Mercurial > repos > davidvanzessen > shm_csr
annotate shm_csr.py @ 91:f387cc1580c6 draft
"planemo upload commit 6f5bdb4189fcc9028c90365d8edf8d1d7c1cf690"
| author | rhpvorderman |
|---|---|
| date | Wed, 02 Feb 2022 10:57:36 +0000 |
| parents | 6809c63d9161 |
| children | 385dea3c6cb5 |
| rev | line source |
|---|---|
| 81 | 1 import argparse |
| 2 import logging | |
| 3 import sys | |
| 4 import os | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
5 import typing |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
6 from typing import Optional |
| 81 | 7 |
| 8 from collections import defaultdict | |
| 9 | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
10 REGION_FILTERS = ("leader", "FR1", "CDR1", "FR2", "CDR2") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
11 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
12 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
13 class Mutation(typing.NamedTuple): |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
14 """Represent a mutation type as a tuple""" |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
15 frm: str # 'from' is a reserved python keyword. |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
16 where: int |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
17 to: str |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
18 frmAA: Optional[str] = None |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
19 whereAA: Optional[int] = None |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
20 toAA: Optional[str] = None |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
21 thing: Optional[str] = None # '(---)' or '(+-+)' etc. No idea |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
22 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
23 @classmethod |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
24 def from_string(cls, string: str): |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
25 # Complete mutation example: a88>g,I30>V(+ - +) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
26 # Only nucleotide example: g303>t |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
27 # Including codon change: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
28 # t169>g,Y57>D(- - -); Y57 tat 169-171 [ta 169-170]>D gac |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
29 # Including codon change (synonumous mutation): |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
30 # c114>t, Y38; Y38 tac 112-114 [tact 112-115]>Y tat |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
31 if ',' in string: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
32 nucleotide_change, aa_change = string.split(',', maxsplit=1) # type: str, Optional[str] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
33 else: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
34 nucleotide_change = string |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
35 aa_change = None |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
36 frm_part, to = nucleotide_change.split('>', maxsplit=1) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
37 frm = frm_part[0] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
38 where = int(frm_part[1:]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
39 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
40 if aa_change is None: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
41 return cls(frm, where, to) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
42 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
43 aa_change = aa_change.strip() |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
44 # The part after semicolon indicates the codon change. This part may |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
45 # not be present. |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
46 semi_colon_index = aa_change.find(";") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
47 if semi_colon_index == -1: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
