annotate shm_csr.py @ 52:22dddabe3637 draft

Uploaded
author davidvanzessen
date Tue, 23 May 2017 08:32:58 -0400
parents c5295dd10dfc
children aa8d37bd1930
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
1 import argparse
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
2 import logging
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
3 import sys
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
4 import os
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
5 import re
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
6
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
7 from collections import defaultdict
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
8
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
9 def main():
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
10 parser = argparse.ArgumentParser()
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
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")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
12 parser.add_argument("--genes", help="The genes available in the 'best_match' column")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
13 parser.add_argument("--empty_region_filter", help="Where does the sequence start?", choices=['leader', 'FR1', 'CDR1', 'FR2'])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
14 parser.add_argument("--output", help="Output file")
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
15
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
16 args = parser.parse_args()
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
17
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
18 infile = args.input
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
19 genes = str(args.genes).split(",")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
20 empty_region_filter = args.empty_region_filter
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
21 outfile = args.output
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
22
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
23 genedic = dict()
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
24
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
25 mutationdic = dict()
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
26 mutationMatcher = re.compile("^(.)(\d+).(.),?(.)?(\d+)?.?(.)?(.?.?.?.?.?)?")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
27 NAMatchResult = (None, None, None, None, None, None, '')
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
28 geneMatchers = {gene: re.compile("^" + gene + ".*") for gene in genes}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
29 linecount = 0
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
30
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
31 IDIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
32 best_matchIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
33 fr1Index = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
34 cdr1Index = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
35 fr2Index = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
36 cdr2Index = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
37 fr3Index = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
38 first = True
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
39 IDlist = []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
40 mutationList = []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
41 mutationListByID = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
42 cdr1LengthDic = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
43 cdr2LengthDic = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
44
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
45 fr1LengthDict = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
46 fr2LengthDict = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
47 fr3LengthDict = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
48
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
49 cdr1LengthIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
50 cdr2LengthIndex = 0
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
51
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
52 fr1SeqIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
53 fr2SeqIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
54 fr3SeqIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
55
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
56 tandem_sum_by_class = defaultdict(int)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
57 expected_tandem_sum_by_class = defaultdict(float)
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
58
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
59 with open(infile, 'ru') as i:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
60 for line in i:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
61 if first:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
62 linesplt = line.split("\t")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
63 IDIndex = linesplt.index("Sequence.ID")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
64 best_matchIndex = linesplt.index("best_match")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
65 fr1Index = linesplt.index("FR1.IMGT")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
66 cdr1Index = linesplt.index("CDR1.IMGT")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
67 fr2Index = linesplt.index("FR2.IMGT")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
68 cdr2Index = linesplt.index("CDR2.IMGT")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
69 fr3Index = linesplt.index("FR3.IMGT")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
70 cdr1LengthIndex = linesplt.index("CDR1.IMGT.seq")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
71 cdr2LengthIndex = linesplt.index("CDR2.IMGT.seq")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
72 fr1SeqIndex = linesplt.index("FR1.IMGT.seq")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
73 fr2SeqIndex = linesplt.index("FR2.IMGT.seq")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
74 fr3SeqIndex = linesplt.index("FR3.IMGT.seq")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
75 first = False
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
76 continue
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
77 linecount += 1
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
78 linesplt = line.split("\t")
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
79 ID = linesplt[IDIndex]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
80 genedic[ID] = linesplt[best_matchIndex]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
81 try:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
82 mutationdic[ID + "_FR1"] = [mutationMatcher.match(x).groups() for x in linesplt[fr1Index].split("|") if x] if (linesplt[fr1Index] != "NA" and empty_region_filter == "leader") else []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
83 mutationdic[ID + "_CDR1"] = [mutationMatcher.match(x).groups() for x in linesplt[cdr1Index].split("|") if x] if (linesplt[cdr1Index] != "NA" and empty_region_filter in ["leader", "FR1"]) else []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
84 mutationdic[ID + "_FR2"] = [mutationMatcher.match(x).groups() for x in linesplt[fr2Index].split("|") if x] if (linesplt[fr2Index] != "NA" and empty_region_filter in ["leader", "FR1", "CDR1"]) else []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
85 mutationdic[ID + "_CDR2"] = [mutationMatcher.match(x).groups() for x in linesplt[cdr2Index].split("|") if x] if (linesplt[cdr2Index] != "NA") else []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
86 mutationdic[ID + "_FR2-CDR2"] = mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
