Mercurial > repos > lecorguille > msnbase_readmsdata
changeset 14:11ab2081bd4a draft
"planemo upload for repository https://github.com/workflow4metabolomics/xcms commit dff3ac53c7c305ff263e6358308db48cf9ed4e27"
| author | workflow4metabolomics |
|---|---|
| date | Mon, 12 Apr 2021 09:35:02 +0000 |
| parents | 226fb89cacc4 |
| children | 7faf9b2d83f6 |
| files | README.rst lib.r macros_msnbase.xml msnbase_readmsdata.r msnbase_readmsdata.xml repository_dependencies.xml |
| diffstat | 6 files changed, 175 insertions(+), 133 deletions(-) [+] |
line wrap: on
line diff
--- a/README.rst Wed Feb 12 08:27:38 2020 -0500 +++ b/README.rst Mon Apr 12 09:35:02 2021 +0000 @@ -2,6 +2,12 @@ Changelog/News -------------- +.. _News: https://lgatto.github.io/MSnbase/news/index.html + +**Version 2.16.1+galaxy0 - 08/04/2019** + +- UPGRADE: upgrade the MSnbase version from 2.8.2 to 2.16.1 (see MSnbase News_). Almost all the new features may not concern our usage of MSnbase. + **Version 2.8.2.1 - 30/04/2019** - BUGFIX: remove the pre-compute of the chromatograms which was memory consuming. Now, only xcms plot chromatogram will generate the Chromatograms.
--- a/lib.r Wed Feb 12 08:27:38 2020 -0500 +++ b/lib.r Mon Apr 12 09:35:02 2021 +0000 @@ -6,8 +6,8 @@ parseCommandArgs <- function(...) { args <- batch::parseCommandArgs(...) for (key in names(args)) { - if (args[key] %in% c("TRUE","FALSE")) - args[key] = as.logical(args[key]) + if (args[key] %in% c("TRUE", "FALSE")) + args[key] <- as.logical(args[key]) } return(args) } @@ -17,14 +17,20 @@ # - load the packages # - display the sessionInfo loadAndDisplayPackages <- function(pkgs) { - for(pkg in pkgs) suppressPackageStartupMessages( stopifnot( library(pkg, quietly=TRUE, logical.return=TRUE, character.only=TRUE))) + for (pkg in pkgs) suppressPackageStartupMessages(stopifnot(library(pkg, quietly = TRUE, logical.return = TRUE, character.only = TRUE))) - sessioninfo = sessionInfo() - cat(sessioninfo$R.version$version.string,"\n") + sessioninfo <- sessionInfo() + cat(sessioninfo$R.version$version.string, "\n") cat("Main packages:\n") - for (pkg in names(sessioninfo$otherPkgs)) { cat(paste(pkg,packageVersion(pkg)),"\t") }; cat("\n") + for (pkg in names(sessioninfo$otherPkgs)) { + cat(paste(pkg, packageVersion(pkg)), "\t") + } + cat("\n") cat("Other loaded packages:\n") - for (pkg in names(sessioninfo$loadedOnly)) { cat(paste(pkg,packageVersion(pkg)),"\t") }; cat("\n") + for (pkg in names(sessioninfo$loadedOnly)) { + cat(paste(pkg, packageVersion(pkg)), "\t") + } + cat("\n") } #@author G. Le Corguille @@ -43,20 +49,20 @@ chromTIC_adjusted <- NULL chromBPI_adjusted <- NULL md5sumList <- NULL - for(image in args$images) { + for (image in args$images) { load(image) # Handle infiles if (!exists("singlefile")) singlefile <- NULL if (!exists("zipfile")) zipfile <- NULL - rawFilePath <- retrieveRawfileInTheWorkingDirectory(singlefile, zipfile, args) + rawFilePath <- retrieveRawfileInTheWorkingDir(singlefile, zipfile, args) zipfile <- rawFilePath$zipfile singlefile <- rawFilePath$singlefile if (exists("raw_data")) xdata <- raw_data if (!exists("xdata")) stop("\n\nERROR: The RData doesn't contain any object called 'xdata'. This RData should have been created by an old version of XMCS 2.*") - cat(sampleNamesList$sampleNamesOrigin,"\n") + cat(sampleNamesList$sampleNamesOrigin, "\n") if (!exists("xdata_merged")) { xdata_merged <- xdata @@ -68,14 +74,14 @@ chromTIC_adjusted_merged <- chromTIC_adjusted chromBPI_adjusted_merged <- chromBPI_adjusted } else { - if (is(xdata, "XCMSnExp")) xdata_merged <- c(xdata_merged,xdata) - else if (is(xdata, "OnDiskMSnExp")) xdata_merged <- xcms:::.concatenate_OnDiskMSnExp(xdata_merged,xdata) + if (is(xdata, "XCMSnExp")) xdata_merged <- c(xdata_merged, xdata) + else if (is(xdata, "OnDiskMSnExp")) xdata_merged <- xcms:::.concatenate_OnDiskMSnExp(xdata_merged, xdata) else stop("\n\nERROR: The RData either a OnDiskMSnExp object called raw_data or a XCMSnExp object called xdata") - singlefile_merged <- c(singlefile_merged,singlefile) - md5sumList_merged$origin <- rbind(md5sumList_merged$origin,md5sumList$origin) - sampleNamesList_merged$sampleNamesOrigin <- c(sampleNamesList_merged$sampleNamesOrigin,sampleNamesList$sampleNamesOrigin) - sampleNamesList_merged$sampleNamesMakeNames <- c(sampleNamesList_merged$sampleNamesMakeNames,sampleNamesList$sampleNamesMakeNames) + singlefile_merged <- c(singlefile_merged, singlefile) + md5sumList_merged$origin <- rbind(md5sumList_merged$origin, md5sumList$origin) + sampleNamesList_merged$sampleNamesOrigin <- c(sampleNamesList_merged$sampleNamesOrigin, sampleNamesList$sampleNamesOrigin) + sampleNamesList_merged$sampleNamesMakeNames <- c(sampleNamesList_merged$sampleNamesMakeNames, sampleNamesList$sampleNamesMakeNames) chromTIC_merged <- mergeChrom(chromTIC_merged, chromTIC) chromBPI_merged <- mergeChrom(chromBPI_merged, chromBPI) chromTIC_adjusted_merged <- mergeChrom(chromTIC_adjusted_merged, chromTIC_adjusted) @@ -91,73 +97,93 @@ if (!is.null(args$sampleMetadata)) { cat("\tXSET PHENODATA SETTING...\n") sampleMetadataFile <- args$sampleMetadata - sampleMetadata <- getDataFrameFromFile(sampleMetadataFile, header=F) - xdata@phenoData@data$sample_group=sampleMetadata$V2[match(xdata@phenoData@data$sample_name,sampleMetadata$V1)] + sampleMetadata <- getDataFrameFromFile(sampleMetadataFile, header = F) + xdata@phenoData@data$sample_group <- sampleMetadata$V2[match(xdata@phenoData@data$sample_name, sampleMetadata$V1)] if (any(is.na(pData(xdata)$sample_group))) { sample_missing <- pData(xdata)$sample_name[is.na(pData(xdata)$sample_group)] - error_message <- paste("Those samples are missing in your sampleMetadata:", paste(sample_missing, collapse=" ")) + error_message <- paste("Those samples are missing in your sampleMetadata:", paste(sample_missing, collapse = " ")) print(error_message) stop(error_message) } } - if (!is.null(chromTIC_merged)) { chromTIC <- chromTIC_merged; chromTIC@phenoData <- xdata@phenoData } - if (!is.null(chromBPI_merged)) { chromBPI <- chromBPI_merged; chromBPI@phenoData <- xdata@phenoData } - if (!is.null(chromTIC_adjusted_merged)) { chromTIC_adjusted <- chromTIC_adjusted_merged; chromTIC_adjusted@phenoData <- xdata@phenoData } - if (!is.null(chromBPI_adjusted_merged)) { chromBPI_adjusted <- chromBPI_adjusted_merged; chromBPI_adjusted@phenoData <- xdata@phenoData } + if (!is.null(chromTIC_merged)) { + chromTIC <- chromTIC_merged; chromTIC@phenoData <- xdata@phenoData + } + if (!is.null(chromBPI_merged)) { + chromBPI <- chromBPI_merged; chromBPI@phenoData <- xdata@phenoData + } + if (!is.null(chromTIC_adjusted_merged)) { + chromTIC_adjusted <- chromTIC_adjusted_merged; chromTIC_adjusted@phenoData <- xdata@phenoData + } + if (!is.null(chromBPI_adjusted_merged)) { + chromBPI_adjusted <- chromBPI_adjusted_merged; chromBPI_adjusted@phenoData <- xdata@phenoData + } - return(list("xdata"=xdata, "singlefile"=singlefile, "md5sumList"=md5sumList,"sampleNamesList"=sampleNamesList, "chromTIC"=chromTIC, "chromBPI"=chromBPI, "chromTIC_adjusted"=chromTIC_adjusted, "chromBPI_adjusted"=chromBPI_adjusted)) + return(list("xdata" = xdata, "singlefile" = singlefile, "md5sumList" = md5sumList, "sampleNamesList" = sampleNamesList, "chromTIC" = chromTIC, "chromBPI" = chromBPI, "chromTIC_adjusted" = chromTIC_adjusted, "chromBPI_adjusted" = chromBPI_adjusted)) } #@author G. Le Corguille # This function convert if it is required the Retention Time in minutes RTSecondToMinute <- function(variableMetadata, convertRTMinute) { - if (convertRTMinute){ + if (convertRTMinute) { #converting the retention times (seconds) into minutes print("converting the retention times into minutes in the variableMetadata") - variableMetadata[,"rt"] <- variableMetadata[,"rt"]/60 - variableMetadata[,"rtmin"] <- variableMetadata[,"rtmin"]/60 - variableMetadata[,"rtmax"] <- variableMetadata[,"rtmax"]/60 + variableMetadata[, "rt"] <- variableMetadata[, "rt"] / 60 + variableMetadata[, "rtmin"] <- variableMetadata[, "rtmin"] / 60 + variableMetadata[, "rtmax"] <- variableMetadata[, "rtmax"] / 60 } - return (variableMetadata) + return(variableMetadata) } #@author G. Le Corguille # This function format ions identifiers -formatIonIdentifiers <- function(variableMetadata, numDigitsRT=0, numDigitsMZ=0) { - splitDeco <- strsplit(as.character(variableMetadata$name),"_") - idsDeco <- sapply(splitDeco, function(x) { deco=unlist(x)[2]; if (is.na(deco)) return ("") else return(paste0("_",deco)) }) - namecustom <- make.unique(paste0("M",round(variableMetadata[,"mz"],numDigitsMZ),"T",round(variableMetadata[,"rt"],numDigitsRT),idsDeco)) - variableMetadata <- cbind(name=variableMetadata$name, namecustom=namecustom, variableMetadata[,!