aboutsummaryrefslogtreecommitdiff
path: root/wqflask/maintenance/quick_search_table.py
blob: 75bc7d009602e7caf85cee41bfa6cc2288b991df (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
from __future__ import print_function, division, absolute_import

"""
Results will be returned for each of several trait types: mRNA assays, phenotypes, genotypes, and
(maybe later) genes

For each trait type, the results for each species should be given; for example, have a "Mouse" tab
with the mouse traits in a table inside it

This table will then list each trait, its dataset, and several columns determined by its trait type
(phenotype, genotype, etc)

"""


import sys
sys.path.append("../../..")

import simplejson as json

import sqlalchemy as sa
from sqlalchemy.dialects import mysql
from sqlalchemy.orm import scoped_session, sessionmaker, relationship, backref
from sqlalchemy.orm.exc import NoResultFound
from sqlalchemy.ext.declarative import declarative_base

from pprint import pformat as pf

import zach_settings as settings

Engine = sa.create_engine(settings.SQLALCHEMY_DATABASE_URI,
                       #encoding='utf-8',
                       #client_encoding='utf-8',
                       #echo="debug",
                       )

Session = scoped_session(sessionmaker(bind=Engine)) #, extension=VersionedListener()))

Base = declarative_base(bind=Engine)
Metadata = sa.MetaData()
Metadata.bind = Engine

class PublishXRef(Base):
    __tablename__ = 'PublishXRef'
    
    Id = sa.Column(sa.Integer, primary_key=True)
    InbredSetId = sa.Column(sa.Integer, primary_key=True)
    PhenotypeId = sa.Column(sa.Integer)
    PublicationId = sa.Column(sa.Integer)
    DataId = sa.Column(sa.Integer)
    Locus = sa.Column(sa.Text)
    LRS = sa.Column(sa.Float)
    additive = sa.Column(sa.Float)
    Sequence = sa.Column(sa.Integer)
    comments = sa.Column(sa.Text)
    
    @classmethod
    def run(cls):
        conn = Engine.connect()
        counter = 0
        for ps in page_query(Session.query(cls)):   #all()
            values = {}
            values['table_name'] = cls.__tablename__
            values['the_key'] = json.dumps([ps.Id, ps.InbredSetId])
            values['terms'] = cls.get_unique_terms(ps.Id, ps.InbredSetId)
            print("terms is:", values['terms'])
            values['result_fields'] = cls.get_result_fields(ps.Id, ps.InbredSetId)
            ins = QuickSearch.insert().values(**values)
            conn.execute(ins)
            counter += 1
            print("Done:", counter)
            
    @staticmethod
    def get_unique_terms(publishxref_id, inbredset_id):
        results = Session.query(
                "pre_publication_description",
                "post_publication_description",
                "pre_publication_abbreviation",
                "post_publication_abbreviation",
                "publication_title"
            ).from_statement(
                "SELECT Phenotype.Pre_publication_description as pre_publication_description, "
                "Phenotype.Post_publication_description as post_publication_description, "
                "Phenotype.Pre_publication_abbreviation as pre_publication_abbreviation, "
                "Phenotype.Post_publication_abbreviation as post_publication_abbreviation, "
                "Publication.Title as publication_title "
                "FROM Phenotype, Publication, PublishXRef "
                "WHERE PublishXRef.Id = :publishxref_id and "
                "PublishXRef.InbredSetId = :inbredset_id and "
                "PublishXRef.PhenotypeId = Phenotype.Id and "
                "PublishXRef.PublicationId = Publication.Id ").params(publishxref_id=publishxref_id,
                                                            inbredset_id=inbredset_id).all()

        unique = set()
        for item in results[0]:
            #print("locals:", locals())
            if not item:
                continue
            for token in item.split():
                if token.startswith(('(','[')):
                    token = token[1:]
                if token.endswith((')', ']')):
                    token = token[:-1]
                if token.endswith(';'):
                    token = token[:-1]
                if len(token) > 2:
                    try:
                        # This hopefully ensures that the token is utf-8
                        token = token.encode('utf-8')
                        print(" ->", token)
                    except UnicodeDecodeError:
                        print("\n-- UDE \n")
                        # Can't get it into utf-8, we won't use it
                        continue 

                    unique.add(token)
        print("\nUnique terms are: {}\n".format(unique))
        return " ".join(unique)            

