Abstract
In this paper, we argue that existing gene selection methods are not effective for selecting important genes when the number of samples and the data dimensions grow sufficiently large. As a solution, we propose two approaches for parallel gene selections, both are based on the well known ReliefF feature selection method. In the first design, denoted by PReliefF p , the input data are split into non-overlapping subsets assigned to cluster nodes. Each node carries out gene selection by using the ReliefF method on its own subset, without interaction with other clusters. The final ranking of the genes is generated by gathering the weight vectors from all nodes. In the second design, namely PReliefF g , each node dynamically updates the global weight vectors so the gene selection results in one node can be used to boost the selection of the other nodes. Experimental results from real-world microarray expression data show that PReliefF p and PReliefF g achieve a speedup factor nearly equal to the number of nodes. When combined with several popular classification methods, the classifiers built from the genes selected from both methods have the same or even better accuracy than the genes selected from the original ReliefF method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Golub, T., et al.: Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286, 531–537 (1999)
Xiong, M., et al.: Biomarker identification by feature wrappers. Genome Research 11, 1878–1887 (2001)
Baker, S., Kramer, B.: Identifying genes that contribute most to good classification in microarrays. BMC Bioinformatics 7, 407 (2006)
Segal, E., et al.: Module networks: identifying regulatory modules and their condition-specific regulators from gene expression data. Nature Genetics 34(2), 166–176 (2003)
Quinlan, J.: C4.5: Programs for Machine learning. M. Kaufmann, San Francisco (1993)
Hua, J., et al.: Optimal number of features as a function of sample size for various classification rules. Bioinformatics 21, 1509–1515 (2005)
Zhan, J., Deng, H.: Gene selection for classification of microarray data based on the Bayes error. BMC Bioinformatics 8, 370 (2007)
Diaz, R., Alvarez, S.: Gene selection and classification of microarray data using random forest. BMC Bioinformatics 7, 3 (2006)
Mamitsuka, H.: Selecting features in microarray classification using ROC curves. Pattern Recognition 39, 2393–2404 (2006)
Dobbin, K., et al.: How large a training set is needed to develop a classifier for microarray data. Clinical Cancer Research 14(1) (2008)
Mukherjee, S., Roberts, S.: A Theoretical Analysis of Gene Selection. In: Proc. of IEEE Computer Society Bioinformatics Conference, pp. 131–141 (2004)
Li, T., et al.: A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression. Bioinformatics 20, 2429–2437 (2004)
Statnikov, A., et al.: A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics 21(5), 631–643 (2005)
Witten, F.E.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, San Francisco (1999)
Plackett, R.: Karl Pearson and the Chi-Squared Test. International Statistical Review 51(1), 59–72 (1983)
Robnik-Šikonja, M., Kononenko, I.: Theoretical and Empirical Analysis of ReliefF and RReliefF Mach. Learn. 53, 23–69 (2003)
Gropp, W., et al.: MPICH2 User’s Guide (2008), http://www.mcs.anl.gov/research/projects/mpich2/index.php
Kohavi, R., John, G.: Wrappers for Feature Subset Selection. Artificial Intelligence 97(1-2), 273–324 (1997)
Kent Ridge Biomedical Data Set Repository, http://sdmc.i2r.a-star.edu.sg/rp/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Slavik, M., Zhu, X., Mahgoub, I., Shoaib, M. (2009). Parallel Selection of Informative Genes for Classification. In: Rajasekaran, S. (eds) Bioinformatics and Computational Biology. BICoB 2009. Lecture Notes in Computer Science(), vol 5462. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-00727-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-00727-9_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-00726-2
Online ISBN: 978-3-642-00727-9
eBook Packages: Computer ScienceComputer Science (R0)