Estrogen receptor status prediction by gene component regression: A comparative study

Chi Cheng Huang, Eric Y. Chuang, Shih Hsin Tu, Heng Hui Lien, Jaan Yeh Jeng, Jung Sen Liu, Ching Shui Huang, Liang Chuan Lai

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The aim of the study is to evaluate gene component analysis for microarray studies. Three dimensional reduction strategies, Principle Component Regression (PCR), Partial Least Square (PLS) and Reduced Rank Regression (RRR) were applied to publicly available breast cancer microarray dataset and the derived gene components were used for tumor classification by Logistic Regression (LR) and Linear Discriminative Analysis (LDA). The impact of gene selection/filtration was evaluated as well. We demonstrated that gene component classifiers could reduce the high-dimensionality of gene expression data and the collinearity problem inherited in most modern microarray experiments. In our study gene component analysis could discriminate Estrogen Receptor (ER) positive breast cancers from negative cancers and the proposed classifiers were successfully reproduced and projected into independent microarray dataset with high predictive accuracy.

Original languageEnglish
Pages (from-to)149-171
Number of pages23
JournalInternational Journal of Data Mining and Bioinformatics
Volume9
Issue number2
DOIs
Publication statusPublished - 2014

Fingerprint

Gene Components
Estrogen Receptors
Microarrays
cancer
Genes
regression
Breast Neoplasms
Classifiers
Microarray Analysis
Least-Squares Analysis
logistics
Neoplasms
Gene expression
Logistic Models
experiment
Logistics
Tumors
Gene Expression
Estrogens
Experiments

Keywords

  • Breast cancer
  • Dimension reduction
  • Estrogen receptor
  • Gene component
  • Microarray
  • Partial least square
  • Principle component regression

ASJC Scopus subject areas

  • Library and Information Sciences
  • Information Systems
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Estrogen receptor status prediction by gene component regression : A comparative study. / Huang, Chi Cheng; Chuang, Eric Y.; Tu, Shih Hsin; Lien, Heng Hui; Jeng, Jaan Yeh; Liu, Jung Sen; Huang, Ching Shui; Lai, Liang Chuan.

In: International Journal of Data Mining and Bioinformatics, Vol. 9, No. 2, 2014, p. 149-171.

Research output: Contribution to journalArticle

Huang, Chi Cheng ; Chuang, Eric Y. ; Tu, Shih Hsin ; Lien, Heng Hui ; Jeng, Jaan Yeh ; Liu, Jung Sen ; Huang, Ching Shui ; Lai, Liang Chuan. / Estrogen receptor status prediction by gene component regression : A comparative study. In: International Journal of Data Mining and Bioinformatics. 2014 ; Vol. 9, No. 2. pp. 149-171.
@article{ce98eb343d4a4f9aae94fdb89a5c51fc,
title = "Estrogen receptor status prediction by gene component regression: A comparative study",
abstract = "The aim of the study is to evaluate gene component analysis for microarray studies. Three dimensional reduction strategies, Principle Component Regression (PCR), Partial Least Square (PLS) and Reduced Rank Regression (RRR) were applied to publicly available breast cancer microarray dataset and the derived gene components were used for tumor classification by Logistic Regression (LR) and Linear Discriminative Analysis (LDA). The impact of gene selection/filtration was evaluated as well. We demonstrated that gene component classifiers could reduce the high-dimensionality of gene expression data and the collinearity problem inherited in most modern microarray experiments. In our study gene component analysis could discriminate Estrogen Receptor (ER) positive breast cancers from negative cancers and the proposed classifiers were successfully reproduced and projected into independent microarray dataset with high predictive accuracy.",
keywords = "Breast cancer, Dimension reduction, Estrogen receptor, Gene component, Microarray, Partial least square, Principle component regression",
author = "Huang, {Chi Cheng} and Chuang, {Eric Y.} and Tu, {Shih Hsin} and Lien, {Heng Hui} and Jeng, {Jaan Yeh} and Liu, {Jung Sen} and Huang, {Ching Shui} and Lai, {Liang Chuan}",
year = "2014",
doi = "10.1504/IJDMB.2014.059065",
language = "English",
volume = "9",
pages = "149--171",
journal = "International Journal of Data Mining and Bioinformatics",
issn = "1748-5673",
publisher = "Inderscience Enterprises Ltd",
number = "2",

}

TY - JOUR

T1 - Estrogen receptor status prediction by gene component regression

T2 - A comparative study

AU - Huang, Chi Cheng

AU - Chuang, Eric Y.

AU - Tu, Shih Hsin

AU - Lien, Heng Hui

AU - Jeng, Jaan Yeh

AU - Liu, Jung Sen

AU - Huang, Ching Shui

AU - Lai, Liang Chuan

PY - 2014

Y1 - 2014

N2 - The aim of the study is to evaluate gene component analysis for microarray studies. Three dimensional reduction strategies, Principle Component Regression (PCR), Partial Least Square (PLS) and Reduced Rank Regression (RRR) were applied to publicly available breast cancer microarray dataset and the derived gene components were used for tumor classification by Logistic Regression (LR) and Linear Discriminative Analysis (LDA). The impact of gene selection/filtration was evaluated as well. We demonstrated that gene component classifiers could reduce the high-dimensionality of gene expression data and the collinearity problem inherited in most modern microarray experiments. In our study gene component analysis could discriminate Estrogen Receptor (ER) positive breast cancers from negative cancers and the proposed classifiers were successfully reproduced and projected into independent microarray dataset with high predictive accuracy.

AB - The aim of the study is to evaluate gene component analysis for microarray studies. Three dimensional reduction strategies, Principle Component Regression (PCR), Partial Least Square (PLS) and Reduced Rank Regression (RRR) were applied to publicly available breast cancer microarray dataset and the derived gene components were used for tumor classification by Logistic Regression (LR) and Linear Discriminative Analysis (LDA). The impact of gene selection/filtration was evaluated as well. We demonstrated that gene component classifiers could reduce the high-dimensionality of gene expression data and the collinearity problem inherited in most modern microarray experiments. In our study gene component analysis could discriminate Estrogen Receptor (ER) positive breast cancers from negative cancers and the proposed classifiers were successfully reproduced and projected into independent microarray dataset with high predictive accuracy.

KW - Breast cancer

KW - Dimension reduction

KW - Estrogen receptor

KW - Gene component

KW - Microarray

KW - Partial least square

KW - Principle component regression

UR - http://www.scopus.com/inward/record.url?scp=84893519219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893519219&partnerID=8YFLogxK

U2 - 10.1504/IJDMB.2014.059065

DO - 10.1504/IJDMB.2014.059065

M3 - Article

C2 - 24864376

AN - SCOPUS:84893519219

VL - 9

SP - 149

EP - 171

JO - International Journal of Data Mining and Bioinformatics

JF - International Journal of Data Mining and Bioinformatics

SN - 1748-5673

IS - 2

ER -