Feature selection and survival modeling in The Cancer Genome Atlas

Hyunsoo Kim,1 Markus Bredel2 1Department of Pathology, The University of Alabama at Birmingham, Birmingham, AL, USA; 2Department of Radiation Oncology, and Comprehensive Cancer Center, The University of Alabama at Birmingham, Birmingham, AL, USA Purpose: Personalized medicine is predicated on the co...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kim H, Bredel M
Formato: article
Lenguaje:EN
Publicado: Dove Medical Press 2013
Materias:
Acceso en línea:https://doaj.org/article/9c42fd775da845d4bb93535c9aa5eb06
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9c42fd775da845d4bb93535c9aa5eb06
record_format dspace
spelling oai:doaj.org-article:9c42fd775da845d4bb93535c9aa5eb062021-12-02T05:10:26ZFeature selection and survival modeling in The Cancer Genome Atlas1176-91141178-2013https://doaj.org/article/9c42fd775da845d4bb93535c9aa5eb062013-09-01T00:00:00Zhttp://www.dovepress.com/feature-selection-and-survival-modeling-in-the-cancer-genome-atlas-a14361https://doaj.org/toc/1176-9114https://doaj.org/toc/1178-2013Hyunsoo Kim,1 Markus Bredel2 1Department of Pathology, The University of Alabama at Birmingham, Birmingham, AL, USA; 2Department of Radiation Oncology, and Comprehensive Cancer Center, The University of Alabama at Birmingham, Birmingham, AL, USA Purpose: Personalized medicine is predicated on the concept of identifying subgroups of a common disease for better treatment. Identifying biomarkers that predict disease subtypes has been a major focus of biomedical science. In the era of genome-wide profiling, there is controversy as to the optimal number of genes as an input of a feature selection algorithm for survival modeling. Patients and methods: The expression profiles and outcomes of 544 patients were retrieved from The Cancer Genome Atlas. We compared four different survival prediction methods: (1) 1-nearest neighbor (1-NN) survival prediction method; (2) random patient selection method and a Cox-based regression method with nested cross-validation; (3) least absolute shrinkage and selection operator (LASSO) optimization using whole-genome gene expression profiles; or (4) gene expression profiles of cancer pathway genes. Results: The 1-NN method performed better than the random patient selection method in terms of survival predictions, although it does not include a feature selection step. The Cox-based regression method with LASSO optimization using whole-genome gene expression data demonstrated higher survival prediction power than the 1-NN method, but was outperformed by the same method when using gene expression profiles of cancer pathway genes alone. Conclusion: The 1-NN survival prediction method may require more patients for better performance, even when omitting censored data. Using preexisting biological knowledge for survival prediction is reasonable as a means to understand the biological system of a cancer, unless the analysis goal is to identify completely unknown genes relevant to cancer biology. Keywords: brain, feature selection, glioblastoma, personalized medicine, survival modeling, TCGAKim HBredel MDove Medical PressarticleMedicine (General)R5-920ENInternational Journal of Nanomedicine, Vol 2013, Iss Supplement 1 Nanoinformatics, Pp 57-62 (2013)
institution DOAJ
collection DOAJ
language EN
topic Medicine (General)
R5-920
spellingShingle Medicine (General)
R5-920
Kim H
Bredel M
Feature selection and survival modeling in The Cancer Genome Atlas
description Hyunsoo Kim,1 Markus Bredel2 1Department of Pathology, The University of Alabama at Birmingham, Birmingham, AL, USA; 2Department of Radiation Oncology, and Comprehensive Cancer Center, The University of Alabama at Birmingham, Birmingham, AL, USA Purpose: Personalized medicine is predicated on the concept of identifying subgroups of a common disease for better treatment. Identifying biomarkers that predict disease subtypes has been a major focus of biomedical science. In the era of genome-wide profiling, there is controversy as to the optimal number of genes as an input of a feature selection algorithm for survival modeling. Patients and methods: The expression profiles and outcomes of 544 patients were retrieved from The Cancer Genome Atlas. We compared four different survival prediction methods: (1) 1-nearest neighbor (1-NN) survival prediction method; (2) random patient selection method and a Cox-based regression method with nested cross-validation; (3) least absolute shrinkage and selection operator (LASSO) optimization using whole-genome gene expression profiles; or (4) gene expression profiles of cancer pathway genes. Results: The 1-NN method performed better than the random patient selection method in terms of survival predictions, although it does not include a feature selection step. The Cox-based regression method with LASSO optimization using whole-genome gene expression data demonstrated higher survival prediction power than the 1-NN method, but was outperformed by the same method when using gene expression profiles of cancer pathway genes alone. Conclusion: The 1-NN survival prediction method may require more patients for better performance, even when omitting censored data. Using preexisting biological knowledge for survival prediction is reasonable as a means to understand the biological system of a cancer, unless the analysis goal is to identify completely unknown genes relevant to cancer biology. Keywords: brain, feature selection, glioblastoma, personalized medicine, survival modeling, TCGA
format article
author Kim H
Bredel M
author_facet Kim H
Bredel M
author_sort Kim H
title Feature selection and survival modeling in The Cancer Genome Atlas
title_short Feature selection and survival modeling in The Cancer Genome Atlas
title_full Feature selection and survival modeling in The Cancer Genome Atlas
title_fullStr Feature selection and survival modeling in The Cancer Genome Atlas
title_full_unstemmed Feature selection and survival modeling in The Cancer Genome Atlas
title_sort feature selection and survival modeling in the cancer genome atlas
publisher Dove Medical Press
publishDate 2013
url https://doaj.org/article/9c42fd775da845d4bb93535c9aa5eb06
work_keys_str_mv AT kimh featureselectionandsurvivalmodelinginthecancergenomeatlas
AT bredelm featureselectionandsurvivalmodelinginthecancergenomeatlas
_version_ 1718400547853172736