--- a/mutation_analysis.r	Wed Aug 10 09:10:45 2016 -0400
+++ b/mutation_analysis.r	Thu Aug 11 08:00:00 2016 -0400
@@ -105,6 +105,8 @@
                     "FR2.IMGT.Nb.of.nonsilent.mutations",
                     "FR3.IMGT.Nb.of.nonsilent.mutations")
 
+
+print("Cleaning up columns")
 for(col in cleanup_columns){
   dat[,col] = gsub("\\(.*\\)", "", dat[,col])
   #dat[dat[,col] == "",] = "0"
@@ -119,6 +121,8 @@
 
 sum_by_row = function(x, columns) { sum(as.numeric(x[columns]), na.rm=T) }
 
+print("aggregating data into new columns")
+
 VRegionMutations_columns = paste(regions, ".IMGT.Nb.of.mutations", sep="")
 dat$VRegionMutations =  apply(dat, FUN=sum_by_row, 1, columns=VRegionMutations_columns)
 
@@ -304,6 +308,8 @@
 funcs = c(median, sum, mean)
 fnames = c("median", "sum", "mean")
 
+print("Creating result tables")
+
 for(i in 1:length(funcs)){
 	func = funcs[[i]]
 	fname = fnames[[i]]
@@ -313,9 +319,10 @@
 		rows = 11
 	}
 	matrx = matrix(data = 0, ncol=((length(genes) + 1) * 3),nrow=rows)
-
+	
 	for(i in 1:length(genes)){
-	  matrx = calculate_result(i, genes[i], dat, matrx, func, fname, genes[i])
+		print(paste("Creating table for", fname, genes[i]))
+		matrx = calculate_result(i, genes[i], dat, matrx, func, fname, genes[i])
 	}
 
 	matrx = calculate_result(i + 1, ".*", dat[!grepl("unmatched", dat$best_match),], matrx, func, fname, name="all")
@@ -330,11 +337,11 @@
 	write.table(x=result, file=paste("mutations_", fname, ".txt", sep=""), sep=",",quote=F,row.names=T,col.names=F)
 }
 
+print("Adding median number of mutations to sum table")
+
 sum.table = read.table("mutations_sum.txt", sep=",", header=F)
 median.table = read.table("mutations_median.txt", sep=",", header=F)
 
-#sum.table["Median of Number of Mutations (%)",] = median.table[1,]
-
 new.table = sum.table[1,]
 new.table[2,] = median.table[1,]
 new.table[3:12,] = sum.table[2:11,]
@@ -345,6 +352,9 @@
 
 write.table(x=new.table, file="mutations_sum.txt", sep=",",quote=F,row.names=F,col.names=F)
 
+
+print("Plotting ca piechart")
+
 dat = dat[!grepl("^unmatched", dat$best_match),]
 
 #blegh
@@ -365,6 +375,8 @@
 	dev.off()
 }
 
+print("Plotting cg piechart")
+
 genesForPlot = dat[grepl("cg", dat$best_match),]$best_match
 if(length(genesForPlot) > 0){
 	genesForPlot = data.frame(table(genesForPlot))
@@ -382,6 +394,9 @@
 	dev.off()
 }
 
+
+print("Plotting scatterplot")
+
 dat$percentage_mutations = round(dat$VRegionMutations / dat$VRegionNucleotides * 100, 2)
 
 p = ggplot(dat, aes(best_match, percentage_mutations))
@@ -396,6 +411,9 @@
 
 write.table(dat, input, sep="\t",quote=F,row.names=F,col.names=T)
 
+
+print("Plotting frequency ranges plot")
+
 dat$best_match_class = substr(dat$best_match, 0, 2)
 freq_labels = c("0", "0-2", "2-5", "5-10", "10-15", "15-20", "20")
 dat$frequency_bins = cut(dat$percentage_mutations, breaks=c(-Inf, 0, 2,5,10,15,20, Inf), labels=freq_labels)