    @staticmethod
    def get_result_fields(publishxref_id, inbredset_id):
        results = Session.query(
                "phenotype_id",
                "species",
                "group_name",
                "description",
                "lrs",
                "publication_id",
                "pubmed_id",
                "year",
                "authors"
            ).from_statement(
                "SELECT PublishXRef.PhenotypeId as phenotype_id, "
                "Species.Name as species, "
                "InbredSet.Name as group_name, "
                "Phenotype.Original_description as description, "
                "PublishXRef.LRS as lrs, "
                "PublishXRef.PublicationId as publication_id, "
                "Publication.PubMed_ID"
                "Publication.Year as year, "
                "Publication.Authors as authors "
                "FROM PublishXRef, "
                "Phenotype, "
                "Publication, "
                "InbredSet, "
                "Species "
                "WHERE PublishXRef.Id = :publishxref_id and "
                "PublishXRef.InbredSetId = :inbredset_id and "
                "PublishXRef.PhenotypeId = Phenotype.Id and "
                "PublishXRef.PublicationId = Publication.Id and "
                "InbredSet.Id = :inbredset_id and "
                "Species.Id = InbredSet.SpeciesId ").params(publishxref_id=publishxref_id,
                                                            inbredset_id=inbredset_id).all()                
                #"InbredSet.SpeciesId = Species.Id and "
                #"Geno.SpeciesId = Species.Id and "
                #"Geno.Name = PublishXRef.Locus ").params(publishxref_id=publishxref_id,
                #                                            inbredset_id=inbredset_id).all()
        for result in results:
            print("****", result)

        assert len(set(result for result in results)) == 1, "Different results or no results"

        print("results are:", results)
        result = results[0]
        result = row2dict(result)
        try:
            json_results = json.dumps(result, sort_keys=True)
        except UnicodeDecodeError:
            print("\n\nTrying to massage unicode\n\n")
            for key, value in result.iteritems():
                print("\tkey is:", key)
                print("\tvalue is:", value)
                if isinstance(value, basestring):
                    result[key] = value.decode('utf-8', errors='ignore')
            json_results = json.dumps(result, sort_keys=True)

        return json_results

class GenoXRef(Base):
    __tablename__ = 'GenoXRef'
    
    GenoFreezeId = sa.Column(sa.Integer, primary_key=True)
    GenoId = sa.Column(sa.Integer, primary_key=True)
    DataId = sa.Column(sa.Integer)
    cM = sa.Column(sa.Float)
    Used_for_mapping = sa.Column(sa.Text)

    @classmethod
    def run(cls):
        conn = Engine.connect()
        counter = 0
        for item in page_query(Session.query(cls)):   #all()
            values = {}
            values['table_name'] = cls.__tablename__
            values['the_key'] = json.dumps([item.GenoId, item.GenoFreezeId])
            values['terms'] = cls.get_unique_terms(item.GenoId)
            print("terms is:", values['terms'])
            if values['terms']:
                values['result_fields'] = cls.get_result_fields(item.GenoId, item.GenoFreezeId)
                ins = QuickSearch.insert().values(**values)
                conn.execute(ins)
            counter += 1
            print("Done:", counter)
    
    @staticmethod
    def get_unique_terms(geno_id):
        print("geno_id: ", geno_id)
        results = Session.query(
                "name",
                "marker_name"
            ).from_statement(
                "SELECT Geno.Name as name, "
                "Geno.Marker_Name as marker_name "
                "FROM Geno "
                "WHERE Geno.Id = :geno_id ").params(geno_id=geno_id).all()
        
        print("results: ", pf(results))
        
        unique = set()
        if len(results):
            for item in results[0]:
                #print("locals:", locals())
                if not item:
                    continue
                for token in item.split():
                    if len(token) > 2:
                        try:
                            # This hopefully ensures that the token is utf-8
                            token = token.encode('utf-8')
                            print(" ->", token)
                        except UnicodeDecodeError:
                            print("\n-- UDE \n")
                            # Can't get it into utf-8, we won't use it
                            continue 
                        
                        unique.add(token)
        print("\nUnique terms are: {}\n".format(unique))
        return " ".join(unique)


    @staticmethod
    def get_result_fields(geno_id, dataset_id):
        results = Session.query(
                "name",
                "marker_name",
                "group_name",
                "species",
                "dataset",
                "dataset_name",
                "chr", "mb",
                "source"
            ).from_statement(
                "SELECT Geno.Name as name, "
                "Geno.Marker_Name as marker_name, "
                "InbredSet.Name as group_name, "
                "Species.Name as species, "
                "GenoFreeze.Name as dataset, "
                "GenoFreeze.FullName as dataset_name, "
                "Geno.Chr as chr, "
                "Geno.Mb as mb, "
                "Geno.Source as source "
                "FROM Geno, "
                "GenoXRef, "
                "GenoFreeze, "
                "InbredSet, "
                "Species "
                "WHERE Geno.Id = :geno_id and "
                "GenoXRef.GenoId = Geno.Id and "
                "GenoFreeze.Id = :dataset_id and "
                "GenoXRef.GenoFreezeId = GenoFreeze.Id and "
                "InbredSet.Id = GenoFreeze.InbredSetId and "
                "InbredSet.SpeciesId = Species.Id ").params(geno_id=geno_id,
                                                                    dataset_id=dataset_id).all()
        for result in results:
            print(result)
        assert len(set(result for result in results)) == 1, "Different results"
        
        print("results are:", results)
        result = results[0]
        result = row2dict(result)
        try:
            json_results = json.dumps(result, sort_keys=True)
        except UnicodeDecodeError:
            print("\n\nTrying to massage unicode\n\n")
            for key, value in result.iteritems():
                print("\tkey is:", key)
                print("\tvalue is:", value)
                if isinstance(value, basestring):
                    result[key] = value.decode('utf-8', errors='ignore')
            json_results = json.dumps(result, sort_keys=True)

        return json_results    

class ProbeSetXRef(Base):
    __tablename__ = 'ProbeSetXRef'
    
    ProbeSetFreezeId = sa.Column(sa.Integer, primary_key=True)
    ProbeSetId = sa.Column(sa.Integer, primary_key=True)
    DataId = sa.Column(sa.Integer, unique=True)
    Locus_old = sa.Column(sa.Text)
    LRS_old = sa.Column(sa.Float)
    pValue_old = sa.Column(sa.Float)
    mean = sa.Column(sa.Float)
    se = sa.Column(sa.Float)
    Locus = sa.Column(sa.Text)
    LRS = sa.Column(sa.Float)
    pValue = sa.Column(sa.Float)
    additive = sa.Column(sa.Float)
    h2 = sa.Column(sa.Float)

    @classmethod
    def run(cls):
        conn = Engine.connect()
        counter = 0
        for ps in page_query(Session.query(cls)):   #all()
            values = {}
            values['table_name'] = cls.__tablename__
            values['the_key'] = json.dumps([ps.ProbeSetId, ps.ProbeSetFreezeId])
            values['terms'] = cls.get_unique_terms(ps.ProbeSetId)
            print("terms is:", values['terms'])
            #values['species'] = get_species("ProbeSet", ps.Id)
            values['result_fields'] = cls.get_result_fields(ps.ProbeSetId, ps.ProbeSetFreezeId)
            ins = QuickSearch.insert().values(**values)
            conn.execute(ins)
            counter += 1
            print("Done:", counter)
    
    @staticmethod
    def get_unique_terms(probeset_id):
        results = Session.query(
                "name",
                "symbol",
                "description",
                "alias"
            ).from_statement(
                "SELECT ProbeSet.Name as name, "
                "ProbeSet.Symbol as symbol, "
                "ProbeSet.description as description, "
                "ProbeSet.alias as alias "
                "FROM ProbeSet "
                "WHERE ProbeSet.Id = :probeset_id ").params(probeset_id=probeset_id).all()
        
        unique = set()
        for item in results[0]:
            #print("locals:", locals())
            if not item:
                continue
            for token in item.split():
                if token.startswith(('(','[')):
                    token = token[1:]
                if token.endswith((')', ']')):
                    token = token[:-1]
                if token.endswith(';'):
                    token = token[:-1]
                if len(token) > 2:
                    try:
                        # This hopefully ensures that the token is utf-8
                        token = token.encode('utf-8')
                        print(" ->", token)
                    except UnicodeDecodeError:
                        print("\n-- UDE \n")
                        # Can't get it into utf-8, we won't use it
                        continue 
                    
                    unique.add(token)
        print("\nUnique terms are: {}\n".format(unique))
        return " ".join(unique)


    @staticmethod
    def get_result_fields(probeset_id, dataset_id):
        results = Session.query(
                "name",
                "species",
                "group_name",
                "dataset",
                "dataset_name",
                "symbol",
                "description",
                "chr", "mb",
                "lrs", "mean",
                "genbank_id",
                "gene_id",
                "chip_id",
                "chip_name"
            ).from_statement(
                "SELECT ProbeSet.Name as name, "
                "Species.Name as species, "
                "InbredSet.Name as group_name, "
                "ProbeSetFreeze.Name as dataset, "
                "ProbeSetFreeze.FullName as dataset_name, "
                "ProbeSet.Symbol as symbol, "
                "ProbeSet.description as description, "
                "ProbeSet.Chr as chr, "
                "ProbeSet.Mb as mb, "
                "ProbeSetXRef.LRS as lrs, "
                "ProbeSetXRef.mean as mean, "
                "ProbeSet.GenbankId as genbank_id, "
                "ProbeSet.GeneId as gene_id, "
                "ProbeSet.ChipId as chip_id, "
                "GeneChip.Name as chip_name "
                "FROM ProbeSet, "
                "ProbeSetXRef, "
                "ProbeSetFreeze, "
                "ProbeFreeze, "
                "InbredSet, "
                "Species, "
                "GeneChip "
                "WHERE ProbeSetXRef.ProbeSetId = :probeset_id and "
                "ProbeSetXRef.ProbeSetFreezeId = :dataset_id and "
                "ProbeSetXRef.ProbeSetId = ProbeSet.Id and "
                "ProbeSet.ChipId = GeneChip.Id and "
                "ProbeSetXRef.ProbeSetFreezeId = ProbeSetFreeze.Id and "
                "ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id and "
                "ProbeFreeze.InbredSetId = InbredSet.Id and "
                "InbredSet.SpeciesId = Species.Id ").params(probeset_id=probeset_id,
                                                                    dataset_id=dataset_id).all()
        for result in results:
            print(result)
        assert len(set(result for result in results)) == 1, "Different results"
        
        print("results are:", results)
        result = results[0]
        result = row2dict(result)
        try:
            json_results = json.dumps(result, sort_keys=True)
        except UnicodeDecodeError:
            print("\n\nTrying to massage unicode\n\n")
            for key, value in result.iteritems():
                print("\tkey is:", key)
                print("\tvalue is:", value)
                if isinstance(value, basestring):
                    result[key] = value.decode('utf-8', errors='ignore')
            json_results = json.dumps(result, sort_keys=True)

        return json_results    


QuickSearch = sa.Table("QuickSearch", Metadata,
        sa.Column('table_name', sa.String(15),
                  primary_key=True, nullable=False, autoincrement=False), # table that item is inserted from
        sa.Column('the_key', sa.String(30),
                  primary_key=True, nullable=False, autoincrement=False), # key in database table
        sa.Column('terms', sa.Text), # terms to compare search string with
        sa.Column('result_fields', sa.Text)  # json
                    )

QuickSearch.drop(Engine, checkfirst=True)
Metadata.create_all(Engine)


def row2dict(row):
    """http://stackoverflow.com/a/2848519/1175849"""
    return dict(zip(row.keys(), row))


def page_query(q):
    """http://stackoverflow.com/a/1217947/1175849"""
    offset = 0
    while True:
        r = False
        for elem in q.limit(1000).offset(offset):
           r = True
           yield elem
        offset += 1000
        if not r:
            break


def main():
    GenoXRef.run()
    ProbeSetXRef.run()
    PublishXRef.run()

if __name__ == "__main__":
    main()