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
|
from __future__ import absolute_import, division, print_function
import string
import resource
import codecs
from htmlgen import HTMLgen2 as HT
from base import webqtlConfig
from base.webqtlCaseData import webqtlCaseData
from base.data_set import create_dataset
from db import webqtlDatabaseFunction
from utility import webqtlUtil
from wqflask import app
import simplejson as json
from MySQLdb import escape_string as escape
from pprint import pformat as pf
from flask import Flask, g, request
from utility.logger import getLogger
logger = getLogger(__name__ )
from wqflask import user_manager
class GeneralTrait(object):
"""
Trait class defines a trait in webqtl, can be either Microarray,
Published phenotype, genotype, or user input trait
"""
def __init__(self, get_qtl_info=False, get_sample_info=True, **kw):
# xor assertion
assert bool(kw.get('dataset')) != bool(kw.get('dataset_name')), "Needs dataset ob. or name";
if kw.get('dataset_name'):
self.dataset = create_dataset(kw.get('dataset_name'))
#print(" in GeneralTrait created dataset:", self.dataset)
else:
self.dataset = kw.get('dataset')
self.name = kw.get('name') # Trait ID, ProbeSet ID, Published ID, etc.
#print("THE NAME IS:", self.name)
self.cellid = kw.get('cellid')
self.identification = kw.get('identification', 'un-named trait')
self.haveinfo = kw.get('haveinfo', False)
self.sequence = kw.get('sequence') # Blat sequence, available for ProbeSet
self.data = kw.get('data', {})
# Sets defaults
self.locus = None
self.lrs = None
self.pvalue = None
self.mean = None
self.additive = None
self.num_overlap = None
self.strand_probe = None
self.symbol = None
self.LRS_score_repr = "N/A"
self.LRS_location_repr = "N/A"
if kw.get('fullname'):
name2 = value.split("::")
if len(name2) == 2:
self.dataset, self.name = name2
# self.cellid is set to None above
elif len(name2) == 3:
self.dataset, self.name, self.cellid = name2
# Todo: These two lines are necessary most of the time, but perhaps not all of the time
# So we could add a simple if statement to short-circuit this if necessary
if self.dataset.type != "Temp":
self = retrieve_trait_info(self, self.dataset, get_qtl_info=get_qtl_info)
if get_sample_info != False:
self = retrieve_sample_data(self, self.dataset)
def export_informative(self, include_variance=0):
"""
export informative sample
mostly used in qtl regression
"""
samples = []
vals = []
the_vars = []
sample_aliases = []
for sample_name, sample_data in self.data.items():
if sample_data.value != None:
if not include_variance or sample_data.variance != None:
samples.append(sample_name)
vals.append(sample_data.value)
the_vars.append(sample_data.variance)
sample_aliases.append(sample_data.name2)
return samples, vals, the_vars, sample_aliases
@property
def description_fmt(self):
'''Return a text formated description'''
if self.dataset.type == 'ProbeSet':
if self.description:
formatted = self.description
if self.probe_target_description:
formatted += "; " + self.probe_target_description
else:
formatted = "Not available"
elif self.dataset.type == 'Publish':
if self.confidential:
formatted = self.pre_publication_description
else:
formatted = self.post_publication_description
else:
formatted = "Not available"
return formatted
@property
def alias_fmt(self):
'''Return a text formatted alias'''
if self.alias:
alias = string.replace(self.alias, ";", " ")
alias = string.join(string.split(alias), ", ")
else:
alias = 'Not available'
return alias
@property
def location_fmt(self):
'''Return a text formatted location
While we're at it we set self.location in case we need it later (do we?)
