Mercurial > repos > yhoogstrate > edger_with_design_matrix
diff edgeR_Differential_Gene_Expression.xml @ 5:bde663b872d9 draft
planemo upload for repository https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools/raw/master/edger_with_design_matrix commit 275a72ec0424e4e5d658d1bc8227077ea46f0fdc
| author | yhoogstrate |
|---|---|
| date | Mon, 14 Dec 2015 11:01:38 -0500 |
| parents | 5d38abf7e4b6 |
| children | 31a23ae7c61e |
line wrap: on
line diff
--- a/edgeR_Differential_Gene_Expression.xml Wed Dec 09 10:43:03 2015 -0500 +++ b/edgeR_Differential_Gene_Expression.xml Mon Dec 14 11:01:38 2015 -0500 @@ -36,18 +36,58 @@ <version_command>echo $(R --version | grep version | grep -v GNU)", EdgeR version" $(R --vanilla --slave -e "library(edgeR) ; cat(sessionInfo()\$otherPkgs\$edgeR\$Version)" 2> /dev/null | grep -v -i "WARNING: ")</version_command> - <command> + <command><![CDATA[ + #if $analysis_type.analysis_select == "multi_factor" + #set $expression_matrix = $analysis_type.expression_matrix + #set $design_matrix = $analysis_type.design_matrix + #set $contrast = $analysis_type.contrast + #else + ## Design and Expression matrices do not exist - create them + #set $expression_matrix = "expression_matrix.txt" + #set $design_matrix = "design_matrix.txt" + #set $contrast = str($analysis_type.factorLevel_condition)+"-"+str($analysis_type.factorLevel_control) + + ## -- Create expression matrix + cut -f 1 "$analysis_type.countsFile_control[1]" > gene_ids.column.txt && + #for $file in $analysis_type.countsFile_control: + cut -f 2 "${file}" > "${file}.expression_column.txt" && + #end for + #for $file in $analysis_type.countsFile_condition: + cut -f 2 "${file}" > "${file}.expression_column.txt" && + #end for + + paste + gene_ids.column.txt + #for $file in $analysis_type.countsFile_control: + "${file}.expression_column.txt" + #end for + #for $file in $analysis_type.countsFile_condition: + "${file}.expression_column.txt" + #end for + > "${expression_matrix}" && + + ## -- Create design matrix matrix + echo "sample-name Condition" >> ${design_matrix} && + #for $file in $analysis_type.countsFile_control: + echo "${file.name} ${analysis_type.factorLevel_control}" >> ${design_matrix} && + #end for + #for $file in $analysis_type.countsFile_condition: + echo "${file.name} ${analysis_type.factorLevel_condition}" >> ${design_matrix} && + #end for + #end if + R --vanilla --slave -f $R_script '--args $expression_matrix $design_matrix $contrast + $analysis_report_genes $fdr $output_count_edgeR $output_cpm - /dev/null <!-- Calculation of FPKM/RPKM should come here --> + /dev/null ### Calculation of FPKM/RPKM should come here #if $output_raw_counts: $output_raw_counts @@ -117,6 +157,7 @@ $output_format_images ' + ]]> </command> <configfiles> @@ -134,28 +175,29 @@ design_matrix_file <- args[2] contrast <- args[3] -fdr <- args[4] +truncate_table_by_fdr <- args[4] +fdr <- as.double(args[5]) -output_count_edgeR <- args[5] -output_cpm <- args[6] +output_count_edgeR <- args[6] +output_cpm <- args[7] -output_xpkm <- args[7] ##FPKM file - to be implemented +output_xpkm <- args[8] ##FPKM file - to be implemented -output_raw_counts <- args[8] +output_raw_counts <- args[9] -output_MDSplot_logFC <- args[9] -output_MDSplot_logFC_coordinates <- args[10] +output_MDSplot_logFC <- args[10] +output_MDSplot_logFC_coordinates <- args[11] -output_MDSplot_bcv <- args[11] -output_MDSplot_bcv_coordinates <- args[12] +output_MDSplot_bcv <- args[12] +output_MDSplot_bcv_coordinates <- args[13] -output_BCVplot <- args[13] -output_MAplot <- args[14] -output_PValue_distribution_plot <- args[15] -output_hierarchical_clustering_plot <- args[16] -output_heatmap_plot <- args[17] -output_RData_obj <- args[18] -output_format_images <- args[19] +output_BCVplot <- args[14] +output_MAplot <- args[15] +output_PValue_distribution_plot <- args[16] +output_hierarchical_clustering_plot <- args[17] +output_heatmap_plot <- args[18] +output_RData_obj <- args[19] +output_format_images <- args[20] ## Obtain read-counts @@ -166,15 +208,22 @@ for(i in 1:ncol(design_matrix)) { old <- design_matrix[,i] - design_matrix[,i] <- make.names(design_matrix[,i]) - if(paste(design_matrix[,i],collapse="\t") != paste(old,collapse="\t")) { - print("Renaming of factors:") - print(old) - print("To:") - print(design_matrix[,i]) + + if(any(grepl("^[0-9]+$", old, perl=TRUE) == FALSE)){ + # Convert invalid names + design_matrix[,i] <- make.names(design_matrix[,i]) + + # Print if names have been converted + if(paste(design_matrix[,i],collapse="\t") != paste(old,collapse="\t")) { + print("Renamed of factors:") + print(old) + print("To:") + print(design_matrix[,i]) + } + } else { + # Only numerical factors: these are blocking / pairing factors + design_matrix[,i] <- as.numeric(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 @@ -348,7 +397,13 @@ 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) + + if(truncate_table_by_fdr =="all") { + write.table(file=output_count_edgeR,topTags(lrt,n=nrow(read_counts))\$table,sep="\t",row.names=TRUE,col.names=NA) + } + else { + write.table(file=output_count_edgeR,subset(topTags(lrt,n=nrow(read_counts))\$table, FDR < fdr),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 @@ -458,12 +513,44 @@ </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'." /> + <conditional name="analysis_type"> + <param name="analysis_select" type="select" label="Analysis type"> + <option value="2_factor" selected="true">2-Group test</option> + <option value="multi_factor">Multigroup test and/or complex designs with e.g. blocking</option> + </param> + <when value="2_factor"> + <param name="factorLevel_control" type="text" value="Control" + label="Specify a factor level" help="Only letters, numbers and underscores will be retained in this field"> + <sanitizer> + <valid initial="string.letters,string.digits"><add value="_" /></valid> + </sanitizer> + </param> + <param name="countsFile_control" type="data" format="tabular,csv" multiple="true" label="Counts file(s)"/> + + <param name="factorLevel_condition" type="text" value="Condition" + label="Specify a factor level" help="Only letters, numbers and underscores will be retained in this field"> + <sanitizer> + <valid initial="string.letters,string.digits"><add value="_" /></valid> + </sanitizer> + </param> + <param name="countsFile_condition" type="data" format="tabular,csv" multiple="true" label="Counts file(s)"/> + </when> + <when value="multi_factor"> + <param name="expression_matrix" type="data" format="tabular,csv" label="Expression (read count) matrix" /> + <param name="design_matrix" type="data" format="tabular,csv" 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." /> + </when> + </conditional> - <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="analysis_report_genes" type="select" label="Report differentially expressed genes"> + <option value="all" selected="true">All genes</option> + <option value="significant">Only significant (defined by FDR cutoff)</option> + </param> - <param name="fdr" type="float" min="0" max="1" value="0.05" label="False Discovery Rate (FDR)" /> + <param name="fdr" type="float" min="0" max="1" value="0.01" label="False Discovery Rate (FDR) cutoff" help="Used to highlight significant genes in figures" /> <param name="outputs" type="select" label="Optional desired outputs" multiple="true" display="checkboxes"> <option value="make_output_raw_counts">Raw counts table</option> @@ -482,19 +569,23 @@ <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> + <option value="svg" selected="true">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_count_edgeR" label="edgeR DGE on ${on_string}: differentially expressed genes" > + <actions> + <action name="column_names" type="metadata" default="original_gene_position,genes,logFC,logCPM,LR,PValue,FDR" /> + </actions> + </data> + <data format="tabular" name="output_cpm" label="edgeR DGE on ${on_string}: CPM" /> - <data format="tabular" name="output_raw_counts" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - raw counts"> + <data format="tabular" name="output_raw_counts" label="edgeR DGE on ${on_string}: 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)"> + <data format="png" name="output_MDSplot_logFC" label="edgeR DGE on ${on_string}: MDS-plot (logFC method)"> <filter>outputs and ("make_output_MDSplot_logFC" in outputs)</filter> <change_format> @@ -504,11 +595,11 @@ </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)"> + <data format="tabular" name="output_MDSplot_logFC_coordinates" label="edgeR DGE on ${on_string}: 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)"> + <data format="png" name="output_MDSplot_bcv" label="edgeR DGE on ${on_string}: MDS-plot (bcv method)"> <filter>outputs and ("make_output_MDSplot_bcv" in outputs)</filter> <change_format> @@ -518,11 +609,11 @@ </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)"> + <data format="tabular" name="output_MDSplot_bcv_coordinates" label="edgeR DGE on ${on_string}: 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"> + <data format="png" name="output_BCVplot" label="edgeR DGE on ${on_string}: BCV-plot"> <filter>outputs and ("make_output_BCVplot" in outputs)</filter> <change_format> @@ -532,7 +623,7 @@ </change_format> </data> - <data format="png" name="output_MAplot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - MA-plot"> + <data