An novel method of protein secondary structure prediction based on compound pyramid model

In this paper, we propose a compound pyramid model to predict protein secondary structure, where homology analysis and an improved support vector machine (SVM) technology are used for predicting protein secondary structure. The homology analysis is based on BP network model which uses pair-wise sequence alignment, and SVM classification considers the physical and chemical properties of amino acids. We employed SVM multi-classification and homogenous analysis methods in integrative layer of compound pyramid model proposed by us. Result shows that the ensemble prediction model gets better results in our experiment compared with other methods.

[1]  Minoru I. Kanehisa,et al.  Pattern recognition in nucleic acid sequences. II. An efficient method for finding locally stable secondary structures , 1982, Nucleic Acids Res..

[2]  P. Y. Chou,et al.  Conformational parameters for amino acids in helical, beta-sheet, and random coil regions calculated from proteins. , 1974, Biochemistry.

[3]  S. B. Needleman,et al.  A general method applicable to the search for similarities in the amino acid sequence of two proteins. , 1970, Journal of molecular biology.

[4]  S. Hua,et al.  A novel method of protein secondary structure prediction with high segment overlap measure: support vector machine approach. , 2001, Journal of molecular biology.

[5]  B. Rost,et al.  Combining evolutionary information and neural networks to predict protein secondary structure , 1994, Proteins.

[6]  Esko Ukkonen,et al.  On Approximate String Matching , 1983, FCT.

[7]  S. Muggleton,et al.  Protein secondary structure prediction using logic-based machine learning. , 1992, Protein engineering.

[8]  B. Rost,et al.  Alignments grow, secondary structure prediction improves , 2002, Proteins.

[9]  Trevor I. Dix,et al.  A Versatile Divide and Conquer Technique for Optimal String Alignment , 1999, Inf. Process. Lett..

[10]  O. Gotoh.  An improved algorithm for matching biological sequences. , 1982, Journal of molecular biology.

[11]  Wen-Lian Hsu,et al.  HYPROSP II-A knowledge-based hybrid method for protein secondary structure prediction based on local prediction confidence , 2005, Bioinform..

[12]  Pierre Baldi,et al.  Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles , 2002, Proteins.

[13]  G J Barton,et al.  Application of multiple sequence alignment profiles to improve protein secondary structure prediction , 2000, Proteins.

[14]  L. Allison,et al.  Fast, optimal alignment of three sequences using linear gap costs. , 2000, Journal of theoretical biology.

[15]  Yang Bing.  MARADBCM: THE MINING ASSOCIATION RULES ALGORITHM BASED ON DOUBLE-BASE COOPERATING MECHANISM , 2002 .

[16]  Yang Bing,et al.  MINING QUANTITATIVE ASSOCIATION RULES WITH STANDARD SQL QUERIES AND IT'S EVALUATION , 2002 .