Skip to main content

Logistic matrix factorisation and generative adversarial neural network-based method for predicting drug-target interactions

Abstract

Identifying drug-target protein association pairs is a prerequisite and a crucial task in drug discovery and development. Numerous computational models, based on different assumptions and algorithms, have been proposed as an alternative to the laborious, costly, and time-consuming traditional wet-lab methods. Most proposed methods focus on separated drug and target descriptors, calculated, respectively, from chemical structures and protein sequences, and fail to introduce and extract features where the interaction information is embedded. In this paper, we propose a new three-step method based on matrix factorisation and generative adversarial network (GAN) for drug-target interaction prediction. Firstly, the matrix factorisation technique is used to capture and extract the joint interaction feature, for both drugs and targets, from the drug-target interaction matrix. Then, a GAN is introduced for data augmentation. It generates a fake positive sample similar to the real positive sample (known interactions) in order to balance the samples, allow the exploitation of the entire negative sample, and increase the data size for an accurate prediction. Finally, a fully connected four-layer neural network is built for classification. Experimental results illustrate a higher prediction performance of the proposed method compared to shallow classifiers and to state-of-the-art methods with an accuracy higher than 97%. Moreover, the data generation effect is confirmed by evaluating the proposed method with and without the generation step. These results demonstrated the efficiency of the latent interaction features and data generation on predicting new drugs or repurposing existing drugs.

Graphic abstract

Overview of the WGANMF-DTI workflow for the Drug-Target Interaction Prediction task.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Availability of data and materials

The used datasets are available in the following link: http://web.kuicr.kyoto-u.ac.jp/supp/yoshi/drugtarget/.

References

  1. 1.

    Hopkins AL (2009) Predicting promiscuity. Nature. https://doi.org/10.1038/462167a

    Article  PubMed  Google Scholar 

  2. 2.

    Lounkine E et al (2012) Large-scale prediction and testing of drug activity on side-effect targets. Nature. https://doi.org/10.1038/nature11159

    Article  PubMed  PubMed Central  Google Scholar 

  3. 3.

    Masoudi-Nejad A, Mousavian Z, Bozorgmehr JH (2013) Drug-target and disease networks: polypharmacology in the post-genomic era. Silico Pharmacol. https://doi.org/10.1186/2193-9616-1-17

    Article  Google Scholar 

  4. 4.

    Pushpakom S et al (2019) Drug repurposing: progress, challenges and recommendations. Nat Rev Drug Discov. https://doi.org/10.1038/nrd.2018.168

    Article  PubMed  Google Scholar 

  5. 5.

    Paul SM et al (2010) How to improve R&D productivity: the pharmaceutical industry’s grand challenge. Nat Rev Drug Discov. https://doi.org/10.1038/nrd3078

    Article  PubMed  Google Scholar 

  6. 6.

    Keiser MJ, Roth BL, Armbruster BN, Ernsberger P, Irwin JJ, Shoichet BK (2007) Relating protein pharmacology by ligand chemistry. Nat Biotechnol. https://doi.org/10.1038/nbt1284

    Article  PubMed  Google Scholar 

  7. 7.

    Mochizuki M, Suzuki SD, Yanagisawa K, Ohue M, Akiyama Y (2019) QEX: target-specific druglikeness filter enhances ligand-based virtual screening. Mol Divers 23(1):11–18. https://doi.org/10.1007/s11030-018-9842-3

    CAS  Article  PubMed  Google Scholar 

  8. 8.

    Saikia S, Bordoloi M (2019) Molecular docking: challenges, advances and its use in drug discovery perspective. Curr Drug Targets 20(5):501–521. https://doi.org/10.2174/1389450119666181022153016

    CAS  Article  PubMed  Google Scholar 

  9. 9.

    Bouziane H, Chouarfia A (2020) Sequence- and structure-based prediction of amyloidogenic regions in proteins. Soft Comput. https://doi.org/10.1007/s00500-019-04087-z

    Article  Google Scholar 

  10. 10.

