SUPPORT VECTOR MACHINES FOR PREDICTION AND ANALYSIS OF BETA AND GAMMA-TURNS IN PROTEINS
Abstract
Tight turns have long been recognized as one of the three important features of proteins, together with α-helix and β-sheet. Tight turns play an important role in globular proteins from both the structural and functional points of view. More than 90% tight turns are β-turns and most of the rest are γ-turns. Analysis and prediction of β-turns and γ-turns is very useful for design of new molecules such as drugs, pesticides, and antigens. In this paper we investigated two aspects of applying support vector machine (SVM), a promising machine learning method for bioinformatics, to prediction and analysis of β-turns and γ-turns. First, we developed two SVM-based methods, called BTSVM and GTSVM, which predict β-turns and γ-turns in a protein from its sequence. When compared with other methods, BTSVM has a superior performance and GTSVM is competitive. Second, we used SVMs with a linear kernel to estimate the support of amino acids for the formation of β-turns and γ-turns depending on their position in a protein. Our analysis results are more comprehensive and easier to use than the previous results in designing turns in proteins.
References
- Trends Biochem Sci. 23, 444 (1998). Crossref, Medline, Google Scholar
- Nucl. Acids Res. 25, 3389 (1997). Crossref, Medline, Google Scholar
- Pattern Recognition 30(7), 1145 (1997). Crossref, Google Scholar
- Brank J., Grobelnik M., Milic-Frayling N., Mladenic D., Feature selection using support vector machines, in 3rd International Conference on Data Mining Methods and Databases for Engineering, Finance and Other Fields, pp. 261–273, 2002 . Google Scholar
- Analytical Biochem. 286, 1 (2000). Crossref, Medline, Google Scholar
- J. Protein Chem. 16, 575 (1997). Crossref, Medline, Google Scholar
- Biochemistry 13, 211 (1974). Crossref, Medline, Google Scholar
- Biophys. J. 26, 367 (1979). Crossref, Medline, Google Scholar
- Cristianini N., Shawe Taylor J., An Introduction to Support Vector Machines. Cambridge, 2002 . Google Scholar
- Deleo J., Measuring classifier intelligence, in Second International Symposium on Uncertainty Modelling and Analysis, pp. 318–325, 1993 . Google Scholar
- PNAS 84(13), 4355 (1987). Crossref, Medline, Google Scholar
- J. Biosci. 25, 143 (2000). Crossref, Medline, Google Scholar
- Machine Learning 46(1/3), 389 (2002). Crossref, Google Scholar
- Protein Sci. 5, 212 (1996). Crossref, Medline, Google Scholar
- Mol. Biol. 292, 195 (1999). Crossref, Google Scholar
- J. Pep. Sci. 8, 297 (2002). Medline, Google Scholar
- Bioinformatics 18, 1508 (2002). Crossref, Medline, Google Scholar
- Protein Sci. 12, 923 (2003). Crossref, Medline, Google Scholar
- Protein Sci. 12, 627 (2003). Crossref, Medline, Google Scholar
- Protein Engin. (2003). Google Scholar
- Minakuchi Y., Satou K., Konagaya A., Prediction of protein-protein interaction sites using support vector machines, in International Conference on Mathematics and Engineering Techniques in Medicine and Bilogical Sciences, pp. 22–28, 2003 . Google Scholar
- Adv. Protein Chem. 34, 167 (1981). Crossref, Medline, Google Scholar
- Adv. Protein Chem. 37, 100 (1985). Google Scholar
- Protein Sci. 8, 1045 (1999). Crossref, Medline, Google Scholar
- Biochemistry 39, 8655 (2000). Crossref, Medline, Google Scholar
-
V. Vapnik , Statistical Learning Theory ( Wiley , N.Y. , 1998 ) . Google Scholar - J. Mol. Biol. 203, 221 (1988). Crossref, Medline, Google Scholar
- Biopolymers 41, 673 (1997). Crossref, Google Scholar