Mercurial > repos > davidvanzessen > mutation_analysis

comparison mutation_analysis.py @ 49:5c6b9e99d576 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Wed, 18 Nov 2015 05:55:04 -0500
parents 4b1bab1a9ad2
children 7290a88ea202
comparison
equal deleted inserted replaced
48:d09b1bdfd388 49:5c6b9e99d576
1 from collections import defaultdict
1 import re 2 import re
2 import argparse 3 import argparse
3 4
4 parser = argparse.ArgumentParser() 5 parser = argparse.ArgumentParser()
5 parser.add_argument("--input", 6 parser.add_argument("--input",
6 help="The '7_V-REGION-mutation-and-AA-change-table' and '10_V-REGION-mutation-hotspots' merged together, with an added 'best_match' annotation") 7 help="The '7_V-REGION-mutation-and-AA-change-table' and '10_V-REGION-mutation-hotspots' merged together, with an added 'best_match' annotation")
7 parser.add_argument("--genes", help="The genes available in the 'best_match' column") 8 parser.add_argument("--genes", help="The genes available in the 'best_match' column")
8 parser.add_argument("--includefr1", help="The genes available in the 'best_match' column") 9 parser.add_argument("--includefr1", help="The genes available in the 'best_match' column")
9 parser.add_argument("--output", help="Output file") 10 parser.add_argument("--output", help="Output file")
10 11
11 args = parser.parse_args() 12 args = parser.parse_args()
31 fr3Index = 0 32 fr3Index = 0
32 first = True 33 first = True
33 IDlist = [] 34 IDlist = []
34 mutationList = [] 35 mutationList = []
35 mutationListByID = {} 36 mutationListByID = {}
37 cdr1LengthDic = {}
38 cdr2LengthDic = {}
36 39
37 with open(infile, 'r') as i: 40 with open(infile, 'r') as i:
38 for line in i: 41 for line in i:
39 if first: 42 if first:
40 linesplt = line.split("\t") 43 linesplt = line.split("\t")
43 fr1Index = linesplt.index("FR1.IMGT") 46 fr1Index = linesplt.index("FR1.IMGT")
44 cdr1Index = linesplt.index("CDR1.IMGT") 47 cdr1Index = linesplt.index("CDR1.IMGT")
45 fr2Index = linesplt.index("FR2.IMGT") 48 fr2Index = linesplt.index("FR2.IMGT")
46 cdr2Index = linesplt.index("CDR2.IMGT") 49 cdr2Index = linesplt.index("CDR2.IMGT")
47 fr3Index = linesplt.index("FR3.IMGT") 50 fr3Index = linesplt.index("FR3.IMGT")
51 cdr1LengthIndex = linesplt.index("CDR1.IMGT.Nb.of.nucleotides")
52 cdr2LengthIndex = linesplt.index("CDR2.IMGT.Nb.of.nucleotides")
48 first = False 53 first = False
49 continue 54 continue
50 linecount += 1 55 linecount += 1
51 linesplt = line.split("\t") 56 linesplt = line.split("\t")
52 ID = linesplt[IDIndex] 57 ID = linesplt[IDIndex]
60 mutationdic[ID + "_FR3"] = [mutationMatcher.match(x).groups() for x in linesplt[fr3Index].split("|") if x] 65 mutationdic[ID + "_FR3"] = [mutationMatcher.match(x).groups() for x in linesplt[fr3Index].split("|") if x]
61 66
