计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (6A): 250800090-7.doi: 10.11896/jsjkx.250800090

• 人工智能 • 上一篇    下一篇

基于双线性注意力网络的药物靶标相互作用预测

卢碧瑶, 徐悠然, 刘莹, 刘锦东, 刘建, 殷文斐, 姜烨   

  1. 合肥工业大学计算机与信息学院 合肥 230009
  • 出版日期:2026-06-16 发布日期:2026-06-12
  • 通讯作者: 刘建(Jianliu@hfut.edu.cn)
  • 作者简介:(hsxdghht@gmail.com)
  • 基金资助:
    安徽省自然科学基金(JZ2025AKZR0608,2508085MF153,2308085QF227);合肥市自然科学基金(HZR2403,JZ2024HKZR0706, W2024JSKF0762);安徽省优秀青年教师培养项目一般项目(YQYB2024096)

Bilinear Attention Network-based Drug-target Interaction Prediction

LU Biyao, XU Youran, LIU Ying, LIU Jindong, LIU Jian, YIN Wenfei, JIANG Ye   

  1. School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230009,China
  • Published:2026-06-16 Online:2026-06-12
  • About author:LU Biyao,born in 2005,bachelor's degree.Her main research interests include machine learning and smart healthcare.
    LIU Jian,born in 1986,Ph.D,associate professor,is a member of CCF(No.P2636M).His main research interests include interpretable machine learning and wise medical.
  • Supported by:
    Anhui Provincial Natural Science Foundation(JZ2025AKZR0608,2508085MF153,2308085QF227),Hefei Natural Science Foundation(HZR2403,JZ2024HKZR0706,W2024JSKF0762) and General Project of the Anhui Provincial Excellent Young Teachers Training Program(YQYB2024096).

PDF (PC)

39

摘要： 药物靶标相互作用(Drug-Target Interaction,DTI)预测是新药研发过程中的核心环节,近年来将其与深度学习结合成为药物发现领域的一个重要发展方向。然而,现有方法在处理药物分子与蛋白靶标的空间结构信息、特征融合策略以及计算复杂度等方面仍存在诸多亟待解决的问题。为应对这些挑战,文中提出了一种基于双线性注意力网络的模型,用于精准预测药物与靶标之间的相互作用。该模型通过多层图注意力网络生成药物分子的特征表示,利用多层卷积神经网络结合SE模块生成蛋白质靶标的特征表示。随后,借助多头注意力机制的双线性注意力网络融合这两种特征表示,并通过块项张量分解模块有效减少模型参数量,从而获得更优的预测性能。在两个公开数据集BindingDB和BioSNAP上进行了实验,所提出的BAN_DTI模型在AUROC,AUPRC,Specifity,Accuracy,Sensitivity 5项评估指标上的表现显著超越了对比的SOTA方法。

关键词: 药物靶标相互作用, 双线性注意力网络, 图注意力网络, 卷积神经网络

Abstract: Drug-target interaction(DTI) prediction is a core component in the process of new drug development.In recent years,the integration of DTI prediction with deep learning has emerged as an important direction in the field of drug discovery.How-ever,existing methods still face numerous challenges in handling the three-dimensional spatial structural information of drug molecules and protein targets,feature fusion strategies,and computational complexity.To address these challenges,a model based on the bilinear attention network is proposed to accurately predict the interactions between drugs and targets.The model generates feature representations of drug molecules using a multi-layer graph attention network and creates feature representations of protein targets using a multi-layer convolutional neural network combined with an SE module.Subsequently,the bilinear attention network with multi-head attention mechanism fuses these two types of feature representations and effectively reduces the model parameter quantity through a block tensor decomposition module,thereby achieving superior predictive performance.Experiments are conducted on two public datasets,BindingDB and BioSNAP,and the proposed BAN_DTI model significantly outperforms the compared state-of-the-art methods in five evaluation metrics:AUROC,AUPRC,Specificity,Accuracy,and Sensitivity.

Key words: Drug-target interaction, Bilinear attention network, Graph attention network, Convolutionalneural network

中图分类号: 