(colnames(variableMetadata) %in% c("name"))]) +formatIonIdentifiers <- function(variableMetadata, numDigitsRT = 0, numDigitsMZ = 0) { + splitDeco <- strsplit(as.character(variableMetadata$name), "_") + idsDeco <- sapply(splitDeco, + function(x) { + deco <- unlist(x)[2]; if (is.na(deco)) return("") else return(paste0("_", deco)) + } + ) + namecustom <- make.unique(paste0("M", round(variableMetadata[, "mz"], numDigitsMZ), "T", round(variableMetadata[, "rt"], numDigitsRT), idsDeco)) + variableMetadata <- cbind(name = variableMetadata$name, namecustom = namecustom, variableMetadata[, !(colnames(variableMetadata) %in% c("name"))]) return(variableMetadata) } #@author G. Le Corguille # This function convert the remain NA to 0 in the dataMatrix naTOzeroDataMatrix <- function(dataMatrix, naTOzero) { - if (naTOzero){ + if (naTOzero) { dataMatrix[is.na(dataMatrix)] <- 0 } - return (dataMatrix) + return(dataMatrix) } #@author G. Le Corguille # Draw the plotChromPeakDensity 3 per page in a pdf file -getPlotChromPeakDensity <- function(xdata, param = NULL, mzdigit=4) { - pdf(file="plotChromPeakDensity.pdf", width=16, height=12) +getPlotChromPeakDensity <- function(xdata, param = NULL, mzdigit = 4) { + pdf(file = "plotChromPeakDensity.pdf", width = 16, height = 12) par(mfrow = c(3, 1), mar = c(4, 4, 1, 0.5)) - group_colors <- brewer.pal(length(unique(xdata$sample_group)), "Set1") + if (length(unique(xdata$sample_group)) < 10) { + group_colors <- brewer.pal(length(unique(xdata$sample_group)), "Set1") + }else{ + group_colors <- hcl.colors(length(unique(xdata$sample_group)), palette = "Dark 3") + } names(group_colors) <- unique(xdata$sample_group) + col_per_samp <- as.character(xdata$sample_group) + for (i in seq_len(length(group_colors))) { + col_per_samp[col_per_samp == (names(group_colors)[i])] <- group_colors[i] + } xlim <- c(min(featureDefinitions(xdata)$rtmin), max(featureDefinitions(xdata)$rtmax)) - for (i in 1:nrow(featureDefinitions(xdata))) { - mzmin = featureDefinitions(xdata)[i,]$mzmin - mzmax = featureDefinitions(xdata)[i,]$mzmax - plotChromPeakDensity(xdata, param = param, mz=c(mzmin,mzmax), col=group_colors, pch=16, xlim=xlim, main=paste(round(mzmin,mzdigit),round(mzmax,mzdigit))) - legend("topright", legend=names(group_colors), col=group_colors, cex=0.8, lty=1) + for (i in seq_len(nrow(featureDefinitions(xdata)))) { + mzmin <- featureDefinitions(xdata)[i, ]$mzmin + mzmax <- featureDefinitions(xdata)[i, ]$mzmax + plotChromPeakDensity(xdata, param = param, mz = c(mzmin, mzmax), col = col_per_samp, pch = 16, xlim = xlim, main = paste(round(mzmin, mzdigit), round(mzmax, mzdigit))) + legend("topright", legend = names(group_colors), col = group_colors, cex = 0.8, lty = 1) } dev.off() @@ -167,53 +193,57 @@ # Draw the plotChromPeakDensity 3 per page in a pdf file getPlotAdjustedRtime <- function(xdata) { - pdf(file="raw_vs_adjusted_rt.pdf", width=16, height=12) + pdf(file = "raw_vs_adjusted_rt.pdf", width = 16, height = 12) # Color by group - group_colors <- brewer.pal(length(unique(xdata$sample_group)), "Set1") + if (length(unique(xdata$sample_group)) < 10) { + group_colors <- brewer.pal(length(unique(xdata$sample_group)), "Set1") + } else { + group_colors <- hcl.colors(length(unique(xdata$sample_group)), palette = "Dark 3") + } if (length(group_colors) > 1) { names(group_colors) <- unique(xdata$sample_group) plotAdjustedRtime(xdata, col = group_colors[xdata$sample_group]) - legend("topright", legend=names(group_colors), col=group_colors, cex=0.8, lty=1) + legend("topright", legend = names(group_colors), col = group_colors, cex = 0.8, lty = 1) } # Color by sample plotAdjustedRtime(xdata, col = rainbow(length(xdata@phenoData@data$sample_name))) - legend("topright", legend=xdata@phenoData@data$sample_name, col=rainbow(length(xdata@phenoData@data$sample_name)), cex=0.8, lty=1) + legend("topright", legend = xdata@phenoData@data$sample_name, col = rainbow(length(xdata@phenoData@data$sample_name)), cex = 0.8, lty = 1) dev.off() } #@author G. Le Corguille # value: intensity values to be used into, maxo or intb -getPeaklistW4M <- function(xdata, intval="into", convertRTMinute=F, numDigitsMZ=4, numDigitsRT=0, naTOzero=T, variableMetadataOutput, dataMatrixOutput, sampleNamesList) { - dataMatrix <- featureValues(xdata, method="medret", value=intval) +getPeaklistW4M <- function(xdata, intval = "into", convertRTMinute = F, numDigitsMZ = 4, numDigitsRT = 0, naTOzero = T, variableMetadataOutput, dataMatrixOutput, sampleNamesList) { + dataMatrix <- featureValues(xdata, method = "medret", value = intval) colnames(dataMatrix) <- make.names(tools::file_path_sans_ext(colnames(dataMatrix))) - dataMatrix = cbind(name=groupnames(xdata), dataMatrix) + dataMatrix <- cbind(name = groupnames(xdata), dataMatrix) variableMetadata <- featureDefinitions(xdata) - colnames(variableMetadata)[1] = "mz"; colnames(variableMetadata)[4] = "rt" - variableMetadata = data.frame(name=groupnames(xdata), variableMetadata) + colnames(variableMetadata)[1] <- "mz"; colnames(variableMetadata)[4] <- "rt" + variableMetadata <- data.frame(name = groupnames(xdata), variableMetadata) variableMetadata <- RTSecondToMinute(variableMetadata, convertRTMinute) - variableMetadata <- formatIonIdentifiers(variableMetadata, numDigitsRT=numDigitsRT, numDigitsMZ=numDigitsMZ) + variableMetadata <- formatIonIdentifiers(variableMetadata, numDigitsRT = numDigitsRT, numDigitsMZ = numDigitsMZ) dataMatrix <- naTOzeroDataMatrix(dataMatrix, naTOzero) # FIX: issue when the vector at peakidx is too long and is written in a new line during the export - variableMetadata[,"peakidx"] <- vapply(variableMetadata[,"peakidx"], FUN = paste, FUN.VALUE = character(1), collapse = ",") + variableMetadata[, "peakidx"] <- vapply(variableMetadata[, "peakidx"], FUN = paste, FUN.VALUE = character(1), collapse = ",") - write.table(variableMetadata, file=variableMetadataOutput,sep="\t",quote=F,row.names=F) - write.table(dataMatrix, file=dataMatrixOutput,sep="\t",quote=F,row.names=F) + write.table(variableMetadata, file = variableMetadataOutput, sep = "\t", quote = F, row.names = F) + write.table(dataMatrix, file = dataMatrixOutput, sep = "\t", quote = F, row.names = F) } #@author G. Le Corguille # It allow different of field separators -getDataFrameFromFile <- function(filename, header=T) { - myDataFrame <- read.table(filename, header=header, sep=";", stringsAsFactors=F) - if (ncol(myDataFrame) < 2) myDataFrame <- read.table(filename, header=header, sep="\t", stringsAsFactors=F) - if (ncol(myDataFrame) < 2) myDataFrame <- read.table(filename, header=header, sep=",", stringsAsFactors=F) +getDataFrameFromFile <- function(filename, header = T) { + myDataFrame <- read.table(filename, header = header, sep = ";", stringsAsFactors = F) + if (ncol(myDataFrame) < 2) myDataFrame <- read.table(filename, header = header, sep = "\t", stringsAsFactors = F) + if (ncol(myDataFrame) < 2) myDataFrame <- read.table(filename, header = header, sep = ",", stringsAsFactors = F) if (ncol(myDataFrame) < 2) { - error_message="Your tabular file seems not well formatted. The column separators accepted are ; , and tabulation" + error_message <- "Your tabular file seems not well formatted. The column separators accepted are ; , and tabulation" print(error_message) stop(error_message) } @@ -223,32 +253,36 @@ #@author G. Le Corguille # Draw the BPI and TIC graphics # colored by sample names or class names -getPlotChromatogram <- function(chrom, xdata, pdfname="Chromatogram.pdf", aggregationFun = "max") { +getPlotChromatogram <- function(chrom, xdata, pdfname = "Chromatogram.pdf", aggregationFun = "max") { if (aggregationFun == "sum") - type="Total Ion Chromatograms" + type <- "Total Ion Chromatograms" else - type="Base Peak Intensity Chromatograms" + type <- "Base Peak Intensity Chromatograms" - adjusted="Raw" + adjusted <- "Raw" if (hasAdjustedRtime(xdata)) - adjusted="Adjusted" + adjusted <- "Adjusted" - main <- paste(type,":",adjusted,"data") + main <- paste(type, ":", adjusted, "data") - pdf(pdfname, width=16, height=10) + pdf(pdfname, width = 16, height = 10) # Color by group - group_colors <- brewer.pal(length(unique(xdata$sample_group)), "Set1") + if (length(unique(xdata$sample_group)) < 10) { + group_colors <- brewer.pal(length(unique(xdata$sample_group)), "Set1") + }else{ + group_colors <- hcl.colors(length(unique(xdata$sample_group)), palette = "Dark 3") + } if (length(group_colors) > 1) { names(group_colors) <- unique(xdata$sample_group) - plot(chrom, col = group_colors[as.factor(chrom$sample_group)], main=main, peakType = "none") - legend("topright", legend=names(group_colors), col=group_colors, cex=0.8, lty=1) + plot(chrom, col = group_colors[chrom$sample_group], main = main, peakType = "none") + legend("topright", legend = names(group_colors), col = group_colors, cex = 0.8, lty = 1) } # Color by sample - plot(chrom, col = rainbow(length(xdata@phenoData@data$sample_name)), main=main, peakType = "none") - legend("topright", legend=xdata@phenoData@data$sample_name, col=rainbow(length(xdata@phenoData@data$sample_name)), cex=0.8, lty=1) + plot(chrom, col = rainbow(length(xdata@phenoData@data$sample_name)), main = main, peakType = "none") + legend("topright", legend = xdata@phenoData@data$sample_name, col = rainbow(length(xdata@phenoData@data$sample_name)), cex = 0.8, lty = 1) dev.off() } @@ -257,7 +291,7 @@ # Get the polarities from all the samples of a condition #@author Misharl Monsoor misharl.monsoor@sb-roscoff.fr ABiMS TEAM #@author Gildas Le Corguille lecorguille@sb-roscoff.fr ABiMS TEAM -getSampleMetadata <- function(xdata=NULL, sampleMetadataOutput="sampleMetadata.tsv") { +getSampleMetadata <- function(xdata = NULL, sampleMetadataOutput = "sampleMetadata.tsv") { cat("Creating the sampleMetadata file...\n") #Create the sampleMetada dataframe @@ -271,7 +305,7 @@ if (any(duplicated(sampleNamesMakeNames))) { write("\n\nERROR: Usually, R has trouble to deal with special characters in its column names, so it rename them using make.names().\nIn your case, at least two columns after the renaming obtain the same name, thus XCMS will collapse those columns per name.", stderr()) for (sampleName in sampleNamesOrigin) { - write(paste(sampleName,"\t->\t",make.names(sampleName)),stderr()) + write(paste(sampleName, "\t->\t", make.names(sampleName)), stderr()) } stop("\n\nERROR: One or more of your files will not be import by xcmsSet. It may due to bad characters in their filenames.") } @@ -279,7 +313,7 @@ if (!all(sampleNamesOrigin == sampleNamesMakeNames)) { cat("\n\nWARNING: Usually, R has trouble to deal with special characters in its column names, so it rename them using make.names()\nIn your case, one or more sample names will be renamed in the sampleMetadata and dataMatrix files:\n") for (sampleName in sampleNamesOrigin) { - cat(paste(sampleName,"\t->\t",make.names(sampleName),"\n")) + cat(paste(sampleName, "\t->\t", make.names(sampleName), "\n")) } } @@ -287,7 +321,7 @@ #For each sample file, the following actions are done - for (fileIdx in 1:length(fileNames(xdata))) { + for (fileIdx in seq_len(length(fileNames(xdata)))) { #Check if the file is in the CDF format if (!mzR:::netCDFIsFile(fileNames(xdata))) { @@ -295,10 +329,10 @@ if (is.null(sampleMetadata$polarity)) sampleMetadata$polarity <- NA #Extract the polarity (a list of polarities) - polarity <- fData(xdata)[fData(xdata)$fileIdx == fileIdx,"polarity"] + polarity <- fData(xdata)[fData(xdata)$fileIdx == fileIdx, "polarity"] #Verify if all the scans have the same polarity uniq_list <- unique(polarity) - if (length(uniq_list)>1){ + if (length(uniq_list) > 1) { polarity <- "mixed" } else { polarity <- as.character(uniq_list) @@ -310,16 +344,16 @@ } - write.table(sampleMetadata, sep="\t", quote=FALSE, row.names=FALSE, file=sampleMetadataOutput) + write.table(sampleMetadata, sep = "\t", quote = FALSE, row.names = FALSE, file = sampleMetadataOutput) - return(list("sampleNamesOrigin"=sampleNamesOrigin, "sampleNamesMakeNames"=sampleNamesMakeNames)) + return(list("sampleNamesOrigin" = sampleNamesOrigin, "sampleNamesMakeNames" = sampleNamesMakeNames)) } # This function will compute MD5 checksum to check the data integrity #@author Gildas Le Corguille lecorguille@sb-roscoff.fr -getMd5sum <- function (files) { +getMd5sum <- function(files) { cat("Compute md5 checksum...