Application of Combining Classifiers Using Dynamic Weights to the Protein Secondary Structure Prediction – Comparative Analysis of Fusion Methods

  • Tomasz Woloszynski
  • Marek Kurzynski
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4345)


We introduce common framework for classifiers fusion methods using dynamic weights in decision making process. Both weighted average combiners with dynamic weights and combiners which dynamically estimate local competence are considered. Few algorithms presented in the literature are shown in accordance with our model. In addition we propose two new methods for combining classifiers. The problem of protein secondary structure prediction was selected as a benchmark test. Experiments were carried out on previously prepared dataset of non-homologous proteins for fusion algorithms comparison. The results have proved that developed framework generalizes dynamic weighting approaches and should be further investigated.


Fusion Method Secondary Structure Prediction Protein Secondary Structure Pattern Recognition Problem Dynamic Weight 
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.
    Akkaladevi, S., Balkasim, M., Pan, Y.: Protein Secondary Structure Prediction Using Neural Network and Simulated Annealing Algorithm. In: Proc. 26th Int. Conf. of the IEEE EMBS, pp. 2987–2990. San Francisco (2004)Google Scholar
  2. 2.
    Aydin, Z., Altunbasak, Y., Borodovsky, M.: Protein Secondary Structure Prediction with Semi Markov HMMS. In: Proc. 26th Int. Conf. of the IEEE EMBS, pp. 2964–2967. San Francisco (2004)Google Scholar
  3. 3.
    Bermann, H., Westbrock, Z., Feng, G., et al.: The Protein Data Bank. Nucleic Acid Res. 2, 235–242 (2000)CrossRefGoogle Scholar
  4. 4.
    Bridle, J.: Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters. In: Touretzky, D. (ed.) Neural Information Processing Systems, vol. 2, pp. 211–217. Morgan Kaufmann, San Mateo, CA (1990)Google Scholar
  5. 5.
    Combet, C., Blanchet, C., Geourjon, C., Deleage, G.: NPS@: Network Protein Sequence Analysis. TIBS 25(3), 147–150 (2000)Google Scholar
  6. 6.
    Garnier, J., Gibrat, J.-F., Robson, B.: GOR secondary structure prediction method version IV. In: Doolittle, R.F. (ed.) Methods in Enzymology, vol. 266, pp. 540–553 (1996)Google Scholar
  7. 7.
    Geourjon, C., Deleage, G.: SOPMA: Significant improvements in protein secondary structure prediction by consensus prediction from multiple alignments. Comput. Appl. Biosci. 681–684 (1995)Google Scholar
  8. 8.
    Giacinto, G., Roli, F.: Design of effective neural network ensembles for image classification processes. Image Vision and Computing Journal, 699–707 (2001)Google Scholar
  9. 9.
    Guermeur, Y.: Combinaison de classifieurs statistiques, Application a la prediction de structure secondaire des proteines, PhD ThesisGoogle Scholar
  10. 10.
    Guermeur, Y.: Combining discriminant models with new multi-class SVMs. Pattern Analysis & Applications 5, 168–179 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Henikoff, S., Henikoff, J.G.: Amino acid substitution matrices from protein blocks. PNAS USA, 10915–10919 (1992)Google Scholar
  12. 12.
    Hobohum, U., Sanders, C.: Enlarged representative set of protein structures. Protein Science 522 (1994)Google Scholar
  13. 13.
    Jones, D.: Protein Secondary Structure Prediction Based on Position-Specific Scoring Matrices. J. Mol. Biol. 292, 397–407 (1999)CrossRefGoogle Scholar
  14. 14.
    Kabsch, W., Sanders, C.: Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers, 2577–2637 (1983)Google Scholar
  15. 15.
    Krierger, E., Hooft, R., Nabuurs, S., Vriend, G.: PDBFinderII - a database for protein structure analysis and prediction (2004)Google Scholar
  16. 16.
    Kuncheva, L.: A theoretical study on six classifier fusion strategies. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(2), 281–286 (2002)CrossRefGoogle Scholar
  17. 17.
    Kuncheva, L.: Combining pattern classifiers: methods and algorithms. John Wiley & Sons, New Jersey (2004)zbMATHCrossRefGoogle Scholar
  18. 18.
    Selbig, J., Mevissen, T., Lenguaer, T.: Decision-tree Based Formation on Consensus Secondary Structure Prediction. Bioinformatics 15, 1039–1046 (1999)CrossRefGoogle Scholar
  19. 19.
    Wang, L., Liu, J., Zhou, H.: A Comparison of Two Machine Learning Methods for Protein Secondary Structure Prediction. In: Proc. 3rd Int. Conf. on Machine Learning and Cybernetics, pp. 2730–2735. Shanghai (2004)Google Scholar
  20. 20.
    Xiaochung, Y., Wang, B.: A Protein Secondary Structure Prediction Framework Based on the Support Vector Machine. In: Dong, G., Tang, C.-j., Wang, W. (eds.) WAIM 2003. LNCS, vol. 2762, pp. 266–277. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  21. 21.
    Xu, H., Lau, K., Lu, L.: Protein Secondary Structure Prediction Using Data Mining Tool C5. In: Proc. 11th IEEE Int. Conf. on Tools in AI, pp. 107–110. Chicago (1999)Google Scholar
  22. 22.
    Zaki, M., Shan, J., Bystroff, C.: Mining Residue Contacts in Protein Using Local Structure Prediction. IEEE Trans. on SMC 33, 258–264 (2003)Google Scholar
  23. 23.
    Zemla, A., Venclovas, C., Fidelis, K., Rost, B.: Some measures of comparative performance in the tree casps. PROTEINS: Structure, Function, and Genetics, 220–223 (1999)Google Scholar
  24. 24.
    Zhang, B., Chen, Z., Murphey, Y.: Protein Secondary Structure Prediction Using Machine Learning. In: Proc. IEEE Int. Conf. on Neural Networks, Montreal, pp. 532–537 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tomasz Woloszynski
    • 1
  • Marek Kurzynski
    • 1
  1. 1.Faculty of Electronics, Chair of Systems and Computer NetworksWroclaw University of TechnologyWroclawPoland

Personalised recommendations