annotate shm_csr.py @ 81:b6f9a640e098 draft

Uploaded

1 import argparse
2 import logging
3 import sys
4 import os
5 import re
6 
7 from collections import defaultdict
8 
9 def main():
10 	parser = argparse.ArgumentParser()
11 	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")
12 	parser.add_argument("--genes", help="The genes available in the 'best_match' column")
13 	parser.add_argument("--empty_region_filter", help="Where does the sequence start?", choices=['leader', 'FR1', 'CDR1', 'FR2'])
14 	parser.add_argument("--output", help="Output file")
15 
16 	args = parser.parse_args()
17 
18 	infile = args.input
19 	genes = str(args.genes).split(",")
20 	empty_region_filter = args.empty_region_filter
21 	outfile = args.output
22 
23 	genedic = dict()
24 
25 	mutationdic = dict()
26 	mutationMatcher = re.compile("^(.)(\d+).(.),?[ ]?(.)?(\d+)?.?(.)?(.?.?.?.?.?)?")
27 	mutationMatcher = re.compile("^([actg])(\d+).([actg]),?[ ]?([A-Z])?(\d+)?.?([A-Z])?(.*)?")
28 	mutationMatcher = re.compile("^([actg])(\d+).([actg]),?[ ]?([A-Z])?(\d+)?[>]?([A-Z;])?(.*)?")
29 	mutationMatcher = re.compile("^([nactg])(\d+).([nactg]),?[ ]?([A-Z])?(\d+)?[>]?([A-Z;])?(.*)?")
30 	NAMatchResult = (None, None, None, None, None, None, '')
31 	geneMatchers = {gene: re.compile("^" + gene + ".*") for gene in genes}
32 	linecount = 0
33 
34 	IDIndex = 0
35 	best_matchIndex = 0
36 	fr1Index = 0
37 	cdr1Index = 0
38 	fr2Index = 0
39 	cdr2Index = 0
40 	fr3Index = 0
41 	first = True
42 	IDlist = []
43 	mutationList = []
44 	mutationListByID = {}
45 	cdr1LengthDic = {}
46 	cdr2LengthDic = {}
47 
48 	fr1LengthDict = {}
49 	fr2LengthDict = {}
50 	fr3LengthDict = {}
51 
52 	cdr1LengthIndex = 0
53 	cdr2LengthIndex = 0
54 
55 	fr1SeqIndex = 0
56 	fr2SeqIndex = 0
57 	fr3SeqIndex = 0
58 
59 	tandem_sum_by_class = defaultdict(int)
60 	expected_tandem_sum_by_class = defaultdict(float)
61 
62 	with open(infile, 'ru') as i:
63 		for line in i:
64 			if first:
65 				linesplt = line.split("\t")
66 				IDIndex = linesplt.index("Sequence.ID")
67 				best_matchIndex = linesplt.index("best_match")
68 				fr1Index = linesplt.index("FR1.IMGT")
69 				cdr1Index = linesplt.index("CDR1.IMGT")
70 				fr2Index = linesplt.index("FR2.IMGT")
71 				cdr2Index = linesplt.index("CDR2.IMGT")
72 				fr3Index = linesplt.index("FR3.IMGT")
73 				cdr1LengthIndex = linesplt.index("CDR1.IMGT.length")
74 				cdr2LengthIndex = linesplt.index("CDR2.IMGT.length")
75 				fr1SeqIndex = linesplt.index("FR1.IMGT.seq")
76 				fr2SeqIndex = linesplt.index("FR2.IMGT.seq")
77 				fr3SeqIndex = linesplt.index("FR3.IMGT.seq")
78 				first = False
79 				continue
80 			linecount += 1
81 			linesplt = line.split("\t")
82 			ID = linesplt[IDIndex]
83 			genedic[ID] = linesplt[best_matchIndex]
84 			
85 			mutationdic[ID + "_FR1"] = []
86 			if len(linesplt[fr1Index]) > 5 and empty_region_filter == "leader":
87 				mutationdic[ID + "_FR1"] = [mutationMatcher.match(x).groups() for x in linesplt[fr1Index].split("|") if x]
88 
89 			mutationdic[ID + "_CDR1"] = []
90 			if len(linesplt[cdr1Index]) > 5 and empty_region_filter in ["leader", "FR1"]:
91 				mutationdic[ID + "_CDR1"] = [mutationMatcher.match(x).groups() for x in linesplt[cdr1Index].split("|") if x]
92 
93 			mutationdic[ID + "_FR2"] = []
94 			if len(linesplt[fr2Index]) > 5 and empty_region_filter in ["leader", "FR1", "CDR1"]:
