Optimal search-based gene subset selection for gene array cancer classification

Jeixun Li, Hua Su, Hsinchun Chen, Bernard W Futscher

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

High dimensionality has been a major problem for gene array-based cancer classification. It is critical to identify marker genes for cancer diagnoses. We developed a framework of gene selection methods based on previous studies. This paper focuses on optimal search-based subset selection methods because they evaluate the group performance of genes and help to pinpoint global optimal set of marker genes. Notably, this paper is the first to introduce tabu search (TS) to gene selection from high-dimensional gene array data. Our comparative study of gene selection methods demonstrated the effectiveness of optimal search-based gene subset selection to identify cancer marker genes. TS was shown to be a promising tool for gene subset selection.

Original languageEnglish (US)
Pages (from-to)398-405
Number of pages8
JournalIEEE Transactions on Information Technology in Biomedicine
Volume11
Issue number4
DOIs
StatePublished - Jul 2007

Fingerprint

Neoplasm Genes
Genes
Taboo
Tabu search

Keywords

  • Genetics
  • Medical diagnosis
  • Optimization methods
  • Pattern classification
  • Search methods

ASJC Scopus subject areas

  • Health Informatics
  • Health Information Management
  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Optimal search-based gene subset selection for gene array cancer classification. / Li, Jeixun; Su, Hua; Chen, Hsinchun; Futscher, Bernard W.

In: IEEE Transactions on Information Technology in Biomedicine, Vol. 11, No. 4, 07.2007, p. 398-405.

Research output: Contribution to journalArticle

@article{ac307373d6e645c3b60585cac6c1248f,
title = "Optimal search-based gene subset selection for gene array cancer classification",
abstract = "High dimensionality has been a major problem for gene array-based cancer classification. It is critical to identify marker genes for cancer diagnoses. We developed a framework of gene selection methods based on previous studies. This paper focuses on optimal search-based subset selection methods because they evaluate the group performance of genes and help to pinpoint global optimal set of marker genes. Notably, this paper is the first to introduce tabu search (TS) to gene selection from high-dimensional gene array data. Our comparative study of gene selection methods demonstrated the effectiveness of optimal search-based gene subset selection to identify cancer marker genes. TS was shown to be a promising tool for gene subset selection.",
keywords = "Genetics, Medical diagnosis, Optimization methods, Pattern classification, Search methods",
author = "Jeixun Li and Hua Su and Hsinchun Chen and Futscher, {Bernard W}",
year = "2007",
month = "7",
doi = "10.1109/TITB.2007.892693",
language = "English (US)",
volume = "11",
pages = "398--405",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Optimal search-based gene subset selection for gene array cancer classification

AU - Li, Jeixun

AU - Su, Hua

AU - Chen, Hsinchun

AU - Futscher, Bernard W

PY - 2007/7

Y1 - 2007/7

N2 - High dimensionality has been a major problem for gene array-based cancer classification. It is critical to identify marker genes for cancer diagnoses. We developed a framework of gene selection methods based on previous studies. This paper focuses on optimal search-based subset selection methods because they evaluate the group performance of genes and help to pinpoint global optimal set of marker genes. Notably, this paper is the first to introduce tabu search (TS) to gene selection from high-dimensional gene array data. Our comparative study of gene selection methods demonstrated the effectiveness of optimal search-based gene subset selection to identify cancer marker genes. TS was shown to be a promising tool for gene subset selection.

AB - High dimensionality has been a major problem for gene array-based cancer classification. It is critical to identify marker genes for cancer diagnoses. We developed a framework of gene selection methods based on previous studies. This paper focuses on optimal search-based subset selection methods because they evaluate the group performance of genes and help to pinpoint global optimal set of marker genes. Notably, this paper is the first to introduce tabu search (TS) to gene selection from high-dimensional gene array data. Our comparative study of gene selection methods demonstrated the effectiveness of optimal search-based gene subset selection to identify cancer marker genes. TS was shown to be a promising tool for gene subset selection.

KW - Genetics

KW - Medical diagnosis

KW - Optimization methods

KW - Pattern classification

KW - Search methods

UR - http://www.scopus.com/inward/record.url?scp=34547126221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547126221&partnerID=8YFLogxK

U2 - 10.1109/TITB.2007.892693

DO - 10.1109/TITB.2007.892693

M3 - Article

VL - 11

SP - 398

EP - 405

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 4

ER -