Improving the prediction accuracy in classification using the combined data sets by ranks of gene expressions

K. Y. Kim, D. H. Ki, H. C. Jeung, Hyuncheol Chung, SunYoung Rha

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Background: The information from different data sets experimented under different conditions may be inconsistent even though they are performed with the same research objectives. More than that, even when the data sets were generated from the same platform, the data agreement may be affected by the technical variation among the laboratories. In this case, it is necessary to use the combined data set after adjusting the differences between such data sets, for detecting the more reliable information. Results: The proposed method combines data sets posterior to the discretization of data sets based on the ranks of the gene expression ratios, and the statistical method is applied to the combined data set for predictive gene selection. The efficiency of the proposed method was evaluated using five colon cancer related data sets, which were experimented using cDNA microarrays with different RNA sources, and one experiment utilized oligonucleotide arrays. NCI-60 cell lines data sets were used, which were performed with two different platforms of cDNA microarrays and Affymetrix HU6800 oligonucleotide arrays. The combined data set by the proposed method predicted the test data sets more accurately than the separated data sets did. The biological significant genes were detected from the combined data set, which were missed on the separated data sets. Conclusion: By transforming gene expressions using ranks, the proposed method is not influenced by systematic bias among chips and normalization method. The method may be especially more useful to find predictive genes from data sets which have different scale in gene expressions.

Original languageEnglish
Number of pages1
JournalBMC Bioinformatics
Volume9
DOIs
Publication statusPublished - 2008 Jun 16

Fingerprint

Gene expression
Gene Expression
Genes
Oligonucleotides
Microarrays
Prediction
Complementary DNA
RNA
Statistical methods
Oligonucleotide Array Sequence Analysis
Cells
CDNA Microarray
Datasets
Experiments
Gene
Gene Selection
Oncogenes
Colonic Neoplasms
Inconsistent
Statistical method

All Science Journal Classification (ASJC) codes

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

@article{f61fadda2460418cb9dc1b27d2f70c74,
title = "Improving the prediction accuracy in classification using the combined data sets by ranks of gene expressions",
abstract = "Background: The information from different data sets experimented under different conditions may be inconsistent even though they are performed with the same research objectives. More than that, even when the data sets were generated from the same platform, the data agreement may be affected by the technical variation among the laboratories. In this case, it is necessary to use the combined data set after adjusting the differences between such data sets, for detecting the more reliable information. Results: The proposed method combines data sets posterior to the discretization of data sets based on the ranks of the gene expression ratios, and the statistical method is applied to the combined data set for predictive gene selection. The efficiency of the proposed method was evaluated using five colon cancer related data sets, which were experimented using cDNA microarrays with different RNA sources, and one experiment utilized oligonucleotide arrays. NCI-60 cell lines data sets were used, which were performed with two different platforms of cDNA microarrays and Affymetrix HU6800 oligonucleotide arrays. The combined data set by the proposed method predicted the test data sets more accurately than the separated data sets did. The biological significant genes were detected from the combined data set, which were missed on the separated data sets. Conclusion: By transforming gene expressions using ranks, the proposed method is not influenced by systematic bias among chips and normalization method. The method may be especially more useful to find predictive genes from data sets which have different scale in gene expressions.",
author = "Kim, {K. Y.} and Ki, {D. H.} and Jeung, {H. C.} and Hyuncheol Chung and SunYoung Rha",
year = "2008",
month = "6",
day = "16",
doi = "10.1186/1471-2105-9-283",
language = "English",
volume = "9",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

Improving the prediction accuracy in classification using the combined data sets by ranks of gene expressions. / Kim, K. Y.; Ki, D. H.; Jeung, H. C.; Chung, Hyuncheol; Rha, SunYoung.

In: BMC Bioinformatics, Vol. 9, 16.06.2008.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improving the prediction accuracy in classification using the combined data sets by ranks of gene expressions

AU - Kim, K. Y.

AU - Ki, D. H.

AU - Jeung, H. C.

AU - Chung, Hyuncheol

AU - Rha, SunYoung

PY - 2008/6/16

Y1 - 2008/6/16

N2 - Background: The information from different data sets experimented under different conditions may be inconsistent even though they are performed with the same research objectives. More than that, even when the data sets were generated from the same platform, the data agreement may be affected by the technical variation among the laboratories. In this case, it is necessary to use the combined data set after adjusting the differences between such data sets, for detecting the more reliable information. Results: The proposed method combines data sets posterior to the discretization of data sets based on the ranks of the gene expression ratios, and the statistical method is applied to the combined data set for predictive gene selection. The efficiency of the proposed method was evaluated using five colon cancer related data sets, which were experimented using cDNA microarrays with different RNA sources, and one experiment utilized oligonucleotide arrays. NCI-60 cell lines data sets were used, which were performed with two different platforms of cDNA microarrays and Affymetrix HU6800 oligonucleotide arrays. The combined data set by the proposed method predicted the test data sets more accurately than the separated data sets did. The biological significant genes were detected from the combined data set, which were missed on the separated data sets. Conclusion: By transforming gene expressions using ranks, the proposed method is not influenced by systematic bias among chips and normalization method. The method may be especially more useful to find predictive genes from data sets which have different scale in gene expressions.

AB - Background: The information from different data sets experimented under different conditions may be inconsistent even though they are performed with the same research objectives. More than that, even when the data sets were generated from the same platform, the data agreement may be affected by the technical variation among the laboratories. In this case, it is necessary to use the combined data set after adjusting the differences between such data sets, for detecting the more reliable information. Results: The proposed method combines data sets posterior to the discretization of data sets based on the ranks of the gene expression ratios, and the statistical method is applied to the combined data set for predictive gene selection. The efficiency of the proposed method was evaluated using five colon cancer related data sets, which were experimented using cDNA microarrays with different RNA sources, and one experiment utilized oligonucleotide arrays. NCI-60 cell lines data sets were used, which were performed with two different platforms of cDNA microarrays and Affymetrix HU6800 oligonucleotide arrays. The combined data set by the proposed method predicted the test data sets more accurately than the separated data sets did. The biological significant genes were detected from the combined data set, which were missed on the separated data sets. Conclusion: By transforming gene expressions using ranks, the proposed method is not influenced by systematic bias among chips and normalization method. The method may be especially more useful to find predictive genes from data sets which have different scale in gene expressions.

UR - http://www.scopus.com/inward/record.url?scp=46849103016&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46849103016&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-9-283

DO - 10.1186/1471-2105-9-283

M3 - Article

VL - 9

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

ER -