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
|
#!/usr/bin/env python
#file: column_parser.py
"""Parser for column format
Works for the following column format:
; COL 1 label
; COL 2 residue
; COL 3 seqpos
; COL 4 alignpos
; COL 5 align_bp
; COL 6 certainty/seqpos_bp
Structure part separated by '; ------' and ends with '; ******'
"""
from string import split
from cogent.struct.rna2d import Pairs
from cogent.struct.pairs_util import adjust_base
__author__ = "Shandy Wikman"
__copyright__ = "Copyright 2007-2009, The Cogent Project"
__contributors__ = ["Shandy Wikman"]
__license__ = "GPL"
__version__ = "1.4.1"
__maintainer__ = "Shandy Wikman"
__email__ = "ens01svn@cs.umu.se"
__status__ = "Development"
def column_parser(lines):
"""Parser column format"""
record = False
result = []
struct = []
seq = ''
for line in lines:
if line.startswith('; ------'): #structure part beginns
record = True
continue
if line.startswith('; ******'): #structure part ends
record = False
struct = adjust_base(struct,-1)
struct = Pairs(struct).directed()#remove duplicates
struct.sort()
result.append([seq,struct])
struct = []
seq = ''
continue
if record:
sline = line.split()
if sline[4] == '.': #skip not paired
seq = ''.join([seq,sline[1]])
continue
seq = ''.join([seq,sline[1]])
pair = (int(sline[3]),int(sline[4])) #(alignpos,align_bp)
struct.append(pair)
return result
|
