Login Register Cart 0
Generic placeholder image

Current Bioinformatics

Editor-in-Chief

ISSN (Print): 1574-8936
ISSN (Online): 2212-392X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Drug-target Interaction Prediction By Combining Transformer and Graph Neural Networks

Author(s): Junkai Liu, Yaoyao Lu, Shixuan Guan, Tengsheng Jiang, Yijie Ding, Qiming Fu, Zhiming Cui and Hongjie Wu*

Volume 19, Issue 4, 2024

Published on: 21 September, 2023

Page: [316 - 326] Pages: 11

DOI: 10.2174/1574893618666230912141426

Price: $65

Abstract

Background: The prediction of drug-target interactions (DTIs) plays an essential role in drug discovery. Recently, deep learning methods have been widely applied in DTI prediction. However, most of the existing research does not fully utilize the molecular structures of drug compounds and the sequence structures of proteins, which makes these models unable to obtain precise and effective feature representations.

Methods: In this study, we propose a novel deep learning framework combining transformer and graph neural networks for predicting DTIs. Our model utilizes graph convolutional neural networks to capture the global and local structure information of drugs, and convolutional neural networks are employed to capture the sequence feature of targets. In addition, the obtained drug and protein representations are input to multi-layer transformer encoders, respectively, to integrate their features and generate final representations.

Results: The experiments on benchmark datasets demonstrated that our model outperforms previous graph-based and transformer-based methods, with 1.5% and 1.8% improvement in precision and 0.2% and 1.0% improvement in recall, respectively. The results indicate that the transformer encoders effectively extract feature information of both drug compounds and proteins.

Conclusion: Overall, our proposed method validates the applicability of combining graph neural networks and transformer architecture in drug discovery, and due to the attention mechanisms, it can extract deep structure feature data of drugs and proteins.

