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
|
# Copyright 2003 by Bartek Wilczynski. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""Parsing AlignACE output files
"""
from Bio.motifs import Motif, Instances
from Bio.Alphabet import IUPAC
from Bio.Seq import Seq
class Record(list):
def __init__(self):
self.parameters = None
def read(handle):
"""read(handle)"""
record = Record()
line = next(handle)
record.version = line.strip()
line = next(handle)
record.command = line.strip()
for line in handle:
line = line.strip()
if line == "":
pass
elif line[:4] == "Para":
record.parameters = {}
elif line[0] == "#":
seq_name = line.split("\t")[1]
record.sequences.append(seq_name)
elif "=" in line:
par_name, par_value = line.split("=")
par_name = par_name.strip()
par_value = par_value.strip()
record.parameters[par_name] = par_value
elif line[:5] == "Input":
record.sequences = []
elif line[:5] == "Motif":
words = line.split()
assert words[0] == "Motif"
number = int(words[1])
instances = []
elif line[:3] == "MAP":
alphabet = IUPAC.unambiguous_dna
instances = Instances(instances, alphabet)
motif = Motif(alphabet, instances)
motif.score = float(line.split()[-1])
motif.number = number
motif.mask = mask
record.append(motif)
elif len(line.split("\t")) == 4:
seq = Seq(line.split("\t")[0], IUPAC.unambiguous_dna)
instances.append(seq)
elif "*" in line:
mask = line.strip("\r\n")
else:
raise ValueError(line)
return record
|
