Authors : Kopoin NDiffon Charlemagne; Koffi Dagou Augustin; Zouneme Boris Stéphane

Volume/Issue : Volume 9 - 2024, Issue 10 - October

Google Scholar : https://tinyurl.com/5448vz8u

Scribd : https://tinyurl.com/mrnecepp

DOI : https://doi.org/10.38124/ijisrt/IJISRT24OCT497

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The problem we address in this paper is a model selection problem. We consider the k-fold cross-validation (KCV) technique, applied to the Gaussian support vector machine (SVM) classification algorithm. In the cross-vali- dation process, the value of k for the number of subsets is generally chosen and set aprioristically (without any ex- periment). However, the value of k affects the choice of the best compromise between the estimation error and the ap- proximation error of the model. In this way, the k value of the number of subsets can severely influence the optimal values of the SVM classifier's hyperparameters and conse- quently affect the performance of the selected model and its ability to generalize. In this work, we propose a rigorous approach for finding the values of the hyperparameters of the Gaussian SVM known as SVOH (Selection of Optimal Hyperparam- eter Values) in a context of protein-protein interaction (PPI) prediction, where it is necessary to classify the pairs of pro- teins that interact together and those that do not interact together. The proposed approach considers the k value of the number of subsets as an influential parameter of the model and therefore performs learning to find an optimal value of k.

Keywords : Machine Learning, Model Selection, Cross-Vali- dation, Prediction of Protein-Protein Interactions

References :