\n") library(tools) return(as.matrix(md5sum(files))) @@ -329,71 +363,71 @@ # - if zipfile: unzip the file with its directory tree # - if singlefiles: set symlink with the good filename #@author Gildas Le Corguille lecorguille@sb-roscoff.fr -retrieveRawfileInTheWorkingDirectory <- function(singlefile, zipfile, args, prefix="") { +retrieveRawfileInTheWorkingDir <- function(singlefile, zipfile, args, prefix = "") { - if (!(prefix %in% c("","Positive","Negative","MS1","MS2"))) stop("prefix must be either '', 'Positive', 'Negative', 'MS1' or 'MS2'") + if (!(prefix %in% c("", "Positive", "Negative", "MS1", "MS2"))) stop("prefix must be either '', 'Positive', 'Negative', 'MS1' or 'MS2'") # single - if the file are passed in the command arguments -> refresh singlefile - if (!is.null(args[[paste0("singlefile_galaxyPath",prefix)]])) { - singlefile_galaxyPaths <- unlist(strsplit(args[[paste0("singlefile_galaxyPath",prefix)]],"\\|")) - singlefile_sampleNames <- unlist(strsplit(args[[paste0("singlefile_sampleName",prefix)]],"\\|")) + if (!is.null(args[[paste0("singlefile_galaxyPath", prefix)]])) { + singlefile_galaxyPaths <- unlist(strsplit(args[[paste0("singlefile_galaxyPath", prefix)]], "\\|")) + singlefile_sampleNames <- unlist(strsplit(args[[paste0("singlefile_sampleName", prefix)]], "\\|")) singlefile <- NULL - for (singlefile_galaxyPath_i in seq(1:length(singlefile_galaxyPaths))) { + for (singlefile_galaxyPath_i in seq_len(length(singlefile_galaxyPaths))) { singlefile_galaxyPath <- singlefile_galaxyPaths[singlefile_galaxyPath_i] singlefile_sampleName <- singlefile_sampleNames[singlefile_galaxyPath_i] # In case, an url is used to import data within Galaxy - singlefile_sampleName <- tail(unlist(strsplit(singlefile_sampleName,"/")), n=1) + singlefile_sampleName <- tail(unlist(strsplit(singlefile_sampleName, "/")), n = 1) singlefile[[singlefile_sampleName]] <- singlefile_galaxyPath } } # zipfile - if the file are passed in the command arguments -> refresh zipfile - if (!is.null(args[[paste0("zipfile",prefix)]])) - zipfile <- args[[paste0("zipfile",prefix)]] + if (!is.null(args[[paste0("zipfile", prefix)]])) + zipfile <- args[[paste0("zipfile", prefix)]] # single - if(!is.null(singlefile) && (length("singlefile")>0)) { + if (!is.null(singlefile) && (length("singlefile") > 0)) { files <- vector() for (singlefile_sampleName in names(singlefile)) { singlefile_galaxyPath <- singlefile[[singlefile_sampleName]] - if(!file.exists(singlefile_galaxyPath)){ - error_message <- paste("Cannot access the sample:",singlefile_sampleName,"located:",singlefile_galaxyPath,". Please, contact your administrator ... if you have one!") + if (!file.exists(singlefile_galaxyPath)) { + error_message <- paste("Cannot access the sample:", singlefile_sampleName, "located:", singlefile_galaxyPath, ". Please, contact your administrator ... if you have one!") print(error_message); stop(error_message) } - if (!suppressWarnings( try (file.link(singlefile_galaxyPath, singlefile_sampleName), silent=T))) + if (!suppressWarnings(try(file.link(singlefile_galaxyPath, singlefile_sampleName), silent = T))) file.copy(singlefile_galaxyPath, singlefile_sampleName) files <- c(files, singlefile_sampleName) } } # zipfile - if(!is.null(zipfile) && (zipfile != "")) { - if(!file.exists(zipfile)){ - error_message <- paste("Cannot access the Zip file:",zipfile,". Please, contact your administrator ... if you have one!") + if (!is.null(zipfile) && (zipfile != "")) { + if (!file.exists(zipfile)) { + error_message <- paste("Cannot access the Zip file:", zipfile, ". Please, contact your administrator ... if you have one!") print(error_message) stop(error_message) } - suppressWarnings(unzip(zipfile, unzip="unzip")) + suppressWarnings(unzip(zipfile, unzip = "unzip")) #get the directory name - suppressWarnings(filesInZip <- unzip(zipfile, list=T)) - directories <- unique(unlist(lapply(strsplit(filesInZip$Name,"/"), function(x) x[1]))) + suppressWarnings(filesInZip <- unzip(zipfile, list = T)) + directories <- unique(unlist(lapply(strsplit(filesInZip$Name, "/"), function(x) x[1]))) directories <- directories[!