    Rai H et al (2021) Molecular docking, binding mode analysis, molecular dynamics, and prediction of ADMET/toxicity properties of selective potential antiviral agents against SARS-CoV-2 main protease: an effort toward drug repurposing to combat COVID-19. Mol Divers. https://doi.org/10.1007/s11030-021-10188-5

    Article  PubMed  PubMed Central  Google Scholar 

  11. 11.

    Cheng F et al (2012) Prediction of drug-target interactions and drug repositioning via network-based inference. PLoS Comput Biol 8(5):e1002503. https://doi.org/10.1371/journal.pcbi.1002503

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  12. 12.

    Chen X, Liu M-X, Yan G-Y (2012) Drug–target interaction prediction by random walk on the heterogeneous network. Mol BioSyst 8(7):1970–1978. https://doi.org/10.1039/C2MB00002D

    CAS  Article  PubMed  Google Scholar 

  13. 13.

    Maldonado AG, Doucet JP, Petitjean M, Fan B-T (2006) Molecular similarity and diversity in chemoinformatics: from theory to applications. Mol Divers 10(1):39–79. https://doi.org/10.1007/s11030-006-8697-1

    CAS  Article  PubMed  Google Scholar 

  14. 14.

    Yamanishi Y, Araki M, Gutteridge A, Honda W, Kanehisa M (2008) Prediction of drug-target interaction networks from the integration of chemical and genomic spaces. Bioinformatics 24(13):i232-240. https://doi.org/10.1093/bioinformatics/btn162

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  15. 15.

    Bleakley K, Yamanishi Y (2009) Supervised prediction of drug-target interactions using bipartite local models. Bioinformatics 25(18):2397–2403. https://doi.org/10.1093/bioinformatics/btp433

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  16. 16.

    Takács G, Pilászy I, Németh B, Tikk D (2008) Matrix factorisation and neighbor based algorithms for the netflix prize problem. In: Proceedings of the 2008 ACM conference on Recommender systems, New York, USA, p. 267–274. https://doi.org/10.1145/1454008.1454049.

  17. 17.

    Ezzat A, Wu M, Li X-L, Kwoh C-K (2019) Computational prediction of drug–target interactions using chemogenomic approaches: an empirical survey. Brief Bioinform 20(4):1337–1357. https://doi.org/10.1093/bib/bby002

    CAS  Article  PubMed  Google Scholar 

  18. 18.

    Byvatov E, Fechner U, Sadowski J, Schneider G (2003) Comparison of support vector machine and artificial neural network systems for drug/nondrug classification. J Chem Inf Comput Sci 43(6):1882–1889. https://doi.org/10.1021/ci0341161

    CAS  Article  PubMed  Google Scholar 

  19. 19.

    Cao D-S et al (2014) Computational prediction of drug target interactions using chemical, biological, and network features. Mol Inf 33(10):669–681. https://doi.org/10.1002/minf.201400009

    CAS  Article  Google Scholar 

  20. 20.

    Myoung Soo Park, Jin Hee Na, and Jin Young Choi (2005) PCA-based feature extraction using class information. In 2005 IEEE International Conference on Systems, Man and Cybernetics, vol 1, p 341–345. https://doi.org/10.1109/ICSMC.2005.1571169.

  21. 21.

    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature. https://doi.org/10.1038/nature14539

    Article  PubMed  Google Scholar 

  22. 22.

    Liu Y, Wu M, Miao C, Zhao P, Li X-L (2016) Neighborhood regularized logistic matrix factorisation for drug-target interaction prediction. PLoS Comput Biol 12(2):e1004760. https://doi.org/10.1371/journal.pcbi.1004760

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  23. 23.

    Gönen M (2012) Predicting drug–target interactions from chemical and genomic kernels using Bayesian matrix factorisation. Bioinformatics 28(18):2304–2310. https://doi.org/10.1093/bioinformatics/bts360

    CAS  Article  PubMed  Google Scholar 

  24. 24.

    Cobanoglu MC, Liu C, Hu F, Oltvai ZN, Bahar I (2013) Predicting drug-target interactions using probabilistic matrix factorisation. J Chem Inf Model 53(12):3399–3409. https://doi.org/10.1021/ci400219z

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  25. 25.

    Zheng X, Ding H, Mamitsuka H, Zhu S (2013) Collaborative matrix factorisation with multiple similarities for predicting drug-target interactions. In Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, New York, USA, p 1025–1033. https://doi.org/10.1145/2487575.2487670.

  26. 26.

    Hao M, Bryant SH, Wang Y (2017) Predicting drug-target interactions by dual-network integrated logistic matrix factorisation. Sci Rep. https://doi.org/10.1038/srep40376

    Article  PubMed  PubMed Central  Google Scholar 

  27. 27.

    Ban T, Ohue M, Akiyama Y (2019) NRLMFβ: Beta-distribution-rescored neighborhood regularized logistic matrix factorisation for improving the performance of drug–target interaction prediction. Biochem Biophys Rep 18:100615. https://doi.org/10.1016/j.bbrep.2019.01.008

    Article  PubMed  PubMed Central  Google Scholar 

  28. 28.

    Ezzat A, Zhao P, Wu M, Li X, Kwoh C (2017) Drug-target interaction prediction with graph regularized matrix factorisation. IEEE/ACM Trans Comput Biol Bioinf 14(3):646–656. https://doi.org/10.1109/TCBB.2016.2530062

    CAS  Article  Google Scholar 

  29. 29.

    Cui Z, Gao Y-L, Liu J-X, Dai L-Y, Yuan S-S (2019) L2,1-GRMF: an improved graph regularized matrix factorisation method to predict drug-target interactions. BMC Bioinformatics 20(8):287. https://doi.org/10.1186/s12859-019-2768-7

    Article  PubMed  PubMed Central  Google Scholar 

  30. 30.

    Shi J-Y, Zhang A-Q, Zhang S-W, Mao K-T, Yiu S-M (2018) A unified solution for different scenarios of predicting drug-target interactions via triple matrix factorisation. BMC Syst Biol 12(9):136. https://doi.org/10.1186/s12918-018-0663-x

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  31. 31.

    Manoochehri HE, Nourani M (2018) Predicting Drug-Target Interaction Using Deep Matrix Factorisation. In 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS), p 1–4. https://doi.org/10.1109/BIOCAS.2018.8584817.

  32. 32.

    Wen M et al (2017) Deep-learning-based drug-target interaction prediction. J Proteome Res 16(4):1401–1409. https://doi.org/10.1021/acs.jproteome.6b00618

    CAS  Article  PubMed  Google Scholar 

  33. 33.

    You J, McLeod RD, Hu P (2019) Predicting drug-target interaction network using deep learning model. Comput Biol Chem 80:90–101. https://doi.org/10.1016/j.compbiolchem.2019.03.016

    CAS  Article  PubMed  Google Scholar 

  34. 34.

    Hu S, Zhang C, Chen P, Gu P, Zhang J, Wang B (2019) Predicting drug-target interactions from drug structure and protein sequence using novel convolutional neural networks. BMC Bioinformatics 20:689. https://doi.org/10.1186/s12859-019-3263-x

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  35. 35.

    Rayhan F, Ahmed S, Mousavian Z, Farid DM, Shatabda S (2020) FRnet-DTI: Deep convolutional neural network for drug-target interaction prediction. Heliyon 6(3):e03444. https://doi.org/10.1016/j.heliyon.2020.e03444

    Article  PubMed  PubMed Central  Google Scholar 

  36. 36.

    Wang Y-B, You Z-H, Yang S, Yi H-C, Chen Z-H, Zheng K (2020) A deep learning-based method for drug-target interaction prediction based on long short-term memory neural network. BMC Med Inform Decis Mak 20(2):49. https://doi.org/10.1186/s12911-020-1052-0

    Article  PubMed  PubMed Central  Google Scholar 

  37. 37.

    Zhao T, Hu Y, Valsdottir LR, Zang T, Peng J (2021) Identifying drug–target interactions based on graph convolutional network and deep neural network. Brief Bioinform. https://doi.org/10.1093/bib/bbaa044

    Article  PubMed  Google Scholar 

  38. 38.

    Sun C, Xuan P, Zhang T, Ye Y (2020) Graph convolutional autoencoder and generative adversarial network-based method for predicting drug-target interactions. IEEE/ACM Trans Comput Biol Bioinf. https://doi.org/10.1109/TCBB.2020.2999084

    Article  Google Scholar 

  39. 39.

    Wishart DS et al (2008) DrugBank: a knowledgebase for drugs, drug actions and drug targets. Nucleic Acids Res. https://doi.org/10.1093/nar/gkm958

    Article  PubMed  PubMed Central  Google Scholar 

  40. 40.

    Kanehisa M et al (2006) From genomics to chemical genomics: new developments in KEGG. Nucleic Acids Res. https://doi.org/10.1093/nar/gkj102

    Article  PubMed  PubMed Central  Google Scholar 

  41. 41.

    Schomburg I et al (2004) BRENDA, the enzyme database: updates and major new developments. Nucleic Acids Res. https://doi.org/10.1093/nar/gkh081

    Article  PubMed  PubMed Central  Google Scholar 

  42. 42.

    Günther S et al (2008) SuperTarget and Matador: resources for exploring drug-target relationships. Nucleic Acids Res. https://doi.org/10.1093/nar/gkm862

    Article  PubMed  PubMed Central  Google Scholar 

  43. 43.

    Li Y, Liu X, You Z-H, Li L-P, Guo J-X, Wang Z (2021) A computational approach for predicting drug–target interactions from protein sequence and drug substructure fingerprint information. Int J Intell Syst 36(1):593–609. https://doi.org/10.1002/int.22332

    Article  Google Scholar 

  44. 44.

    Chu Y et al (2021) DTI-CDF: a cascade deep forest model towards the prediction of drug-target interactions based on hybrid features. Brief Bioinform 22(1):451–462. https://doi.org/10.1093/bib/bbz152

    Article  PubMed  Google Scholar 

  45. 45.

    Goodfellow IJ et al (2020) Generative Adversarial Networks. Available Accessed 18 Nov 2020

  46. 46.

    Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved Training of Wasserstein GANs. Available: Accessed 21 Nov 2020

  47. 47.

    Arjovsky M, Chintala S, Bottou L (2017) Wasserstein GAN. Available: Accessed 21 Nov 2020

  48. 48.

    Schwede T, Kopp J, Guex N, Peitsch MC (2003) SWISS-MODEL: an automated protein homology-modelling server. Nucleic Acids Res 31(13):3381–3385. https://doi.org/10.1093/nar/gkg520

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  49. 49.

    Trott O, Olson AJ (2010) AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization and multithreading. J Comput Chem 31(2):455–461. https://doi.org/10.1002/jcc.21334

    CAS  Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

No funding was received for conducting this study.

Author information

Affiliations

Authors

Contributions

All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by [Sarra Itidal ABBOU]. The first draught of the manuscript was written by [Sarra Itidal ABBOU] and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Sarra Itidal Abbou.

Ethics declarations

Conflicts of interest

The authors report no conflicts of interest in this work.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 599 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Abbou, S.I., Bouziane, H. & Chouarfia, A. Logistic matrix factorisation and generative adversarial neural network-based method for predicting drug-target interactions. Mol Divers 25, 1497–1516 (2021). https://doi.org/10.1007/s11030-021-10273-9

Download citation

Keywords

  • Drug-target interaction (DTI)
  • Drug repurposing
  • Logistic matrix factorisation
  • Deep learning
  • Generative adversarial networks (GAN)
  • Latent interaction features