BridgeDPI: a novel Graph Neural Network for predicting drug-protein interactions.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: Exploring drug-protein interactions (DPIs) provides a rapid and precise approach to assist in laboratory experiments for discovering new drugs. Network-based methods usually utilize a drug-protein association network and predict DPIs by the information of its associated proteins or drugs, called 'guilt-by-association' principle. However, the 'guilt-by-association' principle is not always true because sometimes similar proteins cannot interact with similar drugs. Recently, learning-based methods learn molecule properties underlying DPIs by utilizing existing databases of characterized interactions but neglect the network-level information.

Authors

  • Yifan Wu
    Department of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, China.
  • Min Gao
    Department of Biliary Surgery, West China Hospital of Sichuan University, Chengdu, China.
  • Min Zeng
    Nephrology Department, Affiliated Hospital of Southern Medical University: Shenzhen Longhua New District People's Hospital, Shenzhen, China.
  • Jie Zhang
    College of Physical Education and Health, Linyi University, Linyi, Shandong, China.
  • Min Li
    Hubei Provincial Institute for Food Supervision and Test, Hubei Provincial Engineering and Technology Research Center for Food Quality and Safety Test, Wuhan 430075, China.