48 codon_change = "" |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
49 else: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
50 codon_change = aa_change[semi_colon_index:] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
51 aa_change = aa_change[:semi_colon_index] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
52 change_operator_index = aa_change.find(">") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
53 if change_operator_index == -1: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
54 # Synonymous change |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
55 frmAA_part = aa_change |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
56 toAA_part = "" |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
57 else: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
58 frmAA_part, toAA_part = aa_change.split('>', maxsplit=1) # type: str, str |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
59 frmAA = frmAA_part[0] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
60 whereAA = int(frmAA_part[1:]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
61 if toAA_part: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
62 brace_start = toAA_part.index('(') |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
63 toAA = toAA_part[:brace_start] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
64 thing = toAA_part[brace_start:] + codon_change |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
65 else: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
66 # Synonymous mutation |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
67 toAA = frmAA |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
68 thing = codon_change |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
69 return cls(frm, where, to, frmAA, whereAA, toAA, thing) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
70 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
71 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
72 class Hotspot(typing.NamedTuple): |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
73 start: int |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
74 end: int |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
75 region: str |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
76 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
77 @classmethod |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
78 def from_string(cls, string): |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
79 # Example: aa,40-41(FR1) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
80 sequence, rest = string.split(',') # type: str, str |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
81 brace_pos = rest.index('(') |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
82 numbers = rest[:brace_pos] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
83 start, end = numbers.split('-') |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
84 region = rest[brace_pos + 1:-1] # Remove the braces |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
85 return cls(int(start), int(end), region) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
86 |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
87 |
| 81 | 88 def main(): |
| 89 parser = argparse.ArgumentParser() | |
| 90 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") | |
| 91 parser.add_argument("--genes", help="The genes available in the 'best_match' column") | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
92 parser.add_argument("--empty_region_filter", help="Where does the sequence start?", choices=REGION_FILTERS) |
| 81 | 93 parser.add_argument("--output", help="Output file") |
| 94 | |
| 95 args = parser.parse_args() | |
| 96 | |
| 97 infile = args.input | |
| 98 genes = str(args.genes).split(",") | |
| 99 empty_region_filter = args.empty_region_filter | |
| 100 outfile = args.output | |
| 101 | |
| 102 genedic = dict() | |