87 mutationdic[ID + "_FR3"] = [mutationMatcher.match(x).groups() for x in linesplt[fr3Index].split("|") if x] if linesplt[fr3Index] != "NA" else []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
88 except Exception as e:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
89 print "Something went wrong while processing this line:"
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
90 print linesplt
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
91 print linecount
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
92 print e
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
93 mutationList += mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
94 mutationListByID[ID] = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
95
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
96 cdr1Length = len(linesplt[cdr1LengthIndex])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
97 cdr2Length = len(linesplt[cdr2LengthIndex])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
98
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
99 #print linesplt[fr2SeqIndex]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
100 fr1Length = len(linesplt[fr1SeqIndex]) if empty_region_filter == "leader" else 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
101 fr2Length = len(linesplt[fr2SeqIndex]) if empty_region_filter in ["leader", "FR1", "CDR1"] else 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
102 fr3Length = len(linesplt[fr3SeqIndex])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
103
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
104 cdr1LengthDic[ID] = cdr1Length
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
105 cdr2LengthDic[ID] = cdr2Length
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
106
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
107 fr1LengthDict[ID] = fr1Length
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
108 fr2LengthDict[ID] = fr2Length
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
109 fr3LengthDict[ID] = fr3Length
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
110
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
111 IDlist += [ID]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
112
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
113
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
114 #tandem mutation stuff
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
115 tandem_frequency = defaultdict(int)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
116 mutation_frequency = defaultdict(int)
48
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
117
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
118 mutations_by_id_dic = {}
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
119 first = True
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
120 mutation_by_id_file = os.path.join(os.path.dirname(outfile), "mutation_by_id.txt")
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
121 with open(mutation_by_id_file, 'r') as mutation_by_id:
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
122 for l in mutation_by_id:
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
123 if first:
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
124 first = False
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
125 continue
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
126 splt = l.split("\t")
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
127 mutations_by_id_dic[splt[0]] = int(splt[1])
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
128
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
129 tandem_file = os.path.join(os.path.dirname(outfile), "tandems_by_id.txt")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
130 with open(tandem_file, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
131 highest_tandem_length = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
132
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
133 o.write("Sequence.ID\tnumber_of_mutations\tnumber_of_tandems\tregion_length\texpected_tandems\tlongest_tandem\ttandems\n")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
134 for ID in IDlist:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
135 mutations = mutationListByID[ID]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
136 if len(mutations) == 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
137 continue
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
138 last_mut = max(mutations, key=lambda x: int(x[1]))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
139
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
140 last_mut_pos = int(last_mut[1])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
141
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
142 mut_positions = [False] * (last_mut_pos + 1)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
143
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
144 for mutation in mutations:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
145 frm, where, to, frmAA, whereAA, toAA, thing = mutation
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
146 where = int(where)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
147 mut_positions[where] = True
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
148
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
149 tandem_muts = []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
150 tandem_start = -1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
151 tandem_length = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
152 for i in range(len(mut_positions)):
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
153 if mut_positions[i]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
154 if tandem_start == -1:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
155 tandem_start = i
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
156 tandem_length += 1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
157 #print "".join(["1" if x else "0" for x in mut_positions[:i+1]])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
158 else:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
159 if tandem_length > 1:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
160 tandem_muts.append((tandem_start, tandem_length))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
161 #print "{0}{1} {2}:{3}".format(" " * (i - tandem_length), "^" * tandem_length, tandem_start, tandem_length)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
162 tandem_start = -1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
163 tandem_length = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
164 if tandem_length > 1: # if the sequence ends with a tandem mutation
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
165 tandem_muts.append((tandem_start, tandem_length))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
166
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
167 if len(tandem_muts) > 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
168 if highest_tandem_length < len(tandem_muts):
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
169 highest_tandem_length = len(tandem_muts)
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
170
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
171 region_length = fr1LengthDict[ID] + cdr1LengthDic[ID] + fr2LengthDict[ID] + cdr2LengthDic[ID] + fr3LengthDict[ID]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
172 longest_tandem = max(tandem_muts, key=lambda x: x[1]) if len(tandem_muts) else (0, 0)
48
c5295dd10dfc Uploaded
davidvanzessen
parents: 47
diff changeset
173 num_mutations = mutations_by_id_dic[ID] # len(mutations)
