# HG changeset patch
# User davidvanzessen
# Date 1481117783 18000
# Node ID beaa487ecf43b184ea56eb973266c7f7caa4653e
# Parent  4f8a1d121384b72341545dc1dbca46a67a3957b3
Uploaded

diff -r 4f8a1d121384 -r beaa487ecf43 complete_immunerepertoire.xml
--- a/complete_immunerepertoire.xml	Mon Sep 05 11:15:22 2016 -0400
+++ b/complete_immunerepertoire.xml	Wed Dec 07 08:36:23 2016 -0500
@@ -24,11 +24,11 @@
 		</repeat>
 		<param name="clonaltype" type="select" label="Clonal Type Definition">
 			<option value="none">Don't remove duplicates based on clonaltype</option>
-			<option value="Top.V.Gene,CDR3.Seq">Top.V.Gene, CDR3.Seq</option>
-			<option value="Top.V.Gene,CDR3.Seq.DNA">Top.V.Gene, CDR3.Seq.DNA</option>
-			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq">Top.V.Gene, Top.J.Gene, CDR3.Seq</option>
-			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.J.Gene, CDR3.Seq.DNA</option>
-			<option value="Top.V.Gene,Top.D.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.D.Gene, Top.J.Gene, CDR3.Seq.DNA</option>
+			<option value="Top.V.Gene,CDR3.Seq">Top.V.Gene, CDR3 (AA)</option>
+			<option value="Top.V.Gene,CDR3.Seq.DNA">Top.V.Gene, CDR3 (nt)</option>
+			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq">Top.V.Gene, Top.J.Gene, CDR3 (AA)</option>
+			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.J.Gene, CDR3 (nt)</option>
+			<option value="Top.V.Gene,Top.D.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.D.Gene, Top.J.Gene, CDR3 (nt)</option>
 		</param>
 		
 		<conditional name="gene_selection" >
diff -r 4f8a1d121384 -r beaa487ecf43 report_clonality/RScript.r
--- a/report_clonality/RScript.r	Mon Sep 05 11:15:22 2016 -0400
+++ b/report_clonality/RScript.r	Wed Dec 07 08:36:23 2016 -0500
@@ -10,7 +10,7 @@
 library(ggplot2)
 if (!("plyr" %in% rownames(installed.packages()))) {
   install.packages("plyr", repos="http://cran.xl-mirror.nl/") 
-}			
+}
 library(plyr)
 
 if (!("data.table" %in% rownames(installed.packages()))) {
@@ -717,7 +717,8 @@
                                                DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
                                                Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
-                                               Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T))),
+                                               Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
+                                               Median.CDR3.l=median(.SD$CDR3.Length.DNA)),
                                          by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisProd_mean.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
@@ -735,7 +736,8 @@
                                                DEL.JH=num_median(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
 											   Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
 											   Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
-											   Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T))),
+											   Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
+											   Median.CDR3.l=median(.SD$CDR3.Length.DNA)),
                                          by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisProd_median.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
@@ -753,7 +755,8 @@
                                                 DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
                                                 Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                 Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
-                                                Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T))),
+                                                Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
+                                                Median.CDR3.l=median(.SD$CDR3.Length.DNA)),
                                           by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisUnProd_mean.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
@@ -771,7 +774,8 @@
                                                 DEL.JH=num_median(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
                                                 Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                 Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
-                                                Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T))),
+                                                Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
+                                                Median.CDR3.l=median(.SD$CDR3.Length.DNA)),
 															by=c("Sample")])
 															
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
diff -r 4f8a1d121384 -r beaa487ecf43 report_clonality/r_wrapper.sh
--- a/report_clonality/r_wrapper.sh	Mon Sep 05 11:15:22 2016 -0400
+++ b/report_clonality/r_wrapper.sh	Wed Dec 07 08:36:23 2016 -0500
@@ -219,31 +219,31 @@
 #if [[ "$hasJunctionData" == "Yes" ]] ; then
 if [ -a "$outputDir/junctionAnalysisProd_mean.csv" ] ; then
 	echo "<div class='tabbertab' title='Junction Analysis'>" >> $outputFile
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><thead></tr><tbody>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
-		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td></tr>" >> $outputFile
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisProd_mean.csv
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><thead></tr><tbody>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
-		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td></tr>" >> $outputFile
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisUnProd_mean.csv
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><thead></tr><tbody>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
-		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td></tr>" >> $outputFile
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisProd_median.csv
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><thead></tr><tbody>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
-		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td></tr>" >> $outputFile
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisUnProd_median.csv
 	echo "</tbody></table>" >> $outputFile
 	
diff -r 4f8a1d121384 -r beaa487ecf43 report_clonality_igg.xml
--- a/report_clonality_igg.xml	Mon Sep 05 11:15:22 2016 -0400
+++ b/report_clonality_igg.xml	Wed Dec 07 08:36:23 2016 -0500
@@ -11,12 +11,12 @@
 		<param name="in_file" format="tabular" type="data" label="Data to Process" />
 		<param name="clonaltype" type="select" label="Clonal Type Definition (Needed for clonality calculation)">
 			<option value="none">Don't remove duplicates based on clonaltype</option>
-			<option value="Top.V.Gene,CDR3.Seq">Top.V.Gene, CDR3.AA.Seq</option>
-			<option value="Top.V.Gene,CDR3.Seq.DNA">Top.V.Gene, CDR3.Seq.DNA</option>
-			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq">Top.V.Gene, Top.J.Gene, CDR3.AA.Seq</option>
-			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.J.Gene, CDR3.Seq.DNA</option>
-			<option value="Top.V.Gene,Top.D.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.D.Gene, Top.J.Gene, CDR3.Seq.DNA</option>
-			<option value="Top.V.Gene,Top.D.Gene,Top.J.Gene,CDR3.Seq">Top.V.Gene, Top.D.Gene, Top.J.Gene, CDR3.AA.DNA</option>
+			<option value="Top.V.Gene,CDR3.Seq">Top.V.Gene, CDR3 (AA)</option>
+			<option value="Top.V.Gene,CDR3.Seq.DNA">Top.V.Gene, CDR3 (nt)</option>
+			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq">Top.V.Gene, Top.J.Gene, CDR3 (AA)</option>
+			<option value="Top.V.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.J.Gene, CDR3 (nt)</option>
+			<option value="Top.V.Gene,Top.D.Gene,Top.J.Gene,CDR3.Seq.DNA">Top.V.Gene, Top.D.Gene, Top.J.Gene, CDR3 (nt)</option>
+			<option value="Top.V.Gene,Top.D.Gene,Top.J.Gene,CDR3.Seq">Top.V.Gene, Top.D.Gene, Top.J.Gene, CDR3 (AA)</option>
 		</param>
 		
 		<conditional name="gene_selection" >