| Previous changeset 5:17befe9f8b03 (2014-02-24) Next changeset 7:91e411fcdecc (2014-04-23) |
|
Commit message:
- Added differentially expressed hairpin count output - Added running time output - Added counts table output |
|
modified:
hairpinTool.R hairpinTool.xml |
| b |
| diff -r 17befe9f8b03 -r 3d04308a99f9 hairpinTool.R --- a/hairpinTool.R Mon Feb 24 14:50:08 2014 +1100 +++ b/hairpinTool.R Fri Apr 11 17:17:15 2014 +1000 |
| [ |
| b'@@ -1,3 +1,51 @@\n+# ARGS: 1.inputType -String specifying format of input (fastq or table)\n+# IF inputType is "fastQ":\n+# 2*.fastqPath -One or more strings specifying path to fastq files\n+# 2.annoPath -String specifying path to hairpin annotation table\n+# 3.samplePath -String specifying path to sample annotation table\n+# 4.barStart -Integer specifying starting position of barcode\n+# 5.barEnd -Integer specifying ending position of barcode\n+# 6.hpStart -Integer specifying startins position of hairpin\n+# unique region\n+# 7.hpEnd -Integer specifying ending position of hairpin\n+# unique region\n+# ### \n+# IF inputType is "counts":\n+# 2.countPath -String specifying path to count table\n+# 3.annoPath -String specifying path to hairpin annotation table\n+# 4.samplePath -String specifying path to sample annotation table\n+# ###\n+# 8.cpmReq -Float specifying cpm requirement\n+# 9.sampleReq -Integer specifying cpm requirement\n+# 10.fdrThresh -Float specifying the FDR requirement\n+# 11.lfcThresh -Float specifying the log-fold-change requirement\n+# 12.workMode -String specifying exact test or GLM usage\n+# 13.htmlPath -String specifying path to HTML file\n+# 14.folderPath -STring specifying path to folder for output\n+# IF workMode is "classic" (exact test)\n+# 15.pairData[2] -String specifying first group for exact test\n+# 16.pairData[1] -String specifying second group for exact test\n+# ###\n+# IF workMode is "glm"\n+# 15.contrastData -String specifying contrasts to be made\n+# 16.roastOpt -String specifying usage of gene-wise tests\n+# 17.hairpinReq -String specifying hairpin requirement for gene-\n+# wise test\n+# 18.selectOpt -String specifying type of selection for barcode\n+# plots\n+# 19.selectVals -String specifying members selected for barcode\n+# plots\n+#\n+# OUT: Bar Plot of Counts Per Index\n+# Bar Plot of Counts Per Hairpin\n+# MDS Plot\n+# Smear Plot\n+# Barcode Plots (If Genewise testing was selected)\n+# Top Expression Table\n+# HTML file linking to the ouputs\n+#\n+# Author: Shian Su - registertonysu@gmail.com - Jan 2014\n+\n # Record starting time\n timeStart <- as.character(Sys.time())\n \n@@ -115,7 +163,7 @@\n fastqPath <- as.character(gsub("fastq::", "", argv[grepl("fastq::", argv)], \n fixed=TRUE))\n argv <- argv[!grepl("fastq::", argv, fixed=TRUE)]\n- hairpinPath <- as.character(argv[2])\n+ annoPath <- as.character(argv[2])\n samplePath <- as.character(argv[3])\n barStart <- as.numeric(argv[4])\n barEnd <- as.numeric(argv[5])\n@@ -134,6 +182,7 @@\n workMode <- as.character(argv[12])\n htmlPath <- as.character(argv[13])\n folderPath <- as.character(argv[14])\n+\n if (workMode=="classic") {\n pairData <- character()\n pairData[2] <- as.character(argv[15])\n@@ -147,14 +196,13 @@\n }\n \n # Read in inputs\n-if (inputType=="fastq") {\n- samples <- read.table(samplePath, header=TRUE, sep="\\t")\n- hairpins <- read.table(hairpinPath, header=TRUE, sep="\\t")\n-} else if (inputType=="counts") {\n- samples <- read.table(samplePath, header=TRUE, sep="\\t")\n+\n+samples <- read.table(samplePath, header=TRUE, sep="\\t")\n+anno <- read.table(annoPath, header=TRUE, sep="\\t")\n+if (inputType=="counts") {\n counts <- read.table(countPath, header=TRUE, sep="\\t")\n- anno <- read.table(annoPath, header=TRUE, sep="\\t")\n }\n+\n ###################### Check inputs for correctness ############################\n samples$ID <- make.names(samples$ID)\n \n@@ -166,16 +214,16 @@\n tab <- table(samples$ID)\n offenders <- paste(names(tab[tab>1'..b'[3], "<br/>\\n")\n+ cata(hpReadout[3], "<br />\\n")\n cata("<ul>\\n")\n ListItem(hpReadout[4])\n ListItem(hpReadout[7])\n cata("</ul>\\n")\n- cata(hpReadout[8:11], sep="<br/>\\n")\n+ cata(hpReadout[8:11], sep="<br />\\n")\n cata("<br />\\n")\n cata("<b>Please check that read percentages are consistent with ")\n cata("expectations.