aboutsummaryrefslogtreecommitdiff
path: root/wqflask/base/trait.py
blob: e6e1c6b38ff9d26af140049f2a2a1a9bde761c8e (plain)
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
import requests
import simplejson as json
from wqflask import app

import utility.hmac as hmac
from base import webqtlConfig
from base.webqtlCaseData import webqtlCaseData
from base.data_set import create_dataset
from utility.authentication_tools import check_resource_availability
from utility.tools import GN2_BASE_URL, GN_PROXY_URL
from utility.redis_tools import get_redis_conn, get_resource_id

from flask import g, request, url_for

from wqflask.database import database_connection


Redis = get_redis_conn()


def create_trait(**kw):
    assert bool(kw.get('dataset')) != bool(
        kw.get('dataset_name')), "Needs dataset ob. or name"

    assert bool(kw.get('name')), "Needs trait name"


    if bool(kw.get('dataset')):
        dataset = kw.get('dataset')


    else:
        if kw.get('dataset_name') != "Temp":


            dataset = create_dataset(kw.get('dataset_name'))
        else:

            dataset = create_dataset(
                    dataset_name="Temp",
                    dataset_type="Temp",
                    group_name= kw.get('name').split("_")[2])


    if dataset.type == 'Publish':
        permissions = check_resource_availability(
            dataset, g.user_session.user_id, kw.get('name'))
    else:
        permissions = check_resource_availability(
            dataset, g.user_session.user_id)


    if permissions['data'] != "no-access":
        
        the_trait = GeneralTrait(**dict(kw,dataset=dataset))
        if the_trait.dataset.type != "Temp":
            the_trait = retrieve_trait_info(
                the_trait,
                the_trait.dataset,
                get_qtl_info=kw.get('get_qtl_info'))
        return the_trait
    else:
        return None


class GeneralTrait:
    """
    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 kw.get("dataset"), "Dataset obj is needed as a kwarg"

        # Trait ID, ProbeSet ID, Published ID, etc.
        self.name = kw.get('name')
        self.dataset = kw.get("dataset")
        self.cellid = kw.get('cellid')
        self.identification = kw.get('identification', 'un-named trait')
        self.haveinfo = kw.get('haveinfo', False)
        # Blat sequence, available for ProbeSet
        self.sequence = kw.get('sequence')
        self.data = kw.get('data', {})
        self.view = True

        # 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.abbreviation = None
        self.display_name = self.name

        self.LRS_score_repr = "N/A"
        self.LRS_location_repr = "N/A"
        self.chr = self.mb = self.locus_chr = self.locus_mb = ""

        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 get_sample_info is not 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 list(self.data.items()):
            if sample_data.value is not None:
                if not include_variance or sample_data.variance is not 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"
        if isinstance(formatted, bytes):
            formatted = formatted.decode("utf-8")
        return formatted

    @property
    def alias_fmt(self):
        """Return a text formatted alias"""

        alias = 'Not available'
        if getattr(self, "alias", None):
            alias = self.alias.replace(";", " ")
            alias = ", ".join(alias.split())

        return alias

    @property
    def wikidata_alias_fmt(self):
        """Return a text formatted alias"""

        alias = 'Not available'
        if self.symbol:
            human_response = requests.get(
                GN2_BASE_URL + "gn3/gene/aliases/" + self.symbol.upper())
            mouse_response = requests.get(
                GN2_BASE_URL + "gn3/gene/aliases/" + self.symbol.capitalize())
            other_response = requests.get(
                GN2_BASE_URL + "gn3/gene/aliases/" + self.symbol.lower())

            if human_response and mouse_response and other_response:
                alias_list = json.loads(human_response.content) + json.loads(
                    mouse_response.content) + \
                    json.loads(other_response.content)

                filtered_aliases = []
                seen = set()
                for item in alias_list:
                    if item in seen:
                        continue
                    else:
                        filtered_aliases.append(item)
                        seen.add(item)
                alias = "; ".join(filtered_aliases)

        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 == "Un":
            return 'Not available'