| 103 | |
| 104 mutationdic = dict() | |
| 105 NAMatchResult = (None, None, None, None, None, None, '') | |
| 106 linecount = 0 | |
| 107 | |
| 108 IDIndex = 0 | |
| 109 best_matchIndex = 0 | |
| 110 fr1Index = 0 | |
| 111 cdr1Index = 0 | |
| 112 fr2Index = 0 | |
| 113 cdr2Index = 0 | |
| 114 fr3Index = 0 | |
| 115 first = True | |
| 116 IDlist = [] | |
| 117 mutationList = [] | |
| 118 mutationListByID = {} | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
119 cdr1AALengthDic = {} |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
120 cdr2AALengthDic = {} |
| 81 | 121 |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
122 LengthDic = {} |
| 81 | 123 |
| 124 cdr1LengthIndex = 0 | |
| 125 cdr2LengthIndex = 0 | |
| 126 | |
| 127 tandem_sum_by_class = defaultdict(int) | |
| 128 expected_tandem_sum_by_class = defaultdict(float) | |
| 129 | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
130 with open(infile, 'r') as i: |
| 81 | 131 for line in i: |
| 132 if first: | |
| 133 linesplt = line.split("\t") | |
| 134 IDIndex = linesplt.index("Sequence.ID") | |
| 135 best_matchIndex = linesplt.index("best_match") | |
| 136 fr1Index = linesplt.index("FR1.IMGT") | |
| 137 cdr1Index = linesplt.index("CDR1.IMGT") | |
| 138 fr2Index = linesplt.index("FR2.IMGT") | |
| 139 cdr2Index = linesplt.index("CDR2.IMGT") | |
| 140 fr3Index = linesplt.index("FR3.IMGT") | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
141 fr1LengthIndex = linesplt.index("FR1.IMGT.Nb.of.nucleotides") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
142 fr2LengthIndex = linesplt.index("FR2.IMGT.Nb.of.nucleotides") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
143 fr3LengthIndex = linesplt.index("FR3.IMGT.Nb.of.nucleotides") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
144 cdr1LengthIndex = linesplt.index("CDR1.IMGT.Nb.of.nucleotides") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
145 cdr2LengthIndex = linesplt.index("CDR2.IMGT.Nb.of.nucleotides") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
146 cdr1AALengthIndex = linesplt.index("CDR1.IMGT.length") |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
147 cdr2AALengthIndex = linesplt.index("CDR2.IMGT.length") |
| 81 | 148 first = False |
| 149 continue | |
| 150 linecount += 1 | |
| 151 linesplt = line.split("\t") | |
| 152 ID = linesplt[IDIndex] | |
| 153 genedic[ID] = linesplt[best_matchIndex] | |
| 154 | |
| 155 mutationdic[ID + "_FR1"] = [] | |
| 156 if len(linesplt[fr1Index]) > 5 and empty_region_filter == "leader": | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
157 mutationdic[ID + "_FR1"] = [Mutation.from_string(x) for x in linesplt[fr1Index].split("|") if x] |
| 81 | 158 |
| 159 mutationdic[ID + "_CDR1"] = [] | |
| 160 if len(linesplt[cdr1Index]) > 5 and empty_region_filter in ["leader", "FR1"]: | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
161 mutationdic[ID + "_CDR1"] = [Mutation.from_string(x) for x in linesplt[cdr1Index].split("|") if x] |
| 81 | 162 |
| 163 mutationdic[ID + "_FR2"] = [] | |
| 164 if len(linesplt[fr2Index]) > 5 and empty_region_filter in ["leader", "FR1", "CDR1"]: | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
165 mutationdic[ID + "_FR2"] = [Mutation.from_string(x) for x in linesplt[fr2Index].split("|") if x] |
| 81 | 166 |
| 167 mutationdic[ID + "_CDR2"] = [] | |
| 168 if len(linesplt[cdr2Index]) > 5: | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
169 mutationdic[ID + "_CDR2"] = [Mutation.from_string(x) for x in linesplt[cdr2Index].split("|") if x] |
| 81 | 170 |
| 171 mutationdic[ID + "_FR2-CDR2"] = mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] | |
| 172 | |
| 173 mutationdic[ID + "_FR3"] = [] | |
| 174 if len(linesplt[fr3Index]) > 5: | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
175 mutationdic[ID + "_FR3"] = [Mutation.from_string(x) for x in linesplt[fr3Index].split("|") if x] |
| 81 | 176 |
| 177 mutationList += mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"] | |
| 178 mutationListByID[ID] = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"] | |
| 179 | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
180 fr1Length = int(linesplt[fr1LengthIndex]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
181 fr2Length = int(linesplt[fr2LengthIndex]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
182 fr3Length = int(linesplt[fr3LengthIndex]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
183 cdr1Length = int(linesplt[cdr1LengthIndex]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
184 cdr2Length = int(linesplt[cdr2LengthIndex]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
185 LengthDic[ID] = (fr1Length, cdr1Length, fr2Length, cdr2Length, fr3Length) |
| 81 | 186 |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
187 cdr1AALengthDic[ID] = int(linesplt[cdr1AALengthIndex]) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
188 cdr2AALengthDic[ID] = int(linesplt[cdr2AALengthIndex]) |
| 81 | 189 |
| 190 IDlist += [ID] | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
191 print("len(mutationdic) =", len(mutationdic)) |
| 81 | 192 |
| 193 with open(os.path.join(os.path.dirname(os.path.abspath(infile)), "mutationdict.txt"), 'w') as out_handle: | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
194 for ID, lst in mutationdic.items(): |
| 81 | 195 for mut in lst: |
| 196 out_handle.write("{0}\t{1}\n".format(ID, "\t".join([str(x) for x in mut]))) | |
| 197 | |
| 198 #tandem mutation stuff | |
| 199 tandem_frequency = defaultdict(int) | |
| 200 mutation_frequency = defaultdict(int) | |
| 201 | |
| 202 mutations_by_id_dic = {} | |
| 203 first = True | |
| 204 mutation_by_id_file = os.path.join(os.path.dirname(outfile), "mutation_by_id.txt") | |
| 205 with open(mutation_by_id_file, 'r') as mutation_by_id: | |
| 206 for l in mutation_by_id: | |
| 207 if first: | |
| 208 first = False | |
| 209 continue | |
| 210 splt = l.split("\t") | |
| 211 mutations_by_id_dic[splt[0]] = int(splt[1]) | |
| 212 | |
| 213 tandem_file = os.path.join(os.path.dirname(outfile), "tandems_by_id.txt") | |
| 214 with open(tandem_file, 'w') as o: | |
| 215 highest_tandem_length = 0 | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
216 # LengthDic stores length as a tuple |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
217 # (fr1Length, cdr1Length, fr2Length, cdr2Length, fr3Length) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
218 # To get the total length, we can sum(region_lengths) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
219 # To get the total length for leader: |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
220 # sum(region_lengths[0:]) (Equivalent to everything) |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
221 # sum(region_lengths[1:]) Gets everything except FR1 etc. |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
222 # We determine the position to start summing below. |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
223 # This returns 0 for leader, 1 for FR1 etc. |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
224 length_start_pos = REGION_FILTERS.index(empty_region_filter) |
| 81 | 225 |
| 226 o.write("Sequence.ID\tnumber_of_mutations\tnumber_of_tandems\tregion_length\texpected_tandems\tlongest_tandem\ttandems\n") | |
| 227 for ID in IDlist: | |
| 228 mutations = mutationListByID[ID] | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
229 region_length = sum(LengthDic[ID][length_start_pos:]) |
| 81 | 230 if len(mutations) == 0: |
| 231 continue | |
| 232 last_mut = max(mutations, key=lambda x: int(x[1])) | |
| 233 | |
| 234 last_mut_pos = int(last_mut[1]) | |
| 235 | |
| 236 mut_positions = [False] * (last_mut_pos + 1) | |
| 237 | |
| 238 for mutation in mutations: | |
| 239 frm, where, to, frmAA, whereAA, toAA, thing = mutation | |
| 240 where = int(where) | |
| 241 mut_positions[where] = True | |
| 242 | |
| 243 tandem_muts = [] | |
| 244 tandem_start = -1 | |
