Physico-Chemically Weighted Kernel for SVM Protein Classification

Abstract:

In this paper, a novel kernel taking into consideration of the physico-chemical properties of amino acids as well as the motif information is proposed to tackle the problem of protein classification. Similarity matrix is constructed based on an AAindex2 substitution matrix which measures the amino acid pair distance. Together with the motif content posing importance on the protein sequences, a new kernel is constructed. Numerical examples indicate that the string-based kernel in conjunction with SVM classifier performs significantly better than the traditional spectrum kernel method.

• Periodical: Applied Mechanics and Materials (Volumes 195-196)
• Pages: 385-390
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.195-196.385
• Online since: August 2012
• Authors: Hao Jiang, Wai Ki Ching
• Keywords: AAindex2, Motif, Protein Classification, Spectrum Kernel Method, Support Vector Machine (SVM)

References

[1] A. Krogh, M. Brown, I. Mian, K. Sjolander, and D. Haussler, Hidden Markov models in computational biology: Applicationsto protein modeling, J. Mol. Biol. 235, 1501-1531: (1994).

DOI: 10.1006/jmbi.1994.1104

[2] E. Eskin, W. Noble, and G.Y. Singer, Protein family classification using sparse Markov transducers, Proc. Eighth. Inter. Conf. on Intelligent Systems for Molecular Biology. 131-135, (2000).

[3] T. Jaakkola, M. Diekhans, and D. Haussler, A discriminative framework for detecting remote protein homologies, Journal of Computational Biology. 7(1-2), 95-114: (2000).

DOI: 10.1089/10665270050081405

[4] B. Scholkopf, Kernel methods in computational biology, MIT Press New York: (2004).

[5] C. Leslie, E. Eskin and W.S. Noble, The spectrum kernel: A string kernel for SVM protein classification, Proceedings of the Pacific Biocomputing Symposium. 564-575, (2002).

DOI: 10.1142/9789812799623_0053

[6] C. Leslie, E. Eskin, J. Weston and W.S. Noble, Mismatch string kernel for discriminative protein classification, Bioinformatics. 20(4): 467-476, (2003).

DOI: 10.1093/bioinformatics/btg431

[7] Y.S. Yuan, L. Lin, Q.W. Dong, X.L. Wang and M.H. Li, A protein classification method based on latent semantic analysis, Proceedings of the 2005 IEEE Engineering in Mdeicine and Biology 27th Annl. Conf. 7: 7738-7741, (2005).

DOI: 10.1109/iembs.2005.1616306

[8] G. Ratsch, S. Sonnenburg, B. Scolkopf, RASE: Recognition of Alternatively Spliced Exons in c. elegans., Bioinformatics 21(suppl I): i369-i377, (2005).

DOI: 10.1093/bioinformatics/bti1053

[9] B.J.M. Webb-Robertson, K.G. Ratuiste, C.S. Oehmen, Physic ochemical property distributions for accurate and rapid pair-wise protein homology detection, BMC Bioinformatics 11: 145, (2010).

DOI: 10.1186/1471-2105-11-145

[10] K. Tommi and M. Kanehisa, Analysis of amino acid indices and mutation matrices for sequence comparison and structure, prediction of proteins, Protein Engineering 9(1), 27-36: (1996).

DOI: 10.1093/protein/9.1.27

[11] B.H. Asa and D. Brutlay, Remote homology detection: a motif based approach, Bioinformatics19(1), 26-33: (2003).

[12] T. Miyata, S. Miyazawa and T. Yasunaga MIYT790101, J. Mol. Evol. 12, 219-236: (1979).

[13] R.A. Horn and C.R. Johnson Matrix analysis, Cambridge University Press, (1985).

[14] Functional Glycomics Gateway, http: /www. functionalglycomics. org.

[15] Y. Yang, L. Lin, Q. Dong, X. Wang, M. Li, Remote protein homology detection using recurrence quantification analysis and amino acid physicochemical properties, J. Theor. Biol. 252(1): 145-154, (2008).

DOI: 10.1016/j.jtbi.2008.01.028