Mercurial > repos > lecorguille > xcms_merge
changeset 3:f439ed7a8f03 draft
planemo upload for repository https://github.com/workflow4metabolomics/xcms commit 9f72e947d9c241d11221cad561f3525d27231857
| author | lecorguille |
|---|---|
| date | Tue, 18 Sep 2018 16:09:25 -0400 |
| parents | 3a5204f14fff |
| children | 4c25647cd4df |
| files | README.rst lib-xcms3.x.x.r lib.r macros.xml macros_xcms.xml static/images/xcms_merge_workflow.png test-data/MM14-xset.RData test-data/MM8-xset.RData test-data/ko15-xset.RData test-data/ko15.CDF test-data/ko16-xset.RData test-data/ko16.CDF test-data/noclass.merged.sampleMetadata.tsv test-data/wt15-xset.RData test-data/wt15.CDF test-data/wt16-xset.RData test-data/wt16.CDF xcms_merge.r xcms_merge.xml |
| diffstat | 19 files changed, 1076 insertions(+), 252 deletions(-) [+] |
line wrap: on
line diff
--- a/README.rst Tue Feb 13 04:48:41 2018 -0500 +++ b/README.rst Tue Sep 18 16:09:25 2018 -0400 @@ -2,6 +2,14 @@ Changelog/News -------------- +**Version 3.0.0.0 - 08/03/2018** + +- UPGRADE: upgrade the xcms version from 1.46.0 to 3.0.0. So refactoring of a lot of underlining codes and methods + +- IMPROVMENT: a new dedicated tool "xcms plot chromatogram" will allow you to get TIC and BPI of your raw data. + +- IMPROVMENT: the tool will now generate a sampleMetadata file if any was provided. It will be useful to add some further information for the normalization and statistics steps. + **Version 1.0.1 - 13/02/2017** - IMPROVMENT: the tool will now raise an error if a sample isn't describe in the sampleMetadata file @@ -10,4 +18,3 @@ **Version 1.0.0 - 03/02/2017** - NEW: a new tool to merge individual xcmsSet outputs to be used by xcms.group -
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/lib-xcms3.x.x.r Tue Sep 18 16:09:25 2018 -0400 @@ -0,0 +1,152 @@ + + +#@TODO: remove this function as soon as we can use xcms 3.x.x from Bioconductor 3.7 +# https://github.com/sneumann/xcms/issues/250 +groupnamesW4M <- function(xdata, mzdec = 0, rtdec = 0) { + mzfmt <- paste("%.", mzdec, "f", sep = "") + rtfmt <- paste("%.", rtdec, "f", sep = "") + + gnames <- paste("M", sprintf(mzfmt, featureDefinitions(xdata)[,"mzmed"]), "T", + sprintf(rtfmt, featureDefinitions(xdata)[,"rtmed"]), sep = "") + + if (any(dup <- duplicated(gnames))) + for (dupname in unique(gnames[dup])) { + dupidx <- which(gnames == dupname) + gnames[dupidx] <- paste(gnames[dupidx], seq(along = dupidx), sep = "_") + } + + return (gnames) +} + +#@TODO: remove this function as soon as we can use xcms 3.x.x from Bioconductor 3.7 +# https://github.com/sneumann/xcms/issues/247 +.concatenate_XCMSnExp <- function(...) { + x <- list(...) + if (length(x) == 0) + return(NULL) + if (length(x) == 1) + return(x[[1]]) + ## Check that all are XCMSnExp objects. + if (!all(unlist(lapply(x, function(z) is(z, "XCMSnExp"))))) + stop("All passed objects should be 'XCMSnExp' objects") + new_x <- as(.concatenate_OnDiskMSnExp(...), "XCMSnExp") + ## If any of the XCMSnExp has alignment results or detected features drop + ## them! + x <- lapply(x, function(z) { + if (hasAdjustedRtime(z)) { + z <- dropAdjustedRtime(z) + warning("Adjusted retention times found, had to drop them.") + } + if (hasFeatures(z)) { + z <- dropFeatureDefinitions(z) + warning("Feature definitions found, had to drop them.") + } + z + }) + ## Combine peaks + fls <- lapply(x, fileNames) + startidx <- cumsum(lengths(fls)) + pks <- lapply(x, chromPeaks) + procH <- lapply(x, processHistory) + for (i in 2:length(fls)) { + pks[[i]][, "sample"] <- pks[[i]][, "sample"] + startidx[i - 1] + procH[[i]] <- lapply(procH[[i]], function(z) { + z@fileIndex <- as.integer(z@fileIndex + startidx[i - 1]) + z + }) + } + pks <- do.call(rbind, pks) + new_x@.processHistory <- unlist(procH) + chromPeaks(new_x) <- pks + if (validObject(new_x)) + new_x +} + +#@TODO: remove this function as soon as we can use xcms 3.x.x from Bioconductor 3.7 +# https://github.com/sneumann/xcms/issues/247 +.concatenate_OnDiskMSnExp <- function(...) { + x <- list(...) + if (length(x) == 0) + return(NULL) + if (length(x) == 1) + return(x[[1]]) + ## Check that all are XCMSnExp objects. + if (!all(unlist(lapply(x, function(z) is(z, "OnDiskMSnExp"))))) + stop("All passed objects should be 'OnDiskMSnExp' objects") + ## Check processingQueue + procQ <- lapply(x, function(z) z@spectraProcessingQueue) + new_procQ <- procQ[[1]] + is_ok <- unlist(lapply(procQ, function(z) + !is.character(all.equal(new_procQ, z)) + )) + if (any(!is_ok)) { + warning("Processing queues from the submitted objects differ! ", + "Dropping the processing queue.") + new_procQ <- list() + } + ## processingData + fls <- lapply(x, function(z) z@processingData@files) + startidx <- cumsum(lengths(fls)) + ## featureData + featd <- lapply(x, fData) + ## Have to update the file index and the spectrum names. + for (i in 2:length(featd)) { + featd[[i]]$fileIdx <- featd[[i]]$fileIdx + startidx[i - 1] + rownames(featd[[i]]) <- MSnbase:::formatFileSpectrumNames( + fileIds = featd[[i]]$fileIdx, + spectrumIds = featd[[i]]$spIdx, + nSpectra = nrow(featd[[i]]), + nFiles = length(unlist(fls)) + ) + } + featd <- do.call(rbind, featd) + featd$spectrum <- 1:nrow(featd) + ## experimentData + expdata <- lapply(x, function(z) { + ed <- z@experimentData + data.frame(instrumentManufacturer = ed@instrumentManufacturer, + instrumentModel = ed@instrumentModel, + ionSource = ed@ionSource, + analyser = ed@analyser, + detectorType = ed@detectorType, + stringsAsFactors = FALSE) + }) + expdata <- do.call(rbind, expdata) + expdata <- new("MIAPE", + instrumentManufacturer = expdata$instrumentManufacturer, + instrumentModel = expdata$instrumentModel, + ionSource = expdata$ionSource, + analyser = expdata$analyser, + detectorType = expdata$detectorType) + + ## protocolData + protodata <- lapply(x, function(z) z@protocolData) + if (any(unlist(lapply(protodata, nrow)) > 0)) + warning("Found non-empty protocol data, but merging protocol data is", + " currently not supported. Skipped.") + ## phenoData + pdata <- do.call(rbind, lapply(x, pData)) + res <- new( + "OnDiskMSnExp", + phenoData = new("NAnnotatedDataFrame", data = pdata), + featureData = new("AnnotatedDataFrame", featd), + processingData = new("MSnProcess", + processing = paste0("Concatenated [", date(), "]"), + files = unlist(fls), smoothed = NA), + experimentData = expdata, + spectraProcessingQueue = new_procQ) + if (validObject(res)) + res +} + +#@TODO: remove this function as soon as we can use xcms 3.x.x from Bioconductor 3.7 +# https://github.com/sneumann/xcms/issues/247 +c.XCMSnExp <- function(...) { + .concatenate_XCMSnExp(...) +} + +#@TODO: remove this function as soon as we can use xcms 3.x.x from Bioconductor 3.7 +# https://github.com/sneumann/xcms/issues/247 +c.MSnbase <- function(...) { + .concatenate_OnDiskMSnExp(...) +}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/lib.r Tue Sep 18 16:09:25 2018 -0400 @@ -0,0 +1,510 @@ +#@authors ABiMS TEAM, Y. Guitton +# lib.r for Galaxy Workflow4Metabolomics xcms tools + +#@author G. Le Corguille +# solve an issue with batch if arguments are logical TRUE/FALSE +parseCommandArgs <- function(...) { + args <- batch::parseCommandArgs(...) + for (key in names(args)) { + if (args[key] %in% c("TRUE","FALSE")) + args[key] = as.logical(args[key]) + } + return(args) +} + +#@author G. Le Corguille +# This function will +# - 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))) + + sessioninfo = sessionInfo() + cat(sessioninfo$R.version$version.string,"\n") + cat("Main packages:\n") + for (pkg in names(sessioninfo$otherPkgs)) { cat(paste(pkg,packageVersion(pkg)),"\t") }; cat("\n") + cat("Other loaded packages:\n") + for (pkg in names(sessioninfo$loadedOnly)) { cat(paste(pkg,packageVersion(pkg)),"\t") }; cat("\n") +} + +#@author G. Le Corguille +# This function merge several chromBPI or chromTIC into one. +mergeChrom <- function(chrom_merged, chrom) { + if (is.null(chrom_merged)) return(NULL) + chrom_merged@.Data <- cbind(chrom_merged@.Data, chrom@.Data) + return(chrom_merged) +} + +#@author G. Le Corguille +# This function merge several xdata into one. +mergeXData <- function(args) { + chromTIC <- NULL + chromBPI <- NULL + chromTIC_adjusted <- NULL + chromBPI_adjusted <- NULL + for(image in args$images) { + + load(image) + # Handle infiles + if (!exists("singlefile")) singlefile <- NULL + if (!exists("zipfile")) zipfile <- NULL + rawFilePath <- getRawfilePathFromArguments(singlefile, zipfile, args) + zipfile <- rawFilePath$zipfile + singlefile <- rawFilePath$singlefile + retrieveRawfileInTheWorkingDirectory(singlefile, zipfile) + + if (exists("raw_data")) xdata <- raw_data + if (!exists("xdata")) stop("\n\nERROR: The RData doesn't contain any object called 'xdata'. This RData should have been created by an old version of XMCS 2.*") + + cat(sampleNamesList$sampleNamesOrigin,"\n") + + if (!exists("xdata_merged")) { + xdata_merged <- xdata + singlefile_merged <- singlefile + md5sumList_merged <- md5sumList + sampleNamesList_merged <- sampleNamesList + chromTIC_merged <- chromTIC + chromBPI_merged <- chromBPI + 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 <- .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$sampleNamesMakeNames) + chromTIC_merged <- mergeChrom(chromTIC_merged, chromTIC) + chromBPI_merged <- mergeChrom(chromBPI_merged, chromBPI) + chromTIC_adjusted_merged <- mergeChrom(chromTIC_adjusted_merged, chromTIC_adjusted) + chromBPI_adjusted_merged <- mergeChrom(chromBPI_adjusted_merged, chromBPI_adjusted) + } + } + rm(image) + xdata <- xdata_merged; rm(xdata_merged) + singlefile <- singlefile_merged; rm(singlefile_merged) + md5sumList <- md5sumList_merged; rm(md5sumList_merged) + sampleNamesList <- sampleNamesList_merged; rm(sampleNamesList_merged) + + if (!is.null(args$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$V1)] + + if (any(is.na(pData(xdata)$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=" ")) + 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 } + + 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){ + #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 + } + 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"))]) + return(variableMetadata) +} + +#@author G. Le Corguille +# This function convert the remain NA to 0 in the dataMatrix +naTOzeroDataMatrix <- function(dataMatrix, naTOzero) { + if (naTOzero){ + dataMatrix[is.na(dataMatrix)] <- 0 + } + return (dataMatrix) +} + +#@author G. Le Corguille +# Draw the plotChromPeakDensity 3 per page in a pdf file +getPlotChromPeakDensity <- function(xdata, 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(3, "Set1")[1:length(unique(xdata$sample_group))] + names(group_colors) <- unique(xdata$sample_group) + + 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, 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) + } + + dev.off() +} + +#@author G. Le Corguille +# Draw the plotChromPeakDensity 3 per page in a pdf file +getPlotAdjustedRtime <- function(xdata) { + + pdf(file="raw_vs_adjusted_rt.pdf", width=16, height=12) + + # Color by group + group_colors <- brewer.pal(3, "Set1")[1:length(unique(xdata$sample_group))] + if (length(group_colors) > 1) { + names(group_colors) <- unique(xdata$sample_group) + plotAdjustedRtime(xdata, col = group_colors[xdata$sample_group]) + legend("topright", legend=names(group_colors), col=group_colors, cex=0.8, lty=1) + } + + # Color by sample + plotAdjustedRtime(xdata, col = rainbow(length(xdata@phenoData@data$sample_name))) + legend("topright", legend=xdata@phenoData@data$sample_name, col=rainbow(length(xdata@phenoData@data$sample_name)), cex=0.8, lty=1) + + 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) { + dataMatrix <- featureValues(xdata, method="medret", value=intval) + colnames(dataMatrix) <- tools::file_path_sans_ext(colnames(dataMatrix)) + dataMatrix = cbind(name=groupnamesW4M(xdata), dataMatrix) + variableMetadata <- featureDefinitions(xdata) + colnames(variableMetadata)[1] = "mz"; colnames(variableMetadata)[4] = "rt" + variableMetadata = data.frame(name=groupnamesW4M(xdata), variableMetadata) + + variableMetadata <- RTSecondToMinute(variableMetadata, convertRTMinute) + variableMetadata <- formatIonIdentifiers(variableMetadata, numDigitsRT=numDigitsRT, numDigitsMZ=numDigitsMZ) + dataMatrix <- naTOzeroDataMatrix(dataMatrix, naTOzero) + + 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) + if (ncol(myDataFrame) < 2) { + error_message="Your tabular file seems not well formatted. The column separators accepted are ; , and tabulation" + print(error_message) + stop(error_message) + } + return(myDataFrame) +} + +#@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") { + + if (aggregationFun == "sum") + type="Total Ion Chromatograms" + else + type="Base Peak Intensity Chromatograms" + + adjusted="Raw" + if (hasAdjustedRtime(xdata)) + adjusted="Adjusted" + + main <- paste(type,":",adjusted,"data") + + pdf(pdfname, width=16, height=10) + + # Color by group + group_colors <- brewer.pal(3, "Set1")[1:length(unique(xdata$sample_group))] + if (length(group_colors) > 1) { + names(group_colors) <- unique(xdata$sample_group) + plot(chrom, col = group_colors[chrom$sample_group], main=main) + legend("topright", legend=names(group_colors), col=group_colors, cex=0.8, lty=1) + } + + # Color by sample + plot(chrom, col = rainbow(length(xdata@phenoData@data$sample_name)), main=main) + legend("topright", legend=xdata@phenoData@data$sample_name, col=rainbow(length(xdata@phenoData@data$sample_name)), cex=0.8, lty=1) + + dev.off() +} + + +# 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") { + cat("Creating the sampleMetadata file...\n") + + #Create the sampleMetada dataframe + sampleMetadata <- xdata@phenoData@data + rownames(sampleMetadata) <- NULL + colnames(sampleMetadata) <- c("sampleMetadata", "class") + + sampleNamesOrigin <- sampleMetadata$sampleMetadata + sampleNamesMakeNames <- make.names(sampleNamesOrigin) + + if (any(duplicated(sampleNamesMakeNames))) { + write("\n\nERROR: Usually, R has trouble to deal with special characters in its column names, so it rename them using make.names().