annotate edgeR_Differential_Gene_Expression.xml @ 3:12fb0d4b1e93 draft

planemo upload for repository https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools/raw/master/edger_with_design_matrix commit c7e4f2dfb8c35144b787850b60e116edfbaaa20f

<?xml version="1.0" encoding="UTF-8"?>
<tool id="edger_dge" name="edgeR: Differential Gene(Expression) Analysis" version="3.11.0.b">
    <description>RNA-Seq gene expression analysis using edgeR (R package)</description>
    
    <macros>
        <import>edgeR_macros.xml</import>
    </macros>
    
    <requirements>
        <requirement type="package" version="3.11.0">edger</requirement>
    </requirements>
    
    <stdio>
        <regex match="Error in[^a-z]+contrasts"
               source="both"
               level="fatal"
               description="Have the design- and expression-matrix been swapped?" />
        <regex match="Error in eval\(expr, envir, enclos\)"
               source="both"
               level="fatal"
               description="You have most likely used a condition in the contrast, that is not present in the Design matrix" />
        <regex match="Execution halted"
               source="both"
               level="fatal" />
        <regex match="Calculating library sizes from column" 
               source="stderr" 
               level="log" />
        <regex match="During startup - Warning messages"
               source="stderr"
               level="log" />
        <regex match="Setting LC_[^ ]+ failed"
               source="stderr"
               level="warning"
               description="LOCALE has not been set correctly" />
    </stdio>
    
    <version_command>echo $(R --version | grep version | grep -v GNU)", EdgeR version" $(R --vanilla --slave -e "library(edgeR) ; cat(sessionInfo()\$otherPkgs\$edgeR\$Version)" 2&gt; /dev/null | grep -v -i "WARNING: ")</version_command>
    
    <command>
        R --vanilla --slave -f $R_script '--args
            $expression_matrix
            $design_matrix
            $contrast
            
            $fdr
            
            $output_count_edgeR 
            $output_cpm
            
            /dev/null                                                    <!-- Calculation of FPKM/RPKM should come here -->
            
            #if $output_raw_counts:
                $output_raw_counts
            #else:
                /dev/null
            #end if
            
            #if $output_MDSplot_logFC:
                $output_MDSplot_logFC
            #else:
                /dev/null
            #end if
            
            #if $output_MDSplot_logFC_coordinates:
                $output_MDSplot_logFC_coordinates
            #else:
                /dev/null
            #end if
            
            #if $output_MDSplot_bcv:
                $output_MDSplot_bcv
            #else:
                /dev/null
            #end if
            
            #if $output_MDSplot_bcv_coordinates:
                $output_MDSplot_bcv_coordinates
            #else:
                /dev/null
            #end if
            
            #if $output_BCVplot:
                $output_BCVplot
            #else:
                /dev/null
            #end if
            
            #if $output_MAplot:
                $output_MAplot
            #else:
                /dev/null
            #end if
            
            #if $output_PValue_distribution_plot:
                $output_PValue_distribution_plot
            #else:
                /dev/null
            #end if
            
            #if $output_hierarchical_clustering_plot:
                $output_hierarchical_clustering_plot
            #else:
                /dev/null
            #end if
            
            #if $output_heatmap_plot:
                $output_heatmap_plot
            #else:
                /dev/null
            #end if
            
            #if $output_RData_obj:
                $output_RData_obj
            #else:
                /dev/null
            #end if
            
            $output_format_images
            '
    </command>
    
    <configfiles>
        <configfile name="R_script">
<![CDATA[

library(limma,quietly=TRUE)  ## quietly to avoid unnecessaity stderr messages
library(edgeR,quietly=TRUE)  ## quietly to avoid unnecessaity stderr messages
library(splines,quietly=TRUE)## quietly to avoid unnecessaity stderr messages
 
## Fetch commandline arguments
args <- commandArgs(trailingOnly = TRUE)

expression_matrix_file              <- args[1]
design_matrix_file                  <- args[2]
contrast                            <- args[3]

fdr                                 <- args[4]

output_count_edgeR                  <- args[5]
output_cpm                          <- args[6]

output_xpkm                         <- args[7]        ##FPKM file - to be implemented

output_raw_counts                   <- args[8]

output_MDSplot_logFC                <- args[9]
output_MDSplot_logFC_coordinates    <- args[10]

output_MDSplot_bcv                  <- args[11]
output_MDSplot_bcv_coordinates      <- args[12]

output_BCVplot                      <- args[13]
output_MAplot                       <- args[14]
output_PValue_distribution_plot     <- args[15]
output_hierarchical_clustering_plot <- args[16]
output_heatmap_plot                 <- args[17]
output_RData_obj                    <- args[18]
output_format_images                <- args[19]


