Dual graph convolutional neural network for predicting chemical networks.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Predicting of chemical compounds is one of the fundamental tasks in bioinformatics and chemoinformatics, because it contributes to various applications in metabolic engineering and drug discovery. The recent rapid growth of the amount of available data has enabled applications of computational approaches such as statistical modeling and machine learning method. Both a set of chemical interactions and chemical compound structures are represented as graphs, and various graph-based approaches including graph convolutional neural networks have been successfully applied to chemical network prediction. However, there was no efficient method that can consider the two different types of graphs in an end-to-end manner.

Authors

  • Shonosuke Harada
    Kyoto University, Kyoto, 6068501, Japan. sh1108@ml.ist.i.kyoto-u.ac.jp.
  • Hirotaka Akita
    Preferred Networks, Tokyo, 1000004, Japan.
  • Masashi Tsubaki
    National Institute of Advanced Industrial Science and Technology, Artificial Intelligence Research Center, Tokyo, Japan.
  • Yukino Baba
    Graduate School of Informatics, Kyoto University.
  • Ichigaku Takigawa
    Hokkaido University, Hokkaido, 0600808, Japan.
  • Yoshihiro Yamanishi
    Division of System Cohort, Multi-Scale Research Center for Medical Science, Medical Institute of Bioregulation, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka, Fukuoka, 812-8582, Japan. yamanishi@bioreg.kyushu-u.ac.jp.
  • Hisashi Kashima
    Graduate School of Informatics, Kyoto University.