comparison rgedgeR/rgedgeRpaired.xml @ 7:8c0405de0695 draft

Uploaded

6:cd586457aced

            <option value="hommel">Hommel</option>
            <option value="none">no control for multiple tests</option>
    </param>
  </inputs>
  <outputs>
    <data format="tabular" name="outtab" label="${title}.xls"/>
    <data format="html" name="html_file" label="${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>

  sink()
}



edgeIt = function (Count_Matrix,group,outputfilename,fdrtype='fdr',priordf=5, 
        fdrthresh=0.05,outputdir='.', myTitle='Differential Counts',libSize=c(),useNDF=F,
        filterquantile=0.2, subjects=c(),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") 

  dev.off()
  colnames(normData) = paste( colnames(normData),'N',sep="_")
  print(paste('Raw sample read totals',paste(colSums(nonzerod,na.rm=T),collapse=',')))
  nzd = data.frame(log(nonzerod + 1e-2,10))
  boxPlot(rawrs=nzd,cleanrs=log(normData,10),maint='TMM Normalisation',myTitle=myTitle,pdfname="edgeR_raw_norm_counts_box.pdf")
  write.table(soutput,outputfilename, quote=FALSE, sep="\t",row.names=F)
  tt = cbind( 
    Name=as.character(rownames(DGEList\$counts)),
    DE\$table,
    adj.p.value=p.adjust(DE\$table\$PValue, method=fdrtype),
    Dispersion=DGEList\$tagwise.dispersion,totreads=cmrowsums

    rDESeq = cbind(Contig=rownames(workCM),rDESeq,NReads=cmrowsums,URL=contigurls)
    srDESeq = rDESeq[order(rDESeq\$pvalue),]
    qqPlot(descr=paste(myTitle,'DESeq2 qqplot'),pvector=rDESeq\$pvalue,outpdf='DESeq2_qqplot.pdf')
    cat("# DESeq top 50\n")
    print.noquote(srDESeq[1:50,])
    write.table(srDESeq,paste(mt,'DESeq2_TopTable.xls',sep='_'), quote=FALSE, sep="\t",row.names=F)
    topresults.DESeq = rDESeq[which(rDESeq\$padj < fdrthresh), ]
    DESeqcountsindex = which(allgenes %in% rownames(topresults.DESeq))
    DESeqcounts = rep(0, length(allgenes))
    DESeqcounts[DESeqcountsindex] = 1
    pdf("DESeq2_dispersion_estimates.pdf")

      rvoom = topTable(fit, coef = length(colnames(mydesign)), adj = fdrtype, n = Inf, sort="none")
      qqPlot(descr=paste(myTitle,'VOOM-limma QQ plot'),pvector=rvoom\$P.Value,outpdf='VOOM_qqplot.pdf')
      rownames(rvoom) = rownames(workCM)
      rvoom = cbind(rvoom,NReads=cmrowsums,URL=contigurls)
      srvoom = rvoom[order(rvoom\$P.Value),]
      write.table(srvoom,paste(mt,'VOOM_topTable.xls',sep='_'), quote=FALSE, sep="\t",row.names=F)
      # Use an FDR cutoff to find interesting samples for edgeR, DESeq and voom/limma
      topresults.voom = srvoom[which(rvoom\$adj.P.Val < fdrthresh), ]
      voomcountsindex = which(allgenes %in% topresults.voom\$ID)
      voomcounts = rep(0, length(allgenes))
      voomcounts[voomcountsindex] = 1

#### Done

###sink(stdout(),append=T,type="message")
builtin_gmt=""
history_gmt=""
doDESeq2 = $DESeq2.doDESeq2 # make these T or F
doVoom = $doVoom
doCamera = F 
doedgeR = $edgeR.doedgeR
edgeR_priordf = 0

#if $DESeq2.doDESeq2 == "T"
  DESeq_fitType = "$DESeq2.DESeq_fitType"
#end if
#if $edgeR.doedgeR == "T"
edgeR_priordf = $edgeR.edgeR_priordf
#end if


Out_Dir = "$html_file.files_path"
Input =  "$input1"
TreatmentName = "$treatment_name"
TreatmentCols = "$Treat_cols"

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)) )             #Build a group descriptor
group = factor(group, levels=c(ControlName,TreatmentName))
colnames(Count_Matrix) = paste(group,colnames(Count_Matrix),sep="_")                   #Relable columns
results = edgeIt(Count_Matrix=Count_Matrix,group=group,outputfilename=outputfilename,
                 fdrtype='BH',priordf=edgeR_priordf,fdrthresh=0.05,outputdir='.',
                 myTitle=myTitle,useNDF=F,libSize=c(),filterquantile=fQ,subjects=c(),
                 doDESeq2=doDESeq2,doVoom=doVoom,doCamera=doCamera,doedgeR=doedgeR,org=org,
                 histgmt=history_gmt,bigmt=builtin_gmt,DESeq_fitType=DESeq_fitType)
sessionInfo()