\nIn your case, at least two columns after the renaming obtain the same name, thus XCMS will collapse those columns per name.", stderr()) + for (sampleName in sampleNamesOrigin) { + write(paste(sampleName,"\t->\t",make.names(sampleName)),stderr()) + } + stop("\n\nERROR: One or more of your files will not be import by xcmsSet. It may due to bad characters in their filenames.") + } + + if (!all(sampleNamesOrigin == sampleNamesMakeNames)) { + cat("\n\nWARNING: Usually, R has trouble to deal with special characters in its column names, so it rename them using make.names()\nIn your case, one or more sample names will be renamed in the sampleMetadata and dataMatrix files:\n") + for (sampleName in sampleNamesOrigin) { + cat(paste(sampleName,"\t->\t",make.names(sampleName),"\n")) + } + } + + sampleMetadata$sampleMetadata <- sampleNamesMakeNames + + + #For each sample file, the following actions are done + for (fileIdx in 1:length(fileNames(xdata))) { + #Check if the file is in the CDF format + if (!mzR:::netCDFIsFile(fileNames(xdata))) { + + # If the column isn't exist, with add one filled with NA + if (is.null(sampleMetadata$polarity)) sampleMetadata$polarity <- NA + + #Extract the polarity (a list of polarities) + polarity <- fData(xdata)[fData(xdata)$fileIdx == fileIdx,"polarity"] + #Verify if all the scans have the same polarity + uniq_list <- unique(polarity) + if (length(uniq_list)>1){ + polarity <- "mixed" + } else { + polarity <- as.character(uniq_list) + } + + #Set the polarity attribute + sampleMetadata$polarity[fileIdx] <- polarity + } + + } + + write.table(sampleMetadata, sep="\t", quote=FALSE, row.names=FALSE, file=sampleMetadataOutput) + + return(list("sampleNamesOrigin"=sampleNamesOrigin, "sampleNamesMakeNames"=sampleNamesMakeNames)) + +} + + +# This function check if xcms will found all the files +#@author Gildas Le Corguille lecorguille@sb-roscoff.fr ABiMS TEAM +checkFilesCompatibilityWithXcms <- function(directory) { + cat("Checking files filenames compatibilities with xmcs...\n") + # WHAT XCMS WILL FIND + 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) + files <- c(directory[!info$isdir], listed) + files_abs <- file.path(getwd(), files) + exists <- file.exists(files_abs) + files[exists] <- files_abs[exists] + files[exists] <- sub("//","/",files[exists]) + + # WHAT IS ON THE FILESYSTEM + filesystem_filepaths <- system(paste0("find \"$PWD/",directory,"\" -not -name '\\.*' -not -path '*conda-env*' -type f -name \"*\""), intern=T) + filesystem_filepaths <- filesystem_filepaths[grep(filepattern, filesystem_filepaths, perl=T)] + + # COMPARISON + if (!is.na(table(filesystem_filepaths %in% files)["FALSE"])) { + write("\n\nERROR: List of the files which will not be imported by xcmsSet",stderr()) + write(filesystem_filepaths[!(filesystem_filepaths %in% files)],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.") + } +} + + +#This function list the compatible files within the directory as xcms did +#@author Gildas Le Corguille lecorguille@sb-roscoff.fr ABiMS TEAM +getMSFiles <- function (directory) { + 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) + files <- c(directory[!info$isdir], listed) + exists <- file.exists(files) + files <- files[exists] + return(files) +} + +# This function check if XML contains special caracters. It also checks integrity and completness. +#@author Misharl Monsoor misharl.monsoor@sb-roscoff.fr ABiMS TEAM +checkXmlStructure <- function (directory) { + cat("Checking XML structure...\n") + + cmd <- paste0("IFS=$'\n'; for xml in $(find '",directory,"' -not -name '\\.*' -not -path '*conda-env*' -type f -iname '*.*ml*'); do if [ $(xmllint --nonet --noout \"$xml\" 2> /dev/null; echo $?) -gt 0 ]; then echo $xml;fi; done;") + capture <- system(cmd, intern=TRUE) + + if (length(capture)>0){ + #message=paste("The following mzXML or mzML file is incorrect, please check these files first:",capture) + write("\n\nERROR: The following mzXML or mzML file(s) are incorrect, please check these files first:", stderr()) + write(capture, stderr()) + stop("ERROR: xcmsSet cannot continue with incorrect mzXML or mzML files") + } + +} + + +# This function check if XML contain special characters +#@author Misharl Monsoor misharl.monsoor@sb-roscoff.fr ABiMS TEAM +deleteXmlBadCharacters<- function (directory) { + cat("Checking Non ASCII characters in the XML...\n") + + processed <- F + l <- system( paste0("find '",directory, "' -not -name '\\.*' -not -path '*conda-env*' -type f -iname '*.*ml*'"), intern=TRUE) + for (i in l){ + cmd <- paste("LC_ALL=C grep '[^ -~]' \"", i, "\"", sep="") + capture <- suppressWarnings(system(cmd, intern=TRUE)) + if (length(capture)>0){ + cmd <- paste("perl -i -pe 's/[^[:ascii:]]//g;'",i) + print( paste("WARNING: Non ASCII characters have been removed from the ",i,"file") ) + c <- system(cmd, intern=TRUE) + capture <- "" + processed <- T + } + } + if (processed) cat("\n\n") + return(processed) +} + + +# This function will compute MD5 checksum to check the data integrity +#@author Gildas Le Corguille lecorguille@sb-roscoff.fr +getMd5sum <- function (directory) { + cat("Compute md5 checksum...\n") + # WHAT XCMS WILL FIND + filepattern <- c("[Cc][Dd][Ff]", "[Nn][Cc]", "([Mm][Zz])?[Xx][Mm][Ll]","[Mm][Zz][Dd][Aa][Tt][Aa]", "[Mm][Zz][Mm][Ll]") + filepattern <- paste(paste("\\.", filepattern, "$", sep=""),collapse="|") + info <- file.info(directory) + listed <- list.files(directory[info$isdir], pattern=filepattern, recursive=TRUE, full.names=TRUE) + files <- c(directory[!info$isdir], listed) + exists <- file.exists(files) + files <- files[exists] + + library(tools) + + #cat("\n\n") + + return(as.matrix(md5sum(files))) +} + + +# This function get the raw file path from the arguments +#@author Gildas Le Corguille lecorguille@sb-roscoff.fr +getRawfilePathFromArguments <- function(singlefile, zipfile, args, prefix="") { + if (!(prefix %in% c("","Positive","Negative","MS1","MS2"))) stop("prefix must be either '', 'Positive', 'Negative', 'MS1' or 'MS2'") + + if (!is.null(args[[paste0("zipfile",prefix)]])) zipfile <- args[[paste0("zipfile",prefix)]] + + if (!is.null(args[[paste0("singlefile_galaxyPath",prefix)]])) { + singlefile_galaxyPaths <- args[[paste0("singlefile_galaxyPath",prefix)]] + singlefile_sampleNames <- args[[paste0("singlefile_sampleName",prefix)]] + } + if (exists("singlefile_galaxyPaths")){ + singlefile_galaxyPaths <- unlist(strsplit(singlefile_galaxyPaths,"\\|")) + singlefile_sampleNames <- unlist(strsplit(singlefile_sampleNames,"\\|")) + + singlefile <- NULL + for (singlefile_galaxyPath_i in seq(1: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[[singlefile_sampleName]] <- singlefile_galaxyPath + } + } + return(list(zipfile=zipfile, singlefile=singlefile)) +} + +# This function retrieve the raw file in the working directory +# - 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) { + if(!is.null(singlefile) && (length("singlefile")>0)) { + 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!") + print(error_message); stop(error_message) + } + + if (!suppressWarnings( try (file.link(singlefile_galaxyPath, singlefile_sampleName), silent=T))) + file.copy(singlefile_galaxyPath, singlefile_sampleName) + + } + directory <- "." + + } + 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) + } + + #list all file in the zip file + #zip_files <- unzip(zipfile,list=T)[,"Name"] + + #unzip + suppressWarnings(unzip(zipfile, unzip="unzip")) + + #get the directory name + suppressWarnings(filesInZip <- unzip(zipfile, list=T)) + directories <- unique(unlist(lapply(strsplit(filesInZip$Name,"/"), function(x) x[1]))) + directories <- directories[!