/
getgene.py
executable file
·320 lines (273 loc) · 8.95 KB
/
getgene.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
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
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
#!/usr/bin/env python
# Created: Sun Oct 15 16:16:20 2000
# Last changed: Time-stamp: <01/02/15 09:01:27 thomas>
# thomas@cbs.dtu.dk, http://www.cbs.dtu.dk/thomas
# File: getgene.py
"""Example indexing plain text SwissProt files.
Example code to index a non-reduntant protein database of
SwissProt + TrEMBL for fast lookup and retrieval.
To build the database and index it::
cd /opt/bio/data/
wget -N -nd -r -l1 -A'.dat.Z' ftp://expasy.cbr.nrc.ca/databases/sp_tr_nrdb/
zcat *.dat.Z > nr.dat
./getgene.py --index nr.dat
setenv PYPHY '/opt/bio/data'
To retrieve entries from the command line::
./getgene.py EFTU_ECOLI
To use from a python script::
from getgene import DB_Index
db_index = DB_Index()
# retrieve a complete entry:
db_index.Get('EFTU_ECOLI')
# get organism, lineage and gene
db_index.Get_OS_OC_GN('EFTU_ECOLI')
"""
from __future__ import print_function
import os
import re
import string
import sys
try:
import gdbm # Python 2
except ImportError:
from dbm import gnu as gdbm # Python 3
class DB_Index(object):
def __init__(self, open=True):
"""Initialise.
Optional argument open controls if the index should be opened.
"""
if open:
self.Open()
def Create(self, infile, outfile):
db = gdbm.open(outfile, 'n')
with open(infile) as fid:
db['datafile'] = os.path.abspath(infile)
while True:
line = fid.readline()
if not line or not len(line):
break
if line[:3] == 'ID ':
id = string.split(line)[1]
start = fid.tell() - len(line)
elif line[:3] == 'AC ':
acc = string.split(line)[1]
if acc[-1] == ';':
acc = acc[:-1]
elif line[:2] == '//':
stop = fid.tell()
try:
value = '%d %d' % (start, stop)
db[id] = value
db[acc] = value
id, acc, start, stop = None, None, None, None
except Exception:
print("AARRGGGG %d %d %s %s" %
(start, stop, type(start), type(stop)))
print("%s %s" % (id, acc))
db.close()
def Open(self, indexfile=None):
if not indexfile:
indexfile = os.path.join(os.environ['PYPHY'], 'nr.dat.indexed')
self.db = gdbm.open(indexfile)
self.datafile = self.db['datafile']
self.fid = open(self.datafile)
def Close(self):
self.db.close()
def Get(self, id):
try:
values = self.db[id]
except Exception:
return None
start, stop = [int(x) for x in values.split()]
self.fid.seek(start)
txt = self.fid.read(stop - start)
return txt
def Get_Organism(self, id):
entry = self.Get(id)
if not entry:
return None
for line in string.split(entry, '\n'):
if line[0:5] == 'OS ':
OS = string.strip(line[5:])
if OS[-1] == ".":
OS = OS[0:-1]
return OS
if line[0:2] == "//":
break
return None
def FixOS(self, os):
os = string.split(os, ',')[0]
os = string.split(os, '(')[0]
return string.strip(os)
def Get_Taxonomy(self, id):
entry = self.Get(id)
if not entry:
return None
OC = ""
for line in string.split(entry, '\n'):
if line[0:5] == 'OC ':
OC = OC + string.strip(line[5:])
if OC[-1] == ".":
OC = OC[0:-1]
if line[0:2] == "//":
break
return OC
def Get_Kingdom(self, id):
res = self.Get_Taxonomy(id)
# print("%s %s" % (id, res))
if not res:
return "U"
kd = string.strip(string.split(res, ";")[0])
if kd == "Eubacteria" or kd == "Prokaryota" or kd == "Bacteria":
