- Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathBioPythonUtils.py
More file actions
Latest commit
489 lines (375 loc) · 16.9 KB
/
Copy pathBioPythonUtils.py
File metadata and controls
489 lines (375 loc) · 16.9 KB
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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
importio
importre
importsublime
importsublime_plugin
importthreading
importtime
importsys
importos
importjson
# BioPython 1.68 is bundled with this package
sys.path.append(os.path.dirname(__file__))
fromBioimportSeqIO, Entrez
fromBio.SeqimportSeq
fromBio.SeqRecordimportSeqRecord
fromBio.AlphabetimportIUPAC
fromBio.BlastimportNCBIWWW
# Get BLAST details from the JSON config file
blast_formats=json.load(open(os.path.join(os.path.dirname(__file__),
"config.json")))['blast_formats']
blast_info=json.load(open(os.path.join(os.path.dirname(__file__),
"config.json")))['blast_info']
# Globals which are used or set by show_quick_panel()
blast_db=None
blast_app=None
blast_format=None
# "Download Sequence by Search"
classDownloadSequenceBySearchCommand(sublime_plugin.TextCommand):
defrun(self, edit):
entrez_retmax=sublime.load_settings(
'BioPythonUtils.sublime-settings').get('entrez_retmax')
email_for_eutils=sublime.load_settings(
'BioPythonUtils.sublime-settings').get('email_for_eutils')
ifnotemail_for_eutils:
sublime.error_message("Enter email address for EUtils in \
BioPythonUtils -> Settings - User")
return
forregioninself.view.sel():
search_str=self.view.substr(region).strip()
ifnotsearch_str:
sublime.error_message("No search string in selection")
continue
try:
handle=Entrez.esearch(db="nucleotide",
term=search_str,
retmax=entrez_retmax,
email=email_for_eutils)
ids=Entrez.read(handle)
except (IOError) asexception:
print(str(exception))
print("Entrez count: {}".format(ids['Count']))
dialog_result=sublime.ok_cancel_dialog(
"Download {0} sequences? 'retmax': {1}".format(ids['Count'],
entrez_retmax),
'Download')
ifdialog_resultisTrue:
try:
handle=Entrez.efetch(db="nucleotide",
id=ids['IdList'],
rettype="gb",
retmode="text",
retmax=entrez_retmax,
email=email_for_eutils)
records=handle.read()
print("Entrez download: {} records".format(ids['Count']))
handle.close()
except (IOError) asexception:
print(str(exception))
self.view.window().new_file().insert(edit, 0, records)
# "Download Sequence by Id"
classDownloadSequenceByIdCommand(sublime_plugin.TextCommand):
defrun(self, edit):
email_for_eutils=sublime.load_settings(
'BioPythonUtils.sublime-settings').get('email_for_eutils')
ifnotemail_for_eutils:
sublime.error_message("Enter email address for EUtils \
in BioPythonUtils -> Settings - User")
return
forregioninself.view.sel():
id_str=self.view.substr(region).strip()
ifnotid_str:
sublime.error_message("No identifiers in selection")
continue
ids=re.split('[\n\s,]+', id_str)
threads= []
results=''
# Start jobs
foridinids:
thread=EutilsCall(id=id, email=email_for_eutils)
# AY818147time.sleep(1)
thread.start()
threads.append(thread)
results=handle_threads(threads)
self.view.window().new_file().insert(edit, 0, results)
defhandle_threads(threads, results=''):
next_threads= []
forthreadinthreads:
ifthread.is_alive():
next_threads.append(thread)
# Required, or else this loop runs so quickly that
# the code exits, too much "recursion"
time.sleep(.01)
elifthread.resultisnotFalse:
print("Downloaded "+thread.id)
results=results+str(thread.result)
iflen(next_threads) >0:
# Since this is recursive the "return" is required!
returnhandle_threads(next_threads, results)
# sublime.set_timeout(lambda: self.handle_threads(next_threads), 100)
eliflen(next_threads) ==0:
returnresults
classEutilsCall(threading.Thread):
# Subclass so that the results can be accessed through the object
def__init__(self, id=None, result=None, email=None):
self.id=id
self.email=email
self.result=result
threading.Thread.__init__(self)
defrun(self):
try:
handle=Entrez.efetch(db="nucleotide",
id=self.id,
email=self.email,
rettype="gb",
retmode="text")
self.result=handle.read()
return
except (IOError) asexception:
print(str(exception))
sublime.error_message(
"Error retrieving sequence using id '"+self.id+"'")
self.result=False
# "Download Sequence by Taxon"
classDownloadSequenceByTaxonCommand(sublime_plugin.TextCommand):
defrun(self, edit):
email_for_eutils=sublime.load_settings(
'BioPythonUtils.sublime-settings').get('email_for_eutils')
ifemail_for_eutils:
Entrez.email=email_for_eutils
else:
sublime.error_message("Enter email address for EUtils in \
BioPythonUtils -> Settings - User")
return
forregioninself.view.sel():
id_str=self.view.substr(region).strip()
ifnotid_str:
sublime.error_message("No identifiers in selection")
continue
taxids=re.split('[\n\s,]+', id_str)
seq_txt=''
fortaxidintaxids:
# Check that they're numeric
nummatch=re.match(r'^\d+$', taxid)
ifnotnummatch:
sublime.error_message(
"String '"+taxid+"' is not an NCBI taxon id")
return
try:
links=Entrez.read(
Entrez.elink(dbfrom="taxonomy",
db="nucleotide",
id=taxid))
except (IOError) asexception:
print(str(exception))
sublime.error_message("Error retrieving sequence ids \
using id '"+taxid+"'")
iflen(links[0]["LinkSetDb"]) ==0:
sublime.error_message(
"No sequences found with id "+taxid)
return
nt_ids=list()
forlinkinlinks[0]["LinkSetDb"][0]["Link"]:
nt_ids.append(link["Id"])
print("Entrez count: {}".format(len(nt_ids)))
dialog_result=sublime.ok_cancel_dialog(
"Download {} sequences?".format(len(nt_ids)), 'Download')
ifdialog_resultisTrue:
try:
handle=Entrez.efetch(db="nucleotide",
id=nt_ids,
rettype="gb",
retmode="text")
except (IOError) asexception:
print(str(exception))
sublime.error_message("Error retrieving sequences using id \
'"+taxid+"':"+str(exception))
seq_txt=handle.read()
# Write the fasta string to a new window at position 0
ifseq_txt:
self.view.window().new_file().insert(edit, 0, seq_txt)
# "Translate"
classTranslateCommand(sublime_plugin.TextCommand):
defrun(self, edit):
forregioninself.view.sel():
seq_str=self.view.substr(region).strip()
# Fasta header pattern
patt=re.compile('^>\s*\S+')
# If the selection looks like Fasta
ifpatt.match(seq_str):
# Read from a string and write to a string
seqout=io.StringIO()
withio.StringIO(seq_str) asseqin:
fornt_seq_recordinSeqIO.parse(seqin, "fasta"):
iflen(str(nt_seq_record.seq)) <3:
sublime.error_message(
"Sequence is too short to translate: "+
str(nt_seq_record.seq))
return
try:
# translate() returns a string
aa_seq=nt_seq_record.seq.translate()
except (BaseException) asexception:
print(str(exception))
sublime.error_message(str(exception))
# Copy data to the protein SeqRecord from the starting
# nucleotide sequence
aa_seq_record=SeqRecord(
aa_seq,
id=nt_seq_record.id,
description=nt_seq_record.description)
# Collect the records
SeqIO.write(aa_seq_record, seqout, "fasta")
seqin.close()
# Write the fasta string to a new window at position 0
self.view.window().new_file().insert(
edit, 0, seqout.getvalue())
# If selection is not Fasta
else:
seqout= []
seq_num=1
# Could be more than one sequence, "MULTILINE" required
fornt_strinre.split('^\s*\n', seq_str, 0, re.MULTILINE):
# Remove non-alphabetic ...
nt_str=re.sub(r'[^A-Za-z]+', r'', nt_str)
# and check that it's at least one codon long
iflen(nt_str) <3:
sublime.error_message(
"Selection is too short to translate: "+nt_str)
return
nt_seq=Seq(nt_str, IUPAC.unambiguous_dna)
# Check that it's all valid nucleotide ...
invalid_chars=validate_nt(str(nt_seq))
# ... and if it is valid
iflen(invalid_chars) ==0:
try:
aa_seq=nt_seq.translate()
except (BaseException) asexception:
print(str(exception))
sublime.error_message(str(exception))
seqout.append(str(aa_seq))
seq_num+=1
else:
sublime.error_message("Invalid characters in \
sequence "+str(seq_num) +": "+
''.join(invalid_chars))
return
# Separate the translations with an empty line
self.view.window().new_file().insert(
edit, 0, "\n\n".join(seqout))
# "Genbank To Fasta"
classGenbankToFastaCommand(sublime_plugin.TextCommand):
defrun(self, edit):
forregioninself.view.sel():
seq_str=self.view.substr(region).strip()
ifnotseq_str:
sublime.error_message("No selected text")
return
# Check that the selection begins as expected
startmatch=re.match(r'^LOCUS', seq_str)
# It turns out that SeqIO can handle Genbank format that
# does not end in '//' so there is no need to check for this
ifstartmatch:
# Read from a string and write to a string
seqout=io.StringIO()
withio.StringIO(seq_str) asseqin:
SeqIO.convert(seqin, 'genbank', seqout, 'fasta')
seqin.close()
# Write the fasta string to a new window at position 0
self.view.window().new_file().insert(
edit, 0, seqout.getvalue())
else:
sublime.error_message(
"Selected text does not look like Genbank: no 'LOCUS'")
return
# "Remote Blast"
classRemoteBlastCommand(sublime_plugin.TextCommand):
# FIX! errors from NCBI are not getting displayed by Sublime
defdo_blast(self, blast_app, blast_db, seq_record, blast_format):
try:
result=NCBIWWW.qblast(blast_app, blast_db,
seq_record.format('fasta'),
format_type=blast_format)
except (IOError) asexception:
print(str(exception))
sublime.error_message(str(exception))
returnresult
defrun(self, edit):
globalblast_db, blast_app, blast_format
ifnotblast_app:
blast_app=sublime.load_settings(
'BioPythonUtils.sublime-settings').get('remote_blast_app')
ifnotblast_db:
blast_db=sublime.load_settings(
'BioPythonUtils.sublime-settings').get('remote_blast_db')
ifnotblast_format:
blast_format=sublime.load_settings(
'BioPythonUtils.sublime-settings').get('remote_blast_format')
ifnotblast_db:
sublime.error_message("No BLAST database specified")
return
# 1 page is written for each report if there are multiple selections
forregioninself.view.sel():
seq_str=self.view.substr(region)
# Fasta header pattern
patt=re.compile('^>\s*\S+')
# If the selection looks like Fasta
ifpatt.match(seq_str):
withio.StringIO(seq_str) asseqin:
forseq_recordinSeqIO.parse(seqin, "fasta"):
result=self.do_blast(
blast_app, blast_db, seq_record, blast_format)
# Write the result to a new window at position 0
self.view.window().new_file().insert(
edit, 0, result.read())
print("Wrote BLAST result from Fasta format for "+
seq_record.id)
seqin.close()
else:
# Assume it's "plain" format and use an incrementing
# number as an id
seq_id=1
forseq_strinre.split('^\s*\n', seq_str, 0, re.MULTILINE):
seq_str=re.sub("[^a-zA-Z]", "", seq_str)
seq_record=SeqRecord(Seq(seq_str), id=str(seq_id))
result=self.do_blast(
blast_app, blast_db, seq_record, blast_format)
seq_id+=1
# Write the result to a new window at position 0
self.view.window().new_file().insert(
edit, 0, result.read())
print("Wrote BLAST result from plain format for "+
seq_record.id)
classSelectBlastDatabase(sublime_plugin.WindowCommand):
defrun(self):
sublime.active_window().show_quick_panel(
blast_info[blast_app], setBlastDatabase)
defsetBlastDatabase(index):
globalblast_db
ifindex>-1:
blast_db=blast_info[blast_app][index]
classSelectBlastApplication(sublime_plugin.WindowCommand):
defrun(self):
sublime.active_window().show_quick_panel(
list(blast_info.keys()), setBlastApplication)
defsetBlastApplication(index):
globalblast_app
ifindex>-1:
blast_app=list(blast_info.keys())[index]
classSelectBlastFormat(sublime_plugin.WindowCommand):
defrun(self):
sublime.active_window().show_quick_panel(blast_formats, setBlastFormat)
defsetBlastFormat(index):
globalblast_format
ifindex>-1:
blast_format=blast_formats[index]
defvalidate_nt(seq):
# Valid: {'G', 'T', 'U', 'C', 'A'}
valid_bases=set(IUPAC.unambiguous_dna.letters+
IUPAC.unambiguous_rna.letters)
seq_arr=list(seq.upper())
invalid=list(set(seq_arr) -valid_bases)
returninvalid
defvalidate_aa(seq):
seq_arr=list(seq.upper())
invalid=list(set(seq_arr) -set(IUPAC.protein.letters))
returninvalid