(directories %in% c("__MACOSX")) & file.info(directories)$isdir] + directory <- "." + if (length(directories) == 1) directory <- directories + + cat("files_root_directory\t",directory,"\n") + + } + return (directory) +} + + +# This function retrieve a xset like object +#@author Gildas Le Corguille lecorguille@sb-roscoff.fr +getxcmsSetObject <- function(xobject) { + # XCMS 1.x + if (class(xobject) == "xcmsSet") + return (xobject) + # XCMS 3.x + if (class(xobject) == "XCMSnExp") { + # Get the legacy xcmsSet object + suppressWarnings(xset <- as(xobject, 'xcmsSet')) + if (!is.null(xset@phenoData$sample_group)) + sampclass(xset) <- xset@phenoData$sample_group + else + sampclass(xset) <- "." + return (xset) + } +}
--- a/macros.xml Tue Feb 13 04:48:41 2018 -0500 +++ b/macros.xml Tue Sep 18 16:09:25 2018 -0400 @@ -1,141 +1,52 @@ <?xml version="1.0"?> <macros> - <xml name="requirements"> - <requirements> - <requirement type="package" version="0.4_1">r-snow</requirement> - <requirement type="package" version="1.46.0">bioconductor-xcms</requirement> - <requirement type="package" version="1.1_4">r-batch</requirement> - </requirements> - </xml> - <xml name="requirements_light"> - <requirements> - <requirement type="package" version="1.46.0">bioconductor-xcms</requirement> - </requirements> - </xml> <xml name="stdio"> <stdio> <exit_code range="1" level="fatal" /> </stdio> </xml> - <token name="@COMMAND_XCMS_SCRIPT@"> - LC_ALL=C Rscript $__tool_directory__/xcms.r - </token> + <!-- COMMAND --> + <token name="@COMMAND_RSCRIPT@">LC_ALL=C Rscript $__tool_directory__/</token> <token name="@COMMAND_LOG_EXIT@"> ; return=\$?; - mv log.txt '$log'; - cat '$log'; + cat 'log.txt'; sh -c "exit \$return" </token> - <!-- zipfile load for planemo test --> - - <token name="@COMMAND_FILE_LOAD@"> - #if $file_load_section.file_load_conditional.file_load_select == "yes": - #if $file_load_section.file_load_conditional.input[0].is_of_type("mzxml") or $file_load_section.file_load_conditional.input[0].is_of_type("mzml") or $file_load_section.file_load_conditional.input[0].is_of_type("mzdata") or $file_load_section.file_load_conditional.input[0].is_of_type("netcdf"): - #set singlefile_galaxyPath = ','.join( [ str( $single_file ) for $single_file in $file_load_section.file_load_conditional.input ] ) - #set singlefile_sampleName = ','.join( [ str( $single_file.name ) for $single_file in $file_load_section.file_load_conditional.input ] ) - - singlefile_galaxyPath '$singlefile_galaxyPath' singlefile_sampleName '$singlefile_sampleName' - #else - zipfile '$file_load_section.file_load_conditional.input' - #end if - #end if - </token> - - <xml name="input_file_load"> - <section name="file_load_section" title="Resubmit your raw dataset or your zip file"> - <conditional name="file_load_conditional"> - <param name="file_load_select" type="select" label="Resubmit your dataset or your zip file" help="Use only if you get a message which say that your original dataset or zip file have been deleted on the server." > - <option value="no" >no need</option> - <option value="yes" >yes</option> - </param> - <when value="no"> - </when> - <when value="yes"> - <param name="input" type="data" format="mzxml,mzml,mzdata,netcdf,no_unzip.zip,zip" multiple="true" label="File(s) from your history containing your chromatograms" help="Single file mode for the format: mzxml, mzml, mzdata and netcdf. Zip file mode for the format: no_unzip.zip, zip. See the help section below." /> - </when> - </conditional> - </section> + <!-- INPUT_VALIDATORS --> + <xml name="input_validator_range_integer"> + <validator type="regex" message="The format is 'min,max'" >[0-9]+ *, *[0-9]+</validator> </xml> - <xml name="test_file_load_zip"> - <section name="file_load_section"> - <conditional name="file_load_conditional"> - <param name="file_load_select" value="yes" /> - <param name="input" value="faahKO_reduce.zip" ftype="zip" /> - </conditional> - </section> + <xml name="input_validator_range_float"> + <validator type="regex" message="The format is 'min,max'" >[0-9]+\.?[0-9]* *, *[0-9]+\.?[0-9]*</validator> </xml> - <xml name="test_file_load_single"> - <section name="file_load_section"> - <conditional name="file_load_conditional"> - <param name="file_load_select" value="yes" /> - <param name="input" value="wt15.CDF,ko16.CDF,ko15.CDF,wt16.CDF" ftype="netcdf" /> - </conditional> - </section> + <xml name="input_validator_list_integer"> + <validator type="regex" message="The format is '1,2,4,6'" >[0-9, ]+</validator> </xml> - <token name="@COMMAND_PEAKLIST@"> - #if $peaklist.peaklistBool - variableMetadataOutput '$variableMetadata' - dataMatrixOutput '$dataMatrix' - convertRTMinute $peaklist.convertRTMinute - numDigitsMZ $peaklist.numDigitsMZ - numDigitsRT $peaklist.numDigitsRT - intval $peaklist.intval - #end if - </token> + + <token name="@INPUT_IMAGE_LABEL@">RData file</token> + <token name="@INPUT_IMAGE_HELP@">It contains a xcms3::XCMSnExp object (named xdata)</token> - <xml name="input_peaklist"> - <conditional name="peaklist"> - <param name="peaklistBool" type="boolean" label="Get a Peak List" /> - <when value="true"> - <param name="convertRTMinute" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Convert retention time (seconds) into minutes" help="Convert the columns rtmed, rtmin and rtmax into minutes"/> - <param name="numDigitsMZ" type="integer" value="4" label="Number of decimal places for mass values reported in ions' identifiers." help="A minimum of 4 decimal places is recommended. Useful to avoid duplicates within identifiers" /> - <param name="numDigitsRT" type="integer" value="0" label="Number of decimal places for retention time values reported in ions' identifiers." help="Useful to avoid duplicates within identifiers" /> - <param name="intval" type="select" label="Reported intensity values" help="[intval] See the help section below"> - <option value="into" selected="true">into</option> - <option value="maxo">maxo</option> - <option value="intb">intb</option> - </param> - </when> - <when value="false" /> - </conditional> - </xml> - <xml name="output_peaklist" token_function=""> - <data name="variableMetadata" format="tabular" label="${image.name[:-6]}.