ROAST

Rotation gene set tests for complex microarray experiments

Di Wu, Elgene Lim, François Vaillant, Marie-Liesse Labat, Jane E. Visvader, Gordon K. Smyth

Research output: Contribution to journalArticle

193 Citations (Scopus)

Abstract

Motivation: A gene set test is a differential expression analysis in which a P-value is assigned to a set of genes as a unit. Gene set tests are valuable for increasing statistical power, organizing and interpreting results and for relating expression patterns across different experiments. Existing methods are based on permutation. Methods that rely on permutation of probes unrealistically assume independence of genes, while those that rely on permutation of sample are suitable only for two-group comparisons with a good number of replicates in each group. Results: We present ROAST, a statistically rigorous gene set test that allows for gene-wise correlation while being applicable to almost any experimental design. Instead of permutation, ROAST uses rotation, a Monte Carlo technology for multivariate regression. Since the number of rotations does not depend on sample size, ROAST gives useful results even for experiments with minimal replication. ROAST allows for any experimental design that can be expressed as a linear model, and can also incorporate array weights and correlated samples. ROAST can be tuned for situations in which only a subset of the genes in the set are actively involved in the molecular pathway. ROAST can test for uni-or bi-direction regulation. Probes can also be weighted to allow for prior importance. The power and size of the ROAST procedure is demonstrated in a simulation study, and compared to that of a representative permutation method. Finally, ROAST is used to test the degree of transcriptional conservation between human and mouse mammary stems.

Original languageEnglish (US)
Article numberbtq401
Pages (from-to)2176-2182
Number of pages7
JournalBioinformatics
Volume26
Issue number17
DOIs
StatePublished - Jul 7 2010
Externally publishedYes

Fingerprint

Test Set
Microarrays
Microarray
Genes
Gene
Permutation
Experiment
Experiments
Experimental design
Design of experiments
Research Design
Probe
Statistical Power
Multivariate Regression
Differential Expression
Sample Size
Replication
Conservation
Mouse
Linear Models

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Wu, D., Lim, E., Vaillant, F., Labat, M-L., Visvader, J. E., & Smyth, G. K. (2010). ROAST: Rotation gene set tests for complex microarray experiments. Bioinformatics, 26(17), 2176-2182. [btq401]. https://doi.org/10.1093/bioinformatics/btq401

ROAST : Rotation gene set tests for complex microarray experiments. / Wu, Di; Lim, Elgene; Vaillant, François; Labat, Marie-Liesse; Visvader, Jane E.; Smyth, Gordon K.

In: Bioinformatics, Vol. 26, No. 17, btq401, 07.07.2010, p. 2176-2182.

Research output: Contribution to journalArticle

Wu, D, Lim, E, Vaillant, F, Labat, M-L, Visvader, JE & Smyth, GK 2010, 'ROAST: Rotation gene set tests for complex microarray experiments', Bioinformatics, vol. 26, no. 17, btq401, pp. 2176-2182. https://doi.org/10.1093/bioinformatics/btq401
Wu, Di ; Lim, Elgene ; Vaillant, François ; Labat, Marie-Liesse ; Visvader, Jane E. ; Smyth, Gordon K. / ROAST : Rotation gene set tests for complex microarray experiments. In: Bioinformatics. 2010 ; Vol. 26, No. 17. pp. 2176-2182.
@article{a1374137f599488ebc7ccfa2de464dc8,
title = "ROAST: Rotation gene set tests for complex microarray experiments",
abstract = "Motivation: A gene set test is a differential expression analysis in which a P-value is assigned to a set of genes as a unit. Gene set tests are valuable for increasing statistical power, organizing and interpreting results and for relating expression patterns across different experiments. Existing methods are based on permutation. Methods that rely on permutation of probes unrealistically assume independence of genes, while those that rely on permutation of sample are suitable only for two-group comparisons with a good number of replicates in each group. Results: We present ROAST, a statistically rigorous gene set test that allows for gene-wise correlation while being applicable to almost any experimental design. Instead of permutation, ROAST uses rotation, a Monte Carlo technology for multivariate regression. Since the number of rotations does not depend on sample size, ROAST gives useful results even for experiments with minimal replication. ROAST allows for any experimental design that can be expressed as a linear model, and can also incorporate array weights and correlated samples. ROAST can be tuned for situations in which only a subset of the genes in the set are actively involved in the molecular pathway. ROAST can test for uni-or bi-direction regulation. Probes can also be weighted to allow for prior importance. The power and size of the ROAST procedure is demonstrated in a simulation study, and compared to that of a representative permutation method. Finally, ROAST is used to test the degree of transcriptional conservation between human and mouse mammary stems.",
author = "Di Wu and Elgene Lim and Fran{\cc}ois Vaillant and Marie-Liesse Labat and Visvader, {Jane E.} and Smyth, {Gordon K.}",
year = "2010",
month = "7",
day = "7",
doi = "10.1093/bioinformatics/btq401",
language = "English (US)",
volume = "26",
pages = "2176--2182",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "17",