'''
if self.chr and self.mb:
self.location = 'Chr %s @ %s Mb' % (self.chr,self.mb)
elif self.chr:
self.location = 'Chr %s @ Unknown position' % (self.chr)
else:
self.location = 'Not available'
fmt = self.location
##XZ: deal with direction
if self.strand_probe == '+':
fmt += (' on the plus strand ')
elif self.strand_probe == '-':
fmt += (' on the minus strand ')
return fmt
def retrieve_sample_data(trait, dataset, samplelist=None):
if samplelist == None:
samplelist = []
results = dataset.retrieve_sample_data(trait.name)
# Todo: is this necessary? If not remove
trait.data.clear()
all_samples_ordered = dataset.group.all_samples_ordered()
if results:
for item in results:
name, value, variance, num_cases, name2 = item
if not samplelist or (samplelist and name in samplelist):
trait.data[name] = webqtlCaseData(*item) #name, value, variance, num_cases)
return trait
@app.route("/trait/get_sample_data")
def get_sample_data():
params = request.args
trait = params['trait']
dataset = params['dataset']
trait_ob = GeneralTrait(name=trait, dataset_name=dataset)
return json.dumps([trait, {key: value.value for key, value in trait_ob.data.iteritems() }])
#jsonable_sample_data = {}
#for sample in trait_ob.data.iteritems():
# jsonable_sample_data[sample] = trait_ob.data[sample].value
#
#return jsonable_sample_data
def jsonable(trait):
"""Return a dict suitable for using as json
Actual turning into json doesn't happen here though"""
dataset = create_dataset(dataset_name = trait.dataset.name, dataset_type = trait.dataset.type, group_name = trait.dataset.group.name)
if dataset.type == "ProbeSet":
return dict(name=trait.name,
symbol=trait.symbol,
dataset=dataset.name,
description=trait.description_display,
mean=trait.mean,
location=trait.location_repr,
lrs_score=trait.LRS_score_repr,
lrs_location=trait.LRS_location_repr,
additive=trait.additive
)
elif dataset.type == "Publish":
if trait.pubmed_id:
return dict(name=trait.name,
dataset=dataset.name,
description=trait.description_display,
authors=trait.authors,
pubmed_text=trait.pubmed_text,
pubmed_link=trait.pubmed_link,
lrs_score=trait.LRS_score_repr,
lrs_location=trait.LRS_location_repr,
additive=trait.additive
)
else:
return dict(name=trait.name,
dataset=dataset.name,
description=trait.description_display,
authors=trait.authors,
pubmed_text=trait.pubmed_text,
lrs_score=trait.LRS_score_repr,
lrs_location=trait.LRS_location_repr,
additive=trait.additive
)
elif dataset.type == "Geno":
return dict(name=trait.name,
dataset=dataset.name,
location=trait.location_repr
)
else:
return dict()
def jsonable_table_row(trait, dataset_name, index):
"""Return a list suitable for json and intended to be displayed in a table
Actual turning into json doesn't happen here though"""
dataset = create_dataset(dataset_name)
if dataset.type == "ProbeSet":
if trait.mean == "":
mean = "N/A"
else:
mean = "%.3f" % round(float(trait.mean), 2)
if trait.additive == "":
additive = "N/A"
else:
additive = "%.3f" % round(float(trait.additive), 2)
return ['<input type="checkbox" name="searchResult" class="checkbox trait_checkbox" value="' + user_manager.data_hmac('{}:{}'.format(str(trait.name), dataset.name)) + '">',
index,
'<a href="/show_trait?trait_id='+str(trait.name)+'&dataset='+dataset.name+'">'+str(trait.name)+'</a>',
trait.symbol,
trait.description_display,
trait.location_repr,
mean,
trait.LRS_score_repr,
trait.LRS_location_repr,
additive]
elif dataset.type == "Publish":
if trait.additive == "":
additive = "N/A"
else:
additive = "%.2f" % round(float(trait.additive), 2)
if trait.pubmed_id:
return ['<input type="checkbox" name="searchResult" class="checkbox trait_checkbox" value="' + user_manager.data_hmac('{}:{}'.format(str(trait.name), dataset.name)) + '">',
index,
'<a href="/show_trait?trait_id='+str(trait.name)+'&dataset='+dataset.name+'">'+str(trait.name)+'</a>',
trait.description_display,
trait.authors,
'<a href="' + trait.pubmed_link + '">' + trait.pubmed_text + '</href>',
trait.LRS_score_repr,
trait.LRS_location_repr,
additive]
else:
return ['<input type="checkbox" name="searchResult" class="checkbox trait_checkbox" value="' + user_manager.data_hmac('{}:{}'.format(str(trait.name), dataset.name)) + '">',
index,
'<a href="/show_trait?trait_id='+str(trait.name)+'&dataset='+dataset.name+'">'+str(trait.name)+'</a>',
trait.description_display,
trait.authors,
trait.pubmed_text,
trait.LRS_score_repr,
trait.LRS_location_repr,
additive]
elif dataset.type == "Geno":
return ['<input type="checkbox" name="searchResult" class="checkbox trait_checkbox" value="' + user_manager.data_hmac('{}:{}'.format(str(trait.name), dataset.name)) + '">',
index,
'<a href="/show_trait?trait_id='+str(trait.name)+'&dataset='+dataset.name+'">'+str(trait.name)+'</a>',
trait.location_repr]
else:
return dict()
def retrieve_trait_info(trait, dataset, get_qtl_info=False):
assert dataset, "Dataset doesn't exist"
if dataset.type == 'Publish':
query = """
SELECT
PublishXRef.Id, Publication.PubMed_ID,
Phenotype.Pre_publication_description, Phenotype.Post_publication_description, Phenotype.Original_description,
Phenotype.Pre_publication_abbreviation, Phenotype.Post_publication_abbreviation,
Phenotype.Lab_code, Phenotype.Submitter, Phenotype.Owner, Phenotype.Authorized_Users,
Publication.Authors, Publication.Title, Publication.Abstract,
Publication.Journal, Publication.Volume, Publication.Pages,
Publication.Month, Publication.Year, PublishXRef.Sequence,
Phenotype.Units, PublishXRef.comments
FROM
PublishXRef, Publication, Phenotype, PublishFreeze
WHERE
PublishXRef.Id = %s AND
Phenotype.Id = PublishXRef.PhenotypeId AND
Publication.Id = PublishXRef.PublicationId AND
PublishXRef.InbredSetId = PublishFreeze.InbredSetId AND
PublishFreeze.Id = %s
""" % (trait.name, dataset.id)
logger.sql(query)
trait_info = g.db.execute(query).fetchone()
#XZ, 05/08/2009: Xiaodong add this block to use ProbeSet.Id to find the probeset instead of just using ProbeSet.Name
#XZ, 05/08/2009: to avoid the problem of same probeset name from different platforms.
elif dataset.type == 'ProbeSet':
display_fields_string = ', ProbeSet.'.join(dataset.display_fields)
display_fields_string = 'ProbeSet.' + display_fields_string
query = """
SELECT %s
FROM ProbeSet, ProbeSetFreeze, ProbeSetXRef
WHERE
ProbeSetXRef.ProbeSetFreezeId = ProbeSetFreeze.Id AND
ProbeSetXRef.ProbeSetId = ProbeSet.Id AND
ProbeSetFreeze.Name = '%s' AND
ProbeSet.Name = '%s'
""" % (escape(display_fields_string),
escape(dataset.name),
escape(str(trait.name)))
logger.sql(query)
trait_info = g.db.execute(query).fetchone()
#XZ, 05/08/2009: We also should use Geno.Id to find marker instead of just using Geno.Name
# to avoid the problem of same marker name from different species.
elif dataset.type == 'Geno':
display_fields_string = string.join(dataset.display_fields,',Geno.')
display_fields_string = 'Geno.' + display_fields_string
query = """
SELECT %s
FROM Geno, GenoFreeze, GenoXRef
WHERE
GenoXRef.GenoFreezeId = GenoFreeze.Id AND
GenoXRef.GenoId = Geno.Id AND
GenoFreeze.Name = '%s' AND
Geno.Name = '%s'
""" % (escape(display_fields_string),
escape(dataset.name),
escape(trait.name))
logger.sql(query)
trait_info = g.db.execute(query).fetchone()
else: #Temp type
query = """SELECT %s FROM %s WHERE Name = %s"""
logger.sql(query)
trait_info = g.db.execute(query,
(string.join(dataset.display_fields,','),
dataset.type, trait.name)).fetchone()
if trait_info:
trait.haveinfo = True
#XZ: assign SQL query result to trait attributes.
for i, field in enumerate(dataset.display_fields):
holder = trait_info[i]
if isinstance(trait_info[i], basestring):
holder = unicode(trait_info[i], "utf-8", "ignore")
setattr(trait, field, holder)
if dataset.type == 'Publish':
trait.confidential = 0
if trait.pre_publication_description and not trait.pubmed_id:
trait.confidential = 1
description = trait.post_publication_description
#If the dataset is confidential and the user has access to confidential
#phenotype traits, then display the pre-publication description instead
#of the post-publication description
if trait.confidential:
trait.description_display = trait.pre_publication_description
#if not webqtlUtil.hasAccessToConfidentialPhenotypeTrait(
# privilege=self.dataset.privilege,
# userName=self.dataset.userName,
# authorized_users=self.authorized_users):
#
# description = self.pre_publication_description
else:
if description:
trait.description_display = description.strip()
else:
trait.description_display = ""
if not trait.year.isdigit():
trait.pubmed_text = "N/A"
else:
trait.pubmed_text = trait.year
if trait.pubmed_id:
trait.pubmed_link = webqtlConfig.PUBMEDLINK_URL % trait.pubmed_id
if dataset.type == 'ProbeSet' and dataset.group:
description_string = unicode(str(trait.description).strip(codecs.BOM_UTF8), 'utf-8')
target_string = unicode(str(trait.probe_target_description).strip(codecs.BOM_UTF8), 'utf-8')
if len(description_string) > 1 and description_string != 'None':
description_display = description_string
else:
description_display = trait.symbol
if (len(description_display) > 1 and description_display != 'N/A' and
len(target_string) > 1 and target_string != 'None'):
description_display = description_display + '; ' + target_string.strip()
# Save it for the jinja2 template
trait.description_display = description_display
trait.location_repr = 'N/A'
if trait.chr and trait.mb:
trait.location_repr = 'Chr%s: %.6f' % (trait.chr, float(trait.mb))
elif dataset.type == "Geno":
trait.location_repr = 'N/A'
if trait.chr and trait.mb:
trait.location_repr = 'Chr%s: %.6f' % (trait.chr, float(trait.mb))
if get_qtl_info:
#LRS and its location
trait.LRS_score_repr = "N/A"
trait.LRS_location_repr = "N/A"
if dataset.type == 'ProbeSet' and not trait.cellid:
query = """
SELECT
ProbeSetXRef.Locus, ProbeSetXRef.LRS, ProbeSetXRef.pValue, ProbeSetXRef.mean, ProbeSetXRef.additive
FROM
ProbeSetXRef, ProbeSet
WHERE
ProbeSetXRef.ProbeSetId = ProbeSet.Id AND
ProbeSet.Name = "{}" AND
ProbeSetXRef.ProbeSetFreezeId ={}
""".format(trait.name, dataset.id)
logger.sql(query)
trait_qtl = g.db.execute(query).fetchone()
if trait_qtl:
trait.locus, trait.lrs, trait.pvalue, trait.mean, trait.additive = trait_qtl
if trait.locus:
query = """
select Geno.Chr, Geno.Mb from Geno, Species
where Species.Name = '{}' and
Geno.Name = '{}' and
Geno.SpeciesId = Species.Id
""".format(dataset.group.species, trait.locus)
logger.sql(query)
result = g.db.execute(query).fetchone()
if result:
trait.locus_chr = result[0]
trait.locus_mb = result[1]
else:
trait.locus = trait.locus_chr = trait.locus_mb = trait.additive = ""
else:
trait.locus = trait.locus_chr = trait.locus_mb = trait.additive = ""
else:
trait.locus = trait.locus_chr = trait.locus_mb = trait.lrs = trait.pvalue = trait.mean = trait.additive = ""
if dataset.type == 'Publish':
query = """
SELECT
PublishXRef.Locus, PublishXRef.LRS, PublishXRef.additive
FROM
PublishXRef, PublishFreeze
WHERE
PublishXRef.Id = %s AND
PublishXRef.InbredSetId = PublishFreeze.InbredSetId AND
PublishFreeze.Id =%s
""" % (trait.name, dataset.id)
logger.sql(query)
trait_qtl = g.db.execute(query).fetchone()
if trait_qtl:
trait.locus, trait.lrs, trait.additive = trait_qtl
if trait.locus:
query = """
select Geno.Chr, Geno.Mb from Geno, Species
where Species.Name = '{}' and
Geno.Name = '{}' and
Geno.SpeciesId = Species.Id
""".format(dataset.group.species, trait.locus)
logger.sql(query)
result = g.db.execute(query).fetchone()
if result:
trait.locus_chr = result[0]
trait.locus_mb = result[1]
else:
trait.locus = trait.locus_chr = trait.locus_mb = trait.additive = ""
else:
trait.locus = trait.locus_chr = trait.locus_mb = trait.additive = ""
else:
trait.locus = trait.lrs = trait.additive = ""
if (dataset.type == 'Publish' or dataset.type == "ProbeSet") and trait.locus_chr != "" and trait.locus_mb != "":
trait.LRS_location_repr = LRS_location_repr = 'Chr%s: %.6f' % (trait.locus_chr, float(trait.locus_mb))
if trait.lrs != "":
trait.LRS_score_repr = LRS_score_repr = '%3.1f' % trait.lrs
else:
raise KeyError, `trait.name`+' information is not found in the database.'
return trait
|