Building a classifier for integrated microarray datasets through two-stage approach

Youngmi Yoon, Jongchan Lee, Sanghyun Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Since microarray data acquire tens of thousands of gene expression values simultaneously, they could be very useful in identifying the phenotypes of diseases. However, the results of analyzing several microarray datasets which were independently carried out with the same biological objectives, could turn out to be different. One of the main reasons is attributable to the limited number of samples involved in one microarray experiment. In order to increase the classification accuracy, it is desirable to augment the sample size by integrating and maximizing the use of independently-conducted microarray datasets. In this paper, we propose a two-stage approach which firstly integrates individual microarray datasets to overcome the problem caused by limited number of samples, and identifies informative genes, secondly builds a classifier using only the informative genes. The classifier from large samples by integrating independent microarray datasets achieves high accuracy, sensitivity, and specificity on independent test sample dataset.

Original languageEnglish
Title of host publicationProceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006
Pages94-102
Number of pages9
DOIs
Publication statusPublished - 2006 Dec 1
Event6th IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006 - Arlington, VA, United States
Duration: 2006 Oct 162006 Oct 18

Other

Other6th IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006
CountryUnited States
CityArlington, VA
Period06/10/1606/10/18

Fingerprint

Microarrays
Classifiers
Genes
Sample Size
Gene expression
Datasets
Phenotype
Gene Expression
Sensitivity and Specificity
Experiments

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science Applications
  • Information Systems

Cite this

Yoon, Y., Lee, J., & Park, S. (2006). Building a classifier for integrated microarray datasets through two-stage approach. In Proceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006 (pp. 94-102). [4019646] https://doi.org/10.1109/BIBE.2006.253321
Yoon, Youngmi ; Lee, Jongchan ; Park, Sanghyun. / Building a classifier for integrated microarray datasets through two-stage approach. Proceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006. 2006. pp. 94-102
@inproceedings{f5b4facd1d1b4a398e70364558874ae5,
title = "Building a classifier for integrated microarray datasets through two-stage approach",
abstract = "Since microarray data acquire tens of thousands of gene expression values simultaneously, they could be very useful in identifying the phenotypes of diseases. However, the results of analyzing several microarray datasets which were independently carried out with the same biological objectives, could turn out to be different. One of the main reasons is attributable to the limited number of samples involved in one microarray experiment. In order to increase the classification accuracy, it is desirable to augment the sample size by integrating and maximizing the use of independently-conducted microarray datasets. In this paper, we propose a two-stage approach which firstly integrates individual microarray datasets to overcome the problem caused by limited number of samples, and identifies informative genes, secondly builds a classifier using only the informative genes. The classifier from large samples by integrating independent microarray datasets achieves high accuracy, sensitivity, and specificity on independent test sample dataset.",
author = "Youngmi Yoon and Jongchan Lee and Sanghyun Park",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/BIBE.2006.253321",
language = "English",
isbn = "0769527272",
pages = "94--102",
booktitle = "Proceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006",

}

Yoon, Y, Lee, J & Park, S 2006, Building a classifier for integrated microarray datasets through two-stage approach. in Proceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006., 4019646, pp. 94-102, 6th IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006, Arlington, VA, United States, 06/10/16. https://doi.org/10.1109/BIBE.2006.253321

Building a classifier for integrated microarray datasets through two-stage approach. / Yoon, Youngmi; Lee, Jongchan; Park, Sanghyun.

Proceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006. 2006. p. 94-102 4019646.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Building a classifier for integrated microarray datasets through two-stage approach

AU - Yoon, Youngmi

AU - Lee, Jongchan

AU - Park, Sanghyun

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Since microarray data acquire tens of thousands of gene expression values simultaneously, they could be very useful in identifying the phenotypes of diseases. However, the results of analyzing several microarray datasets which were independently carried out with the same biological objectives, could turn out to be different. One of the main reasons is attributable to the limited number of samples involved in one microarray experiment. In order to increase the classification accuracy, it is desirable to augment the sample size by integrating and maximizing the use of independently-conducted microarray datasets. In this paper, we propose a two-stage approach which firstly integrates individual microarray datasets to overcome the problem caused by limited number of samples, and identifies informative genes, secondly builds a classifier using only the informative genes. The classifier from large samples by integrating independent microarray datasets achieves high accuracy, sensitivity, and specificity on independent test sample dataset.

AB - Since microarray data acquire tens of thousands of gene expression values simultaneously, they could be very useful in identifying the phenotypes of diseases. However, the results of analyzing several microarray datasets which were independently carried out with the same biological objectives, could turn out to be different. One of the main reasons is attributable to the limited number of samples involved in one microarray experiment. In order to increase the classification accuracy, it is desirable to augment the sample size by integrating and maximizing the use of independently-conducted microarray datasets. In this paper, we propose a two-stage approach which firstly integrates individual microarray datasets to overcome the problem caused by limited number of samples, and identifies informative genes, secondly builds a classifier using only the informative genes. The classifier from large samples by integrating independent microarray datasets achieves high accuracy, sensitivity, and specificity on independent test sample dataset.

UR - http://www.scopus.com/inward/record.url?scp=34547441268&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547441268&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2006.253321

DO - 10.1109/BIBE.2006.253321

M3 - Conference contribution

SN - 0769527272

SN - 9780769527277

SP - 94

EP - 102

BT - Proceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006

ER -

Yoon Y, Lee J, Park S. Building a classifier for integrated microarray datasets through two-stage approach. In Proceedings - Sixth IEEE Symposium on BioInformatics and BioEngineering, BIBE 2006. 2006. p. 94-102. 4019646 https://doi.org/10.1109/BIBE.2006.253321