Mercurial > repos > davidvanzessen > argalaxy_tools

changeset 54:5ba0377b7737 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Fri, 29 Jan 2016 08:10:21 -0500
parents 379856bef228
children 67627d77d63b
files complete.sh complete_immunerepertoire.xml report_clonality/RScript.r report_clonality/r_wrapper.sh report_clonality_igg.xml
diffstat 5 files changed, 9 insertions(+), 72 deletions(-) [+]
line wrap: on
line diff
--- a/complete.sh	Fri Jan 29 05:39:58 2016 -0500
+++ b/complete.sh	Fri Jan 29 08:10:21 2016 -0500
@@ -8,7 +8,6 @@
 locus=$6
 filterproductive=$7
 clonality_method=$8
-filter_uniques=$9
 
 html=$2
 dir="$(cd "$(dirname "$0")" && pwd)"
@@ -64,5 +63,5 @@
 
 echo "after ED"
 
-bash $dir/report_clonality/r_wrapper.sh $PWD/merged.txt $2 $outputDir $clonalType "$species" "$locus" $filterproductive $clonality_method $filter_uniques
+bash $dir/report_clonality/r_wrapper.sh $PWD/merged.txt $2 $outputDir $clonalType "$species" "$locus" $filterproductive $clonality_method
 
--- a/complete_immunerepertoire.xml	Fri Jan 29 05:39:58 2016 -0500
+++ b/complete_immunerepertoire.xml	Fri Jan 29 08:10:21 2016 -0500
@@ -10,9 +10,9 @@
 #end for
 " $out_file $out_file.files_path "$clonaltype"
 #if $gene_selection.source == "imgtdb"		
-	"${gene_selection.species}" "${gene_selection.locus}" $filterproductive $clonality_method $filter_uniques
+	"${gene_selection.species}" "${gene_selection.locus}" $filterproductive $clonality_method
 #else
-	"custom" "${gene_selection.vgenes};${gene_selection.dgenes};${gene_selection.jgenes}" $filterproductive $clonality_method $filter_uniques
+	"custom" "${gene_selection.vgenes};${gene_selection.dgenes};${gene_selection.jgenes}" $filterproductive $clonality_method
 #end if
 	</command>
 	<inputs>
@@ -107,11 +107,6 @@
 			<option value="old">Old</option>
 			<option value="boyd">R Package</option>
 		</param>
-		
-		<param name="filter_uniques" type="select" label="Filter unique sequences" help="Filter out the sequences (based on CDR1, FR2, CDR2, FR3 and CDR3) that only occur once.">
-			<option value="yes">Yes</option>
-			<option value="no">No</option>
-		</param>
 
 	</inputs>
 	<outputs>
--- a/report_clonality/RScript.r	Fri Jan 29 05:39:58 2016 -0500
+++ b/report_clonality/RScript.r	Fri Jan 29 08:10:21 2016 -0500
@@ -41,9 +41,7 @@
 locus = args[6] # IGH, IGK, IGL, TRB, TRA, TRG or TRD
 filterproductive = ifelse(args[7] == "yes", T, F) #should unproductive sequences be filtered out? (yes/no)
 clonality_method = args[8]
-filter_uniques = args[9]
 
-print(paste("filter_uniques", filter_uniques))
 
 # ---------------------- Data preperation ----------------------
 
@@ -64,29 +62,6 @@
 #filter uniques
 inputdata.removed = inputdata[NULL,]
 
-filter_uniques = filter_uniques == "yes" && c("CDR1.Seq", "CDR2.Seq", "CDR3.Seq", "FR1.IMGT", "FR2.IMGT", "FR3.IMGT") %in% names(inputdata)
-
-print(paste("filter_uniques", filter_uniques))
-
-if(filter_uniques){
-	
-	clmns = names(inputdata)
-	
-	inputdata$unique.def = paste(inputdata$CDR1.Seq, inputdata$CDR2.Seq, inputdata$CDR3.Seq, inputdata$FR1.IMGT, inputdata$FR2.IMGT, inputdata$FR3.IMGT)
-	inputdata.filtered = inputdata[duplicated(inputdata$unique.def),]
-	fltr = inputdata$unique.def %in% inputdata.filtered$unique.def
-	
-	inputdata.removed = inputdata[!fltr,]
-	inputdata.removed$samples_replicates = paste(inputdata.removed$Sample, inputdata.removed$Replicate, sep="_")
-	
-	inputdata = inputdata[fltr,]
-	
-	inputdata = inputdata[,clmns]
-	
-	write.table(inputdata.removed, "unique_removed.csv", sep=",",quote=F,row.names=F,col.names=T)
-}
-
-
 inputdata$clonaltype = 1:nrow(inputdata)
 
 PRODF = inputdata
@@ -183,18 +158,6 @@
 sample_productive_count$perc_unprod = round(sample_productive_count$Unproductive / sample_productive_count$All * 100)
 sample_productive_count$perc_unprod_un = round(sample_productive_count$Unproductive_unique / sample_productive_count$All * 100)
 
-
-if(filter_uniques){
-	inputdata.removed.s = data.table(inputdata.removed)[, list(UniqueRemoved=.N), by=c("Sample")]
-
-	sample_productive_count = merge(sample_productive_count, inputdata.removed.s, by="Sample")
-
-	sample_productive_count$perc_rem = round(sample_productive_count$UniqueRemoved / sample_productive_count$All * 100)
-} else {
-	sample_productive_count$UniqueRemoved = 0
-	sample_productive_count$perc_rem = 0
-}
-
 sample_replicate_productive_count = inputdata.dt[, list(All=.N, 
                                                         Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]), 
                                                         perc_prod = 1,
@@ -212,18 +175,6 @@
 sample_replicate_productive_count$perc_unprod = round(sample_replicate_productive_count$Unproductive / sample_replicate_productive_count$All * 100)
 sample_replicate_productive_count$perc_unprod_un = round(sample_replicate_productive_count$Unproductive_unique / sample_replicate_productive_count$All * 100)
 