95 				mutationdic[ID + "_FR2"] = [mutationMatcher.match(x).groups() for x in linesplt[fr2Index].split("|") if x]
96 
97 			mutationdic[ID + "_CDR2"] = []
98 			if len(linesplt[cdr2Index]) > 5:
99 				mutationdic[ID + "_CDR2"] = [mutationMatcher.match(x).groups() for x in linesplt[cdr2Index].split("|") if x]
00 			
01 			mutationdic[ID + "_FR2-CDR2"] = mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"]
02 
03 			mutationdic[ID + "_FR3"] = []
04 			if len(linesplt[fr3Index]) > 5:
05 				mutationdic[ID + "_FR3"] = [mutationMatcher.match(x).groups() for x in linesplt[fr3Index].split("|") if x]
06 				
07 			mutationList += mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
08 			mutationListByID[ID] = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
09 
10 			try:
11 				cdr1Length = int(linesplt[cdr1LengthIndex])
12 			except:
13 				cdr1Length = 0
14 			
15 			try:
16 				cdr2Length = int(linesplt[cdr2LengthIndex])
17 			except:
18 				cdr2Length = 0
19 
20 			#print linesplt[fr2SeqIndex]
21 			fr1Length = len(linesplt[fr1SeqIndex]) if empty_region_filter == "leader" else 0
22 			fr2Length = len(linesplt[fr2SeqIndex]) if empty_region_filter in ["leader", "FR1", "CDR1"] else 0
23 			fr3Length = len(linesplt[fr3SeqIndex])
24 
25 			cdr1LengthDic[ID] = cdr1Length
26 			cdr2LengthDic[ID] = cdr2Length
27 
28 			fr1LengthDict[ID] = fr1Length
29 			fr2LengthDict[ID] = fr2Length
30 			fr3LengthDict[ID] = fr3Length
31 
32 			IDlist += [ID]
33 	print "len(mutationdic) =", len(mutationdic)
34 
35 	with open(os.path.join(os.path.dirname(os.path.abspath(infile)), "mutationdict.txt"), 'w') as out_handle:
36 		for ID, lst in mutationdic.iteritems():
37 			for mut in lst:
38 				out_handle.write("{0}\t{1}\n".format(ID, "\t".join([str(x) for x in mut])))
39 
40 	#tandem mutation stuff
41 	tandem_frequency = defaultdict(int)
42 	mutation_frequency = defaultdict(int)
43 	
44 	mutations_by_id_dic = {}
45 	first = True
46 	mutation_by_id_file = os.path.join(os.path.dirname(outfile), "mutation_by_id.txt")
47 	with open(mutation_by_id_file, 'r') as mutation_by_id:
48 		for l in mutation_by_id:
49 			if first:
50 				first = False
51 				continue
52 			splt = l.split("\t")
53 			mutations_by_id_dic[splt[0]] = int(splt[1])
54     
55 	tandem_file = os.path.join(os.path.dirname(outfile), "tandems_by_id.txt")
56 	with open(tandem_file, 'w') as o:
57 		highest_tandem_length = 0
58 
59 		o.write("Sequence.ID\tnumber_of_mutations\tnumber_of_tandems\tregion_length\texpected_tandems\tlongest_tandem\ttandems\n")
60 		for ID in IDlist:
61 			mutations = mutationListByID[ID]
62 			if len(mutations) == 0:
63 				continue
64 			last_mut = max(mutations, key=lambda x: int(x[1]))
65 
66 			last_mut_pos = int(last_mut[1])
67 
68 			mut_positions = [False] * (last_mut_pos + 1)
69 
70 			for mutation in mutations:
71 				frm, where, to, frmAA, whereAA, toAA, thing = mutation
72 				where = int(where)
73 				mut_positions[where] = True
74 
75 			tandem_muts = []
76 			tandem_start = -1
77 			tandem_length = 0
78 			for i in range(len(mut_positions)):
79 				if mut_positions[i]:
80 					if tandem_start == -1:
81 						tandem_start = i
82 					tandem_length += 1
83 					#print "".join(["1" if x else "0" for x in mut_positions[:i+1]])
84 				else:
85 					if tandem_length > 1:
86 						tandem_muts.append((tandem_start, tandem_length))