## Obtain read-counts
expression_matrix <- read.delim(expression_matrix_file,header=T,stringsAsFactors=F,row.names=1,check.names=FALSE,na.strings=c(""))
design_matrix <- read.delim(design_matrix_file,header=T,stringsAsFactors=F,row.names=1,check.names=FALSE,na.strings=c(""))

colnames(design_matrix) <- make.names(colnames(design_matrix))

for(i in 1:ncol(design_matrix)) {
  old <- design_matrix[,i]
  design_matrix[,i] <- make.names(design_matrix[,i])
  if(paste(design_matrix[,i],collapse="\t") != paste(old,collapse="\t")) {
    print("Renaming of factors:")
    print(old)
    print("To:")
    print(design_matrix[,i])
  }
  ## The following line seems to malfunction the script:
  ##design_matrix[,i] <- as.factor(design_matrix[,i])
}

## 1) In the expression matrix, you only want to have the samples described in the design matrix
columns <- match(rownames(design_matrix),colnames(expression_matrix))
columns <- columns[!is.na(columns)]
read_counts <- expression_matrix[,columns]

## 2) In the design matrix, you only want to have samples of which you really have the counts
columns <- match(colnames(read_counts),rownames(design_matrix))
columns <- columns[!is.na(columns)]
design_matrix <- design_matrix[columns,,drop=FALSE]

## Filter for HTSeq predifined counts:
exclude_HTSeq <- c("no_feature","ambiguous","too_low_aQual","not_aligned","alignment_not_unique")
exclude_DEXSeq <- c("_ambiguous","_empty","_lowaqual","_notaligned")

exclude <- match(c(exclude_HTSeq, exclude_DEXSeq),rownames(read_counts))
exclude <- exclude[is.na(exclude)==0]
if(length(exclude) != 0)  {
  read_counts <- read_counts[-exclude,]
}


## sorting expression matrix with the order of the read_counts
##order <- match(colnames(read_counts) , rownames(design_matrix))
##read_counts_ordered  <- read_counts[,order2]

empty_samples <- apply(read_counts,2,function(x) sum(x) == 0)
if(sum(empty_samples) > 0) {
  write(paste("There are ",sum(empty_samples)," empty samples found:",sep=""),stderr())
  write(colnames(read_counts)[empty_samples],stderr())
} else {
  
  dge <- DGEList(counts=read_counts,genes=rownames(read_counts))
  
  formula <- paste(c("~0",make.names(colnames(design_matrix))),collapse = " + ")
  design_matrix_tmp <- design_matrix
  colnames(design_matrix_tmp) <- make.names(colnames(design_matrix_tmp))
  design <- model.matrix(as.formula(formula),design_matrix_tmp)
  rm(design_matrix_tmp)
  
  # Filter prefixes
  prefixes = colnames(design_matrix)[attr(design,"assign")]
  avoid = nchar(prefixes) == nchar(colnames(design))
  replacements = substr(colnames(design),nchar(prefixes)+1,nchar(colnames(design)))
  replacements[avoid] = colnames(design)[avoid]
  colnames(design) = replacements
  
  # Do normalization
  write("Calculating normalization factors...",stdout())
  dge <- calcNormFactors(dge)
  write("Estimating common dispersion...",stdout())
  dge <- estimateGLMCommonDisp(dge,design)
  write("Estimating trended dispersion...",stdout())
  dge <- estimateGLMTrendedDisp(dge,design)
  write("Estimating tagwise dispersion...",stdout())
  dge <- estimateGLMTagwiseDisp(dge,design)
  
  
  # hierarchical clustering makes use of the distance of the MDS
  if(output_MDSplot_logFC != "/dev/null" || output_MDSplot_logFC_coordinates != "/dev/null" || output_hierarchical_clustering_plot != "/dev/null") {
    write("Calculating MDS plot (logFC method)",stdout())
    n_dim <- nrow(dge\$samples)
    mds_distance_logFC <- plotMDS.DGEList(dge,top=500,labels=rep("",nrow(dge\$samples)),dim.plot=c(n_dim-2,n_dim-1))
    dev.off()# Kill it
    
