aboutsummaryrefslogtreecommitdiff
path: root/gn3/db/datasets.py
blob: 788e9cf99c0de15f5ce7308873b7fea2d58814d1 (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
"""
This module contains functions relating to specific trait dataset manipulation
"""
import re
from string import Template
from typing import Any, Dict, Optional
from SPARQLWrapper import JSON, SPARQLWrapper
from gn3.settings import SPARQL_ENDPOINT

def retrieve_probeset_trait_dataset_name(
        threshold: int, name: str, connection: Any):
    """
    Get the ID, DataScale and various name formats for a `ProbeSet` trait.
    """
    query = (
        "SELECT Id, Name, FullName, ShortName, DataScale "
        "FROM ProbeSetFreeze "
        "WHERE "
        "public > %(threshold)s "
        "AND "
        "(Name = %(name)s OR FullName = %(name)s OR ShortName = %(name)s)")
    with connection.cursor() as cursor:
        cursor.execute(
            query,
            {
                "threshold": threshold,
                "name": name
            })
        res = cursor.fetchone()
        if res:
            return dict(zip(
                ["dataset_id", "dataset_name", "dataset_fullname",
                 "dataset_shortname", "dataset_datascale"],
                res))
        return {"dataset_id": None, "dataset_name": name, "dataset_fullname": name}

def retrieve_publish_trait_dataset_name(
        threshold: int, name: str, connection: Any):
    """
    Get the ID, DataScale and various name formats for a `Publish` trait.
    """
    query = (
        "SELECT Id, Name, FullName, ShortName "
        "FROM PublishFreeze "
        "WHERE "
        "public > %(threshold)s "
        "AND "
        "(Name = %(name)s OR FullName = %(name)s OR ShortName = %(name)s)")
    with connection.cursor() as cursor:
        cursor.execute(
            query,
            {
                "threshold": threshold,
                "name": name
            })
        return dict(zip(
            ["dataset_id", "dataset_name", "dataset_fullname",
             "dataset_shortname"],
            cursor.fetchone()))

def retrieve_geno_trait_dataset_name(
        threshold: int, name: str, connection: Any):
    """
    Get the ID, DataScale and various name formats for a `Geno` trait.
    """
    query = (
        "SELECT Id, Name, FullName, ShortName "
        "FROM GenoFreeze "
        "WHERE "
        "public > %(threshold)s "
        "AND "
        "(Name = %(name)s OR FullName = %(name)s OR ShortName = %(name)s)")
    with connection.cursor() as cursor:
        cursor.execute(
            query,
            {
                "threshold": threshold,
                "name": name
            })
        return dict(zip(
            ["dataset_id", "dataset_name", "dataset_fullname",
             "dataset_shortname"],
            cursor.fetchone()))

def retrieve_temp_trait_dataset_name(
        threshold: int, name: str, connection: Any):
    """
    Get the ID, DataScale and various name formats for a `Temp` trait.
    """
    query = (
        "SELECT Id, Name, FullName, ShortName "
        "FROM TempFreeze "
        "WHERE "
        "public > %(threshold)s "
        "AND "
        "(Name = %(name)s OR FullName = %(name)s OR ShortName = %(name)s)")
    with connection.cursor() as cursor:
        cursor.execute(
            query,
            {
                "threshold": threshold,
                "name": name
            })
        return dict(zip(
            ["dataset_id", "dataset_name", "dataset_fullname",
             "dataset_shortname"],
            cursor.fetchone()))

def retrieve_dataset_name(
        trait_type: str, threshold: int, trait_name: str, dataset_name: str,
        conn: Any):
    """
    Retrieve the name of a trait given the trait's name

    This is extracted from the `webqtlDataset.retrieveName` function as is
    implemented at
    https://github.com/genenetwork/genenetwork1/blob/master/web/webqtl/base/webqtlDataset.py#L140-L169
    """
    fn_map = {
        "ProbeSet": retrieve_probeset_trait_dataset_name,
        "Publish": retrieve_publish_trait_dataset_name,
        "Geno": retrieve_geno_trait_dataset_name,
        "Temp": retrieve_temp_trait_dataset_name}
    if trait_type == "Temp":
        return retrieve_temp_trait_dataset_name(threshold, trait_name, conn)
    return fn_map[trait_type](threshold, dataset_name, conn)


def retrieve_geno_group_fields(name, conn):
    """
    Retrieve the Group, and GroupID values for various Geno trait types.
    """
    query = (
        "SELECT InbredSet.Name, InbredSet.Id "
        "FROM InbredSet, GenoFreeze "
        "WHERE GenoFreeze.InbredSetId = InbredSet.Id "
        "AND GenoFreeze.Name = %(name)s")
    with conn.cursor() as cursor:
        cursor.execute(query, {"name": name})
        return dict(zip(["group", "groupid"], cursor.fetchone()))
    return {}

