Estrogen receptor status prediction by gene component regression: a comparative study. (1st January 2014)

• Record Type: Journal Article
• Authors: Huang, Chi-Cheng; Tu, Shih-Hsin; Lien, Heng-Hui; Jeng, Jaan-Yeh; Liu, Jung-Sen; Huang, Ching-Shui; Lai, Liang-Chuan; Chuang, Eric Y.
• Is Part Of: International journal of data mining and bioinformatics. Volume 9:Number 2(2014)
• Page Start: 149
• Page End: 171
• Publication Date: 2014-01-01
• Subjects: gene component -- dimension reduction -- principle component regression -- partial least square -- microarray -- breast cancer -- estrogen receptor; Data mining -- Periodicals; Bioinformatics -- Periodicals; 006.312
• Languages: English
• ISSNs: 1748-5673

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.