changeset 2:aac19ac7cb21 draft

Uploaded
author davidvanzessen
date Fri, 11 Oct 2013 09:11:03 -0400
parents c43c63f4ef80
children d27d745d0556
files RScript.r
diffstat 1 files changed, 22 insertions(+), 13 deletions(-) [+]
line wrap: on
line diff
--- a/RScript.r	Wed Oct 09 07:29:08 2013 -0400
+++ b/RScript.r	Fri Oct 11 09:11:03 2013 -0400
@@ -9,7 +9,7 @@
 if (!require("gridExtra")) {
 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/") 
 }
-library (gridExtra)
+library(gridExtra)
 if (!require("ggplot2")) {
 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/") 
 }
@@ -84,6 +84,7 @@
 
 pV = ggplot(PRODFV)
 pV = pV + geom_bar( aes( x=factor(reorder(Top.V.Gene, chr.orderV)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
+pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
 
 png("VPlot.png",width = 1280, height = 720)
 pV
@@ -91,6 +92,7 @@
 
 pD = ggplot(PRODFD)
 pD = pD + geom_bar( aes( x=factor(reorder(Top.D.Gene, chr.orderD)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
+pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
 
 png("DPlot.png",width = 800, height = 600)
 pD
@@ -98,6 +100,7 @@
 
 pJ = ggplot(PRODFJ)
 pJ = pJ + geom_bar( aes( x=factor(reorder(Top.J.Gene, chr.orderJ)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
+pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
 
 png("JPlot.png",width = 800, height = 600)
 pJ
@@ -106,10 +109,12 @@
 
 plotVD <- function(dat){
 	ggplot() + 
-	geom_tile(data=dat, aes(x=factor(Top.V.Gene), y=factor(Top.D.Gene), fill=log)) + 
+	geom_tile(data=dat, aes(x=factor(Top.D.Gene), y=factor(Top.V.Gene), fill=log)) + 
 	theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
-	scale_fill_gradient(low="white", high="red") + 
-	ggtitle(unique(dat$Sample))
+	scale_fill_gradient(low="gold", high="blue") + 
+	ggtitle(unique(dat$Sample)) + 
+	xlab("D genes") + 
+	ylab("V Genes")
 }
 
 
@@ -121,17 +126,19 @@
 completeVD$log = log(completeVD$Length)
 completeVD$log[is.na(completeVD$log)] = 0
 l = split(completeVD, f=completeVD[,"Sample"])
-png("HeatmapVD%d.png", width=100+(15*length(Vchain$v.name)), height=100+(15*length(Dchain$v.name)))
+png("HeatmapVD%d.png", width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
 lapply(l, FUN=plotVD)
 dev.off()
 
 
 plotVJ <- function(dat){
 	ggplot() + 
-	geom_tile(data=dat, aes(x=factor(Top.V.Gene), y=factor(Top.J.Gene), fill=log)) + 
+	geom_tile(data=dat, aes(x=factor(Top.J.Gene), y=factor(Top.V.Gene), fill=log)) + 
 	theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
-	scale_fill_gradient(low="white", high="red") + 
-	ggtitle(unique(dat$Sample))
+	scale_fill_gradient(low="gold", high="blue") + 
+	ggtitle(unique(dat$Sample)) + 
+	xlab("J genes") + 
+	ylab("V Genes")
 }
 
 VandJCount = ddply(PRODF, c("Top.V.Gene", "Top.J.Gene", "Sample"), function(x) summary(x$VDJCDR3))
@@ -142,16 +149,18 @@
 completeVJ$log = log(completeVJ$Length)
 completeVJ$log[is.na(completeVJ$log)] = 0
 l = split(completeVJ, f=completeVJ[,"Sample"])
-png("HeatmapVJ%d.png", width=100+(15*length(Vchain$v.name)), height=100+(15*length(Jchain$v.name)))
+png("HeatmapVJ%d.png", width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
 lapply(l, FUN=plotVJ)
 dev.off()
 
 plotDJ <- function(dat){
 	ggplot() + 
-	geom_tile(data=dat, aes(x=factor(Top.D.Gene), y=factor(Top.J.Gene), fill=log)) + 
+	geom_tile(data=dat, aes(x=factor(Top.J.Gene), y=factor(Top.D.Gene), fill=log)) + 
 	theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
-	scale_fill_gradient(low="white", high="red") + 
-	ggtitle(unique(dat$Sample))
+	scale_fill_gradient(low="gold", high="blue") + 
+	ggtitle(unique(dat$Sample)) + 
+	xlab("J genes") + 
+	ylab("D Genes")
 }
 
 DandJCount = ddply(PRODF, c("Top.D.Gene", "Top.J.Gene", "Sample"), function(x) summary(x$VDJCDR3))
@@ -162,7 +171,7 @@
 completeDJ$log = log(completeDJ$Length)
 completeDJ$log[is.na(completeDJ$log)] = 0
 l = split(completeDJ, f=completeDJ[,"Sample"])
-png("HeatmapDJ%d.png", width=100+(15*length(Dchain$v.name)), height=100+(15*length(Jchain$v.name)))
+png("HeatmapDJ%d.png", width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
 lapply(l, FUN=plotDJ)
 dev.off()