Sparse Maximum Margin Discriminant Analysis for Gene Selection

Dimensionality reduction is necessary for gene expression data classification. In this paper, based on sparse representation, we propose a sparse maximum margin discriminant analysis (SMMDA) method for reducing the dimensionality of gene expression data. It could find the one dimension projection in the most separable direction of gene expression data, thus one can use sparse representation technique to regress the projection to obtain the relevance vector for the gene set and select genes according to the vector. Extensive experiments on publicly available gene expression datasets show that SMMDA is efficient for gene selection.

[1]  J. G. Liao,et al.  Logistic regression for disease classification using microarray data: model selection in a large p and small n case , 2007, Bioinform..

[2]  J. Mesirov,et al.  Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. , 1999, Science.

[3]  E. Lander,et al.  Gene expression correlates of clinical prostate cancer behavior. , 2002, Cancer cell.

[4]  S. Dudoit,et al.  Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data , 2002 .

[5]  Lei Zhang,et al.  Tumor Clustering Using Nonnegative Matrix Factorization With Gene Selection , 2009, IEEE Transactions on Information Technology in Biomedicine.

[6]  U. Alon,et al.  Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays. , 1999, Proceedings of the National Academy of Sciences of the United States of America.

[7]  T. Golub,et al.  Gene expression-based classification of malignant gliomas correlates better with survival than histological classification. , 2003, Cancer research.

[8]  Tao Jiang,et al.  Efficient and robust feature extraction by maximum margin criterion , 2003, IEEE Transactions on Neural Networks.

[9]  Yudong D. He,et al.  Gene expression profiling predicts clinical outcome of breast cancer , 2002, Nature.

[10]  D. Donoho.  For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution , 2006 .

[11]  Angel R. Martinez,et al.  MATLAB Statistics Toolbox , 2001 .

[12]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.