# HG changeset patch
# User davidvanzessen
# Date 1422000403 18000
# Node ID 5454af6fece10824a012f29f6576c6ede9665371
# Parent  5f0597a3fd8b7c4f07e9d01fe9e709ed10dbef2f
Uploaded

diff -r 5f0597a3fd8b -r 5454af6fece1 RScript.r
--- a/RScript.r	Fri Jan 16 07:37:41 2015 -0500
+++ b/RScript.r	Fri Jan 23 03:06:43 2015 -0500
@@ -584,3 +584,42 @@
                                           by=c("Sample")])
   write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
 }
+
+# ---------------------- AA composition in CDR3 ----------------------
+
+AACDR3 = PRODF[,c("Sample", "CDR3.Seq")]
+
+TotalPerSample = data.frame(data.table(AACDR3)[, list(total=sum(nchar(as.character(.SD$CDR3.Seq)))), by=Sample])
+
+AAfreq = list()
+
+for(i in 1:nrow(TotalPerSample)){
+	sample = TotalPerSample$Sample[i]
+  AAfreq[[i]] = data.frame(table(unlist(strsplit(as.character(AACDR3[AACDR3$Sample == sample,c("CDR3.Seq")]), ""))))
+  AAfreq[[i]]$Sample = sample
+}
+
+AAfreq = ldply(AAfreq, data.frame)
+AAfreq = merge(AAfreq, TotalPerSample, by="Sample", all.x = T)
+AAfreq$freq_perc = as.numeric(AAfreq$Freq / AAfreq$total * 100)
+
+
+AAorder = read.table(sep="\t", header=TRUE, text="order.aa\tAA\n1\tR\n2\tK\n3\tN\n4\tD\n5\tQ\n6\tE\n7\tH\n8\tP\n9\tY\n10\tW\n11\tS\n12\tT\n13\tG\n14\tA\n15\tM\n16\tC\n17\tF\n18\tL\n19\tV\n20\tI")
+AAfreq = merge(AAfreq, AAorder, by.x='Var1', by.y='AA', all.x=TRUE)
+
+AAfreq = AAfreq[!is.na(AAfreq$order.aa),]
+
+AAfreqplot = ggplot(AAfreq)
+AAfreqplot = AAfreqplot + geom_bar(aes( x=factor(reorder(Var1, order.aa)), y = freq_perc, fill = Sample), stat='identity', position='dodge' )
+AAfreqplot = AAfreqplot + annotate("rect", xmin = 0.5, xmax = 2.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
+AAfreqplot = AAfreqplot + annotate("rect", xmin = 3.5, xmax = 4.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
+AAfreqplot = AAfreqplot + annotate("rect", xmin = 5.5, xmax = 6.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
+AAfreqplot = AAfreqplot + annotate("rect", xmin = 6.5, xmax = 7.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
+AAfreqplot = AAfreqplot + ggtitle("Amino Acid Composition in the CDR3") + xlab("Amino Acid, from Hydrophilic (left) to Hydrophobic (right)") + ylab("Percentage")
+
+png("AAComposition.png",width = 1280, height = 720)
+AAfreqplot
+dev.off()
+write.table(AAfreq, "AAComposition.csv" , sep=",",quote=F,na="-",row.names=F,col.names=T)
+
+
diff -r 5f0597a3fd8b -r 5454af6fece1 r_wrapper.sh
--- a/r_wrapper.sh	Fri Jan 16 07:37:41 2015 -0500
+++ b/r_wrapper.sh	Fri Jan 23 03:06:43 2015 -0500
@@ -65,7 +65,8 @@
 if [[ "$useD" == "true" ]] ; then
 	echo "<img src='DPlot.png'/>" >> $outputFile
 fi
-echo "<img src='JPlot.png'/></div>" >> $outputFile
+echo "<img src='JPlot.png'/>" >> $outputFile
+echo "<img src='AAComposition.png'/></div>" >> $outputFile
 