7:8c0405de0695

            <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>

  sink()
}



edgeIt = function (Count_Matrix,group,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(),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") 

  dev.off()
  colnames(normData) = paste( colnames(normData),'N',sep="_")
  print(paste('Raw sample read totals',paste(colSums(nonzerod,na.rm=T),collapse=',')))
  nzd = data.frame(log(nonzerod + 1e-2,10))
  boxPlot(rawrs=nzd,cleanrs=log(normData,10),maint='TMM Normalisation',myTitle=myTitle,pdfname="edgeR_raw_norm_counts_box.pdf")
  write.table(soutput,out_edgeR, quote=FALSE, sep="\t",row.names=F)
  tt = cbind( 
    Name=as.character(rownames(DGEList\$counts)),
    DE\$table,
    adj.p.value=p.adjust(DE\$table\$PValue, method=fdrtype),
    Dispersion=DGEList\$tagwise.dispersion,totreads=cmrowsums

    rDESeq = cbind(Contig=rownames(workCM),rDESeq,NReads=cmrowsums,URL=contigurls)
    srDESeq = rDESeq[order(rDESeq\$pvalue),]
    qqPlot(descr=paste(myTitle,'DESeq2 qqplot'),pvector=rDESeq\$pvalue,outpdf='DESeq2_qqplot.pdf')
    cat("# DESeq top 50\n")
    print.noquote(srDESeq[1:50,])
    write.table(srDESeq,out_DESeq2, quote=FALSE, sep="\t",row.names=F)
    topresults.DESeq = rDESeq[which(rDESeq\$padj < fdrthresh), ]
    DESeqcountsindex = which(allgenes %in% rownames(topresults.DESeq))
    DESeqcounts = rep(0, length(allgenes))
    DESeqcounts[DESeqcountsindex] = 1
    pdf("DESeq2_dispersion_estimates.pdf")

      rvoom = topTable(fit, coef = length(colnames(mydesign)), adj = fdrtype, n = Inf, sort="none")
      qqPlot(descr=paste(myTitle,'VOOM-limma QQ plot'),pvector=rvoom\$P.Value,outpdf='VOOM_qqplot.pdf')
      rownames(rvoom) = rownames(workCM)
      rvoom = cbind(rvoom,NReads=cmrowsums,URL=contigurls)
      srvoom = rvoom[order(rvoom\$P.Value),]
      write.table(srvoom,out_VOOM, quote=FALSE, sep="\t",row.names=F)
      # Use an FDR cutoff to find interesting samples for edgeR, DESeq and voom/limma
      topresults.voom = srvoom[which(rvoom\$adj.P.Val < fdrthresh), ]
      voomcountsindex = which(allgenes %in% topresults.voom\$ID)
      voomcounts = rep(0, length(allgenes))
      voomcounts[voomcountsindex] = 1

#### Done

###sink(stdout(),append=T,type="message")
builtin_gmt=""
history_gmt=""
out_edgeR = F
out_DESeq2 = F
out_VOOM = F
doDESeq2 = $DESeq2.doDESeq2 # make these T or F
doVoom = $doVoom
doCamera = F 
doedgeR = $edgeR.doedgeR
edgeR_priordf = 0

#if $DESeq2.doDESeq2 == "T"
  out_DESeq2 = "$out_DESeq2"
  DESeq_fitType = "$DESeq2.DESeq_fitType"
#end if
#if $edgeR.doedgeR == "T"
  out_edgeR = "$out_edgeR"
  edgeR_priordf = $edgeR.edgeR_priordf
#end if
#if $doVoom == "T"
  out_VOOM = "$out_VOOM"
#end if

Out_Dir = "$html_file.files_path"
Input =  "$input1"
TreatmentName = "$treatment_name"
TreatmentCols = "$Treat_cols"

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)) )             #Build a group descriptor
group = factor(group, levels=c(ControlName,TreatmentName))
colnames(Count_Matrix) = paste(group,colnames(Count_Matrix),sep="_")                   #Relable columns
results = edgeIt(Count_Matrix=Count_Matrix,group=group,out_edgeR=out_edgeR, out_VOOM=out_VOOM, out_DESeq2=out_DESeq2,
                 fdrtype='BH',priordf=edgeR_priordf,fdrthresh=0.05,outputdir='.',
                 myTitle=myTitle,useNDF=F,libSize=c(),filterquantile=fQ,subjects=c(),
                 doDESeq2=doDESeq2,doVoom=doVoom,doCamera=doCamera,doedgeR=doedgeR,org=org,
                 histgmt=history_gmt,bigmt=builtin_gmt,DESeq_fitType=DESeq_fitType)
sessionInfo()