changeset 149:3107df74056e draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/differential_count_models commit 344140b8df53b8b7024618bb04594607a045c03a
author iuc
date Mon, 04 May 2015 22:47:36 -0400
parents 1e20061decdd
children
files rgedgeRpaired_nocamera.xml
diffstat 1 files changed, 175 insertions(+), 175 deletions(-) [+]
line wrap: on
line diff
--- a/rgedgeRpaired_nocamera.xml	Wed Apr 29 12:07:19 2015 -0400
+++ b/rgedgeRpaired_nocamera.xml	Mon May 04 22:47:36 2015 -0400
@@ -7,119 +7,16 @@
     <requirement type="package" version="9.10">ghostscript</requirement>
     <requirement type="package" version="2.14">biocbasics</requirement>
   </requirements>
-  <command interpreter="python">
-     rgToolFactory.py --script_path "$runme" --interpreter "Rscript" --tool_name "Differential_Counts" 
-    --output_dir "$html_file.files_path" --output_html "$html_file" --make_HTML "yes"
-  </command>
-  <inputs>
-    <param name="input1" type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample" help="Use the HTSeq based count matrix preparation tool to create these matrices from BAM/SAM files and a GTF file of genomic features"/>
-    <param name="title" type="text" value="Differential Counts" size="80" label="Title for job outputs" help="Supply a meaningful name here to remind you what the outputs contain">
-      <sanitizer invalid_char="">
-        <valid initial="string.letters,string.digits">
-          <add value="_"/>
-        </valid>
-      </sanitizer>
-    </param>
-    <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/>
-    <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
-      <validator type="no_options" message="Please select at least one column."/>
-    </param>
-    <param name="control_name" type="text" value="Control" size="50" label="Control Name"/>
-    <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
-    </param>
-    <param name="subjectids" type="text" optional="true" size="120" value="" label="IF SUBJECTS NOT ALL INDEPENDENT! Enter comma separated strings to indicate sample labels for (eg) pairing - must be one for every column in input" help="Leave blank if no pairing, but eg if data from sample id A99 is in columns 2,4 and id C21 is in 3,5 then enter 'A99,C21,A99,C21'">
-      <sanitizer>
-        <valid initial="string.letters,string.digits">
-          <add value=","/>
-        </valid>
-      </sanitizer>
-    </param>
-    <param name="fQ" type="float" value="0.3" size="5" label="Non-differential contig count quantile threshold - zero to analyze all non-zero read count contigs" help="May be a good or a bad idea depending on the biology and the question. EG 0.3 = sparsest 30% of contigs with at least one read are removed before analysis"/>
-    <param name="useNDF" type="boolean" truevalue="T" falsevalue="F" checked="false" size="1" label="Non differential filter - remove contigs below a threshold (1 per million) for half or more samples" help="May be a good or a bad idea depending on the biology and the question. This was the old default. Quantile based is available as an alternative"/>
-    <conditional name="edgeR">
-      <param name="doedgeR" type="select" label="Run this model using edgeR" help="edgeR uses a negative binomial model and seems to be powerful, even with few replicates">
-        <option value="F">Do not run edgeR</option>
-        <option value="T" selected="true">Run edgeR</option>
-      </param>
-      <when value="T">
-        <param name="edgeR_priordf" type="integer" value="10" size="3" label="prior.df for tagwise dispersion - larger value = more squeezing of tag dispersions to common dispersion. Replaces prior.n  and prior.df = prior.n * residual.df" help="10 = edgeR default. Use a larger value to 'smooth' small samples. See edgeR docs and note below"/>
-        <param name="edgeR_robust_method" type="select" value="20" size="3" label="Use robust dispersion method" help="Use ordinary, anscombe or deviance robust deviance estimates">
-          <option value="ordinary" selected="true">Use ordinary deviance estimates</option>
-          <option value="deviance">Use robust deviance estimates</option>
-          <option value="anscombe">use Anscombe robust deviance estimates</option>
-        </param>
-      </when>
-      <when value="F"/>
-    </conditional>
-    <conditional name="DESeq2">
-      <param name="doDESeq2" type="select" label="Run the same model with DESeq2 and compare findings" help="DESeq2 is an update to the DESeq package. It uses different assumptions and methods to edgeR">
-        <option value="F" selected="true">Do not run DESeq2</option>
-        <option value="T">Run DESeq2</option>
-      </param>
-      <when value="T">
-        <param name="DESeq_fitType" type="select">
-          <option value="parametric" selected="true">Parametric (default) fit for dispersions</option>
-          <option value="local">Local fit - this will automagically be used if parametric fit fails</option>
-          <option value="mean">Mean dispersion fit- use this if you really understand what you're doing - read the fine manual linked below in the documentation</option>
-        </param>
-      </when>
-      <when value="F"> </when>
-    </conditional>