 count=1
 echo "<div class='tabbertab' title='Heatmaps'><div class='tabber'>" >> $outputFile
@@ -170,6 +171,7 @@
 	echo "<tr><td>The dataset used to generate the D gene frequency graph</td><td><a href='DFrequency.csv'>Download</a></td></tr>" >> $outputFile
 fi
 echo "<tr><td>The dataset used to generate the J gene frequency graph</td><td><a href='JFrequency.csv'>Download</a></td></tr>" >> $outputFile
+echo "<tr><td>The dataset used to generate the AA composition graph</td><td><a href='AAComposition.csv'>Download</a></td></tr>" >> $outputFile
 
 for sample in $samples; do
 	if [[ "$useD" == "true" ]] ; then
diff -r 5f0597a3fd8b -r 5454af6fece1 report_clonality_igg.xml
--- a/report_clonality_igg.xml	Fri Jan 16 07:37:41 2015 -0500
+++ b/report_clonality_igg.xml	Fri Jan 23 03:06:43 2015 -0500
@@ -107,56 +107,76 @@
 
 IGH::
 
-    V:IGHV3-74,IGHV3-73,IGHV3-72,IGHV2-70,IGHV1-69D,IGHV1-69-2,IGHV2-70D,IGHV1-69,IGHV3-66,IGHV3-64,IGHV4-61,IGHV4-59,IGHV1-58,IGHV3-53,IGHV5-51,IGHV3-49,IGHV3-48,IGHV1-46,IGHV1-45,IGHV3-43,IGHV4-39,IGHV3-43D,IGHV4-38-2,IGHV4-34,IGHV3-33,IGHV4-31,IGHV3-30-5,IGHV4-30-4,IGHV3-30-3,IGHV4-30-2,IGHV4-30-1,IGHV3-30,IGHV4-28,IGHV2-26,IGHV1-24,IGHV3-23D,IGHV3-23,IGHV3-21,IGHV3-20,IGHV1-18,IGHV3-15,IGHV3-13,IGHV3-11,IGHV5-10-1,IGHV3-9,IGHV1-8,IGHV3-64D,IGHV3-7,IGHV2-5,IGHV7-4-1,IGHV4-4,IGHV1-3,IGHV1-2,IGHV6-1
-    D:IGHD1-1,IGHD2-2,IGHD3-3,IGHD4-4,IGHD5-5,IGHD6-6,IGHD1-7,IGHD2-8,IGHD3-9,IGHD3-10,IGHD5-12,IGHD6-13,IGHD2-15,IGHD3-16,IGHD4-17,IGHD5-18,IGHD6-19,IGHD1-20,IGHD2-21,IGHD3-22,IGHD5-24,IGHD6-25,IGHD1-26,IGHD7-27
-    J:IGHJ1,IGHJ2,IGHJ3,IGHJ4,IGHJ5,IGHJ6
+    V:
+    IGHV3-74,IGHV3-73,IGHV3-72,IGHV2-70,IGHV1-69D,IGHV1-69-2,IGHV2-70D,IGHV1-69,IGHV3-66,IGHV3-64,IGHV4-61,IGHV4-59,IGHV1-58,IGHV3-53,IGHV5-51,IGHV3-49,IGHV3-48,IGHV1-46,IGHV1-45,IGHV3-43,IGHV4-39,IGHV3-43D,IGHV4-38-2,IGHV4-34,IGHV3-33,IGHV4-31,IGHV3-30-5,IGHV4-30-4,IGHV3-30-3,IGHV4-30-2,IGHV4-30-1,IGHV3-30,IGHV4-28,IGHV2-26,IGHV1-24,IGHV3-23D,IGHV3-23,IGHV3-21,IGHV3-20,IGHV1-18,IGHV3-15,IGHV3-13,IGHV3-11,IGHV5-10-1,IGHV3-9,IGHV1-8,IGHV3-64D,IGHV3-7,IGHV2-5,IGHV7-4-1,IGHV4-4,IGHV1-3,IGHV1-2,IGHV6-1
+    D:
+    IGHD1-1,IGHD2-2,IGHD3-3,IGHD4-4,IGHD5-5,IGHD6-6,IGHD1-7,IGHD2-8,IGHD3-9,IGHD3-10,IGHD5-12,IGHD6-13,IGHD2-15,IGHD3-16,IGHD4-17,IGHD5-18,IGHD6-19,IGHD1-20,IGHD2-21,IGHD3-22,IGHD5-24,IGHD6-25,IGHD1-26,IGHD7-27
+    J:
+    IGHJ1,IGHJ2,IGHJ3,IGHJ4,IGHJ5,IGHJ6
 
