Close
Help




JOURNAL

Cancer Informatics

415,708 Journal Article Views | Journal Analytics

Improved Sparse Multi-Class SVM and Its Application for Gene Selection in Cancer Classification

Submit a Paper



Publication Date: 04 Aug 2013

Type: Original Research

Journal: Cancer Informatics

Citation: Cancer Informatics 2013:12 143-153

doi: 10.4137/CIN.S10212

Abstract

Background: Microarray techniques provide promising tools for cancer diagnosis using gene expression profiles. However, molecular diagnosis based on high-throughput platforms presents great challenges due to the overwhelming number of variables versus the small sample size and the complex nature of multi-type tumors. Support vector machines (SVMs) have shown superior performance in cancer classification due to their ability to handle high dimensional low sample size data. The multi-class SVM algorithm of Crammer and Singer provides a natural framework for multi-class learning. Despite its effective performance, the procedure utilizes all variables without selection. In this paper, we propose to improve the procedure by imposing shrinkage penalties in learning to enforce solution sparsity.

Results: The original multi-class SVM of Crammer and Singer is effective for multi-class classification but does not conduct variable selection. We improved the method by introducing soft-thresholding type penalties to incorporate variable selection into multi-class classification for high dimensional data. The new methods were applied to simulated data and two cancer gene expression data sets. The results demonstrate that the new methods can select a small number of genes for building accurate multi-class classification rules. Furthermore, the important genes selected by the methods overlap significantly, suggesting general agreement among different variable selection schemes.

Conclusions: High accuracy and sparsity make the new methods attractive for cancer diagnostics with gene expression data and defining targets of therapeutic intervention.

Availability: The source MATLAB code are available from http://math.arizona.edu/~hzhang/software.html.


Downloads

PDF  (768.33 KB PDF FORMAT)

RIS citation   (ENDNOTE, REFERENCE MANAGER, PROCITE, REFWORKS)

BibTex citation   (BIBDESK, LATEX)

XML


External Resources

MATLAB source code






What Your Colleagues Say About Cancer Informatics
testimonial_image
Compared with other journals we considered for publishing, Cancer Informatics provided extremely rapid but quality turnaround from draft submission to a flawlessly typeset final publication.  Moreover, sharing the article is now as easy as sharing a link with no subscriptions required, and additional code and data files are equally accessible, supporting reproducible research.  Because it has published many of our references we feel confident that our target readership must follow the journal.  This is further ...
Dr Seppo Karrila (Prince of Songkla University, Thailand)
More Testimonials

Quick Links


New article and journal news notification services