    # Reset to primary dimensions
    mds_distance_logFC\$x = mds_distance_logFC\$cmdscale.out[,1]
    mds_distance_logFC\$y = mds_distance_logFC\$cmdscale.out[,2]
    
    if(output_MDSplot_logFC != "/dev/null") {  
      write("Creating MDS plot (logFC method)",stdout())
      if(output_format_images == "pdf") {
        pdf(output_MDSplot_logFC,height=14,width=14)
      } else if(output_format_images == "svg") {
        svg(output_MDSplot_logFC,height=14,width=14)
      } else {
        ## png(output_MDSplot_logFC)
        ## png does not work out of the box in the Galaxy Toolshed Version of R due to its compile settings: https://biostar.usegalaxy.org/p/9170/
        
        bitmap(output_MDSplot_logFC,type="png16m",height=7*3,width=7*3)
      }
      
      diff_x <- abs(max(mds_distance_logFC\$x)-min(mds_distance_logFC\$x))
      diff_y <-(max(mds_distance_logFC\$y)-min(mds_distance_logFC\$y))
      plot(c(min(mds_distance_logFC\$x),max(mds_distance_logFC\$x) + 0.45 * diff_x), c(min(mds_distance_logFC\$y) - 0.05 * diff_y,max(mds_distance_logFC\$y) + 0.05 * diff_y), main="edgeR logFC-MDS Plot on top 500 genes",type="n", xlab="Leading logFC dim 1", ylab="Leading logFC dim 2")
      points(mds_distance_logFC\$x,mds_distance_logFC\$y,pch=20)
      text(mds_distance_logFC\$x,mds_distance_logFC\$y,rownames(dge\$samples),cex=1.25,col="gray",pos=4)
      rm(diff_x,diff_y)
      
      dev.off()
    }
    
    if(output_MDSplot_logFC_coordinates != "/dev/null") {
      n_dim <- ncol(mds_distance_logFC\$cmdscale.out)
      colnames(mds_distance_logFC\$cmdscale.out) <- paste(rep("Dim",n_dim),(1:n_dim),sep="_")
      export <- data.frame(samples=rownames(mds_distance_logFC\$cmdscale.out),mds_distance_logFC\$cmdscale.out)
      row.names(export) <- NULL
      write.table(file=output_MDSplot_logFC_coordinates,export,sep="\t",row.names=FALSE,col.names=TRUE)
    }
  }
  
  
  if(output_MDSplot_bcv != "/dev/null" || output_MDSplot_bcv_coordinates != "/dev/null" ) {
    write("Creating MDS plot (bcv method)",stdout())
    
    ## 1. First create a virtual plot to obtain the desired coordinates
    n_dim <- nrow(dge\$samples)
    mds_distance_BCV <- plotMDS.DGEList(dge,method="bcv",top=500,labels=rep("",nrow(dge\$samples)),dim.plot=c(n_dim-2,n_dim-1))
    dev.off()
    
    if(output_MDSplot_logFC != "/dev/null") {  
      ## 2. Re-plot the coordinates in a new figure with the size and settings.
      if(output_format_images == "pdf") {
        pdf(output_MDSplot_bcv,height=14,width=14)
      } else if(output_format_images == "svg") {
        svg(output_MDSplot_bcv,height=14,width=14)
      } else {
        ## png(output_MDSplot_bcv)
        ## png does not work out of the box in the Galaxy Toolshed Version of R due to its compile settings: https://biostar.usegalaxy.org/p/9170/
        
        bitmap(output_MDSplot_bcv,type="png16m",height=7*3,width=7*3)
      }
      
      diff_x <- abs(max(mds_distance_BCV\$x)-min(mds_distance_BCV\$x))
      diff_y <- (max(mds_distance_BCV\$y)-min(mds_distance_BCV\$y))
      plot(c(min(mds_distance_BCV\$x),max(mds_distance_BCV\$x) + 0.45 * diff_x), c(min(mds_distance_BCV\$y) - 0.05 * diff_y,max(mds_distance_BCV\$y) + 0.05 * diff_y), main="edgeR BCV-MDS Plot",type="n", xlab="Leading BCV dim 1", ylab="Leading BCV dim 2")
      points(mds_distance_BCV\$x,mds_distance_BCV\$y,pch=20)
      text(mds_distance_BCV\$x, mds_distance_BCV\$y,rownames(dge\$samples),cex=1.25,col="gray",pos=4)
      rm(diff_x,diff_y)
      
      dev.off()
    }
    
    if(output_MDSplot_bcv_coordinates != "/dev/null") { 
      n_dim <- ncol(mds_distance_BCV\$cmdscale.out)
      colnames(mds_distance_BCV\$cmdscale.out) <- paste(rep("Dim",n_dim),(1:n_dim),sep="_")
      export <- data.frame(samples=rownames(mds_distance_BCV\$cmdscale.out),mds_distance_BCV\$cmdscale.out)
      row.names(export) <- NULL
      write.table(file=output_MDSplot_bcv_coordinates,export,sep="\t",row.names=FALSE,col.names=TRUE)
    }
  }
  
  
  if(output_BCVplot != "/dev/null") {
    write("Creating Biological coefficient of variation plot",stdout())
    
    if(output_format_images == "pdf") {
      pdf(output_BCVplot)
    } else if(output_format_images == "svg") {
      svg(output_BCVplot)
    } else {
      ## png(output_BCVplot)
      ## png does not work out of the box in the Galaxy Toolshed Version of R due to its compile settings: https://biostar.usegalaxy.org/p/9170/
      
      bitmap(output_BCVplot,type="png16m",width=10.5*3,height=7*3)
    }
    
    plotBCV(dge, cex=0.4, main="edgeR: Biological coefficient of variation (BCV) vs abundance")
    dev.off()
  }
  
  
  write("Fitting GLM...",stdout())
  fit <- glmFit(dge,design)

  write(paste("Performing likelihood ratio test: ",contrast,sep=""),stdout())
  cont <- c(contrast)
  cont <- makeContrasts(contrasts=cont, levels=design)

  lrt <- glmLRT(fit, contrast=cont[,1])
  write(paste("Exporting DGE results to file...",output_count_edgeR,sep=""),stdout())
  write.table(file=output_count_edgeR,topTags(lrt,n=nrow(read_counts))\$table,sep="\t",row.names=TRUE,col.names=NA)
  write.table(file=output_cpm,cpm(dge,normalized.lib.sizes=TRUE),sep="\t",row.names=TRUE,col.names=NA)

  ## todo EXPORT FPKM
  write.table(file=output_raw_counts,dge\$counts,sep="\t",row.names=TRUE,col.names=NA)
  
  if(output_MAplot != "/dev/null" || output_PValue_distribution_plot != "/dev/null") {
    etable <- topTags(lrt, n=nrow(dge))\$table
    etable <- etable[order(etable\$FDR), ]
    
    if(output_MAplot != "/dev/null") {
      write("Creating MA plot...",stdout())
      
      if(output_format_images == "pdf") {
        pdf(output_MAplot)
      } else if(output_format_images == "svg") {
        svg(output_MAplot)
      } else {
        ## png(output_MAplot)
        ## png does not work out of the box in the Galaxy Toolshed Version of R due to its compile settings: https://biostar.usegalaxy.org/p/9170/
        
        bitmap(output_MAplot,type="png16m",width=10.5*3,height=7*3)
      }
      
      with(etable, plot(logCPM, logFC, pch=20, main="edgeR: Fold change vs abundance"))
      with(subset(etable, FDR < fdr), points(logCPM, logFC, pch=20, col="red"))
      abline(h=c(-1,1), col="blue")
      dev.off()
    }
  
    if(output_PValue_distribution_plot != "/dev/null") {
      write("Creating P-value distribution plot...",stdout())
      
      if(output_format_images == "pdf") {
        pdf(output_PValue_distribution_plot,width=14,height=14)
      } else if(output_format_images == "svg") {
        svg(output_PValue_distribution_plot,width=14,height=14)
      } else {
        ## png(output_PValue_distribution_plot)
        ## png does not work out of the box in the Galaxy Toolshed Version of R due to its compile settings: https://biostar.usegalaxy.org/p/9170/
        
        bitmap(output_PValue_distribution_plot,type="png16m",width=7*3,height=7*3)
      }
      
