--- a/mutation_analysis.r	Tue Apr 07 03:52:34 2015 -0400
+++ b/mutation_analysis.r	Tue Apr 07 04:46:35 2015 -0400
@@ -130,13 +130,20 @@
 totalMutationsAtGC_columns = paste(rep(regions, each=6), c(".IMGT.g.a",".IMGT.c.t",".IMGT.c.a",".IMGT.g.c",".IMGT.c.g",".IMGT.g.t"), sep="")
 dat$totalMutationsAtGC = apply(dat, FUN=sum_by_row, 1, columns=totalMutationsAtGC_columns)
 
+silentMutations_columns = paste(regions, ".IMGT.Nb.of.silent.mutations", sep="")
+silentMutations_columns
+dat[,silentMutations_columns]
+dat$silentMutations = apply(dat, FUN=sum_by_row, 1, columns=silentMutations_columns)
+
+nonSilentMutations_columns = paste(regions, ".IMGT.Nb.of.nonsilent.mutations", sep="")
+dat$nonSilentMutations = apply(dat, FUN=sum_by_row, 1, columns=nonSilentMutations_columns)
 
 
 setwd(outputdir)
 
 nts = c("a", "t", "g", "c")
 zeros=rep(0, 4)
-matrx = matrix(data = 0, ncol=((length(genes) + 1) * 3),nrow=5)
+matrx = matrix(data = 0, ncol=((length(genes) + 1) * 3),nrow=6)
 for(i in 1:length(genes)){
   gene = genes[i]
   tmp = dat[grepl(paste(".*", gene, ".*", sep=""), dat$best_match),]
@@ -162,6 +169,10 @@
   matrx[5,x] = sum(tmp$totalMutationsAtGC)
   matrx[5,y] = sum(tmp$VRegionMutations)
   matrx[5,z] = round(matrx[5,x] / matrx[5,y] * 100, digits=1)
+  matrx[6,x] = sum(tmp$silentMutations)
+  matrx[6,y] = sum(tmp$nonSilentMutations)
+  matrx[6,z] = round(matrx[6,x] / matrx[6,y] * 100, digits=1)
+  
   
   transitionTable = data.frame(A=zeros,C=zeros,G=zeros,T=zeros)
   row.names(transitionTable) = c("A", "C", "G", "T")
@@ -221,6 +232,9 @@
 matrx[5,x] = sum(tmp$totalMutationsAtGC)
 matrx[5,y] = sum(tmp$VRegionMutations)
 matrx[5,z] = round(matrx[5,x] / matrx[5,y] * 100, digits=1)
+matrx[6,x] = sum(tmp$silentMutations)
+matrx[6,y] = sum(tmp$nonSilentMutations)
+matrx[6,z] = round(matrx[6,x] / matrx[6,y] * 100, digits=1)
 
 transitionTable = data.frame(A=1:4,C=1:4,G=1:4,T=1:4)
 row.names(transitionTable) = c("A", "C", "G", "T")
@@ -257,7 +271,7 @@
 
 
 result = data.frame(matrx)
-row.names(result) = c("Number of Mutations (%)", "Transition (%)", "Transversions (%)", "Transitions at G C (%)", "Targeting of C.G (%)")
+row.names(result) = c("Number of Mutations (%)", "Transition (%)", "Transversions (%)", "Transitions at G C (%)", "Targeting of C.G (%)", "Silent/Non Silent (%)")
 
 write.table(x=result, file="mutations.txt", sep=",",quote=F,row.names=T,col.names=F)
 
@@ -320,7 +334,7 @@
 dat$percentage_mutations = round(dat$VRegionMutations / dat$VRegionNucleotides * 100, 2)
 
 p = ggplot(dat, aes(best_match, percentage_mutations))# + scale_y_log10(breaks=scales,labels=scales)
-p = p + geom_point(aes(colour=best_match), position="jitter")
+p = p + geom_boxplot(aes(middle=mean(percentage_mutations)), alpha=0.1, outlier.shape = NA) + geom_point(aes(colour=best_match), position="jitter")
 p = p + xlab("Subclass") + ylab("Frequency") + ggtitle("Frequency scatter plot")
 
 png(filename="scatter.png")