« Previous Next »
Graphical Abstract

[1]
Scannell JW, Blanckley A, Boldon H, Warrington B. Diagnosing the decline in pharmaceutical R&D efficiency. Nat Rev Drug Discov 2012; 11(3): 191-200.
[http://dx.doi.org/10.1038/nrd3681] [PMID: 22378269]
[2]
Lin X, Li X, Lin X. A review on applications of computational methods in drug screening and design. Molecules 2020; 25(6): 1375.
[http://dx.doi.org/10.3390/molecules25061375] [PMID: 32197324]
[3]
He Y, Shen Z, Zhang Q, Wang S, Huang DS. A survey on deep learning in DNA/RNA motif mining. Brief Bioinform 2021; 22(4): bbaa229.
[http://dx.doi.org/10.1093/bib/bbaa229] [PMID: 33005921]
[4]
da Silva Rocha SFL, Olanda CG, Fokoue HH, Sant’Anna CMR. Virtual screening techniques in drug discovery: Review and recent applications. Curr Top Med Chem 2019; 19(19): 1751-67.
[http://dx.doi.org/10.2174/1568026619666190816101948] [PMID: 31418662]
[5]
Guo X, Zhou W, Shi B, et al. An efficient multiple kernel support vector regression model for assessing dry weight of hemodialysis patients. Curr Bioinform 2021; 16(2): 284-93.
[http://dx.doi.org/10.2174/1574893615999200614172536]
[6]
Chuai G, Ma H, Yan J, et al. DeepCRISPR: Optimized CRISPR guide RNA design by deep learning. Genome Biol 2018; 19(1): 80.
[http://dx.doi.org/10.1186/s13059-018-1459-4] [PMID: 29945655]
[7]
Chao WANG, Quan ZOU. A machine learning method for differentiating and predicting human‐infective coronavirus based on physicochemical features and composition of the spike protein. Chin J Electron 2021; 30(5): 815-23.
[http://dx.doi.org/10.1049/cje.2021.06.003]
[8]
Zhang F, Song H, Zeng M, et al. A deep learning framework for gene ontology annotations with sequence- and network-based information. IEEE/ACM Trans Comput Biol Bioinformatics 2021; 18(6): 2208-17.
[http://dx.doi.org/10.1109/TCBB.2020.2968882] [PMID: 31985440]
[9]
Wang L, You ZH, Huang YA, Huang DS, Chan KCC. An efficient approach based on multi-sources information to predict circRNA – disease associations using deep convolutional neural network. Bioinformatics 2020; 36(13): 4038-46.
[http://dx.doi.org/10.1093/bioinformatics/btz825] [PMID: 31793982]
[10]
Luo X, Tu X, Ding Y, Gao G, Deng M. Expectation pooling: An effective and interpretable pooling method for predicting DNA–protein binding. Bioinformatics 2020; 36(5): 1405-12.
[http://dx.doi.org/10.1093/bioinformatics/btz768] [PMID: 31598637]
[11]
Kimber TB, Chen Y, Volkamer A. Deep learning in virtual screening: Recent applications and developments. Int J Mol Sci 2021; 22(9): 4435.
[http://dx.doi.org/10.3390/ijms22094435] [PMID: 33922714]
[12]
Liu S, Wang Y, Deng Y, et al. Improved drug–target interaction prediction with intermolecular graph transformer. Brief Bioinform 2022; 23(5): bbac162.
[http://dx.doi.org/10.1093/bib/bbac162] [PMID: 35514186]
[13]
Ding Y, Tang J, Guo F, Zou Q. Identification of drug–target interactions via multiple kernel-based triple collaborative matrix factorization. Brief Bioinform 2022; 23(2): bbab582.
[http://dx.doi.org/10.1093/bib/bbab582] [PMID: 35134117]
[14]
Öztürk H, Özgür A, Ozkirimli E. DeepDTA: Deep drug–target binding affinity prediction. Bioinformatics 2018; 34(17): i821-9.
[http://dx.doi.org/10.1093/bioinformatics/bty593] [PMID: 30423097]
[15]
Ozturk H, Ozkirimli E, Ozgur A. WideDTA: Prediction of drug-target binding affinity arXiv:190204166 2019.
[16]
Lee I, Keum J, Nam H. DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences. PLOS Comput Biol 2019; 15(6): e1007129.
[http://dx.doi.org/10.1371/journal.pcbi.1007129] [PMID: 31199797]
[17]
Zheng S, Li Y, Chen S, Xu J, Yang Y. Predicting drug–protein interaction using quasi-visual question answering system. Nat Mach Intell 2020; 2(2): 134-40.
[http://dx.doi.org/10.1038/s42256-020-0152-y]
[18]