@FUNCTION@.variableMetadata.tsv"> - <filter>(peaklist['peaklistBool'])</filter> - </data> - <data name="dataMatrix" format="tabular" label="${image.name[:-6]}.@FUNCTION@.dataMatrix.tsv" > - <filter>(peaklist['peaklistBool'])</filter> - </data> - </xml> - - <token name="@HELP_AUTHORS@"> -.. class:: infomark - -**Authors** Colin A. Smith csmith@scripps.edu, Ralf Tautenhahn rtautenh@gmail.com, Steffen Neumann sneumann@ipb-halle.de, Paul Benton hpaul.benton08@imperial.ac.uk and Christopher Conley cjconley@ucdavis.edu + <!-- MISC --> + <token name="@HELP_AUTHORS_WRAPPERS@"> .. class:: infomark -**Galaxy integration** ABiMS TEAM - UPMC/CNRS - Station biologique de Roscoff and Yann Guitton yann.guitton@oniris-nantes.fr - part of Workflow4Metabolomics.org [W4M] +**Galaxy integration** ABiMS TEAM - SU/CNRS - Station biologique de Roscoff and Yann Guitton - LABERCA +Part of Workflow4Metabolomics.org [W4M] | Contact support@workflow4metabolomics.org for any questions or concerns about the Galaxy implementation of this tool. ---------------------------------------------------- - </token> - - <xml name="citation"> - <citations> - <citation type="doi">10.1021/ac051437y</citation> + <xml name="citation_w4m"> <citation type="doi">10.1093/bioinformatics/btu813</citation> - </citations> </xml> </macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros_xcms.xml Tue Sep 18 16:09:25 2018 -0400 @@ -0,0 +1,244 @@ +<?xml version="1.0"?> +<macros> + + <token name="@WRAPPER_VERSION@">3.0.0</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@WRAPPER_VERSION@">bioconductor-xcms</requirement> + <requirement type="package" version="1.1_4">r-batch</requirement> + <requirement type="package" version="1.1_2">r-rcolorbrewer</requirement> + <requirement type="package" version="6.0">unzip</requirement> + <yield /> + </requirements> + </xml> + + <!-- FILE_LOAD for planemo test --> + <token name="@COMMAND_FILE_LOAD@"> + #if $file_load_section.file_load_conditional.file_load_select == "yes": + #if $file_load_section.file_load_conditional.input[0].is_of_type("mzxml") or $file_load_section.file_load_conditional.input[0].is_of_type("mzml") or $file_load_section.file_load_conditional.input[0].is_of_type("mzdata") or $file_load_section.file_load_conditional.input[0].is_of_type("netcdf"): + #set singlefile_galaxyPath = '|'.join( [ str( $single_file ) for $single_file in $file_load_section.file_load_conditional.input ] ) + #set singlefile_sampleName = '|'.join( [ str( $single_file.name ) for $single_file in $file_load_section.file_load_conditional.input ] ) + + singlefile_galaxyPath '$singlefile_galaxyPath' singlefile_sampleName '$singlefile_sampleName' + #else + zipfile '$file_load_section.file_load_conditional.input' + #end if + #end if + </token> + + <xml name="input_file_load"> + <section name="file_load_section" title="Resubmit your raw dataset or your zip file"> + <conditional name="file_load_conditional"> + <param name="file_load_select" type="select" label="Resubmit your dataset or your zip file" help="Use only if you get a message saying that your original dataset or zip file have been deleted on the server." > + <option value="no" >no need</option> + <option value="yes" >yes</option> + </param> + <when value="no"> + </when> + <when value="yes"> + <param name="input" type="data" format="mzxml,mzml,mzdata,netcdf,no_unzip.zip,zip" multiple="true" label="File(s) from your history containing your chromatograms" help="Single file mode for the format: mzxml, mzml, mzdata and netcdf. Zip file mode for the format: no_unzip.zip, zip. See the help section below." /> + </when> + </conditional> + </section> + </xml> + + <xml name="test_file_load_zip"> + <section name="file_load_section"> + <conditional name="file_load_conditional"> + <param name="file_load_select" value="yes" /> + <param name="input" value="faahKO_reduce.zip" ftype="zip" /> + </conditional> + </section> + </xml> + + <xml name="test_file_load_zip_sacuri"> + <section name="file_load_section"> + <conditional name="file_load_conditional"> + <param name="file_load_select" value="yes" /> + <param name="input" value="sacuri_dir_root.zip" ftype="zip" /> + </conditional> + </section> + </xml> + + <xml name="test_file_load_single"> + <section name="file_load_section"> + <conditional name="file_load_conditional"> + <param name="file_load_select" value="yes" /> + <param name="input" value="wt15.CDF,ko16.CDF,ko15.CDF,wt16.CDF" ftype="netcdf" /> + </conditional> + </section> + </xml> + + <xml name="test_file_load_single_ko15"> + <section name="file_load_section"> + <conditional name="file_load_conditional"> + <param name="file_load_select" value="yes" /> + <param name="input" value="ko15.CDF" ftype="netcdf" /> + </conditional> + </section> + </xml> + + <!-- PEAKLIST --> + <token name="@COMMAND_PEAKLIST@"> + #if $peaklist.peaklistBool + convertRTMinute $peaklist.convertRTMinute + numDigitsMZ $peaklist.numDigitsMZ + numDigitsRT $peaklist.numDigitsRT + intval $peaklist.intval + naTOzero $peaklist.naTOzero + #end if + </token> + + <xml name="input_peaklist"> + <conditional name="peaklist"> + <param name="peaklistBool" type="boolean" label="Get a Peak List" /> + <when value="true"> + <param name="convertRTMinute" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Convert retention time (seconds) into minutes" help="Convert the columns rtmed, rtmin and rtmax into minutes"/> + <param name="numDigitsMZ" type="integer" value="4" label="Number of decimal places for mass values reported in ions' identifiers." help="A minimum of 4 decimal places is recommended. Useful to avoid duplicates within identifiers" /> + <param name="numDigitsRT" type="integer" value="0" label="Number of decimal places for retention time values reported in ions' identifiers." help="Useful to avoid duplicates within identifiers" /> + <param name="intval" type="select" label="Reported intensity values" help="[intval] See the help section below"> + <option value="into" selected="true">into</option> + <option value="maxo">maxo</option> + <option value="intb">intb</option> + </param> + <param name="naTOzero" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Replace the remain NA by 0 in the dataMatrix" help="Rather mandatory for some downstream statistical steps"/> + </when> + <when value="false" /> + </conditional> + </xml> + + <xml name="output_peaklist" token_function=""> + <data name="variableMetadata" format="tabular" label="${image.name[:-6]}.@FUNCTION@.variableMetadata.tsv" from_work_dir="variableMetadata.tsv" > + <filter>(peaklist['peaklistBool'])</filter> + </data> + <data name="dataMatrix" format="tabular" label="${image.name[:-6]}.@FUNCTION@.dataMatrix.tsv" from_work_dir="dataMatrix.tsv" > + <filter>(peaklist['peaklistBool'])</filter> + </data> + </xml> + + <token name="@HELP_PEAKLIST@"> + +Get a Peak List +--------------- + +If 'true', the module generates two additional files corresponding to the peak list: +- the variable metadata file (corresponding to information about extracted ions such as mass or retention time) +- the data matrix (corresponding to related intensities) + +**decimal places for [mass or retention time] values in identifiers** + + | Ions' identifiers are constructed as MxxxTyyy where 'xxx' is the ion median mass and 'yyy' the ion median retention time. + | Two parameters are used to adjust the number of decimal places wanted in identifiers for mass and retention time respectively. + | Theses parameters do not affect decimal places in columns other than the identifier one. + +**Reported intensity values** + + | This parameter determines which values should be reported as intensities in the dataMatrix table; it correspond to xcms 'intval' parameter: + | - into: integrated area of original (raw) peak + | - maxo: maximum intensity of original (raw) peak + | - intb: baseline corrected integrated peak area (only available if peak detection was done by ‘findPeaks.centWave’) + + </token> + + <token name="@HELP_PEAKLIST_OUTPUT@"> +xset.variableMetadata.tsv : tabular format + + | Table containing information about ions; can be used as one input of **Quality_Metrics** or **Generic_filter** modules. + +xset.dataMatrix.tsv : tabular format + + | Table containing ions' intensities; can be used as one input of **Quality_Metrics** or **Generic_filter** modules. + </token> + + <!-- CENTWAVE --> + <token name="@COMMAND_CENTWAVE@"> + ppm $methods.ppm + peakwidth "c($methods.peakwidth)" + + ## Advanced + snthresh $methods.CentWaveAdv.snthresh + prefilter "c($methods.CentWaveAdv.prefilter)" + mzCenterFun $methods.CentWaveAdv.mzCenterFun + integrate $methods.CentWaveAdv.integrate + mzdiff $methods.CentWaveAdv.mzdiff + fitgauss $methods.CentWaveAdv.fitgauss + noise $methods.CentWaveAdv.noise + verboseColumns $methods.CentWaveAdv.verboseColumns + </token> + + <xml name="input_centwave"> + <param argument="ppm" type="integer" value="25" label="Max tolerated ppm m/z deviation in consecutive scans in ppm" help="for the initial ROI definition." /> + <param argument="peakwidth" type="text" value="20,50" label="Min,Max peak width in seconds" help="with the expected approximate peak width in chromatographic space."> + <expand macro="input_validator_range_float"/> + </param> + </xml> + + <xml name="input_centwaveAdv"> + <param argument="snthresh" type="integer" value="10" label="Signal to Noise ratio cutoff" /> + <param argument="prefilter" type="text" value="3,100" label="Prefilter step for for the first analysis step (ROI detection)" help="Separate by coma k, I. Mass traces are only retained if they contain at least ‘k‘ peaks with intensity ‘>= I‘."> + <expand macro="input_validator_range_integer"/> + </param> + <param argument="mzCenterFun" type="select" label="Name of the function to calculate the m/z center of the chromatographic peak" > + <option value="wMean">intensity weighted mean of the peak's m/z values</option> + <option value="mean">mean of the peak's m/z values</option> + <option value="apex">use the m/z value at the peak apex</option> + <option value="wMeanApex3">ntensity weighted mean of the m/z value at the peak apex and the m/z values left and right of it</option> + <option value="meanApex3">mean of the m/z value of the peak apex and the m/z values left and right of it</option> + </param> + <param argument="integrate" type="select" label="Integration method" > + <option value="1">peak limits are found through descent on the mexican hat filtered data (more robust, but less exact)</option> + <option value="2">peak limits based on real data (more accurate but prone to noise)</option> + </param> + <param argument="mzdiff" type="float" value="-0.001" label="Minimum difference in m/z for peaks with overlapping retention times" help="can be negative to allow overlap" /> + <param argument="fitgauss" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="fitgauss" help="whether or not a Gaussian should be fitted to each peak" /> + <param argument="noise" type="integer" value="0" label="Noise filter" help="allowing to set a minimum intensity required for centroids to be considered in the first analysis step (centroids with intensity lower than ‘noise’ are omitted from ROI detection)." /> + <param argument="verboseColumns" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="verbose Columns" help="whether additional peak meta data columns should be returned" /> + </xml> + + <token name="@COMMAND_CENTWAVEADVROI@"> + #if $sectionROI.roiList: + roiList '$sectionROI.roiList' + firstBaselineCheck $sectionROI.firstBaselineCheck + #if $sectionROI.roiScales != "": + roiScales "c($sectionROI.roiScales)" + #end if + #end if + </token> + + <xml name="input_centwaveAdvROI" token_optional="true"> + <param argument="roiList" type="data" format="tabular" optional="@OPTIONAL@" label="List of regions-of-interest (ROI) representing detected mass traces" help="If ROIs are submitted the first analysis step is omitted and chromatographic peak detection is performed on the submitted ROIs. Each ROI is expected to have the following elements specified: ‘scmin’ (start scan index), ‘scmax’ (end scan index), ‘mzmin’ (minimum m/z), ‘mzmax’ (maximum m/z), ‘length’ (number of scans), ‘intensity’ (summed intensity)." /> + <param argument="firstBaselineCheck" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Is continuous data within regions of interest is checked to be above the first baseline." /> + <param argument="roiScales" type="text" value="" optional="true" label="Numeric vector defining the scale for each region of interest in ‘roiList’" help="Length equal to ‘roiList’ - Should be used for the centWave-wavelets (format 0.9,1,0.2)"> + <expand macro="input_validator_range_float"/> + </param> + </xml> + + <!-- MISC --> + <token name="@HELP_AUTHORS@"> +.. class:: infomark + +**Authors** Colin A. Smith csmith@scripps.edu, Ralf Tautenhahn rtautenh@gmail.com, Steffen Neumann sneumann@ipb-halle.de, Paul Benton hpaul.benton08@imperial.ac.uk and Christopher Conley cjconley@ucdavis.edu + +@HELP_AUTHORS_WRAPPERS@ + +--------------------------------------------------- + + </token> + + <token name="@HELP_XCMS_MANUAL@"> + +For details and explanations concerning all the parameters and workflow of xcms_ package, see its manual_ and this example_ + +.. _xcms: https://bioconductor.org/packages/release/bioc/html/xcms.html +.. _manual: http://www.bioconductor.org/packages/release/bioc/manuals/xcms/man/xcms.pdf +.. _example: https://bioconductor.org/packages/release/bioc/vignettes/xcms/inst/doc/xcms.html + + </token> + + <xml name="citation"> + <citations> + <citation type="doi">10.1021/ac051437y</citation> + <expand macro="citation_w4m"/> + </citations> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/noclass.merged.sampleMetadata.tsv Tue Sep 18 16:09:25 2018 -0400 @@ -0,0 +1,5 @@ +sampleMetadata class +ko15 . +ko16 . +wt15 . +wt16 .
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/xcms_merge.r Tue Sep 18 16:09:25 2018 -0400 @@ -0,0 +1,45 @@ +#!/usr/bin/env Rscript + +#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("lib.r") +source_local("lib-xcms3.x.x.r") + +pkgs <- c("xcms","batch") +loadAndDisplayPackages(pkgs) +cat("\n\n"); + +args <- parseCommandArgs(evaluate=FALSE) #interpretation of arguments given in command line as an R list of objects + + +cat("\tXSET MERGING...\n") + +mergeXDataReturn <- mergeXData(args) +xdata <- mergeXDataReturn$xdata +singlefile <- mergeXDataReturn$singlefile +md5sumList <- mergeXDataReturn$md5sumList +sampleNamesList <- mergeXDataReturn$sampleNamesList +chromTIC <- mergeXDataReturn$chromTIC +chromBPI <- mergeXDataReturn$chromBPI + +# Create a sampleMetada file +sampleNamesList <- getSampleMetadata(xdata=xdata, sampleMetadataOutput="sampleMetadata.tsv") + +cat("\n\n") + +cat("\tXCMSnExp OBJECT INFO\n") +print(pData(xdata)) +print(xdata) +cat("\n\n") + +cat("\txcmsSet OBJECT INFO\n") +# Get the legacy xcmsSet object +xset <- getxcmsSetObject(xdata) +print(xset@phenoData) +print(xset) +cat("\n\n") + +cat("\tSAVE RData\n") +#saving R data in .Rdata file to save the variables used in the present tool +objects2save <- c("xdata", "zipfile", "singlefile", "md5sumList", "sampleNamesList", "chromTIC", "chromBPI") +save(list=objects2save[objects2save %in% ls()], file="merged.RData")
--- a/xcms_merge.xml Tue Feb 13 04:48:41 2018 -0500 +++ b/xcms_merge.xml Tue Sep 18 16:09:25 2018 -0400 @@ -1,99 +1,45 @@ -<tool id="xcms_merge" name="xcms.xcmsSet Merger" version="1.1.0"> - <description>Merge xcms.xcmsSet xset in one to be used by group</description> +<tool id="xcms_merge" name="xcms findChromPeaks Merger" version="@WRAPPER_VERSION@.0"> + <description>Merge xcms findChromPeaks RData into a unique file to be used by group</description> <macros> <import>macros.xml</import> + <import>macros_xcms.xml</import> </macros> - <expand macro="requirements_light"/> + <expand macro="requirements"/> <expand macro="stdio"/> <command><![CDATA[ - Rscript $script_file + @COMMAND_RSCRIPT@/xcms_merge.r + + images 'c("${"\",\"".join(map(str, $images))}")' + + #if str($sampleMetadata) != 'None': + sampleMetadata '$sampleMetadata' + #end if + + @COMMAND_FILE_LOAD@ ]]></command> - <configfiles> - <configfile name="script_file"><![CDATA[ -suppressPackageStartupMessages(library(xcms, quietly=TRUE)) - -images=c( -"${"\",\"".join(map(str, $images))}" -) - - -cat("\tXSET MERGING...\n") - -for(image in images) { - load(image) - cat(sampleNamesList\$sampleNamesOrigin,"\n") - if (!exists("xset_merged")) { - xset_merged=xset - singlefile_merged=singlefile - listOFlistArguments_merged=listOFlistArguments - md5sumList_merged=md5sumList - sampleNamesList_merged=sampleNamesList - } else { - xset_merged=c(xset_merged,xset) - singlefile_merged=c(singlefile_merged,singlefile) - listOFlistArguments_merged=c(listOFlistArguments_merged,listOFlistArguments) - md5sumList_merged\$origin=rbind(md5sumList_merged\$origin,md5sumList\$origin) - sampleNamesList_merged\$sampleNamesOrigin=c(sampleNamesList_merged\$sampleNamesOrigin,sampleNamesList\$sampleNamesOrigin) - sampleNamesList_merged\$sampleNamesMakeNames=c(sampleNamesList_merged\$sampleNamesMakeNames,sampleNamesList\$sampleNamesMakeNames) - } -} -rm(image) -xset=xset_merged; rm(xset_merged) -singlefile=singlefile_merged; rm(singlefile_merged) -listOFlistArguments=listOFlistArguments_merged; rm(listOFlistArguments_merged) -md5sumList=md5sumList_merged; rm(md5sumList_merged) -sampleNamesList=sampleNamesList_merged; rm(sampleNamesList_merged) + <inputs> + <param name="images" type="data" format="rdata.xcms.findchrompeaks,rdata" label="@INPUT_IMAGE_LABEL@" help="@INPUT_IMAGE_HELP@ from multiple findChromPeaks" multiple="true" /> + <param name="sampleMetadata" label="Sample metadata file " format="tabular" type="data" optional="true" help="must contain at least one column with the sample id and one column with the sample class"/> -#if str($sampleMetadata) != 'None': - cat("\tXSET PHENODATA SETTING...\n") - sampleMetadata=read.table("$sampleMetadata", h=F, sep=";", stringsAsFactors=F) - if (ncol(sampleMetadata) < 2) sampleMetadata=read.table("$sampleMetadata", h=F, sep="\t", stringsAsFactors=F) - if (ncol(sampleMetadata) < 2) sampleMetadata=read.table("$sampleMetadata", h=F, sep=",", stringsAsFactors=F) - if (ncol(sampleMetadata) < 2) { - error_message="Your sampleMetadata file seems not well formatted. The column separators accepted are ; , and tabulation" - print(error_message) - stop(error_message) - } - - sampclass(xset)=sampleMetadata\$V2[match(rownames(xset@phenoData),sampleMetadata\$V1)] - - if (any(is.na(sampclass(xset)))) { - sample_missing <- rownames(phenoData(xset))[is.na(sampclass(xset))] - error_message <- paste("Those samples are missing in your sampleMetadata:", paste(sample_missing, collapse=" ")) - print(error_message) - stop(error_message) - } -#end if - - - -cat("\tXSET OBJECT INFO\n") - -print(xset@phenoData) -print(xset) - -cat("\tSAVE RData\n") -save.image("$xsetRData") - - ]]></configfile> - </configfiles> - - <inputs> - <param name="images" type="data" format="rdata.xcms.raw,rdata" label="xset RData / xcms.xcmsSet file" help="output file from another xcms.xcmsSet" multiple="true" /> - <param name="sampleMetadata" label="Sample metadata file " format="tabular" type="data" optional="true" help="must contain at least one column with the sample id and one column with the sample class"/> + <expand macro="input_file_load"/> </inputs> <outputs> - <data name="xsetRData" format="rdata.xcms.raw" label="xset.merged.RData" /> + <data name="xsetRData" format="rdata.xcms.findchrompeaks" label="xset.merged.RData" from_work_dir="merged.RData" /> + <data name="sampleMetadataOutput" format="tabular" label="xset.merged.sampleMetadata.tsv" from_work_dir="sampleMetadata.tsv"> + <filter>not sampleMetadata</filter> + </data> </outputs> <tests> + <!-- DISABLE FOR TRAVIS <test> - <param name="images" value="ko15-xset.RData,ko16-xset.RData,wt15-xset.RData,wt16-xset.RData" /> + <param name="images" value="ko15-xset.RData,ko16-xset.RData,wt15-xset.RData,wt16-xset.RData" ftype="rdata"/> + <expand macro="test_file_load_single"/> <assert_stdout> <has_text text="object with 4 samples" /> <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" /> @@ -102,15 +48,18 @@ <has_text text="Peak Groups: 0" /> <has_text text="Sample classes: ." /> </assert_stdout> + <output name="sampleMetadataOutput" file="noclass.merged.sampleMetadata.tsv" /> </test> + --> <test> - <param name="images" value="ko15-xset.RData,ko16-xset.RData,wt15-xset.RData,wt16-xset.RData" /> + <param name="images" value="ko15-xset.RData,ko16-xset.RData,wt15-xset.RData,wt16-xset.RData" ftype="rdata"/> + <expand macro="test_file_load_single"/> <param name="sampleMetadata" value="sampleMetadata.tab" /> <assert_stdout> - <has_text text="ko15 KO" /> - <has_text text="ko16 KO" /> - <has_text text="wt15 WT" /> - <has_text text="wt16 WT" /> + <has_text_matching expression="ko15\s+KO" /> + <has_text_matching expression="ko16\s+KO" /> + <has_text_matching expression="wt15\s+WT" /> + <has_text_matching expression="wt16\s+WT" /> <has_text text="object with 4 samples" /> <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" /> <has_text text="Mass range: 200.1-600 m/z" /> @@ -119,43 +68,32 @@ <has_text text="Sample classes: KO, WT" /> </assert_stdout> </test> - <test> - <param name="images" value="MM8-xset.RData,MM14-xset.RData" /> - <assert_stdout> - <has_text text="object with 2 samples" /> - <has_text text="Time range: 19.7-307.3 seconds (0.3-5.1 minutes)" /> - <has_text text="Mass range: 117.0357-936.7059 m/z" /> - <has_text text="Peaks: 236 (about 118 per sample)" /> - <has_text text="Peak Groups: 0" /> - <has_text text="Sample classes: ." /> - </assert_stdout> - </test> - <test expect_failure="True"> - <param name="images" value="ko15-xset.RData,ko16-xset.RData,wt15-xset.RData,wt16-xset.RData" /> + <!--<test expect_failure="True"> + <param name="images" value="ko15-xset.RData,ko16-xset.RData,wt15-xset.RData,wt16-xset.RData" ftype="rdata"/> <param name="sampleMetadata" value="sampleMetadata_missing.tab" /> <expand macro="test_file_load_single"/> <assert_stderr> <has_text text="Those samples are missing in your sampleMetadata: ko16" /> </assert_stderr> - </test> + </test>--> </tests> <help><![CDATA[ @HELP_AUTHORS@ -=================== -Xcms.xcmsSet Merger -=================== +========================== +xcms findChromPeaks Merger +========================== ----------- Description ----------- -This tool will allow you to run one xcms.xcmsSet process per sample in parallel and then to merge all RData images in one. -The result is then suitable for xcms.group. +This tool allows you to run one xcms findChromPeaks process per sample in parallel and then to merge all RData images into one. +The result is then suitable for xcms groupChromPeaks. -You can provide a sampleMetadata table to attribute phenotypic value to your samples. +You can provide a sampleMetadata table to attribute phenotypic values to your samples. ----------------- @@ -164,26 +102,28 @@ **Upstream tools** -========================= ================= =================== ========== -Name output file format parameter -========================= ================= =================== ========== -xcms.xcmsSet xset.RData rdata.xcms.raw RData file -------------------------- ----------------- ------------------- ---------- -xcms.xcmsSet xset.RData rdata.xcms.raw RData file -------------------------- ----------------- ------------------- ---------- -xcms.xcmsSet xset.RData rdata.xcms.raw RData file -------------------------- ----------------- ------------------- ---------- -... ... ... ... -========================= ================= =================== ========== +========================= ===================== ============================== +Name Output file Format +========================= ===================== ============================== +xcms.findChromPeaks ``*``.raw.xset.RData rdata.xcms.findchrompeaks +------------------------- --------------------- ------------------------------ +xcms.findChromPeaks ``*``.raw.xset.RData rdata.xcms.findchrompeaks +------------------------- --------------------- ------------------------------ +xcms.findChromPeaks ``*``.raw.xset.RData rdata.xcms.findchrompeaks +------------------------- --------------------- ------------------------------ +... ... ... +------------------------- --------------------- ------------------------------ +Upload file [optional] sampleMetadata tabular +========================= ===================== ============================== **Downstream tools** -+---------------------------+--------------------+-----------------+ -| Name | Output file | Format | -+===========================+====================+=================+ -|xcms.group | xset.RData | rdata.xcms.raw | -+---------------------------+--------------------+-----------------+ +=========================== ==================== ============================ +Name Output file Format +=========================== ==================== ============================ +xcms.groupChromPeaks xset.merged.RData rdata.xcms.findchrompeaks +=========================== ==================== ============================ .. image:: xcms_merge_workflow.png @@ -191,50 +131,60 @@ Input files ----------- -+---------------------------+-----------------------+ -| Parameter : num + label | Format | -+===========================+=======================+ -| 1 : RData file | rdata.xcms.raw | -+---------------------------+-----------------------+ -| 2 : RData file | rdata.xcms.raw | -+---------------------------+-----------------------+ -| N : RData file | rdata.xcms.raw | -+---------------------------+-----------------------+ -| Optional : sampleMetadata | tsv or csv | -+---------------------------+-----------------------+ +=========================== ================================== +Parameter : num + label Format +=========================== ================================== +1 : RData file rdata.xcms.findchrompeaks +--------------------------- ---------------------------------- +2 : RData file rdata.xcms.findchrompeaks +--------------------------- ---------------------------------- +N : RData file rdata.xcms.findchrompeaks +--------------------------- ---------------------------------- +Optional : sampleMetadata tsv or csv +=========================== ================================== Example of a sampleMetadata: -+---------------------------+------------+ -|HU_neg_028 | bio | -+---------------------------+------------+ -|HU_neg_034 | bio | -+---------------------------+------------+ -|Blanc04 | blank | -+---------------------------+------------+ -|Blanc06 | blank | -+---------------------------+------------+ -|Blanc09 | blank | -+---------------------------+------------+ +=========================== ============ +Samples class +=========================== ============ +HU_neg_028 bio +--------------------------- ------------ +HU_neg_034 bio +--------------------------- ------------ +Blanc04 blank +--------------------------- ------------ +Blanc06 blank +--------------------------- ------------ +Blanc09 blank +=========================== ============ + ------------ Output files ------------ -xset.merged.RData: rdata.xcms.raw format +xset.merged.RData: rdata.xcms.findchrompeaks format - | Rdata file that is necessary in the next step of the workflow "xcms.group". + | Rdata file that is necessary in the next step of the workflow "xcms.groupChromPeaks". --------------------------------------------------- Changelog/News -------------- +**Version 3.0.0.0 - 08/03/2018** + +- UPGRADE: upgrade the xcms version from 1.46.0 to 3.0.0. So refactoring of a lot of underlining codes and methods + +- IMPROVMENT: a new dedicated tool "xcms plot chromatogram" will allow you to get TIC and BPI of your raw data. + +- IMPROVMENT: the tool will now generate a sampleMetadata file if any was provided. It will be useful to add some further information for the normalization and statistics steps. + **Version 1.0.1 - 13/02/2017** - IMPROVMENT: the tool will now raise an error if a sample isn't describe in the sampleMetadata file - **Version 1.0.0 - 03/02/2017** - NEW: a new tool to merge individual xcmsSet outputs to be used by xcms.group