Cancer classification using ensemble of neural networks with multiple significant gene subsets

Sung-Bae Cho, Hong Hee Won

Research output: Contribution to journalArticle

79 Citations (Scopus)

Abstract

Molecular level diagnostics based on microarray technologies can offer the methodology of precise, objective, and systematic cancer classification. Genome-wide expression patterns generally consist of thousands of genes. It is desirable to extract some significant genes for accurate diagnosis of cancer because not all genes are associated with a cancer. In this paper, we have used representative gene vectors that are highly discriminatory for cancer classes and extracted multiple significant gene subsets based on those representative vectors respectively. Also, an ensemble of neural networks learned from the multiple significant gene subsets is proposed to classify a sample into one of several cancer classes. The performance of the proposed method is systematically evaluated using three different cancer types: Leukemia, colon, and B-cell lymphoma.

Original languageEnglish
Pages (from-to)243-250
Number of pages8
JournalApplied Intelligence
Volume26
Issue number3
DOIs
Publication statusPublished - 2007 Jun 1

Fingerprint

Genes
Neural networks
Microarrays
Cells

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

@article{d825564096c044d191aa9d1b7224e8e7,
title = "Cancer classification using ensemble of neural networks with multiple significant gene subsets",
abstract = "Molecular level diagnostics based on microarray technologies can offer the methodology of precise, objective, and systematic cancer classification. Genome-wide expression patterns generally consist of thousands of genes. It is desirable to extract some significant genes for accurate diagnosis of cancer because not all genes are associated with a cancer. In this paper, we have used representative gene vectors that are highly discriminatory for cancer classes and extracted multiple significant gene subsets based on those representative vectors respectively. Also, an ensemble of neural networks learned from the multiple significant gene subsets is proposed to classify a sample into one of several cancer classes. The performance of the proposed method is systematically evaluated using three different cancer types: Leukemia, colon, and B-cell lymphoma.",
author = "Sung-Bae Cho and Won, {Hong Hee}",
year = "2007",
month = "6",
day = "1",
doi = "10.1007/s10489-006-0020-4",
language = "English",
volume = "26",
pages = "243--250",
journal = "Applied Intelligence",
issn = "0924-669X",
publisher = "Springer Netherlands",
number = "3",

}

Cancer classification using ensemble of neural networks with multiple significant gene subsets. / Cho, Sung-Bae; Won, Hong Hee.

In: Applied Intelligence, Vol. 26, No. 3, 01.06.2007, p. 243-250.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cancer classification using ensemble of neural networks with multiple significant gene subsets

AU - Cho, Sung-Bae

AU - Won, Hong Hee

PY - 2007/6/1

Y1 - 2007/6/1

N2 - Molecular level diagnostics based on microarray technologies can offer the methodology of precise, objective, and systematic cancer classification. Genome-wide expression patterns generally consist of thousands of genes. It is desirable to extract some significant genes for accurate diagnosis of cancer because not all genes are associated with a cancer. In this paper, we have used representative gene vectors that are highly discriminatory for cancer classes and extracted multiple significant gene subsets based on those representative vectors respectively. Also, an ensemble of neural networks learned from the multiple significant gene subsets is proposed to classify a sample into one of several cancer classes. The performance of the proposed method is systematically evaluated using three different cancer types: Leukemia, colon, and B-cell lymphoma.

AB - Molecular level diagnostics based on microarray technologies can offer the methodology of precise, objective, and systematic cancer classification. Genome-wide expression patterns generally consist of thousands of genes. It is desirable to extract some significant genes for accurate diagnosis of cancer because not all genes are associated with a cancer. In this paper, we have used representative gene vectors that are highly discriminatory for cancer classes and extracted multiple significant gene subsets based on those representative vectors respectively. Also, an ensemble of neural networks learned from the multiple significant gene subsets is proposed to classify a sample into one of several cancer classes. The performance of the proposed method is systematically evaluated using three different cancer types: Leukemia, colon, and B-cell lymphoma.

UR - http://www.scopus.com/inward/record.url?scp=34247154511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34247154511&partnerID=8YFLogxK

U2 - 10.1007/s10489-006-0020-4

DO - 10.1007/s10489-006-0020-4

M3 - Article

AN - SCOPUS:34247154511

VL - 26

SP - 243

EP - 250

JO - Applied Intelligence

JF - Applied Intelligence

SN - 0924-669X

IS - 3

ER -