format="png" name="output_MAplot" label="edgeR DGE on ${on_string}: MA-plot"> <filter>outputs and ("make_output_MAplot" in outputs)</filter> <change_format> @@ -542,7 +633,7 @@ </change_format> </data> - <data format="png" name="output_PValue_distribution_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - P-Value distribution"> + <data format="png" name="output_PValue_distribution_plot" label="edgeR DGE on ${on_string}: P-Value distribution"> <filter>outputs and ("make_output_PValue_distribution_plot" in outputs)</filter> <change_format> @@ -552,7 +643,7 @@ </change_format> </data> - <data format="png" name="output_hierarchical_clustering_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - Hierarchical custering"> + <data format="png" name="output_hierarchical_clustering_plot" label="edgeR DGE on ${on_string}: Hierarchical custering"> <filter>outputs and ("make_output_hierarchical_clustering_plot" in outputs)</filter> <change_format> @@ -562,7 +653,7 @@ </change_format> </data> - <data format="png" name="output_heatmap_plot" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - Heatmap"> + <data format="png" name="output_heatmap_plot" label="edgeR DGE on ${on_string}: Heatmap"> <filter>outputs and ("make_output_heatmap_plot" in outputs)</filter> <change_format> @@ -572,28 +663,83 @@ </change_format> </data> - <data format="RData" name="output_RData_obj" label="edgeR DGE on ${design_matrix.hid}: ${design_matrix.name} - R data object"> + <data format="RData" name="output_RData_obj" label="edgeR DGE on ${on_string}: 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)" > + <data format="txt" name="output_R" label="edgeR DGE on ${on_string}: R output (debug)" > <filter>outputs and ("make_output_R_stdout" in outputs)</filter> </data> </outputs> <tests> <test> + <param name="analysis_select" value="multi_factor" /> + + <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="analysis_report_genes" value="all"/> + <param name="fdr" value="0.01" /> + + <output name="output_count_edgeR" file="Differential_Gene_Expression/differentially_expressed_genes.tabular.txt" /> + </test> + <test> + <param name="analysis_select" value="multi_factor" /> + <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="analysis_report_genes" value="significant"/> <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.significant.tabular.txt" /> + </test> + <test> + <param name="analysis_select" value="2_factor" /> + + <param name="factorLevel_control" value="C" /> + <param name="countsFile_control" value="Differential_Gene_Expression/C1,Differential_Gene_Expression/C2,Differential_Gene_Expression/C3,Differential_Gene_Expression/C4" ftype="tabular" /> + + <param name="factorLevel_condition" value="E" /> + <param name="countsFile_condition" value="Differential_Gene_Expression/E1,Differential_Gene_Expression/E2,Differential_Gene_Expression/E3,Differential_Gene_Expression/E4" ftype="tabular" /> + + <param name="analysis_report_genes" value="all"/> + <param name="fdr" value="0.01" /> <output name="output_count_edgeR" file="Differential_Gene_Expression/differentially_expressed_genes.tabular.txt" /> </test> + <test> + <param name="analysis_select" value="2_factor" /> + + <param name="factorLevel_control" value="C" /> + <param name="countsFile_control" value="Differential_Gene_Expression/C1,Differential_Gene_Expression/C2,Differential_Gene_Expression/C3,Differential_Gene_Expression/C4" ftype="tabular" /> + + <param name="factorLevel_condition" value="E" /> + <param name="countsFile_condition" value="Differential_Gene_Expression/E1,Differential_Gene_Expression/E2,Differential_Gene_Expression/E3,Differential_Gene_Expression/E4" ftype="tabular" /> + + <param name="analysis_report_genes" value="significant"/> + <param name="fdr" value="0.05" /> + + <output name="output_count_edgeR" file="Differential_Gene_Expression/differentially_expressed_genes.significant.tabular.txt" /> + </test> + <test> + <param name="analysis_select" value="multi_factor" /> + + <param name="expression_matrix" value="Differential_Gene_Expression/expression_matrix.tabular.txt" /> + <param name="design_matrix" value="Differential_Gene_Expression/design_matrix.tabular.batch-effects.txt" /> + + <param name="contrast" value="E-C"/> + + <param name="analysis_report_genes" value="all"/> + <param name="fdr" value="0.01" /> + + <output name="output_count_edgeR" file="Differential_Gene_Expression/differentially_expressed_genes.batch-effects.tabular.txt" /> + </test> </tests> <help> @@ -661,24 +807,6 @@ - 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 & GPL 3 -- limma - - GPL (>=2) -- edgeR - - GPL (>=2) - @CONTACT@ </help>