-    <param name="doVoom" type="select" label="Run the same model with Voom/limma and compare findings" help="Voom uses counts per million and a precise transformation of variance so count data can be analysed using limma">
-      <option value="F" selected="true">Do not run VOOM</option>
-      <option value="T">Run VOOM</option>
-    </param>
-    <param name="fdrthresh" type="float" value="0.05" size="5" label="P value threshold for FDR filtering for amily wise error rate control" help="Conventional default value of 0.05 recommended"/>
-    <param name="fdrtype" type="select" label="FDR (Type II error) control method" help="Use fdr or bh typically to control for the number of tests in a reliable way">
-      <option value="fdr" selected="true">fdr</option>
-      <option value="BH">Benjamini Hochberg</option>
-      <option value="BY">Benjamini Yukateli</option>
-      <option value="bonferroni">Bonferroni</option>
-      <option value="hochberg">Hochberg</option>
-      <option value="holm">Holm</option>
-      <option value="hommel">Hommel</option>
-      <option value="none">no control for multiple tests</option>
-    </param>
-  </inputs>
-  <outputs>
-    <data format="tabular" name="out_edgeR" label="${title}_topTable_edgeR.xls">
-      <filter>edgeR['doedgeR'] == "T"</filter>
-    </data>
-    <data format="tabular" name="out_DESeq2" label="${title}_topTable_DESeq2.xls">
-      <filter>DESeq2['doDESeq2'] == "T"</filter>
-    </data>
-    <data format="tabular" name="out_VOOM" label="${title}_topTable_VOOM.xls">
-      <filter>doVoom == "T"</filter>
-    </data>
-    <data format="html" name="html_file" label="${title}.html"/>
-  </outputs>
   <stdio>
     <exit_code range="4" level="fatal" description="Number of subject ids must match total number of samples in the input matrix"/>
   </stdio>
-  <tests>
-    <test>
-      <param name="input1" value="test_bams2mx.xls" ftype="tabular"/>
-      <param name="treatment_name" value="liver"/>
-      <param name="title" value="edgeRtest"/>
-      <param name="useNDF" value=""/>
-      <param name="doedgeR" value="T"/>
-      <param name="doVoom" value="T"/>
-      <param name="doDESeq2" value="T"/>
-      <param name="fdrtype" value="fdr"/>
-      <param name="edgeR_priordf" value="8"/>
-      <param name="edgeR_robust" value="ordinary"/>
-      <param name="fdrthresh" value="0.05"/>
-      <param name="control_name" value="heart"/>
-      <param name="subjectids" value=""/>
-      <param name="Control_cols" value="3,4,5,9"/>
-      <param name="Treat_cols" value="2,6,7,8"/>
-      <output name="out_edgeR" file="edgeRtest1out.xls" compare="diff" lines_diff="20"/>
-      <output name="html_file" file="edgeRtest1out.html" compare="diff" lines_diff="20"/>
-    </test>
-  </tests>
+  <command interpreter="python">
+     rgToolFactory.py --script_path "$runme" --interpreter "Rscript" --tool_name "Differential_Counts"
+    --output_dir "$html_file.files_path" --output_html "$html_file" --make_HTML "yes"
+  </command>
   <configfiles>
     <configfile name="runme"><![CDATA[
-# 
+#
 # edgeR.Rscript
 # updated feb 2014 adding outlier-robust deviance estimate options by ross for R 3.0.2/bioc 2.13
 # updated npv 2011 for R 2.14.0 and edgeR 2.4.0 by ross
@@ -143,11 +40,11 @@
     gn = rownames(cmat)
     if (length(gu) == 2) {
         col.map = function(g) {if (g==gu[1]) "#FF0000" else "#0000FF"}
-        pcols = unlist(lapply(group,col.map))        
+        pcols = unlist(lapply(group,col.map))
         } else {
         colours = rainbow(length(gu),start=0,end=4/6)
         pcols = colours[match(group,gu)]        }
-    dm = cmat[(! is.na(gn)),] 
+    dm = cmat[(! is.na(gn)),]
     # remove unlabelled hm rows
     nprobes = nrow(dm)
     # sub = paste('Showing',nprobes,'contigs ranked for evidence of differential abundance')
@@ -209,9 +106,9 @@
         grid(col="lightgray", lty="dotted")
         dev.off()
         }
-        
+
 boxPlot = function(rawrs,cleanrs,maint,myTitle,pdfname)
-{    
+{
         nc = ncol(rawrs)
         ##### for (i in c(1:nc)) {rawrs[(rawrs[,i] < 0),i] = NA}
         fullnames = colnames(rawrs)
@@ -231,7 +128,7 @@
         boxplot(cleanrs,varwidth=T,notch=T,ylab='log contig count',col="maroon",las=3,cex.axis=0.35,main=paste('log2 counts after ',maint))
         grid(col="lightgray",lty="dotted")
         dev.off()
-        pdfname = "sample_counts_histogram.pdf" 
+        pdfname = "sample_counts_histogram.pdf"
         nc = ncol(rawrs)
         print.noquote(paste('Using ncol rawrs=',nc))
         ncroot = round(sqrt(nc))
@@ -243,35 +140,35 @@
              }
         ymax = max(m)
         ncols = length(fullnames)
-        if (ncols > 20) 
+        if (ncols > 20)
         {
            scale = 7*ncols/20
            pdf(pdfname,width=scale,height=scale)
-        } else { 
+        } else {
            pdf(pdfname)
         }
         par(mfrow=c(ncroot,ncroot))
         for (i in c(1:nc)) {
-                 hist(rawrs[,i], main=paste("Contig logcount",i), xlab='log raw count', col="maroon", 
+                 hist(rawrs[,i], main=paste("Contig logcount",i), xlab='log raw count', col="maroon",
                  breaks=100,sub=fullnames[i],cex=0.8,ylim=c(0,ymax))
              }
         dev.off()
         par(defpar)
-      
+
 }
 