-
-if(filter_uniques){
-	inputdata.removed.sr = data.table(inputdata.removed)[, list(UniqueRemoved=.N), by=c("samples_replicates")]
-
-	sample_replicate_productive_count = merge(sample_replicate_productive_count, inputdata.removed.sr, by="samples_replicates")
-
-	sample_replicate_productive_count$perc_rem = round(sample_replicate_productive_count$UniqueRemoved / sample_productive_count$All * 100)
-} else {
-	sample_replicate_productive_count$UniqueRemoved = 0
-	sample_replicate_productive_count$perc_rem = 0
-}
-
 setnames(sample_replicate_productive_count, colnames(sample_productive_count))
 
 counts = rbind(sample_replicate_productive_count, sample_productive_count)
--- a/report_clonality/r_wrapper.sh	Fri Jan 29 05:39:58 2016 -0500
+++ b/report_clonality/r_wrapper.sh	Fri Jan 29 08:10:21 2016 -0500
@@ -8,7 +8,7 @@
 locus=$6
 filterproductive=$7
 clonality_method=$8
-filter_uniques=$9
+
 dir="$(cd "$(dirname "$0")" && pwd)"
 useD="false"
 if grep -q "$species.*${locus}D" "$dir/genes.txt" ; then
@@ -26,7 +26,7 @@
 fi
 mkdir $3
 cp $dir/genes.txt $outputDir
-Rscript --verbose $dir/RScript.r $inputFile $outputDir $outputDir $clonalType "$species" "$locus" $filterproductive ${clonality_method} ${filter_uniques} 2>&1
+Rscript --verbose $dir/RScript.r $inputFile $outputDir $outputDir $clonalType "$species" "$locus" $filterproductive ${clonality_method} 2>&1
 cp $dir/tabber.js $outputDir
 cp $dir/style.css $outputDir
 cp $dir/script.js $outputDir
@@ -35,13 +35,10 @@
 
 echo "<html><center><h1><a href='index.html'>Click here for the results</a></h1>Tip: Open it in a new tab (middle mouse button or right mouse button -> 'open in new tab' on the link above)<br />" > $2
 echo "<table border = 1>" >> $2
-echo "<thead><tr><th>Sample/Replicate</th><th>Input</th><th>Removed</th><th>All</th><th>Productive</th><th>Unique Productive</th><th>Unproductive</th><th>Unique Unproductive</th></tr></thead>" >> $2
-while IFS=, read sample all productive perc_prod productive_unique perc_prod_un unproductive perc_unprod unproductive_unique perc_unprod_un removed perc_rem
+echo "<thead><tr><th>Sample/Replicate</th><th>All</th><th>Productive</th><th>Unique Productive</th><th>Unproductive</th><th>Unique Unproductive</th></tr></thead>" >> $2
+while IFS=, read sample all productive perc_prod productive_unique perc_prod_un unproductive perc_unprod unproductive_unique perc_unprod_un
 	do
 		echo "<tr><td>$sample</td>" >> $2
-		
-		echo "<td>$((all+removed))</td>" >> $2
-		echo "<td>${removed} (${perc_rem}%)</td>" >> $2
 		echo "<td>$all</td>" >> $2
 		echo "<td>$productive (${perc_prod}%)</td>" >> $2
 		echo "<td>$productive_unique (${perc_prod_un}%)</td>" >> $2
--- a/report_clonality_igg.xml	Fri Jan 29 05:39:58 2016 -0500
+++ b/report_clonality_igg.xml	Fri Jan 29 08:10:21 2016 -0500
@@ -2,9 +2,9 @@
 	<description> </description>
 	<command interpreter="bash">
 #if $gene_selection.source == "imgtdb"		
-	report_clonality/r_wrapper.sh $in_file $out_file $out_file.files_path "$clonaltype" "${gene_selection.species}" "${gene_selection.locus}" $filterproductive $clonality_method $filter_uniques
+	report_clonality/r_wrapper.sh $in_file $out_file $out_file.files_path "$clonaltype" "${gene_selection.species}" "${gene_selection.locus}" $filterproductive $clonality_method
 #else
-	report_clonality/r_wrapper.sh $in_file $out_file $out_file.files_path "$clonaltype" "custom" "${gene_selection.vgenes};${gene_selection.dgenes};${gene_selection.jgenes}" $filterproductive $clonality_method $filter_uniques
+	report_clonality/r_wrapper.sh $in_file $out_file $out_file.files_path "$clonaltype" "custom" "${gene_selection.vgenes};${gene_selection.dgenes};${gene_selection.jgenes}" $filterproductive $clonality_method
 #end if
 	</command>
 	<inputs>
@@ -95,11 +95,6 @@
 			<option value="boyd">R Package</option>
 		</param>
 		
-		<param name="filter_uniques" type="select" label="Filter unique sequences" help="Filter out the sequences (based on CDR1, FR2, CDR2, FR3 and CDR3) that only occur once.">
-			<option value="yes">Yes</option>
-			<option value="no">No</option>
-		</param>
-		
 	</inputs>
 	<outputs>
 		<data format="html" name="out_file" />