BACKGROUND:For the last eight years, microarray-based classification has been a major topic in statistics, bioinformatics and biomedicine research. Traditional methods often yield unsatisfactory results or may even be inapplicable in the so-called "p >> n" setting where the number of predictors p by far exceeds the number of observations n, hence the term "ill-posed-problem". Careful model selection and evaluation satisfying accepted good-practice standards is a very complex task for statisticians without experience in this area or for scientists with limited statistical background. The multiplicity of available methods for class prediction based on high-dimensional data is an additional practical challenge for inexperienced researchers.RESULTS:In this article, we introduce a new Bioconductor package called CMA (standing for "Classification for MicroArrays") for automatically performing variable selection, parameter tuning, classifier construction, and unbiased evaluation of the constructed classifiers using a large number of usual methods. Without much time and effort, users are provided with an overview of the unbiased accuracy of most top-performing classifiers. Furthermore, the standardized evaluation framework underlying CMA can also be beneficial in statistical research for comparison purposes, for instance if a new classifier has to be compared to existing approaches.CONCLUSION:CMA is a user-friendly comprehensive package for classifier construction and evaluation implementing most usual approaches. It is freely available from the Bioconductor website at http://bioconductor.org/packages/2.3/bioc/html/CMA.html.
Description
BioMed Central | Full text | CMA - A comprehensive Bioconductor package for supervised classification with high dimensional data
%0 Journal Article
%1 18925941
%A Slawski, M
%A Daumer, M
%A Boulesteix, A-L
%D 2008
%J BMC Bioinformatics
%K R class gene genetics pls
%N 1
%P 439
%R 10.1186/1471-2105-9-439
%T CMA - a comprehensive Bioconductor package for supervised classification with high dimensional data
%U http://www.biomedcentral.com/1471-2105/9/439
%V 9
%X BACKGROUND:For the last eight years, microarray-based classification has been a major topic in statistics, bioinformatics and biomedicine research. Traditional methods often yield unsatisfactory results or may even be inapplicable in the so-called "p >> n" setting where the number of predictors p by far exceeds the number of observations n, hence the term "ill-posed-problem". Careful model selection and evaluation satisfying accepted good-practice standards is a very complex task for statisticians without experience in this area or for scientists with limited statistical background. The multiplicity of available methods for class prediction based on high-dimensional data is an additional practical challenge for inexperienced researchers.RESULTS:In this article, we introduce a new Bioconductor package called CMA (standing for "Classification for MicroArrays") for automatically performing variable selection, parameter tuning, classifier construction, and unbiased evaluation of the constructed classifiers using a large number of usual methods. Without much time and effort, users are provided with an overview of the unbiased accuracy of most top-performing classifiers. Furthermore, the standardized evaluation framework underlying CMA can also be beneficial in statistical research for comparison purposes, for instance if a new classifier has to be compared to existing approaches.CONCLUSION:CMA is a user-friendly comprehensive package for classifier construction and evaluation implementing most usual approaches. It is freely available from the Bioconductor website at http://bioconductor.org/packages/2.3/bioc/html/CMA.html.
@article{18925941,
abstract = {BACKGROUND:For the last eight years, microarray-based classification has been a major topic in statistics, bioinformatics and biomedicine research. Traditional methods often yield unsatisfactory results or may even be inapplicable in the so-called "p >> n" setting where the number of predictors p by far exceeds the number of observations n, hence the term "ill-posed-problem". Careful model selection and evaluation satisfying accepted good-practice standards is a very complex task for statisticians without experience in this area or for scientists with limited statistical background. The multiplicity of available methods for class prediction based on high-dimensional data is an additional practical challenge for inexperienced researchers.RESULTS:In this article, we introduce a new Bioconductor package called CMA (standing for "Classification for MicroArrays") for automatically performing variable selection, parameter tuning, classifier construction, and unbiased evaluation of the constructed classifiers using a large number of usual methods. Without much time and effort, users are provided with an overview of the unbiased accuracy of most top-performing classifiers. Furthermore, the standardized evaluation framework underlying CMA can also be beneficial in statistical research for comparison purposes, for instance if a new classifier has to be compared to existing approaches.CONCLUSION:CMA is a user-friendly comprehensive package for classifier construction and evaluation implementing most usual approaches. It is freely available from the Bioconductor website at http://bioconductor.org/packages/2.3/bioc/html/CMA.html.},
added-at = {2011-05-06T22:46:36.000+0200},
author = {Slawski, M and Daumer, M and Boulesteix, A-L},
biburl = {https://www.bibsonomy.org/bibtex/2e967bb4ef9c89a6c58d8bc7bcac3daf5/vivion},
description = {BioMed Central | Full text | CMA - A comprehensive Bioconductor package for supervised classification with high dimensional data},
doi = {10.1186/1471-2105-9-439},
interhash = {0739b57a5bf9645ce457f24f903f3f9e},
intrahash = {e967bb4ef9c89a6c58d8bc7bcac3daf5},
issn = {1471-2105},
journal = {BMC Bioinformatics},
keywords = {R class gene genetics pls},
number = 1,
pages = 439,
pubmedid = {18925941},
timestamp = {2011-05-06T22:46:36.000+0200},
title = {CMA - a comprehensive Bioconductor package for supervised classification with high dimensional data},
url = {http://www.biomedcentral.com/1471-2105/9/439},
volume = 9,
year = 2008
}