Multiclass classification of microarray data with repeated measurements: application to cancer

Prediction of the diagnostic category of a tissue sample from its gene-expression profile and selection of relevant genes for class prediction have important applications in cancer research. We have developed the uncorrelated shrunken centroid (USC) and error-weighted, uncorrelated shrunken centroid...

Descripción completa

Detalles Bibliográficos
Autores principales: Yeung, Ka Yee, Bumgarner, Roger E
Formato: Texto
Lenguaje:English
Publicado: BioMed Central 2003
Materias:
Software
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC329422/
https://www.ncbi.nlm.nih.gov/pubmed/14659020
_version_ 1782121194166681600
author Yeung, Ka Yee
Bumgarner, Roger E
author_facet Yeung, Ka Yee
Bumgarner, Roger E
author_sort Yeung, Ka Yee
collection PubMed
description Prediction of the diagnostic category of a tissue sample from its gene-expression profile and selection of relevant genes for class prediction have important applications in cancer research. We have developed the uncorrelated shrunken centroid (USC) and error-weighted, uncorrelated shrunken centroid (EWUSC) algorithms that are applicable to microarray data with any number of classes. We show that removing highly correlated genes typically improves classification results using a small set of genes.
format Text
id pubmed-329422
institution National Center for Biotechnology Information
language English
publishDate 2003
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-3294222004-02-05 Multiclass classification of microarray data with repeated measurements: application to cancer Yeung, Ka Yee Bumgarner, Roger E Genome Biol Software Prediction of the diagnostic category of a tissue sample from its gene-expression profile and selection of relevant genes for class prediction have important applications in cancer research. We have developed the uncorrelated shrunken centroid (USC) and error-weighted, uncorrelated shrunken centroid (EWUSC) algorithms that are applicable to microarray data with any number of classes. We show that removing highly correlated genes typically improves classification results using a small set of genes. BioMed Central 2003 2003-11-24 /pmc/articles/PMC329422/ /pubmed/14659020 Text en Copyright © 2003 Yeung and Bumgarner; licensee BioMed Central Ltd. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose, provided this notice is preserved along with the article's original URL.
spellingShingle Software
Yeung, Ka Yee
Bumgarner, Roger E
Multiclass classification of microarray data with repeated measurements: application to cancer
title Multiclass classification of microarray data with repeated measurements: application to cancer
title_full Multiclass classification of microarray data with repeated measurements: application to cancer
title_fullStr Multiclass classification of microarray data with repeated measurements: application to cancer
title_full_unstemmed Multiclass classification of microarray data with repeated measurements: application to cancer
title_short Multiclass classification of microarray data with repeated measurements: application to cancer
title_sort multiclass classification of microarray data with repeated measurements: application to cancer
topic Software
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC329422/
https://www.ncbi.nlm.nih.gov/pubmed/14659020
work_keys_str_mv AT yeungkayee multiclassclassificationofmicroarraydatawithrepeatedmeasurementsapplicationtocancer
AT bumgarnerrogere multiclassclassificationofmicroarraydatawithrepeatedmeasurementsapplicationtocancer

Ejemplares similares