Leukemia Prediction from Gene Expression Data—A Rough Set Approach

  • Jianwen Fang
  • Jerzy W. Grzymala-Busse
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4029)


We present our results on the prediction of leukemia from microarray data. Our methodology was based on data mining (rule induction) using rough set theory. We used a novel methodology based on rule generations and cumulative rule sets. The final rule set contained only eight rules, using some combinations of eight genes. All cases from the training data set and all but one cases from the testing data set were correctly classified. Moreover, six out of eight genes found by us are well known in the literature as relevant to leukemia.


Acute Myeloid Leukemia Rule Induction Matching Rule Bayesian Model Average Data Mining System 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Booker, L.B., Goldberg, D.E., Holland, J.F.: Classifier systems and genetic algorithms. In: Carbonell, J.G. (ed.) Machine Learning. Paradigms and Methods, pp. 235–282. The MIT Press, Menlo Park (1990)Google Scholar
  2. 2.
    Broberg, P.: Statistical methods for ranking differentially expressed genes. Genome Biology 4 (2003), http://genomebiology.com
  3. 3.
    Chu, W., Ghahramani, Z., Falciani, F., Wild, D.L.: Biomarker discovery in microarray gene expression data with Gaussian processes. Bioinformatics 21, 3385–3393 (2005)CrossRefGoogle Scholar
  4. 4.
    Cohen, A.J., Franklin, W.A., Magill, C., Sorenson, J., Miller, Y.E.: Low neutral endopeptidase levels in bronchoalveolar lavage fluid of lung cancer patients. American Journal of Respiratory and Critical Care Medicine 159, 907–910 (1999)Google Scholar
  5. 5.
    Golub, T.R., Slonim, D.K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J.P., Coller, H., Loh, M.L., Downing, J.R., Caligiuri, M.A., et al.: Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring. Science 286, 531–537 (1999)CrossRefGoogle Scholar
  6. 6.
    Grzymala-Busse, J.W.: Knowledge acquisition under uncertainty—A rough set approach. Journal of Intelligent & Robotic Systems 1, 3–16 (1988)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Grzymala-Busse, J.W.: LERS—A system for learning from examples based on rough sets. In: Slowinski, R. (ed.) Intelligent Decision Support. Handbook of Applications and Advances of the Rough Sets Theory, pp. 3–18. Kluwer Academic Publishers, Dordrecht (1992)Google Scholar
  8. 8.
    Grzymala-Busse, J.W.: A new version of the rule induction system LERS. Fundamenta Informaticae 31, 27–39 (1997)MATHGoogle Scholar
  9. 9.
    Grzymala-Busse, J.W.: MLEM2: A new algorithm for rule induction from imperfect data. In: Proceedings of the 9th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2002, July 1–5, 2002, Annecy, France, pp. 243–250 (2002)Google Scholar
  10. 10.
    Grzymala-Busse, J.W., Goodwin, L.K., Grzymala-Busse, W.J., Zheng, X.: An approach to imbalanced data sets based on changing rule strength. In: Learning from Imblanced Data Sets, AAAI Workshop at the 17th Conference on AI, AAAI-2000, Austin, TX, July 30–31, 2000, pp. 69–74 (2000)Google Scholar
  11. 11.
    Holland, J.H., Holyoak, K.J., Nisbett, R.E.: Induction. Processes of Inference, Learning, and Discovery. The MIT Press, Menlo Park (1986)Google Scholar
  12. 12.
    Jirapech-Umpai, T., Aitken, S.: Feature selection and classification for microarray data analysis: Evolutionary methods for identifying predictive genes. BMC Bioinformatics 6 (2005), http://www.biomedcentral.com
  13. 13.
    Kuopio, T., Kankaanranta, A., Jalava, P., Kronqvist, P., Kotkansalo, T., Weber, E., Collan, Y.: Cysteine proteinase inhibitor cystatin A in breast cancer. Cancer Research 58, 432–436 (1998)Google Scholar
  14. 14.
    Lee, K.E., Sha, N.J., Dougherty, E.R., Vannucci, M., Mallick, B.K.: Gene selection: a Bayesian variable selection approach. Bioinformatics 19, 90–97 (2003)CrossRefGoogle Scholar
  15. 15.
    Mori, N., Murakami, Y.I., Shimada, S., Iwamizu-Watanabe, S., Yamashita, Y., Hasegawa, Y., Kojima, H., Nagasawa, T.: TIA-1 expression in hairy cell leukemia. Modern Pathology 17, 840–846 (2004)CrossRefGoogle Scholar
  16. 16.
    Nguyen, D.V., Rocke, D.M.: Tumor classification by partial least squares using microarray gene expression data. Bioinformatics 18, 39–50 (2002)CrossRefGoogle Scholar
  17. 17.
    Pawlak, Z.: Rough Sets. International Journal of Computer and Information Sciences 11, 341–356 (1982)MATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Pawlak, Z.: Rough Sets. In: Theoretical Aspects of Reasoning about Data, Kluwer Academic Publishers, Dordrecht (1991)Google Scholar
  19. 19.
    Sakhinia, E., Faranghpour, M., Yin, J.A.L., Brady, G., Hoyland, J.A., Byers, R.J.: Routine expression profiling of microarray gene signatures in acute leukaemia by real-time PCR of human bone marrow. British Journal of Haematology 130, 233–248 (2005)CrossRefGoogle Scholar
  20. 20.
    Souza, D.G., Soares, A.C., Pinho, V., Torloni, H., Reis, L.F.L., Martins, M.T., Dias, A.A.M.: Increased mortality and inflammation in tumor necrosis factor-stimulated gene-14 transgenic mice after ischemia and reperfusion injury. American Journal of Pathology 160, 1755–1765 (2002)CrossRefGoogle Scholar
  21. 21.
    Thomas, J.G., Olson, J.M., Tapscott, S.J., Zhao, L.P.: An efficient and robust statistical modeling approach to discover differentially expressed genes using genomic expression profiles. Genome Research 11, 1227–1236 (2001)CrossRefGoogle Scholar
  22. 22.
    Vinterbo, S.A., Kim, E.Y., Ohno-Machado, L.: Small, fuzzy and interpretable gene expression based classifiers. Bioinformatics 21, 1964–1970 (2005)CrossRefGoogle Scholar
  23. 23.
    Wadman, I., Li, J.X., Bash, R.O., Forster, A., Osada, H., Rabbitts, T.H., Baer, R.: Specific in-vivo association between the Bhlh and Lim proteins implicated in human T-cell leukemia. EMBO Journal 13, 4831–4839 (1994)Google Scholar
  24. 24.
    Yeung, K.Y., Bumgarner, R.E., Raftery, A.E.: Bayesian model averaging: development of an improved multi-class, gene selection and classification tool for microarray data. Bioinformatics 21, 2394–2402 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jianwen Fang
    • 1
  • Jerzy W. Grzymala-Busse
    • 2
    • 3
  1. 1.Bioinformatics Core Facility, and Information and Telecommunication Technology CenterUniversity of KansasLawrenceUSA
  2. 2.Department of Electrical Engineering and Computer ScienceUniversity of KansasLawrenceUSA
  3. 3.Institute of Computer Science Polish Academy of SciencesWarsawPoland

Personalised recommendations