--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mutation_analysis.py	Mon Aug 18 04:04:37 2014 -0400
@@ -0,0 +1,80 @@
+import re
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--mutationfile", help="The '7_V-REGION-mutation-and-AA-change-table' file from the IMGT output")
+parser.add_argument("--hotspotfile", help="The '10_V-REGION-mutation-hotspots' file from the IMGT output")
+parser.add_argument("--output", help="Output file")
+
+args = parser.parse_args()
+
+mutationfile = args.mutationfile #"test_VH-Ca_Cg_25nt/7_V-REGION-mutation-and-AA-change-table_test_VH-Ca_Cg_25nt_241013.txt"
+hotspotsfile = args.hotspotfile #"test_VH-Ca_Cg_25nt/10_V-REGION-mutation-hotspots_test_VH-Ca_Cg_25nt_241013.txt"
+outfile = args.output #"out.txt"
+
+mutationdic = dict()
+mutationMatcher = re.compile("^(.)(\d+).(.),?(.)?(\d+)?.?(.)?(.?.?.?.?.?)?")
+linecount = 0
+
+with open(mutationfile, 'r') as i:
+  for line in i.readlines()[1:]:
+		linecount += 1
+		linesplt = line.split("\t")
+		if linesplt[2] != "productive":
+			continue
+		ID = linesplt[1]
+		mutationdic[ID + "_FR1"] = [mutationMatcher.match(x).groups() for x in linesplt[5].split("|") if x]
+		mutationdic[ID + "_CDR1"] = [mutationMatcher.match(x).groups() for x in linesplt[6].split("|") if x]
+		mutationdic[ID + "_FR2"] = [mutationMatcher.match(x).groups() for x in linesplt[7].split("|") if x]
+		mutationdic[ID + "_CDR2"] = [mutationMatcher.match(x).groups() for x in linesplt[8].split("|") if x]
+		mutationdic[ID + "_FR2-CDR2"] = mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"]
+		mutationdic[ID + "_FR3"] = [mutationMatcher.match(x).groups() for x in linesplt[9].split("|") if x]
+    
+if linecount == 0:
+	print "No data, exiting"
+	with open(outfile, 'w') as o:
+		o.write("RGYW (%),0,0,NA\n")
+		o.write("WRCY (%),0,0,NA\n")
+		o.write("WA (%),0,0,NA\n")
+		o.write("TW (%),0,0,NA\n")
+	import sys
+	sys.exit()
+
+hotspotMatcher = re.compile("[actg]+,(\d+)-(\d+)\((.*)\)")
+RGYWCount = 0
+WRCYCount = 0
+WACount = 0
+TWCount = 0
+
+with open(hotspotsfile, 'r') as i:
+	for line in i.readlines()[1:]:
+		linesplt = line.split("\t")
+		if linesplt[2] != "productive":
+			continue
+		ID = linesplt[1]
+		RGYW = [(int(x),int(y),z) for (x,y,z) in [hotspotMatcher.match(x).groups() for x in linesplt[6].split("|") if x]]
+		WRCY = [(int(x),int(y),z) for (x,y,z) in [hotspotMatcher.match(x).groups() for x in linesplt[7].split("|") if x]]
+		WA = [(int(x),int(y),z) for (x,y,z) in [hotspotMatcher.match(x).groups() for x in linesplt[4].split("|") if x]]
+		TW = [(int(x),int(y),z) for (x,y,z) in [hotspotMatcher.match(x).groups() for x in linesplt[5].split("|") if x]]
+		RGYWCount += sum([1 for (x,y,z) in RGYW if z != "CDR3" and any([(x <= int(where) <= y) for (frm, where, to, a,b,c,d) in mutationdic[ID + "_" + z]])])
+		WRCYCount += sum([1 for (x,y,z) in WRCY if z != "CDR3" and any([(x <= int(where) <= y) for (frm, where, to, a,b,c,d) in mutationdic[ID + "_" + z]])])
+		WACount += sum([1 for (x,y,z) in WA if z != "CDR3" and any([(x <= int(where) <= y) for (frm, where, to, a,b,c,d) in mutationdic[ID + "_" + z]])])
+		TWCount += sum([1 for (x,y,z) in TW if z != "CDR3" and any([(x <= int(where) <= y) for (frm, where, to, a,b,c,d) in mutationdic[ID + "_" + z]])])
+
+path = outfile[:outfile.rfind("/") + 1] + "mutations.txt"
+value = 0;
+with open(path, 'r') as f:
+	value = f.readlines()[0].split(",")[1]
+with open(outfile, 'w') as o:
+	if value != "0":
+		o.write("RGYW (%)," + str(RGYWCount) + "," + value + "," + str(round(RGYWCount / float(value) * 100, 1)) + "\n")
+		o.write("WRCY (%)," + str(WRCYCount) + "," + value + "," + str(round(WRCYCount / float(value) * 100, 1)) + "\n")
+		o.write("WA (%)," + str(WACount) + "," + value + "," + str(round(WACount / float(value) * 100, 1)) + "\n")
+		o.write("TW (%)," + str(TWCount) + "," + value + "," + str(round(TWCount / float(value) * 100, 1)) + "\n")
+	else:
+		o.write("RGYW (%)," + str(RGYWCount) + ",0,NA\n")
+		o.write("WRCY (%)," + str(WRCYCount) + ",0,NA\n")
+		o.write("WA (%)," + str(WACount) + ",0,NA\n")
+		o.write("TW (%)," + str(TWCount) + ",0,NA\n")
+
+