I'm using GSVA (v1.18.0) on R 3.2.2 and trying to perform a gene set analysis on a small data set (75 genes, 6 samples). However, whenever I set the bootstrap rounds to > 10, I end up with a segfault. As far as I can tell there is no issue with the data itself (e.g., genes with sd = 0). The details of my R session I provided below. Any pointers would be appreciated.(I face the same problem with R 3.2.3 on OS X 10.9.5)

My invocation I'm using is given below, and the input data (gdat, with row names being the Entrez Gene ID's) can be obtained from 

library(org.Hs.eg.db)
library(GSVA)
library(GSEABase)
library(GSVAdata)
data(c2BroadSets)
gse <- gsva(gdat,c2BroadSets,rnaseq=FALSE,min.sz=4,no.bootstraps=1000)

After a few gene sets it segfaults with the following error:

 *** caught segfault ***
address 0x7f01da2843a0, cause 'memory not mapped'
Traceback:
 1: .C("matrix_density_R", as.double(t(expr[, sample.idxs, drop = FALSE])),     as.double(t(expr)), R = double(n.test.samples * n.genes),     n.density.samples, n.test.samples, n.genes, as.integer(rnaseq))
 2: compute.gene.density(expr, sample.idxs, rnaseq, kernel)
 3: compute.geneset.es(expr, gset.idx.list, sample(n.samples, bootstrap.nsamples,     replace = T), rnaseq = rnaseq, abs.ranking = abs.ranking,     mx.diff = mx.diff, tau = tau, kernel = kernel, verbose = verbose)
 4: .gsva(expr, mapped.gset.idx.list, method, rnaseq, abs.ranking,     no.bootstraps, bootstrap.percent, parallel.sz, parallel.type,     mx.diff, tau, kernel, ssgsea.norm, verbose)
 5: .local(expr, gset.idx.list, ...)
 6: gsva(gdat, c2BroadSets, rnaseq = FALSE, min.sz = 4, no.bootstraps = 1000)
 7: gsva(gdat, c2BroadSets, rnaseq = FALSE, min.sz = 4, no.bootstraps = 1000)

The output of sessionInfo() is given below

> sessionInfo()

R version 3.2.2 (2015-08-14)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Scientific Linux release 6.7 (Carbon)

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8     LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8    LC_PAPER=en_US.UTF-8      
 [8] LC_NAME=C                  LC_ADDRESS=C               LC_TELEPHONE=C             LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] parallel  stats4    stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] GSVAdata_1.6.0       hgu95a.db_3.2.2      GSEABase_1.32.0      graph_1.48.0         annotate_1.48.0      XML_3.98-1.3         org.Hs.eg.db_3.2.3   RSQLite_1.0.0        DBI_0.3.1           
[10] AnnotationDbi_1.32.0 IRanges_1.22.10      Biobase_2.24.0       BiocGenerics_0.16.1  GSVA_1.18.0         

loaded via a namespace (and not attached):
[1] xtable_1.8-2     S4Vectors_0.8.11 tools_3.2.2     

Hi,

the expression data data set you provide cannot be used because it has duplicated gene identifiers (e.g., gene '780'). However, using one example data set (leukemia) from the GSVA package I cannot reproduce the problem in a similar setup like yours in linux:

library(org.Hs.eg.db)
library(GSVA)
library(GSEABase)
library(GSVAdata)
data(c2BroadSets)
data(leukemia) ## loads the 'leukemia_eset' ExpressionSet object
gse <- gsva(leukemia_eset,c2BroadSets,rnaseq=FALSE,min.sz=4,no.bootstraps=10) ## this runs fine

sessionInfo()

R version 3.2.2 (2015-08-14)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Fedora release 12 (Constantine)

locale:
 [1] LC_CTYPE=en_US.UTF8       LC_NUMERIC=C              LC_TIME=en_US.UTF8        LC_COLLATE=en_US.UTF8    
 [5] LC_MONETARY=en_US.UTF8    LC_MESSAGES=en_US.UTF8    LC_PAPER=en_US.UTF8       LC_NAME=C                
 [9] LC_ADDRESS=C              LC_TELEPHONE=C            LC_MEASUREMENT=en_US.UTF8 LC_IDENTIFICATION=C      

attached base packages:
[1] parallel  stats4    stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] GSVAdata_1.6.0       hgu95a.db_3.2.2      GSEABase_1.32.0      graph_1.48.0         annotate_1.48.0     
 [6] XML_3.98-1.3         GSVA_1.18.0          org.Hs.eg.db_3.2.3   RSQLite_1.0.0        DBI_0.3.1           
[11] AnnotationDbi_1.32.3 IRanges_2.4.7        S4Vectors_0.8.11     Biobase_2.30.0       BiocGenerics_0.16.1
[16] vimcom_1.2-3         setwidth_1.0-4       colorout_1.1-0      

loaded via a namespace (and not attached):
[1] xtable_1.8-2 tools_3.2.2

In any case, it is recommended that you upgrade to the latest BioC release 3.3 that just came out yesterday; see http://www.bioconductor.org/news/bioc_3_3_release.

cheers,

robert.