comparison edgeR_Differential_Gene_Expression.xml @ 120:5c94a732bd62 draft

planemo upload for repository https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools/raw/master/edger_with_design_matrix commit 608485ef08f6221f3247dafe3f8b0ab451871795

119:0a05f6a91d71

        R --vanilla --slave -f $R_script '--args
            $expression_matrix
            $design_matrix
            $contrast
            
            $fdr
            
            $output_count_edgeR 
            $output_cpm
            

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(""))

  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)
  

                <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="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>

            <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" />
            
            <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="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="fdr" value="0.05" />
            
            <output name="output_count_edgeR" file="Differential_Gene_Expression/differentially_expressed_genes.tabular.txt" />
        </test>
    </tests>
    
    <help>
edgeR: Differential Gene(Expression) Analysis

120:5c94a732bd62

        R --vanilla --slave -f $R_script '--args
            $expression_matrix
            $design_matrix
            $contrast
            
            $analysis_report_genes
            $fdr
            
            $output_count_edgeR 
            $output_cpm
            

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

truncate_table_by_fdr               <- args[4]
fdr                                 <- as.double(args[5])

output_count_edgeR                  <- args[6]
output_cpm                          <- args[7]

output_xpkm                         <- args[8]        ##FPKM file - to be implemented

output_raw_counts                   <- args[9]

output_MDSplot_logFC                <- args[10]
output_MDSplot_logFC_coordinates    <- args[11]

output_MDSplot_bcv                  <- args[12]
output_MDSplot_bcv_coordinates      <- args[13]

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
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(""))

  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())
  
  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
  write.table(file=output_raw_counts,dge\$counts,sep="\t",row.names=TRUE,col.names=NA)
  

                <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="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="0.01" 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>
            <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>

            <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" />
            
            <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="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>
    </tests>
    
    <help>
edgeR: Differential Gene(Expression) Analysis