return "B"
elif kd == "Eukaryota" or kd == "Eukaryotae":
return "E"
elif kd == "Archaebacteria" or kd == "Archaea":
return "A"
elif kd == "Viridae" or kd == "Viruses":
return "V"
else:
print("%s UNKNOWN" % kd)
return "U"
def Get_Gene(self, id):
entry = self.Get(id)
if not entry:
return None
GN = ''
for line in string.split(entry, '\n'):
if line[0:5] == 'GN ':
GN = string.strip(line[5:])
if GN[-1] == ".":
GN = GN[0:-1]
return GN
if line[0:2] == "//":
break
return GN
def Get_OS_OC_GN(self, id):
entry = self.Get(id)
if not entry:
return None, None, None
OS, OC, GN = "", "", ""
for line in string.split(entry, '\n'):
if line[0:5] == 'OS ':
OS = string.strip(line[5:])
if OS[-1] == ".":
OS = OS[0:-1]
if line[0:5] == 'OC ':
OC = OC + string.strip(line[5:])
if OC[-1] == ".":
OC = OC[0:-1]
if line[0:5] == 'GN ':
GN = string.strip(line[5:])
if GN[-1] == ".":
GN = GN[0:-1]
if line[0:2] == "//":
break
return OS, OC, GN
def Get_OS_OC_OG(self, id):
entry = self.Get(id)
if not entry:
return None, None, None
OS, OC, OG = "", "", ""
for line in string.split(entry, '\n'):
if line[0:5] == 'OS ':
OS = string.strip(line[5:])
if OS[-1] == ".":
OS = OS[0:-1]
if line[0:5] == 'OC ':
OC = OC + string.strip(line[5:])
if OC[-1] == ".":
OC = OC[0:-1]
if line[0:5] == 'OG ':
OG = string.strip(line[5:])
if OG[-1] == ".":
OG = OG[0:-1]
if line[0:2] == "//":
break
return OS, OC, OG
def Get_SQ(self, id, fasta=1):
entry = self.Get(id)
if not entry:
return ""
SQ = ""
record = 0
for line in string.split(entry, '\n'):
if record:
SQ = SQ + string.strip(line[5:])
if line[0:5] == 'SQ ':
record = 1
if line[0:2] == "//":
break
SQ = re.sub('[ \n]', '', SQ)
if fasta:
SQ = '>%s\n%s' % (id, re.sub('(.{60})', '\\1\n', SQ))
return SQ
def Get_XX(self, id, xx):
entry = self.Get(id)
if not entry:
return ""
XX = ""
for line in string.split(entry, '\n'):
if line[0:5] == '%s ' % xx:
XX = XX + string.strip(line[5:])
if XX[-1] == ".":
XX = XX[0:-1]
if line[0:2] == "//":
break
return XX
def Get_Keywords(self, id):
entry = self.Get(id)
if not entry:
return []
keywords = []
for line in string.split(entry, '\n'):
if line[0:5] == 'KW ':
for i in string.split(string.strip(line[5:]), ';'):
kw = string.strip(i)
if len(kw) < 2:
continue
if kw[-1] == '.':
kw = kw[:-1]
keywords.append(kw)
if line[0:2] == "//":
break
return keywords
def usage(exit=0):
name = os.path.basename(sys.argv[0])
print('Usage: %s <db> <gene ID>' % name)
print(' or %s --index <db.dat>' % name)
if exit:
sys.exit(0)
if __name__ == '__main__':
pyphy_home = os.environ.get('PYPHY')
if len(sys.argv) == 1:
usage(exit=1)
db_index = DB_Index(open=0)
func = db_index.Get
for arg in sys.argv[1:]:
if arg == '--index':
sys.argv.remove(arg)
infile = sys.argv[1]
outfile = os.path.basename(infile) + '.indexed'
db_index.Create(infile, outfile)
sys.exit(0)
elif arg[:4] == '-Get':
sys.argv.remove(arg)
func = getattr(db_index, arg[1:])
elif arg == '-h' or arg == '--help':
usage(exit=1)
db = 'nr.dat'
if len(sys.argv) == 2:
# shortcut, mostly we use nr.dat so dont bother to name it
ids = sys.argv[1:]
else:
try:
db = sys.argv[1]
ids = sys.argv[2:]
except Exception:
usage(exit=1)
dbfile = os.path.join(pyphy_home, db + '.indexed')
db_index.Open(dbfile)
for id in ids:
# print(db_index.Get(id))
print(func(id))