 cumPlot = function(rawrs,cleanrs,maint,myTitle)
 {   # updated to use ecdf
         pdfname = "Differential_rowsum_bar_charts.pdf"
         defpar = par(no.readonly=T)
-        lrs = log(rawrs,10) 
+        lrs = log(rawrs,10)
         lim = max(lrs)
         pdf(pdfname)
         par(mfrow=c(2,1))
         hist(lrs,breaks=100,main=paste('Before:',maint),xlab="# Reads (log)",
              ylab="Count",col="maroon",sub=myTitle, xlim=c(0,lim),las=1)
         grid(col="lightgray", lty="dotted")
-        lrs = log(cleanrs,10) 
+        lrs = log(cleanrs,10)
         hist(lrs,breaks=100,main=paste('After:',maint),xlab="# Reads (log)",
              ylab="Count",col="maroon",sub=myTitle,xlim=c(0,lim),las=1)
         grid(col="lightgray", lty="dotted")
@@ -344,7 +241,7 @@
       if (! is.null(camres)) {
       rownames(camres) = g # gene set name
       camres = cbind(GeneSet=g,URL=u,camres)
-      if (camres\$Direction == "Up") 
+      if (camres\$Direction == "Up")
         {
         upcam = rbind(upcam,camres) } else {
           downcam = rbind(downcam,camres)
@@ -433,7 +330,7 @@
     {  upcam = rbind(upcam,camres)
     } else { downcam = rbind(downcam,camres)
     }
-              
+
     }
   }
   uscam = upcam[order(upcam\$PValue),]
@@ -454,12 +351,12 @@
   }
 
 
-edgeIt = function (Count_Matrix=c(),group=c(),out_edgeR=F,out_Voom=F,out_DESeq2=F,fdrtype='fdr',priordf=5, 
+edgeIt = function (Count_Matrix=c(),group=c(),out_edgeR=F,out_Voom=F,out_DESeq2=F,fdrtype='fdr',priordf=5,
         fdrthresh=0.05,outputdir='.', myTitle='Differential Counts',libSize=c(),useNDF=F,
         filterquantile=0.2, subjects=c(),TreatmentName="Rx",ControlName="Ctrl",mydesign=NULL,
         doDESeq2=T,doVoom=T,doCamera=T,doedgeR=T,org='hg19',
         histgmt="", bigmt="/data/genomes/gsea/3.1/Abetterchoice_nocgp_c2_c3_c5_symbols_all.gmt",
-        doCook=F,DESeq_fitType="parameteric",robust_meth='ordinary') 
+        doCook=F,DESeq_fitType="parameteric",robust_meth='ordinary')
 {
 
 logf = file('Differential.log', open = "a")
@@ -476,20 +373,20 @@
   if (robust_meth == 'ordinary') {
        myDGEList = estimateGLMCommonDisp(myDGEList,mydesign)
        myDGEList = estimateGLMTrendedDisp(myDGEList,mydesign)
-       if (priordf > 0) {  myDGEList = estimateGLMTagwiseDisp(myDGEList,mydesign,prior.df = priordf) 
+       if (priordf > 0) {  myDGEList = estimateGLMTagwiseDisp(myDGEList,mydesign,prior.df = priordf)
        } else { myDGEList = estimateGLMTagwiseDisp(myDGEList,mydesign) }
        comdisp = myDGEList\$common.dispersion
        estpriorn = getPriorN(myDGEList)
        print(paste("Common Dispersion =",comdisp,"CV = ",sqrt(comdisp),"getPriorN = ",estpriorn),quote=F)
-     } else { 
+     } else {
        myDGEList = estimateGLMRobustDisp(myDGEList,design=mydesign, prior.df = priordf, maxit = 6, residual.type = robust_meth)
           }
-    
-  
+
+
   DGLM = glmFit(myDGEList,design=mydesign)
   DE = glmLRT(DGLM,coef=ncol(DGLM\$design)) # always last one - subject is first if needed
   normData = cpm(myDGEList)
-  uoutput = cbind( 
+  uoutput = cbind(
     Name=as.character(rownames(myDGEList\$counts)),
     DE\$table,
     adj.p.value=p.adjust(DE\$table\$PValue, method=fdrtype),
@@ -501,7 +398,7 @@
   if (sum(goodness\$outlier) > 0) {
     print.noquote('GLM outliers:')
     print(paste(rownames(DGLM)[(goodness\$outlier)],collapse=','),quote=F)
-    } else { 
+    } else {
       print('No GLM fit outlier genes found\n')
     }
   z = limma::zscoreGamma(goodness\$gof.statistic, shape=goodness\$df/2, scale=2)
@@ -512,7 +409,7 @@
   dev.off()
   uniqueg = unique(group)
   write.table(soutput,file=out_edgeR, quote=FALSE, sep="\t",row.names=F)
-  tt = cbind( 
+  tt = cbind(
     Name=as.character(rownames(myDGEList)),
     DE\$table,
     adj.p.value=p.adjust(DE\$table\$PValue, method=fdrtype),
@@ -610,13 +507,13 @@
 run_Voom = function(workCM,pdata,subjects,group,mydesign,mt,out_Voom)
   {
     logf = file('VOOM.log', open = "a")
-    sink(logf,type = c("output", "message")) 
+    sink(logf,type = c("output", "message"))
     if (doedgeR == F) {
         #### Setup myDGEList object
         myDGEList = DGEList(counts=workCM, group = group)
         myDGEList = calcNormFactors(myDGEList)
         myDGEList = estimateGLMCommonDisp(myDGEList,mydesign)
-        myDGEList = estimateGLMTrendedDisp(myDGEList,mydesign) 
+        myDGEList = estimateGLMTrendedDisp(myDGEList,mydesign)
         myDGEList = estimateGLMTagwiseDisp(myDGEList,mydesign)
     }
     pdf(paste("VOOM",mt,"mean_variance_plot.pdf",sep='_'))
@@ -653,12 +550,12 @@
     q()
     }
   require(edgeR)
-  options(width = 512) 
+  options(width = 512)
   mt = paste(unlist(strsplit(myTitle,'_')),collapse=" ")
   allN = nrow(Count_Matrix)
   nscut = round(ncol(Count_Matrix)/2) # half samples
   colTotmillionreads = colSums(Count_Matrix)/1e6
-  counts.dataframe = as.data.frame(c()) 
+  counts.dataframe = as.data.frame(c())
   rawrs = rowSums(Count_Matrix)
   nonzerod = Count_Matrix[(rawrs > 0),] # remove all zero count genes
   nzN = nrow(nonzerod)
@@ -676,7 +573,7 @@
     meth = paste( "After removing",length(lo),"contigs with fewer than ",nscut," sample read counts >= 1 per million, there are",sep="")
     print(paste("Read",allN,"contigs. Removed",zN,"contigs with no reads.",meth,cleanN,"contigs"),quote=F)
     maint = paste('Filter >=1/million reads in >=',nscut,'samples')
-  }   else {        
+  }   else {
     useme = (nzrs > quantile(nzrs,filterquantile))
     workCM = nonzerod[useme,]
     lo = colSums(nonzerod[!useme,])
@@ -700,20 +597,20 @@
     print("@@ using genecards substitution for urls")
     contigurls = paste0(genecards,allgenes,"\'>",allgenes,"</a>")
   }
-  print.noquote(paste("@@ Total low count contigs per sample = ",paste(table(lo),collapse=','))) 
+  print.noquote(paste("@@ Total low count contigs per sample = ",paste(table(lo),collapse=',')))
   cmrowsums = rowSums(workCM)
   TName=unique(group)[1]
   CName=unique(group)[2]
   if (is.null(mydesign)) {
-    if (length(subjects) == 0) 
+    if (length(subjects) == 0)
     {
       mydesign = model.matrix(~group)
-    } 
-    else { 
+    }
+    else {
       subjf = factor(subjects)
       mydesign = model.matrix(~subjf+group) # we block on subject so make group last to simplify finding it
     }
-  } 
+  }
   print.noquote(paste('Using samples:',paste(colnames(workCM),collapse=',')))
   print.noquote('Using design matrix:')
   print.noquote(mydesign)
@@ -751,7 +648,7 @@
   if ((doDESeq2==T) || (doVoom==T) || (doedgeR==T)) {
     if ((doVoom==T) && (doDESeq2==T) && (doedgeR==T)) {
         vennmain = paste(mt,'Voom,edgeR and DESeq2 overlap at FDR=',fdrthresh)
-        counts.dataframe = data.frame(edgeR = edgeRcounts, DESeq2 = DESeqcounts, 
+        counts.dataframe = data.frame(edgeR = edgeRcounts, DESeq2 = DESeqcounts,
                                        VOOM_limma = voomcounts, row.names = allgenes)
        } else if ((doDESeq2==T) && (doedgeR==T))  {
          vennmain = paste(mt,'DESeq2 and edgeR overlap at FDR=',fdrthresh)
@@ -760,10 +657,10 @@
         vennmain = paste(mt,'Voom and edgeR overlap at FDR=',fdrthresh)
         counts.dataframe = data.frame(edgeR = edgeRcounts, VOOM_limma = voomcounts, row.names = allgenes)
        }
-    
+
     if (nrow(counts.dataframe > 1)) {
       counts.venn = vennCounts(counts.dataframe)
-      vennf = paste("Differential_venn",mt,"significant_genes_overlap.pdf",sep="_") 
+      vennf = paste("Differential_venn",mt,"significant_genes_overlap.pdf",sep="_")
       pdf(vennf)
       vennDiagram(counts.venn,main=vennmain,col="maroon")
       dev.off()
@@ -779,7 +676,7 @@
 out_edgeR = F
 out_DESeq2 = F
 out_Voom = "$out_VOOM"
-edgeR_robust_meth = "ordinary" 
+edgeR_robust_meth = "ordinary"
 doDESeq2 = $DESeq2.doDESeq2
 doVoom = $doVoom
 doCamera = F
@@ -799,7 +696,7 @@
 
 #if $edgeR.doedgeR == "T":
   out_edgeR = "$out_edgeR"
-  edgeR_priordf = $edgeR.edgeR_priordf  
+  edgeR_priordf = $edgeR.edgeR_priordf
   edgeR_robust_meth = "$edgeR.edgeR_robust_method"
 #end if
 
@@ -827,7 +724,7 @@
 subjects = unlist(sids)
 nsubj = length(subjects)
 TCols = as.numeric(strsplit(TreatmentCols,",")[[1]])-1
-CCols = as.numeric(strsplit(ControlCols,",")[[1]])-1 
+CCols = as.numeric(strsplit(ControlCols,",")[[1]])-1
 cat('Got TCols=')
 cat(TCols)
 cat('; CCols=')
@@ -836,7 +733,7 @@
 <![CDATA[
 useCols = c(TCols,CCols)
 if (file.exists(Out_Dir) == F) dir.create(Out_Dir)
-Count_Matrix = read.table(Input,header=T,row.names=1,sep='\t') 
+Count_Matrix = read.table(Input,header=T,row.names=1,sep='\t')
 snames = colnames(Count_Matrix)
 nsamples = length(snames)
 if (nsubj >  0 & nsubj != nsamples) {
@@ -852,9 +749,9 @@
 islib = rn %in% c('librarySize','NotInBedRegions')
 LibSizes = Count_Matrix[subset(rn,islib),][1] # take first
 Count_Matrix = Count_Matrix[subset(rn,! islib),]
-group = c(rep(TreatmentName,length(TCols)), rep(ControlName,length(CCols)) )             
+group = c(rep(TreatmentName,length(TCols)), rep(ControlName,length(CCols)) )
 group = factor(group, levels=c(ControlName,TreatmentName))
-colnames(Count_Matrix) = paste(group,colnames(Count_Matrix),sep="_")        
+colnames(Count_Matrix) = paste(group,colnames(Count_Matrix),sep="_")
 results = edgeIt(Count_Matrix=Count_Matrix,group=group, out_edgeR=out_edgeR, out_Voom=out_Voom, out_DESeq2=out_DESeq2,
                  fdrtype='BH',mydesign=NULL,priordf=edgeR_priordf,fdrthresh=fdrthresh,outputdir='.',
                  myTitle=myTitle,useNDF=F,libSize=c(),filterquantile=fQ,subjects=subjects,TreatmentName=TreatmentName,ControlName=ControlName,
@@ -866,6 +763,109 @@
 ]]>
 </configfile>
   </configfiles>
+  <inputs>
+    <param name="input1" type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample" help="Use the HTSeq based count matrix preparation tool to create these matrices from BAM/SAM files and a GTF file of genomic features"/>
+    <param name="title" type="text" value="Differential Counts" size="80" label="Title for job outputs" help="Supply a meaningful name here to remind you what the outputs contain">
+      <sanitizer invalid_char="">
+        <valid initial="string.letters,string.digits">
+          <add value="_"/>
+        </valid>
+      </sanitizer>
+    </param>
+    <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/>
+    <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
+      <validator type="no_options" message="Please select at least one column."/>
+    </param>
+    <param name="control_name" type="text" value="Control" size="50" label="Control Name"/>
+    <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
+    </param>
+    <param name="subjectids" type="text" optional="true" size="120" value="" label="IF SUBJECTS NOT ALL INDEPENDENT! Enter comma separated strings to indicate sample labels for (eg) pairing - must be one for every column in input" help="Leave blank if no pairing, but eg if data from sample id A99 is in columns 2,4 and id C21 is in 3,5 then enter 'A99,C21,A99,C21'">
+      <sanitizer>
+        <valid initial="string.letters,string.digits">
+          <add value=","/>
+        </valid>
+      </sanitizer>
+    </param>
+    <param name="fQ" type="float" value="0.3" size="5" label="Non-differential contig count quantile threshold - zero to analyze all non-zero read count contigs" help="May be a good or a bad idea depending on the biology and the question. EG 0.3 = sparsest 30% of contigs with at least one read are removed before analysis"/>
+    <param name="useNDF" type="boolean" truevalue="T" falsevalue="F" checked="false" size="1" label="Non differential filter - remove contigs below a threshold (1 per million) for half or more samples" help="May be a good or a bad idea depending on the biology and the question. This was the old default. Quantile based is available as an alternative"/>
+    <conditional name="edgeR">
+      <param name="doedgeR" type="select" label="Run this model using edgeR" help="edgeR uses a negative binomial model and seems to be powerful, even with few replicates">
+        <option value="F">Do not run edgeR</option>
+        <option value="T" selected="true">Run edgeR</option>
+      </param>
+      <when value="T">
+        <param name="edgeR_priordf" type="integer" value="10" size="3" label="prior.df for tagwise dispersion - larger value = more squeezing of tag dispersions to common dispersion. Replaces prior.n  and prior.df = prior.n * residual.df" help="10 = edgeR default. Use a larger value to 'smooth' small samples. See edgeR docs and note below"/>
+        <param name="edgeR_robust_method" type="select" value="20" size="3" label="Use robust dispersion method" help="Use ordinary, anscombe or deviance robust deviance estimates">
+          <option value="ordinary" selected="true">Use ordinary deviance estimates</option>
+          <option value="deviance">Use robust deviance estimates</option>
+          <option value="anscombe">use Anscombe robust deviance estimates</option>
+        </param>
+      </when>
+      <when value="F"/>
+    </conditional>
+    <conditional name="DESeq2">
+      <param name="doDESeq2" type="select" label="Run the same model with DESeq2 and compare findings" help="DESeq2 is an update to the DESeq package. It uses different assumptions and methods to edgeR">
+        <option value="F" selected="true">Do not run DESeq2</option>
+        <option value="T">Run DESeq2</option>
+      </param>
+      <when value="T">
+        <param name="DESeq_fitType" type="select">
+          <option value="parametric" selected="true">Parametric (default) fit for dispersions</option>
+          <option value="local">Local fit - this will automagically be used if parametric fit fails</option>
+          <option value="mean">Mean dispersion fit- use this if you really understand what you're doing - read the fine manual linked below in the documentation</option>
+        </param>
+      </when>
+      <when value="F"> </when>
+    </conditional>
+    <param name="doVoom" type="select" label="Run the same model with Voom/limma and compare findings" help="Voom uses counts per million and a precise transformation of variance so count data can be analysed using limma">
+      <option value="F" selected="true">Do not run VOOM</option>
+      <option value="T">Run VOOM</option>
+    </param>
+    <param name="fdrthresh" type="float" value="0.05" size="5" label="P value threshold for FDR filtering for amily wise error rate control" help="Conventional default value of 0.05 recommended"/>
+    <param name="fdrtype" type="select" label="FDR (Type II error) control method" help="Use fdr or bh typically to control for the number of tests in a reliable way">
+      <option value="fdr" selected="true">fdr</option>
+      <option value="BH">Benjamini Hochberg</option>
+      <option value="BY">Benjamini Yukateli</option>
+      <option value="bonferroni">Bonferroni</option>
+      <option value="hochberg">Hochberg</option>
+      <option value="holm">Holm</option>
+      <option value="hommel">Hommel</option>
+      <option value="none">no control for multiple tests</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format="tabular" name="out_edgeR" label="${title}_topTable_edgeR.xls">
+      <filter>edgeR['doedgeR'] == "T"</filter>
+    </data>
+    <data format="tabular" name="out_DESeq2" label="${title}_topTable_DESeq2.xls">
+      <filter>DESeq2['doDESeq2'] == "T"</filter>
+    </data>
+    <data format="tabular" name="out_VOOM" label="${title}_topTable_VOOM.xls">
+      <filter>doVoom == "T"</filter>
+    </data>
+    <data format="html" name="html_file" label="${title}.html"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input1" value="test_bams2mx.xls" ftype="tabular"/>
+      <param name="treatment_name" value="liver"/>
+      <param name="title" value="edgeRtest"/>
+      <param name="useNDF" value=""/>
+      <param name="doedgeR" value="T"/>
+      <param name="doVoom" value="T"/>
+      <param name="doDESeq2" value="T"/>
+      <param name="fdrtype" value="fdr"/>
+      <param name="edgeR_priordf" value="8"/>
+      <param name="edgeR_robust" value="ordinary"/>
+      <param name="fdrthresh" value="0.05"/>
+      <param name="control_name" value="heart"/>
+      <param name="subjectids" value=""/>
+      <param name="Control_cols" value="3,4,5,9"/>
+      <param name="Treat_cols" value="2,6,7,8"/>
+      <output name="out_edgeR" file="edgeRtest1out.xls" compare="diff" lines_diff="20"/>
+      <output name="html_file" file="edgeRtest1out.html" compare="diff" lines_diff="20"/>
+    </test>
+  </tests>
   <help>
 
