changeset 11:7e8af58c8052 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/limma_voom commit 4bcbd83574ecf7194f3370aa883a9573563afdbc

--- a/limma_voom.R	Fri Jun 08 02:20:16 2018 -0400
+++ b/limma_voom.R	Mon Jun 11 08:18:25 2018 -0400
@@ -177,7 +177,8 @@
     "weightOpt", "w", 0, "logical",
     "topgenes", "G", 1, "integer",
     "treatOpt", "T", 0, "logical",
-    "plots", "P", 1, "character"),
+    "plots", "P", 1, "character",
+    "libinfoOpt", "L", 0, "logical"),
     byrow=TRUE, ncol=4)
 opt <- getopt(spec)
 
@@ -250,6 +251,12 @@
     wantTreat <- TRUE
 }
 
+if (is.null(opt$libinfoOpt)) {
+    wantLibinfo <- FALSE
+} else {
+    wantLibinfo <- TRUE
+}
+
 
 if (!is.null(opt$filesPath)) {
     # Process the separate count files (adapted from DESeq2 wrapper)
@@ -283,14 +290,14 @@
 
 } else {
     # Process the single count matrix
-    counts <- read.table(opt$matrixPath, header=TRUE, sep="\t", stringsAsFactors=FALSE)
+    counts <- read.table(opt$matrixPath, header=TRUE, sep="\t", strip.white=TRUE, stringsAsFactors=FALSE)
     row.names(counts) <- counts[, 1]
     counts <- counts[ , -1]
     countsRows <- nrow(counts)
 
     # Process factors
     if (is.null(opt$factInput)) {
-            factorData <- read.table(opt$factFile, header=TRUE, sep="\t")
+            factorData <- read.table(opt$factFile, header=TRUE, sep="\t", strip.white=TRUE)
             factors <- factorData[, -1, drop=FALSE]
     }  else {
             factors <- unlist(strsplit(opt$factInput, "|", fixed=TRUE))
@@ -313,7 +320,7 @@
 
  # if annotation file provided
 if (haveAnno) {
-    geneanno <- read.table(opt$annoPath, header=TRUE, sep="\t", stringsAsFactors=FALSE)
+    geneanno <- read.table(opt$annoPath, header=TRUE, sep="\t", quote= "", strip.white=TRUE, stringsAsFactors=FALSE)
 }
 
 #Create output directory
@@ -512,6 +519,7 @@
 
 # Calculating normalising factors
 print("Calculating Normalisation Factors")
+logcounts <- y #store for plots
 y <- calcNormFactors(y, method=opt$normOpt)
 
 # Generate contrasts information
@@ -653,7 +661,11 @@
     pdf(mdsamOutPdf, width=6.5, height=10)
     par(mfrow=c(3, 2))
     for (i in 1:nsamples) {
-        plotMD(y, column = i)
+        if (opt$normOpt != "none") {
+            plotMD(logcounts, column=i, main=paste(colnames(logcounts)[i], "(before)"))
+            abline(h=0, col="red", lty=2, lwd=2)
+        }
+        plotMD(y, column=i)
         abline(h=0, col="red", lty=2, lwd=2)
     }
     linkName <- "MDPlots_Samples.pdf"
@@ -761,6 +773,16 @@
     plotData <- vData
 }
 
+ # Save library size info
+if (wantLibinfo) {
+    efflibsize <- round(y$samples$lib.size * y$samples$norm.factors)
+    libsizeinfo <- cbind(y$samples, EffectiveLibrarySize=efflibsize)
+    libsizeinfo$lib.size <- round(libsizeinfo$lib.size)
+    names(libsizeinfo)[names(libsizeinfo)=="sampleID"] <- "SampleID"
+    names(libsizeinfo)[names(libsizeinfo)=="lib.size"] <- "LibrarySize"
+    names(libsizeinfo)[names(libsizeinfo)=="norm.factors"] <- "NormalisationFactor"
+    write.table(libsizeinfo, file="libsizeinfo", row.names=FALSE, sep="\t", quote=FALSE)
+}
 
 print("Generating DE results")
 

--- a/limma_voom.xml	Fri Jun 08 02:20:16 2018 -0400
+++ b/limma_voom.xml	Mon Jun 11 08:18:25 2018 -0400
@@ -1,4 +1,4 @@
-<tool id="limma_voom" name="limma" version="3.34.9.6">
+<tool id="limma_voom" name="limma" version="3.34.9.7">
     <description>
         Perform differential expression with limma-voom or limma-trend
     </description>
@@ -81,10 +81,15 @@
     -x
 #end if
 
+#if $out.libinfo:
+    -L
+#end if
+
 #if $out.rdaOption:
     -r
 #end if
 
+
 -l '$adv.lfc'
 -p '$adv.pVal'
 -d '$adv.pAdjust'
@@ -271,6 +276,10 @@
                 label="Output Normalised Counts Table?"
                 help="Output a file containing the normalised counts, these are in log2 counts per million (logCPM). Default: No">
             </param>
+            <param name="libinfo" type="boolean" truevalue="1" falsevalue="0" checked="false"
+                label="Output Library information file?"
+                help="Output a tabular file showing the library sizes, normalisation factors and effective library sizes for the samples. Default: No">
+            </param>
             <param name="rscript" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Output Rscript?" help="If this option is set to Yes, the Rscript used will be provided as a text file in the output. Default: No"/>
             <param name="rdaOption" type="boolean" truevalue="1" falsevalue="0" checked="false"
                 label="Output RData file?"
@@ -317,6 +326,9 @@
         <data name="rscript" format="txt" label="${tool.name} on ${on_string}: Rscript">
             <filter>out['rscript']</filter>
         </data>
+        <data name="libinfo" format="tabular" from_work_dir="libsizeinfo" label="${tool.name} on ${on_string}: Library information">
+            <filter>out['libinfo']</filter>
+        </data>
     </outputs>
 
     <tests>
@@ -796,6 +808,7 @@
 Optionally, under **Output Options** you can choose to output
 
     * a normalised counts table
+    * a library size information file
     * the R script used by this tool
     * an RData file