Advertisement

A New Wavelet-Based Approach for Mass Spectrometry Data Classification

  • Achraf Cohen
  • Chaimaa Messaoudi
  • Hassan Badir
Chapter
Part of the ICSA Book Series in Statistics book series (ICSABSS)

Abstract

Proteomic patterns can help the diagnosis of the underlying pathological state of an organ such as the ovary, the lung, and the breast, to name a few. An accurate classification of mass spectrometry is a crucial point to establish a reliable diagnosis and decision process regarding the type of cancer. A statistical methodology for classifying mass spectrometry data is proposed. An overview of wavelets, principal component analysis-T2 statistic, and support vector machines is given. The study is performed on low-mass SELDI spectra derived from patients with breast cancer and from normal controls. There are 156 samples where control (normal) patients contribute with 57 samples and 99 samples are cancer. A hyperparameter optimization is conducted to select a support vector machine classification model based on grid search. The performance was evaluated with a k-fold cross validation technique and Monte-Carlo simulation with 100 replications. The average accuracy is 100% with standard error equals to 0. The averages of the sensitivity and specificity are both equal to 100%, as well as the area under the curve. The excellent performance of our proposed method is mainly due to the statistical modeling and the feature extraction procedure proposed.

References

  1. Aebersold, R., & Mann, M. (2003). Mass spectrometry-based proteomics. Nature, 422(6928), 198–207.CrossRefGoogle Scholar
  2. Awedat, K., Abdel-Qader, I., & Springstead, J. R. (2016). Mass spectrometry sensing data for robust cancer classification. In Electro Information Technology (EIT), 2016 IEEE International Conference on (pp. 0258–0262). Piscataway: IEEE.Google Scholar
  3. Cohen, A., Daubechies, I., & Feauveau, J.-C. (1992). Biorthogonal bases of compactly supported wavelets. Communications on Pure and Applied Mathematics, 45(5), 485–560.MathSciNetzbMATHCrossRefGoogle Scholar
  4. Cortes, C., & Vapnik, V. (1995). Support vector networks. Machine Learning, 20(3), 273–297.zbMATHGoogle Scholar
  5. Cravatt, B. F., Simon, G. M., & Yates Iii, J. R. (2007). The biological impact of mass-spectrometry-based proteomics. Nature, 450(7172), 991.CrossRefGoogle Scholar
  6. Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge: Cambridge University Press.zbMATHCrossRefGoogle Scholar
  7. Das, S. (2001). Filters, wrappers and a boosting-based hybrid for feature selection. In ICML (Vol. 1, pp. 74–81).Google Scholar
  8. Daubechies, I. (1992). Ten lectures on wavelets. Philadelphia, PA: Society for Industrial and Applied Mathematics.zbMATHCrossRefGoogle Scholar
  9. de Noo, M. E., Mertens, B. J., Özalp, A., Bladergroen, M. R., van der Werff, M. P., van de Velde, C. J., et al. (2006). Detection of colorectal cancer using maldi-tof serum protein profiling. European Journal of Cancer, 42(8), 1068–1076.CrossRefGoogle Scholar
  10. Diamandis, E. P. (2004). Mass spectrometry as a diagnostic and a cancer biomarker discovery tool opportunities and potential limitations. Molecular & Cellular Proteomics, 3(4), 367–378.CrossRefGoogle Scholar
  11. Donoho, D. (1995). De-noising by soft-thresholding. IEEE Transactions on Information Theory, 41(3), 613–627.MathSciNetzbMATHCrossRefGoogle Scholar
  12. Donoho, D. L., & Johnstone, J. M. (1994). Ideal spatial adaptation by wavelet shrinkage. Biometrika, 81(3), 425–455.MathSciNetzbMATHCrossRefGoogle Scholar
  13. Donoho, D. L., & Johnstone, J. M. (1995). Adapting to unknown smoothness via wavelet shrinkage. Jouranl of the American Statistical Association, 90, 1200–1224.MathSciNetzbMATHCrossRefGoogle Scholar
  14. Du, J., Wu, X.-M., Wang, B., Su, H.-J., Ma, K., & Zhang, H.-Q. (2009). Wavelet transform and bagging predictor approaches to cancer identification from mass spectrometry-based proteomic data. In Bioinformatics and Biomedical Engineering, 2009. ICBBE 2009. 3rd International Conference on (pp. 1–4). Piscataway: IEEE.Google Scholar
  15. Dubitzky, W., Granzow, M., & Berrar, D. P. (2007). Fundamentals of data mining in genomics and proteomics. Berlin: Springer Science and Business Media.zbMATHCrossRefGoogle Scholar
  16. Gao, H.-Y. (1998). Wavelet shrinkage denoising using the non-negative garrote. Journal of Computational and Graphical Statistics, 7(4), 469–488.MathSciNetGoogle Scholar
  17. Gao, H.-Y., & Bruce, A. G. (1997). Waveshrink with firm shrinkage. Statistica Sinica, 7(4), 855–874.MathSciNetzbMATHGoogle Scholar
