Applying Kernel Methods on Protein Complexes Detection Problem

  • Charalampos Moschopoulos
  • Griet Laenen
  • George Kritikos
  • Yves Moreau
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 311)


During the last years, various methodologies have made possible the detection of large parts of the protein interaction network of various organisms. However, these networks are containing highly noisy data, degrading the quality of information they carry. Various weighting schemes have been applied in order to eliminate noise from interaction data and help bioinformaticians to extract valuable information such as the detection of protein complexes. In this contribution, we propose the addition of an extra step on these weighting schemes by using kernel methods to better assess the reliability of each pairwise interaction. Our experimental results prove that kernel methods clearly help the elimination of noise by producing improved results on the protein complexes detection problem.


kernel methods protein-protein interactions protein interaction graphs protein complexes 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bader, G.D., Hogue, C.W.: An automated method for finding molecular complexes in large protein interaction networks. BMC Bioinformatics 4, 2 (2003)CrossRefGoogle Scholar
  2. 2.
    King, A.D., Przulj, N., Jurisica, I.: Protein complex prediction via cost-based clustering. Bioinformatics 20(17), 3013–3020 (2004)CrossRefGoogle Scholar
  3. 3.
    Sharan, R., Ulitsky, I., Shamir, R.: Network-based prediction of protein function. Mol. Syst. Biol. 3, 88 (2007)CrossRefGoogle Scholar
  4. 4.
    Yu, J., Finley Jr., R.L.: Combining multiple positive training sets to generate confidence scores for protein-protein interactions. Bioinformatics 25(1), 105–111 (2009)CrossRefGoogle Scholar
  5. 5.
    Brun, C., et al.: Functional classification of proteins for the prediction of cellular function from a protein-protein interaction network. Genome Biol. 5(1), R6 (2003)Google Scholar
  6. 6.
    Patil, A., Nakamura, H.: Filtering high-throughput protein-protein interaction data using a combination of genomic features. BMC Bioinformatics 6(1), 100 (2005)CrossRefGoogle Scholar
  7. 7.
    Samanta, M.P., Liang, S.: Predicting protein functions from redundancies in large-scale protein interaction networks. Proc. Natl. Acad. Sci. USA 100(22), 12579–12583 (2003)CrossRefGoogle Scholar
  8. 8.
    Liu, G., Wong, L., Chua, H.N.: Complex discovery from weighted PPI networks. Bioinformatics 25(15), 1891–1897 (2009)CrossRefGoogle Scholar
  9. 9.
    Chua, H.N., Sung, W.K., Wong, L.: Exploiting indirect neighbours and topological weight to predict protein function from protein-protein interactions. Bioinformatics 22(13), 1623–1630 (2006)CrossRefGoogle Scholar
  10. 10.
    Kritikos, G.D., et al.: Noise reduction in protein-protein interaction graphs by the implementation of a novel weighting scheme. BMC Bioinformatics 12, 239 (2011)CrossRefGoogle Scholar
  11. 11.
    Enright, A.J., Van Dongen, S., Ouzounis, C.A.: An efficient algorithm for large-scale detection of protein families. Nucleic Acids Res. 30(7), 1575–1584 (2002)CrossRefGoogle Scholar
  12. 12.
    Moschopoulos, C.N., et al.: An enchanced Markov clustering method for detecting protein complexes. In: 8th IEEE International Conference on BioInformatics and BioEngineering (BIBE 2008), Athens (2008)Google Scholar
  13. 13.
    Razick, S., Magklaras, G., Donaldson, I.M.: iRefIndex: a consolidated protein interaction database with provenance. BMC Bioinformatics 9, 405 (2008)CrossRefGoogle Scholar
  14. 14.
    Wu, M., et al.: A core-attachment based method to detect protein complexes in PPI networks. BMC Bioinformatics 10, 169 (2009)CrossRefGoogle Scholar
  15. 15.
    Mewes, H.W., et al.: MIPS: analysis and annotation of proteins from whole genomes in 2005. Nucleic Acids Res. 34(Database issue), D169–D172 (2006)Google Scholar
  16. 16.
    Kandola, N., Cristianini, N., Shawe-Taylor, J.: Learning semantic similarity. In: Advances in Neural Information Processing Systems, pp. 657–664 (2002)Google Scholar
  17. 17.
    Kondor, R., Lafferty, J.: Diffusion kernels on graphs and other discrete structures. In: Proceedings of the Nineteenth International Conference on Machine Learning (2002)Google Scholar
  18. 18.
    Brohee, S., van Helden, J.: Evaluation of clustering algorithms for protein-protein interaction networks. BMC Bioinformatics 7, 488 (2006)CrossRefGoogle Scholar
  19. 19.
    Moschopoulos, C., et al.: Which clustering algorithm is better for predicting protein complexes? BMC Research Notes 4(1), 549 (2011)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Charalampos Moschopoulos
    • 1
    • 2
  • Griet Laenen
    • 1
    • 2
  • George Kritikos
    • 3
    • 4
  • Yves Moreau
    • 1
    • 2
  1. 1.Department of Electrical Engineering-ESAT, SCD-SISTAKatholieke Universiteit LeuvenLeuvenBelgium
  2. 2.IBBT Future Health DepartmentKatholieke Universiteit LeuvenLeuvenBelgium
  3. 3.Bioinformatics & Medical Informatics Team, Biomedical Research FoundationAcademy of AthensAthensGreece
  4. 4.Department of Genome BiologyEMBL - European Molecular Biology LaboratoryHeidelbergGermany

Personalised recommendations