SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction

被引:14
|
作者
Zhang, Shuke [1 ,2 ]
Jin, Yanzhao [1 ,2 ]
Liu, Tianmeng [1 ,2 ]
Wang, Qi [1 ,2 ]
Zhang, Zhaohui [1 ,3 ]
Zhao, Shuliang [3 ,4 ,5 ]
Shan, Bo [1 ,2 ]
机构
[1] Hebei Normal Univ, Software Coll, Shijiazhuang 050024, Peoples R China
[2] Shijiazhuang Xianyu Digital Biotechnol Co Ltd, Shijiazhuang 050024, Peoples R China
[3] Hebei Normal Univ, Coll Comp & Cyber Secur, Shijiazhuang 050024, Peoples R China
[4] Hebei Prov Key Lab Network & Informat Secur, Shijiazhuang 050024, Peoples R China
[5] Hebei Prov Engn Res Ctr Supply Chain Big Data Anal, Shijiazhuang 050024, Peoples R China
来源
ACS OMEGA | 2023年 / 8卷 / 25期
关键词
TARGET INTERACTION PREDICTION; PROTEIN-LIGAND COMPLEXES; SCORING FUNCTION; BINDING AFFINITIES; PDBBIND DATABASE;
D O I
10.1021/acsomega.3c00085
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Efficient and effective drug-target binding affinity (DTBA) prediction is a challenging task due to the limited computational resources in practical applications and is a crucial basis for drug screening. Inspired by the good representation ability of graph neural networks (GNNs), we propose a simple-structured GNN model named SS-GNN to accurately predict DTBA. By constructing a single undirected graph based on a distance threshold to represent protein-ligand interactions, the scale of the graph data is greatly reduced. Moreover, ignoring covalent bonds in the protein further reduces the computational cost of the model. The graph neural network-multilayer perceptron (GNN-MLP) module takes the latent feature extraction of atoms and edges in the graph as two mutually independent processes. We also develop an edge-based atom-pair feature aggregation method to represent complex interactions and a graph pooling-based method to predict the binding affinity of the complex. We achieve state-of-the-art prediction performance using a simple model (with only 0.6 M parameters) without introducing complicated geometric feature descriptions. SS-GNN achieves Pearson's R ( p ) = 0.853 on the PDBbind v2016 core set, outperforming state-of-the-art GNN-based methods by 5.2%. Moreover, the simplified model structure and concise data processing procedure improve the prediction efficiency of the model. For a typical protein-ligand complex, affinity prediction takes only 0.2 ms. All codes are freely accessible at https://github.com/xianyuco/SS-GNN.
引用
收藏
页码:22496 / 22507
页数:12
相关论文
共 50 条
  • [11] MAST-GNN: A multimodal adaptive spatio-temporal graph neural network for airspace complexity prediction
    Li, Biyue
    Li, Zhishuai
    Chen, Jun
    Yan, Yongjie
    Lv, Yisheng
    Du, Wenbo
    TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2024, 160
  • [12] QTIAH-GNN: Quantity and Topology Imbalance-aware Heterogeneous Graph Neural Network for Bankruptcy Prediction
    Liu, Yucheng
    Gao, Zipeng
    Liu, Xiangyang
    Luo, Pengfei
    Yang, Yang
    Xiong, Hui
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 1572 - 1582
  • [13] Drug-target affinity prediction using graph neural network and contact maps
    Jiang, Mingjian
    Li, Zhen
    Zhang, Shugang
    Wang, Shuang
    Wang, Xiaofeng
    Yuan, Qing
    Wei, Zhiqiang
    RSC ADVANCES, 2020, 10 (35) : 20701 - 20712
  • [14] Equivariant Line Graph Neural Network for Protein-Ligand Binding Affinity Prediction
    Yi, Yiqiang
    Wan, Xu
    Zhao, Kangfei
    Le, Ou-Yang
    Zhao, Peilin
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (07) : 4336 - 4347
  • [15] GraphscoreDTA: optimized graph neural network for protein-ligand binding affinity prediction
    Wang, Kaili
    Zhou, Renyi
    Tang, Jing
    Li, Min
    BIOINFORMATICS, 2023, 39 (06)
  • [16] OOD-GNN: Out-of-Distribution Generalized Graph Neural Network
    Li, Haoyang
    Wang, Xin
    Zhang, Ziwei
    Zhu, Wenwu
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (07) : 7328 - 7340
  • [17] Performance Analysis of Graph Neural Network (GNN) for Manufacturing Feature Recognition Problem
    Betkier, Igor
    Oszczypala, Mateusz
    Pobozniak, Janusz
    Sobieski, Sergiusz
    2023 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE, HPEC, 2023,
  • [18] API-GNN: attribute preserving oriented interactive graph neural network
    Zhou, Yuchen
    Shang, Yanmin
    Cao, Yanan
    Li, Qian
    Zhou, Chuan
    Xu, Guandong
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2022, 25 (01): : 239 - 258
  • [19] API-GNN: attribute preserving oriented interactive graph neural network
    Yuchen Zhou
    Yanmin Shang
    Yanan Cao
    Qian Li
    Chuan Zhou
    Guandong Xu
    World Wide Web, 2022, 25 : 239 - 258
  • [20] Ha-gnn: a novel graph neural network based on hyperbolic attention
    Qu H.
    Song Y.-R.
    Zhang M.
    Jiang G.-P.
    Li R.
    Song B.
    Neural Computing and Applications, 2024, 36 (20) : 12427 - 12442