 
 IGK::
 
-    V:IGKV3D-7,IGKV1D-8,IGKV1D-43,IGKV3D-11,IGKV1D-12,IGKV1D-13,IGKV3D-15,IGKV1D-16,IGKV1D-17,IGKV3D-20,IGKV2D-26,IGKV2D-28,IGKV2D-29,IGKV2D-30,IGKV1D-33,IGKV1D-39,IGKV2D-40,IGKV2-40,IGKV1-39,IGKV1-33,IGKV2-30,IGKV2-29,IGKV2-28,IGKV1-27,IGKV2-24,IGKV3-20,IGKV1-17,IGKV1-16,IGKV3-15,IGKV1-13,IGKV1-12,IGKV3-11,IGKV1-9,IGKV1-8,IGKV1-6,IGKV1-5,IGKV5-2,IGKV4-1
-    J:IGKJ1,IGKJ2,IGKJ3,IGKJ4,IGKJ5
+    V:
+    IGKV3D-7,IGKV1D-8,IGKV1D-43,IGKV3D-11,IGKV1D-12,IGKV1D-13,IGKV3D-15,IGKV1D-16,IGKV1D-17,IGKV3D-20,IGKV2D-26,IGKV2D-28,IGKV2D-29,IGKV2D-30,IGKV1D-33,IGKV1D-39,IGKV2D-40,IGKV2-40,IGKV1-39,IGKV1-33,IGKV2-30,IGKV2-29,IGKV2-28,IGKV1-27,IGKV2-24,IGKV3-20,IGKV1-17,IGKV1-16,IGKV3-15,IGKV1-13,IGKV1-12,IGKV3-11,IGKV1-9,IGKV1-8,IGKV1-6,IGKV1-5,IGKV5-2,IGKV4-1
+    J:
+    IGKJ1,IGKJ2,IGKJ3,IGKJ4,IGKJ5
 
 
 IGL::
 
-    V:IGLV4-69,IGLV8-61,IGLV4-60,IGLV6-57,IGLV5-52,IGLV1-51,IGLV9-49,IGLV1-47,IGLV7-46,IGLV5-45,IGLV1-44,IGLV7-43,IGLV1-41,IGLV1-40,IGLV5-39,IGLV5-37,IGLV1-36,IGLV3-27,IGLV3-25,IGLV2-23,IGLV3-22,IGLV3-21,IGLV3-19,IGLV2-18,IGLV3-16,IGLV2-14,IGLV3-12,IGLV2-11,IGLV3-10,IGLV3-9,IGLV2-8,IGLV4-3,IGLV3-1
-    J:IGLJ1,IGLJ2,IGLJ3,IGLJ6,IGLJ7
+    V:
+    IGLV4-69,IGLV8-61,IGLV4-60,IGLV6-57,IGLV5-52,IGLV1-51,IGLV9-49,IGLV1-47,IGLV7-46,IGLV5-45,IGLV1-44,IGLV7-43,IGLV1-41,IGLV1-40,IGLV5-39,IGLV5-37,IGLV1-36,IGLV3-27,IGLV3-25,IGLV2-23,IGLV3-22,IGLV3-21,IGLV3-19,IGLV2-18,IGLV3-16,IGLV2-14,IGLV3-12,IGLV2-11,IGLV3-10,IGLV3-9,IGLV2-8,IGLV4-3,IGLV3-1
+    J:
+    IGLJ1,IGLJ2,IGLJ3,IGLJ6,IGLJ7
 
 
 TRB::
 
