\name{collectionGsea} \alias{collectionGsea} \title{ Compute observed and permutation-based enrichment scores for a collection (list) of gene sets } \description{ This function computes observed and permutation-based scores associated with a gene set enrichment analysis for a collection of gene sets. } \usage{ collectionGsea(collectionOfGeneSets, geneList, exponent=1, nPermutations= 1000, minGeneSetSize=15, verbose=TRUE) } \arguments{ \item{collectionOfGeneSets}{ a list of gene sets. Each gene set in the list is a character vector of gene identifiers. } \item{geneList}{ a numeric or integer vector which has been named and ordered. It cannot contain any duplicates nor NAs. } \item{exponent}{ a single numeric or integer value (set as 1 by default) specifying the exponent of the GSEA method. } \item{nPermutations}{ a single numeric or integer value specifying the number of permutation tests for each gene set } \item{minGeneSetSize}{ a single numeric or integer value specifying the minimum size required for a gene set to be considered. } \item{verbose}{ a single logical value specifying to display detailed messages (when verbose=TRUE) or not (when verbose=FALSE) } } \value{ \item{Observed.scores}{The observed scores for the given gene sets (a named vector)} \item{Permutation.scores}{The scores for the permutation tests (one column for each permutation and a row for each gene set)} } \references{ Subramanian, A., Tamayo, P., Mootha, V. K., Mukherjee, S., Ebert, B. L., Gillette, M. A., Paulovich, A., Pomeroy, S. L., Golub, T. R., Lander, E. S. & Mesirov, J. P. (2005) \emph{ Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles.} Proc. Natl. Acad. Sci. USA 102, 15545-15550. } \author{ Camille Terfve, Xin Wang } \seealso{ \code{\link[HTSanalyzeR:FDRcollectionGsea]{FDRcollectionGsea}} } \examples{ ##example 1 gl <- runif(100, min=0, max=5) gl <- gl[order(gl, decreasing=TRUE)] names(gl) <- as.character(sample(x=seq(from=1, to=100, by=1), size=100, replace=FALSE)) gs1 <- sample(names(gl), size=20, replace=FALSE) gs2 <- sample(names(gl), size=20, replace=FALSE) gsc <- list(subset1=gs1, subset2=gs2) GSCscores <- collectionGsea(collectionOfGeneSets=gsc, geneList=gl, exponent=1, nPermutations=1000, minGeneSetSize=5) GSCpvalues <- permutationPvalueCollectionGsea(permScores= GSCscores$Permutation.scores, dataScores=GSCscores$Observed.scores) ##example 2 \dontrun{ library(org.Dm.eg.db) library(KEGG.db) ##load phenotype vector (see the vignette for details about the ##preprocessing of this data set) data("KcViab_Data4Enrich") DM_KEGG <- KeggGeneSets(species="Dm") GSCscores <- collectionGsea(collectionOfGeneSets=DM_KEGG, geneList= KcViab_Data4Enrich, exponent=1, nPermutations=1000, minGeneSetSize=100) GSCpvalues <- permutationPvalueCollectionGsea(permScores= GSCscores$Permutation.scores, dataScores=GSCscores$Observed.scores) } }