Comparison of One-Class SVM and Two-Class SVM for Fold Recognition

  • Alexander Senf
  • Xue-wen Chen
  • Anne Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


The best protein structure prediction results today are achieved by incorporating initial structural prediction using alignments to known protein structures. The performance of these algorithms directly depends on the quality and significance of the alignment results. Support Vector Machines (SVMs) have shown great potential in providing good alignment results in cases where very low similarities to known proteins exist. In this paper we propose the use of a one-class SVM to reduce the computational resources required to perform SVM learning and classification. Experimental results show its efficiency compared to two-class SVM algorithms while producing results of similar accuracy.


Support Vector Machine Feature Vector Positive Class Support Vector Machine Algorithm Fold Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Altschul, S.F., et al.: Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Research 25, 3389–3402 (1997)CrossRefGoogle Scholar
  2. 2.
    Brenner, S.E., Koehl, P., Levitt, M.: The ASTRAL compendium for sequence and structure analysis. Nucleic Acids Research 28, 254–256 (2000)CrossRefGoogle Scholar
  3. 3.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2001), Software available at
  4. 4.
    Chen, Y., Zhou, X., Huang, T.S.: One-Class SVM For Learning in Image Retrieval. In: Proc. IEEE Int’l Conf. On Image Processing (ICIP), October 7-10, 2001, vol. 1, pp. 34–37 (2001)Google Scholar
  5. 5.
    Han, S., Lee, B.-c., et al.: Fold recognition by combining profile-profile alignment and support vector machine. Bioinformatics 21(11), 2667–2673 (2005)CrossRefGoogle Scholar
  6. 6.
    Jones, D.T.: GenTHREADER: an efficient and reliable protein fold recognition method for genomic sequences. Journal of Molecular Biology 287, 797–815 (1999)CrossRefGoogle Scholar
  7. 7.
    Karplus, K., et al.: Predicting protein structure using only sequence information. Proteins suppl. 3, 121–125 (1999)CrossRefGoogle Scholar
  8. 8.
    Kelly, L.A., et al.: Enhanced genome annotation using structural profiles in the program 3D-PSSM. Journal of Molecular Biology 299, 499–520 (2000)Google Scholar
  9. 9.
    Liao, L., Noble, W.S.: Combining Pairwise Sequence Similarity and Support Vector Machines for Detecting Remote Protein Evolutionary and Structural Relationships. Journal of Computational Biology 10(6), 857–868 (2003)CrossRefGoogle Scholar
  10. 10.
    Manewitz, L.M., Yousef, M.: One-Class SVMs for Document Classification. Journal of Machine Learning Research 2(3), 139–154 (2001)Google Scholar
  11. 11.
    Murzin, A.G., Brenner, S.E., Hubbard, T., Chothia, C.: SCOP: a structural classification of proteins database for the investigation of sequences and structures. J. Mol. Biol. 247, 536–540 (1995)Google Scholar
  12. 12.
    Onoda, T., Murata, H., Yamada, S.: One Class Support Vector Machine based Non-Relevance Feedback Document Retrieval. In: Proc. IEEE Int’l Joint Conf. on Neural Networks (ICJNN), July 31-August 4, 2005, vol. 1, pp. 552–557 (2005)Google Scholar
  13. 13.
    Rangwala, H., Karpys, G.: Profile-based direct kernels for remote homology detection and fold recognition. Bioinformatics 21(23), 4239–4247 (2005)CrossRefGoogle Scholar
  14. 14.
    Saigo, H., et al.: Protein homology detection using string alignment kernels. Bioinformatics 20(11), 1682–1689 (2004)CrossRefGoogle Scholar
  15. 15.
    Schölkopf, B., Platt, J., Shawe-Taylor, J., Smola, A., Williamson, A.: Estimating the support for a high-dimensional distribution. Microsoft Research, One Microsoft Way Redmond WA 98052, Tech. Rep. MSR-TR-99-87 (1999)Google Scholar
  16. 16.
    Söding, J.: Protein homology detection by HMM-HMM comparison. Bioinformatics 21(7), 951–960 (2005)CrossRefGoogle Scholar
  17. 17.
    Spinosa, E.J., de Carvalho, A.C.P.L.F.: Support vector machines for novel class detection in Bioinformatics. Genet. Mol. Res. 4(3), 608–615 (2005)Google Scholar
  18. 18.
    Tax, D.M.J.: One-class classification-concept learning in the absence of counter-examples. Ph.D. Dissertation, Delft University of Technology. ASCI Dissertation Series. Vol. 65, pp. 1–190 (2001)Google Scholar
  19. 19.
    Tress, M.L., et al.: Predicting reliable regions in protein alignments from sequence profiles. Journal of Molecular Biology 330, 705–718 (2003)CrossRefGoogle Scholar
  20. 20.
    Tsirigos, A., Rigoutsos, I.: A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes. Nucleic Acids Research 33(12), 3699–3707 (2005)CrossRefGoogle Scholar
  21. 21.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)MATHGoogle Scholar
  22. 22.
    Zhang, J., Ma, K.-K., Er, M.H., Chong, V.: Tumor Segmentation from Magnetic Resonance Imaging by Learning Via One-Class Support Vector Machine. In: International Workshop on Advanced Image Technology (IWAIT 2004), pp. 207–211 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alexander Senf
    • 1
  • Xue-wen Chen
    • 1
  • Anne Zhang
    • 1
  1. 1.The University of KansasLawrenceUSA

Personalised recommendations