Transformer and Graph Transformer-Based Prediction of Drug-Target Interactions


Cite item

Full Text

Abstract

Background:As we all know, finding new pharmaceuticals requires a lot of time and money, which has compelled people to think about adopting more effective approaches to locate drugs. Researchers have made significant progress recently when it comes to using Deep Learning (DL) to create DTI

Methods:Therefore, we propose a deep learning model that applies Transformer to DTI prediction. The model uses a Transformer and Graph Transformer to extract the feature information of protein and compound molecules, respectively, and combines their respective representations to predict interactions.

Results:We used Human and C.elegans, the two benchmark datasets, evaluated the proposed method in different experimental settings and compared it with the latest DL model.

Conclusion:The results show that the proposed model based on DL is an effective method for the classification and recognition of DTI prediction, and its performance on the two data sets is significantly better than other DL based methods.

About the authors

Meiling Qian

School of Electronic and Information Engineering, Suzhou University of Science and Technology

Author for correspondence.
Email: info@benthamscience.net

Weizhong Lu

School of Electronic and Information Engineering,, Suzhou University of Science and Technology

Author for correspondence.
Email: info@benthamscience.net

Yu Zhang

, Suzhou Industrial Park Institute of Services Outsourcing

Email: info@benthamscience.net

Junkai Liu

School of Electronic and Information Engineering, Suzhou University of Science and Technology

Email: info@benthamscience.net

Hongjie Wu

School of Electronic and Information Engineering, Suzhou University of Science and Technology

Email: info@benthamscience.net

Yaoyao Lu

School of Electronic and Information Engineering, Suzhou University of Science and Technology

Email: info@benthamscience.net

Haiou Li

School of Electronic and Information Engineering, Suzhou University of Science and Technology

Email: info@benthamscience.net

Qiming Fu

School of Electronic and Information Engineering, Suzhou University of Science and Technology

Email: info@benthamscience.net

Jiyun Shen

Provincial Key Laboratory for Computer Information Processing Technology, Soochow University