 **What it does**
@@ -876,30 +876,30 @@
 **Input**
 
 Requires a count matrix as a tabular file. These are best made using the companion HTSeq_ based counter Galaxy wrapper
-and your fave gene model to generate inputs. Each row is a genomic feature (gene or exon eg) and each column the 
+and your fave gene model to generate inputs. Each row is a genomic feature (gene or exon eg) and each column the
 non-negative integer count of reads from one sample overlapping the feature.
 
-The matrix must have a header row uniquely identifying the source samples, and unique row names in 
+The matrix must have a header row uniquely identifying the source samples, and unique row names in
 the first column. Typically the row names are gene symbols or probe ids for downstream use in GSEA and other methods.
-They must be unique and R names or they will be mangled - please read the fine R docs for the rules on identifiers. 
+They must be unique and R names or they will be mangled - please read the fine R docs for the rules on identifiers.
 
 **Specifying comparisons**
 
 This is basically dumbed down for two factors - case vs control.
 
-More complex interfaces are possible but painful at present. 
+More complex interfaces are possible but painful at present.
 Probably need to specify a phenotype file to do this better.
 Work in progress. Send code.
 
 If you have (eg) paired samples and wish to include a term in the GLM to account for some other factor (subject in the case of paired samples),
-put a comma separated list of indicators for every sample (whether modelled or not!) indicating (eg) the subject number or 
+put a comma separated list of indicators for every sample (whether modelled or not!) indicating (eg) the subject number or
 A list of integers, one for each subject or an empty string if samples are all independent.
 If not empty, there must be exactly as many integers in the supplied integer list as there are columns (samples) in the count matrix.
 Integers for samples that are not in the analysis *must* be present in the string as filler even if not used.
 
