An Efficient Two-Stage Gene Selection Method for Microarray Data - Intelligent Computing for Sustainable Energy and Environment - page 432

5Conluon
The paper has proposed a two-stage gene selection algorithm for microarray
data with small samples and variant correlation. The L 2 -norm penalty are firstly
introduced to achieve the grouping effect for the highly correlated genes. By using
the augmented data technique, an augmented data set can be then produced.
The most informative genes can be selected effectively by the proposed two-
stage algorithm. Compared with the popular Elastic Net method, the proposed
TSGS method demonstrates the better results. The identified gene clusters may
provide a chance for the exploratory analysis of microarray data.
Acknowledgment. The authors would like to thank the Research Councils
UK under grant EP/G042594/1, the National Science Foundation of China
(61074032, 60834002, 51007052, 61104089), Science and Technology Commis-
sion of Shanghai Municipality (11ZR1413100), the innovation fund project for
Shanghai University.
References
1. Golub, T.R., et al.: Molecular classification of cancer: class discovery and class
prediction by gene expression monitoring. Science 286, 531-537 (1999)
2. Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Journal
of Machine Learning Research 3, 1157-1182 (2003)
3. Liu, B., Wan, C., Wang, L.: An e cient semi-unsupervised gene selecttion method
via spectra biclustering. IEEE Transactions on Nanobioscience 5(2), 110-114
(2006)
4. Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artificial Intelli-
gence 97(1-2), 273-324 (1997)
5. Cai, R., Hao, Z., Yang, X., Wen, W.: An ecient gene selection algorithm based
on mutual information. Neurocomputing 72, 991-999 (2009)
6. Zhou, X., Mao, K.Z.: LS bound based gene selection for DNA micorarray data.
Bioinformatics 21(8), 1559-1564 (2005)
7. Freund, Y., Schapire, R.: A dicision-theoretic generalization of on-line learning and
an application to boosting. Journal of Computer and System Sciences 55, 119-139
(1997)
8. Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J.R.
Statist. Soc.B 67(2), 301-320 (2005)
9. Li, K., Peng, J.X., Bai, E.W.: A two-stage algorithm for identification of nonlinear
dynamic systems. Automatica 42(7), 1189-1197 (2006)
10. Marquardt, D.W.: Generalized inverses, ridge regression, biased linerar estimation,
and nonlinear estimation. Technometrics 12(3), 591-612 (1970)
11. Nelles, O.: Nonlinear system identification. Springer (2001)
12. Sha, N., Vannucci, M., Brown, P., Trower, M., Amphlett, G.: Gene selection in
arthritis classification with large-scale microarray expression profiles. Comparative
and Functional Genomics 4, 171-181 (2003)