comparison edgeR_Differential_Gene_Expression.xml @ 111:b9abc9d3b429 draft

planemo upload for repository https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools/raw/master/edger_with_design_matrix commit 097f2974042345a231e431299a031f236f3eb689

110:3112b2926266

  dge <- estimateGLMTrendedDisp(dge,design)
  write("Estimating tagwise dispersion...",stdout())
  dge <- estimateGLMTagwiseDisp(dge,design)
  
  
  if(output_MDSplot_logFC != "/dev/null") {
    write("Creating MDS plot (logFC method)",stdout())
    points <- plotMDS.DGEList(dge,top=500,labels=rep("",nrow(dge\$samples)))# Get coordinates of unflexible plot
    dev.off()# Kill it
    
    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=14,width=14)
    }
    
    
    diff_x <- abs(max(points\$x)-min(points\$x))
    diff_y <-(max(points\$y)-min(points\$y))
    plot(c(min(points\$x),max(points\$x) + 0.45 * diff_x), c(min(points\$y) - 0.05 * diff_y,max(points\$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(points\$x,points\$y,pch=20)
    text(points\$x, points\$y,rownames(dge\$samples),cex=1.25,col="gray",pos=4)
    rm(diff_x,diff_y)
    
    dev.off()
  }
  
  if(output_MDSplot_bcv != "/dev/null") {
    write("Creating MDS plot (bcv method)",stdout())
    
    ## 1. First create a virtual plot to obtain the desired coordinates
    pdf("bcvmds.pdf")
    points <- plotMDS.DGEList(dge,method="bcv",top=500,labels=rep("",nrow(dge\$samples)))
    dev.off()# Kill it
    
    ## 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)

      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=14,width=14)
    }
    
    diff_x <- abs(max(points\$x)-min(points\$x))
    diff_y <- (max(points\$y)-min(points\$y))
    plot(c(min(points\$x),max(points\$x) + 0.45 * diff_x), c(min(points\$y) - 0.05 * diff_y,max(points\$y) + 0.05 * diff_y), main="edgeR BCV-MDS Plot",type="n", xlab="Leading BCV dim 1", ylab="Leading BCV dim 2")
    points(points\$x,points\$y,pch=20)
    text(points\$x, points\$y,rownames(dge\$samples),cex=1.25,col="gray",pos=4)
    rm(diff_x,diff_y)
    
    dev.off()
  }
  

      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")
    }
    
    plotBCV(dge, cex=0.4, main="edgeR: Biological coefficient of variation (BCV) vs abundance")
    dev.off()
  }

  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 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)

        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")
      }
      
      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")

        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=14,height=14)
      }
      
      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)

      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)
    }
    
    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()
  }
  
  ##output_hierarchical_clustering_plot = args[13]
  
  if(output_RData_obj != "/dev/null") {
    save.image(output_RData_obj)
  }
  

            <option value="make_output_MDSplot_logFC">MDS-plot (logFC-method)</option>
            <option value="make_output_MDSplot_bcv">MDS-plot (BCV-method; much slower)</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 (under contstruction)</option>
            <option value="make_output_heatmap_plot">Heatmap</option>
            
            <option value="make_output_R_stdout">R stdout</option>
            <option value="make_output_RData_obj">R Data object</option>
        </param>

111:b9abc9d3b429

  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_hierarchical_clustering_plot != "/dev/null") {
    write("Calculating MDS plot (logFC method)",stdout())
    mds_distance_logFC <- plotMDS.DGEList(dge,top=500,labels=rep("",nrow(dge\$samples)))# Get coordinates of unflexible plot
    dev.off()# Kill it
    
    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")
      mds_distance_logFC(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_bcv != "/dev/null") {
    write("Creating MDS plot (bcv method)",stdout())
    
    ## 1. First create a virtual plot to obtain the desired coordinates
    pdf("bcvmds.pdf")
    mds_distance_BCV <- plotMDS.DGEList(dge,method="bcv",top=500,labels=rep("",nrow(dge\$samples)))
    dev.off()# Kill it
    
    ## 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)

      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")
    mds_distance_BCV(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()
  }
  

      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(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)

        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")

        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)

      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)
  }
  

            <option value="make_output_MDSplot_logFC">MDS-plot (logFC-method)</option>
            <option value="make_output_MDSplot_bcv">MDS-plot (BCV-method; much slower)</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_R_stdout">R stdout</option>
            <option value="make_output_RData_obj">R Data object</option>
        </param>