| 245 tandem_length = 0 | |
| 246 for i in range(len(mut_positions)): | |
| 247 if mut_positions[i]: | |
| 248 if tandem_start == -1: | |
| 249 tandem_start = i | |
| 250 tandem_length += 1 | |
| 251 #print "".join(["1" if x else "0" for x in mut_positions[:i+1]]) | |
| 252 else: | |
| 253 if tandem_length > 1: | |
| 254 tandem_muts.append((tandem_start, tandem_length)) | |
| 255 #print "{0}{1} {2}:{3}".format(" " * (i - tandem_length), "^" * tandem_length, tandem_start, tandem_length) | |
| 256 tandem_start = -1 | |
| 257 tandem_length = 0 | |
| 258 if tandem_length > 1: # if the sequence ends with a tandem mutation | |
| 259 tandem_muts.append((tandem_start, tandem_length)) | |
| 260 | |
| 261 if len(tandem_muts) > 0: | |
| 262 if highest_tandem_length < len(tandem_muts): | |
| 263 highest_tandem_length = len(tandem_muts) | |
| 264 | |
| 265 longest_tandem = max(tandem_muts, key=lambda x: x[1]) if len(tandem_muts) else (0, 0) | |
| 266 num_mutations = mutations_by_id_dic[ID] # len(mutations) | |
| 267 f_num_mutations = float(num_mutations) | |
| 268 num_tandem_muts = len(tandem_muts) | |
| 269 expected_tandem_muts = f_num_mutations * (f_num_mutations - 1.0) / float(region_length) | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
270 # String format and round disagree slightly (see 3.605). |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
271 # So round before formatting. |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
272 o.write(f"{ID}\t{num_mutations}\t{num_tandem_muts}\t{region_length}\t" |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
273 f"{round(expected_tandem_muts, 2):.2f}\t" |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
274 f"{longest_tandem[1]}\t{tandem_muts}\n") |
| 81 | 275 gene = genedic[ID] |
| 276 if gene.find("unmatched") == -1: | |
| 277 tandem_sum_by_class[gene] += num_tandem_muts | |
| 278 expected_tandem_sum_by_class[gene] += expected_tandem_muts | |
| 279 | |
| 280 tandem_sum_by_class["all"] += num_tandem_muts | |
| 281 expected_tandem_sum_by_class["all"] += expected_tandem_muts | |
| 282 | |
| 283 gene = gene[:3] | |
| 284 if gene in ["IGA", "IGG"]: | |
| 285 tandem_sum_by_class[gene] += num_tandem_muts | |
| 286 expected_tandem_sum_by_class[gene] += expected_tandem_muts | |
| 287 else: | |
| 288 tandem_sum_by_class["unmatched"] += num_tandem_muts | |
| 289 expected_tandem_sum_by_class["unmatched"] += expected_tandem_muts | |
| 290 | |
| 291 | |
| 292 for tandem_mut in tandem_muts: | |
| 293 tandem_frequency[str(tandem_mut[1])] += 1 | |
| 294 #print "\t".join([ID, str(len(tandem_muts)), str(longest_tandem[1]) , str(tandem_muts)]) | |
| 295 | |
| 296 tandem_freq_file = os.path.join(os.path.dirname(outfile), "tandem_frequency.txt") | |
| 297 with open(tandem_freq_file, 'w') as o: | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
298 for frq in sorted([int(x) for x in list(tandem_frequency.keys())]): |
| 81 | 299 o.write("{0}\t{1}\n".format(frq, tandem_frequency[str(frq)])) |
| 300 | |
| 301 tandem_row = [] | |
| 302 genes_extra = list(genes) | |
| 303 genes_extra.append("all") | |
| 304 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]): | |
| 305 if y != 0: | |
| 306 tandem_row += [x, round(y, 2), round(x / y, 2)] | |
| 307 else: | |
| 308 tandem_row += [x, round(y, 2), 0] | |
| 309 | |
| 310 tandem_freq_file = os.path.join(os.path.dirname(outfile), "shm_overview_tandem_row.txt") | |
| 311 with open(tandem_freq_file, 'w') as o: | |
| 312 o.write("Tandems/Expected (ratio),{0}\n".format(",".join([str(x) for x in tandem_row]))) | |
| 313 | |
| 314 #print mutationList, linecount | |
| 315 | |
| 316 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 | |
| 317 if AALength < 60: | |
| 318 AALength = 64 | |
| 319 | |
| 320 AA_mutation = [0] * AALength | |
| 321 AA_mutation_dic = {"IGA": AA_mutation[:], "IGG": AA_mutation[:], "IGM": AA_mutation[:], "IGE": AA_mutation[:], "unm": AA_mutation[:], "all": AA_mutation[:]} | |