      expressed_genes <- subset(etable, PValue < 0.99)
      h <- hist(expressed_genes\$PValue,breaks=nrow(expressed_genes)/15,main="Binned P-Values (< 0.99)")
      center <- sum(h\$counts) / length(h\$counts)
      lines(c(0,1),c(center,center),lty=2,col="red",lwd=2)
      k <- ksmooth(h\$mid, h\$counts)
      lines(k\$x,k\$y,col="red",lwd=2)
      rmsd <- (h\$counts) - center
      rmsd <- rmsd^2
      rmsd <- sum(rmsd)
      rmsd <- sqrt(rmsd)
      text(0,max(h\$counts),paste("e=",round(rmsd,2),sep=""),pos=4,col="blue")
      ## change e into epsilon somehow
      dev.off()
    }
  }
  
  if(output_heatmap_plot != "/dev/null") {
    
    if(output_format_images == "pdf") {
      pdf(output_heatmap_plot,width=10.5)
    } else if(output_format_images == "svg") {
      svg(output_heatmap_plot,width=10.5)
    } else {
      ## png(output_heatmap_plot)
      ## png does not work out of the box in the Galaxy Toolshed Version of R due to its compile settings: https://biostar.usegalaxy.org/p/9170/
      
      bitmap(output_heatmap_plot,type="png16m",width=10.5*3,height=7*3)
    }
    
    etable2 <- topTags(lrt, n=100)\$table
    order <- rownames(etable2)
    cpm_sub <- cpm(dge,normalized.lib.sizes=TRUE,log=TRUE)[as.numeric(order),]
    heatmap(t(cpm_sub))
    dev.off()
  }
  
  if(output_hierarchical_clustering_plot != "/dev/null") {
    if(output_hierarchical_clustering_plot == "pdf") {
      pdf(output_hierarchical_clustering_plot,width=10.5)
    } else if(output_hierarchical_clustering_plot == "svg") {
      svg(output_hierarchical_clustering_plot,width=10.5)
    } else {
      ## png(output_hierarchical_clustering_plot)
      ## png does not work out of the box in the Galaxy Toolshed Version of R due to its compile settings: https://biostar.usegalaxy.org/p/9170/
      
      bitmap(output_hierarchical_clustering_plot,type="png16m",width=10.5*3,height=7*3)
    }
    
    mds_distance = as.dist(mds_distance_logFC\$distance.matrix)
    clustering = hclust(mds_distance)
    plot(clustering,main=paste("Cluster Dendogram on the ",mds_distance_logFC\$top," TopTags",sep="",sub="\ncomplete linkage on logFC MDS distance"))
    
    dev.off()
  }
  
  if(output_RData_obj != "/dev/null") {
    save.image(output_RData_obj)
  }
  
  write("Done!",stdout())
}
]]>
        </configfile>
    </configfiles>
    
    <inputs>
        <param name="expression_matrix" type="data" format="tabular" label="Expression (read count) matrix" />
        <param name="design_matrix" type="data" format="tabular" label="Design matrix" help="Ensure your samplenames are identical to those in the expression matrix. Preferentially, create the contrast matrix using 'edgeR: Design- from Expression matrix'." />
        
        <param name="contrast" type="text" label="Contrast (biological question)" help="e.g. 'tumor-normal' or '(G1+G2)/2-G3' using the factors chosen in the design matrix. Read the 'makeContrasts' manual from Limma package for more info: http://www.bioconductor.org/packages/release/bioc/html/limma.html and http://www.bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf." />
        
        <param name="fdr" type="float" min="0" max="1" value="0.05" label="False Discovery Rate (FDR)" />
        
        <param name="outputs" type="select" label="Optional desired outputs" multiple="true" display="checkboxes">
            <option value="make_output_raw_counts">Raw counts table</option>
            <option value="make_output_MDSplot_logFC">MDS-plot (logFC-method)</option>
            <option value="make_output_MDSplot_logFC_coordinates">MDS-plot coordinates table (logFC-method)</option>
            <option value="make_output_MDSplot_bcv">MDS-plot (BCV-method; slow)</option>
            <option value="make_output_MDSplot_bcv_coordinates">MDS-plot coordinates table (BCV-method; slow)</option>
            <option value="make_output_BCVplot">BCV-plot</option>
            <option value="make_output_MAplot">MA-plot</option>
            <option value="make_output_PValue_distribution_plot">P-Value distribution plot</option>
            <option value="make_output_hierarchical_clustering_plot">Hierarchical custering</option>
            <option value="make_output_heatmap_plot">Heatmap</option>
            <option value="make_output_RData_obj">R Data object</option>
        </param>
        
