SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network

Zhang, Shugang; Jiang, Mingjian; Wang, Shuang; Wang, Xiaofeng; Wei, Zhiqiang; Li, Zhen

doi:10.3390/ijms22168993

Open AccessArticle

SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network

by

Shugang Zhang

¹,

Mingjian Jiang

²,

Shuang Wang

³,

Xiaofeng Wang

⁴,

Zhiqiang Wei

¹ and

Zhen Li

^5,*

¹

College of Computer Science and Technology, Ocean University of China, Qingdao 266100, China

²

School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266033, China

³

College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China

⁴

MindRank AI Ltd., Hangzhou 311113, China

⁵

College of Computer Science and Technology, Qingdao University, Qingdao 266071, China

^*

Author to whom correspondence should be addressed.

Int. J. Mol. Sci. 2021, 22(16), 8993; https://doi.org/10.3390/ijms22168993

Submission received: 7 July 2021 / Revised: 14 August 2021 / Accepted: 17 August 2021 / Published: 20 August 2021

(This article belongs to the Section Molecular Informatics)

Download

Browse Figures

Versions Notes

Abstract

The prediction of drug–target affinity (DTA) is a crucial step for drug screening and discovery. In this study, a new graph-based prediction model named SAG-DTA (self-attention graph drug–target affinity) was implemented. Unlike previous graph-based methods, the proposed model utilized self-attention mechanisms on the drug molecular graph to obtain effective representations of drugs for DTA prediction. Features of each atom node in the molecular graph were weighted using an attention score before being aggregated as molecule representation. Various self-attention scoring methods were compared in this study. In addition, two pooing architectures, namely, global and hierarchical architectures, were presented and evaluated on benchmark datasets. Results of comparative experiments on both regression and binary classification tasks showed that SAG-DTA was superior to previous sequence-based or other graph-based methods and exhibited good generalization ability.

Keywords: drug–target affinity; graph neural network; self-attention

Share and Cite

MDPI and ACS Style

Zhang, S.; Jiang, M.; Wang, S.; Wang, X.; Wei, Z.; Li, Z. SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network. Int. J. Mol. Sci. 2021, 22, 8993. https://doi.org/10.3390/ijms22168993

AMA Style

Zhang S, Jiang M, Wang S, Wang X, Wei Z, Li Z. SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network. International Journal of Molecular Sciences. 2021; 22(16):8993. https://doi.org/10.3390/ijms22168993

Chicago/Turabian Style

Zhang, Shugang, Mingjian Jiang, Shuang Wang, Xiaofeng Wang, Zhiqiang Wei, and Zhen Li. 2021. "SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network" International Journal of Molecular Sciences 22, no. 16: 8993. https://doi.org/10.3390/ijms22168993

APA Style

Zhang, S., Jiang, M., Wang, S., Wang, X., Wei, Z., & Li, Z. (2021). SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network. International Journal of Molecular Sciences, 22(16), 8993. https://doi.org/10.3390/ijms22168993

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI