-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmca2bracket2.py
executable file
·165 lines (130 loc) · 4.68 KB
/
mca2bracket2.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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
#!/usr/bin/python
import re
import os
import sys
import math
import minilib as biolib
import mdg_dt as MDGDT
ix_pattern = re.compile('([A-Za-z]|\'[0-9]\')-?[0-9]+(\.[A-Z])?')
def is_ss_pair(line, edge_re, pair_re):
# 'antiparallel' in line -- not in online version
return 'cis' in line and \
edge_re.search(line) and \
pair_re.search(line)
###
def read_data(fn):
sequence = []
structure = []
unidentified = set([])
edge_re = re.compile('W[a-z]/W[a-z]')
pair_re = re.compile('([AG]-U)|(C-G)|(G-[CU])|(U-[AG])')
mode = 'ignore'
for line in open(fn):
line = line.strip()
if not line:
mode = 'ignore'
elif line.endswith('----'):
if line.startswith('Residue conformations'):
mode = 'sequence'
if len(sequence) > 0:
""" ignore multimodels """
break
elif line.startswith('Base-pairs'):
mode = 'structure'
else:
mode = 'ignore'
pass
continue
pass
if mode == 'ignore':
continue
elif mode == 'sequence':
line = line.split()
base = line[2].strip()
if base in biolib.BASEDICT:
base = biolib.BASEDICT[base]
sequence.append((line[0], base))
else:
unidentified.add(base)
elif mode == 'structure':
# print line, mode
# print 'edge_re:', edge_re.search(line)
# print 'pair_re:', pair_re.search(line)
if is_ss_pair(line, edge_re, pair_re):
line = line.split()
line = line[0]
try:
base1 = ix_pattern.search(line)
line = line[base1.end():]
base2 = ix_pattern.search(line)
# print base1.group(), base2.group()
structure.append([base1.group(), base2.group()])
except:
print line, 'fail'
sys.exit(1) #pass
"""
if len(tmp) == len(line) - 1:
structure.append(line[0].split('-'))
elif len(tmp) == len(line) - 2:
pass
else:
p = line.find('-')
"""
else:
continue
pass
if len(unidentified) > 0:
sys.stderr.write('UNIDENTIFIED RESIDUES: %s\n' % \
str(list(unidentified)))
pass
# print structure
return sequence, structure
###
def create_brackets(structure, sequence):
brackets = ['.' for i in xrange(len(sequence))]
index = [x[0] for x in sequence]
structure = [(index.index(b1), index.index(b2))
for b1, b2 in structure]
ss_tree = MDGDT.MDG_Stem()
ss_tree.assemble(sorted(structure), outp=sys.stderr)
knotless = sorted(ss_tree.preorder())
if ss_tree.has_tertiary_pairs() and ss_tree.has_tertiary_stem():
print ss_tree.te_contacts
return None
# print 'KLESS', knotless
def write_structure(structure, n):
brackets = ['.' for i in xrange(n)]
for i, j in structure:
if brackets[i] != '.' or brackets[j] != '.':
sys.stderr.write('%s %s %i %i already occupied\n' % \
(b1, b2, i, j))
if brackets[i] == '(' or brackets[i] == '<':
brackets[i] = '<'
elif brackets[i] == ')' or brackets[i] == '>':
brackets[i] ='#'
if brackets[j] == '(' or brackets[j] == '<':
brackets[j] = '@'
elif brackets[j] == ')' or brackets[j] == '>':
brackets[j] ='>'
else:
brackets[i] = '('
brackets[j] = ')'
pass
# sys.stderr.write('***\n')
return ''.join(brackets)
return (write_structure(structure, len(sequence)),
write_structure(knotless, len(sequence)))
###
def main(argv):
#
if len(argv) < 1:
sys.stderr.write('Usage: python mca2bracket2.py <MC-Annotate-file>\n')
sys.exit(1)
elif not os.path.exists(argv[0]):
sys.stderr.write('Error: file %s does not exist. Aborting.\n' % argv[0])
sys.exit(1)
seq, struc = read_data(argv[0])
brackets = create_brackets(struc, seq)
print 'Structure with knots:\n%s\nKnotless:\n%s\n' % brackets
return None
if __name__ == '__main__': main(sys.argv[1:])