        <param name="output_format_images" type="select" label="Output format of images" display="radio">
            <option value="png">Portable network graphics (.png)</option>
            <option value="pdf">Portable document format (.pdf)</option>
            <option value="svg">Scalable vector graphics (.svg)</option>
        </param>
    </inputs>
    
    <outputs>
        <data format="tabular" name="output_count_edgeR" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - differentially expressed genes" />
        <data format="tabular" name="output_cpm" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - CPM" />
        
        <data format="tabular" name="output_raw_counts" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - raw counts">
            <filter>outputs and ("make_output_raw_counts" in outputs)</filter>
        </data>
        
        <data format="png" name="output_MDSplot_logFC" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MDS-plot (logFC method)">
            <filter>outputs and ("make_output_MDSplot_logFC" in outputs)</filter>
            
            <change_format>
                <when input="output_format_images" value="png" format="png" />
                <when input="output_format_images" value="pdf" format="pdf" />
                <when input="output_format_images" value="svg" format="svg" />
            </change_format>
        </data>
        
        <data format="tabular" name="output_MDSplot_logFC_coordinates" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MDS-plot coordinates table (logFC method)">
            <filter>outputs and ("make_output_MDSplot_logFC_coordinates" in outputs)</filter>
        </data>
        
        <data format="png" name="output_MDSplot_bcv" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MDS-plot (bcv method)">
            <filter>outputs and ("make_output_MDSplot_bcv" in outputs)</filter>
            
            <change_format>
                <when input="output_format_images" value="png" format="png" />
                <when input="output_format_images" value="pdf" format="pdf" />
                <when input="output_format_images" value="svg" format="svg" />
            </change_format>
        </data>
        
        <data format="tabular" name="output_MDSplot_bcv_coordinates" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MDS-plot coordinates table (BCV method)">
            <filter>outputs and ("make_output_MDSplot_bcv_coordinates" in outputs)</filter>
        </data>
        
        <data format="png" name="output_BCVplot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - BCV-plot">
            <filter>outputs and ("make_output_BCVplot" in outputs)</filter>
            
            <change_format>
                <when input="output_format_images" value="png" format="png" />
                <when input="output_format_images" value="pdf" format="pdf" />
                <when input="output_format_images" value="svg" format="svg" />
            </change_format>
        </data>
        
        <data format="png" name="output_MAplot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MA-plot">
            <filter>outputs and ("make_output_MAplot" in outputs)</filter>
            
            <change_format>
                <when input="output_format_images" value="png" format="png" />
                <when input="output_format_images" value="pdf" format="pdf" />
                <when input="output_format_images" value="svg" format="svg" />
            </change_format>
        </data>
        
        <data format="png" name="output_PValue_distribution_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - P-Value distribution">
            <filter>outputs and ("make_output_PValue_distribution_plot" in outputs)</filter>
            
            <change_format>
                <when input="output_format_images" value="png" format="png" />
                <when input="output_format_images" value="pdf" format="pdf" />
                <when input="output_format_images" value="svg" format="svg" />
            </change_format>
        </data>
        
        <data format="png" name="output_hierarchical_clustering_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - Hierarchical custering">
            <filter>outputs and ("make_output_hierarchical_clustering_plot" in outputs)</filter>
            
            <change_format>
                <when input="output_format_images" value="png" format="png" />
                <when input="output_format_images" value="pdf" format="pdf" />
                <when input="output_format_images" value="svg" format="svg" />
            </change_format>
        </data>
        
        <data format="png" name="output_heatmap_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - Heatmap">
            <filter>outputs and ("make_output_heatmap_plot" in outputs)</filter>
            
            <change_format>
                <when input="output_format_images" value="png" format="png" />
                <when input="output_format_images" value="pdf" format="pdf" />
                <when input="output_format_images" value="svg" format="svg" />
            </change_format>
        </data>
        
        <data format="RData" name="output_RData_obj" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - R data object">
            <filter>outputs and ("make_output_RData_obj" in outputs)</filter>
        </data>
        
        <data format="txt" name="output_R" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - R output (debug)" >
            <filter>outputs and ("make_output_R_stdout" in outputs)</filter>
        </data>
    </outputs>
    
