message=paste0("The number of peaks is very high, subsequent steps may be slow, particularly in the prepareBinning and binningTF steps. Make sure the preparingBinning step has enough memory available. We recommend at least 50 GB. Alternatively, consider decreasing the number of peaks for improved performance.")
message=paste0("In addition to the high number of peaks, more than 5 permutations have been selected, which will further increase running times and memory footprint. Consider decreasing the number of peaks for improved performance.")
message=paste0("At least 3 columns are required, but only ",ncol(peaks.df)," columns have been found in the file ",snakemake@config$peaks$consensusPeaks)
# methods needed here because Rscript does not loads this package automatically, see http://stackoverflow.com/questions/19468506/rscript-could-not-find-function
...
...
@@ -106,80 +106,96 @@ if (nrow(TF.motifs.ori) == 0) {
stop(message)
}
# TODO: eventuell löschen: chr, MSS, MES, PSS, PES
#Filter permutations in the original files that the user does not want anymore
message<-paste0("The file ",fileCur," contains ",nRowsNA," rows out of ",nrow(TF.motifs.CG.cur)," with a missing value for the CG content, which most likely results from an assembly discordance between the BAM files and the specified fasta file. These regions will be removed in subsequent steps. The first 10 are printed with their first 3 columns here for debugging purposes:")
stop("Error when parsing the file ",fileCur,", see errors above")
}
colnames(TF.motifs.CG.cur)=c("TFBSID","TF","CG")
nRowsNA=length(which(is.na(TF.motifs.CG.cur$CG)))
if(nRowsNA>0){
message<-paste0("The file ",fileCur," contains ",nRowsNA," rows out of ",nrow(TF.motifs.CG.cur)," with a missing value for the CG content, which most likely results from an assembly discordance between the BAM files and the specified fasta file. These regions will be removed in subsequent steps. The first 10 are printed with their first 3 columns here for debugging purposes:")
