Predicting Drug–Target Interactions Based on the Ensemble Models of Multiple Feature Pairs
Abstract
:1. Introduction
2. Materials and Methods
2.1. Benchmark Datasets
2.2. Evaluation Criteria
2.3. Negative Sampling and Data Construction
2.4. Feature Pairs and Algorithm
3. Results
3.1. Performance on DTIs
3.2. Comparison with State-of-the-Art Methods
4. Discussion
4.1. Robustness of Prediction
4.2. Weight Optimization of Ensemble Models
4.3. Comparison between Ensemble Models and Individual Model
4.4. External Validation
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
DTI | drug–target Interaction |
Ensemble-MFP | Fusion of Multiple Feature Pairs |
AUC | Area Under the Curve for ROC |
ROC | Receiver Operating Characteristics |
PU | Positive-Unlabeled problems |
GPCR | G Protein-Coupled Receptors |
SVM | Support Vector Machines |
RBF | Radial Basis Function |
Appendix A. Predictions for New Targets
Appendix B. Comparison between Simple Connection of Feature Pairs and Ensemble-MFP
Appendix C. Predicted Drug–Target Pairs
GPCR | Drug | Drug Name | Target | Gene Name | Record of Database | Score |
---|---|---|---|---|---|---|
1 | D00394 | Trimipramine | hsa3355 | HTR1F | - | 1.0973 |
2 | D00563 | Mirtazapine | hsa3355 | HTR1F | - | 1.0623 |
3 | D00394 | Trimipramine | hsa154 | ADRB2 | - | 1.0365 |
4 | D02566 | Maprotiline | hsa3355 | HTR1F | - | 1.0350 |
5 | D00563 | Mirtazapine | hsa154 | ADRB2 | - | 0.9933 |
6 | D00483 | Propranolol | hsa3355 | HTR1F | - | 0.9854 |
7 | D00394 | Trimipramine | hsa147 | ADRA1B | DrugBank | 0.9768 |
8 | D00394 | Trimipramine | hsa1128 | CHRM1 | - | 0.9765 |
9 | D00563 | Mirtazapine | hsa147 | ADRA1B | - | 0.9696 |
10 | D00394 | Trimipramine | hsa3350 | HTR1A | DrugBank | 0.9666 |
References
- Rayhan, F.; Ahmed, S.; Mousavian, Z.; Farid, D.M.; Shatabda, S. FRnet-DTI: Deep convolutional neural network for drug–target interaction prediction. Heliyon 2020, 6, e03444. [Google Scholar] [CrossRef]
- Parsons, A.B.; Brost, R.L.; Ding, H.; Li, Z.; Zhang, C.; Sheikh, B.; Brown, G.W.; Kane, P.M.; Hughes, T.R.; Boone, C. Integration of chemical-genetic and genetic interaction data links bioactive compounds to cellular target pathways. Nat. Biotechnol. 2004, 22, 62. [Google Scholar] [CrossRef] [PubMed]
- He, Z.; Zhang, J.; Shi, X.H.; Hu, L.L.; Kong, X.; Cai, Y.D.; Chou, K.C. Predicting drug–target interaction networks based on functional groups and biological features. PLoS ONE 2010, 5, e9603. [Google Scholar] [CrossRef] [PubMed]
- Claes, R.A.; Mats, G.G.; Helena, S. Quantitative Chemogenomics: Machine-Learning Models of Protein-Ligand Interaction. Curr. Top. Med. Chem. 2011, 11, 1978–1993. [Google Scholar]
- Bredel, M.; Jacoby, E. Chemogenomics: An emerging strategy for rapid target and drug discovery. Nat. Rev. Genet. 2004, 5, 262–275. [Google Scholar] [CrossRef] [Green Version]
- Alaimo, S.; Pulvirenti, A.; Giugno, R.; Ferro, A. drug–target interaction prediction through domain-tuned network-based inference. Bioinformatics 2013, 29, 2004–2008. [Google Scholar] [CrossRef]
- Hu, S.; Xia, D.N.; Su, B.; Chen, P.; Li, J. A Convolutional Neural Network System to Discriminate drug–target Interactions. IEEE/ACM Trans. Comput. Biol. Bioinform. 2019. [Google Scholar] [CrossRef] [PubMed]
- Jacob, L.; Hoffmann, B.; Stoven, V.; Vert, J.P. Virtual screening of GPCRs: An in silico chemogenomics approach. BMC Bioinform. 2008, 9, 363. [Google Scholar] [CrossRef] [Green Version]
- Wang, L.; You, Z.H.; Chen, X.; Xia, S.X.; Liu, F.; Yan, X.; Zhou, Y.; Song, K.J. A Computational-Based Method for Predicting drug–target interactions by Using Stacked Autoencoder Deep Neural Network. J. Comput. Biol. 2018, 25, 361–373. [Google Scholar] [CrossRef]
- Cheng, F.; Liu, C.; Jiang, J.; Lu, W.; Li, W.; Liu, G.; Zhou, W.; Huang, J.; Tang, Y. Prediction of drug–target interactions and drug repositioning via network-based inference. PLoS Comput. Biol. 2012, 8, e1002503. [Google Scholar] [CrossRef] [Green Version]
- Bahi, M.; Batouche, M. Drug–target Interaction Prediction in Drug Repositioning Based on Deep Semi-Supervised Learning. In IFIP Advances in Information and Communication Technology; Springer: London, UK, 2018; Volume 522, pp. 302–313. [Google Scholar] [CrossRef]
- Gove, R.; Faytong, J. Machine Learning and Event-Based Software Testing: Classifiers for Identifying Infeasible GUI Event Sequences. Adv. Comput. 2012, 86, 109–135. [Google Scholar]
- Bleakley, K.; Yamanishi, Y. Supervised prediction of drug–target interactions using bipartite local models. Bioinformatics 2009, 25, 2397–2403. [Google Scholar] [CrossRef] [Green Version]
- Bing, W.; Fang, A.; Xue, S.; Kim, S.; Xiang, Z. DISCO2: A Comprehensive Peak Alignment Algorithm for Two-Dimensional Gas Chromatography Time-of-Flight Mass Spectrometry. In Lecture Notes in Computer Science, Proceedings of the Bio-Inspired Computing and Applications—7th International Conference on Intelligent Computing, ICIC 2011, Zhengzhou, China, 11–14 August 2011; Revised Selected Papers; Springer: Berlin/Heidelberg, Germany, 2011. [Google Scholar]
- Chen, H.; Zhang, Z. A semi-supervised method for drug–target interaction prediction with consistency in networks. PLoS ONE 2013, 8, e62975. [Google Scholar] [CrossRef] [Green Version]
- Mousavian, Z.; Khakabimamaghani, S.; Kavousi, K.; Masoudi-Nejad, A. drug–target interaction prediction from PSSM based evolutionary information. J. Pharmacol. Toxicol. Methods 2016, 78, 42–51. [Google Scholar] [CrossRef] [PubMed]
- Rayhan, F.; Ahmed, S.; Shatabda, S.; Farid, D.M.; Mousavian, Z.; Dehzangi, A.; Rahman, M.S. iDTI-ESBoost: Identification of Drug Target Interaction Using Evolutionary and Structural Features with Boosting. Sci. Rep. 2017, 7, 17731. [Google Scholar] [CrossRef] [PubMed]
- Ezzat, A.; Zhao, P.; Wu, M.; Li, X.L.; Kwoh, C.K. drug–target Interaction Prediction with Graph Regularized Matrix Factorization. IEEE/ACM Trans. Comput. Biol. Bioinform. 2017, 14, 646–656. [Google Scholar] [CrossRef]
- Yamanishi, Y.; Araki, M.; Gutteridge, A.; Honda, W.; Kanehisa, M. Prediction of drug–target interaction networks from the integration of chemical and genomic spaces. Bioinformatics 2008, 24, i232–i240. [Google Scholar] [CrossRef]
- Bleakley, K.; Biau, G.; Vert, J.P. Supervised reconstruction of biological networks with local models. Bioinformatics 2007, 23, i57–i65. [Google Scholar] [CrossRef]
- Wen, M.; Zhang, Z.; Niu, S.; Sha, H.; Yang, R.; Yun, Y.; Lu, H. Deep-Learning-Based drug–target Interaction Prediction. J. Proteome Res. 2017, 16, 1401–1409. [Google Scholar] [CrossRef]
- 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, i221–i229. [Google Scholar] [CrossRef] [PubMed]
- Mordelet, F.; Vert, J.P. A bagging SVM to learn from positive and unlabeled examples. Pattern Recognit. Lett. 2013, 37, 201–209. [Google Scholar] [CrossRef] [Green Version]
- Wang, C.; Wang, W.; Lu, K.; Zhang, J.; Wang, B. Predicting drug–target interactions with Electrotopological State Fingerprints and Amphiphilic Pseudo Amino Acid Composition. Int. J. Mol. Sci. 2020, 21, 5694. [Google Scholar] [CrossRef]
- Hu, P.W.; Chan, K.C.C.; You, Z.H. Large-scale prediction of drug–target interactions from deep representations. In Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada, 24–29 July 2016. [Google Scholar]
- Feng, Q.; Dueva, E.; Cherkasov, A.; Ester, M. PADME: A Deep Learning-based Framework for drug–target Interaction Prediction. arXiv 2018, arXiv:1807.09741. [Google Scholar]
- Kanehisa, M. From genomics to chemical genomics: New developments in KEGG. Nucleic Acids Res. 2006, 34, D354–D357. [Google Scholar] [CrossRef] [PubMed]
- Wishart, D.S.; Knox, C.; Guo, A.C.; Cheng, D.; Shrivastava, S.; Tzur, D.; Gautam, B.; Hassanali, M. DrugBank: A knowledgebase for drugs, drug actions and drug targets. Nucleic Acids Res. 2008, 36, D901–D906. [Google Scholar] [CrossRef] [PubMed]
- Stefan, G.; Michael, K.; Mathias, D.; Monica, C.; Christian, S.; Evangelia, P.; Jessica, A.; Garcia, U.E.; Andreas, G.; Juhl, J.L. SuperTarget and Matador: Resources for exploring drug–target relationships. Nuclc Acids Res. 2008, 36, D919–D922. [Google Scholar]
- Ida, S.; Chang, A.; Christian, E.; Marion, G.; Christian, H.; Gregor, H.; Dietmar, S. BRENDA, the enzyme database: Updates and major new developments. Nucleic Acids Res. 2004, 32, D431–D433. [Google Scholar]
- Ezzat, A.; Wu, M.; Li, X.L.; Kwoh, C.K. drug–target interaction prediction using ensemble learning and dimensionality reduction. Methods 2017, 129, 81–88. [Google Scholar] [CrossRef]
- Lee, I.; Nam, H. Identification of drug–target interaction by a random walk with restart method on an interactome network. BMC Bioinform. 2018, 19, 208. [Google Scholar] [CrossRef] [Green Version]
- Ozturk, H.; Ozkirimli, E.; Ozgur, A. A comparative study of SMILES-based compound similarity functions for drug–target interaction prediction. BMC Bioinform. 2016, 17, 128. [Google Scholar] [CrossRef] [Green Version]
- Yap, C.W. PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints. J. Comput. Chem. 2011, 32, 1466–1474. [Google Scholar] [CrossRef] [PubMed]
- Li, Z.R.; Lin, H.H.; Han, L.Y.; Jiang, L.; Chen, X.; Chen, Y.Z. PROFEAT: A web server for computing structural and physicochemical features of proteins and peptides from amino acid sequence. Nucleic Acids Res. 2006, 34, W32–W37. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Zhang, P.; Tao, L.; Zeng, X.; Qin, C.; Chen, S.Y.; Zhu, F.; Yang, S.Y.; Li, Z.R.; Chen, W.P.; Chen, Y.Z. PROFEAT Update: A Protein Features Web Server with Added Facility to Compute Network Descriptors for Studying Omics-Derived Networks. J. Mol. Biol. 2017, 429, 416–425. [Google Scholar] [CrossRef]
- Hsu, C.; Chang, C.; Lin, C. A practical guide to support vector classification. Bju Int. 2008, 101, 1396–1400. [Google Scholar]
- Cao, D.S.; Liu, S.; Xu, Q.S.; Lu, H.M.; Huang, J.H.; Hu, Q.N.; Liang, Y.Z. Large-scale prediction of drug–target interactions using protein sequences and drug topological structures. Anal. Chim. Acta 2012, 752, 1–10. [Google Scholar] [CrossRef]
- Anna, G.; Anne, H.; Michał, N.; Patrícia, B.A.; Jon, C.; David, M.; Prudence, M.; Francis, A.; Bellis, L.J.; Elena, C.U. The ChEMBL database in 2017. Nucleic Acids Res. 2016, 45, D945–D954. [Google Scholar]
- Collins, J.E.; Wright, C.L.; Edwards, C.A.; Davis, M. A genome annotation-driven approach to cloning the human ORFeome. Genome Biol. 2004, 5, 1–11. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Gerhard, D.S.; Wagner, L.; Feingold, E.A.; Shenmen, C.M.; Grouse, L.H.; Schuler, G.; Klein, S.L.; Old, S.; Rasooly, R.; Good, P.; et al. The status, quality, and expansion of the NIH full-length cDNA project: The Mammalian Gene Collection (MGC). Genome Res. 2004, 14, 2121–2127. [Google Scholar]
- Pel, H.J.; Winde, J.D.; Archer, D.B.; Dyer, P.S.; Hofmann, G.; Schaap, P.J.; Turner, G.; Vries, R.D.; Al Ba Ng, R.; Albermann, K. Genome sequencing and analysis of the versatile cell factory Aspergillus niger CBS 513.88. Nat. Biotechnol. 2007, 25, 221–231. [Google Scholar] [CrossRef] [Green Version]