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
174 f_num_mutations = float(num_mutations)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
175 num_tandem_muts = len(tandem_muts)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
176 expected_tandem_muts = f_num_mutations * (f_num_mutations - 1.0) / float(region_length)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
177 o.write("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\n".format(ID,
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
178 str(num_mutations),
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
179 str(num_tandem_muts),
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
180 str(region_length),
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
181 str(round(expected_tandem_muts, 2)),
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
182 str(longest_tandem[1]),
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
183 str(tandem_muts)))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
184 gene = genedic[ID]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
185 if gene.find("unmatched") == -1:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
186 tandem_sum_by_class[gene] += num_tandem_muts
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
187 expected_tandem_sum_by_class[gene] += expected_tandem_muts
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
188
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
189 tandem_sum_by_class["all"] += num_tandem_muts
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
190 expected_tandem_sum_by_class["all"] += expected_tandem_muts
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
191
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
192 gene = gene[:3]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
193 if gene in ["IGA", "IGG"]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
194 tandem_sum_by_class[gene] += num_tandem_muts
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
195 expected_tandem_sum_by_class[gene] += expected_tandem_muts
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
196 else:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
197 tandem_sum_by_class["unmatched"] += num_tandem_muts
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
198 expected_tandem_sum_by_class["unmatched"] += expected_tandem_muts
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
199
40
ca2512e1e3ab Uploaded
davidvanzessen
parents: 26
diff changeset
200
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
201 for tandem_mut in tandem_muts:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
202 tandem_frequency[str(tandem_mut[1])] += 1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
203 #print "\t".join([ID, str(len(tandem_muts)), str(longest_tandem[1]) , str(tandem_muts)])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
204
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
205 tandem_freq_file = os.path.join(os.path.dirname(outfile), "tandem_frequency.txt")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
206 with open(tandem_freq_file, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
207 for frq in sorted([int(x) for x in tandem_frequency.keys()]):
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
208 o.write("{0}\t{1}\n".format(frq, tandem_frequency[str(frq)]))
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
209
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
210 tandem_row = []
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
211 genes_extra = list(genes)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
212 genes_extra.append("all")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
213 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]):
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
214 if y != 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
215 tandem_row += [x, round(y, 2), round(x / y, 2)]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
216 else:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
217 tandem_row += [x, round(y, 2), 0]
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
218
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
219 tandem_freq_file = os.path.join(os.path.dirname(outfile), "shm_overview_tandem_row.txt")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
220 with open(tandem_freq_file, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
221 o.write("Tandems/Expected (ratio),{0}\n".format(",".join([str(x) for x in tandem_row])))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
222
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
223 #print mutationList, linecount
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
224
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
225 AALength = (int(max(mutationList, key=lambda i: int(i[4]) if i[4] else 0)[4]) + 1) # [4] is the position of the AA mutation, None if silent
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
226 if AALength < 60:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
227 AALength = 64
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
228
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
229 AA_mutation = [0] * AALength
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
230 AA_mutation_dic = {"IGA": AA_mutation[:], "IGG": AA_mutation[:], "IGM": AA_mutation[:], "IGE": AA_mutation[:], "unm": AA_mutation[:], "all": AA_mutation[:]}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
231 AA_mutation_empty = AA_mutation[:]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
232
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
233 aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/aa_id_mutations.txt"
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
234 with open(aa_mutations_by_id_file, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
235 o.write("ID\tbest_match\t" + "\t".join([str(x) for x in range(1,AALength)]) + "\n")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
236 for ID in mutationListByID.keys():
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
237 AA_mutation_for_ID = AA_mutation_empty[:]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
238 for mutation in mutationListByID[ID]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
239 if mutation[4]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
240 AA_mutation_position = int(mutation[4])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
241 AA_mutation[AA_mutation_position] += 1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
242 AA_mutation_for_ID[AA_mutation_position] += 1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
243 clss = genedic[ID][:3]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
244 AA_mutation_dic[clss][AA_mutation_position] += 1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
245 o.write(ID + "\t" + genedic[ID] + "\t" + "\t".join([str(x) for x in AA_mutation_for_ID[1:]]) + "\n")
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
246
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
247
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
248
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
249 #absent AA stuff
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
250 absentAACDR1Dic = defaultdict(list)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
251 absentAACDR1Dic[5] = range(29,36)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
252 absentAACDR1Dic[6] = range(29,35)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
253 absentAACDR1Dic[7] = range(30,35)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
254 absentAACDR1Dic[8] = range(30,34)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
255 absentAACDR1Dic[9] = range(31,34)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
256 absentAACDR1Dic[10] = range(31,33)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
257 absentAACDR1Dic[11] = [32]
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
258
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
259 absentAACDR2Dic = defaultdict(list)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
260 absentAACDR2Dic[0] = range(55,65)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
261 absentAACDR2Dic[1] = range(56,65)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
262 absentAACDR2Dic[2] = range(56,64)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
263 absentAACDR2Dic[3] = range(57,64)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
264 absentAACDR2Dic[4] = range(57,63)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
265 absentAACDR2Dic[5] = range(58,63)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
266 absentAACDR2Dic[6] = range(58,62)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
267 absentAACDR2Dic[7] = range(59,62)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
268 absentAACDR2Dic[8] = range(59,61)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
269 absentAACDR2Dic[9] = [60]
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
270
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
271 absentAA = [len(IDlist)] * (AALength-1)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
272 for k, cdr1Length in cdr1LengthDic.iteritems():
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
273 for c in absentAACDR1Dic[cdr1Length]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
274 absentAA[c] -= 1
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
275
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
276 for k, cdr2Length in cdr2LengthDic.iteritems():
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
277 for c in absentAACDR2Dic[cdr2Length]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
278 absentAA[c] -= 1
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
279
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
280
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
281 aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/absent_aa_id.txt"
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
282 with open(aa_mutations_by_id_file, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
283 o.write("ID\tcdr1length\tcdr2length\tbest_match\t" + "\t".join([str(x) for x in range(1,AALength)]) + "\n")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
284 for ID in IDlist:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
285 absentAAbyID = [1] * (AALength-1)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
286 cdr1Length = cdr1LengthDic[ID]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
287 for c in absentAACDR1Dic[cdr1Length]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
288 absentAAbyID[c] -= 1
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
289
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
290 cdr2Length = cdr2LengthDic[ID]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
291 for c in absentAACDR2Dic[cdr2Length]:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
292 absentAAbyID[c] -= 1
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
293 o.write(ID + "\t" + str(cdr1Length) + "\t" + str(cdr2Length) + "\t" + genedic[ID] + "\t" + "\t".join([str(x) for x in absentAAbyID]) + "\n")
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
294
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
295 if linecount == 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
296 print "No data, exiting"
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
297 with open(outfile, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
298 o.write("RGYW (%)," + ("0,0,0\n" * len(genes)))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
299 o.write("WRCY (%)," + ("0,0,0\n" * len(genes)))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
300 o.write("WA (%)," + ("0,0,0\n" * len(genes)))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
301 o.write("TW (%)," + ("0,0,0\n" * len(genes)))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
302 import sys
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
303
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
304 sys.exit()
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
305
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
306 hotspotMatcher = re.compile("[actg]+,(\d+)-(\d+)\((.*)\)")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
307 RGYWCount = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
308 WRCYCount = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
309 WACount = {}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
310 TWCount = {}
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
311
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
312 #IDIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
313 ataIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
314 tatIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
315 aggctatIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
316 atagcctIndex = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
317 first = True
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
318 with open(infile, 'ru') as i:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
319 for line in i:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
320 if first:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
321 linesplt = line.split("\t")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
322 ataIndex = linesplt.index("X.a.t.a")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
323 tatIndex = linesplt.index("t.a.t.")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
324 aggctatIndex = linesplt.index("X.a.g.g.c.t..a.t.")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
325 atagcctIndex = linesplt.index("X.a.t..a.g.c.c.t.")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
326 first = False
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
327 continue
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
328 linesplt = line.split("\t")
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
329 gene = linesplt[best_matchIndex]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
330 ID = linesplt[IDIndex]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
331 RGYW = [(int(x), int(y), z) for (x, y, z) in
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
332 [hotspotMatcher.match(x).groups() for x in linesplt[aggctatIndex].split("|") if x]]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
333 WRCY = [(int(x), int(y), z) for (x, y, z) in
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
334 [hotspotMatcher.match(x).groups() for x in linesplt[atagcctIndex].split("|") if x]]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
335 WA = [(int(x), int(y), z) for (x, y, z) in
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
336 [hotspotMatcher.match(x).groups() for x in linesplt[ataIndex].split("|") if x]]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
337 TW = [(int(x), int(y), z) for (x, y, z) in
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
338 [hotspotMatcher.match(x).groups() for x in linesplt[tatIndex].split("|") if x]]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
339 RGYWCount[ID], WRCYCount[ID], WACount[ID], TWCount[ID] = 0, 0, 0, 0
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
340
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
341 mutationList = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
342 for mutation in mutationList:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
343 frm, where, to, AAfrm, AAwhere, AAto, junk = mutation