    <tests>
        <test>
            <param name="expression_matrix" value="Differential_Gene_Expression/expression_matrix.tabular.txt" />
            <param name="design_matrix" value="Differential_Gene_Expression/design_matrix.tabular.txt" />
            
            <param name="contrast" value="E-C"/>
        
            <param name="fdr" value="0.05" />
            
            <param name="output_format_images" value="png" />
            
            <output name="output_count_edgeR" file="Differential_Gene_Expression/differentially_expressed_genes.tabular.txt" />
        </test>
    </tests>
    
    <help>
edgeR: Differential Gene(Expression) Analysis
#############################################

Overview
--------
Differential expression analysis of RNA-seq and digital gene expression profiles with biological replication. Uses empirical Bayes estimation and exact tests based on the negative binomial distribution. Also useful for differential signal analysis with other types of genome-scale count data [1].

For every experiment, the algorithm requires a design matrix. This matrix describes which samples belong to which groups.
More details on this are given in the edgeR manual: http://www.bioconductor.org/packages/2.12/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf
and the limma manual.

Because the creation of a design matrix can be complex and time consuming, especially if no GUI is used, this package comes with an alternative tool which can help you with it.
This tool is called *edgeR Design Matrix Creator*.
If the appropriate design matrix (with corresponding links to the files) is given,
the correct contrast ( http://en.wikipedia.org/wiki/Contrast_(statistics) ) has to be given.

If you have for example two groups, with an equal weight, you would like to compare either
"g1-g2" or "normal-cancer".

The test function makes use of a MCF7 dataset used in a study that indicates that a higher sequencing depth is not neccesairily more important than a higher amount of replaciates[2].

Input
-----
Expression matrix
^^^^^^^^^^^^^^^^^
::

  Geneid  "\t" Sample-1 "\t" Sample-2 "\t" Sample-3 "\t" Sample-4 [...] "\n"
  SMURF   "\t"      123 "\t"       21 "\t"    34545 "\t"       98  ...  "\n"
  BRCA1   "\t"      435 "\t"     6655 "\t"       45 "\t"       55  ...  "\n"
  LINK33  "\t"        4 "\t"      645 "\t"      345 "\t"        1  ...  "\n"
  SNORD78 "\t"      498 "\t"       65 "\t"       98 "\t"       27  ...  "\n"
  [...]

*Note: Make sure the number of columns in the header is identical to the number of columns in the body.*

Design matrix
^^^^^^^^^^^^^
::

  Sample    "\t" Condition "\t" Ethnicity "\t" Patient "\t" Batch "\n"
  Sample-1  "\t"     Tumor "\t"  European "\t"       1 "\t"     1 "\n"
  Sample-2  "\t"    Normal "\t"  European "\t"       1 "\t"     1 "\n"
  Sample-3  "\t"     Tumor "\t"  European "\t"       2 "\t"     1 "\n"
  Sample-4  "\t"    Normal "\t"  European "\t"       2 "\t"     1 "\n"
  Sample-5  "\t"     Tumor "\t"   African "\t"       3 "\t"     1 "\n"
  Sample-6  "\t"    Normal "\t"   African "\t"       3 "\t"     1 "\n"
  Sample-7  "\t"     Tumor "\t"   African "\t"       4 "\t"     2 "\n"
  Sample-8  "\t"    Normal "\t"   African "\t"       4 "\t"     2 "\n"
  Sample-9  "\t"     Tumor "\t"     Asian "\t"       5 "\t"     2 "\n"
  Sample-10 "\t"    Normal "\t"     Asian "\t"       5 "\t"     2 "\n"
  Sample-11 "\t"     Tumor "\t"     Asian "\t"       6 "\t"     2 "\n"
  Sample-12 "\t"    Normal "\t"     Asian "\t"       6 "\t"     2 "\n"

*Note: Avoid factor names that are (1) numerical, (2) contain mathematical symbols and preferebly only use letters.*

Contrast
^^^^^^^^
The contrast represents the biological question. There can be many questions asked, e.g.:

- Tumor-Normal
- African-European
- 0.5*(Control+Placebo) / Treated

Installation
------------

This tool requires no specific configuration. The following dependencies will installed automatically:

- R
- limma
- edgeR

License
-------
- R
    - GPL 2 &amp; GPL 3
- limma
    - GPL (&gt;=2)
- edgeR
    - GPL (&gt;=2)

@CONTACT@
    </help>
    
    <expand macro="citations" />
</tool>