        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 is None:
        samplelist = []

    if dataset.type == "Temp":
        results = Redis.get(trait.name).split()
    else:
        results = dataset.retrieve_sample_data(trait.name)
    # Todo: is this necessary? If not remove
    trait.data.clear()

    if results:
        if dataset.type == "Temp":
            all_samples_ordered = dataset.group.all_samples_ordered()
            for i, item in enumerate(results):
                try:
                    trait.data[all_samples_ordered[i]] = webqtlCaseData(
                        all_samples_ordered[i], float(item))
                except:
                    pass
        else:
            for item in results:
                name, value, variance, num_cases, name2 = item
                if not samplelist or (samplelist and name in samplelist):
                    # name, value, variance, num_cases)
                    trait.data[name] = webqtlCaseData(*item)
    return trait


@app.route("/trait/get_sample_data")
def get_sample_data():
    params = request.args
    trait = params['trait']
    dataset = params['dataset']

    trait_ob = create_trait(name=trait, dataset_name=dataset)
    if trait_ob:
        trait_dict = {}
        trait_dict['name'] = trait
        trait_dict['db'] = dataset
        trait_dict['type'] = trait_ob.dataset.type
        trait_dict['group'] = trait_ob.dataset.group.name
        trait_dict['tissue'] = trait_ob.dataset.tissue
        trait_dict['species'] = trait_ob.dataset.group.species
        trait_dict['url'] = url_for(
            'show_trait_page', trait_id=trait, dataset=dataset)
        if trait_ob.dataset.type == "ProbeSet":
            trait_dict['symbol'] = trait_ob.symbol
            trait_dict['location'] = trait_ob.location_repr
            trait_dict['description'] = trait_ob.description_display
        elif trait_ob.dataset.type == "Publish":
            trait_dict['description'] = trait_ob.description_display
            if trait_ob.pubmed_id:
                trait_dict['pubmed_link'] = trait_ob.pubmed_link
            trait_dict['pubmed_text'] = trait_ob.pubmed_text
        else:
            trait_dict['location'] = trait_ob.location_repr

        return json.dumps([trait_dict, {key: value.value for
                                        key, value in list(
                                            trait_ob.data.items())}])
    else:
        return None


def jsonable(trait, dataset=None):
    """Return a dict suitable for using as json

    Actual turning into json doesn't happen here though"""

    if not dataset:
        dataset = create_dataset(dataset_name=trait.dataset.name,
                                dataset_type=trait.dataset.type,
                                group_name=trait.dataset.group.name)


    trait_symbol = "N/A"
    trait_mean = "N/A"
    if trait.symbol:
        trait_symbol = trait.symbol
    if trait.mean:
        trait_mean = trait.mean

    if dataset.type == "ProbeSet":
        return dict(name=trait.name,
                    display_name=trait.display_name,
                    hmac=hmac.data_hmac('{}:{}'.format(trait.display_name, dataset.name)),
                    view=str(trait.view),
                    symbol=trait_symbol,
                    dataset=dataset.name,
                    dataset_name=dataset.shortname,
                    description=trait.description_display,
                    mean=trait_mean,
                    location=trait.location_repr,
                    chr=trait.chr,
                    mb=trait.mb,
                    lrs_score=trait.LRS_score_repr,
                    lrs_location=trait.LRS_location_repr,
                    lrs_chr=trait.locus_chr,
                    lrs_mb=trait.locus_mb,
                    additive=trait.additive
                    )
    elif dataset.type == "Publish":
        if trait.pubmed_id:
            return dict(name=trait.name,
                        display_name=trait.display_name,
                        hmac=hmac.data_hmac('{}:{}'.format(trait.name, dataset.name)),
                        view=str(trait.view),
                        symbol=trait.abbreviation,
                        dataset=dataset.name,
                        dataset_name=dataset.shortname,
                        description=trait.description_display,
                        abbreviation=trait.abbreviation,
                        authors=trait.authors,
                        pubmed_id=trait.pubmed_id,
                        pubmed_text=trait.pubmed_text,
                        pubmed_link=trait.pubmed_link,
                        mean=trait_mean,
                        lrs_score=trait.LRS_score_repr,
                        lrs_location=trait.LRS_location_repr,
                        lrs_chr=trait.locus_chr,
                        lrs_mb=trait.locus_mb,
                        additive=trait.additive
                        )
        else:
            return dict(name=trait.name,
                        display_name=trait.display_name,
                        hmac=hmac.data_hmac('{}:{}'.format(trait.name, dataset.name)),
                        view=str(trait.view),
                        symbol=trait.abbreviation,
                        dataset=dataset.name,
                        dataset_name=dataset.shortname,
                        description=trait.description_display,
                        abbreviation=trait.abbreviation,
                        authors=trait.authors,
                        pubmed_text=trait.pubmed_text,
                        mean=trait_mean,
                        lrs_score=trait.LRS_score_repr,
                        lrs_location=trait.LRS_location_repr,
                        lrs_chr=trait.locus_chr,
                        lrs_mb=trait.locus_mb,
                        additive=trait.additive
                        )
    elif dataset.type == "Geno":
        return dict(name=trait.name,
                    display_name=trait.display_name,
                    hmac=hmac.data_hmac('{}:{}'.format(trait.display_name, dataset.name)),
                    view=str(trait.view),
                    dataset=dataset.name,
                    dataset_name=dataset.shortname,
                    location=trait.location_repr,
                    chr=trait.chr,
                    mb=trait.mb
                    )
    elif dataset.name == "Temp":
        return dict(name=trait.name,
                    display_name=trait.display_name,
                    hmac=hmac.data_hmac('{}:{}'.format(trait.display_name, dataset.name)),
                    view=str(trait.view),
                    dataset="Temp",
                    dataset_name="Temp")
    else:
        return dict()


def retrieve_trait_info(trait, dataset, get_qtl_info=False):
    if not dataset:
        raise ValueError("Dataset doesn't exist")

    with database_connection() as conn, conn.cursor() as cursor:
        trait_info = ()
        if dataset.type == 'Publish':
            cursor.execute(
                "SELECT PublishXRef.Id, InbredSet.InbredSetCode, "
                "Publication.PubMed_ID, "
                "CAST(Phenotype.Pre_publication_description AS BINARY), "
                "CAST(Phenotype.Post_publication_description AS BINARY), "
                "CAST(Phenotype.Original_description AS BINARY), "
                "CAST(Phenotype.Pre_publication_abbreviation AS BINARY), "
                "CAST(Phenotype.Post_publication_abbreviation AS BINARY), "
                "PublishXRef.mean, Phenotype.Lab_code, "
                "Phenotype.Submitter, Phenotype.Owner, "
                "Phenotype.Authorized_Users, "
                "CAST(Publication.Authors AS BINARY), "
                "CAST(Publication.Title AS BINARY), "
                "CAST(Publication.Abstract AS BINARY), "
                "CAST(Publication.Journal AS BINARY), "
                "Publication.Volume, Publication.Pages, "
                "Publication.Month, Publication.Year, "
                "PublishXRef.Sequence, Phenotype.Units, "
                "PublishXRef.comments FROM PublishXRef, Publication, "
                "Phenotype, PublishFreeze, InbredSet WHERE "
                "PublishXRef.Id = %s AND "
                "Phenotype.Id = PublishXRef.PhenotypeId "
                "AND Publication.Id = PublishXRef.PublicationId "
                "AND PublishXRef.InbredSetId = PublishFreeze.InbredSetId "
                "AND PublishXRef.InbredSetId = InbredSet.Id AND "
                "PublishFreeze.Id = %s",
                (trait.name, dataset.id,)
            )
            trait_info = cursor.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 = f'ProbeSet.{display_fields_string}'
            cursor.execute(
                f"SELECT {display_fields_string} FROM ProbeSet, ProbeSetFreeze, "
                "ProbeSetXRef WHERE "
                "ProbeSetXRef.ProbeSetFreezeId = ProbeSetFreeze.Id "
                "AND ProbeSetXRef.ProbeSetId = ProbeSet.Id AND "
                "ProbeSetFreeze.Name = %s AND "
                "ProbeSet.Name = %s",
                (dataset.name, str(trait.name),)
            )
            trait_info = cursor.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 = ',Geno.'.join(dataset.display_fields)
            display_fields_string = f'Geno.{display_fields_string}'
            cursor.execute(
                f"SELECT {display_fields_string} FROM Geno, GenoFreeze, "
                "GenoXRef WHERE "
                "GenoXRef.GenoFreezeId = GenoFreeze.Id "
                "AND GenoXRef.GenoId = Geno.Id "
                "AND GenoFreeze.Name = %s "
                "AND Geno.Name = %s",
                (dataset.name, trait.name)
            )
            trait_info = cursor.fetchone()
        else:  # Temp type
            cursor.execute(
                f"SELECT {','.join(dataset.display_fields)} "
                f"FROM {dataset.type} WHERE Name = %s",
                (trait.name,)
            )
            trait_info = cursor.fetchone()

        if trait_info:
            trait.haveinfo = True
            for i, field in enumerate(dataset.display_fields):
                holder = trait_info[i]
                if isinstance(holder, bytes):
                    holder = holder.decode("utf-8", errors="ignore")
                setattr(trait, field, holder)

            if dataset.type == 'Publish':
                if trait.group_code:
                    trait.display_name = trait.group_code + "_" + str(trait.name)

                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
                trait.description_display = "N/A"
                trait.abbreviation = "N/A"
                if not trait.pubmed_id:
                    if trait.pre_publication_abbreviation:
                        trait.abbreviation = trait.pre_publication_abbreviation
                    if trait.pre_publication_description:
                        trait.description_display = trait.pre_publication_description
                else:
                    if trait.post_publication_abbreviation:
                        trait.abbreviation = trait.post_publication_abbreviation
                    if description:
                        trait.description_display = description.strip()

                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 = trait.description
                target_string = trait.probe_target_description

                if str(description_string or "") != "" and description_string != 'None':
                    description_display = description_string
                else:
                    description_display = trait.symbol

                if (str(description_display or "") != ""
                    and description_display != 'N/A'
                        and str(target_string or "") != "" 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"
                trait.locus = trait.locus_chr = trait.locus_mb = trait.lrs = trait.pvalue = trait.additive = ""
                if dataset.type == 'ProbeSet' and not trait.cellid:
                    trait.mean = ""
                    cursor.execute(
                        "SELECT ProbeSetXRef.Locus, ProbeSetXRef.LRS, "
                        "ProbeSetXRef.pValue, ProbeSetXRef.mean, "
                        "ProbeSetXRef.additive FROM ProbeSetXRef, "
                        "ProbeSet WHERE "
                        "ProbeSetXRef.ProbeSetId = ProbeSet.Id "
                        "AND ProbeSet.Name = %s AND "
                        "ProbeSetXRef.ProbeSetFreezeId = %s",
                        (trait.name, dataset.id,)
                    )
                    trait_qtl = cursor.fetchone()
                    if any(trait_qtl):
                        trait.locus, trait.lrs, trait.pvalue, trait.mean, trait.additive = trait_qtl
                        if trait.locus:
                            cursor.execute(
                                "SELECT Geno.Chr, Geno.Mb FROM "
                                "Geno, Species WHERE "
                                "Species.Name = %s AND "
                                "Geno.Name = %s AND "
                                "Geno.SpeciesId = Species.Id",
                                (dataset.group.species, trait.locus,)
                            )
                            if result := cursor.fetchone() :
                                trait.locus_chr = result[0]
                                trait.locus_mb = result[1]
                            else:
                                trait.locus_chr = trait.locus_mb = ""
                        else:
                            trait.locus = trait.locus_chr = trait.locus_mb = trait.additive = ""

                if dataset.type == 'Publish':
                    cursor.execute(
                        "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,)
                    )
                    if trait_qtl := cursor.fetchone():
                        trait.locus, trait.lrs, trait.additive = trait_qtl
                        if trait.locus:
                            cursor.execute(
                                "SELECT Geno.Chr, Geno.Mb FROM Geno, "
                                "Species WHERE Species.Name = %s "
                                "AND Geno.Name = %s AND "
                                "Geno.SpeciesId = Species.Id",
                                (dataset.group.species, trait.locus,)
                            )
                            if result := cursor.fetchone():
                                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"):
                    if str(trait.locus_chr or "") != "" and str(trait.locus_mb or "") != "":
                        trait.LRS_location_repr = LRS_location_repr = 'Chr%s: %.6f' % (
                            trait.locus_chr, float(trait.locus_mb))
                    if str(trait.lrs or "") != "":
                        trait.LRS_score_repr = LRS_score_repr = '%3.1f' % trait.lrs
        else:
            raise KeyError(
                f"{repr(trait.name)} information is not found in the database "
                f"for dataset '{dataset.name}' with id '{dataset.id}'.")
        return trait