A New Gene Selection Method for Microarray Data Based on PSO and Informativeness Metric

  • Jian Guan
  • Fei Han
  • Shanxiu Yang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7996)


In this paper, a new method encoding a priori information of informativeness metric of microarray data into particle swarm optimization (PSO) is proposed to select informative genes. The informativeness metric is an analysis of variance statistic that represents the regulation hide in the microarray data. In the new method, the informativeness metric is combined with the global searching algorithms PSO to perform gene selection. The genes selected by the new method reveal the data structure highly hided in the microarray data and therefore improve the classification accuracy rate. Experiment results on two microarray datasets achieved by the proposed method verify its effectiveness and efficiency.


Gene selection particle swarm optimization informativeness metric extreme learning machine 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Saeys, Y., Inza, I., Larranaga, P.: A review of feature selection techniques in bioinformatics. Bioinformatics 23(19), 2507–2517 (2007)CrossRefGoogle Scholar
  2. 2.
    Hobson, A., Cheng, B.: A comparison of the Shannon and Kullback information measures. Journal of Statistical Physics 7(4), 301–310 (1973)MathSciNetzbMATHCrossRefGoogle Scholar
  3. 3.
    Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. The Journal of Machine Learning Research 3, 1157–1182 (2003)zbMATHGoogle Scholar
  4. 4.
    Kononenko, Šimec, E., Robnik-Šikonja, M.: Overcoming the myopia of inductive learning algorithms with RELIEFF. Applied Intelligence 7(1), 39–55 (1997)CrossRefGoogle Scholar
  5. 5.
    Blanco, R., Larranaga, P., Inza, I., Sierra, B.: Gene selection for cancer classification using wrapper approaches. International Journal of Pattern Recognition and Artificial Intelligence 18(8), 1373–1390 (2004)CrossRefGoogle Scholar
  6. 6.
    Guyon, I., Gunn, S., Nikravesh, M., Zadeh, L.: Feature Extraction: Foundations and Applications. STUDFUZZ, vol. 207. Physica-Verlag, Springer (2006)Google Scholar
  7. 7.
    Eiben, E., Smith, J.E.: Introduction to Evolutionary Computing. Natural Computing Series. MIT Press, Springer, Berlin (2003)zbMATHCrossRefGoogle Scholar
  8. 8.
    She, Q., Shi, W.M., Kong, W., Ye, B.X.: A combination of modified particle swarm optimization algorithm and support vector machine for gene selection and tumor classification. Talanta 71, 1679–1683 (2007)CrossRefGoogle Scholar
  9. 9.
    Kennedy, J., Eberhart, R.: Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, vol. 4, pp. 1942–1948 (1995)Google Scholar
  10. 10.
    Shi, Y., Eberhart, R.C.: A modified particle swarm optimizer. In: Proceeding of IEEE World Conference on Computation Intelligence, pp. 69–73 (1998)Google Scholar
  11. 11.
    Mar, J.C., Wells, C.A., Quackenbush, J.: Defining an Informativeness Metric for Clustering Gene Expression Data. Bioinfromatics 27(8), 1094–1100 (2011)CrossRefGoogle Scholar
  12. 12.
    Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme Learning Machine: Theory and Applications. Neurocomputing 70, 489–501 (2006)CrossRefGoogle Scholar
  13. 13.
    Juliusdottir, T., Corne, D., Keedwell, E., Narayanan, A.: Two-Phase EA/k-NN for Feature Selection and Classification in Cancer Microarray Datasets, CIBCB, 1594891, pp. 1–8 (2005)Google Scholar
  14. 14.
    Guyon, J., Weston, S., Barnhill, Vapnik, V.: Gene selection for cancer classification using support vector machines. Machine Learning 46(1-3), 389–422 (2002)zbMATHCrossRefGoogle Scholar
  15. 15.
    Huerta, E.B., Duval, B., Hao, J.-K.: A Hybrid GA/SVM Approach for Gene Selection and Classification of Microarray Data. In: Rothlauf, F., Branke, J., Cagnoni, S., Costa, E., Cotta, C., Drechsler, R., Lutton, E., Machado, P., Moore, J.H., Romero, J., Smith, G.D., Squillero, G., Takagi, H. (eds.) EvoWorkshops 2006. LNCS, vol. 3907, pp. 34–44. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  16. 16.
    Deb, K., Reddy, A.R.: Classification of two-class cancer data reliably using evolutionary algorithms. Biosystems 72(1-2), 111–129 (2003)CrossRefGoogle Scholar
  17. 17.
    Yu, L., Liu, H.: Redundancy based feature selection for microarray data. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, Washington, August 22–25, pp. 737–742 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Jian Guan
    • 1
  • Fei Han
    • 1
  • Shanxiu Yang
    • 1
  1. 1.School of Computer Science and Telecommunication EngineeringJiangsu UniversityZhenjiangChina

Personalised recommendations