Protein–ligand binding affinity prediction with edge awareness and supervised attention
Yuliang Gu,
Xiangzhou Zhang,
Anqi Xu,
Weiqi Chen,
Kang Liu,
Lijuan Wu,
Shenglong Mo,
Yong Hu,
Mei Liu,
Qichao Luo
Affiliations
Yuliang Gu
Department of Pharmacology, School of Basic Medicine, Anhui Medical University, Hefei, Anhui 230022, China; Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China
Xiangzhou Zhang
Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China; Faculty of Medical Science, Jinan University, Guangzhou, Guangdong 510632, China
Anqi Xu
Department of Pharmacology, School of Basic Medicine, Anhui Medical University, Hefei, Anhui 230022, China; Research Center for Neurological disorders , School of Basic Medicine, Anhui Medical University, Hefei, Anhui 230022, China
Weiqi Chen
Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China; Faculty of Medical Science, Jinan University, Guangzhou, Guangdong 510632, China
Kang Liu
Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China
Lijuan Wu
Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China
Shenglong Mo
Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China
Yong Hu
Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China; Faculty of Medical Science, Jinan University, Guangzhou, Guangdong 510632, China; Corresponding author
Mei Liu
Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL 32610, USA; Corresponding author
Qichao Luo
Department of Pharmacology, School of Basic Medicine, Anhui Medical University, Hefei, Anhui 230022, China; Big Data Decision Institute, Jinan University, Guangzhou, Guangdong 510632, China; Research Center for Neurological disorders , School of Basic Medicine, Anhui Medical University, Hefei, Anhui 230022, China; Corresponding author
Summary: Accurate prediction of protein–ligand binding affinity is crucial in structure-based drug design but remains some challenges even with recent advances in deep learning: (1) Existing methods neglect the edge information in protein and ligand structure data; (2) current attention mechanisms struggle to capture true binding interactions in the small dataset. Herein, we proposed SEGSA_DTA, a SuperEdge Graph convolution-based and Supervised Attention-based Drug–Target Affinity prediction method, where the super edge graph convolution can comprehensively utilize node and edge information and the multi-supervised attention module can efficiently learn the attention distribution consistent with real protein-ligand interactions. Results on the multiple datasets show that SEGSA_DTA outperforms current state-of-the-art methods. We also applied SEGSA_DTA in repurposing FDA-approved drugs to identify potential coronavirus disease 2019 (COVID-19) treatments. Besides, by using SHapley Additive exPlanations (SHAP), we found that SEGSA_DTA is interpretable and further provides a new quantitative analytical solution for structure-based lead optimization.
