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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
|
# Copyright 2001 by Tarjei Mikkelsen. All rights reserved.
# Copyright 2007 by Michiel de Hoon. 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.
"""Code to work with the KEGG Ligand/Compound database.
Functions:
parse - Returns an iterator giving Record objects.
Classes:
Record - A representation of a KEGG Ligand/Compound.
"""
# other Biopython stuff
from __future__ import print_function
from Bio.KEGG import _write_kegg
from Bio.KEGG import _wrap_kegg
# Set up line wrapping rules (see Bio.KEGG._wrap_kegg)
name_wrap = [0, "",
(" ", "$", 1, 1),
("-", "$", 1, 1)]
id_wrap = lambda indent: [indent, "", (" ", "", 1, 0)]
struct_wrap = lambda indent: [indent, "", (" ", "", 1, 1)]
class Record(object):
"""Holds info from a KEGG Ligand/Compound record.
Members:
entry The entry identifier.
name A list of the compund names.
formula The chemical formula for the compound
mass The molecular weight for the compound
pathway A list of 3-tuples: (database, id, pathway)
enzyme A list of 2-tuples: (enzyme id, role)
structures A list of 2-tuples: (database, list of struct ids)
dblinks A list of 2-tuples: (database, list of link ids)
"""
def __init__(self):
"""__init___(self)
Create a new Record.
"""
self.entry = ""
self.name = []
self.formula = ""
self.mass = ""
self.pathway = []
self.enzyme = []
self.structures = []
self.dblinks = []
def __str__(self):
"""__str__(self)
Returns a string representation of this Record.
"""
return self._entry() + \
self._name() + \
self._formula() + \
self._mass() + \
self._pathway() + \
self._enzyme() + \
self._structures() + \
self._dblinks() + \
"///"
def _entry(self):
return _write_kegg("ENTRY",
[self.entry])
def _name(self):
return _write_kegg("NAME",
[_wrap_kegg(l, wrap_rule=name_wrap)
for l in self.name])
def _formula(self):
return _write_kegg("FORMULA",
[self.formula])
def _mass(self):
return _write_kegg("MASS",
[self.mass])
def _pathway(self):
s = []
for entry in self.pathway:
s.append(entry[0] + ": " + entry[1] + " " + entry[2])
return _write_kegg("PATHWAY",
[_wrap_kegg(l, wrap_rule=id_wrap(16))
for l in s])
def _enzyme(self):
s = ""
for entry in self.enzyme:
if entry[1]:
t = entry[0] + " (" + entry[1] + ")"
else:
t = entry[0]
s = s + t.ljust(16)
return _write_kegg("ENZYME",
[_wrap_kegg(s, wrap_rule=id_wrap(0))])
def _structures(self):
s = []
for entry in self.structures:
s.append(entry[0] + ": " + " ".join(entry[1]) + " ")
return _write_kegg("STRUCTURES",
[_wrap_kegg(l, wrap_rule=struct_wrap(5))
for l in s])
def _dblinks(self):
s = []
for entry in self.dblinks:
s.append(entry[0] + ": " + " ".join(entry[1]))
return _write_kegg("DBLINKS",
[_wrap_kegg(l, wrap_rule=id_wrap(9))
for l in s])
def parse(handle):
"""Parse a KEGG Ligan/Compound file, returning Record objects.
This is an iterator function, typically used in a for loop. For
example, using one of the example KEGG files in the Biopython
test suite,
>>> with open("KEGG/compound.sample") as handle:
... for record in parse(handle):
... print("%s %s" % (record.entry, record.name[0]))
...
C00023 Iron
C00017 Protein
C00099 beta-Alanine
C00294 Inosine
C00298 Trypsin
C00348 Undecaprenyl phosphate
C00349 2-Methyl-3-oxopropanoate
C01386 NH2Mec
"""
record = Record()
for line in handle:
if line[:3] == "///":
yield record
record = Record()
continue
if line[:12] != " ":
keyword = line[:12]
data = line[12:].strip()
if keyword == "ENTRY ":
words = data.split()
record.entry = words[0]
elif keyword == "NAME ":
data = data.strip(";")
record.name.append(data)
elif keyword == "ENZYME ":
while data:
column = data[:16]
data = data[16:]
if '(' in column:
entry = column.split()
enzyme = (entry[0], entry[1][1:-1])
else:
enzyme = (column.strip(), "")
record.enzyme.append(enzyme)
elif keyword == "PATHWAY ":
if data[:5] == 'PATH:':
path, map, name = data.split(None, 2)
pathway = (path[:-1], map, name)
record.pathway.append(pathway)
else:
pathway = record.pathway[-1]
path, map, name = pathway
name = name + " " + data
pathway = path, map, name
record.pathway[-1] = pathway
elif keyword == "FORMULA ":
record.formula = data
elif keyword == "MASS ":
record.mass = data
elif keyword == "DBLINKS ":
if ":" in data:
key, values = data.split(":")
values = values.split()
row = (key, values)
record.dblinks.append(row)
else:
row = record.dblinks[-1]
key, values = row
values.extend(data.split())
row = key, values
record.dblinks[-1] = row
if __name__ == "__main__":
from Bio._utils import run_doctest
run_doctest()
|