62 mutationList += mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"] 67 mutationList += mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
63 mutationListByID[ID] = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"] 68 mutationListByID[ID] = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
64 69
70 cdr1Length = linesplt[cdr1LengthIndex]
71 cdr2Length = linesplt[cdr2LengthIndex]
72
73 cdr1LengthDic[ID] = int(cdr1Length) / 3
74 cdr2LengthDic[ID] = int(cdr2Length) / 3
75
65 IDlist += [ID] 76 IDlist += [ID]
66 77
67 AA_mutation = [0] * (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 78 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
79
80 AA_mutation = [0] * AALength
68 AA_mutation_empty = AA_mutation[:] 81 AA_mutation_empty = AA_mutation[:]
69 82
70 aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/aa_id_mutations.txt" 83 aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/aa_id_mutations.txt"
71 with open(aa_mutations_by_id_file, 'w') as o: 84 with open(aa_mutations_by_id_file, 'w') as o:
72 for ID in mutationListByID.keys(): 85 for ID in mutationListByID.keys():
73 AA_mutation_for_ID = AA_mutation_empty[:] 86 AA_mutation_for_ID = AA_mutation_empty[:]
74 for mutation in mutationListByID[ID]: 87 for mutation in mutationListByID[ID]:
75 if mutation[4]: 88 if mutation[4]:
76 AA_mutation[int(mutation[4])] += 1 89 AA_mutation[int(mutation[4])] += 1
77 AA_mutation_for_ID[int(mutation[4])] += 1 90 AA_mutation_for_ID[int(mutation[4])] += 1
78 o.write(ID + "\t" + "\t".join([str(x) for x in AA_mutation_for_ID]) + "\n") 91 o.write(ID + "\t" + "\t".join([str(x) for x in AA_mutation_for_ID[1:]]) + "\n")
79 92
80 93
81 94
82 #for mutation in mutationList: 95 #absent AA stuff
83 # if mutation[4]: # if non silent mutation 96 absentAACDR1Dic = defaultdict(list)
84 # AA_mutation[int(mutation[4])] += 1 97 absentAACDR1Dic[5] = range(29,36)
98 absentAACDR1Dic[6] = range(29,35)
99 absentAACDR1Dic[7] = range(30,35)
100 absentAACDR1Dic[8] = range(30,34)
101 absentAACDR1Dic[9] = range(31,34)
102 absentAACDR1Dic[10] = range(31,33)
103 absentAACDR1Dic[11] = [32]
104
105 absentAACDR2Dic = defaultdict(list)
106 absentAACDR2Dic[0] = range(55,65)
107 absentAACDR2Dic[1] = range(56,65)
108 absentAACDR2Dic[2] = range(56,64)
109 absentAACDR2Dic[3] = range(57,64)
110 absentAACDR2Dic[4] = range(57,63)
111 absentAACDR2Dic[5] = range(58,63)
112 absentAACDR2Dic[6] = range(58,62)
113 absentAACDR2Dic[7] = range(59,62)
114 absentAACDR2Dic[8] = range(59,61)
115 absentAACDR2Dic[9] = [60]
116
117 absentAA = [len(IDlist)] * (AALength-1)
118 for k, cdr1Length in cdr1LengthDic.iteritems():
119 for c in absentAACDR1Dic[cdr1Length]:
120 absentAA[c] -= 1
121
122 for k, cdr2Length in cdr2LengthDic.iteritems():
123 for c in absentAACDR2Dic[cdr2Length]:
124 absentAA[c] -= 1
125
126
127 aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/absent_aa_id.txt"