</b><br >\\n")\n@@ -582,7 +653,7 @@\n \n cata("<h4>Output:</h4>\\n")\n cata("All images displayed have PDF copy at the bottom of the page, these can ")\n-cata("exported in a pdf viewer to high resolution image format. <br/>\\n")\n+cata("exported in a pdf viewer to high resolution image format. <br />\\n")\n for (i in 1:nrow(imageData)) {\n if (grepl("barcode", imageData$Link[i])) {\n if (packageVersion("limma")<"3.19.19") {\n@@ -596,7 +667,7 @@\n HtmlImage(imageData$Link[i], imageData$Label[i])\n }\n }\n-cata("<br/>\\n")\n+cata("<br />\\n")\n \n cata("<h4>Plots:</h4>\\n")\n for (i in 1:nrow(linkData)) {\n@@ -617,14 +688,80 @@\n cata("disk icon to download all files in a zip archive.</p>\\n")\n cata("<p>.tsv files are tab seperated files that can be viewed using Excel ")\n cata("or other spreadsheet programs</p>\\n")\n+\n+cata("<h4>Additional Information:</h4>\\n")\n+\n+if (inputType == "fastq") {\n+ ListItem("Data was gathered from fastq raw read file(s).")\n+} else if (inputType == "counts") {\n+ ListItem("Data was gathered from a table of counts.")\n+}\n+\n+if (cpmReq!=0 && sampleReq!=0) {\n+ tempStr <- paste("Hairpins that do not have more than", cpmReq,\n+ "CPM in at least", sampleReq, "samples are considered",\n+ "insignificant and filtered out.")\n+ ListItem(tempStr)\n+ filterProp <- round(filteredCount/preFilterCount*100, digits=2)\n+ tempStr <- paste0(filteredCount, " of ", preFilterCount," (", filterProp,\n+ "%) hairpins were filtered out for low count-per-million.")\n+ ListItem(tempStr)\n+}\n+\n+if (workMode == "classic") {\n+ ListItem("An exact test was performed on each hairpin.")\n+} else if (workMode == "glm") {\n+ ListItem("A generalised linear model was fitted to each hairpin.")\n+}\n+\n+\n+\n+cit <- character()\n+link <-character()\n+link[1] <- paste0("<a href=\\"",\n+ "http://www.bioconductor.org/packages/release/bioc/",\n+ "vignettes/limma/inst/doc/usersguide.pdf",\n+ "\\">", "limma User\'s Guide", "</a>.")\n+link[2] <- paste0("<a href=\\"",\n+ "http://www.bioconductor.org/packages/release/bioc/",\n+ "vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf",\n+ "\\">", "edgeR User\'s Guide", "</a>")\n+ \n+cit[1] <- paste("Robinson MD, McCarthy DJ and Smyth GK (2010).",\n+ "edgeR: a Bioconductor package for differential",\n+ "expression analysis of digital gene expression",\n+ "data. Bioinformatics 26, 139-140")\n+cit[2] <- paste("Robinson MD and Smyth GK (2007). Moderated statistical tests",\n+ "for assessing differences in tag abundance. Bioinformatics",\n+ "23, 2881-2887")\n+cit[3] <- paste("Robinson MD and Smyth GK (2008). Small-sample estimation of",\n+ "negative binomial dispersion, with applications to SAGE data.",\n+ "Biostatistics, 9, 321-332")\n+\n+cit[4] <- paste("McCarthy DJ, Chen Y and Smyth GK (2012). Differential",\n+ "expression analysis of multifactor RNA-Seq experiments with",\n+ "respect to biological variation. Nucleic Acids Research 40,",\n+ "4288-4297")\n+\n+cata("<h4>Citations</h4>")\n+cata("<ol>\\n")\n+ListItem(cit[1])\n+ListItem(cit[2])\n+ListItem(cit[3])\n+ListItem(cit[4])\n+cata("</ol>\\n")\n+\n cata("<table border=\\"0\\">\\n")\n-\n cata("<tr>\\n")\n TableItem("Task started at:"); TableItem(timeStart)\n cata("</tr>\\n")\n cata("<tr>\\n")\n TableItem("Task ended at:"); TableItem(timeEnd)\n cata("</tr>\\n")\n+cata("<tr>\\n")\n+TableItem("Task run time:"); TableItem(timeTaken)\n+cata("<tr>\\n")\n+cata("</table>\\n")\n \n cata("</body>\\n")\n cata("</html>")\n' |