 So if you have 2 pairs out of 6 samples, you need to put in unique integers for the unpaired ones
 eg if you had 6 samples with the first two independent but the second and third pairs each being from independent subjects. you might use
-8,9,1,1,2,2 
+8,9,1,1,2,2
 as subject IDs to indicate two paired samples from the same subject in columns 3/4 and 5/6
 
 **Methods available**
@@ -916,7 +916,7 @@
 
 **Outputs**
 
-Some helpful plots and analysis results. Note that most of these are produced using R code 
+Some helpful plots and analysis results. Note that most of these are produced using R code
 suggested by the excellent documentation and vignettes for the Bioconductor
 packages invoked. The Tool Factory is used to automatically lay these out for you to enjoy.
 
@@ -961,10 +961,10 @@
 
 ***old rant on changes to Bioconductor package variable names between versions***
 
-The edgeR authors made a small cosmetic change in the name of one important variable (from p.value to PValue) 
-breaking this and all other code that assumed the old name for this variable, 
-between edgeR2.4.4 and 2.4.6 (the version for R 2.14 as at the time of writing). 
-This means that all code using edgeR is sensitive to the version. I think this was a very unwise thing 
+The edgeR authors made a small cosmetic change in the name of one important variable (from p.value to PValue)
+breaking this and all other code that assumed the old name for this variable,
+between edgeR2.4.4 and 2.4.6 (the version for R 2.14 as at the time of writing).
+This means that all code using edgeR is sensitive to the version. I think this was a very unwise thing
 to do because it wasted hours of my time to track down and will similarly cost other edgeR users dearly
 when their old scripts break. This tool currently now works with 2.4.6.
 
@@ -974,19 +974,19 @@
 
 *prior.n*
 
-The value for prior.n determines the amount of smoothing of tagwise dispersions towards the common dispersion. 
-You can think of it as like a "weight" for the common value. (It is actually the weight for the common likelihood 
-in the weighted likelihood equation). The larger the value for prior.n, the more smoothing, i.e. the closer your 
-tagwise dispersion estimates will be to the common dispersion. If you use a prior.n of 1, then that gives the 
+The value for prior.n determines the amount of smoothing of tagwise dispersions towards the common dispersion.
+You can think of it as like a "weight" for the common value. (It is actually the weight for the common likelihood
+in the weighted likelihood equation). The larger the value for prior.n, the more smoothing, i.e. the closer your
+tagwise dispersion estimates will be to the common dispersion. If you use a prior.n of 1, then that gives the
 common likelihood the weight of one observation.
 
-In answer to your question, it is a good thing to squeeze the tagwise dispersions towards a common value, 
-or else you will be using very unreliable estimates of the dispersion. I would not recommend using the value that 
-you obtained from estimateSmoothing()---this is far too small and would result in virtually no moderation 
-(squeezing) of the tagwise dispersions. How many samples do you have in your experiment? 
-What is the experimental design? If you have few samples (less than 6) then I would suggest a prior.n of at least 10. 
-If you have more samples, then the tagwise dispersion estimates will be more reliable, 
-so you could consider using a smaller prior.n, although I would hesitate to use a prior.n less than 5. 
+In answer to your question, it is a good thing to squeeze the tagwise dispersions towards a common value,
+or else you will be using very unreliable estimates of the dispersion. I would not recommend using the value that
+you obtained from estimateSmoothing()---this is far too small and would result in virtually no moderation
+(squeezing) of the tagwise dispersions. How many samples do you have in your experiment?
+What is the experimental design? If you have few samples (less than 6) then I would suggest a prior.n of at least 10.
+If you have more samples, then the tagwise dispersion estimates will be more reliable,
+so you could consider using a smaller prior.n, although I would hesitate to use a prior.n less than 5.
 
 
 From Bioconductor Digest, Vol 118, Issue 5, Gordon writes:
@@ -1023,17 +1023,17 @@
 
 **Attributions**
 
-edgeR - edgeR_ 
+edgeR - edgeR_
 
-VOOM/limma - limma_VOOM_ 
+VOOM/limma - limma_VOOM_
 
 DESeq2 - DESeq2_ for details
 
 See above for Bioconductor package documentation for packages exposed in Galaxy by this tool and app store package.
 
-Galaxy_ (that's what you are using right now!) for gluing everything together 
+Galaxy_ (that's what you are using right now!) for gluing everything together
 
-Otherwise, all code and documentation comprising this tool was written by Ross Lazarus and is 
+Otherwise, all code and documentation comprising this tool was written by Ross Lazarus and is
 licensed to you under the LGPL_ like other rgenetics artefacts
 
 .. _LGPL: http://www.gnu.org/copyleft/lesser.html