Identification of biomarkers for esophageal squamous cell carcinoma using feature selection and decision tree methods

Chun Wei Tung, Ming Tsang Wu, Yu Kuei Chen, Chun Chieh Wu, Wei Chung Chen, Hsien Pin Li, Shah Hwa Chou, Deng Chyang Wu, I. Chen Wu

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Esophageal squamous cell cancer (ESCC) is one of the most common fatal human cancers. The identification of biomarkers for early detection could be a promising strategy to decrease mortality. Previous studies utilized microarray techniques to identify more than one hundred genes; however, it is desirable to identify a small set of biomarkers for clinical use. This study proposes a sequential forward feature selection algorithm to design decision tree models for discriminating ESCC from normal tissues. Two potential biomarkers of RUVBL1 and CNIH were identified and validated based on two public available microarray datasets. To test the discrimination ability of the two biomarkers, 17 pairs of expression profiles of ESCC and normal tissues from Taiwanese male patients were measured by using microarray techniques. The classification accuracies of the two biomarkers in all three datasets were higher than 90%. Interpretable decision tree models were constructed to analyze expression patterns of the two biomarkers. RUVBL1 was consistently overexpressed in all three datasets, although we found inconsistent CNIH expression possibly affected by the diverse major risk factors for ESCC across different areas.

Original languageEnglish
Article number782031
JournalThe Scientific World Journal
Volume2013
DOIs
Publication statusPublished - Dec 1 2013
Externally publishedYes

Fingerprint

Decision Trees
Biomarkers
Decision trees
biomarker
Feature extraction
Squamous Cell Neoplasms
cancer
Esophageal Neoplasms
Microarrays
Tissue
risk factor
Esophageal Squamous Cell Carcinoma
Epithelial Cells
decision
method
Genes
mortality
Mortality
gene
Datasets

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Environmental Science(all)

Cite this

Identification of biomarkers for esophageal squamous cell carcinoma using feature selection and decision tree methods. / Tung, Chun Wei; Wu, Ming Tsang; Chen, Yu Kuei; Wu, Chun Chieh; Chen, Wei Chung; Li, Hsien Pin; Chou, Shah Hwa; Wu, Deng Chyang; Wu, I. Chen.

In: The Scientific World Journal, Vol. 2013, 782031, 01.12.2013.

Research output: Contribution to journalArticle

Tung, Chun Wei ; Wu, Ming Tsang ; Chen, Yu Kuei ; Wu, Chun Chieh ; Chen, Wei Chung ; Li, Hsien Pin ; Chou, Shah Hwa ; Wu, Deng Chyang ; Wu, I. Chen. / Identification of biomarkers for esophageal squamous cell carcinoma using feature selection and decision tree methods. In: The Scientific World Journal. 2013 ; Vol. 2013.
@article{27ecd06eb1fe4ac9b0eabed392c6744b,
title = "Identification of biomarkers for esophageal squamous cell carcinoma using feature selection and decision tree methods",
abstract = "Esophageal squamous cell cancer (ESCC) is one of the most common fatal human cancers. The identification of biomarkers for early detection could be a promising strategy to decrease mortality. Previous studies utilized microarray techniques to identify more than one hundred genes; however, it is desirable to identify a small set of biomarkers for clinical use. This study proposes a sequential forward feature selection algorithm to design decision tree models for discriminating ESCC from normal tissues. Two potential biomarkers of RUVBL1 and CNIH were identified and validated based on two public available microarray datasets. To test the discrimination ability of the two biomarkers, 17 pairs of expression profiles of ESCC and normal tissues from Taiwanese male patients were measured by using microarray techniques. The classification accuracies of the two biomarkers in all three datasets were higher than 90{\%}. Interpretable decision tree models were constructed to analyze expression patterns of the two biomarkers. RUVBL1 was consistently overexpressed in all three datasets, although we found inconsistent CNIH expression possibly affected by the diverse major risk factors for ESCC across different areas.",
author = "Tung, {Chun Wei} and Wu, {Ming Tsang} and Chen, {Yu Kuei} and Wu, {Chun Chieh} and Chen, {Wei Chung} and Li, {Hsien Pin} and Chou, {Shah Hwa} and Wu, {Deng Chyang} and Wu, {I. Chen}",
year = "2013",
month = "12",
day = "1",
doi = "10.1155/2013/782031",
language = "English",
volume = "2013",
journal = "The Scientific World Journal",
issn = "2356-6140",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Identification of biomarkers for esophageal squamous cell carcinoma using feature selection and decision tree methods

AU - Tung, Chun Wei

AU - Wu, Ming Tsang

AU - Chen, Yu Kuei

AU - Wu, Chun Chieh

AU - Chen, Wei Chung

AU - Li, Hsien Pin

AU - Chou, Shah Hwa

AU - Wu, Deng Chyang

AU - Wu, I. Chen

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Esophageal squamous cell cancer (ESCC) is one of the most common fatal human cancers. The identification of biomarkers for early detection could be a promising strategy to decrease mortality. Previous studies utilized microarray techniques to identify more than one hundred genes; however, it is desirable to identify a small set of biomarkers for clinical use. This study proposes a sequential forward feature selection algorithm to design decision tree models for discriminating ESCC from normal tissues. Two potential biomarkers of RUVBL1 and CNIH were identified and validated based on two public available microarray datasets. To test the discrimination ability of the two biomarkers, 17 pairs of expression profiles of ESCC and normal tissues from Taiwanese male patients were measured by using microarray techniques. The classification accuracies of the two biomarkers in all three datasets were higher than 90%. Interpretable decision tree models were constructed to analyze expression patterns of the two biomarkers. RUVBL1 was consistently overexpressed in all three datasets, although we found inconsistent CNIH expression possibly affected by the diverse major risk factors for ESCC across different areas.

AB - Esophageal squamous cell cancer (ESCC) is one of the most common fatal human cancers. The identification of biomarkers for early detection could be a promising strategy to decrease mortality. Previous studies utilized microarray techniques to identify more than one hundred genes; however, it is desirable to identify a small set of biomarkers for clinical use. This study proposes a sequential forward feature selection algorithm to design decision tree models for discriminating ESCC from normal tissues. Two potential biomarkers of RUVBL1 and CNIH were identified and validated based on two public available microarray datasets. To test the discrimination ability of the two biomarkers, 17 pairs of expression profiles of ESCC and normal tissues from Taiwanese male patients were measured by using microarray techniques. The classification accuracies of the two biomarkers in all three datasets were higher than 90%. Interpretable decision tree models were constructed to analyze expression patterns of the two biomarkers. RUVBL1 was consistently overexpressed in all three datasets, although we found inconsistent CNIH expression possibly affected by the diverse major risk factors for ESCC across different areas.

UR - http://www.scopus.com/inward/record.url?scp=84893836961&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893836961&partnerID=8YFLogxK

U2 - 10.1155/2013/782031

DO - 10.1155/2013/782031

M3 - Article

C2 - 24396308

AN - SCOPUS:84893836961

VL - 2013

JO - The Scientific World Journal

JF - The Scientific World Journal

SN - 2356-6140

M1 - 782031

ER -