Identifying significant genes from microarray data

Han Yu Chuang, Hongfang D Liu, Stuart Brown, Cameron McMunn-Coffran, Cheng Yan Kao, D. Frank Hsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

Microarray technology is a recent development in experimental molecular biology which can produce quantitative expression measurements for thousands of genes in a single, cellular mRNA sample. These many gene expression measurements form a composite profile of the sample, which can be used to differentiate samples from different classes such as tissue types or treatments. However, for the gene expression profile data obtained in a specific comparison, most likely only some of the genes will, be differentially expressed between the classes, while many other genes have similar expression levels. Selecting a list of informative differential genes from these data is important for microarray data analysis. In this paper, we describe a framework for selecting informative genes, called Ranking and Combination analysis (RAC), which combines various existing informative gene selection methods. We conducted experiments using three data sets and six existing feature selection methods. The results show that the RAC framework is a robust and efficient approach to identify informative gene for microarray data. The combination approach on two selecting methods almost always performed better than the less efficient individual, and in many cases, better than both. More significantly, when considering all three data sets together, the combination approach, on average, outperforms each individual feature selection method. All of these indicate that RCA might be a viable and feasible approach for the microarray gene expression analysis.

Original languageEnglish (US)
Title of host publicationProceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004
Pages358-365
Number of pages8
StatePublished - 2004
Externally publishedYes
EventProceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004 - Taichung, Taiwan, Province of China
Duration: May 19 2004May 21 2004

Other

OtherProceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004
CountryTaiwan, Province of China
CityTaichung
Period5/19/045/21/04

Fingerprint

Microarrays
Genes
Gene expression
Feature extraction
Molecular biology
Tissue
Composite materials
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Chuang, H. Y., Liu, H. D., Brown, S., McMunn-Coffran, C., Kao, C. Y., & Hsu, D. F. (2004). Identifying significant genes from microarray data. In Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004 (pp. 358-365)

Identifying significant genes from microarray data. / Chuang, Han Yu; Liu, Hongfang D; Brown, Stuart; McMunn-Coffran, Cameron; Kao, Cheng Yan; Hsu, D. Frank.

Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004. 2004. p. 358-365.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chuang, HY, Liu, HD, Brown, S, McMunn-Coffran, C, Kao, CY & Hsu, DF 2004, Identifying significant genes from microarray data. in Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004. pp. 358-365, Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004, Taichung, Taiwan, Province of China, 5/19/04.
Chuang HY, Liu HD, Brown S, McMunn-Coffran C, Kao CY, Hsu DF. Identifying significant genes from microarray data. In Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004. 2004. p. 358-365
Chuang, Han Yu ; Liu, Hongfang D ; Brown, Stuart ; McMunn-Coffran, Cameron ; Kao, Cheng Yan ; Hsu, D. Frank. / Identifying significant genes from microarray data. Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004. 2004. pp. 358-365
@inproceedings{299b972cd4fe43e394e271b218cea0d3,
title = "Identifying significant genes from microarray data",
abstract = "Microarray technology is a recent development in experimental molecular biology which can produce quantitative expression measurements for thousands of genes in a single, cellular mRNA sample. These many gene expression measurements form a composite profile of the sample, which can be used to differentiate samples from different classes such as tissue types or treatments. However, for the gene expression profile data obtained in a specific comparison, most likely only some of the genes will, be differentially expressed between the classes, while many other genes have similar expression levels. Selecting a list of informative differential genes from these data is important for microarray data analysis. In this paper, we describe a framework for selecting informative genes, called Ranking and Combination analysis (RAC), which combines various existing informative gene selection methods. We conducted experiments using three data sets and six existing feature selection methods. The results show that the RAC framework is a robust and efficient approach to identify informative gene for microarray data. The combination approach on two selecting methods almost always performed better than the less efficient individual, and in many cases, better than both. More significantly, when considering all three data sets together, the combination approach, on average, outperforms each individual feature selection method. All of these indicate that RCA might be a viable and feasible approach for the microarray gene expression analysis.",
author = "Chuang, {Han Yu} and Liu, {Hongfang D} and Stuart Brown and Cameron McMunn-Coffran and Kao, {Cheng Yan} and Hsu, {D. Frank}",
year = "2004",
language = "English (US)",
isbn = "0769521738",
pages = "358--365",
booktitle = "Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004",

}

TY - GEN

T1 - Identifying significant genes from microarray data

AU - Chuang, Han Yu

AU - Liu, Hongfang D

AU - Brown, Stuart

AU - McMunn-Coffran, Cameron

AU - Kao, Cheng Yan

AU - Hsu, D. Frank

PY - 2004

Y1 - 2004

N2 - Microarray technology is a recent development in experimental molecular biology which can produce quantitative expression measurements for thousands of genes in a single, cellular mRNA sample. These many gene expression measurements form a composite profile of the sample, which can be used to differentiate samples from different classes such as tissue types or treatments. However, for the gene expression profile data obtained in a specific comparison, most likely only some of the genes will, be differentially expressed between the classes, while many other genes have similar expression levels. Selecting a list of informative differential genes from these data is important for microarray data analysis. In this paper, we describe a framework for selecting informative genes, called Ranking and Combination analysis (RAC), which combines various existing informative gene selection methods. We conducted experiments using three data sets and six existing feature selection methods. The results show that the RAC framework is a robust and efficient approach to identify informative gene for microarray data. The combination approach on two selecting methods almost always performed better than the less efficient individual, and in many cases, better than both. More significantly, when considering all three data sets together, the combination approach, on average, outperforms each individual feature selection method. All of these indicate that RCA might be a viable and feasible approach for the microarray gene expression analysis.

AB - Microarray technology is a recent development in experimental molecular biology which can produce quantitative expression measurements for thousands of genes in a single, cellular mRNA sample. These many gene expression measurements form a composite profile of the sample, which can be used to differentiate samples from different classes such as tissue types or treatments. However, for the gene expression profile data obtained in a specific comparison, most likely only some of the genes will, be differentially expressed between the classes, while many other genes have similar expression levels. Selecting a list of informative differential genes from these data is important for microarray data analysis. In this paper, we describe a framework for selecting informative genes, called Ranking and Combination analysis (RAC), which combines various existing informative gene selection methods. We conducted experiments using three data sets and six existing feature selection methods. The results show that the RAC framework is a robust and efficient approach to identify informative gene for microarray data. The combination approach on two selecting methods almost always performed better than the less efficient individual, and in many cases, better than both. More significantly, when considering all three data sets together, the combination approach, on average, outperforms each individual feature selection method. All of these indicate that RCA might be a viable and feasible approach for the microarray gene expression analysis.

UR - http://www.scopus.com/inward/record.url?scp=4544297364&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544297364&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0769521738

SN - 9780769521732

SP - 358

EP - 365

BT - Proceedings - Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004

ER -