def retrieve_publish_group_fields(name, conn):
    """
    Retrieve the Group, and GroupID values for various Publish trait types.
    """
    query = (
        "SELECT InbredSet.Name, InbredSet.Id "
        "FROM InbredSet, PublishFreeze "
        "WHERE PublishFreeze.InbredSetId = InbredSet.Id "
        "AND PublishFreeze.Name = %(name)s")
    with conn.cursor() as cursor:
        cursor.execute(query, {"name": name})
        return dict(zip(["group", "groupid"], cursor.fetchone()))
    return {}

def retrieve_probeset_group_fields(name, conn):
    """
    Retrieve the Group, and GroupID values for various ProbeSet trait types.
    """
    query = (
        "SELECT InbredSet.Name, InbredSet.Id "
        "FROM InbredSet, ProbeSetFreeze, ProbeFreeze "
        "WHERE ProbeFreeze.InbredSetId = InbredSet.Id "
        "AND ProbeFreeze.Id = ProbeSetFreeze.ProbeFreezeId "
        "AND ProbeSetFreeze.Name = %(name)s")
    with conn.cursor() as cursor:
        cursor.execute(query, {"name": name})
        return dict(zip(["group", "groupid"], cursor.fetchone()))
    return {}

def retrieve_temp_group_fields(name, conn):
    """
    Retrieve the Group, and GroupID values for `Temp` trait types.
    """
    query = (
        "SELECT InbredSet.Name, InbredSet.Id "
        "FROM InbredSet, Temp "
        "WHERE Temp.InbredSetId = InbredSet.Id "
        "AND Temp.Name = %(name)s")
    with conn.cursor() as cursor:
        cursor.execute(query, {"name": name})
        return dict(zip(["group", "groupid"], cursor.fetchone()))
    return {}

def retrieve_group_fields(trait_type, trait_name, dataset_info, conn):
    """
    Retrieve the Group, and GroupID values for various trait types.
    """
    group_fns_map = {
        "Geno": retrieve_geno_group_fields,
        "Publish": retrieve_publish_group_fields,
        "ProbeSet": retrieve_probeset_group_fields
    }

    if trait_type == "Temp":
        group_info = retrieve_temp_group_fields(trait_name, conn)
    else:
        group_info = group_fns_map[trait_type](dataset_info["dataset_name"], conn)

    return {
        **dataset_info,
        **group_info,
        "group": (
            "BXD" if group_info.get("group") == "BXD300"
            else group_info.get("group", ""))
    }

def retrieve_temp_trait_dataset():
    """
    Retrieve the dataset that relates to `Temp` traits
    """
    # pylint: disable=[C0330]
    return {
        "searchfield": ["name", "description"],
        "disfield": ["name", "description"],
        "type": "Temp",
        "dataset_id": 1,
        "fullname": "Temporary Storage",
        "shortname": "Temp"
    }

def retrieve_geno_trait_dataset():
    """
    Retrieve the dataset that relates to `Geno` traits
    """
    # pylint: disable=[C0330]
    return {
        "searchfield": ["name", "chr"],
	"disfield": ["name", "chr", "mb", "source2", "sequence"],
	"type": "Geno"
    }

def retrieve_publish_trait_dataset():
    """
    Retrieve the dataset that relates to `Publish` traits
    """
    # pylint: disable=[C0330]
    return {
        "searchfield": [
            "name", "post_publication_description", "abstract", "title",
            "authors"],
        "disfield": [
            "name", "pubmed_id", "pre_publication_description",
            "post_publication_description", "original_description",
	    "pre_publication_abbreviation", "post_publication_abbreviation",
	    "lab_code", "submitter", "owner", "authorized_users",
	    "authors", "title", "abstract", "journal", "volume", "pages",
            "month", "year", "sequence", "units", "comments"],
        "type": "Publish"
    }

def retrieve_probeset_trait_dataset():
    """
    Retrieve the dataset that relates to `ProbeSet` traits
    """
    # pylint: disable=[C0330]
    return {
        "searchfield": [
            "name", "description", "probe_target_description", "symbol",
            "alias", "genbankid", "unigeneid", "omim", "refseq_transcriptid",
            "probe_set_specificity", "probe_set_blat_score"],
	"disfield": [
            "name", "symbol", "description", "probe_target_description", "chr",
            "mb", "alias", "geneid", "genbankid", "unigeneid", "omim",
            "refseq_transcriptid", "blatseq", "targetseq", "chipid", "comments",
            "strand_probe", "strand_gene", "probe_set_target_region",
            "proteinid", "probe_set_specificity", "probe_set_blat_score",
            "probe_set_blat_mb_start", "probe_set_blat_mb_end",
            "probe_set_strand", "probe_set_note_by_rw", "flag"],
	"type": "ProbeSet"
    }

def retrieve_trait_dataset(trait_type, trait, threshold, conn):
    """
    Retrieve the dataset that relates to a specific trait.
    """
    dataset_fns = {
        "Temp": retrieve_temp_trait_dataset,
        "Geno": retrieve_geno_trait_dataset,
        "Publish": retrieve_publish_trait_dataset,
        "ProbeSet": retrieve_probeset_trait_dataset
    }
    dataset_name_info = {
        "dataset_id": None,
        "dataset_name": trait["db"]["dataset_name"],
        **retrieve_dataset_name(
            trait_type, threshold, trait["trait_name"],
            trait["db"]["dataset_name"], conn)
    }
    group = retrieve_group_fields(
        trait_type, trait["trait_name"], dataset_name_info, conn)
    return {
        "display_name": dataset_name_info["dataset_name"],
        **dataset_name_info,
        **dataset_fns[trait_type](),
        **group
    }

def sparql_query(query: str) -> Dict[str, Any]:
    """Run a SPARQL query and return the bound variables."""
    sparql = SPARQLWrapper(SPARQL_ENDPOINT)
    sparql.setQuery(query)
    sparql.setReturnFormat(JSON)
    return sparql.queryAndConvert()['results']['bindings']

def dataset_metadata(accession_id: str) -> Optional[Dict[str, Any]]:
    """Return info about dataset with ACCESSION_ID."""
    # Check accession_id to protect against query injection.
    # TODO: This function doesn't yet return the names of the actual dataset files.
    pattern = re.compile(r'GN\d+', re.ASCII)
    if not pattern.fullmatch(accession_id):
        return None
    # KLUDGE: We split the SPARQL query because virtuoso is very slow on a
    # single large query.
    queries = ["""
PREFIX gn: <http://genenetwork.org/>
SELECT ?name ?dataset_group ?status ?title ?geo_series
WHERE {
  ?dataset gn:accessionId "$accession_id" ;
           rdf:type gn:dataset ;
           gn:name ?name .
  OPTIONAL { ?dataset gn:datasetGroup ?dataset_group } .
  # FIXME: gn:datasetStatus should not be optional. But, some records don't
  # have it.
  OPTIONAL { ?dataset gn:datasetStatus ?status } .
  OPTIONAL { ?dataset gn:title ?title } .
  OPTIONAL { ?dataset gn:geoSeries ?geo_series } .
}
""",
               """
PREFIX gn: <http://genenetwork.org/>
SELECT ?platform_name ?normalization_name ?species_name ?inbred_set_name ?tissue_name
WHERE {
  ?dataset gn:accessionId "$accession_id" ;
           rdf:type gn:dataset ;
           gn:normalization / gn:name ?normalization_name ;
           gn:datasetOfSpecies / gn:menuName ?species_name ;
           gn:datasetOfInbredSet / gn:name ?inbred_set_name .
  OPTIONAL { ?dataset gn:datasetOfTissue / gn:name ?tissue_name } .
  OPTIONAL { ?dataset gn:datasetOfPlatform / gn:name ?platform_name } .
}
""",
               """
PREFIX gn: <http://genenetwork.org/>
SELECT ?specifics ?summary ?about_cases ?about_tissue ?about_platform
       ?about_data_processing ?notes ?experiment_design ?contributors
       ?citation ?acknowledgment
WHERE {
  ?dataset gn:accessionId "$accession_id" ;
           rdf:type gn:dataset .
  OPTIONAL { ?dataset gn:specifics ?specifics . }
  OPTIONAL { ?dataset gn:summary ?summary . }
  OPTIONAL { ?dataset gn:aboutCases ?about_cases . }
  OPTIONAL { ?dataset gn:aboutTissue ?about_tissue . }
  OPTIONAL { ?dataset gn:aboutPlatform ?about_platform . }
  OPTIONAL { ?dataset gn:aboutDataProcessing ?about_data_processing . }
  OPTIONAL { ?dataset gn:notes ?notes . }
  OPTIONAL { ?dataset gn:experimentDesign ?experiment_design . }
  OPTIONAL { ?dataset gn:contributors ?contributors . }
  OPTIONAL { ?dataset gn:citation ?citation . }
  OPTIONAL { ?dataset gn:acknowledgment ?acknowledgment . }
}
"""]
    result = {'accession_id': accession_id,
              'investigator': {}}
    query_result = {}
    for query in queries:
        if sparql_result := sparql_query(Template(query).substitute(accession_id=accession_id)):
            query_result.update(sparql_result[0])
        else:
            return None
    for key, value in query_result.items():
        result[key] = value['value']
    investigator_query_result = sparql_query(Template("""
PREFIX gn: <http://genenetwork.org/>
SELECT ?name ?address ?city ?state ?zip ?phone ?email ?country ?homepage
WHERE {
  ?dataset gn:accessionId "$accession_id" ;
           rdf:type gn:dataset ;
           gn:datasetOfInvestigator ?investigator .
  OPTIONAL { ?investigator foaf:name ?name . }
  OPTIONAL { ?investigator gn:address ?address . }
  OPTIONAL { ?investigator gn:city ?city . }
  OPTIONAL { ?investigator gn:state ?state . }
  OPTIONAL { ?investigator gn:zipCode ?zip . }
  OPTIONAL { ?investigator foaf:phone ?phone . }
  OPTIONAL { ?investigator foaf:mbox ?email . }
  OPTIONAL { ?investigator gn:country ?country . }
  OPTIONAL { ?investigator foaf:homepage ?homepage . }
}
""").substitute(accession_id=accession_id))[0]
    for key, value in investigator_query_result.items():
        result['investigator'][key] = value['value']
    return result