128 with open(aa_mutations_by_id_file, 'w') as o:
129 o.write("ID\tcdr1length\tcdr2length\t" + "\t".join([str(x) for x in range(1,AALength-1)]) + "\n")
130 for ID in IDlist:
131 absentAAbyID = [1] * (AALength-1)
132 cdr1Length = cdr1LengthDic[ID]
133 for c in absentAACDR1Dic[cdr1Length]:
134 absentAAbyID[c] -= 1
135
136 cdr2Length = cdr2LengthDic[ID]
137 for c in absentAACDR2Dic[cdr2Length]:
138 absentAAbyID[c] -= 1
139 o.write(ID + "\t" + str(cdr1Length) + "\t" + str(cdr2Length) + "\t" + "\t".join([str(x) for x in absentAAbyID]) + "\n")
140
141
85 142
86 aa_mutations_file = outfile[:outfile.rindex("/")] + "/aa_mutations.txt" 143 aa_mutations_file = outfile[:outfile.rindex("/")] + "/aa_mutations.txt"
87 with open(aa_mutations_file, 'w') as o: 144 with open(aa_mutations_file, 'w') as o:
88 o.write(",".join([str(x) for x in AA_mutation]) + "\n") 145 o.write("row.name\t" + "\t".join([str(x) for x in range(1, AALength-1)]) + "\n")
146 o.write("mutations.at.position\t" + "\t".join([str(x) for x in AA_mutation[1:]]) + "\n")
147 o.write("AA.at.position\t" + "\t".join([str(x) for x in absentAA]) + "\n")
89 148
90 if linecount == 0: 149 if linecount == 0:
91 print "No data, exiting" 150 print "No data, exiting"
92 with open(outfile, 'w') as o: 151 with open(outfile, 'w') as o:
93 o.write("RGYW (%)," + ("0,0,0\n" * len(genes))) 152 o.write("RGYW (%)," + ("0,0,0\n" * len(genes)))
94 o.write("WRCY (%)," + ("0,0,0\n" * len(genes))) 153 o.write("WRCY (%)," + ("0,0,0\n" * len(genes)))
95 o.write("WA (%)," + ("0,0,0\n" * len(genes))) 154 o.write("WA (%)," + ("0,0,0\n" * len(genes)))
96 o.write("TW (%)," + ("0,0,0\n" * len(genes))) 155 o.write("TW (%)," + ("0,0,0\n" * len(genes)))
97 import sys 156 import sys
98 157
99 sys.exit() 158 sys.exit()
100 159
101 hotspotMatcher = re.compile("[actg]+,(\d+)-(\d+)\((.*)\)") 160 hotspotMatcher = re.compile("[actg]+,(\d+)-(\d+)\((.*)\)")
102 RGYWCount = {g: 0 for g in genes} 161 RGYWCount = {g: 0 for g in genes}
103 WRCYCount = {g: 0 for g in genes} 162 WRCYCount = {g: 0 for g in genes}
104 WACount = {g: 0 for g in genes} 163 WACount = {g: 0 for g in genes}
109 tatIndex = 0 168 tatIndex = 0
110 aggctatIndex = 0 169 aggctatIndex = 0
111 atagcctIndex = 0 170 atagcctIndex = 0
112 first = True 171 first = True
113 with open(infile, 'r') as i: 172 with open(infile, 'r') as i:
114 for line in i: 173 for line in i:
115 if first: 174 if first:
116 linesplt = line.split("\t") 175 linesplt = line.split("\t")
117 ataIndex = linesplt.index("X.a.t.a") 176 ataIndex = linesplt.index("X.a.t.a")
118 tatIndex = linesplt.index("t.a.t.") 177 tatIndex = linesplt.index("t.a.t.")
119 aggctatIndex = linesplt.index("X.a.g.g.c.t..a.t.") 178 aggctatIndex = linesplt.index("X.a.g.g.c.t..a.t.")
120 atagcctIndex = linesplt.index("X.a.t..a.g.c.c.t.") 179 atagcctIndex = linesplt.index("X.a.t..a.g.c.c.t.")
121 first = False 180 first = False
122 continue 181 continue
123 linesplt = line.split("\t") 182 linesplt = line.split("\t")
124 gene = linesplt[best_matchIndex] 183 gene = linesplt[best_matchIndex]
125 ID = linesplt[IDIndex] 184 ID = linesplt[IDIndex]
126 RGYW = [(int(x), int(y), z) for (x, y, z) in 185 RGYW = [(int(x), int(y), z) for (x, y, z) in
127 [hotspotMatcher.match(x).groups() for x in linesplt[aggctatIndex].split("|") if x]] 186 [hotspotMatcher.match(x).groups() for x in linesplt[aggctatIndex].split("|") if x]]
128 WRCY = [(int(x), int(y), z) for (x, y, z) in 187 WRCY = [(int(x), int(y), z) for (x, y, z) in
129 [hotspotMatcher.match(x).groups() for x in linesplt[atagcctIndex].split("|") if x]] 188 [hotspotMatcher.match(x).groups() for x in linesplt[atagcctIndex].split("|") if x]]
130 WA = [(int(x), int(y), z) for (x, y, z) in 189 WA = [(int(x), int(y), z) for (x, y, z) in
131 [hotspotMatcher.match(x).groups() for x in linesplt[ataIndex].split("|") if x]] 190 [hotspotMatcher.match(x).groups() for x in linesplt[ataIndex].split("|") if x]]
132 TW = [(int(x), int(y), z) for (x, y, z) in 191 TW = [(int(x), int(y), z) for (x, y, z) in
133 [hotspotMatcher.match(x).groups() for x in linesplt[tatIndex].split("|") if x]] 192 [hotspotMatcher.match(x).groups() for x in linesplt[tatIndex].split("|") if x]]
134 RGYWCount[ID], WRCYCount[ID], WACount[ID], TWCount[ID] = 0, 0, 0, 0 193 RGYWCount[ID], WRCYCount[ID], WACount[ID], TWCount[ID] = 0, 0, 0, 0
135 194
136 mutationList = (mutationdic[ID + "_FR1"] if include_fr1 else []) + mutationdic[ID + "_CDR1"] + mutationdic[ 195 mutationList = (mutationdic[ID + "_FR1"] if include_fr1 else []) + mutationdic[ID + "_CDR1"] + mutationdic[
137 ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"] 196 ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
138 for mutation in mutationList: 197 for mutation in mutationList:
139 frm, where, to, AAfrm, AAwhere, AAto, junk = mutation 198 frm, where, to, AAfrm, AAwhere, AAto, junk = mutation
140 mutation_in_RGYW = any([(start <= int(where) <= end) for (start, end, region) in RGYW]) 199 mutation_in_RGYW = any([(start <= int(where) <= end) for (start, end, region) in RGYW])
141 mutation_in_WRCY = any([(start <= int(where) <= end) for (start, end, region) in WRCY]) 200 mutation_in_WRCY = any([(start <= int(where) <= end) for (start, end, region) in WRCY])
142 mutation_in_WA = any([(start <= int(where) <= end) for (start, end, region) in WA]) 201 mutation_in_WA = any([(start <= int(where) <= end) for (start, end, region) in WA])
143 mutation_in_TW = any([(start <= int(where) <= end) for (start, end, region) in TW]) 202 mutation_in_TW = any([(start <= int(where) <= end) for (start, end, region) in TW])
144 203
145 in_how_many_motifs = sum([mutation_in_RGYW, mutation_in_WRCY, mutation_in_WA, mutation_in_TW]) 204 in_how_many_motifs = sum([mutation_in_RGYW, mutation_in_WRCY, mutation_in_WA, mutation_in_TW])
146 205
147 if in_how_many_motifs > 0: 206 if in_how_many_motifs > 0:
148 RGYWCount[ID] += (1.0 * int(mutation_in_RGYW)) / in_how_many_motifs 207 RGYWCount[ID] += (1.0 * int(mutation_in_RGYW)) / in_how_many_motifs
149 WRCYCount[ID] += (1.0 * int(mutation_in_WRCY)) / in_how_many_motifs 208 WRCYCount[ID] += (1.0 * int(mutation_in_WRCY)) / in_how_many_motifs
