--- a/mutation_analysis.py	Wed May 04 04:28:02 2016 -0400
+++ b/mutation_analysis.py	Wed May 04 08:40:31 2016 -0400
@@ -7,7 +7,7 @@
 parser.add_argument("--input",
 					help="The '7_V-REGION-mutation-and-AA-change-table' and '10_V-REGION-mutation-hotspots' merged together, with an added 'best_match' annotation")
 parser.add_argument("--genes", help="The genes available in the 'best_match' column")
-parser.add_argument("--includefr1", help="The genes available in the 'best_match' column")
+parser.add_argument("--includefr1", help="Should the mutation/nucleotides in the FR1 region be included?")
 parser.add_argument("--output", help="Output file")
 
 args = parser.parse_args()
@@ -57,6 +57,7 @@
 		linesplt = line.split("\t")
 		ID = linesplt[IDIndex]
 		genedic[ID] = linesplt[best_matchIndex]
+		print line
 		try:
 			mutationdic[ID + "_FR1"] = [mutationMatcher.match(x).groups() for x in linesplt[fr1Index].split("|") if x] if include_fr1 else []
 			mutationdic[ID + "_CDR1"] = [mutationMatcher.match(x).groups() for x in linesplt[cdr1Index].split("|") if x]

--- a/mutation_analysis.r	Wed May 04 04:28:02 2016 -0400
+++ b/mutation_analysis.r	Wed May 04 08:40:31 2016 -0400
@@ -6,7 +6,6 @@
 input = args[1]
 genes = unlist(strsplit(args[2], ","))
 outputdir = args[3]
-print(args[4])
 include_fr1 = ifelse(args[4] == "yes", T, F)
 setwd(outputdir)
 
@@ -28,8 +27,6 @@
   stop("No data")
 }
 
-
-
 cleanup_columns = c("FR1.IMGT.c.a",
                     "FR2.IMGT.g.t",
                     "CDR1.IMGT.Nb.of.nucleotides",
@@ -111,7 +108,7 @@
   dat[,col] = gsub("\\(.*\\)", "", dat[,col])
   #dat[dat[,col] == "",] = "0"
   dat[,col] = as.numeric(dat[,col])
-  dat[is.na(dat[,col]),] = 0
+  dat[is.na(dat[,col]),col] = 0
 }
 
 regions = c("FR1", "CDR1", "FR2", "CDR2", "FR3")
@@ -171,7 +168,6 @@
 
 setwd(outputdir)
 
-
 calculate_result = function(i, gene, dat, matrx, f, fname, name){
 	tmp = dat[grepl(paste(".*", gene, ".*", sep=""), dat$best_match),]
 
@@ -313,7 +309,6 @@
 	install.packages("ggplot2", repos="http://cran.xl-mirror.nl/") 
 }
 
-
 genesForPlot = gsub("[0-9]", "", dat$best_match)
 genesForPlot = data.frame(table(genesForPlot))
 colnames(genesForPlot) = c("Gene","Freq")
@@ -330,7 +325,6 @@
 pc
 dev.off()
 
-
 #blegh
 genesForPlot = dat[grepl("ca", dat$best_match),]$best_match
 if(length(genesForPlot) > 0){