Application of the Multi-modal Relevance Vector Machine to the Problem of Protein Secondary Structure Prediction

  • Nikolay Razin
  • Dmitry Sungurov
  • Vadim Mottl
  • Ivan Torshin
  • Valentina Sulimova
  • Oleg Seredin
  • David Windridge
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7632)


The aim of the paper is to experimentally examine the plausibility of Relevance Vector Machines (RVM) for protein secondary structure prediction. We restrict our attention to detecting strands which represent an especially problematic element of the secondary structure. The commonly adopted local principle of secondary structure prediction is applied, which implies comparison of a sliding window in the given polypeptide chain with a number of reference amino-acid sequences cut out of the training proteins as benchmarks representing the classes of secondary structure. As distinct from the classical RVM, the novel version applied in this paper allows for selective combination of several tentative window comparison modalities. Experiments on the RS126 data set have shown its ability to essentially decrease the number of reference fragments in the resulting decision rule and to select a subset of the most appropriate comparison modalities within the given set of the tentative ones.


Protein secondary structure prediction machine learning multimodal relational pattern recognition Relevance Vector Machine controlled selectivity of reference objects object-comparison modalities 


  1. 1.
    Branden, C., Tooze, J.: Introduction to Protein Structure, 2nd edn., p. 410. Garland Publishing, Inc., New York (1999)Google Scholar
  2. 2.
    Rost, B.: Protein secondary structure prediction continues to rise. Journal of Structural Biology 134(2-3), 204–218 (2001)CrossRefGoogle Scholar
  3. 3.
    Yoo, P., Zhou, B., Zomaya, A.: Machine learning techniques for protein secondary structure prediction: An overview and evaluation. Current Bioinformatics 3(2), 74–86 (2008)CrossRefGoogle Scholar
  4. 4.
    Critical Assessment of the Protein Structure Prediction. Protein Structure Prediction Center. Sponsored by the US National Library of Medicine (NIH/NLM),
  5. 5.
    Aloy, P., Stark, A., Hadley, C., Russell, R.: Predictions without templates: new folds, secon-dary structure, and contacts in CASP5. Proteins 53(suppl. 6), 436–456 (2003)CrossRefGoogle Scholar
  6. 6.
    Torshin, I.Y.: Bioinformatics in the Post-Genomic Era: The Role of Biophysics. Nova Biomedical Books, NY (2007) ISBN: 1-60021-048Google Scholar
  7. 7.
    Vapnik, V.: Statistical Learning Theory, p. 736. John-Wiley & Sons, Inc. (1998)Google Scholar
  8. 8.
    Ward, J., McGuffin, L., Buxton, B., Jones, D.: Secondary structure prediction with support vector machines. Bioinformatics 19(13), 1650–1655 (2003)CrossRefGoogle Scholar
  9. 9.
    Bishop, C., Tipping, M.: Variational Relevance Vector Machines. In: Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, pp. 46–53. Morgan Kaufmann (2000)Google Scholar
  10. 10.
    Seredin, O., Mottl, V., Tatarchuk, A., Razin, N., Windridge, D.: Convex Support and Relevance Vector Machines for selective multimodal pattern recognition. In: The 21th International Conference on Pattern Recognition, Tsukuba Science City, Japan, November 11-15 (2012)Google Scholar
  11. 11.
    Engel, D., DeGrado, W.: Amino acid propensities are position-dependent throughout the length of α-helices. J. Mol. Biol. 337, 1195–1205 (2004)CrossRefGoogle Scholar
  12. 12.
    Ni, Y., Niranjan, M.: Exploiting long-range dependencies in protein β-sheet secondary structure prediction. In: Proceedings of the 5th IAPR International Conference on Pattern Recognition in Bioinformatics, Nijmegen, The Netherlands, September 22-24, pp. 349–357 (2010)Google Scholar
  13. 13.
    Cole, C., Barber, J., Barton, G.: The Jpred 3 secondary structure prediction server. Nucl. Acids Res. 36 (suppl. 2), W197–W201 (2008)Google Scholar
  14. 14.
    Duin, R., Pekalska, E., de Ridder, D.: Relational discriminant analysis. Pattern Recognition Letters 20, 1175–1181 (1999)CrossRefGoogle Scholar
  15. 15.
    Wang, L., Zhu, J., Zou, H.: The doubly regularized support vector machine. Statistica Sinica 16, 589–615 (2006)MathSciNetzbMATHGoogle Scholar
  16. 16.
    Dayhoff, M., Schwarts, R., Orcutt, B.: A model of evolutionary change in proteins. Atlas of Protein Sequences and Structures 5(suppl. 3), 345–352 (1978)Google Scholar
  17. 17.
    Sulimova, V., Mottl, V., Kulikowski, C., Muchnik, I.: Probabilistic evolutionary model for substitution matrices of PAM and BLOSUM families. DIMACS Technical Report 2008-16, Rutgers University, p. 17 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Nikolay Razin
    • 1
  • Dmitry Sungurov
    • 1
  • Vadim Mottl
    • 2
  • Ivan Torshin
    • 2
  • Valentina Sulimova
    • 3
  • Oleg Seredin
    • 3
  • David Windridge
    • 4
  1. 1.Moscow Institute of Physics and TechnologyMoscowRussia
  2. 2.Computing Center of the Russian Academy of SciencesMoscowRussia
  3. 3.Tula State UniversityTulaRussia
  4. 4.University of SurreyGuildfordUK

Personalised recommendations