-    V:TRBV2,TRBV3-1,TRBV4-1,TRBV5-1,TRBV6-1,TRBV4-2,TRBV6-2,TRBV4-3,TRBV6-3,TRBV7-2,TRBV6-4,TRBV7-3,TRBV9,TRBV10-1,TRBV11-1,TRBV10-2,TRBV11-2,TRBV6-5,TRBV7-4,TRBV5-4,TRBV6-6,TRBV5-5,TRBV7-6,TRBV5-6,TRBV6-8,TRBV7-7,TRBV6-9,TRBV7-8,TRBV5-8,TRBV7-9,TRBV13,TRBV10-3,TRBV11-3,TRBV12-3,TRBV12-4,TRBV12-5,TRBV14,TRBV15,TRBV16,TRBV18,TRBV19,TRBV20-1,TRBV24-1,TRBV25-1,TRBV27,TRBV28,TRBV29-1,TRBV30
-    D:TRBD1,TRBD2
-    J:TRBJ1-1,TRBJ1-2,TRBJ1-3,TRBJ1-4,TRBJ1-5,TRBJ1-6,TRBJ2-1,TRBJ2-2,TRBJ2-3,TRBJ2-4,TRBJ2-5,TRBJ2-6,TRBJ2-7
+    V:
+    TRBV2,TRBV3-1,TRBV4-1,TRBV5-1,TRBV6-1,TRBV4-2,TRBV6-2,TRBV4-3,TRBV6-3,TRBV7-2,TRBV6-4,TRBV7-3,TRBV9,TRBV10-1,TRBV11-1,TRBV10-2,TRBV11-2,TRBV6-5,TRBV7-4,TRBV5-4,TRBV6-6,TRBV5-5,TRBV7-6,TRBV5-6,TRBV6-8,TRBV7-7,TRBV6-9,TRBV7-8,TRBV5-8,TRBV7-9,TRBV13,TRBV10-3,TRBV11-3,TRBV12-3,TRBV12-4,TRBV12-5,TRBV14,TRBV15,TRBV16,TRBV18,TRBV19,TRBV20-1,TRBV24-1,TRBV25-1,TRBV27,TRBV28,TRBV29-1,TRBV30
+    D:
+    TRBD1,TRBD2
+    J:
+    TRBJ1-1,TRBJ1-2,TRBJ1-3,TRBJ1-4,TRBJ1-5,TRBJ1-6,TRBJ2-1,TRBJ2-2,TRBJ2-3,TRBJ2-4,TRBJ2-5,TRBJ2-6,TRBJ2-7
 
 
 TRA::
 