| b |
| diff -r 17befe9f8b03 -r 3d04308a99f9 hairpinTool.xml --- a/hairpinTool.xml Mon Feb 24 14:50:08 2014 +1100 +++ b/hairpinTool.xml Fri Apr 11 17:17:15 2014 +1000 |
| b |
| @@ -1,11 +1,11 @@ -<tool id="shRNAseq" name="shRNAseq Tool" version="1.0.5"> +<tool id="shRNAseq" name="shRNAseq Tool" version="1.0.7"> <description> Analyse hairpin differential representation using edgeR </description> <requirements> - <requirement type="R-module">edgeR</requirement> - <requirement type="R-module">limma</requirement> + <requirement type="R-module" version="3.5.27">edgeR</requirement> + <requirement type="R-module" version="3.18.13">limma</requirement> </requirements> <stdio> @@ -13,8 +13,8 @@ </stdio> <command interpreter="Rscript"> - hairpinTool.R $inputOpt.type - #if $inputOpt.type=="fastq": + hairpinTool.R $inputOpt.inputType + #if $inputOpt.inputType=="fastq": #for $i, $fas in enumerate($inputOpt.fastq): fastq::$fas.file #end for @@ -22,7 +22,7 @@ $inputOpt.hairpin $inputOpt.samples - #if $inputOpt.positions.option=="yes": + #if $inputOpt.positions.posOption=="yes": $inputOpt.positions.barstart $inputOpt.positions.barend $inputOpt.positions.hpstart @@ -35,12 +35,12 @@ #end if #else: $inputOpt.counts - $inputOpt.anno - "$inputOpt.factors" + $inputOpt.hairpin + $inputOpt.samples 0 0 0 #end if - #if $filterCPM.option=="yes": + #if $filterCPM.filtOption=="yes": $filterCPM.cpmReq $filterCPM.sampleReq #else: @@ -57,12 +57,12 @@ #if $workMode.mode=="classic": "$workMode.pair1" "$workMode.pair2" - #else: + #elif $workMode.mode=="glm": "$workMode.contrast" - $workMode.roast.option - #if $workMode.roast.option=="yes": + $workMode.roast.roastOption + #if $workMode.roast.roastOption=="yes": $workMode.roast.hairpinReq - $workMode.roast.select.option + $workMode.roast.select.selOption "$workMode.roast.select.selection" #else: 0 @@ -74,7 +74,7 @@ <inputs> <conditional name="inputOpt"> - <param name="type" type="select" label="Input File Type"> + <param name="inputType" type="select" label="Input File Type"> <option value="fastq">FastQ File</option> <option value="counts">Table of Counts</option> </param> @@ -92,7 +92,7 @@ </repeat> <conditional name="positions"> - <param name="option" type="select" + <param name="posOption" type="select" label="Specify Barcode and Hairpin Locations?" help="Default Positions: Barcode: 1 to 5, Hairpin: 37 to 57."> <option value="no" selected="True">No</option> @@ -118,15 +118,15 @@ <when value="counts"> <param name="counts" type="data" format="tabular" label="Counts Table"/> - <param name="anno" type="data" format="tabular" + <param name="hairpin" type="data" format="tabular" label="Hairpin Annotation"/> - <param name="factors" type="data" format="tabular" + <param name="samples" type="data" format="tabular" label="Sample Annotation"/> </when> </conditional> <conditional name="filterCPM"> - <param name="option" type="select" label="Filter Low CPM?" + <param name="filtOption" type="select" label="Filter Low CPM?" help="Ignore hairpins with very low representation when performing analysis."> <option value="yes">Yes</option> @@ -172,7 +172,7 @@ expression."/> <conditional name="roast"> - <param name="option" type="select" + <param name="roastOption" type="select" label="Perform Gene Level Analysis?" help="Analyse LogFC tendencies for hairpins belonging to the same gene."> @@ -187,7 +187,7 @@ be analysed."/> <conditional name="select"> - <param name="option" type="select" + <param name="selOption" type="select" label="Gene Selection Method"> <option value="rank">By p-value Rank</option> <option value="geneID">By Gene Identifier</option> @@ -232,7 +232,6 @@ <outputs> <data format="html" name="outFile" label="shRNAseq Analysis"/> </outputs> - <help> .. class:: infomark |