Email: info@benthamscience.net

Yongbiao Xiao

School of Artificial Intelligence and Computer Science, JiangNan University

Email: info@benthamscience.net

References

  1. Stanzione F, Giangreco I, Cole JC. Use of molecular docking computational tools in drug discovery. Prog Med Chem 2021; 60: 273-343. doi: 10.1016/bs.pmch.2021.01.004 PMID: 34147204
  2. Liu C, Zhao J, Yang ZZ, Zhao DX. Dividing the periodic box into subdivisions with their surroundings to accelerate molecular dynamics simulation with high accuracy. J Chem Theory Comput 2020; 16(12): 7618-31. doi: 10.1021/acs.jctc.0c00808 PMID: 33231445
  3. Bredel M, Jacoby E. Chemogenomics: An emerging strategy for rapid target and drug discovery. Nat Rev Genet 2004; 5(4): 262-75. doi: 10.1038/nrg1317 PMID: 15131650
  4. Pahikkala T, Airola A, Pietilä S, et al. Toward more realistic drug-target interaction predictions. Brief Bioinform 2015; 16(2): 325-37. doi: 10.1093/bib/bbu010 PMID: 24723570
  5. Olayan RS, Ashoor H, Bajic VB. DDR: efficient computational method to predict drug–target interactions using graph mining and machine learning approaches. Bioinformatics 2018; 34(7): 1164-73. doi: 10.1093/bioinformatics/btx731 PMID: 29186331
  6. Shen C, Ding Y, Tang J, Xu X, Guo F. An ameliorated prediction of drug–target interactions based on multi-scale discrete wavelet transform and network features. Int J Mol Sci 2017; 18(8): 1781. doi: 10.3390/ijms18081781 PMID: 28813000
  7. Lavecchia A. Machine-learning approaches in drug discovery: Methods and applications. Drug Discov Today 2015; 20(3): 318-31. doi: 10.1016/j.drudis.2014.10.012 PMID: 25448759
  8. Zhang J, Zhu M, Chen P, Wang B. DrugRPE: Random projection ensemble approach to drug-target interaction prediction. Neurocomputing 2017; 228: 256-62. doi: 10.1016/j.neucom.2016.10.039
  9. Zeng X, Zhu S, Hou Y, et al. Network-based prediction of drug–target interactions using an arbitrary-order proximity embedded deep forest. Bioinformatics 2020; 36(9): 2805-12. doi: 10.1093/bioinformatics/btaa010 PMID: 31971579
  10. Li L, Koh CC, Reker D, et al. Predicting protein-ligand interactions based on bow-pharmacological space and Bayesian additive regression trees. Sci Rep 2019; 9(1): 7703. doi: 10.1038/s41598-019-43125-6 PMID: 31118426
  11. Cichonska A, Pahikkala T, Szedmak S, et al. Learning with multiple pairwise kernels for drug bioactivity prediction. Bioinformatics 2018; 34(13): i509-18. doi: 10.1093/bioinformatics/bty277 PMID: 29949975
  12. Cichonska A, Ravikumar B, Parri E, et al. Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors. PLOS Comput Biol 2017; 13(8): e1005678. doi: 10.1371/journal.pcbi.1005678 PMID: 28787438
  13. Shi H, Liu S, Chen J, Li X, Ma Q, Yu B. Predicting drug-target interactions using Lasso with random forest based on evolutionary information and chemical structure. Genomics 2019; 111(6): 1839-52. doi: 10.1016/j.ygeno.2018.12.007 PMID: 30550813
  14. Tabei Y, Pauwels E, Stoven V, Takemoto K, Yamanishi Y. Identification of chemogenomic features from drug–target interaction networks using interpretable classifiers. Bioinformatics 2012; 28(18): i487-94. doi: 10.1093/bioinformatics/bts412 PMID: 22962471
  15. 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. doi: 10.1371/journal.pcbi.1007129 PMID: 31199797
  16. 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)(2): 49. doi: 10.1186/s12911-020-1052-0 PMID: 32183788
  17. Torng W, Altman RB. Graph convolutional neural networks for predicting drug-target interactions. J Chem Inf Model 2019; 59(10): 4131-49. doi: 10.1021/acs.jcim.9b00628 PMID: 31580672
  18. 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. doi: 10.1093/bioinformatics/bty535 PMID: 29982330
  19. Li Y, Qiao G, Wang K, Wang G. Drug–target interaction predication via multi-channel graph neural networks. Brief Bioinform 2022; 23(1): bbab346. doi: 10.1093/bib/bbab346 PMID: 34661237
  20. 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. doi: 10.1093/bioinformatics/btaa524 PMID: 32428219
  21. Liu S, Wang Y, Deng Y, et al. Improved drug–target interaction prediction with intermolecular graph transformer. Brief Bioinform 2022; 23(5): bbac162. doi: 10.1093/bib/bbac162 PMID: 35514186
  22. Popov P, Buslaev P, Kozlovskii I. Rationalizing viral drug target identification using computational approaches: The SARS-CoV-2 spike glycoprotein s case study. ChemRxiv preprint, version 1 2020.
  23. Mikolov T, Chen K, Corrado G. Efficient estimation of word representations in vector space arXiv:13013781 2013.
  24. Pang S, Zhang Y, Song T, Zhang X, Wang X, Rodriguez-Patón A. AMDE: A novel attention-mechanism-based multidimensional feature encoder for drug–drug interaction prediction. Brief Bioinform 2022; 23(1): bbab545. doi: 10.1093/bib/bbab545 PMID: 34965586
  25. Ju W, Fang Z, Gu Y. A Comprehensive survey on deep graph representation learning arXiv: 230405055 2023.
  26. Ju W, Liu Z, Qin Y, et al. Few-shot molecular property prediction via hierarchically structured learning on relation graphs. Neural Netw 2023; 163: 122-31. doi: 10.1016/j.neunet.2023.03.034 PMID: 37037059
  27. Ju W, Luo X, Ma Z, Yang J, Deng M, Zhang M. GHNN: Graph harmonic neural networks for semi-supervised graph-level classification. Neural Netw 2022; 151: 70-9. doi: 10.1016/j.neunet.2022.03.018 PMID: 35398673
  28. Ju W, Luo X, Qu M. TGNN: A joint semi-supervised framework for graph-level classification arXiv:230411688 2023.
  29. Ju W, Gu Y, Chen B, et al. Glcc: A general framework for graph-level clustering. Proc Conf AAAI Artif Intell 2023; 37(4): 4391-9. doi: 10.1609/aaai.v37i4.25559
  30. Wang MY. Towards efficient and scalable deep learning on graphs. ICLR workshop on representation learning on graphs and manifolds; New Orleans, Louisiana, United States 2019.
  31. Jiang D, Hsieh CY, Wu Z, et al. Interactiongraphnet: A novel and efficient deep graph representation learning framework for accurate protein–ligand interaction predictions. J Med Chem 2021; 64(24): 18209-32. doi: 10.1021/acs.jmedchem.1c01830 PMID: 34878785
  32. 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. doi: 10.1021/acs.jmedchem.1c00421 PMID: 33961429
  33. Vaswani A, Shazeer N, Parmar N. Attention is all you need. Adv Neural Inf Process Syst 2017; 30.
  34. Gehring J, Auli M, Grangier D. Convolutional sequence to sequence learning. Proc Mach Learn Res 2017; 70: 1243-52.
  35. Dwivedi VP, Bresson X. A generalization of transformer networks to graphs. arXiv:201209699 2020.
  36. Cai R, Chen X, Fang Y, Wu M, Hao Y. Dual-dropout graph convolutional network for predicting synthetic lethality in human cancers. Bioinformatics 2020; 36(16): 4458-65. doi: 10.1093/bioinformatics/btaa211 PMID: 32221609
  37. Liu L, Jiang H, He P. On the variance of the adaptive learning rate and beyond arXiv:190803265 2019.
  38. 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. doi: 10.1093/bioinformatics/btv256 PMID: 26072486
  39. Le NQK, Do DT, Nguyen TTD, Le QA. A sequence-based prediction of Kruppel-like factors proteins using XGBoost and optimized features. Gene 2021; 787: 145643. doi: 10.1016/j.gene.2021.145643 PMID: 33848577
  40. Kha QH, Ho QT, Le NQK. Identifying SNARE proteins using an alignment-free method based on multiscan convolutional neural network and PSSM profiles. J Chem Inf Model 2022; 62(19): 4820-6. doi: 10.1021/acs.jcim.2c01034 PMID: 36166351
  41. Li P, Li Y, Hsieh CY, et al. TrimNet: Learning molecular representation from triplet messages for biomedicine. Brief Bioinform 2021; 22(4): bbaa266. doi: 10.1093/bib/bbaa266 PMID: 33147620
  42. 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. doi: 10.1093/bioinformatics/btaa921 PMID: 33119053
  43. 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. doi: 10.1038/s42256-020-0152-y
  44. Zhao T, Hu Y, Valsdottir LR, et al. Identifying debug target interactions based on graph convolutional network and deep neural network. Briefings in bioinformatics 2021; 22(2) 2141-2150.

Supplementary files

Supplementary Files
Action
1. JATS XML

Copyright (c) 2024 Bentham Science Publishers