87 						#print "{0}{1} {2}:{3}".format(" " * (i - tandem_length), "^" * tandem_length, tandem_start, tandem_length)
88 					tandem_start = -1
89 					tandem_length = 0
90 			if tandem_length > 1:  # if the sequence ends with a tandem mutation
91 				tandem_muts.append((tandem_start, tandem_length))
92 
93 			if len(tandem_muts) > 0:
94 				if highest_tandem_length < len(tandem_muts):
95 					highest_tandem_length = len(tandem_muts)
96 
97 			region_length = fr1LengthDict[ID] + cdr1LengthDic[ID] + fr2LengthDict[ID] + cdr2LengthDic[ID] + fr3LengthDict[ID]
98 			longest_tandem = max(tandem_muts, key=lambda x: x[1]) if len(tandem_muts) else (0, 0)
99 			num_mutations = mutations_by_id_dic[ID] # len(mutations)
00 			f_num_mutations = float(num_mutations)
01 			num_tandem_muts = len(tandem_muts)
02 			expected_tandem_muts = f_num_mutations * (f_num_mutations - 1.0) / float(region_length)
03 			o.write("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\n".format(ID,
04 																str(num_mutations),
05 																str(num_tandem_muts),
06 																str(region_length),
07 																str(round(expected_tandem_muts, 2)),
08 																str(longest_tandem[1]),
09 																str(tandem_muts)))
10 			gene = genedic[ID]
11 			if gene.find("unmatched") == -1:
12 				tandem_sum_by_class[gene] += num_tandem_muts
13 				expected_tandem_sum_by_class[gene] += expected_tandem_muts
14 
15 				tandem_sum_by_class["all"] += num_tandem_muts
16 				expected_tandem_sum_by_class["all"] += expected_tandem_muts
17 
18 				gene = gene[:3]
19 				if gene in ["IGA", "IGG"]:
20 					tandem_sum_by_class[gene] += num_tandem_muts
21 					expected_tandem_sum_by_class[gene] += expected_tandem_muts
22 			else:
23 				tandem_sum_by_class["unmatched"] += num_tandem_muts
24 				expected_tandem_sum_by_class["unmatched"] += expected_tandem_muts
25 
26 
27 			for tandem_mut in tandem_muts:
28 				tandem_frequency[str(tandem_mut[1])] += 1
29 			#print "\t".join([ID, str(len(tandem_muts)), str(longest_tandem[1]) , str(tandem_muts)])
30 
31 	tandem_freq_file = os.path.join(os.path.dirname(outfile), "tandem_frequency.txt")
32 	with open(tandem_freq_file, 'w') as o:
33 		for frq in sorted([int(x) for x in tandem_frequency.keys()]):
34 			o.write("{0}\t{1}\n".format(frq, tandem_frequency[str(frq)]))
35 
36 	tandem_row = []
37 	genes_extra = list(genes)
38 	genes_extra.append("all")
39 	for x, y, in zip([tandem_sum_by_class[x] for x in genes_extra], [expected_tandem_sum_by_class[x] for x in genes_extra]):
40 		if y != 0:
41 			tandem_row += [x, round(y, 2), round(x / y, 2)]
42 		else:
43 			tandem_row += [x, round(y, 2), 0]
44 
45 	tandem_freq_file = os.path.join(os.path.dirname(outfile), "shm_overview_tandem_row.txt")
46 	with open(tandem_freq_file, 'w') as o:
47 		o.write("Tandems/Expected (ratio),{0}\n".format(",".join([str(x) for x in tandem_row])))
48 
49 	#print mutationList, linecount
50 
51 	AALength = (int(max(mutationList, key=lambda i: int(i[4]) if i[4] and i[5] != ";" else 0)[4]) + 1)  # [4] is the position of the AA mutation, None if silent
52 	if AALength < 60:
53 		AALength = 64
54 
55 	AA_mutation = [0] * AALength
56 	AA_mutation_dic = {"IGA": AA_mutation[:], "IGG": AA_mutation[:], "IGM": AA_mutation[:], "IGE": AA_mutation[:], "unm": AA_mutation[:], "all": AA_mutation[:]}
57 	AA_mutation_empty = AA_mutation[:]
58 
