uji, Kyoto, 611 - 0011, Japan.