1. X.-Y. Pan, Y.-N. Zhang, et H.-B. Shen, « Large-Scale Prediction of Human Protein−Protein Interactions from Amino Acid Sequence Based on Latent Topic Features », J. Proteome Res., vol. 9, n^o 10, p. 4992‑5001, oct. 2010, doi: 10.1021/pr100618t.
2. W. Ma, Y. Cao, W. Bao, B. Yang, et Y. Chen, « ACT-SVM: Prediction of Protein-Protein Interactions Based on Support Vector Basis Model », Sci. Program., vol. 2020, p. e8866557, juill. 2020, doi: 10.1155/2020/8866557.
3. C. N. Kopoin, N. T. Tchimou, B. K. Saha, et M. Babri, « A Feature Extraction Method in Large Scale Prediction of Human Protein-Protein Interactions using Physicochemical Properties into Bi-gram », in 2020 IEEE International Conf on Natural and Engineering Sciences for Sahel’s Sustainable Development - Impact of Big Data Application on Society and Environment (IBASE-BF), Ouagadougou, Burkina Faso: IEEE, févr. 2020, p. 1‑7. doi: 10.1109/IBASE-BF48578.2020.9069594.
4. M. W. Gardner et S. R. Dorling, « Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences », Atmos. Environ., vol. 32, n^o 14‑15, p. 2627‑2636, 1998.
5. D. Anguita, A. Ghio, S. Ridella, et D. Sterpi, « K-Fold Cross Validation for Error Rate Estimate in Support Vector Machines. », in DMIN, 2009, p. 291‑297.
6. D. Anguita, L. Ghelardoni, A. Ghio, L. Oneto, et S. Ridella, « The’K’in K-fold Cross Validation. », in ESANN, 2012, p. 441‑446.
7. J. D. Rodriguez, A. Perez, et J. A. Lozano, « Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation », IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, n^o 3, p. 569‑575, mars 2010, doi: 10.1109/TPAMI.2009.187.
8. Y. Bengio et Y. Grandvalet, « No unbiased estimator of the variance of k-fold cross-validation », J. Mach. Learn. Res., vol. 5, n^o Sep, p. 1089‑1105, 2004.
9. S. Arlot et A. Celisse, « A survey of cross-validation procedures for model selection », Stat. Surv., vol. 4, n^o none, p. 40‑79, janv. 2010, doi: 10.1214/09-SS054.
10. V. Vapnik, The Nature of Statistical Learning Theory. Springer Science & Business Media, 2013.
11. J. L. Rodgers, « The bootstrap, the jackknife, and the randomization test: A sampling taxonomy », Multivar. Behav. Res., vol. 34, n^o 4, p. 441‑456, 1999.
12. C.-W. Hsu, C.-C. Chang, et C.-J. Lin, A practical guide to support vector classification. Taipei, 2003.
13. G. A. Y. Laura, « Algorithme de descente du gradient stochastique », 2015.
14. J. A. A. Brito, F. E. McNeill, C. E. Webber, et D. R. Chettle, « Grid search: an innovative method for the estimation of the rates of lead exchange between body compartments », J. Environ. Monit., vol. 7, n^o 3, p. 241‑247, févr. 2005, doi: 10.1039/B416054A.
15. L. Yang et A. Shami, « On hyperparameter optimization of machine learning algorithms: Theory and practice », Neurocomputing, vol. 415, p. 295‑316, nov. 2020, doi: 10.1016/j.neucom.2020.07.061.
16. C. N. Kopoin, A. K. Atiampo, B. G. N’Guessan, et M. Babri, « Prediction of Protein-Protein Interactions from Sequences using a Correlation Matrix of the Physicochemical Properties of Amino Acids », Int. J. Comput. Sci. Netw. Secur., vol. 21, n^o 3, p. 41‑47, mars 2021, doi: 10.22937/IJCSNS.2021.21.3.6.
17. J. R. Bock et D. A. Gough, « Predicting protein–protein interactions from primary structure », Bioinformatics, vol. 17, n^o 5, p. 455‑460, mai 2001, doi: 10.1093/bioinformatics/17.5.455.
18. Y. E. Göktepe et H. Kodaz, « Prediction of Protein-Protein Interactions Using An Effective Sequence Based Combined Method », Neurocomputing, vol. 303, p. 68‑74, août 2018, doi: 10.1016/j.neucom.2018.03.062.
19. Z.-H. You, Y.-K. Lei, L. Zhu, J. Xia, et B. Wang, « Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis », BMC Bioinformatics, vol. 14, n^o S8, p. S10, mai 2013, doi: 10.1186/1471-2105-14-S8-S10.
20. Z.-H. You, S. Li, X. Gao, X. Luo, et Z. Ji, « Large-Scale Protein-Protein Interactions Detection by Integrating Big Biosensing Data with Computational Model », BioMed Research International. Consulté le: 5 janvier 2019. [En ligne]. Disponible sur: https://www.hindawi.com/journals/bmri/2014/598129/abs/
21. J. Martin, « Prédiction de la structure locale des protéines par des modeles de chaˆınes de Markov cachées », PhD Thesis, Citeseer, 2005.
22. C.-H. Huang, H.-S. Peng, et K.-L. Ng, « Prediction of Cancer Proteins by Integrating Protein Interaction, Domain Frequency, and Domain Interaction Data Using Machine Learning Algorithms », BioMed Research International. Consulté le: 28 mai 2018. [En ligne]. Disponible sur: https://www.hindawi.com/journals/bmri/2015/312047/abs/
23. M. Riley, « Functions of the Gene Products of Escherichia coli », MICROBIOL REV, vol. 57, p. 91, 1993.
24. X.-T. Huang, Y. Zhu, L. L. H. Chan, Z. Zhao, et H. Yan, « An integrative C. elegans protein–protein interaction network with reliability assessment based on a probabilistic graphical model », Mol. Biosyst., vol. 12, n^o 1, p. 85‑92, 2016.
25. Y. Z. Zhou, Y. Gao, et Y. Y. Zheng, « Prediction of Protein-Protein Interactions Using Local Description of Amino Acid Sequence », in Advances in Computer Science and Education Applications, vol. 202, M. Zhou et H. Tan, Éd., Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, p. 254‑262. doi: 10.1007/978-3-642-22456-0_37.
26. V. N. Vapnik, « An overview of statistical learning theory », IEEE Trans. Neural Netw., vol. 10, n^o 5, p. 988‑999, 1999.
27. C. J. van Oss, « Hydrophobicity and hydrophilicity of biosurfaces », Curr. Opin. Colloid Interface Sci., vol. 2, n^o 5, p. 503‑512, 1997.
28. P. Wira, « Réseaux de neurones artificiels: architectures et applications », Cours En Ligne Univ. Haute-Alsace, 2009.
29. L. Bottou, « Stochastic gradient descent tricks », in Neural networks: Tricks of the trade, Springer, 2012, p. 421‑436.
30. X. Cao, W. Zhang, et Y. Yu, « A Bootstrapping Framework With Interactive Information Modeling for Network Alignment », IEEE Access, vol. 6, p. 13685‑13696, 2018, doi: 10.1109/ACCESS.2018.2811721.