59 	print "AALength:", AALength
60 	aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/aa_id_mutations.txt"
61 	with open(aa_mutations_by_id_file, 'w') as o:
62 		o.write("ID\tbest_match\t" + "\t".join([str(x) for x in range(1,AALength)]) + "\n")
63 		for ID in mutationListByID.keys():
64 			AA_mutation_for_ID = AA_mutation_empty[:]
65 			for mutation in mutationListByID[ID]:
66 				if mutation[4] and mutation[5] != ";":
67 					AA_mutation_position = int(mutation[4])
68 					try:
69 						AA_mutation[AA_mutation_position] += 1
70 						AA_mutation_for_ID[AA_mutation_position] += 1
71 					except Exception as e:
72 						print e
73 						print mutation
74 						sys.exit()
75 					clss = genedic[ID][:3]
76 					AA_mutation_dic[clss][AA_mutation_position] += 1
77 			o.write(ID + "\t" + genedic[ID] + "\t" + "\t".join([str(x) for x in AA_mutation_for_ID[1:]]) + "\n")
78 
79 
80 
81 	#absent AA stuff
82 	absentAACDR1Dic = defaultdict(list)
83 	absentAACDR1Dic[5] = range(29,36)
84 	absentAACDR1Dic[6] = range(29,35)
85 	absentAACDR1Dic[7] = range(30,35)
86 	absentAACDR1Dic[8] = range(30,34)
87 	absentAACDR1Dic[9] = range(31,34)
88 	absentAACDR1Dic[10] = range(31,33)
89 	absentAACDR1Dic[11] = [32]
90 
91 	absentAACDR2Dic = defaultdict(list)
92 	absentAACDR2Dic[0] = range(55,65)
93 	absentAACDR2Dic[1] = range(56,65)
94 	absentAACDR2Dic[2] = range(56,64)
95 	absentAACDR2Dic[3] = range(57,64)
96 	absentAACDR2Dic[4] = range(57,63)
97 	absentAACDR2Dic[5] = range(58,63)
98 	absentAACDR2Dic[6] = range(58,62)
99 	absentAACDR2Dic[7] = range(59,62)
00 	absentAACDR2Dic[8] = range(59,61)
01 	absentAACDR2Dic[9] = [60]
02 
03 	absentAA = [len(IDlist)] * (AALength-1)
04 	for k, cdr1Length in cdr1LengthDic.iteritems():
05 		for c in absentAACDR1Dic[cdr1Length]:
06 			absentAA[c] -= 1
07 
08 	for k, cdr2Length in cdr2LengthDic.iteritems():
09 		for c in absentAACDR2Dic[cdr2Length]:
10 			absentAA[c] -= 1
11 
12 
13 	aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/absent_aa_id.txt"
14 	with open(aa_mutations_by_id_file, 'w') as o:
15 		o.write("ID\tcdr1length\tcdr2length\tbest_match\t" + "\t".join([str(x) for x in range(1,AALength)]) + "\n")
16 		for ID in IDlist:
17 			absentAAbyID = [1] * (AALength-1)
18 			cdr1Length = cdr1LengthDic[ID]
19 			for c in absentAACDR1Dic[cdr1Length]:
20 				absentAAbyID[c] -= 1
21 
22 			cdr2Length = cdr2LengthDic[ID]
23 			for c in absentAACDR2Dic[cdr2Length]:
24 				absentAAbyID[c] -= 1
25 			o.write(ID + "\t" + str(cdr1Length) + "\t" + str(cdr2Length) + "\t" + genedic[ID] + "\t" + "\t".join([str(x) for x in absentAAbyID]) + "\n")
26 
27 	if linecount == 0:
28 		print "No data, exiting"
29 		with open(outfile, 'w') as o:
30 			o.write("RGYW (%)," + ("0,0,0\n" * len(genes)))
31 			o.write("WRCY (%)," + ("0,0,0\n" * len(genes)))
32 			o.write("WA (%)," + ("0,0,0\n" * len(genes)))
33 			o.write("TW (%)," + ("0,0,0\n" * len(genes)))
34 		import sys
35 
36 		sys.exit()
37 
38 	hotspotMatcher = re.compile("[actg]+,(\d+)-(\d+)\((.*)\)")
39 	RGYWCount = {}
40 	WRCYCount = {}
41 	WACount = {}
42 	TWCount = {}
43 
44 	#IDIndex = 0
45 	ataIndex = 0
46 	tatIndex = 0
47 	aggctatIndex = 0
48 	atagcctIndex = 0
49 	first = True
50 	with open(infile, 'ru') as i:
51 		for line in i:
52 			if first:
53 				linesplt = line.split("\t")
54 				ataIndex = linesplt.index("X.a.t.a")
55 				tatIndex = linesplt.index("t.a.t.")
