Forward selection method with regression analysis for optimal gene selection in cancer classification

Han Saem Park, Si Ho Yoo, Sung Bae Cho

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

The development of DNA microarray technology has facilitated in-depth research into cancer classification, and has made it possible to process thousands of genes simultaneously. Since not all genes are crucial for classifying cancer, it is necessary to select informative genes which are associated with cancer. Many gene selection methods have been investigated, but none is perfect. In this paper we investigate methods of finding optimal informative genes for classification of gene expression profiles. We propose a new gene selection method based on the forward selection method with regression analysis in order to find informative genes which predict cancer. The genes selected by this method tend to have information about the cancer that does not overlap with the other genes selected. We have measured the sensitivity, specificity, and recognition rate of the selected genes with the $k$-nearest-neighbour classifier for the colon cancer dataset and the lymphoma dataset. In most cases, the proposed method produces better results than gene selection based on other feature selection methods, yielding a high accuracy of 90.3% for the colon cancer dataset and 72% for the lymphoma dataset.

Original languageEnglish
Pages (from-to)653-667
Number of pages15
JournalInternational Journal of Computer Mathematics
Volume84
Issue number5
DOIs
Publication statusPublished - 2007 May 1

Fingerprint

Cancer Classification
Gene Selection
Regression Analysis
Regression analysis
Genes
Gene
Cancer
DNA Microarray
Gene Expression Profile
Feature Selection
Specificity
Overlap
Nearest Neighbor
High Accuracy
Microarrays
Classifier
Tend
Gene expression
Predict
Feature extraction

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computational Theory and Mathematics
  • Applied Mathematics

Cite this

@article{63bb4557029b4a72a9f0f9d0ef6afd00,
title = "Forward selection method with regression analysis for optimal gene selection in cancer classification",
abstract = "The development of DNA microarray technology has facilitated in-depth research into cancer classification, and has made it possible to process thousands of genes simultaneously. Since not all genes are crucial for classifying cancer, it is necessary to select informative genes which are associated with cancer. Many gene selection methods have been investigated, but none is perfect. In this paper we investigate methods of finding optimal informative genes for classification of gene expression profiles. We propose a new gene selection method based on the forward selection method with regression analysis in order to find informative genes which predict cancer. The genes selected by this method tend to have information about the cancer that does not overlap with the other genes selected. We have measured the sensitivity, specificity, and recognition rate of the selected genes with the $k$-nearest-neighbour classifier for the colon cancer dataset and the lymphoma dataset. In most cases, the proposed method produces better results than gene selection based on other feature selection methods, yielding a high accuracy of 90.3{\%} for the colon cancer dataset and 72{\%} for the lymphoma dataset.",
author = "Park, {Han Saem} and Yoo, {Si Ho} and Cho, {Sung Bae}",
year = "2007",
month = "5",
day = "1",
doi = "10.1080/00207160701294384",
language = "English",
volume = "84",
pages = "653--667",
journal = "International Journal of Computer Mathematics",
issn = "0020-7160",
publisher = "Taylor and Francis Ltd.",
number = "5",

}

Forward selection method with regression analysis for optimal gene selection in cancer classification. / Park, Han Saem; Yoo, Si Ho; Cho, Sung Bae.

In: International Journal of Computer Mathematics, Vol. 84, No. 5, 01.05.2007, p. 653-667.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Forward selection method with regression analysis for optimal gene selection in cancer classification

AU - Park, Han Saem

AU - Yoo, Si Ho

AU - Cho, Sung Bae

PY - 2007/5/1

Y1 - 2007/5/1

N2 - The development of DNA microarray technology has facilitated in-depth research into cancer classification, and has made it possible to process thousands of genes simultaneously. Since not all genes are crucial for classifying cancer, it is necessary to select informative genes which are associated with cancer. Many gene selection methods have been investigated, but none is perfect. In this paper we investigate methods of finding optimal informative genes for classification of gene expression profiles. We propose a new gene selection method based on the forward selection method with regression analysis in order to find informative genes which predict cancer. The genes selected by this method tend to have information about the cancer that does not overlap with the other genes selected. We have measured the sensitivity, specificity, and recognition rate of the selected genes with the $k$-nearest-neighbour classifier for the colon cancer dataset and the lymphoma dataset. In most cases, the proposed method produces better results than gene selection based on other feature selection methods, yielding a high accuracy of 90.3% for the colon cancer dataset and 72% for the lymphoma dataset.

AB - The development of DNA microarray technology has facilitated in-depth research into cancer classification, and has made it possible to process thousands of genes simultaneously. Since not all genes are crucial for classifying cancer, it is necessary to select informative genes which are associated with cancer. Many gene selection methods have been investigated, but none is perfect. In this paper we investigate methods of finding optimal informative genes for classification of gene expression profiles. We propose a new gene selection method based on the forward selection method with regression analysis in order to find informative genes which predict cancer. The genes selected by this method tend to have information about the cancer that does not overlap with the other genes selected. We have measured the sensitivity, specificity, and recognition rate of the selected genes with the $k$-nearest-neighbour classifier for the colon cancer dataset and the lymphoma dataset. In most cases, the proposed method produces better results than gene selection based on other feature selection methods, yielding a high accuracy of 90.3% for the colon cancer dataset and 72% for the lymphoma dataset.

UR - http://www.scopus.com/inward/record.url?scp=34547352268&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547352268&partnerID=8YFLogxK

U2 - 10.1080/00207160701294384

DO - 10.1080/00207160701294384

M3 - Article

AN - SCOPUS:34547352268

VL - 84

SP - 653

EP - 667

JO - International Journal of Computer Mathematics

JF - International Journal of Computer Mathematics

SN - 0020-7160

IS - 5

ER -