Abstract
The problem of secondary structure prediction can be formulated as a pattern classification problem and methods from statistics and machine learning are suitable. This paper proposes a new combination approach between Gaussian Mixture Model (GMM) and Support Vector Machine (SVM) by typical sample extraction based on a UBM/GMM system for SVM in protein secondary structure prediction. Our hybrid model achieved a good performance of three-state overall per residue accuracy Q 3 = 77.6% which is comparable to the best techniques available.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Baldi, P., Brunak, S.: Bioinformatics, the Machine Learning approach, 2nd edn. The MIT Press, Cambridge, MA (2001)
Eidhammer, I., Jonassen, I., Taylor, W.R.: Protein Bioinformatics: An algorithmic Approach to Sequence and Strcture Analysis. John Wiley & Sons Ltd., New York (2004)
Hua, S., Sun, Z.: A novel method of protein secondary structure prediction with high segment overlap measure: Support vector machine approach. Jour. Mol. Biology 308, 397–407 (2001)
Liu, M., Xie, Y., Yao, Z., Dai, B.: A New Hybrid GMM/SVM for Speaker Verification. In: The 18th International Confrence on Pattern Recognition (ICPR 2006) (2006)
Bredin, H., Dehak, N., Chollet, G.: GMM-based SVM for face detection. In: The 18th International Confrence on Pattern Recognition (ICPR 2006)
Zhu, Y., Fujimura, K.: Driver Face Tracking using Gaussian Mixture Model (GMM). In: Proceedings, International IEEE conference on Image Processing. (2003)
Qian, N., Sejnowski, T.: Predicting the secondary structure of globular proteins using neural network models. Journal of Molecular Biology 202, 865–884 (1988)
Rost, B., Sander, C.: Prediction of secondary Structure at better than 70% accuracy. Journal of Molecular Biology 232, 584–599 (1993)
Cuff, J.A., Barton, G.J.: Evaluation and improvement of multiple sequence methods for protein secondary structure prediction. Proteins: Struct. Funct. Genet. 34, 508–519 (1999)
Avbelj, F., Fele, L.: Role of Main-chain Electrostatics, Hydrophobic effect and Side-chain conformational entropy in determining the secondary structure of proteins. Journal of Molecular Biology 279, 665–684 (1998)
Muggleton, S., King, R.D., Sternberg, M.J.E.: Protein secondary structure prediction using logic. Protein Eng. 5, 647–657 (1992)
Fan, R.E., Chen, P.H., Lin, C.J.: Working set selection using the second order information for training SVM. Journal of Machine Learning Research 6, 1889–1918 (2005)
Cambridge University Engineering Department: HTK library modules and tools available in C source form at : http://htk.eng.cam.ac.uk/download.shtml
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Samani, E.B., Homayounpour, M.M., Gu, H. (2007). A Novel Hybrid GMM/SVM Architecture for Protein Secondary Structure Prediction. In: Masulli, F., Mitra, S., Pasi, G. (eds) Applications of Fuzzy Sets Theory. WILF 2007. Lecture Notes in Computer Science(), vol 4578. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73400-0_62
Download citation
DOI: https://doi.org/10.1007/978-3-540-73400-0_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73399-7
Online ISBN: 978-3-540-73400-0
eBook Packages: Computer ScienceComputer Science (R0)