forked from weka511/bioinformatics
-
Notifications
You must be signed in to change notification settings - Fork 0
/
BA10E.py
129 lines (108 loc) · 5.46 KB
/
BA10E.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
#!/usr/bin/env python
# Copyright (C) 2020-2023 Simon Crase
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
'''
BA10E Construct a Profile HMM
'''
from argparse import ArgumentParser
from os.path import basename
from time import time
from helpers import read_strings
from hmm import ConstructProfileHMM,formatEmission,formatTransition
if __name__=='__main__':
start = time()
parser = ArgumentParser(__doc__)
parser.add_argument('--sample', default=False, action='store_true', help='Process sample dataset')
parser.add_argument('--extra', default=False, action='store_true', help='Process extra dataset')
parser.add_argument('--rosalind', default=False, action='store_true', help='Process Rosalind dataset')
parser.add_argument('--text', default=False, action='store_true', help='Process dataset from textbook')
parser.add_argument('--precision', default=3, help='Controls display of probabilities')
parser.add_argument('--elapsed', default=False, action='store_true', help='Print elapsed time')
args = parser.parse_args()
if args.sample:
Transition,Emission,States = ConstructProfileHMM(0.289,
['A', 'B', 'C', 'D', 'E'],
['EBA', 'EBD', 'EB-', 'EED', 'EBD', 'EBE','E-D','EBD'])
for row in formatTransition(Transition,States,precision=args.precision):
print (row)
print ('--------')
for row in formatEmission(Emission,States,['A', 'B', 'C', 'D', 'E'],precision=args.precision):
print (row)
if args.text:
Alphabet = ['A', 'C', 'D', 'E', 'F']
Transition,Emission,States = ConstructProfileHMM(0.35,
Alphabet,
['ACDEFACADF',
'AFDA---CCF',
'A--EFD-FDC',
'ACAEF--A-C',
'ADDEFAAADF'])
for row in formatTransition(Transition,States,precision=args.precision):
print (row)
print ('--------')
for row in formatEmission(Emission,States,Alphabet,precision=args.precision):
print (row)
def compare(Expected,Actual):
Mismatch = False
if len(Expected)!=len(Actual):
print(f'{len(Expected)}!={len(Actual)}')
Mismatch = True
for i in range(min(len(Expected),len(Actual))):
if Expected[i] != Actual[i]:
print (f'{i} {Expected[i]} {Actual[i]}')
Mismatch = True
return Mismatch
if args.extra:
Input,Expected = read_strings(f'data/ProfileHMM.txt',init=0)
Transition,Emission,States = ConstructProfileHMM(float(Input[0]),
Input[2].split(),
Input[4:-1])
i = 0
mismatches = 0
with open(f'{basename(__file__).split(".")[0]}.txt','w') as f:
for row in formatTransition(Transition,States,precision=args.precision):
print (row)
f.write(f'{row}\n')
if compare(Expected[i],row):
mismatches+=1
i += 1
print ('--------')
f.write('--------\n')
if compare(Expected[i],'--------'):
mismatches+=1
i += 1
for row in formatEmission(Emission,States,Input[2].split(),precision=args.precision):
print (row)
f.write(f'{row}\n')
if compare(Expected[i],row):
mismatches+=1
i += 1
print (f'{mismatches} mismatches')
if args.rosalind:
Input = read_strings(f'data/rosalind_{basename(__file__).split(".")[0]}.txt')
Transition,Emission,States = ConstructProfileHMM(float(Input[0]),
Input[2].split(),
Input[4:])
with open(f'{basename(__file__).split(".")[0]}.txt','w') as f:
for row in formatTransition(Transition,States,precision=args.precision):
print (row)
f.write(f'{row}\n')
print ('--------')
f.write('--------\n')
for row in formatEmission(Emission,States,Input[2].split(),precision=args.precision):
print (row)
f.write(f'{row}\n')
if args.elapsed:
elapsed = time() - start
minutes = int(elapsed/60)
seconds = elapsed - 60*minutes
print (f'Elapsed Time {minutes} m {seconds:.2f} s')