An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph

  • Wan, Xiaozhe
  • Wu, Xiaolong
  • Wang, Dingyan
  • Tan, Xiaoqin
  • Liu, Xiaohong
  • Fu, Zunyun
  • Jiang, Hualiang
  • Zheng, Mingyue
  • Li, Xutong

  • 1State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No.19A Yuquan Road, Beijing 100049, China

    2State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China

    4ByteDance AI Lab, Shanghai 201103, China

    5AlphaMa Inc., No. 108, Yuxin Road, Suzhou Industrial Park, Suzhou 215128, China

    6State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China

    7State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China; School of Life Science and Technology, ShanghaiTech University, 393 Huaxiazhong Road, Shanghai 200031, China

    8State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China

*Corresponding authors: Xutong Li, State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China. Tel: +86-13821547729; E-mail: [email protected]; Mingyue Zheng, State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China. Tel: +86-21-50807188; E-mail: [email protected]

Received: December 3, 2021. Revised: February 9, 2022. Accepted: February 11, 2022

Xiaozhe Wan is a PhD student at Shanghai Institute of Materia Medica. Her research interest is artificial intelligence-assisted drug design. Her affiliation is State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No.19A Yuquan Road, Beijing 100049, China.

Xiaolong Wu is a PhD student at Shanghai Institute of Materia Medica. His research interests are artificial intelligence-assisted drug design and bioinformatics. His affiliation is State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China.

Dingyan Wang is a PhD student at Shanghai Institute of Materia Medica. His research interest is artificial intelligence-assisted drug design. His affiliation is State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No.19A Yuquan Road, Beijing 100049, China.

Xiaoqin Tan got her PhD degree at Shanghai Institute of Materia Medica in 2021. Her research interest is artificial intelligence-assisted drug design. Her affiliation is ByteDance AI Lab, Shanghai 201103, China.

Xiaohong Liu got his PhD degree at Shanghai Institute of Materia Medica in 2021. His research interest is artificial intelligence-assisted drug design. His affiliation is AlphaMa Inc., No. 108, Yuxin Road, Suzhou Industrial Park, Suzhou 215128, China.

Zunyun Fu is a PhD student at Shanghai Institute of Materia Medica. Her research interests are artificial intelligence-assisted drug design and quantum calculation. Her affiliation is State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China.

Hualiang Jiang is an academician medicinal scientist of the Chinese Academy of Sciences. His research interests are artificial intelligence-assisted drug design, computational chemistry, computational biology and pharmaceutical chemistry. His affiliation is State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China; School of Life Science and Technology, ShanghaiTech University, 393 Huaxiazhong Road, Shanghai 200031, China.

Mingyue Zheng is a professor at Shanghai Institute of Materia Medica. His research interests are artificial intelligence-assisted drug design, computational chemistry and computational biology. His affiliation is State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China.

Xutong Li is a postdoctoral researcher at Shanghai Institute of Materia Medica. Her research interest is artificial intelligence-assisted drug design. Her affiliation is State Key Laboratory of Drug Research, Drug Discovery and Design Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China; University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China.

Briefings in Bioinformatics 23(3):p bbac073, May 2022. | DOI: 10.1093/bib/bbac073

Abstract

Identifying the potential compound-protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most of the network-based methods use heterogeneous graphs, which is challenging due to their complex structures and heterogeneous attributes. Therefore, in this work, we transformed the compound-protein heterogeneous graph to a homogeneous graph by integrating the ligand-based protein representations and overall similarity associations. We then proposed an Inductive Graph AggrEgator-based framework, named CPI-IGAE, for CPI prediction. CPI-IGAE learns the low-dimensional representations of compounds and proteins from the homogeneous graph in an end-to-end manner. The results show that CPI-IGAE performs better than some state-of-the-art methods. Further ablation study and visualization of embeddings reveal the advantages of the model architecture and its role in feature extraction, and some of the top ranked CPIs by CPI-IGAE have been validated by a review of recent literature. The data and source codes are available at https://github.com/wanxiaozhe/CPI-IGAE.

Copyright © Copyright Oxford University Press 2022.