-
Notifications
You must be signed in to change notification settings - Fork 23
/
Copy pathgenewise.py
762 lines (660 loc) · 32.4 KB
/
genewise.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
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
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
#!/usr/bin/env python
# -*- coding: utf-8 -*-
###############################################################################
#
# Copyright 2012-2024 EMBL - European Bioinformatics Institute
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Python Client Automatically generated with:
# https://github.com/ebi-jdispatcher/webservice-clients-generator
#
# Genewise (REST) web service Python client using xmltramp2.
#
# For further information see:
# https://www.ebi.ac.uk/Tools/webservices/
#
###############################################################################
from __future__ import print_function
import os
import sys
import time
import requests
import platform
from xmltramp2 import xmltramp
from optparse import OptionParser
try:
from urllib.parse import urlparse, urlencode
from urllib.request import urlopen, Request
from urllib.error import HTTPError
from urllib.request import __version__ as urllib_version
except ImportError:
from urlparse import urlparse
from urllib import urlencode
from urllib2 import urlopen, Request, HTTPError
from urllib2 import __version__ as urllib_version
# Debug print
def printDebugMessage(functionName, message, level):
if (level <= debugLevel):
print(u'[' + functionName + u'] ' + message, file=sys.stderr)
# User-agent for request (see RFC2616).
def getUserAgent():
printDebugMessage(u'getUserAgent', u'Begin', 11)
# Agent string for urllib2 library.
urllib_agent = u'Python-urllib/%s' % urllib_version
clientRevision = version
# Prepend client specific agent string.
try:
pythonversion = platform.python_version()
pythonsys = platform.system()
except ValueError:
pythonversion, pythonsys = "Unknown", "Unknown"
user_agent = u'EBI-Sample-Client/%s (%s; Python %s; %s) %s' % (
clientRevision, os.path.basename(__file__),
pythonversion, pythonsys, urllib_agent)
printDebugMessage(u'getUserAgent', u'user_agent: ' + user_agent, 12)
printDebugMessage(u'getUserAgent', u'End', 11)
return user_agent
# Wrapper for a REST (HTTP GET) request
def restRequest(url):
printDebugMessage(u'restRequest', u'Begin', 11)
printDebugMessage(u'restRequest', u'url: ' + url, 11)
try:
# Set the User-agent.
user_agent = getUserAgent()
http_headers = {u'User-Agent': user_agent}
req = Request(url, None, http_headers)
# Make the request (HTTP GET).
reqH = urlopen(req)
resp = reqH.read()
contenttype = reqH.info()
if (len(resp) > 0 and contenttype != u"image/png;charset=UTF-8"
and contenttype != u"image/jpeg;charset=UTF-8"
and contenttype != u"application/gzip;charset=UTF-8"):
try:
result = unicode(resp, u'utf-8')
except UnicodeDecodeError:
result = resp
else:
result = resp
reqH.close()