150 WACount[ID] += (1.0 * int(mutation_in_WA)) / in_how_many_motifs 209 WACount[ID] += (1.0 * int(mutation_in_WA)) / in_how_many_motifs
151 TWCount[ID] += (1.0 * int(mutation_in_TW)) / in_how_many_motifs 210 TWCount[ID] += (1.0 * int(mutation_in_TW)) / in_how_many_motifs
152 211
153 directory = outfile[:outfile.rfind("/") + 1] 212 directory = outfile[:outfile.rfind("/") + 1]
154 value = 0 213 value = 0
155 valuedic = dict() 214 valuedic = dict()
156 for gene in genes: 215 for gene in genes:
157 with open(directory + gene + "_value.txt", 'r') as v: 216 with open(directory + gene + "_value.txt", 'r') as v:
158 valuedic[gene] = int(v.readlines()[0].rstrip()) 217 valuedic[gene] = int(v.readlines()[0].rstrip())
159 with open(directory + "total_value.txt", 'r') as v: 218 with open(directory + "total_value.txt", 'r') as v:
160 valuedic["total"] = int(v.readlines()[0].rstrip()) 219 valuedic["total"] = int(v.readlines()[0].rstrip())
161 220
162 dic = {"RGYW": RGYWCount, "WRCY": WRCYCount, "WA": WACount, "TW": TWCount} 221 dic = {"RGYW": RGYWCount, "WRCY": WRCYCount, "WA": WACount, "TW": TWCount}
163 arr = ["RGYW", "WRCY", "WA", "TW"] 222 arr = ["RGYW", "WRCY", "WA", "TW"]
164 with open(outfile, 'w') as o: 223 with open(outfile, 'w') as o:
165 for typ in arr: 224 for typ in arr:
166 o.write(typ + " (%)") 225 o.write(typ + " (%)")
167 curr = dic[typ] 226 curr = dic[typ]
168 for gene in genes: 227 for gene in genes:
169 geneMatcher = re.compile(".*" + gene + ".*") 228 geneMatcher = re.compile(".*" + gene + ".*")
170 if valuedic[gene] is 0: 229 if valuedic[gene] is 0:
171 o.write(",0,0,0") 230 o.write(",0,0,0")
172 else: 231 else:
173 x = int(round(sum([curr[x] for x in [y for y, z in genedic.iteritems() if geneMatcher.match(z)]]))) 232 x = int(round(sum([curr[x] for x in [y for y, z in genedic.iteritems() if geneMatcher.match(z)]])))
174 y = valuedic[gene] 233 y = valuedic[gene]
175 z = str(round(x / float(valuedic[gene]) * 100, 1)) 234 z = str(round(x / float(valuedic[gene]) * 100, 1))
176 o.write("," + str(x) + "," + str(y) + "," + z) 235 o.write("," + str(x) + "," + str(y) + "," + z)
177 # for total 236 # for total
178 x = int(round(sum([y for x, y in curr.iteritems()]))) 237 x = int(round(sum([y for x, y in curr.iteritems()])))
179 y = valuedic["total"] 238 y = valuedic["total"]
180 z = str(round(x / float(valuedic["total"]) * 100, 1)) 239 z = str(round(x / float(valuedic["total"]) * 100, 1))
181 o.write("," + str(x) + "," + str(y) + "," + z + "\n") 240 o.write("," + str(x) + "," + str(y) + "," + z + "\n")
182 241
183 242
184 # for testing 243 # for testing
185 seq_motif_file = outfile[:outfile.rindex("/")] + "/motif_per_seq.txt" 244 seq_motif_file = outfile[:outfile.rindex("/")] + "/motif_per_seq.txt"
186 with open(seq_motif_file, 'w') as o: 245 with open(seq_motif_file, 'w') as o:
187 o.write("ID\tRGYWC\tWRCY\tWA\tTW\n") 246 o.write("ID\tRGYWC\tWRCY\tWA\tTW\n")
188 for ID in IDlist: 247 for ID in IDlist:
189 o.write(ID + "\t" + str(round(RGYWCount[ID], 2)) + "\t" + str(round(WRCYCount[ID], 2)) + "\t" + str( 248 o.write(ID + "\t" + str(round(RGYWCount[ID], 2)) + "\t" + str(round(WRCYCount[ID], 2)) + "\t" + str(
190 round(WACount[ID], 2)) + "\t" + str(round(TWCount[ID], 2)) + "\n") 249 round(WACount[ID], 2)) + "\t" + str(round(TWCount[ID], 2)) + "\n")