| 322 AA_mutation_empty = AA_mutation[:] | |
| 323 | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
324 print("AALength:", AALength) |
| 81 | 325 aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/aa_id_mutations.txt" |
| 326 with open(aa_mutations_by_id_file, 'w') as o: | |
| 327 o.write("ID\tbest_match\t" + "\t".join([str(x) for x in range(1,AALength)]) + "\n") | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
328 for ID in list(mutationListByID.keys()): |
| 81 | 329 AA_mutation_for_ID = AA_mutation_empty[:] |
| 330 for mutation in mutationListByID[ID]: | |
| 331 if mutation[4] and mutation[5] != ";": | |
| 332 AA_mutation_position = int(mutation[4]) | |
| 333 try: | |
| 334 AA_mutation[AA_mutation_position] += 1 | |
| 335 AA_mutation_for_ID[AA_mutation_position] += 1 | |
| 336 except Exception as e: | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
337 print(e) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
338 print(mutation) |
| 81 | 339 sys.exit() |
| 340 clss = genedic[ID][:3] | |
| 341 AA_mutation_dic[clss][AA_mutation_position] += 1 | |
| 342 o.write(ID + "\t" + genedic[ID] + "\t" + "\t".join([str(x) for x in AA_mutation_for_ID[1:]]) + "\n") | |
| 343 | |
| 344 | |
| 345 | |
| 346 #absent AA stuff | |
| 347 absentAACDR1Dic = defaultdict(list) | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
348 absentAACDR1Dic[5] = list(range(29,36)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
349 absentAACDR1Dic[6] = list(range(29,35)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
350 absentAACDR1Dic[7] = list(range(30,35)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
351 absentAACDR1Dic[8] = list(range(30,34)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
352 absentAACDR1Dic[9] = list(range(31,34)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
353 absentAACDR1Dic[10] = list(range(31,33)) |
| 81 | 354 absentAACDR1Dic[11] = [32] |
| 355 | |
| 356 absentAACDR2Dic = defaultdict(list) | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
357 absentAACDR2Dic[0] = list(range(55,65)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
358 absentAACDR2Dic[1] = list(range(56,65)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
359 absentAACDR2Dic[2] = list(range(56,64)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
360 absentAACDR2Dic[3] = list(range(57,64)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
361 absentAACDR2Dic[4] = list(range(57,63)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
362 absentAACDR2Dic[5] = list(range(58,63)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
363 absentAACDR2Dic[6] = list(range(58,62)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
364 absentAACDR2Dic[7] = list(range(59,62)) |
|
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
365 absentAACDR2Dic[8] = list(range(59,61)) |
| 81 | 366 absentAACDR2Dic[9] = [60] |
| 367 | |
| 368 absentAA = [len(IDlist)] * (AALength-1) | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
369 for k, cdr1Length in cdr1AALengthDic.items(): |
| 81 | 370 for c in absentAACDR1Dic[cdr1Length]: |
| 371 absentAA[c] -= 1 | |
| 372 | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
373 for k, cdr2Length in cdr2AALengthDic.items(): |
| 81 | 374 for c in absentAACDR2Dic[cdr2Length]: |
| 375 absentAA[c] -= 1 | |
| 376 | |
| 377 | |
| 378 aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/absent_aa_id.txt" | |
| 379 with open(aa_mutations_by_id_file, 'w') as o: | |
| 380 o.write("ID\tcdr1length\tcdr2length\tbest_match\t" + "\t".join([str(x) for x in range(1,AALength)]) + "\n") | |
| 381 for ID in IDlist: | |
| 382 absentAAbyID = [1] * (AALength-1) | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
383 cdr1Length = cdr1AALengthDic[ID] |
| 81 | 384 for c in absentAACDR1Dic[cdr1Length]: |
| 385 absentAAbyID[c] -= 1 | |
| 386 | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
387 cdr2Length = cdr2AALengthDic[ID] |
| 81 | 388 for c in absentAACDR2Dic[cdr2Length]: |