# Errors are indicated by HTTP status codes.
except HTTPError as ex:
result = requests.get(url).content
printDebugMessage(u'restRequest', u'End', 11)
return result
# Get input parameters list
def serviceGetParameters():
printDebugMessage(u'serviceGetParameters', u'Begin', 1)
requestUrl = baseUrl + u'/parameters'
printDebugMessage(u'serviceGetParameters', u'requestUrl: ' + requestUrl, 2)
xmlDoc = restRequest(requestUrl)
doc = xmltramp.parse(xmlDoc)
printDebugMessage(u'serviceGetParameters', u'End', 1)
return doc[u'id':]
# Get list of parameters for error handling
def getListOfParameters():
printDebugMessage(u'getListOfParameters', u'Begin', 1)
return [str(x) for x in serviceGetParameters()]
# Print list of parameters
def printGetParameters():
printDebugMessage(u'printGetParameters', u'Begin', 1)
idList = serviceGetParameters()
for id_ in idList:
print(id_)
printDebugMessage(u'printGetParameters', u'End', 1)
# Get input parameter information
def serviceGetParameterDetails(paramName):
printDebugMessage(u'serviceGetParameterDetails', u'Begin', 1)
printDebugMessage(u'serviceGetParameterDetails', u'paramName: ' + paramName, 2)
requestUrl = baseUrl + u'/parameterdetails/' + paramName
printDebugMessage(u'serviceGetParameterDetails', u'requestUrl: ' + requestUrl, 2)
xmlDoc = restRequest(requestUrl)
doc = xmltramp.parse(xmlDoc)
printDebugMessage(u'serviceGetParameterDetails', u'End', 1)
return doc
# Print description of a parameter
def printGetParameterDetails(paramName):
printDebugMessage(u'printGetParameterDetails', u'Begin', 1)
doc = serviceGetParameterDetails(paramName)
print(unicode(doc.name) + u"\t" + unicode(doc.type))
print(doc.description)
if hasattr(doc, 'values'):
for value in doc.values:
print(value.value)
if unicode(value.defaultValue) == u'true':
print(u'default')
print(u"\t" + unicode(value.label))
if hasattr(value, u'properties'):
for wsProperty in value.properties:
print(u"\t" + unicode(wsProperty.key) + u"\t" + unicode(wsProperty.value))
printDebugMessage(u'printGetParameterDetails', u'End', 1)
# Submit job
def serviceRun(email, title, params):
printDebugMessage(u'serviceRun', u'Begin', 1)
# Insert e-mail and title into params
params[u'email'] = email
if title:
params[u'title'] = title
requestUrl = baseUrl + u'/run/'
printDebugMessage(u'serviceRun', u'requestUrl: ' + requestUrl, 2)
# Get the data for the other options
requestData = urlencode(params)
printDebugMessage(u'serviceRun', u'requestData: ' + requestData, 2)
# Errors are indicated by HTTP status codes.
try:
# Set the HTTP User-agent.
user_agent = getUserAgent()
http_headers = {u'User-Agent': user_agent}
req = Request(requestUrl, None, http_headers)
# Make the submission (HTTP POST).
reqH = urlopen(req, requestData.encode(encoding=u'utf_8', errors=u'strict'))
jobId = unicode(reqH.read(), u'utf-8')
reqH.close()
except HTTPError as ex:
print(xmltramp.parse(unicode(ex.read(), u'utf-8'))[0][0])
quit()
printDebugMessage(u'serviceRun', u'jobId: ' + jobId, 2)
printDebugMessage(u'serviceRun', u'End', 1)
return jobId
# Get job status
def serviceGetStatus(jobId):
printDebugMessage(u'serviceGetStatus', u'Begin', 1)
printDebugMessage(u'serviceGetStatus', u'jobId: ' + jobId, 2)
requestUrl = baseUrl + u'/status/' + jobId
printDebugMessage(u'serviceGetStatus', u'requestUrl: ' + requestUrl, 2)
status = restRequest(requestUrl)
printDebugMessage(u'serviceGetStatus', u'status: ' + status, 2)
printDebugMessage(u'serviceGetStatus', u'End', 1)
return status
# Print the status of a job
def printGetStatus(jobId):
printDebugMessage(u'printGetStatus', u'Begin', 1)
status = serviceGetStatus(jobId)
if outputLevel > 0:
print("Getting status for job %s" % jobId)
print(status)
if outputLevel > 0 and status == "FINISHED":
print("To get results: python %s --polljob --jobid %s"
"" % (os.path.basename(__file__), jobId))
printDebugMessage(u'printGetStatus', u'End', 1)
# Get available result types for job
def serviceGetResultTypes(jobId):
printDebugMessage(u'serviceGetResultTypes', u'Begin', 1)
printDebugMessage(u'serviceGetResultTypes', u'jobId: ' + jobId, 2)
requestUrl = baseUrl + u'/resulttypes/' + jobId
printDebugMessage(u'serviceGetResultTypes', u'requestUrl: ' + requestUrl, 2)
xmlDoc = restRequest(requestUrl)
doc = xmltramp.parse(xmlDoc)
printDebugMessage(u'serviceGetResultTypes', u'End', 1)
return doc[u'type':]
