A multi-index ROC-based methodology for high throughput experiments in gene discovery

Dimitri Kagaris, Constantin Yiannoutsos

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We address the problem of ranking differentially expressed genes in high throughput experiments using Receiver Operating Characteristic (ROC) curves. As it is generally unknown whether large expression values constitute 'positive' or 'negative' results or which group is 'healthy' or 'diseased', we generate four ROC curves per gene. We then consider classification indices based on all or part of the four ROC curves and identify genes ranked low by the area under the curve (AUC) but high by at least one alternative index, invariably resulting to the discovery of genes that would otherwise be missed by the AUC index.

Original languageEnglish
Pages (from-to)42-65
Number of pages24
JournalInternational Journal of Data Mining and Bioinformatics
Volume8
Issue number1
DOIs
StatePublished - 2013

Fingerprint

Genetic Association Studies
ROC Curve
recipient
Genes
Throughput
Area Under Curve
experiment
methodology
Experiments
ranking
Values
Group

Keywords

  • Breast cancer
  • Gene expression
  • Gene selection
  • Microarray data analysis
  • Ovarian cancer
  • Receiver operating characteristic (ROC) curve

ASJC Scopus subject areas

  • Library and Information Sciences
  • Information Systems
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

@article{66f6aa3d9833462ea7166c190c6dc227,
title = "A multi-index ROC-based methodology for high throughput experiments in gene discovery",
abstract = "We address the problem of ranking differentially expressed genes in high throughput experiments using Receiver Operating Characteristic (ROC) curves. As it is generally unknown whether large expression values constitute 'positive' or 'negative' results or which group is 'healthy' or 'diseased', we generate four ROC curves per gene. We then consider classification indices based on all or part of the four ROC curves and identify genes ranked low by the area under the curve (AUC) but high by at least one alternative index, invariably resulting to the discovery of genes that would otherwise be missed by the AUC index.",
keywords = "Breast cancer, Gene expression, Gene selection, Microarray data analysis, Ovarian cancer, Receiver operating characteristic (ROC) curve",
author = "Dimitri Kagaris and Constantin Yiannoutsos",
year = "2013",
doi = "10.1504/IJDMB.2013.054693",
language = "English",
volume = "8",
pages = "42--65",
journal = "International Journal of Data Mining and Bioinformatics",
issn = "1748-5673",
publisher = "Inderscience Enterprises Ltd",
number = "1",

}

TY - JOUR

T1 - A multi-index ROC-based methodology for high throughput experiments in gene discovery

AU - Kagaris, Dimitri

AU - Yiannoutsos, Constantin

PY - 2013

Y1 - 2013

N2 - We address the problem of ranking differentially expressed genes in high throughput experiments using Receiver Operating Characteristic (ROC) curves. As it is generally unknown whether large expression values constitute 'positive' or 'negative' results or which group is 'healthy' or 'diseased', we generate four ROC curves per gene. We then consider classification indices based on all or part of the four ROC curves and identify genes ranked low by the area under the curve (AUC) but high by at least one alternative index, invariably resulting to the discovery of genes that would otherwise be missed by the AUC index.

AB - We address the problem of ranking differentially expressed genes in high throughput experiments using Receiver Operating Characteristic (ROC) curves. As it is generally unknown whether large expression values constitute 'positive' or 'negative' results or which group is 'healthy' or 'diseased', we generate four ROC curves per gene. We then consider classification indices based on all or part of the four ROC curves and identify genes ranked low by the area under the curve (AUC) but high by at least one alternative index, invariably resulting to the discovery of genes that would otherwise be missed by the AUC index.

KW - Breast cancer

KW - Gene expression

KW - Gene selection

KW - Microarray data analysis

KW - Ovarian cancer

KW - Receiver operating characteristic (ROC) curve

UR - http://www.scopus.com/inward/record.url?scp=84879665895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879665895&partnerID=8YFLogxK

U2 - 10.1504/IJDMB.2013.054693

DO - 10.1504/IJDMB.2013.054693

M3 - Article

VL - 8

SP - 42

EP - 65

JO - International Journal of Data Mining and Bioinformatics

JF - International Journal of Data Mining and Bioinformatics

SN - 1748-5673

IS - 1

ER -