- Damveld, R.A.; van Kuyk, P.A.; Arentshorst, M.; Klis, F.M.; van den Hondel, C.A.M.J.J.; Ram, A.F.J. Expression of agsA, one of five 1,3-α-d-glucan synthase-encoding genes in Aspergillus niger, is induced in response to cell wall stress. Fungal Genet. Biol. 2005, 42, 165–177. [Google Scholar] [CrossRef]
- Kawanishi, Y.; Harada, S.; Tachikawa, H.; Okubo, T.; Shiraishi, H. Novel mutations in the promoter and coding region of the human 5-HT1A receptor gene and association analysis in schizophrenia. Am. J. Med. Genet. 2010, 81, 434–439. [Google Scholar] [CrossRef]
- Nakhai, B.; Nielsen, D.; Linnoila, M.; Goldman, D. 2 Naturally Occurring Amino Acid Substitutions in the Human 5-HT1A Receptor: Glycine 22 to Serine 22 and Isoleucine 28 to Valine 28. Biochem. Biophys. Res. Commun. 1995, 210, 530–536. [Google Scholar] [CrossRef] [Green Version]
- Wright, C.D.; Chen, Q.; Baye, N.L.; Huang, Y.; Healy, C.L.; Kasinathan, S.; O’Connell, T.D. Nuclear alpha1-adrenergic receptors signal activated ERK localization to caveolae in adult cardiac myocytes. Circ. Res. 2008, 103, 992–1000. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Wright, C.D.; Wu, S.C.; Dahl, E.F.; Sazama, A.J.; O’Connell, T.D. Nuclear Localization Drives α1-Adrenergic Receptor Oligomerization and Signaling in Cardiac Myocytes. Cell. Signal. 2012, 24, 794–802. [Google Scholar] [CrossRef] [PubMed] [Green Version]
Enzyme | GPCR | Ion Channel | Nuclear Receptor | |
---|---|---|---|---|
Drugs | 445 | 223 | 210 | 54 |
Targets | 664 | 95 | 204 | 26 |
DTIs | 2926 | 635 | 1476 | 90 |
unlabeled DT-pairs | 292,554 | 20,550 | 41,364 | 1314 |
Drug Descriptor | Dimension | Target Descriptor | Dimension | |
---|---|---|---|---|
Feature Pair 1 | Estate-FP | 79 | AAC | 20 |
Feature Pair 2 | MACCS-FP | 166 | APAAC | 80 |
Feature Pair 3 | Sub-FP Count | 307 | QSO | 160 |
Enzyme | GPCR | Ion Channel | Nuclear Receptor | |
---|---|---|---|---|
Accuracy (%) | 89.92 ± 0.93 # | 96.50 ± 0.70 | 85.01 ± 1.68 | 84.32 ± 12.44 |
Precision (%) | 90.37 ± 0.93 | 98.89 ± 0.16 | 84.90 ± 1.68 | 91.29 ± 13.70 |
Recall (%) | 100 ± 0.00 | 97.14 ± 0.96 | 100.00 ± 0.00 | 89.68 ± 17.01 |
F1-scores (%) | 94.94 ± 0.72 | 98.01 ± 0.23 | 91.83 ± 0.98 | 90.48 ± 8.72 |
AUC (%) | 95.92 ± 0.39 | 94.32 ± 0.57 | 95.97 ± 0.26 | 83.87 ± 7.38 |
AUC | Enzyme | GPCR | Ion Channel | Nuclear Receptor |
---|---|---|---|---|
Wang et al. | 0.916 | 0.897 | 0.907 | 0.775 |
MFDR | 0.969 | 0.904 | 0.933 | 0.886 |
Cao et al. | 0.938 | 0.839 | 0.875 | 0.809 |
FRnet-DTI | 0.972 | 0.912 | 0.943 | 0.872 |
Proposed | 0.959 | 0.943 | 0.960 | 0.839 |
ran-proposed | 0.933 | 0.908 | 0.925 | 0.821 |
TPR (%) | TNR (%) | Accuracy (%) | AUC (%) | |
---|---|---|---|---|
DeepDTI | 82.27 | 89.53 | 85.88 | 91.58 |
proposed-DeepDTI | 86.23 | 88.65 | 91.69 | 93.01 |
proposed-ChEMBL | 90.09 | 93.18 | 90.57 | 92.78 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, C.; Zhang, J.; Chen, P.; Wang, B. Predicting Drug–Target Interactions Based on the Ensemble Models of Multiple Feature Pairs. Int. J. Mol. Sci. 2021, 22, 6598. https://doi.org/10.3390/ijms22126598
Wang C, Zhang J, Chen P, Wang B. Predicting Drug–Target Interactions Based on the Ensemble Models of Multiple Feature Pairs. International Journal of Molecular Sciences. 2021; 22(12):6598. https://doi.org/10.3390/ijms22126598
Chicago/Turabian StyleWang, Cheng, Jun Zhang, Peng Chen, and Bing Wang. 2021. "Predicting Drug–Target Interactions Based on the Ensemble Models of Multiple Feature Pairs" International Journal of Molecular Sciences 22, no. 12: 6598. https://doi.org/10.3390/ijms22126598