Mass Spectrometry Based Cancer Classification Using Fuzzy Fractal Dimensions

  • Tuan D. Pham
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

Cancer classification using high-throughput mass spectrometry data for early disease detection and prevention has recently become an attractive topic of research in bioinformatics. Recently, several studies have shown that the synergy of proteomic technology and pattern classification techniques is promising for the predictive diagnoses of several cancer diseases. However, the extraction of some effective features that can represent the identities of different classes plays a critical factor for any classification problems involving the analysis of complex data. In this paper we present the concept of a fuzzy fractal dimension that can be utilized as a novel feature of mass spectrometry (MS) data. We then apply vector quantization (VQ) to model the class prototyes using the fuzzy fractal dimensions for classification. The proposed methodology was tested with an MS-based ovarian cancer dataset. Using a simple VQ-based classification rule, the overall average classification rates of the proposed approach were found to be superior to some other methods.

Keywords

Feature extraction fuzzy fractal dimension fuzzy c-means vector quantization mass spectrometry data cancer classification 

References

  1. 1.
    Griffin, T., Goodlett, D., Aebersold, R.: Advances in proteomic analysis by mass spectrometry. Curr. Opin. Biotechnol. 12, 607–612 (2001)CrossRefGoogle Scholar
  2. 2.
    Aebersold, R., Mann, M.: Mass spectrometry-based proteomics. Nature 422, 198–207 (2003)CrossRefGoogle Scholar
  3. 3.
    Petricoin, E.F., et al.: Use of proteomic patterns in serum to identify ovarian cancer. Lancet 359, 572–577 (2002)CrossRefGoogle Scholar
  4. 4.
    Conrads, T.P., Zhou, M., Petricoin III, E.F., Liotta, I.L., Veenstra, T.D.: Cancer diagnosis using proteomic patterns. Expert Rev. Mol. Diagn. 3, 411–420 (2003)CrossRefGoogle Scholar
  5. 5.
    Petricoin, E.F., Liotta, L.A.: Mass spectrometry-based diagnostics: The upcoming revolution in disease detection. Clinical Chemistry 49, 533–534 (2003)CrossRefGoogle Scholar
  6. 6.
    Wulfkuhle, J.D., Liotta, L.A., Petricoin, E.F.: Proteomic applications for the early detection of cancer. Nature 3, 267–275 (2003)Google Scholar
  7. 7.
    Lilien, R.H., Farid, H., Donald, B.R.: Probabilistic disease classification of expression-dependent proteomic data from mass spectrometry of human serum. J. Computational Biology 10, 925–946 (2003)CrossRefGoogle Scholar
  8. 8.
    Wu, B., Abbott, T., Fishman, D., McMurray, W., Mor, G., Stone, K., Ward, D., Williams, K., Zhao, H.: Comparison of statistical methods for classification of ovarian cancer using mass spectrometry data. Bioinformatics 19, 1636–1643 (2003)CrossRefGoogle Scholar
  9. 9.
    Tibshirani, R., Hastie, T., Narasimhan, B., Soltys, S., Shi, G., Koong, A.: Sample classification from protein mass spectrometry, by ‘peak probability contrasts’. Bioinformatics 20, 3034–3044 (2004)CrossRefGoogle Scholar
  10. 10.
    Morris, J.S., Coombes, K.R., Koomen, J., Baggerly, K.A., Kobayashi, R.: Feature extraction and quantification for mass spectrometry in biomedical applications using the mean spectrum. Bioinformatics 21, 1764–1775 (2005)CrossRefGoogle Scholar
  11. 11.
    Yu, J.S., Ongarello, S., Fiedler, R., Chen, X.W., Toffolo, G., Cobelli, C., Trajanoski, Z.: Ovarian cancer identification based on dimensionality reduction for high-throughput mass spectrometry data. Bioinformatics 21, 2200–2209 (2005)CrossRefGoogle Scholar
  12. 12.
    Mandelbrot, B.B.: How long is the coast of Britain? Statistical self-similarity and fractional dimension. Science 156, 636–638 (1967)CrossRefGoogle Scholar
  13. 13.
    Liebovitch, L.S.: Chaos Simplified for the Life Sciences. Oxford University Press, New York (1998)MATHGoogle Scholar
  14. 14.
    Hastings, H.M., Sugihara, G.: Fractals A User’s Guide for the Natural Sciences. Oxford University Press, New York (1993)Google Scholar
  15. 15.
    Lovejoy, S.: Area-perimeter relation for rain and cloud areas. Science 216, 185 (1982)CrossRefGoogle Scholar
  16. 16.
    Sun, W., Xu, G., Gong, P., Liang, S.: Fractal analysis of remotely sensed images: A review of methods and applications. Int. J. Remote Sensing 27, 4963–4990 (2006)CrossRefGoogle Scholar
  17. 17.
    Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York (1981)MATHGoogle Scholar
  18. 18.
    Linde, Y., Buzo, A., Gray, R.M.: An Algorithm for Vector Quantization. IEEE Trans. Communications 28, 84–95 (1980)CrossRefGoogle Scholar
  19. 19.
    Pham, T.D., Chandramohan, V., Zhou, X., Wong, S.T.C.: Robust feature extraction and reduction of mass spectrometry data for cancer classification. In: Proc. IEEE-ICDM Workshop on Data Mining in Bioinformatics, pp. 202–206 (2006)Google Scholar
  20. 20.
    Ginsburg, G.S., McCarthy, J.J.: Personalized medicine: revolutionizing drug discovery and patient care. Trends Biotechnol. 19, 491–496 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Tuan D. Pham
    • 1
  1. 1.Bioinformatics Applications Research Center, School of Mathematics, Physics, and Information Technology, James Cook University, Townsville, QLD 4811Australia

Personalised recommendations