Neighborhood rough set reduction-based gene selection and prioritization for gene expression profile analysis and molecular cancer classification

Mei Ling Hou, Shu Lin Wang, Xue Ling Li, Ying Ke Lei

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Selection of reliable cancer biomarkers is crucial for gene expression profile-based precise diagnosis of cancer type and successful treatment. However, current studies are confronted with overfitting and dimensionality curse in tumor classification and false positives in the identification of cancer biomarkers. Here, we developed a novel gene-ranking method based on neighborhood rough set reduction for molecular cancer classification based on gene expression profile. Comparison with other methods such as PAM, ClaNC, Kruskal-Wallis rank sum test, and Relief-F, our method shows that only few top-ranked genes could achieve higher tumor classification accuracy. Moreover, although the selected genes are not typical of known oncogenes, they are found to play a crucial role in the occurrence of tumor through searching the scientific literature and analyzing protein interaction partners, which may be used as candidate cancer biomarkers.

Original languageEnglish (US)
Article number726413
JournalJournal of Biomedicine and Biotechnology
Volume2010
DOIs
StatePublished - 2010
Externally publishedYes

Fingerprint

Tumor Biomarkers
Transcriptome
Gene expression
Tumors
Genes
Neoplasms
Pulse amplitude modulation
Literature
Nonparametric Statistics
Oncogenes
Proteins

ASJC Scopus subject areas

  • Biotechnology
  • Molecular Medicine
  • Genetics
  • Molecular Biology
  • Health, Toxicology and Mutagenesis
  • Medicine(all)

Cite this

Neighborhood rough set reduction-based gene selection and prioritization for gene expression profile analysis and molecular cancer classification. / Hou, Mei Ling; Wang, Shu Lin; Li, Xue Ling; Lei, Ying Ke.

In: Journal of Biomedicine and Biotechnology, Vol. 2010, 726413, 2010.

Research output: Contribution to journalArticle

@article{55b9eac975224aebb4a50a8763045b01,
title = "Neighborhood rough set reduction-based gene selection and prioritization for gene expression profile analysis and molecular cancer classification",
abstract = "Selection of reliable cancer biomarkers is crucial for gene expression profile-based precise diagnosis of cancer type and successful treatment. However, current studies are confronted with overfitting and dimensionality curse in tumor classification and false positives in the identification of cancer biomarkers. Here, we developed a novel gene-ranking method based on neighborhood rough set reduction for molecular cancer classification based on gene expression profile. Comparison with other methods such as PAM, ClaNC, Kruskal-Wallis rank sum test, and Relief-F, our method shows that only few top-ranked genes could achieve higher tumor classification accuracy. Moreover, although the selected genes are not typical of known oncogenes, they are found to play a crucial role in the occurrence of tumor through searching the scientific literature and analyzing protein interaction partners, which may be used as candidate cancer biomarkers.",
author = "Hou, {Mei Ling} and Wang, {Shu Lin} and Li, {Xue Ling} and Lei, {Ying Ke}",
year = "2010",
doi = "10.1155/2010/726413",
language = "English (US)",
volume = "2010",
journal = "BioMed Research International",
issn = "2314-6133",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Neighborhood rough set reduction-based gene selection and prioritization for gene expression profile analysis and molecular cancer classification

AU - Hou, Mei Ling

AU - Wang, Shu Lin

AU - Li, Xue Ling

AU - Lei, Ying Ke

PY - 2010

Y1 - 2010

N2 - Selection of reliable cancer biomarkers is crucial for gene expression profile-based precise diagnosis of cancer type and successful treatment. However, current studies are confronted with overfitting and dimensionality curse in tumor classification and false positives in the identification of cancer biomarkers. Here, we developed a novel gene-ranking method based on neighborhood rough set reduction for molecular cancer classification based on gene expression profile. Comparison with other methods such as PAM, ClaNC, Kruskal-Wallis rank sum test, and Relief-F, our method shows that only few top-ranked genes could achieve higher tumor classification accuracy. Moreover, although the selected genes are not typical of known oncogenes, they are found to play a crucial role in the occurrence of tumor through searching the scientific literature and analyzing protein interaction partners, which may be used as candidate cancer biomarkers.

AB - Selection of reliable cancer biomarkers is crucial for gene expression profile-based precise diagnosis of cancer type and successful treatment. However, current studies are confronted with overfitting and dimensionality curse in tumor classification and false positives in the identification of cancer biomarkers. Here, we developed a novel gene-ranking method based on neighborhood rough set reduction for molecular cancer classification based on gene expression profile. Comparison with other methods such as PAM, ClaNC, Kruskal-Wallis rank sum test, and Relief-F, our method shows that only few top-ranked genes could achieve higher tumor classification accuracy. Moreover, although the selected genes are not typical of known oncogenes, they are found to play a crucial role in the occurrence of tumor through searching the scientific literature and analyzing protein interaction partners, which may be used as candidate cancer biomarkers.

UR - http://www.scopus.com/inward/record.url?scp=77955398577&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955398577&partnerID=8YFLogxK

U2 - 10.1155/2010/726413

DO - 10.1155/2010/726413

M3 - Article

VL - 2010

JO - BioMed Research International

JF - BioMed Research International

SN - 2314-6133

M1 - 726413

ER -