  • TP391
[1] LUO Y,ZHAO B,ZHOU T,et al.A network integrationapproach for drug-target interaction prediction and computationaldrug repositioning from heterogeneous information [J].Nature Communications,2017,8(573):1-13.
[2] ZITNIK M,NGUYEN F,WANG B,et al.Machine learning for integrating data in biology and medicine:principles practice and opportunities [J].Information Fusion,2019,50(C):71-91.
[3] ÖZTÜRK H,ÖZGÜR A,OZKIRIMLI E.Deep drug-targetbinding affinity prediction[J].Bioinformatics,2018,34(17):i821-i829.
[4] DING Y J,TANG J J,GUO F,et al.Identification of drug-target interactions via multiple kernel-based triple collaborative matrix factorization[J].Briefings in Bioinformatics,2021,22(6):bbab582.
[5] CHEN R L,XIA F,HU B,et al.Drug-target interactions prediction via deep collaborative filtering with multiembeddings[J].Briefingsin Bioinformatics,2022,23(1):bbab550.
[6] SHAO K,ZHANG Z,HE S,et al.DTIGCCN:prediction ofdrug-target interactions based on GCN and CNN[C]//2020 IEEE 32nd International Conference on Tools with Artificial Intelligence(ICTAI).Baltimore,MD,USA:IEEE,2020:337-342.
[7] KIPF T N,WELLING M.Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations.Toulon,France:ICLR,2017.
[8] ZHAO B W,SU X R,HU P W,et al.iGRLDTI:an improved graph representation learning method for predicting drug-target interactions over heterogeneous biological information network[J].Bioinformatics,2023,39(8):btad451.
[9] YANG Y,SU X,ZHAO B,et al.Fuzzy-based deep attributed graph clustering[J].IEEE Transactions on Fuzzy Systems,2024,32(4):1951-1964.
[10] LEE I,KEUM J,NAM H.DeepConv-DTI:prediction of drug-target interactions via deep learning with convolution on protein sequences[J].PLoS Computational Biology,2019,15(6):e1007129.
[11] HARSHMAN R A,LADEFOGED P,REICHENBACH H,et al.Foundations of the parafac procedure:Models and conditions for an “explanatory” multimodal factor analysis[J].UCLA Working Papers in Phonetics,2001(1):1-84.
[12] VELICˇKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[C]//Proceedings of the 6th International Conference on Learning Representations.Vancouver Canada,ICLR,2018.
[13] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[14] HU J,SHEN L,SUN G.Squeeze-and-Excitation Networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:7132-7141.
[15] KIM J H,JUN J,ZHANG B T.Bilinearattention networks[C]//Advances in Neural Information Processing Systems 31(NeurIPS 2018).Montréal,Canada:NeurIPS,2018:1564-1574.
[16] BEN-YOUNES H,CADENE R,THOME N,et al.BLOCK:Bilinear superdiagonal fusion for visualquestion answering and visual relationship detection[C]//Proceedings of the 15th European Conference on Computer Vision(ECCV 2018).Munich,Germany:Springer,2018:822-838.
[17] TSUBAKI M,TOMII K,SESE J.Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences[J].Bioinformatics,2019,35(2):309-318.
[18] HUANG K,XIAO C,GLASS L,et al.MolTrans:molecular interaction transformer for drug-target interaction prediction[J].Bioinformatics,2021,37(6):830-836.
[19] LI M,ZHOU J,HU J,et al.DGL-LifeSci:An open-source toolkit for deep learning on graphs in life science[J].ACS Omega,2021,6(41):27233-27238.
[20] RAMSUNDAR B,EASTMAN P,WALTERS P,et al.Deeplearning for the life sciences:Applying deep learning to genomics,microscopy,drug discovery,and more[M]//Sebastopol,CA:O'Reilly Media,2019:63-76.
[21] GILSON M K,LIU T,BAITALUK M,et al.BindingDB in2015:a public database for medicinal chemistry,computational chemistry and systems pharmacology[J].Nucleic Acids Research,2016,44(D1):D1045-D1053.
[22] BAI P,ZHANG Y,ZHOU X,et al.Hierarchical clustering split for low-bias evaluation of drug-target interaction prediction[C]//2021 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).Houston,TX,USA:IEEE,2021:641-644.
[23] WISHART D S,KNOX C,GUO A C,et al.DrugBank:a knowledgebase for drugs,drug actions and drug targets[J].Nucleic Acids Research,2008,36(Database issue):D901-D906.
[24] PASZKE A,GROSS S,MASSA F,et al.PyTorch:An imperative style,high-performance deeplearning library[C]//Advances in Neural Information Processing Systems 32(NeurIPS 2019).Vancouver,Canada:NeurIPS,2019:8024-8035.
[25] KINGMA D P,BA J.Adam:A method for stochastic optimization[EB/OL].(2014-12-22) [2023-04-12] .https://arxiv.org/abs/1412.6980.
[26] CORTES C,VAPNIK V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[27] HO T K.Random decision forests[C]//Proceedings of the 3rd International Conference on Document Analysis and Recognition.Montreal,Canada:IEEE,1995,1:278-282.
[28] NGUYEN T,LE H,QUINN T P,et al.GraphDTA:predicting drug-target binding affinity with graph neural networks[J].Bioinformatics,2021,37(8):1140-1147
[29] HUANG K,XIAO C,GLASS L,et al.MolTrans:molecular in-teraction transformer for drug-target interaction prediction[J].Bioinformatics,2021,37(3):830-836.
[30] BAI P Z,MILJKOVIĆ F,JOHN B,et al.Interpretable bilinear attention network with domain adaptation improves drug-target prediction[J].Nature Machine Intelligence,2023,5(2):149-157.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发