  18. Ge, G., & Wong, G. W. (2008). Classification of premalignant pancreatic cancer mass-spectrometry data using decision tree ensembles. BMC Bioinformatics, 9(1), 275.CrossRefGoogle Scholar
  19. Gromski, P. S., Xu, Y., Correa, E., Ellis, D. I., Turner, M. L., & Goodacre, R. (2014). A comparative investigation of modern feature selection and classification approaches for the analysis of mass spectrometry data. Analytica Chimica Acta, 829, 1–8.CrossRefGoogle Scholar
  20. Jolliffe, I. T. (1986). Principal component analysis and factor analysis. In Principal component analysis (pp. 115–128). Berlin: Springer.CrossRefGoogle Scholar
  21. Lancashire, L. J., Lemetre, C., & Ball, G. R. (2009). An introduction to artificial neural networks in bioinformatics—application to complex microarray and mass spectrometry datasets in cancer studies. Briefings in Bioinformatics, 10, 315–329.  https://doi.org/10.1093/bib/bbp012.CrossRefGoogle Scholar
  22. Li, Y., & Zeng, X. (2016). Serum seldi-tof ms analysis model applied to benign and malignant ovarian tumor identification. Analytical Methods, 8(1), 183–188.CrossRefGoogle Scholar
  23. Mallat, S. G. (1989). A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(7), 674–693.zbMATHCrossRefGoogle Scholar
  24. Misiti, M., Misiti, Y., Oppenheim, G., & Poggi, J. (1996). Wavelet toolbox. Natick, MA: The MathWorks Inc.zbMATHGoogle Scholar
  25. Morris, J. S., Brown, P. J., Baggerly, K. A., & Coombes, K. R. (2006). Analysis of mass spectrometry data using bayesian wavelet-based functional mixed models. In Bayesian inference for gene expression and proteomics (pp. 269–288). Cambridge: Cambridge University Press.CrossRefGoogle Scholar
  26. Nguyen, T., Nahavandi, S., Creighton, D., & Khosravi, A. (2015). Mass spectrometry cancer data classification using wavelets and genetic algorithm. FEBS Letters, 589(24), 3879–3886.CrossRefGoogle Scholar
  27. Ohn, S.-Y., Chi, S.-D., & Heo, C. (2016). Identification of breast cancer by classification of proteome patterns. International Journal of Modeling, Simulation, and Scientific Computing, 7(04), 1643004.CrossRefGoogle Scholar
  28. P. Datasets for Breast Cancer (2004). http://bioinformatics.mdanderson.org/pubdata.html.
  29. Petricoin, E. F., Ardekani, A. M., Hitt, B. A., Levine, P. J., Fusaro, V. A., Steinberg, S. M., et al. (2002). Use of proteomic patterns in serum to identify ovarian cancer. The Lancet, 359(9306), 572–577.CrossRefGoogle Scholar
  30. Schleif, F.-M., Lindemann, M., Diaz, M., Maaß, P., Decker, J., Elssner, T., et al. (2009). Support vector classification of proteomic profile spectra based on feature extraction with the bi-orthogonal discrete wavelet transform. Computing and Visualization in Science, 12(4), 189–199.MathSciNetCrossRefGoogle Scholar
  31. Sharma, A., & Singh, S. (2016). Neural network for diagnosis of ovarian cancer based on proteomic patterns in serum. Journal of Scientific and Technical Advancements, 2(2), 25–27.Google Scholar
  32. Shawe-Taylor, J. & Cristianini, N. (2004). Kernel methods for pattern analysis. Cambridge: Cambridge University Press.zbMATHCrossRefGoogle Scholar
  33. Tang, K.-L., Li, T.-H., Xiong, W.-W., & Chen, K. (2010). Ovarian cancer classification based on dimensionality reduction for seldi-tof data. BMC Bioinformatics, 11(1), 109.CrossRefGoogle Scholar
  34. Vapnik, V. (2013). The nature of statistical learning theory. Berlin: Springer Science and Business Media.zbMATHGoogle Scholar
  35. Ward, D. G., Nyangoma, S., Joy, H., Hamilton, E., Wei, W., Tselepis, C., et al. (2008). Proteomic profiling of urine for the detection of colon cancer. Proteome Science, 6(1), 19.CrossRefGoogle Scholar
  36. Wu, J., Ji, Y., Zhao, L., Ji, M., Ye, Z., & Li, S. (2016). A mass spectrometric analysis method based on ppca and svm for early detection of ovarian cancer. Computational and Mathematical Methods in Medicine, 2016, 6169249.Google Scholar
  37. Yildiz, P. B., Shyr, Y., Rahman, J. S., Wardwell, N. R., Zimmerman,L. J., Shakhtour, B., et al. (2007). Diagnostic accuracy of maldi mass spectrometric analysis of unfractionated serum in lung cancer. Journal of Thoracic Oncology, 2(10), 893–901.CrossRefGoogle Scholar
  38. Yu, J., Ongarello, S., Fiedler, R., Chen, X., Toffolo, G., Cobelli, C., et al. (2005). Ovarian cancer identification based on dimensionality reduction for high-throughput mass spectrometry data. Bioinformatics, 21(10), 2200–2209.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Mathematics and StatisticsUniversity of West FloridaPensacolaUSA
  2. 2.National School of Applied Sciences-Tangier, ENSATAbdelmalek Essaadi UniversityTangierMorocco

Personalised recommendations