edger_with_design_matrix: edgeR_Differential_Gene

comparison edgeR_Differential_Gene_Expression.xml @ 2:ec951a5017f8 draft

planemo upload for repository https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools/raw/master/edger_with_design_matrix commit a6cf3ec153ca4a3846258a223d287ca125eea7be

author	yhoogstrate
date	Tue, 01 Sep 2015 09:15:07 -0400
parents	a4a4c88783ea
children	12fb0d4b1e93

comparison

equal deleted inserted replaced

-:a4a4c88783ea
+:ec951a5017f8
 <?xml version="1.0" encoding="UTF-8"?>
-<tool id="edger_dge" name="edgeR: Differential Gene(Expression) Analysis" version="3.11.0.a">
+<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>
 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>
+<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
 /dev/null
 #end if
 $output_format_images
 '
-#if $output_R:
-> $output_R
-#else:
-> /dev/null
-#end if
 </command>
 <configfiles>
 <configfile name="R_script">
 <![CDATA[
 dge <- estimateGLMTrendedDisp(dge,design)
 write("Estimating tagwise dispersion...",stdout())
 dge <- estimateGLMTagwiseDisp(dge,design)
-if(output_MDSplot_logFC != "/dev/null") {
+# hierarchical clustering makes use of the distance of the MDS
-write("Creating MDS plot (logFC method)",stdout())
+if(output_MDSplot_logFC != "/dev/null" || output_hierarchical_clustering_plot != "/dev/null") {
-points <- plotMDS.DGEList(dge,top=500,labels=rep("",nrow(dge\$samples)))# Get coordinates of unflexible plot
+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_format_images == "pdf") {
+if(output_MDSplot_logFC != "/dev/null") {
-pdf(output_MDSplot_logFC,height=14,width=14)
+write("Creating MDS plot (logFC method)",stdout())
-} else if(output_format_images == "svg") {
+if(output_format_images == "pdf") {
-svg(output_MDSplot_logFC,height=14,width=14)
+pdf(output_MDSplot_logFC,height=14,width=14)
-} else {
+} else if(output_format_images == "svg") {
-## png(output_MDSplot_logFC)
+svg(output_MDSplot_logFC,height=14,width=14)
-## 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/
+} else {
+## png(output_MDSplot_logFC)
-bitmap(output_MDSplot_logFC,type="png16m",height=14,width=14)
+## 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(points\$x)-min(points\$x))
-diff_y <-(max(points\$y)-min(points\$y))
+diff_x <- abs(max(mds_distance_logFC\$x)-min(mds_distance_logFC\$x))
-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")
+diff_y <-(max(mds_distance_logFC\$y)-min(mds_distance_logFC\$y))
-points(points\$x,points\$y,pch=20)
+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")
-text(points\$x, points\$y,rownames(dge\$samples),cex=1.25,col="gray",pos=4)
+points(mds_distance_logFC\$x,mds_distance_logFC\$y,pch=20)
-rm(diff_x,diff_y)
+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()
-}
+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)))
+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=14,width=14)
+bitmap(output_MDSplot_bcv,type="png16m",height=7*3,width=7*3)
 }
-diff_x <- abs(max(points\$x)-min(points\$x))
+diff_x <- abs(max(mds_distance_BCV\$x)-min(mds_distance_BCV\$x))
-diff_y <- (max(points\$y)-min(points\$y))
+diff_y <- (max(mds_distance_BCV\$y)-min(mds_distance_BCV\$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")
+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(points\$x,points\$y,pch=20)
+points(mds_distance_BCV\$x,mds_distance_BCV\$y,pch=20)
-text(points\$x, points\$y,rownames(dge\$samples),cex=1.25,col="gray",pos=4)
+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")
+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 to file: ",output_count_edgeR,sep=""),stdout())
+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")
+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=14,height=14)
+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)
+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()
 }
-##output_hierarchical_clustering_plot = args[13]
+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 (under contstruction)</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>
 <param name="output_format_images" type="select" label="Output format of images" display="radio">
 <option value="png">Portable network graphics (.png)</option>
 - 0.5*(Control+Placebo) / Treated
 Installation
 ------------
-This tool requires no specific configurations. The following dependencies are installed automatically:
+This tool requires no specific configuration. The following dependencies will installed automatically:
 - R
 - limma
 - edgeR
 - limma
 - GPL (&gt;=2)
 - edgeR
 - GPL (&gt;=2)
-References
-----------
-EdgeR
-^^^^^
-**[1] edgeR: a Bioconductor package for differential expression analysis of digital gene expression data.**
-*Mark D. Robinson, Davis J. McCarthy and Gordon K. Smyth* - Bioinformatics (2010) 26 (1): 139-140.
-- http://www.bioconductor.org/packages/2.12/bioc/html/edgeR.html
-- http://dx.doi.org/10.1093/bioinformatics/btp616
-- http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
-Test-data (MCF7)
-^^^^^^^^^^^^^^^^
-**[2] RNA-seq differential expression studies: more sequence or more replication?**
-*Yuwen Liu, Jie Zhou and Kevin P. White* - Bioinformatics (2014) 30 (3): 301-304.
-- http://www.ncbi.nlm.nih.gov/pubmed/24319002
-- http://dx.doi.org/10.1093/bioinformatics/btt688
 @CONTACT@
 </help>
 <expand macro="citations" />
 </tool>

Mercurial > repos > yhoogstrate > edger_with_design_matrix

comparison edgeR_Differential_Gene_Expression.xml @ 2:ec951a5017f8 draft