}

TY - JOUR

T1 - ROAST

T2 - Rotation gene set tests for complex microarray experiments

AU - Wu, Di

AU - Lim, Elgene

AU - Vaillant, François

AU - Labat, Marie-Liesse

AU - Visvader, Jane E.

AU - Smyth, Gordon K.

PY - 2010/7/7

Y1 - 2010/7/7

N2 - Motivation: A gene set test is a differential expression analysis in which a P-value is assigned to a set of genes as a unit. Gene set tests are valuable for increasing statistical power, organizing and interpreting results and for relating expression patterns across different experiments. Existing methods are based on permutation. Methods that rely on permutation of probes unrealistically assume independence of genes, while those that rely on permutation of sample are suitable only for two-group comparisons with a good number of replicates in each group. Results: We present ROAST, a statistically rigorous gene set test that allows for gene-wise correlation while being applicable to almost any experimental design. Instead of permutation, ROAST uses rotation, a Monte Carlo technology for multivariate regression. Since the number of rotations does not depend on sample size, ROAST gives useful results even for experiments with minimal replication. ROAST allows for any experimental design that can be expressed as a linear model, and can also incorporate array weights and correlated samples. ROAST can be tuned for situations in which only a subset of the genes in the set are actively involved in the molecular pathway. ROAST can test for uni-or bi-direction regulation. Probes can also be weighted to allow for prior importance. The power and size of the ROAST procedure is demonstrated in a simulation study, and compared to that of a representative permutation method. Finally, ROAST is used to test the degree of transcriptional conservation between human and mouse mammary stems.

AB - Motivation: A gene set test is a differential expression analysis in which a P-value is assigned to a set of genes as a unit. Gene set tests are valuable for increasing statistical power, organizing and interpreting results and for relating expression patterns across different experiments. Existing methods are based on permutation. Methods that rely on permutation of probes unrealistically assume independence of genes, while those that rely on permutation of sample are suitable only for two-group comparisons with a good number of replicates in each group. Results: We present ROAST, a statistically rigorous gene set test that allows for gene-wise correlation while being applicable to almost any experimental design. Instead of permutation, ROAST uses rotation, a Monte Carlo technology for multivariate regression. Since the number of rotations does not depend on sample size, ROAST gives useful results even for experiments with minimal replication. ROAST allows for any experimental design that can be expressed as a linear model, and can also incorporate array weights and correlated samples. ROAST can be tuned for situations in which only a subset of the genes in the set are actively involved in the molecular pathway. ROAST can test for uni-or bi-direction regulation. Probes can also be weighted to allow for prior importance. The power and size of the ROAST procedure is demonstrated in a simulation study, and compared to that of a representative permutation method. Finally, ROAST is used to test the degree of transcriptional conservation between human and mouse mammary stems.

UR - http://www.scopus.com/inward/record.url?scp=77955889132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955889132&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btq401

DO - 10.1093/bioinformatics/btq401

M3 - Article

VL - 26

SP - 2176

EP - 2182

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 17

M1 - btq401

ER -