(directories %in% c("__MACOSX")) & file.info(directories)$isdir] directory <- "." if (length(directories) == 1) directory <- directories - cat("files_root_directory\t",directory,"\n") + cat("files_root_directory\t", directory, "\n") - filepattern <- c("[Cc][Dd][Ff]", "[Nn][Cc]", "([Mm][Zz])?[Xx][Mm][Ll]","[Mm][Zz][Dd][Aa][Tt][Aa]", "[Mm][Zz][Mm][Ll]") - filepattern <- paste(paste("\\.", filepattern, "$", sep=""),collapse="|") + filepattern <- c("[Cc][Dd][Ff]", "[Nn][Cc]", "([Mm][Zz])?[Xx][Mm][Ll]", "[Mm][Zz][Dd][Aa][Tt][Aa]", "[Mm][Zz][Mm][Ll]") + filepattern <- paste(paste("\\.", filepattern, "$", sep = ""), collapse = "|") info <- file.info(directory) - listed <- list.files(directory[info$isdir], pattern=filepattern,recursive=TRUE, full.names=TRUE) + listed <- list.files(directory[info$isdir], pattern = filepattern, recursive = TRUE, full.names = TRUE) files <- c(directory[!info$isdir], listed) exists <- file.exists(files) files <- files[exists] } - return(list(zipfile=zipfile, singlefile=singlefile, files=files)) + return(list(zipfile = zipfile, singlefile = singlefile, files = files)) } @@ -403,15 +437,15 @@ getxcmsSetObject <- function(xobject) { # XCMS 1.x if (class(xobject) == "xcmsSet") - return (xobject) + return(xobject) # XCMS 3.x if (class(xobject) == "XCMSnExp") { # Get the legacy xcmsSet object - suppressWarnings(xset <- as(xobject, 'xcmsSet')) + suppressWarnings(xset <- as(xobject, "xcmsSet")) if (!is.null(xset@phenoData$sample_group)) sampclass(xset) <- xset@phenoData$sample_group else sampclass(xset) <- "." - return (xset) + return(xset) } }
--- a/macros_msnbase.xml Wed Feb 12 08:27:38 2020 -0500 +++ b/macros_msnbase.xml Mon Apr 12 09:35:02 2021 +0000 @@ -1,10 +1,10 @@ <?xml version="1.0"?> <macros> - <token name="@WRAPPER_VERSION@">2.8.2</token> + <token name="@WRAPPER_VERSION@">2.16.1</token> <xml name="requirements"> <requirements> <requirement type="package" version="@WRAPPER_VERSION@">bioconductor-msnbase</requirement> - <requirement type="package" version="1.1_4">r-batch</requirement> + <requirement type="package" version="1.1_5">r-batch</requirement> <requirement type="package" version="6.0">unzip</requirement> <yield /> </requirements>
--- a/msnbase_readmsdata.r Wed Feb 12 08:27:38 2020 -0500 +++ b/msnbase_readmsdata.r Mon Apr 12 09:35:02 2021 +0000 @@ -1,7 +1,7 @@ #!/usr/bin/env Rscript # ----- LOG FILE ----- -log_file <- file("log.txt", open="wt") +log_file <- file("log.txt", open = "wt") sink(log_file) sink(log_file, type = "output") @@ -10,10 +10,12 @@ cat("\tSESSION INFO\n") #Import the different functions -source_local <- function(fname){ argv <- commandArgs(trailingOnly=FALSE); base_dir <- dirname(substring(argv[grep("--file=", argv)], 8)); source(paste(base_dir, fname, sep="/")) } +source_local <- function(fname) { + argv <- commandArgs(trailingOnly = FALSE); base_dir <- dirname(substring(argv[grep("--file=", argv)], 8)); source(paste(base_dir, fname, sep = "/")) +} source_local("lib.r") -pkgs <- c("MSnbase","batch") +pkgs <- c("MSnbase", "batch") loadAndDisplayPackages(pkgs) cat("\n\n"); @@ -21,7 +23,7 @@ # ----- ARGUMENTS ----- cat("\tARGUMENTS INFO\n") args <- parseCommandArgs(evaluate = FALSE) #interpretation of arguments given in command line as an R list of objects -write.table(as.matrix(args), col.names=F, quote=F, sep='\t') +write.table(as.matrix(args), col.names = F, quote = F, sep = "\t") cat("\n\n") @@ -38,7 +40,7 @@ # Handle infiles if (!exists("singlefile")) singlefile <- NULL if (!exists("zipfile")) zipfile <- NULL -rawFilePath <- retrieveRawfileInTheWorkingDirectory(singlefile, zipfile, args) +rawFilePath <- retrieveRawfileInTheWorkingDir(singlefile, zipfile, args) zipfile <- rawFilePath$zipfile singlefile <- rawFilePath$singlefile files <- rawFilePath$files @@ -55,23 +57,19 @@ cat("\t\tCOMPUTE\n") cat("\t\t\tCreate a phenodata data.frame\n") -s_groups <- sapply(files, function(x) tail(unlist(strsplit(dirname(x),"/")), n=1)) +s_groups <- sapply(files, function(x) tail(unlist(strsplit(dirname(x), "/")), n = 1)) s_name <- tools::file_path_sans_ext(basename(files)) -pd <- data.frame(sample_name=s_name, sample_group=s_groups, stringsAsFactors=FALSE) +pd <- data.frame(sample_name = s_name, sample_group = s_groups, stringsAsFactors = FALSE) print(pd) cat("\t\t\tLoad Raw Data\n") -raw_data <- readMSData(files=files, pdata = new("NAnnotatedDataFrame", pd), mode="onDisk") +raw_data <- readMSData(files = files, pdata = new("NAnnotatedDataFrame", pd), mode = "onDisk") # Transform the files absolute pathways into relative pathways -raw_data@processingData@files <- sub(paste(getwd(), "/", sep="") , "", raw_data@processingData@files) +raw_data@processingData@files <- sub(paste(getwd(), "/", sep = ""), "", raw_data@processingData@files) # Create a sampleMetada file -sampleNamesList <- getSampleMetadata(xdata=raw_data, sampleMetadataOutput="sampleMetadata.tsv") - -#cat("\t\t\tCompute and Store TIC and BPI\n") -#chromTIC <- chromatogram(raw_data, aggregationFun = "sum") -#chromBPI <- chromatogram(raw_data, aggregationFun = "max") +sampleNamesList <- getSampleMetadata(xdata = raw_data, sampleMetadataOutput = "sampleMetadata.tsv") cat("\n\n") @@ -85,7 +83,7 @@ #saving R data in .Rdata file to save the variables used in the present tool objects2save <- c("raw_data", "zipfile", "singlefile", "md5sumList", "sampleNamesList") #, "chromTIC", "chromBPI") -save(list=objects2save[objects2save %in% ls()], file="readmsdata.RData") +save(list = objects2save[objects2save %in% ls()], file = "readmsdata.RData") cat("\tDONE\n")
--- a/msnbase_readmsdata.xml Wed Feb 12 08:27:38 2020 -0500 +++ b/msnbase_readmsdata.xml Mon Apr 12 09:35:02 2021 +0000 @@ -1,4 +1,4 @@ -<tool id="msnbase_readmsdata" name="MSnbase readMSData" version="@WRAPPER_VERSION@.2"> +<tool id="msnbase_readmsdata" name="MSnbase readMSData" version="@WRAPPER_VERSION@+galaxy0"> <description>Imports mass-spectrometry data files</description> <macros> @@ -47,7 +47,7 @@ <has_text text="rowNames: faahKO_reduce/KO/ko15.CDF faahKO_reduce/KO/ko16.CDF" /> <has_text text="faahKO_reduce/WT/wt15.CDF faahKO_reduce/WT/wt16.CDF" /> <has_text text="featureNames: F1.S0001 F1.S0002 ... F4.S1278 (5112 total)" /> - <has_text text="fvarLabels: fileIdx spIdx ... spectrum (28 total)" /> + <has_text text="fvarLabels: fileIdx spIdx ... spectrum (33 total)" /> <has_text text="faahKO_reduce/KO/ko15.CDF ko15 KO" /> <has_text text="faahKO_reduce/KO/ko16.CDF ko16 KO" /> <has_text text="faahKO_reduce/WT/wt15.CDF wt15 WT" /> @@ -61,7 +61,7 @@ <has_text text="rowNames: ko15.CDF" /> <has_text text="ko15.CDF" /> <has_text text="featureNames: F1.S0001 F1.S0002 ... F1.S1278 (1278 total)" /> - <has_text text="fvarLabels: fileIdx spIdx ... spectrum (28 total)" /> + <has_text text="fvarLabels: fileIdx spIdx ... spectrum (33 total)" /> <has_text text="ko15.CDF ko15 ." /> </assert_stdout> </test> @@ -234,7 +234,11 @@ Changelog/News -------------- -.. _News: https://bioconductor.org/packages/release/bioc/news/MSnbase/NEWS +.. _News: https://lgatto.github.io/MSnbase/news/index.html + +**Version 2.16.1+galaxy0 - 08/04/2019** + +- UPGRADE: upgrade the MSnbase version from 2.8.2 to 2.16.1 (see MSnbase News_). Almost all the new features may not concern our usage of MSnbase. **Version 2.8.2.1 - 30/04/2019**
--- a/repository_dependencies.xml Wed Feb 12 08:27:38 2020 -0500 +++ b/repository_dependencies.xml Mon Apr 12 09:35:02 2021 +0000 @@ -1,5 +1,5 @@ <?xml version="1.0" ?> <repositories> - <repository changeset_revision="7800ba9a4c1e" name="no_unzip_datatype" owner="lecorguille" toolshed="https://toolshed.g2.bx.psu.edu"/> - <repository changeset_revision="544f6d2329ac" name="rdata_xcms_datatypes" owner="lecorguille" toolshed="https://toolshed.g2.bx.psu.edu"/> + <repository name="no_unzip_datatype" owner="lecorguille" toolshed="https://toolshed.g2.bx.psu.edu" changeset_revision="7800ba9a4c1e"/> + <repository name="rdata_xcms_datatypes" owner="lecorguille" toolshed="https://toolshed.g2.bx.psu.edu" changeset_revision="544f6d2329ac"/> </repositories> \ No newline at end of file