Gao KY, Fokoue A, Luo H, et al. Interpretable drug target prediction using deep neural representation[C]. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Stockholm Sweden. 2018; pp. 3371-7.
[http://dx.doi.org/10.24963/ijcai.2018/468]
[19]
Karimi M, Wu D, Wang Z, Shen Y. Explainable deep relational networks for predicting compound–protein affinities and contacts. J Chem Inf Model 2021; 61(1): 46-66.
[http://dx.doi.org/10.1021/acs.jcim.0c00866] [PMID: 33347301]
[20]
Wang YB, You ZH, Yang S, Yi HC, Chen ZH, Zheng K. A deep learning-based method for drug-target interaction prediction based on long short-term memory neural network. BMC Med Inform Decis Mak 2020; 20(S2) (Suppl. 2): 49.
[http://dx.doi.org/10.1186/s12911-020-1052-0] [PMID: 32183788]
[21]
Mahdaddi A, Meshoul S, Belguidoum M. EA-based hyperparameter optimization of hybrid deep learning models for effective drug-target interactions prediction. Expert Syst Appl 2021; 185: 115525.
[http://dx.doi.org/10.1016/j.eswa.2021.115525]
[22]
Luo X, Ju W, Qu M, et al. CLEAR: Cluster-enhanced contrast for self-supervised graph representation learning. IEEE Trans Neural Netw Learn Syst 2022; PP: 1-14.
[http://dx.doi.org/10.1109/TNNLS.2022.3177775] [PMID: 35675236]
[23]
Ju W, Gu Y, Luo X, et al. Unsupervised graph-level representation learning with hierarchical contrasts. Neural Netw 2023; 158: 359-68.
[http://dx.doi.org/10.1016/j.neunet.2022.11.019] [PMID: 36516542]
[24]
Gu Z, Luo X, Chen J, Deng M, Lai L. Hierarchical graph transformer with contrastive learning for protein function prediction. Bioinformatics 2023; 39(7): btad410.
[http://dx.doi.org/10.1093/bioinformatics/btad410] [PMID: 37369035]
[25]
Xia C, Feng SH, Xia Y, Pan X, Shen HB. Leveraging scaffold information to predict protein–ligand binding affinity with an empirical graph neural network. Brief Bioinform 2023; 24(1): bbac603.
[http://dx.doi.org/10.1093/bib/bbac603] [PMID: 36627113]
[26]
Guo B, Zheng H, Jiang H, et al. Enhanced compound-protein binding affinity prediction by representing protein multimodal information via a coevolutionary strategy. Brief Bioinform 2023; 24(2): bbac628.
[http://dx.doi.org/10.1093/bib/bbac628] [PMID: 36682005]
[27]
Tsubaki M, Tomii K, Sese J. Compound–protein interaction prediction with end-to-end learning of neural networks for graphs and sequences. Bioinformatics 2019; 35(2): 309-18.
[http://dx.doi.org/10.1093/bioinformatics/bty535] [PMID: 29982330]
[28]
Nguyen T, Le H, Quinn TP, Nguyen T, Le TD, Venkatesh S. GraphDTA: Predicting drug–target binding affinity with graph neural networks. Bioinformatics 2021; 37(8): 1140-7.
[http://dx.doi.org/10.1093/bioinformatics/btaa921] [PMID: 33119053]
[29]
Jiang M, Li Z, Zhang S, et al. Drug–target affinity prediction using graph neural network and contact maps. RSC Advances 2020; 10(35): 20701-12.
[http://dx.doi.org/10.1039/D0RA02297G] [PMID: 35517730]
[30]
Yang Z, Zhong W, Zhao L, Yu-Chian Chen C. MGraphDTA: Deep multiscale graph neural network for explainable drug–target binding affinity prediction. Chem Sci (Camb) 2022; 13(3): 816-33.
[http://dx.doi.org/10.1039/D1SC05180F] [PMID: 35173947]
[31]
Zhao Q, Zhao H, Zheng K, Wang J. HyperAttentionDTI: Improving drug–protein interaction prediction by sequence-based deep learning with attention mechanism. Bioinformatics 2022; 38(3): 655-62.
[http://dx.doi.org/10.1093/bioinformatics/btab715] [PMID: 34664614]
[32]
Yazdani-Jahromi M, Yousefi N, Tayebi A, et al. AttentionSiteDTI: An interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification. Brief Bioinform 2022; 23(4): bbac272.
[http://dx.doi.org/10.1093/bib/bbac272] [PMID: 35817396]
[33]
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Adv Neural Inf Process Syst 2017; 2017: 5998-6008.