-    V:TRAV1-1,TRAV1-2,TRAV2,TRAV3,TRAV4,TRAV5,TRAV6,TRAV7,TRAV8-1,TRAV9-1,TRAV10,TRAV12-1,TRAV8-2,TRAV8-3,TRAV13-1,TRAV12-2,TRAV8-4,TRAV13-2,TRAV14/DV4,TRAV9-2,TRAV12-3,TRAV8-6,TRAV16,TRAV17,TRAV18,TRAV19,TRAV20,TRAV21,TRAV22,TRAV23/DV6,TRAV24,TRAV25,TRAV26-1,TRAV27,TRAV29/DV5,TRAV30,TRAV26-2,TRAV34,TRAV35,TRAV36/DV7,TRAV38-1,TRAV38-2/DV8,TRAV39,TRAV40,TRAV41
-    J:TRAJ57,TRAJ56,TRAJ54,TRAJ53,TRAJ52,TRAJ50,TRAJ49,TRAJ48,TRAJ47,TRAJ46,TRAJ45,TRAJ44,TRAJ43,TRAJ42,TRAJ41,TRAJ40,TRAJ39,TRAJ38,TRAJ37,TRAJ36,TRAJ34,TRAJ33,TRAJ32,TRAJ31,TRAJ30,TRAJ29,TRAJ28,TRAJ27,TRAJ26,TRAJ24,TRAJ23,TRAJ22,TRAJ21,TRAJ20,TRAJ18,TRAJ17,TRAJ16,TRAJ15,TRAJ14,TRAJ13,TRAJ12,TRAJ11,TRAJ10,TRAJ9,TRAJ8,TRAJ7,TRAJ6,TRAJ5,TRAJ4,TRAJ3
+    V:
+    TRAV1-1,TRAV1-2,TRAV2,TRAV3,TRAV4,TRAV5,TRAV6,TRAV7,TRAV8-1,TRAV9-1,TRAV10,TRAV12-1,TRAV8-2,TRAV8-3,TRAV13-1,TRAV12-2,TRAV8-4,TRAV13-2,TRAV14/DV4,TRAV9-2,TRAV12-3,TRAV8-6,TRAV16,TRAV17,TRAV18,TRAV19,TRAV20,TRAV21,TRAV22,TRAV23/DV6,TRAV24,TRAV25,TRAV26-1,TRAV27,TRAV29/DV5,TRAV30,TRAV26-2,TRAV34,TRAV35,TRAV36/DV7,TRAV38-1,TRAV38-2/DV8,TRAV39,TRAV40,TRAV41
+    J:
+    TRAJ57,TRAJ56,TRAJ54,TRAJ53,TRAJ52,TRAJ50,TRAJ49,TRAJ48,TRAJ47,TRAJ46,TRAJ45,TRAJ44,TRAJ43,TRAJ42,TRAJ41,TRAJ40,TRAJ39,TRAJ38,TRAJ37,TRAJ36,TRAJ34,TRAJ33,TRAJ32,TRAJ31,TRAJ30,TRAJ29,TRAJ28,TRAJ27,TRAJ26,TRAJ24,TRAJ23,TRAJ22,TRAJ21,TRAJ20,TRAJ18,TRAJ17,TRAJ16,TRAJ15,TRAJ14,TRAJ13,TRAJ12,TRAJ11,TRAJ10,TRAJ9,TRAJ8,TRAJ7,TRAJ6,TRAJ5,TRAJ4,TRAJ3
 
 
 TRG::
 
-    V:TRGV9,TRGV8,TRGV5,TRGV4,TRGV3,TRGV2
-    J:TRGJ2,TRGJP2,TRGJ1,TRGJP1
+    V:
+    TRGV9,TRGV8,TRGV5,TRGV4,TRGV3,TRGV2
+    J:
+    TRGJ2,TRGJP2,TRGJ1,TRGJP1
 
 
 TRD::
 
-    V:TRDV1,TRDV2,TRDV3
-    D:TRDD1,TRDD2,TRDD3
-    J:TRDJ1,TRDJ4,TRDJ2,TRDJ3
+    V:
+    TRDV1,TRDV2,TRDV3
+    D:
+    TRDD1,TRDD2,TRDD3
+    J:
+    TRDJ1,TRDJ4,TRDJ2,TRDJ3
 
 
 **Mouse**
 
 TRB::
 
-    V:TRBV1,TRBV2,TRBV3,TRBV4,TRBV5,TRBV12-1,TRBV13-1,TRBV12-2,TRBV13-2,TRBV13-3,TRBV14,TRBV15,TRBV16,TRBV17,TRBV19,TRBV20,TRBV23,TRBV24,TRBV26,TRBV29,TRBV30,TRBV31
-    D:TRBD1,TRBD2
-    J:TRBJ1-1,TRBJ1-2,TRBJ1-3,TRBJ1-4,TRBJ1-5,TRBJ2-1,TRBJ2-2,TRBJ2-3,TRBJ2-4,TRBJ2-5,TRBJ2-6,TRBJ2-7
+    V:
+    TRBV1,TRBV2,TRBV3,TRBV4,TRBV5,TRBV12-1,TRBV13-1,TRBV12-2,TRBV13-2,TRBV13-3,TRBV14,TRBV15,TRBV16,TRBV17,TRBV19,TRBV20,TRBV23,TRBV24,TRBV26,TRBV29,TRBV30,TRBV31
+    D:
+    TRBD1,TRBD2
+    J:
+    TRBJ1-1,TRBJ1-2,TRBJ1-3,TRBJ1-4,TRBJ1-5,TRBJ2-1,TRBJ2-2,TRBJ2-3,TRBJ2-4,TRBJ2-5,TRBJ2-6,TRBJ2-7
     
 
 **OUTPUT**