| 389 absentAAbyID[c] -= 1 | |
| 390 o.write(ID + "\t" + str(cdr1Length) + "\t" + str(cdr2Length) + "\t" + genedic[ID] + "\t" + "\t".join([str(x) for x in absentAAbyID]) + "\n") | |
| 391 | |
| 392 if linecount == 0: | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
393 print("No data, exiting") |
| 81 | 394 with open(outfile, 'w') as o: |
| 395 o.write("RGYW (%)," + ("0,0,0\n" * len(genes))) | |
| 396 o.write("WRCY (%)," + ("0,0,0\n" * len(genes))) | |
| 397 o.write("WA (%)," + ("0,0,0\n" * len(genes))) | |
| 398 o.write("TW (%)," + ("0,0,0\n" * len(genes))) | |
| 399 sys.exit() | |
| 400 | |
| 401 RGYWCount = {} | |
| 402 WRCYCount = {} | |
| 403 WACount = {} | |
| 404 TWCount = {} | |
| 405 | |
| 406 #IDIndex = 0 | |
| 407 ataIndex = 0 | |
| 408 tatIndex = 0 | |
| 409 aggctatIndex = 0 | |
| 410 atagcctIndex = 0 | |
| 411 first = True | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
412 with open(infile, 'r') as i: |
| 81 | 413 for line in i: |
| 414 if first: | |
| 415 linesplt = line.split("\t") | |
| 416 ataIndex = linesplt.index("X.a.t.a") | |
| 417 tatIndex = linesplt.index("t.a.t.") | |
| 418 aggctatIndex = linesplt.index("X.a.g.g.c.t..a.t.") | |
| 419 atagcctIndex = linesplt.index("X.a.t..a.g.c.c.t.") | |
| 420 first = False | |
| 421 continue | |
| 422 linesplt = line.split("\t") | |
| 423 gene = linesplt[best_matchIndex] | |
| 424 ID = linesplt[IDIndex] | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
425 RGYW = [Hotspot.from_string(x) for x in linesplt[aggctatIndex].split("|") if x] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
426 WRCY = [Hotspot.from_string(x) for x in linesplt[atagcctIndex].split("|") if x] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
427 WA = [Hotspot.from_string(x) for x in linesplt[ataIndex].split("|") if x] |
|
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
428 TW = [Hotspot.from_string(x) for x in linesplt[tatIndex].split("|") if x] |
| 81 | 429 RGYWCount[ID], WRCYCount[ID], WACount[ID], TWCount[ID] = 0, 0, 0, 0 |
| 430 | |
| 431 with open(os.path.join(os.path.dirname(os.path.abspath(infile)), "RGYW.txt"), 'a') as out_handle: | |
| 432 for hotspot in RGYW: | |
| 433 out_handle.write("{0}\t{1}\n".format(ID, "\t".join([str(x) for x in hotspot]))) | |
| 434 | |
| 435 mutationList = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"] | |
| 436 for mutation in mutationList: | |
| 437 frm, where, to, AAfrm, AAwhere, AAto, junk = mutation | |
| 438 mutation_in_RGYW = any(((start <= int(where) <= end) for (start, end, region) in RGYW)) | |
| 439 mutation_in_WRCY = any(((start <= int(where) <= end) for (start, end, region) in WRCY)) | |
| 440 mutation_in_WA = any(((start <= int(where) <= end) for (start, end, region) in WA)) | |
| 441 mutation_in_TW = any(((start <= int(where) <= end) for (start, end, region) in TW)) | |
| 442 | |
| 443 in_how_many_motifs = sum([mutation_in_RGYW, mutation_in_WRCY, mutation_in_WA, mutation_in_TW]) | |
| 444 | |
| 445 if in_how_many_motifs > 0: | |
| 446 RGYWCount[ID] += (1.0 * int(mutation_in_RGYW)) / in_how_many_motifs | |
| 447 WRCYCount[ID] += (1.0 * int(mutation_in_WRCY)) / in_how_many_motifs | |
| 448 WACount[ID] += (1.0 * int(mutation_in_WA)) / in_how_many_motifs | |
| 449 TWCount[ID] += (1.0 * int(mutation_in_TW)) / in_how_many_motifs | |
| 450 | |
| 451 mutations_in_motifs_file = os.path.join(os.path.dirname(os.path.abspath(infile)), "mutation_in_motifs.txt") | |
| 452 if not os.path.exists(mutation_by_id_file): | |
| 453 with open(mutations_in_motifs_file, 'w') as out_handle: | |
| 454 out_handle.write("{0}\n".format("\t".join([ | |
| 455 "Sequence.ID", | |
| 456 "mutation_position", | |
| 457 "region", | |
| 458 "from_nt", | |
| 459 "to_nt", | |
| 460 "mutation_position_AA", | |
| 461 "from_AA", | |
| 462 "to_AA", | |
| 463 "motif", | |
| 464 "motif_start_nt", | |
| 465 "motif_end_nt", | |
| 466 "rest" | |
| 467 ]))) | |
| 468 | |
| 469 with open(mutations_in_motifs_file, 'a') as out_handle: | |
| 470 motif_dic = {"RGYW": RGYW, "WRCY": WRCY, "WA": WA, "TW": TW} | |
| 471 for mutation in mutationList: | |
| 472 frm, where, to, AAfrm, AAwhere, AAto, junk = mutation | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
473 for motif in list(motif_dic.keys()): |
| 81 | 474 |
| 475 for start, end, region in motif_dic[motif]: | |
| 476 if start <= int(where) <= end: | |
| 477 out_handle.write("{0}\n".format( | |
| 478 "\t".join([ | |
| 479 ID, | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
480 str(where), |
| 81 | 481 region, |
| 482 frm, | |
| 483 to, | |
| 484 str(AAwhere), | |
| 485 str(AAfrm), | |
| 486 str(AAto), | |
| 487 motif, | |
| 488 str(start), | |
| 489 str(end), | |
| 490 str(junk) | |
| 491 ]) | |
| 492 )) | |
| 493 | |
| 494 | |
| 495 | |
| 496 def mean(lst): | |
| 497 return (float(sum(lst)) / len(lst)) if len(lst) > 0 else 0.0 | |
| 498 | |
| 499 | |
| 500 def median(lst): | |
| 501 lst = sorted(lst) | |
| 502 l = len(lst) | |
| 503 if l == 0: | |
| 504 return 0 | |
| 505 if l == 1: | |
| 506 return lst[0] | |
| 507 | |
| 508 l = int(l / 2) | |
| 509 | |
| 510 if len(lst) % 2 == 0: | |
| 511 return float(lst[l] + lst[(l - 1)]) / 2.0 | |
| 512 else: | |
| 513 return lst[l] | |
| 514 | |
| 515 funcs = {"mean": mean, "median": median, "sum": sum} | |
| 516 | |
| 517 directory = outfile[:outfile.rfind("/") + 1] | |
| 518 value = 0 | |
| 519 valuedic = dict() | |
| 520 | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
521 for fname in list(funcs.keys()): |
| 81 | 522 for gene in genes: |
| 523 with open(directory + gene + "_" + fname + "_value.txt", 'r') as v: | |
| 524 valuedic[gene + "_" + fname] = float(v.readlines()[0].rstrip()) | |
| 525 with open(directory + "all_" + fname + "_value.txt", 'r') as v: | |
| 526 valuedic["total_" + fname] = float(v.readlines()[0].rstrip()) | |
| 527 | |
| 528 | |
| 529 def get_xyz(lst, gene, f, fname): | |
| 530 x = round(round(f(lst), 1)) | |
| 531 y = valuedic[gene + "_" + fname] | |
| 532 z = str(round(x / float(y) * 100, 1)) if y != 0 else "0" | |
| 533 return (str(x), str(y), z) | |
| 534 | |
| 535 dic = {"RGYW": RGYWCount, "WRCY": WRCYCount, "WA": WACount, "TW": TWCount} | |
| 536 arr = ["RGYW", "WRCY", "WA", "TW"] | |
| 537 | |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
538 for fname in list(funcs.keys()): |
| 81 | 539 func = funcs[fname] |
| 540 foutfile = outfile[:outfile.rindex("/")] + "/hotspot_analysis_" + fname + ".txt" | |
| 541 with open(foutfile, 'w') as o: | |
| 542 for typ in arr: | |
| 543 o.write(typ + " (%)") | |
| 544 curr = dic[typ] | |
| 545 for gene in genes: | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
546 if valuedic[gene + "_" + fname] == 0: |
| 81 | 547 o.write(",0,0,0") |
| 548 else: | |
|
90
6809c63d9161
"planemo upload commit fd64827ff6e63df008f6f50ddb8576ad2b1dbb26"
rhpvorderman
parents:
83
diff
changeset
|
549 x, y, z = get_xyz([curr[x] for x in [y for y, z in genedic.items() if z.startswith(gene)]], gene, func, fname) |
| 81 | 550 o.write("," + x + "," + y + "," + z) |
|
83
729738462297
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
rhpvorderman
parents:
81
diff
changeset
|
551 x, y, z = get_xyz([y for x, y in curr.items() if not genedic[x].startswith("unmatched")], "total", func, fname) |
| 81 | 552 #x, y, z = get_xyz([y for x, y in curr.iteritems()], "total", func, fname) |
| 553 o.write("," + x + "," + y + "," + z + "\n") | |
| 554 | |
| 555 | |
| 556 # for testing | |
| 557 seq_motif_file = outfile[:outfile.rindex("/")] + "/motif_per_seq.txt" | |
| 558 with open(seq_motif_file, 'w') as o: | |
| 559 o.write("ID\tRGYW\tWRCY\tWA\tTW\n") | |
| 560 for ID in IDlist: | |
| 561 #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") | |
| 562 o.write(ID + "\t" + str(RGYWCount[ID]) + "\t" + str(WRCYCount[ID]) + "\t" + str(WACount[ID]) + "\t" + str(TWCount[ID]) + "\n") | |
| 563 | |
| 564 if __name__ == "__main__": | |
| 565 main() |