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
344 mutation_in_RGYW = any([(start <= int(where) <= end) for (start, end, region) in RGYW])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
345 mutation_in_WRCY = any([(start <= int(where) <= end) for (start, end, region) in WRCY])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
346 mutation_in_WA = any([(start <= int(where) <= end) for (start, end, region) in WA])
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
347 mutation_in_TW = any([(start <= int(where) <= end) for (start, end, region) in TW])
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
348
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
349 in_how_many_motifs = sum([mutation_in_RGYW, mutation_in_WRCY, mutation_in_WA, mutation_in_TW])
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
350
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
351 if in_how_many_motifs > 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
352 RGYWCount[ID] += (1.0 * int(mutation_in_RGYW)) / in_how_many_motifs
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
353 WRCYCount[ID] += (1.0 * int(mutation_in_WRCY)) / in_how_many_motifs
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
354 WACount[ID] += (1.0 * int(mutation_in_WA)) / in_how_many_motifs
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
355 TWCount[ID] += (1.0 * int(mutation_in_TW)) / in_how_many_motifs
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
356
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
357
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
358 def mean(lst):
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
359 return (float(sum(lst)) / len(lst)) if len(lst) > 0 else 0.0
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
360
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
361
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
362 def median(lst):
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
363 lst = sorted(lst)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
364 l = len(lst)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
365 if l == 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
366 return 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
367 if l == 1:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
368 return lst[0]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
369
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
370 l = int(l / 2)
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
371
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
372 if len(lst) % 2 == 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
373 return float(lst[l] + lst[(l - 1)]) / 2.0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
374 else:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
375 return lst[l]
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
376
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
377 funcs = {"mean": mean, "median": median, "sum": sum}
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
378
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
379 directory = outfile[:outfile.rfind("/") + 1]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
380 value = 0
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
381 valuedic = dict()
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
382
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
383 for fname in funcs.keys():
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
384 for gene in genes:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
385 with open(directory + gene + "_" + fname + "_value.txt", 'r') as v:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
386 valuedic[gene + "_" + fname] = float(v.readlines()[0].rstrip())
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
387 with open(directory + "all_" + fname + "_value.txt", 'r') as v:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
388 valuedic["total_" + fname] = float(v.readlines()[0].rstrip())
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
389
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
390
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
391 def get_xyz(lst, gene, f, fname):
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
392 x = round(round(f(lst), 1))
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
393 y = valuedic[gene + "_" + fname]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
394 z = str(round(x / float(y) * 100, 1)) if y != 0 else "0"
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
395 return (str(x), str(y), z)
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
396
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
397 dic = {"RGYW": RGYWCount, "WRCY": WRCYCount, "WA": WACount, "TW": TWCount}
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
398 arr = ["RGYW", "WRCY", "WA", "TW"]
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
399
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
400 for fname in funcs.keys():
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
401 func = funcs[fname]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
402 foutfile = outfile[:outfile.rindex("/")] + "/hotspot_analysis_" + fname + ".txt"
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
403 with open(foutfile, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
404 for typ in arr:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
405 o.write(typ + " (%)")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
406 curr = dic[typ]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
407 for gene in genes:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
408 geneMatcher = geneMatchers[gene]
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
409 if valuedic[gene + "_" + fname] is 0:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
410 o.write(",0,0,0")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
411 else:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
412 x, y, z = get_xyz([curr[x] for x in [y for y, z in genedic.iteritems() if geneMatcher.match(z)]], gene, func, fname)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
413 o.write("," + x + "," + y + "," + z)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
414 x, y, z = get_xyz([y for x, y in curr.iteritems() if not genedic[x].startswith("unmatched")], "total", func, fname)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
415 #x, y, z = get_xyz([y for x, y in curr.iteritems()], "total", func, fname)
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
416 o.write("," + x + "," + y + "," + z + "\n")
0
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
417
c33d93683a09 Uploaded
davidvanzessen
parents:
diff changeset
418
47
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
419 # for testing
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
420 seq_motif_file = outfile[:outfile.rindex("/")] + "/motif_per_seq.txt"
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
421 with open(seq_motif_file, 'w') as o:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
422 o.write("ID\tRGYW\tWRCY\tWA\tTW\n")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
423 for ID in IDlist:
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
424 #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")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
425 o.write(ID + "\t" + str(RGYWCount[ID]) + "\t" + str(WRCYCount[ID]) + "\t" + str(WACount[ID]) + "\t" + str(TWCount[ID]) + "\n")
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
426
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
427 if __name__ == "__main__":
64711f461c8e Uploaded
davidvanzessen
parents: 43
diff changeset
428 main()