metaMA (version 1.2)

EScombination: Effect size combination for unpaired data

Description

Calculates effect sizes from unpaired data either from classical or moderated t-tests (Limma, SMVar) for each study and combines these effect sizes.

Usage

EScombination(esets, classes, moderated = c("limma", "SMVar", "t")[1], BHth = 0.05)

Arguments

esets

List of matrices (or data frames), one matrix per study. Each matrix has one row per gene and one column per replicate and gives the expression data for both conditions with the order specified in the classes argument. All studies must have t

classes

List of class memberships, one per study. Each vector or factor of the list can only contain two levels which correspond to the two conditions studied.

moderated

Method to calculate the test statistic inside each study from which the effect size is computed. moderated has to be chosen between "limma", "SMVar" and "t".

BHth

Benjamini Hochberg threshold. By default, the False Discovery Rate is controlled at 5%.

Value

• List
• Study1
  Vector of indices of differentially expressed genes in study 1. Similar names are given for the other individual studies.
• AllIndStudies
  Vector of indices of differentially expressed genes found by at least one of the individual studies.
• Meta
  Vector of indices of differentially expressed genes in the meta-analysis.
• TestStatistic
  Vector with test statistics for differential expression in the meta-analysis.

References

Marot, G., Foulley, J.-L., Mayer, C.-D., Jaffrezic, F. (2009) Moderated effect size and p-value combinations for microarray meta-analyses. Bioinformatics. 25 (20): 2692-2699.

Examples

data(Singhdata)
#Meta-analysis
res=EScombination(esets=Singhdata$esets,classes=Singhdata$classes)
#Number of differentially expressed genes in the meta-analysis
length(res$Meta)
#To plot an histogram of raw p-values
rawpval=2*(1-pnorm(abs(res$TestStatistic)))
hist(rawpval,nclass=100)