Predict the Tertiary Structure of Protein with Binary Tree and Ensemble Strategy

Abstract:

In this paper we intend to apply a new method to predict tertiary structure. Several feature extraction methods adopted are physicochemical composition, recurrence quantification analysis (RQA) , pseudo amino acid composition (PseAA) and Distance frequency. We construct the binary tree Classification model, and adopt flexible neural tree models as the classifiers. We will train a number of based classifiers through different features extraction methods for every node of binary tree, then employ the selective ensemble method to ensemble them. 640 dataset is selected to our experiment. The predict accuracy with our method on this data set is 63.58%, higher than some other methods on the 640 datasets. So, our method is feasible and effective in some extent.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 3081-3085
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.3081
• Online since: September 2013
• Authors: Yi Ming Chen, Yue Hui Chen
• Keywords: Binary Tree, FNT, Selective Ensemble, Tertiary Structure

References

[1] Shi JY, Zhang SW, Pan Q, Cheng YM, Xie J. SVM-based method for subcellular localization of protein using multi-scale energy and pseudo amino acid composition Amino Acids, 33(1): 69-74 (2007).

DOI: 10.1007/s00726-006-0475-y

[2] Giuliani, A, Sirabella, P., Benigni, R., Colosimo, A, 2000. Mapping protein sequence spaces by recurrence: a case study on chimeric structures. Protein Eng. 13, 671-678.

DOI: 10.1093/protein/13.10.671

[3] Giuliani, A, Tomasi, M., 2002. Recurrence quantification analysis reveals interac-tion partners in paramyxoviridae envelope glycoproteins. Proteins 46, 171-176.

DOI: 10.1002/prot.10044

[4] Marwan, N., Romano, M. e., Thiel, M., Kurths, 1, 2007. Recurrenceplots for the analysis of complex systems. Phys. Rep. 438, 237-329.

[5] Deschavanne, P, Tuffe ' ry, P., 2008. Exploring an alignment free approach for protein classification and structural class prediction. Biochimie 90, 615-625.

DOI: 10.1016/j.biochi.2007.11.004

[6] Fiser, A., Tusna 'dy, G. E, Simon, I. Chaos game representation of protein structures. J. Mol. Graphics 12, 302-304.

DOI: 10.1016/0263-7855(94)80109-6

[7] Jianyi Yang, Zhenling Peng, et al. Prediction of protein structural classes by recurrence quantification analysis based on chaos game representation. J. TheoL BioI. 2009, doi: 10. 1 OJ6/j. jtbi. 2008. 12. 027.

[8] Chou KC. Prediction of protein cellular attributes using pseudo-amino acid composition,. Proteins: Struct Funct Genet, 43(3): 246-255 (2001).

DOI: 10.1002/prot.1035

[9] Huang Y, Li Y D. Prediction of protein subcellular locations using fuzzy K-NN method,. Bioinformatics, 20 (1): 21-28 (2004).

DOI: 10.1093/bioinformatics/btg366

[10] Thomas G. Dietterich G. Bakiri. Solving multiclass learning problems via Error-Correcting output codes,. Artificial Intelligence Research, (2): 263-286 (1995).

DOI: 10.1613/jair.105

[11] LUO D F, JUN, XIONG RONG. Distance function learning in error-correcting output coding framework, [C]/ICON IP 2006 Proceeding of the 13th International Conference on Neural Information Proceeding LNCS 4233. Berlin: Springer-Berlag: 1-10 (2006).

DOI: 10.1007/11893257_1

[12] Chen, Y., Yang, B., Dong, J., Nonlinear systems modelling via optimal design of neural trees. International Journal of Neural systems. 14, (2004) 125-138.

DOI: 10.1142/s0129065704001905

[13] Chen, Y., Yang, B., Dong, J., Abraham A.: Time-series forecasting using flexible neural tree model. Information Science, Vol. 174, Issues 3/4, pp.219-235, (2005).

DOI: 10.1016/j.ins.2004.10.005

[14] Chen, Y., Yang, B., Abraham A. Feature Selection and Classification using Flexible Neural Tree, Neurocomputing, 2006. (In press).

DOI: 10.1016/j.neucom.2006.01.022

[15] Masulli F, Valentini G. Effectiveness of error correcting output codes in multiclass learning problems,. Lecture Notes in Computer Science 1857, 107-116 (2000).

DOI: 10.1007/3-540-45014-9_10

[16] Chou, K.C., Zhang, C.T., 1995. Review: Prediction of protein structural classes. Crit. Rev. Biochem. Mol. Biol. 30, 275–349.

[17] Chen, C., Chen, L., Zou, X., Cai, P., 2009. Prediction of protein secondary structure content by using the concept of Chou's pseudo-amino acid composition and support vector machine. Protein Pept. Lett. 16, 27–31.

DOI: 10.2174/092986609787049420

[18] Ke Chen, LUKASZ A. KURGAN, Jishou ruan. Prediction of protein structural class using novel evolutionary collocation-based sequence representation. J. Computational Chemistry. 2008, 29: 1596–1604.

DOI: 10.1002/jcc.20918

[19] Wang ZX and Yuan Z: How good is the prediction of protein structural class by the component-coupled method? Pattern Recogn 2000, 38: 165–175.

DOI: 10.1002/(sici)1097-0134(20000201)38:2<165::aid-prot5>3.0.co;2-v

[20] Kurgan LA and Homaeian L: Prediction of structural classes for protein sequences and domains-Impact of prediction algorithms, sequence representation and homology, and test procedures on accuracy. Pattern Recogn 2006, 39: 2323–2343.

DOI: 10.1016/j.patcog.2006.02.014

[21] Kedarisetti KD, Kurgan LA and Dick S: Classifier ensembles for protein structural class prediction with varying homology. Biochem Biophys Res Commun 2006, 348: 981–988.

DOI: 10.1016/j.bbrc.2006.07.141

[22] Pa'nek J，Eidhammer I，Aasland R．A new method for identification of protein (Sub) families in a set of proteins based on hydropathy di stribution in proteins．Proteins：Struct Funct Bioinformatics，2005，58：923—934.

DOI: 10.1002/prot.20356

[23] Zhang Li，Liao Bo，Li Dachao，Zhu Wen．A novel representation for apoptosis protein subcellular localization prediction using support Vector machine．J Theor Bi01．2009，259：361-365.

DOI: 10.1016/j.jtbi.2009.03.025

[24] Zhihua, Z., Jianxin, W., Wei, T.: Ensembling neural networks: Many could be better than all. Artif. Intell. 137, 239–263 (2002).

DOI: 10.1016/s0004-3702(02)00190-x