Cargando…

A Robust Gene Selection Method for Microarray-based Cancer Classification

Gene selection is of vital importance in molecular classification of cancer using high-dimensional gene expression data. Because of the distinct characteristics inherent to specific cancerous gene expression profiles, developing flexible and robust feature selection methods is extremely crucial. We...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Xiaosheng, Gotoh, Osamu
Formato: Texto
Lenguaje:English
Publicado: Libertas Academica 2010
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2834377/
https://www.ncbi.nlm.nih.gov/pubmed/20234770
_version_ 1782178567421952000
author Wang, Xiaosheng
Gotoh, Osamu
author_facet Wang, Xiaosheng
Gotoh, Osamu
author_sort Wang, Xiaosheng
collection PubMed
description Gene selection is of vital importance in molecular classification of cancer using high-dimensional gene expression data. Because of the distinct characteristics inherent to specific cancerous gene expression profiles, developing flexible and robust feature selection methods is extremely crucial. We investigated the properties of one feature selection approach proposed in our previous work, which was the generalization of the feature selection method based on the depended degree of attribute in rough sets. We compared the feature selection method with the established methods: the depended degree, chi-square, information gain, Relief-F and symmetric uncertainty, and analyzed its properties through a series of classification experiments. The results revealed that our method was superior to the canonical depended degree of attribute based method in robustness and applicability. Moreover, the method was comparable to the other four commonly used methods. More importantly, the method can exhibit the inherent classification difficulty with respect to different gene expression datasets, indicating the inherent biology of specific cancers.
format Text
id pubmed-2834377
institution National Center for Biotechnology Information
language English
publishDate 2010
publisher Libertas Academica
record_format MEDLINE/PubMed
spelling pubmed-28343772010-03-16 A Robust Gene Selection Method for Microarray-based Cancer Classification Wang, Xiaosheng Gotoh, Osamu Cancer Inform Original Research Gene selection is of vital importance in molecular classification of cancer using high-dimensional gene expression data. Because of the distinct characteristics inherent to specific cancerous gene expression profiles, developing flexible and robust feature selection methods is extremely crucial. We investigated the properties of one feature selection approach proposed in our previous work, which was the generalization of the feature selection method based on the depended degree of attribute in rough sets. We compared the feature selection method with the established methods: the depended degree, chi-square, information gain, Relief-F and symmetric uncertainty, and analyzed its properties through a series of classification experiments. The results revealed that our method was superior to the canonical depended degree of attribute based method in robustness and applicability. Moreover, the method was comparable to the other four commonly used methods. More importantly, the method can exhibit the inherent classification difficulty with respect to different gene expression datasets, indicating the inherent biology of specific cancers. Libertas Academica 2010-02-04 /pmc/articles/PMC2834377/ /pubmed/20234770 Text en © the author(s), publisher and licensee Libertas Academica Ltd. This is an open access article. Unrestricted non-commercial use is permitted provided the original work is properly cited.
spellingShingle Original Research
Wang, Xiaosheng
Gotoh, Osamu
A Robust Gene Selection Method for Microarray-based Cancer Classification
title A Robust Gene Selection Method for Microarray-based Cancer Classification
title_full A Robust Gene Selection Method for Microarray-based Cancer Classification
title_fullStr A Robust Gene Selection Method for Microarray-based Cancer Classification
title_full_unstemmed A Robust Gene Selection Method for Microarray-based Cancer Classification
title_short A Robust Gene Selection Method for Microarray-based Cancer Classification
title_sort robust gene selection method for microarray-based cancer classification
topic Original Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2834377/
https://www.ncbi.nlm.nih.gov/pubmed/20234770
work_keys_str_mv AT wangxiaosheng arobustgeneselectionmethodformicroarraybasedcancerclassification
AT gotohosamu arobustgeneselectionmethodformicroarraybasedcancerclassification
AT wangxiaosheng robustgeneselectionmethodformicroarraybasedcancerclassification
AT gotohosamu robustgeneselectionmethodformicroarraybasedcancerclassification