56 				aggctatIndex = linesplt.index("X.a.g.g.c.t..a.t.")
57 				atagcctIndex = linesplt.index("X.a.t..a.g.c.c.t.")
58 				first = False
59 				continue
60 			linesplt = line.split("\t")
61 			gene = linesplt[best_matchIndex]
62 			ID = linesplt[IDIndex]
63 			RGYW = [(int(x), int(y), z) for (x, y, z) in
64 					[hotspotMatcher.match(x).groups() for x in linesplt[aggctatIndex].split("|") if x]]
65 			WRCY = [(int(x), int(y), z) for (x, y, z) in
66 					[hotspotMatcher.match(x).groups() for x in linesplt[atagcctIndex].split("|") if x]]
67 			WA = [(int(x), int(y), z) for (x, y, z) in
68 				[hotspotMatcher.match(x).groups() for x in linesplt[ataIndex].split("|") if x]]
69 			TW = [(int(x), int(y), z) for (x, y, z) in
70 				[hotspotMatcher.match(x).groups() for x in linesplt[tatIndex].split("|") if x]]
71 			RGYWCount[ID], WRCYCount[ID], WACount[ID], TWCount[ID] = 0, 0, 0, 0
72 
73 			with open(os.path.join(os.path.dirname(os.path.abspath(infile)), "RGYW.txt"), 'a') as out_handle:
74 				for hotspot in RGYW:
75 					out_handle.write("{0}\t{1}\n".format(ID, "\t".join([str(x) for x in hotspot])))
76 
77 			mutationList = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
78 			for mutation in mutationList:
79 				frm, where, to, AAfrm, AAwhere, AAto, junk = mutation
80 				mutation_in_RGYW = any(((start <= int(where) <= end) for (start, end, region) in RGYW))
81 				mutation_in_WRCY = any(((start <= int(where) <= end) for (start, end, region) in WRCY))
82 				mutation_in_WA = any(((start <= int(where) <= end) for (start, end, region) in WA))
83 				mutation_in_TW = any(((start <= int(where) <= end) for (start, end, region) in TW))
84 
85 				in_how_many_motifs = sum([mutation_in_RGYW, mutation_in_WRCY, mutation_in_WA, mutation_in_TW])
86 
87 				if in_how_many_motifs > 0:
88 					RGYWCount[ID] += (1.0 * int(mutation_in_RGYW)) / in_how_many_motifs
89 					WRCYCount[ID] += (1.0 * int(mutation_in_WRCY)) / in_how_many_motifs
90 					WACount[ID] += (1.0 * int(mutation_in_WA)) / in_how_many_motifs
91 					TWCount[ID] += (1.0 * int(mutation_in_TW)) / in_how_many_motifs
92 			
93 			mutations_in_motifs_file = os.path.join(os.path.dirname(os.path.abspath(infile)), "mutation_in_motifs.txt")
94 			if not os.path.exists(mutation_by_id_file):
95 				with open(mutations_in_motifs_file, 'w') as out_handle:
96 					out_handle.write("{0}\n".format("\t".join([
97 						"Sequence.ID",
98 						"mutation_position",
99 						"region",
00 						"from_nt",
01 						"to_nt",
02 						"mutation_position_AA",
03 						"from_AA",
04 						"to_AA",
05 						"motif",
06 						"motif_start_nt",
07 						"motif_end_nt",
08 						"rest"
09 					])))
10 
11 			with open(mutations_in_motifs_file, 'a') as out_handle:
12 				motif_dic = {"RGYW": RGYW, "WRCY": WRCY, "WA": WA, "TW": TW}
13 				for mutation in mutationList:
14 					frm, where, to, AAfrm, AAwhere, AAto, junk = mutation
15 					for motif in motif_dic.keys():
16 							
17 						for start, end, region in motif_dic[motif]:
18 							if start <= int(where) <= end:
19 								out_handle.write("{0}\n".format(
20 									"\t".join([
21 										ID,
22 										where,
23 										region,
24 										frm,
25 										to,
26 										str(AAwhere),
27 										str(AAfrm),
28 										str(AAto),
29 										motif,
30 										str(start),
31 										str(end),
32 										str(junk)
33 									])
34 								))
35 
36 
37 
38 	def mean(lst):
39 		return (float(sum(lst)) / len(lst)) if len(lst) > 0 else 0.0
40 
41 
42 	def median(lst):
43 		lst = sorted(lst)
44 		l = len(lst)
45 		if l == 0:
46 			return 0
47 		if l == 1:
48 			return lst[0]
49 			
50 		l = int(l / 2)
51 		
52 		if len(lst) % 2 == 0:
53 			return float(lst[l] + lst[(l - 1)]) / 2.0
54 		else:
55 			return lst[l]
56 
57 	funcs = {"mean": mean, "median": median, "sum": sum}
58 
59 	directory = outfile[:outfile.rfind("/") + 1]
60 	value = 0
61 	valuedic = dict()
62 
63 	for fname in funcs.keys():
64 		for gene in genes:
65 			with open(directory + gene + "_" + fname + "_value.txt", 'r') as v:
66 				valuedic[gene + "_" + fname] = float(v.readlines()[0].rstrip())
67 		with open(directory + "all_" + fname + "_value.txt", 'r') as v:
68 			valuedic["total_" + fname] = float(v.readlines()[0].rstrip())
69 		
70 
71 	def get_xyz(lst, gene, f, fname):
72 		x = round(round(f(lst), 1))
73 		y = valuedic[gene + "_" + fname]
74 		z = str(round(x / float(y) * 100, 1)) if y != 0 else "0"
75 		return (str(x), str(y), z)
76 
77 	dic = {"RGYW": RGYWCount, "WRCY": WRCYCount, "WA": WACount, "TW": TWCount}
78 	arr = ["RGYW", "WRCY", "WA", "TW"]
79 
80 	for fname in funcs.keys():
81 		func = funcs[fname]
82 		foutfile = outfile[:outfile.rindex("/")] + "/hotspot_analysis_" + fname + ".txt"
83 		with open(foutfile, 'w') as o:
84 			for typ in arr:
85 				o.write(typ + " (%)")
86 				curr = dic[typ]
87 				for gene in genes:
88 					geneMatcher = geneMatchers[gene]
89 					if valuedic[gene + "_" + fname] is 0:
90 						o.write(",0,0,0")
91 					else:
92 						x, y, z = get_xyz([curr[x] for x in [y for y, z in genedic.iteritems() if geneMatcher.match(z)]], gene, func, fname)
93 						o.write("," + x + "," + y + "," + z)
94 				x, y, z = get_xyz([y for x, y in curr.iteritems() if not genedic[x].startswith("unmatched")], "total", func, fname)
95 				#x, y, z = get_xyz([y for x, y in curr.iteritems()], "total", func, fname)
96 				o.write("," + x + "," + y + "," + z + "\n")
97 
98 
99 	# for testing
00 	seq_motif_file = outfile[:outfile.rindex("/")] + "/motif_per_seq.txt"
01 	with open(seq_motif_file, 'w') as o:
02 		o.write("ID\tRGYW\tWRCY\tWA\tTW\n")
03 		for ID in IDlist:
04 			#o.write(ID + "\t" + str(round(RGYWCount[ID], 2)) + "\t" + str(round(WRCYCount[ID], 2)) + "\t" + str(round(WACount[ID], 2)) + "\t" + str(round(TWCount[ID], 2)) + "\n")
05 			o.write(ID + "\t" + str(RGYWCount[ID]) + "\t" + str(WRCYCount[ID]) + "\t" + str(WACount[ID]) + "\t" + str(TWCount[ID]) + "\n")
06 
07 if __name__ == "__main__":
08 	main()