# Print list of available result types for a job.
def printGetResultTypes(jobId):
printDebugMessage(u'printGetResultTypes', u'Begin', 1)
if outputLevel > 0:
print("Getting result types for job %s" % jobId)
resultTypeList = serviceGetResultTypes(jobId)
if outputLevel > 0:
print("Available result types:")
for resultType in resultTypeList:
print(resultType[u'identifier'])
if hasattr(resultType, u'label'):
print(u"\t", resultType[u'label'])
if hasattr(resultType, u'description'):
print(u"\t", resultType[u'description'])
if hasattr(resultType, u'mediaType'):
print(u"\t", resultType[u'mediaType'])
if hasattr(resultType, u'fileSuffix'):
print(u"\t", resultType[u'fileSuffix'])
if outputLevel > 0:
print("To get results:\n python %s --polljob --jobid %s\n"
" python %s --polljob --outformat <type> --jobid %s"
"" % (os.path.basename(__file__), jobId,
os.path.basename(__file__), jobId))
printDebugMessage(u'printGetResultTypes', u'End', 1)
# Get result
def serviceGetResult(jobId, type_):
printDebugMessage(u'serviceGetResult', u'Begin', 1)
printDebugMessage(u'serviceGetResult', u'jobId: ' + jobId, 2)
printDebugMessage(u'serviceGetResult', u'type_: ' + type_, 2)
requestUrl = baseUrl + u'/result/' + jobId + u'/' + type_
result = restRequest(requestUrl)
printDebugMessage(u'serviceGetResult', u'End', 1)
return result
# Client-side poll
def clientPoll(jobId):
printDebugMessage(u'clientPoll', u'Begin', 1)
result = u'QUEUED'
while result == u'RUNNING' or result == u'QUEUED':
result = serviceGetStatus(jobId)
if outputLevel > 0:
print(result)
if result == u'RUNNING' or result == u'QUEUED':
time.sleep(pollFreq)
printDebugMessage(u'clientPoll', u'End', 1)
# Get result for a jobid
# Allows more than one output file written when 'outformat' is defined.
def getResult(jobId):
printDebugMessage(u'getResult', u'Begin', 1)
printDebugMessage(u'getResult', u'jobId: ' + jobId, 1)
if outputLevel > 1:
print("Getting results for job %s" % jobId)
# Check status and wait if necessary
clientPoll(jobId)
# Get available result types
resultTypes = serviceGetResultTypes(jobId)
for resultType in resultTypes:
# Derive the filename for the result
if options.outfile:
filename = (options.outfile + u'.' + unicode(resultType[u'identifier']) +
u'.' + unicode(resultType[u'fileSuffix']))
else:
filename = (jobId + u'.' + unicode(resultType[u'identifier']) +
u'.' + unicode(resultType[u'fileSuffix']))
# Write a result file
outformat_parm = str(options.outformat).split(',')
for outformat_type in outformat_parm:
outformat_type = outformat_type.replace(' ', '')
if outformat_type == 'None':
outformat_type = None
if not outformat_type or outformat_type == unicode(resultType[u'identifier']):
if outputLevel > 1:
print("Getting %s" % unicode(resultType[u'identifier']))
# Get the result
result = serviceGetResult(jobId, unicode(resultType[u'identifier']))
if (unicode(resultType[u'mediaType']) == u"image/png"
or unicode(resultType[u'mediaType']) == u"image/jpeg"
or unicode(resultType[u'mediaType']) == u"application/gzip"):
fmode = 'wb'
else:
fmode = 'w'
try:
fh = open(filename, fmode)
fh.write(result)
fh.close()
except TypeError:
fh.close()
fh = open(filename, "wb")
fh.write(result)
fh.close()
if outputLevel > 0:
print("Creating result file: " + filename)
printDebugMessage(u'getResult', u'End', 1)
# Read a file
def readFile(filename):
printDebugMessage(u'readFile', u'Begin', 1)
fh = open(filename, 'r')
data = fh.read()
fh.close()
printDebugMessage(u'readFile', u'End', 1)
return data
def print_usage():
print("""\
EMBL-EBI Genewise Python Client:
Pairwise sequence alignment with Genewise.
[Required (for job submission)]
--email E-mail address.
--asequence The protein sequence can be entered directly into this form.
The sequence can be in GCG, FASTA, EMBL (Nucleotide only),
GenBank, PIR, NBRF, PHYLIP or UniProtKB/Swiss-Prot (Protein
only) format. A partially formatted sequence is not
accepted. Adding a return to the end of the sequence may
help certain applications understand the input. Note that
directly using data from word processors may yield
unpredictable results as hidden/control characters may be
present. There is a limit of 1MB for the sequence entry.
--bsequence The DNA sequence to be compared can be entered directly into
the form. The sequence must be in a recognised format eg.
GCG, FASTA, EMBL, GenBank. Partially formatted sequences are
not accepted. Adding a return to the end of the sequence may
help certain applications understand the input. Note that
directly using data from word processors may yield
unpredictable results as hidden/control characters may be
present. There is a limit of 1MB for the sequence entry.
[Optional]
--para Show parameters in the output alignmment, as in genewise.
--pretty Show pretty ASCII alignment viewing, as in genewise.
--genes Show gene structure, as in genewise.
--trans Show protein translation, breaking at frameshifts.
--cdna Show cDNA, as in genewise.
--embl EMBL feature table format with CDS key.
--ace Show Ace file gene structure, as in genewise.
--gff Show Gene Feature Format file, as in genewise.
--diana Show EMBL FT format suitable for diana.
--init Model in local/global mode. You should only put the model in
global mode if you expect your protein homolog to have
homology from start to end to the gene in the DNA sequence.
--splice Using splice model or GT/AG? Use the full blown model for
splice sites, or a simplistic GT/AG. Generally if you are
using a DNA sequence which is from human or worm, then leave
this on. If you are using a very different (eg plant)
species, switch it off.
--random The probability of the model has to compared to an
alternative model (in fact to all alternative models which
are possible) to allow proper Bayesian inference. This
causes considerable difficulty in these algorithms because
from a algorithmical point of view we would probably like to
use an alternative model which is a single state, like the
random model in profile-HMMs, where we can simply 'log-odd'
the scored model, whereas from a biological point of view we
probably want to use a full gene predicting alternative
model. In addition we need to account for the fact that the
protein HMM or protein homolog probably does not extend over
all the gene sequence, nor in fact does the gene have to be
the only gene in the DNA sequence. This means that there are
very good splice sites/poly-pyrimidine tracts outside of the
'matched' alignment can severely de-rail the alignment.
--alg The solutions is different in the genewise21:93 compared to
the genewise 6:23 algorithms. (1) In 6:23 we force the
external match portions of the homology model to be
identical to the alternative model, thus cancelling each
other out. This is a pretty gross approximation and is sort
of equivalent to the intron tie'ing. It makes things
algorithmically easier... However this means a) 6:23 is
nowhere near a probabilistic model and b) you really have to
used a tied intron model in 6:23 otherwise very bad edge
effects (final introns being ridiculously long) occur. (2)
In 21:93 we have a full probabilistic model on each side of
the homology segment. This is not reported in the -pretty
output but you can see it in the -alb output if you like. Do
not trust the gene model outside of the homology segment
however. By having these external gene model parts we can
use all the gene model features safe in the knowledge that
if the homology segments do not justify the match then the
external part of the model will soak up the additional
intron/py-tract/splice site biases.
[General]
-h, --help Show this help message and exit.
--asyncjob Forces to make an asynchronous query.
--title Title for job.
--status Get job status.
--resultTypes Get available result types for job.
--polljob Poll for the status of a job.
--pollFreq Poll frequency in seconds (default 3s).
--jobid JobId that was returned when an asynchronous job was submitted.
--outfile File name for results (default is JobId; for STDOUT).
--outformat Result format(s) to retrieve. It accepts comma-separated values.
--params List input parameters.
--paramDetail Display details for input parameter.
--verbose Increase output.
--version Prints out the version of the Client and exit.
--quiet Decrease output.
--baseUrl Base URL. Defaults to:
https://www.ebi.ac.uk/Tools/services/rest/genewise
Synchronous job:
The results/errors are returned as soon as the job is finished.
Usage: python genewise.py --email <[email protected]> [options...] <SeqFile|SeqID(s)>
Returns: results as an attachment
Asynchronous job:
Use this if you want to retrieve the results at a later time. The results
are stored for up to 24 hours.
Usage: python genewise.py --asyncjob --email <[email protected]> [options...] <SeqFile|SeqID(s)>
Returns: jobid
Check status of Asynchronous job:
Usage: python genewise.py --status --jobid <jobId>
Retrieve job data:
Use the jobid to query for the status of the job. If the job is finished,
it also returns the results/errors.
Usage: python genewise.py --polljob --jobid <jobId> [--outfile string]
Returns: string indicating the status of the job and if applicable, results
as an attachment.
Further information:
https://www.ebi.ac.uk/Tools/webservices and
https://github.com/ebi-jdispatcher/webservice-clients
Support/Feedback:
https://www.ebi.ac.uk/support/""")
# allow unicode(str) to be used in python 3
try:
unicode('')
except NameError:
unicode = str
# Base URL for service
baseUrl = u'https://www.ebi.ac.uk/Tools/services/rest/genewise'
version = u'2024-07-11 07:51'
# Set interval for checking status
pollFreq = 3
# Output level
outputLevel = 1
# Debug level
debugLevel = 0
# Number of option arguments.
numOpts = len(sys.argv)
# Process command-line options
parser = OptionParser(add_help_option=False)
# Tool specific options (Try to print all the commands automatically)
parser.add_option('--para', action='store_true', help=('Show parameters in the output alignmment, as in genewise.'))
parser.add_option('--pretty', action='store_true', help=('Show pretty ASCII alignment viewing, as in genewise.'))
parser.add_option('--genes', action='store_true', help=('Show gene structure, as in genewise'))
parser.add_option('--trans', action='store_true', help=('Show protein translation, breaking at frameshifts.'))
parser.add_option('--cdna', action='store_true', help=('Show cDNA, as in genewise.'))
parser.add_option('--embl', action='store_true', help=('EMBL feature table format with CDS key.'))
parser.add_option('--ace', action='store_true', help=('Show Ace file gene structure, as in genewise.'))
parser.add_option('--gff', action='store_true', help=('Show Gene Feature Format file, as in genewise.'))
parser.add_option('--diana', action='store_true', help=('Show EMBL FT format suitable for diana.'))
parser.add_option('--init', type=str, help=('Model in local/global mode. You should only put the model in global'
'mode if you expect your protein homolog to have homology from start to'
'end to the gene in the DNA sequence.'))
parser.add_option('--splice', type=str, help=('Using splice model or GT/AG? Use the full blown model for splice'
'sites, or a simplistic GT/AG. Generally if you are using a DNA'
'sequence which is from human or worm, then leave this on. If you are'
'using a very different (eg plant) species, switch it off.'))
parser.add_option('--random', type=str, help=('The probability of the model has to compared to an alternative model'
'(in fact to all alternative models which are possible) to allow proper'
'Bayesian inference. This causes considerable difficulty in these'
'algorithms because from a algorithmical point of view we would'
'probably like to use an alternative model which is a single state,'
'like the random model in profile-HMMs, where we can simply log-odd the'
'scored model, whereas from a biological point of view we probably want'
'to use a full gene predicting alternative model. In addition we need'
'to account for the fact that the protein HMM or protein homolog'
'probably does not extend over all the gene sequence, nor in fact does'
'the gene have to be the only gene in the DNA sequence. This means that'
'there are very good splice sites/poly-pyrimidine tracts outside of the'
'matched alignment can severely de-rail the alignment.'))
parser.add_option('--alg', type=str, help=('The solutions is different in the genewise21:93 compared to the'
'genewise 6:23 algorithms. (1) In 6:23 we force the external match'
'portions of the homology model to be identical to the alternative'
'model, thus cancelling each other out. This is a pretty gross'
'approximation and is sort of equivalent to the intron tieing. It makes'
'things algorithmically easier... However this means a) 6:23 is nowhere'
'near a probabilistic model and b) you really have to used a tied'
'intron model in 6:23 otherwise very bad edge effects (final introns'
'being ridiculously long) occur. (2) In 21:93 we have a full'
'probabilistic model on each side of the homology segment. This is not'
'reported in the -pretty output but you can see it in the -alb output'
'if you like. Do not trust the gene model outside of the homology'
'segment however. By having these external gene model parts we can use'
'all the gene model features safe in the knowledge that if the homology'
'segments do not justify the match then the external part of the model'
'will soak up the additional intron/py-tract/splice site biases.'))
parser.add_option('--asequence', type=str, help=('The protein sequence can be entered directly into this form. The'
'sequence can be in GCG, FASTA, EMBL (Nucleotide only), GenBank, PIR,'
'NBRF, PHYLIP or UniProtKB/Swiss-Prot (Protein only) format. A'
'partially formatted sequence is not accepted. Adding a return to the'
'end of the sequence may help certain applications understand the'
'input. Note that directly using data from word processors may yield'
'unpredictable results as hidden/control characters may be present.'
'There is a limit of 1MB for the sequence entry.'))
parser.add_option('--bsequence', type=str, help=('The DNA sequence to be compared can be entered directly into the form.'
'The sequence must be in a recognised format eg. GCG, FASTA, EMBL,'
'GenBank. Partially formatted sequences are not accepted. Adding a'
'return to the end of the sequence may help certain applications'
'understand the input. Note that directly using data from word'
'processors may yield unpredictable results as hidden/control'
'characters may be present. There is a limit of 1MB for the sequence'
'entry.'))
# General options
parser.add_option('-h', '--help', action='store_true', help='Show this help message and exit.')
parser.add_option('--email', help='E-mail address.')
parser.add_option('--title', help='Job title.')
parser.add_option('--outfile', help='File name for results.')
parser.add_option('--outformat', help='Output format for results.')
parser.add_option('--asyncjob', action='store_true', help='Asynchronous mode.')
parser.add_option('--jobid', help='Job identifier.')
parser.add_option('--polljob', action="store_true", help='Get job result.')
parser.add_option('--pollFreq', type='int', default=3, help='Poll frequency in seconds (default 3s).')
parser.add_option('--status', action="store_true", help='Get job status.')
parser.add_option('--resultTypes', action='store_true', help='Get result types.')
parser.add_option('--params', action='store_true', help='List input parameters.')
parser.add_option('--paramDetail', help='Get details for parameter.', choices=getListOfParameters())
parser.add_option('--quiet', action='store_true', help='Decrease output level.')
parser.add_option('--verbose', action='store_true', help='Increase output level.')
parser.add_option('--version', action='store_true', help='Prints out the version of the Client and exit.')
parser.add_option('--debugLevel', type='int', default=debugLevel, help='Debugging level.')
parser.add_option('--baseUrl', default=baseUrl, help='Base URL for service.')
(options, args) = parser.parse_args()
# Increase output level
if options.verbose:
outputLevel += 1
# Decrease output level
if options.quiet:
outputLevel -= 1
# Debug level
if options.debugLevel:
debugLevel = options.debugLevel
if options.pollFreq:
pollFreq = options.pollFreq
if options.baseUrl:
baseUrl = options.baseUrl
# No options... print help.
if numOpts < 2:
print_usage()
elif options.help:
print_usage()
# List parameters
elif options.params:
printGetParameters()
# Get parameter details
elif options.paramDetail:
printGetParameterDetails(options.paramDetail)
# Print Client version
elif options.version:
print("Revision: %s" % version)
sys.exit()
# Submit job
elif options.email and not options.jobid:
params = {}
if len(args) == 1 and "true" not in args and "false" not in args:
if os.path.exists(args[0]): # Read file into content
params[u'sequence'] = readFile(args[0])
else: # Argument is a sequence id
params[u'sequence'] = args[0]
elif len(args) == 2 and "true" not in args and "false" not in args:
if os.path.exists(args[0]) and os.path.exists(args[1]): # Read file into content
params[u'asequence'] = readFile(args[0])
params[u'bsequence'] = readFile(args[1])
else: # Argument is a sequence id
params[u'asequence'] = args[0]
params[u'bsequence'] = args[0]
elif hasattr(options, "sequence") or (hasattr(options, "asequence") and hasattr(options, "bsequence")): # Specified via option
if hasattr(options, "sequence"):
if os.path.exists(options.sequence): # Read file into content
params[u'sequence'] = readFile(options.sequence)
else: # Argument is a sequence id
params[u'sequence'] = options.sequence
elif hasattr(options, "asequence") and hasattr(options, "bsequence"):
if os.path.exists(options.asequence) and os.path.exists(options.bsequence): # Read file into content
params[u'asequence'] = readFile(options.asequence)
params[u'bsequence'] = readFile(options.bsequence)
else: # Argument is a sequence id
params[u'asequence'] = options.asequence
params[u'bsequence'] = options.bsequence
# Pass default values and fix bools (without default value)
if not options.para:
params['para'] = 'true'
if options.para:
params['para'] = options.para
if not options.pretty:
params['pretty'] = 'true'
if options.pretty:
params['pretty'] = options.pretty
if not options.genes:
params['genes'] = 'true'
if options.genes:
params['genes'] = options.genes
if not options.trans:
params['trans'] = 'true'
if options.trans:
params['trans'] = options.trans
if not options.cdna:
params['cdna'] = 'true'
if options.cdna:
params['cdna'] = options.cdna
if not options.embl:
params['embl'] = 'true'
if options.embl:
params['embl'] = options.embl
if not options.ace:
params['ace'] = 'true'
if options.ace:
params['ace'] = options.ace
if not options.gff:
params['gff'] = 'true'
if options.gff:
params['gff'] = options.gff
if not options.diana:
params['diana'] = 'true'
if options.diana:
params['diana'] = options.diana
if not options.init:
params['init'] = 'local'
if options.init:
params['init'] = options.init
if not options.splice:
params['splice'] = 'flat'
if options.splice:
params['splice'] = options.splice
if not options.random:
params['random'] = 'syn'
if options.random:
params['random'] = options.random
if not options.alg:
params['alg'] = '623'
if options.alg:
params['alg'] = options.alg
# Submit the job
jobId = serviceRun(options.email, options.title, params)
if options.asyncjob: # Async mode
print(jobId)
if outputLevel > 0:
print("To check status: python %s --status --jobid %s"
"" % (os.path.basename(__file__), jobId))
else:
# Sync mode
if outputLevel > 0:
print("JobId: " + jobId, file=sys.stderr)
else:
print(jobId)
time.sleep(pollFreq)
getResult(jobId)
# Get job status
elif options.jobid and options.status:
printGetStatus(options.jobid)
elif options.jobid and (options.resultTypes or options.polljob):
status = serviceGetStatus(options.jobid)
if status == 'QUEUED' or status == 'RUNNING':
print("Error: Job status is %s. "
"To get result types the job must be finished." % status)
quit()
# List result types for job
if options.resultTypes:
printGetResultTypes(options.jobid)
# Get results for job
elif options.polljob:
getResult(options.jobid)
else:
# Checks for 'email' parameter
if not options.email:
print('\nParameter "--email" is missing in your command. It is required!\n')
print(u'Error: unrecognised argument combination', file=sys.stderr)
print_usage()