[http://dx.doi.org/10.5555/3295222.3295349]
[34]
Maziarka U, Danel T, Mucha S, et al. Molecule attention Transformer arXiv:200208264v1 2021.
[35]
Chen L, Tan X, Wang D, et al. TransformerCPI: Improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 2020; 36(16): 4406-14.
[http://dx.doi.org/10.1093/bioinformatics/btaa524] [PMID: 32428219]
[36]
Huang K, Xiao C, Glass LM, Sun J. MolTrans: Molecular Interaction Transformer for drug–target interaction prediction. Bioinformatics 2021; 37(6): 830-6.
[http://dx.doi.org/10.1093/bioinformatics/btaa880] [PMID: 33070179]
[37]
Wang JT, Li X, Zhang H. GNN-PT: Enhanced prediction of compound-protein interactions by integrating protein transformer arXiv:200900805 2020.
[38]
Kalakoti Y, Yadav S, Sundar D. TransDTI: Transformer-based language models for estimating DTIs and building a drug recommendation workflow. ACS Omega 2022; 7(3): 2706-17.
[http://dx.doi.org/10.1021/acsomega.1c05203] [PMID: 35097268]
[39]
Weininger D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci 1988; 28(1): 31-6.
[http://dx.doi.org/10.1021/ci00057a005]
[40]
Bento AP, Hersey A, Félix E, et al. An open source chemical structure curation pipeline using RDKit. J Cheminform 2020; 12(1): 51.
[http://dx.doi.org/10.1186/s13321-020-00456-1] [PMID: 33431044]
[41]
Wu Z, Jiang D, Wang J, Hsieh CY, Cao D, Hou T. Mining toxicity information from large amounts of toxicity data. J Med Chem 2021; 64(10): 6924-36.
[http://dx.doi.org/10.1021/acs.jmedchem.1c00421] [PMID: 33961429]
[42]
Shen C, Zhang X, Deng Y, et al. Boosting protein-ligand binding pose prediction and virtual screening based on residue-atom distance likelihood potential and graph transformer. J Med Chem 2022; 65(15): 10691-706.
[http://dx.doi.org/10.1021/acs.jmedchem.2c00991] [PMID: 35917397]
[43]
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(16): 8993.
[http://dx.doi.org/10.3390/ijms22168993] [PMID: 34445696]
[44]
Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv:160902907 2016.
[45]
Li M, Lu Z, Wu Y, Li Y. BACPI: A bi-directional attention neural network for compound–protein interaction and binding affinity prediction. Bioinformatics 2022; 38(7): 1995-2002.
[http://dx.doi.org/10.1093/bioinformatics/btac035] [PMID: 35043942]
[46]
Liu H, Sun J, Guan J, Zheng J, Zhou S. Improving compound–protein interaction prediction by building up highly credible negative samples. Bioinformatics 2015; 31(12): i221-9.
[http://dx.doi.org/10.1093/bioinformatics/btv256] [PMID: 26072486]
[47]
Wishart DS, Knox C, Guo AC, et al. DrugBank: A knowledgebase for drugs, drug actions and drug targets. Nucleic Acids Res 2008; 36(Database issue) (Suppl. 1): D901-6.
[http://dx.doi.org/10.1093/nar/gkm958] [PMID: 18048412]
[48]
Günther S, Kuhn M, Dunkel M, et al. SuperTarget and Matador: Resources for exploring drug-target relationships. Nucleic Acids Res 2007; 36(Database): D919-22.
[http://dx.doi.org/10.1093/nar/gkm862] [PMID: 17942422]
[49]
Kuhn M, Szklarczyk D, Pletscher-Frankild S, et al. STITCH 4: Integration of protein–chemical interactions with user data. Nucleic Acids Res 2014; 42(D1): D401-7.
[http://dx.doi.org/10.1093/nar/gkt1207] [PMID: 24293645]
[50]
Wu Q, Peng Z, Anishchenko I, Cong Q, Baker D, Yang J. Protein contact prediction using metagenome sequence data and residual neural networks. Bioinformatics 2020; 36(1): 41-8.
[http://dx.doi.org/10.1093/bioinformatics/btz477] [PMID: 31173061]
[51]
Kingma D, Ba J. Adam: A method for stochastic optimization. arXiv:14126980 2014.
[52]
Li P, Li Y, Hsieh CY, et al. TrimNet: Learning molecular representation from triplet messages for biomedicine. Brief Bioinform 2021; 22(4): bbaa266.
[http://dx.doi.org/10.1093/bib/bbaa266] [PMID: 33147620]

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy