Mercurial > repos > shians > voom_rnaseq
changeset 0:7a80e9ec63cb
- Initial commit
| author | shian_su <registertonysu@gmail.com> |
|---|---|
| date | Tue, 16 Dec 2014 14:38:15 +1100 |
| parents | |
| children | b2fe55fd0651 |
| files | diffexp.R diffexp.xml |
| diffstat | 2 files changed, 1016 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/diffexp.R Tue Dec 16 14:38:15 2014 +1100 @@ -0,0 +1,644 @@ +# This tool takes in a matrix of feature counts as well as gene annotations and +# outputs a table of top expressions as well as various plots for differential +# expression analysis +# +# ARGS: 1.countPath -Path to RData input containing counts +# 2.annoPath -Path to RData input containing gene annotations +# 3.htmlPath -Path to html file linking to other outputs +# 4.outPath -Path to folder to write all output to +# 5.rdaOpt -String specifying if RData should be saved +# 6.normOpt -String specifying type of normalisation used +# 7.weightOpt -String specifying usage of weights +# 8.contrastData -String containing contrasts of interest +# 9.cpmReq -Float specifying cpm requirement +# 10.sampleReq -Integer specifying cpm requirement +# 11.pAdjOpt -String specifying the p-value adjustment method +# 12.pValReq -Float specifying the p-value requirement +# 13.lfcReq -Float specifying the log-fold-change requirement +# 14.factorData -String containing factor names and values +# +# OUT: Voom Plot +# BCV Plot +# MA Plot +# Top Expression Table +# HTML file linking to the ouputs +# +# Author: Shian Su - registertonysu@gmail.com - Jan 2014 + +# Record starting time +timeStart <- as.character(Sys.time()) + +# Load all required libraries +library(methods, quietly=TRUE, warn.conflicts=FALSE) +library(statmod, quietly=TRUE, warn.conflicts=FALSE) +library(splines, quietly=TRUE, warn.conflicts=FALSE) +library(edgeR, quietly=TRUE, warn.conflicts=FALSE) +library(limma, quietly=TRUE, warn.conflicts=FALSE) +library(scales, quietly=TRUE, warn.conflicts=FALSE) + +if (packageVersion("limma") < "3.20.1") { + stop("Please update 'limma' to version >= 3.20.1 to run this tool") +} + +################################################################################ +### Function Delcaration +################################################################################ +# Function to sanitise contrast equations so there are no whitespaces +# surrounding the arithmetic operators, leading or trailing whitespace +sanitiseEquation <- function(equation) { + equation <- gsub(" *[+] *", "+", equation) + equation <- gsub(" *[-] *", "-", equation) + equation <- gsub(" *[/] *", "/", equation) + equation <- gsub(" *[*] *", "*", equation) + equation <- gsub("^\\s+|\\s+$", "", equation) + return(equation) +} + +# Function to sanitise group information +sanitiseGroups <- function(string) { + string <- gsub(" *[,] *", ",", string) + string <- gsub("^\\s+|\\s+$", "", string) + return(string) +} + +# Function to change periods to whitespace in a string +unmake.names <- function(string) { + string <- gsub(".", " ", string, fixed=TRUE) + return(string) +} + +# Generate output folder and paths +makeOut <- function(filename) { + return(paste0(outPath, "/", filename)) +} + +# Generating design information +pasteListName <- function(string) { + return(paste0("factors$", string)) +} + +# Create cata function: default path set, default seperator empty and appending +# true by default (Ripped straight from the cat function with altered argument +# defaults) +cata <- function(..., file = htmlPath, sep = "", fill = FALSE, labels = NULL, + append = TRUE) { + if (is.character(file)) + if (file == "") + file <- stdout() + else if (substring(file, 1L, 1L) == "|") { + file <- pipe(substring(file, 2L), "w") + on.exit(close(file)) + } + else { + file <- file(file, ifelse(append, "a", "w")) + on.exit(close(file)) + } + .Internal(cat(list(...), file, sep, fill, labels, append)) +} + +# Function to write code for html head and title +HtmlHead <- function(title) { + cata("<head>\n") + cata("<title>", title, "</title>\n") + cata("</head>\n") +} + +# Function to write code for html links +HtmlLink <- function(address, label=address) { + cata("<a href=\"", address, "\" target=\"_blank\">", label, "</a><br />\n") +} + +# Function to write code for html images +HtmlImage <- function(source, label=source, height=600, width=600) { + cata("<img src=\"", source, "\" alt=\"", label, "\" height=\"", height) + cata("\" width=\"", width, "\"/>\n") +} + +# Function to write code for html list items +ListItem <- function(...) { + cata("<li>", ..., "</li>\n") +} + +TableItem <- function(...) { + cata("<td>", ..., "</td>\n") +} + +TableHeadItem <- function(...) { + cata("<th>", ..., "</th>\n") +} + +################################################################################ +### Input Processing +################################################################################ + +# Collects arguments from command line +argv <- commandArgs(TRUE) + +# Grab arguments +countPath <- as.character(argv[1]) +annoPath <- as.character(argv[2]) +htmlPath <- as.character(argv[3]) +outPath <- as.character(argv[4]) +rdaOpt <- as.character(argv[5]) +normOpt <- as.character(argv[6]) +weightOpt <- as.character(argv[7]) +contrastData <- as.character(argv[8]) +cpmReq <- as.numeric(argv[9]) +sampleReq <- as.numeric(argv[10]) +pAdjOpt <- as.character(argv[11]) +pValReq <- as.numeric(argv[12]) +lfcReq <- as.numeric(argv[13]) +factorData <- list() +for (i in 14:length(argv)) { + newFact <- unlist(strsplit(as.character(argv[i]), split="::")) + factorData <- rbind(factorData, newFact) +} # Factors have the form: FACT_NAME::LEVEL,LEVEL,LEVEL,LEVEL,... + +# Process arguments +if (weightOpt=="yes") { + wantWeight <- TRUE +} else { + wantWeight <- FALSE +} + +if (rdaOpt=="yes") { + wantRda <- TRUE +} else { + wantRda <- FALSE +} + +if (annoPath=="None") { + haveAnno <- FALSE +} else { + haveAnno <- TRUE +} + +# Set the row names to be the name of the factor and delete first row +row.names(factorData) <- factorData[, 1] +factorData <- factorData[, -1] +factorData <- sapply(factorData, sanitiseGroups) +factorData <- sapply(factorData, strsplit, split=",") +factorData <- sapply(factorData, make.names) + +# Transform factor data into data frame of R factor objects +factors <- data.frame(factorData) + +#Create output directory +dir.create(outPath, showWarnings=FALSE) + +# Split up contrasts seperated by comma into a vector then sanitise +contrastData <- unlist(strsplit(contrastData, split=",")) +contrastData <- sanitiseEquation(contrastData) +contrastData <- gsub(" ", ".", contrastData, fixed=TRUE) + +bcvOutPdf <- makeOut("bcvplot.pdf") +bcvOutPng <- makeOut("bcvplot.png") +mdsOutPdf <- makeOut("mdsplot.pdf") +mdsOutPng <- makeOut("mdsplot.png") +voomOutPdf <- makeOut("voomplot.pdf") +voomOutPng <- makeOut("voomplot.png") +maOutPdf <- character() # Initialise character vector +maOutPng <- character() +topOut <- character() +for (i in 1:length(contrastData)) { + maOutPdf[i] <- makeOut(paste0("maplot(", contrastData[i], ").pdf")) + maOutPng[i] <- makeOut(paste0("maplot(", contrastData[i], ").png")) + topOut[i] <- makeOut(paste0("toptab(", contrastData[i], ").tsv")) +} # Save output paths for each contrast as vectors +rdaOut <- makeOut("RData.rda") +sessionOut <- makeOut("session_info.txt") + +# Initialise data for html links and images, data frame with columns Label and +# Link +linkData <- data.frame(Label=character(), Link=character(), + stringsAsFactors=FALSE) +imageData <- data.frame(Label=character(), Link=character(), + stringsAsFactors=FALSE) + +# Initialise vectors for storage of up/down/neutral regulated counts +upCount <- numeric() +downCount <- numeric() +flatCount <- numeric() + +# Read in counts and geneanno data +counts <- read.table(countPath, header=TRUE, sep="\t") +row.names(counts) <- counts$GeneID +counts <- counts[ , !(colnames(counts)=="GeneID")] +countsRows <- nrow(counts) +if (haveAnno) { + geneanno <- read.table(annoPath, header=TRUE, sep="\t") +} + +################################################################################ +### Data Processing +################################################################################ + +# Extract counts and annotation data +data <- list() +data$counts <- counts +if (haveAnno) { + data$genes <- geneanno +} else { + data$genes <- data.frame(GeneID=row.names(counts)) +} + +# Filter out genes that do not have a required cpm in a required number of +# samples +preFilterCount <- nrow(data$counts) +sel <- rowSums(cpm(data$counts) > cpmReq) >= sampleReq +data$counts <- data$counts[sel, ] +data$genes <- data$genes[sel, ] +postFilterCount <- nrow(data$counts) +filteredCount <- preFilterCount-postFilterCount + +# Creating naming data +samplenames <- colnames(data$counts) +sampleanno <- data.frame("sampleID"=samplenames, factors) + +# Generating the DGEList object "data" +data$samples <- sampleanno +data$samples$lib.size <- colSums(data$counts) +data$samples$norm.factors <- 1 +row.names(data$samples) <- colnames(data$counts) +data <- new("DGEList", data) + +factorList <- sapply(names(factors), pasteListName) +formula <- "~0" +for (i in 1:length(factorList)) { + formula <- paste(formula, factorList[i], sep="+") +} +formula <- formula(formula) +design <- model.matrix(formula) +for (i in 1:length(factorList)) { + colnames(design) <- gsub(factorList[i], "", colnames(design), fixed=TRUE) +} + +# Calculating normalising factor, estimating dispersion +data <- calcNormFactors(data, method=normOpt) +#data <- estimateDisp(data, design=design, robust=TRUE) + +# Generate contrasts information +contrasts <- makeContrasts(contrasts=contrastData, levels=design) + +# Name rows of factors according to their sample +row.names(factors) <- names(data$counts) + +################################################################################ +### Data Output +################################################################################ + +# BCV Plot +#png(bcvOutPng, width=600, height=600) +#plotBCV(data, main="BCV Plot") +#imageData[1, ] <- c("BCV Plot", "bcvplot.png") +#invisible(dev.off()) + +#pdf(bcvOutPdf) +#plotBCV(data, main="BCV Plot") +#invisible(dev.off()) + +if (wantWeight) { + # Creating voom data object and plot + png(voomOutPng, width=1000, height=600) + vData <- voomWithQualityWeights(data, design=design, plot=TRUE) + imageData[1, ] <- c("Voom Plot", "voomplot.png") + invisible(dev.off()) + + pdf(voomOutPdf, width=14) + vData <- voomWithQualityWeights(data, design=design, plot=TRUE) + linkData[1, ] <- c("Voom Plot (.pdf)", "voomplot.pdf") + invisible(dev.off()) + + # Generating fit data and top table with weights + wts <- vData$weights + voomFit <- lmFit(vData, design, weights=wts) + +} else { + # Creating voom data object and plot + png(voomOutPng, width=600, height=600) + vData <- voom(data, design=design, plot=TRUE) + imageData[1, ] <- c("Voom Plot", "voomplot.png") + invisible(dev.off()) + + pdf(voomOutPdf) + vData <- voom(data, design=design, plot=TRUE) + linkData[1, ] <- c("Voom Plot (.pdf)", "voomplot.pdf") + invisible(dev.off()) + + # Generate voom fit + voomFit <- lmFit(vData, design) + +} + +# Fit linear model and estimate dispersion with eBayes +voomFit <- contrasts.fit(voomFit, contrasts) +voomFit <- eBayes(voomFit) + +# Plot MDS +labels <- names(counts) +png(mdsOutPng, width=600, height=600) +# Currently only using a single factor +plotMDS(vData, labels=labels, col=as.numeric(factors[, 1]), cex=0.8) +imgName <- "Voom Plot" +imgAddr <- "mdsplot.png" +imageData <- rbind(imageData, c(imgName, imgAddr)) +invisible(dev.off()) + +pdf(mdsOutPdf) +plotMDS(vData, labels=labels, cex=0.5) +linkName <- paste0("MDS Plot (.pdf)") +linkAddr <- paste0("mdsplot.pdf") +linkData <- rbind(linkData, c(linkName, linkAddr)) +invisible(dev.off()) + + +for (i in 1:length(contrastData)) { + + status = decideTests(voomFit[, i], adjust.method=pAdjOpt, p.value=pValReq, + lfc=lfcReq) + + sumStatus <- summary(status) + + # Collect counts for differential expression + upCount[i] <- sumStatus["1",] + downCount[i] <- sumStatus["-1",] + flatCount[i] <- sumStatus["0",] + + # Write top expressions table + top <- topTable(voomFit, coef=i, number=Inf, sort.by="P") + write.table(top, file=topOut[i], row.names=FALSE, sep="\t") + + linkName <- paste0("Top Differential Expressions(", contrastData[i], + ") (.tsv)") + linkAddr <- paste0("toptab(", contrastData[i], ").tsv") + linkData <- rbind(linkData, c(linkName, linkAddr)) + + # Plot MA (log ratios vs mean average) using limma package on weighted data + pdf(maOutPdf[i]) + limma::plotMA(voomFit, status=status, coef=i, + main=paste("MA Plot:", unmake.names(contrastData[i])), + col=alpha(c("firebrick", "blue"), 0.4), values=c("1", "-1"), + xlab="Average Expression", ylab="logFC") + + abline(h=0, col="grey", lty=2) + + linkName <- paste0("MA Plot(", contrastData[i], ")", " (.pdf)") + linkAddr <- paste0("maplot(", contrastData[i], ").pdf") + linkData <- rbind(linkData, c(linkName, linkAddr)) + invisible(dev.off()) + + png(maOutPng[i], height=600, width=600) + limma::plotMA(voomFit, status=status, coef=i, + main=paste("MA Plot:", unmake.names(contrastData[i])), + col=alpha(c("firebrick", "blue"), 0.4), values=c("1", "-1"), + xlab="Average Expression", ylab="logFC") + + abline(h=0, col="grey", lty=2) + + imgName <- paste0("MA Plot(", contrastData[i], ")") + imgAddr <- paste0("maplot(", contrastData[i], ").png") + imageData <- rbind(imageData, c(imgName, imgAddr)) + invisible(dev.off()) +} +sigDiff <- data.frame(Up=upCount, Flat=flatCount, Down=downCount) +row.names(sigDiff) <- contrastData + +# Save relevant items as rda object +if (wantRda) { + if (wantWeight) { + save(data, status, vData, labels, factors, wts, voomFit, top, contrasts, + design, + file=rdaOut, ascii=TRUE) + } else { + save(data, status, vData, labels, factors, voomFit, top, contrasts, design, + file=rdaOut, ascii=TRUE) + } + linkData <- rbind(linkData, c("RData (.rda)", "RData.rda")) +} + +# Record session info +writeLines(capture.output(sessionInfo()), sessionOut) +linkData <- rbind(linkData, c("Session Info", "session_info.txt")) + +# Record ending time and calculate total run time +timeEnd <- as.character(Sys.time()) +timeTaken <- capture.output(round(difftime(timeEnd,timeStart), digits=3)) +timeTaken <- gsub("Time difference of ", "", timeTaken, fixed=TRUE) +################################################################################ +### HTML Generation +################################################################################ + +# Clear file +cat("", file=htmlPath) + +cata("<html>\n") + +cata("<body>\n") +cata("<h3>Limma Voom Analysis Output:</h3>\n") +cata("PDF copies of JPEGS available in 'Plots' section.<br />\n") +if (wantWeight) { + HtmlImage(imageData$Link[1], imageData$Label[1], width=1000) +} else { + HtmlImage(imageData$Link[1], imageData$Label[1]) +} + +for (i in 2:nrow(imageData)) { + HtmlImage(imageData$Link[i], imageData$Label[i]) +} + +cata("<h4>Differential Expression Counts:</h4>\n") + +cata("<table border=\"1\" cellpadding=\"4\">\n") +cata("<tr>\n") +TableItem() +for (i in colnames(sigDiff)) { + TableHeadItem(i) +} +cata("</tr>\n") +for (i in 1:nrow(sigDiff)) { + cata("<tr>\n") + TableHeadItem(unmake.names(row.names(sigDiff)[i])) + for (j in 1:ncol(sigDiff)) { + TableItem(as.character(sigDiff[i, j])) + } + cata("</tr>\n") +} +cata("</table>") + +cata("<h4>Plots:</h4>\n") +for (i in 1:nrow(linkData)) { + if (grepl(".pdf", linkData$Link[i])) { + HtmlLink(linkData$Link[i], linkData$Label[i]) + } +} + +cata("<h4>Tables:</h4>\n") +for (i in 1:nrow(linkData)) { + if (grepl(".tsv", linkData$Link[i])) { + HtmlLink(linkData$Link[i], linkData$Label[i]) + } +} + +if (wantRda) { + cata("<h4>R Data Object:</h4>\n") + for (i in 1:nrow(linkData)) { + if (grepl(".rda", linkData$Link[i])) { + HtmlLink(linkData$Link[i], linkData$Label[i]) + } + } +} + +cata("<p>Alt-click links to download file.</p>\n") +cata("<p>Click floppy disc icon associated history item to download ") +cata("all files.</p>\n") +cata("<p>.tsv files can be viewed in Excel or any spreadsheet program.</p>\n") + +cata("<h4>Additional Information</h4>\n") +cata("<ul>\n") +if (cpmReq!=0 && sampleReq!=0) { + tempStr <- paste("Genes without more than", cpmReq, + "CPM in at least", sampleReq, "samples are insignificant", + "and filtered out.") + ListItem(tempStr) + filterProp <- round(filteredCount/preFilterCount*100, digits=2) + tempStr <- paste0(filteredCount, " of ", preFilterCount," (", filterProp, + "%) genes were filtered out for low expression.") + ListItem(tempStr) +} +ListItem(normOpt, " was the method used to normalise library sizes.") +if (wantWeight) { + ListItem("Weights were applied to samples.") +} else { + ListItem("Weights were not applied to samples.") +} +if (pAdjOpt!="none") { + if (pAdjOpt=="BH" || pAdjOpt=="BY") { + tempStr <- paste0("MA-Plot highlighted genes are significant at FDR ", + "of ", pValReq," and exhibit log2-fold-change of at ", + "least ", lfcReq, ".") + ListItem(tempStr) + } else if (pAdjOpt=="holm") { + tempStr <- paste0("MA-Plot highlighted genes are significant at adjusted ", + "p-value of ", pValReq," by the Holm(1979) ", + "method, and exhibit log2-fold-change of at least ", + lfcReq, ".") + ListItem(tempStr) + } +} else { + tempStr <- paste0("MA-Plot highlighted genes are significant at p-value ", + "of ", pValReq," and exhibit log2-fold-change of at ", + "least ", lfcReq, ".") + ListItem(tempStr) +} +cata("</ul>\n") + +cata("<h4>Summary of experimental data:</h4>\n") + +cata("<p>*CHECK THAT SAMPLES ARE ASSOCIATED WITH CORRECT GROUP*</p>\n") + +cata("<table border=\"1\" cellpadding=\"3\">\n") +cata("<tr>\n") +TableItem() +for (i in names(factors)) { + TableHeadItem(i) +} +cata("</tr>\n") + +for (i in 1:nrow(factors)) { + cata("<tr>\n") + TableHeadItem(row.names(factors)[i]) + for (j in ncol(factors)) { + TableItem(as.character(unmake.names(factors[i, j]))) + } + cata("</tr>\n") +} +cata("</table>") + +cit <- character() +link <- character() +link[1] <- paste0("<a href=\"", + "http://www.bioconductor.org/packages/release/bioc/", + "vignettes/limma/inst/doc/usersguide.pdf", + "\">", "limma User's Guide", "</a>.") + +link[2] <- paste0("<a href=\"", + "http://www.bioconductor.org/packages/release/bioc/", + "vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf", + "\">", "edgeR User's Guide", "</a>") + +cit[1] <- paste("Please cite the paper below for the limma software itself.", + "Please also try to cite the appropriate methodology articles", + "that describe the statistical methods implemented in limma,", + "depending on which limma functions you are using. The", + "methodology articles are listed in Section 2.1 of the", + link[1], + "Cite no. 3 only if sample weights were used.") +cit[2] <- paste("Smyth, GK (2005). Limma: linear models for microarray data.", + "In: 'Bioinformatics and Computational Biology Solutions using", + "R and Bioconductor'. R. Gentleman, V. Carey, S. doit,.", + "Irizarry, W. Huber (eds), Springer, New York, pages 397-420.") +cit[3] <- paste("Please cite the first paper for the software itself and the", + "other papers for the various original statistical methods", + "implemented in edgeR. See Section 1.2 in the", link[2], + "for more detail.") +cit[4] <- paste("Robinson MD, McCarthy DJ and Smyth GK (2010). edgeR: a", + "Bioconductor package for differential expression analysis", + "of digital gene expression data. Bioinformatics 26, 139-140") +cit[5] <- paste("Robinson MD and Smyth GK (2007). Moderated statistical tests", + "for assessing differences in tag abundance. Bioinformatics", + "23, 2881-2887") +cit[6] <- paste("Robinson MD and Smyth GK (2008). Small-sample estimation of", + "negative binomial dispersion, with applications to SAGE data.", + "Biostatistics, 9, 321-332") +cit[7] <- paste("McCarthy DJ, Chen Y and Smyth GK (2012). Differential", + "expression analysis of multifactor RNA-Seq experiments with", + "respect to biological variation. Nucleic Acids Research 40,", + "4288-4297") +cit[8] <- paste("Law, CW, Chen, Y, Shi, W, and Smyth, GK (2014). Voom:", + "precision weights unlock linear model analysis tools for", + "RNA-seq read counts. Genome Biology 15, R29.") +cit[9] <- paste("Ritchie, M. E., Diyagama, D., Neilson, J., van Laar,", + "R., Dobrovic, A., Holloway, A., and Smyth, G. K. (2006).", + "Empirical array quality weights for microarray data.", + "BMC Bioinformatics 7, Article 261.") +cata("<h3>Citations</h3>\n") + +cata("<h4>limma</h4>\n") +cata(cit[1], "\n") +cata("<ol>\n") +ListItem(cit[2]) +ListItem(cit[8]) +ListItem(cit[9]) +cata("</ol>\n") + +cata("<h4>edgeR</h4>\n") +cata(cit[3], "\n") +cata("<ol>\n") +ListItem(cit[4]) +ListItem(cit[5]) +ListItem(cit[6]) +ListItem(cit[7]) +cata("</ol>\n") + +cata("<p>Report problems to: su.s@wehi.edu.au</p>\n") + +for (i in 1:nrow(linkData)) { + if (grepl("session_info", linkData$Link[i])) { + HtmlLink(linkData$Link[i], linkData$Label[i]) + } +} + +cata("<table border=\"0\">\n") +cata("<tr>\n") +TableItem("Task started at:"); TableItem(timeStart) +cata("</tr>\n") +cata("<tr>\n") +TableItem("Task ended at:"); TableItem(timeEnd) +cata("</tr>\n") +cata("<tr>\n") +TableItem("Task run time:"); TableItem(timeTaken) +cata("<tr>\n") +cata("</table>\n") + +cata("</body>\n") +cata("</html>") \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/diffexp.xml Tue Dec 16 14:38:15 2014 +1100 @@ -0,0 +1,372 @@ +<tool id="diffexp" name="Voom Rnaseq" version="1.1.0"> + <description> + Perform differential expression analysis using pipeline based on the voom + function of the limma bioconductor package. This tool takes a count matrix + (tab separated) as input and produces a HTML report as output. + </description> + + <requirements> + <requirement type="R-module" version="3.5.27">edgeR</requirement> + <requirement type="R-module" version="3.18.13">limma</requirement> + </requirements> + + <stdio> + <exit_code range="1:" level="fatal" description="Tool exception" /> + </stdio> + + <command interpreter="Rscript"> + diffexp.R $counts + + #if $anno.annoOpt=="yes": + $geneanno + #else: + None + #end if + + $outFile + $outFile.files_path + "no" <!-- Disabled Rda option --> + $normalisationOption + $weightCond.weightOption + "$contrast" + + #if $filterCPM.filterLowCPM=="yes": + $filterCPM.cpmReq + $filterCPM.sampleReq + #else: + 0 + 0 + #end if + + #if $testOpt.wantOpt=="yes": + "$testOpt.pAdjust" + $testOpt.pVal + $testOpt.lfc + #else: + "BH" + 0.05 + 0 + #end if + + <!--*Code commented until solution for multiple factors is found* + #for $i, $fct in enumerate($factors): + $fct.factName::$fct.factLevel + #end for + --> + "$factName::$factLevel" + + </command> + + <inputs> + <param name="counts" type="data" format="tabular" label="Counts Data"/> + + <conditional name="anno"> + <param name="annoOpt" type="select" label="Use Gene Annotations?" + help="Annotations will be added to table of top differential + expressions to provide descriptions for each gene."> + <option value="no">No</option> + <option value="yes">Yes</option> + </param> + + <when value="yes"> + <param name="geneanno" type="data" format="tabular" + label="Gene Annotations"/> + </when> + </conditional> + + <!--*Code commented until solution for multiple factors is found* + <repeat name="factors" title="Factors" min="1" max="5" default="1"> + <param name="factName" type="text" label="Factor Name (No spaces)" + help="Eg. Genotype"/> + <param name="factLevel" type="text" size="100" + label="Factor Levels (No spaces)" + help="Eg. WT,WT,Mut,Mut,WT"/> + </repeat> + --> + + <param name="factName" type="text" label="Factor Name" + help="Eg. Genotype."/> + <param name="factLevel" type="text" size="100" + label="Factor Values" + help="Eg. WT,WT,Mut,Mut,WT... NOTE: Please ensure that the same + levels are typed identically when repeated, with all cases + matching."/> + + <param name="contrast" type="text" size="30" + label="Contrasts of interest" + help="Eg. Mut-WT,KD-Control."/> + + <conditional name="filterCPM"> + <param name="filterLowCPM" type="select" label="Filter Low CPM?" + help="Treat genes with very low expression as unexpressed and + filter out to speed up computation."> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + + <when value="yes"> + <param name="cpmReq" type="float" value="0.5" min="0" + label="Minimum CPM"/> + + <param name="sampleReq" type="integer" value="1" min="0" + label="Minimum Samples" + help="Filter out all the genes that do not meet the minimum + CPM in at least this many samples."/> + </when> + + <when value="no"/> + + </conditional> + + <conditional name="weightCond"> + <param name="weightOption" type="select" label="Apply sample weights?" + display="radio" help="Apply weights if outliers are present."> + + <option value="no">No</option> + <option value="yes">Yes</option> + + </param> + </conditional> + + <param name="normalisationOption" type="select" + label="Normalisation Method"> + + <option value="TMM">TMM</option> + <option value="RLE">RLE</option> + <option value="upperquartile">Upperquartile</option> + <option value="none">None (Don't normalise)</option> + + </param> + + <conditional name="testOpt"> + <param name="wantOpt" type="select" label="Use Advanced Testing Options?" + help="Enable choices for p-value adjustment method, p-value threshold + and log2-fold-change threshold."> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + + <when value="yes"> + <param name="pAdjust" type="select" label="P-Value Adjustment Method."> + <option value="BH">Benjamini and Hochberg (1995)</option> + <option value="BY">Benjamini and Yekutieli (2001)</option> + <option value="holm">Holm (1979)</option> + <option value="none">None</option> + </param> + + <param name="pVal" type="float" value="0.05" min="0" max="1" + label="Adjusted Threshold" + help="Genes below this threshold are considered significant and + highlighted in the MA plot. If either BH(1995) or + BY(2001) were selected then this value is a + false-discovery-rate control. If Holm(1979) was selected + then this is an adjusted p-value for family-wise error + rate."/> + + <param name="lfc" type="float" value="0" min="0" + label="Minimum log2-fold-change Required" + help="Genes above this threshold and below the p-value + threshold are considered significant and highlighted + in the MA plot."/> + </when> + + <when value="no"/> + + </conditional> + + <!-- <conditional name="wantRda"> + <param name="rdaOption" type="select" label="Output RData?" + display="radio" + help="Output all the data R used to construct the plots, + can be loaded into R."> + + <option value="no">No</option> + <option value="yes">Yes</option> + + </param> + </conditional> --> + </inputs> + + <outputs> + <data format="html" name="outFile" label="Voom Output"/> + </outputs> + + +<help> +.. class:: infomark + +**What it does** + +Given a matrix of counts and optional information about the genes, this tool +produces plots and tables useful in the analysis of differential gene +expression. + +.. class:: warningmark + +This tool is dependent on the R packages limma_ and edgeR_ as a part of the +bioconductor project. Please ensure that these packages are installed on the +server running this tool. + +----- + +**Counts Data:** +A matrix of expression level with rows corresponding to particular genes +and columns corresponding to the feature count in particular samples. +Values must be tab separated and there must be a row for the sample/column +labels and a column for the row/gene labels. + +Example:: + + "GeneID" "Smpl1" "Smpl2" "Smpl3" "Smpl4" "Smpl5" + "27395" 1699 1528 1463 1441 1495 + "18777" 1905 1744 1345 1291 1346 + "15037" 6 8 4 5 5 + "21399" 2099 1974 1574 1519 1654 + "58175" 356 312 347 361 346 + "10866" 2528 2438 1762 1942 2027 + "12421" 2182 2005 1786 1799 1858 + "24069" 3 4 2 3 3 + "31926" 1337 1380 1004 1102 1000 + "71096" 0 0 2 1 6 + "59014" 1466 1426 1296 1097 1175 + ... + +**Gene Annotations:** +Optional input for gene annotations, this can contain more +information about the genes than just an ID number. The annotations will +be avaiable in the top differential expression table. + +Example:: + + "GeneID" "Length" "EntrezID" "Symbols" "GeneName" "Chr" + "11287" "11287" 4681 "11287" "Pzp" "pregnancy zone protein" "6" + "11298" "11298" 1455 "11298" "Aanat" "arylalkylamine N-acetyltransferase" "11" + "11302" "11302" 5743 "11302" "Aatk" "apoptosis-associated tyrosine kinase" "11" + "11303" "11303" 10260 "11303" "Abca1" "ATP-binding cassette, sub-family A (ABC1), member 1" "4" + "11304" "11304" 7248 "11304" "Abca4" "ATP-binding cassette, sub-family A (ABC1), member 4" "3" + "11305" "11305" 8061 "11305" "Abca2" "ATP-binding cassette, sub-family A (ABC1), member 2" "2" + ... + +**Factor Name:** +The name of the factor being investigated. This tool currently assumes +that only one factor is of interest. + +**Factor Levels:** +The levels of the factor of interest, this must be entered in the same +order as the samples to which the levels correspond as listed in the +columns of the counts matrix. + +The values should be seperated by commas, and spaces must not be used. + +**Contrasts of Interest:** +The contrasts you wish to make between levels. + +Common contrasts would be a simple difference between two levels: "Mut-WT" +represents the difference between the mutant and wild type genotypes. + +The values should be seperated by commas and spaces must not be used. + +**Filter Low CPM:** +Option to ignore the genes that do not show significant levels of +expression, this filtering is dependent on two criteria: + + * **Minimum CPM:** This is the counts per million that a gene must have in at + least some specified number of samples. + + * **Minumum Samples:** This is the number of samples in which the CPM + requirement must be met in order for that gene to be acknowledged. + +Only genes that exhibit a CPM greater than the required amount in at least the +number of samples specified will be used for analysis. Care should be taken to +ensure that the sample requirement is appropriate. In the case of an experiment +with two experimental groups each with two members, if there is a change from +insignificant cpm to significant cpm but the sample requirement is set to 3, +then this will cause that gene to fail the criteria. When in doubt simply do not +filter. + + +**Normalisation Method:** +Option for using different methods to rescale the raw library +size. For more information, see calcNormFactor section in the edgeR_ user's +manual. + +**Apply Sample Weights:** +Option to downweight outlier samples such that their information is still +used in the statistical analysis but their impact is reduced. Use this +whenever significant outliers are present. The MDS plotting tool in this package +is useful for identifying outliers + +**Use Advanced Testing Options?:** +By default error rate for multiple testing is controlled using Benjamini and +Hochberg's false discovery rate control at a threshold value of 0.05. However +there are options to change this to custom values. + + * **P-Value Adjustment Method:** + Change the multiple testing control method, the options are BH(1995) and + BY(2001) which are both false discovery rate controls. There is also + Holm(1979) which is a method for family-wise error rate control. + + * **Adjusted Threshold:** + Set the threshold for the resulting value of the multiple testing control + method. Only observations whose statistic falls below this value is + considered significant, thus highlighted in the MA plot. + + * **Minimum log2-fold-change Required:** + In addition to meeting the requirement for the adjusted statistic for + multiple testing, the observation must have an absolute log2-fold-change + greater than this threshold to be considered significant, thus highlighted + in the MA plot. + +----- + +**Citations:** + +.. class:: infomark + +limma + +Please cite the paper below for the limma software itself. Please also try +to cite the appropriate methodology articles that describe the statistical +methods implemented in limma, depending on which limma functions you are +using. The methodology articles are listed in Section 2.1 of the limma +User's Guide. + + * Smyth, GK (2005). Limma: linear models for microarray data. In: + 'Bioinformatics and Computational Biology Solutions using R and + Bioconductor'. R. Gentleman, V. Carey, S. Dudoit, R. Irizarry, + W. Huber (eds), Springer, New York, pages 397-420. + + * Law, CW, Chen, Y, Shi, W, and Smyth, GK (2014). Voom: + precision weights unlock linear model analysis tools for + RNA-seq read counts. Genome Biology 15, R29. + +.. class:: infomark + +edgeR + +Please cite the first paper for the software itself and the other papers for +the various original statistical methods implemented in edgeR. See +Section 1.2 in the User's Guide for more detail. + + * Robinson MD, McCarthy DJ and Smyth GK (2010). edgeR: a Bioconductor + package for differential expression analysis of digital gene expression + data. Bioinformatics 26, 139-140 + + * Robinson MD and Smyth GK (2007). Moderated statistical tests for assessing + differences in tag abundance. Bioinformatics 23, 2881-2887 + + * Robinson MD and Smyth GK (2008). Small-sample estimation of negative + binomial dispersion, with applications to SAGE data. + Biostatistics, 9, 321-332 + + * McCarthy DJ, Chen Y and Smyth GK (2012). Differential expression analysis + of multifactor RNA-Seq experiments with respect to biological variation. + Nucleic Acids Research 40, 4288-4297 + +Report problems to: su.s@wehi.edu.au + +.. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html +.. _limma: http://www.bioconductor.org/packages/release/bioc/html/limma.html + +</help> +</tool>