aboutsummaryrefslogtreecommitdiff
path: root/wqflask/base/data_set/dataset.py
blob: f035e0288cfe634c6e194cf5fc051433d33d9cf7 (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
"Base Dataset class ..."

import math
import collections


from redis import Redis


from base import species
from utility import chunks
from .datasetgroup import DatasetGroup
from wqflask.database import database_connection
from utility.db_tools import escape, mescape, create_in_clause
from .utils import fetch_cached_results, cache_dataset_results

class DataSet:
    """
    DataSet class defines a dataset in webqtl, can be either Microarray,
    Published phenotype, genotype, or user input dataset(temp)

    """

    def __init__(self, name, get_samplelist=True, group_name=None, redis_conn=Redis()):

        assert name, "Need a name"
        self.name = name
        self.id = None
        self.shortname = None
        self.fullname = None
        self.type = None
        self.data_scale = None  # ZS: For example log2
        self.accession_id = None

        self.setup()

        if self.type == "Temp":  # Need to supply group name as input if temp trait
            # sets self.group and self.group_id and gets genotype
            self.group = DatasetGroup(self, name=group_name)
        else:
            self.check_confidentiality()
            self.retrieve_other_names()
            # sets self.group and self.group_id and gets genotype
            self.group = DatasetGroup(self)
            self.accession_id = self.get_accession_id()
        if get_samplelist == True:
            self.group.get_samplelist(redis_conn)
        self.species = species.TheSpecies(self)

    def as_dict(self):
        return {
            'name': self.name,
            'shortname': self.shortname,
            'fullname': self.fullname,
            'type': self.type,
            'data_scale': self.data_scale,
            'group': self.group.name,
            'accession_id': self.accession_id
        }

    def get_accession_id(self):
        results = None
        with database_connection() as conn, conn.cursor() as cursor:
            if self.type == "Publish":
                cursor.execute(
                    "SELECT InfoFiles.GN_AccesionId FROM "
                    "InfoFiles, PublishFreeze, InbredSet "
                    "WHERE InbredSet.Name = %s AND "
                    "PublishFreeze.InbredSetId = InbredSet.Id "
                    "AND InfoFiles.InfoPageName = PublishFreeze.Name "
                    "AND PublishFreeze.public > 0 AND "
                    "PublishFreeze.confidentiality < 1 "
                    "ORDER BY PublishFreeze.CreateTime DESC",
                    (self.group.name,)
                )
                results = cursor.fetchone()
            elif self.type == "Geno":
                cursor.execute(
                    "SELECT InfoFiles.GN_AccesionId FROM "
                    "InfoFiles, GenoFreeze, InbredSet "
                    "WHERE InbredSet.Name = %s AND "
                    "GenoFreeze.InbredSetId = InbredSet.Id "
                    "AND InfoFiles.InfoPageName = GenoFreeze.ShortName "
                    "AND GenoFreeze.public > 0 AND "
                    "GenoFreeze.confidentiality < 1 "
                    "ORDER BY GenoFreeze.CreateTime DESC",
                    (self.group.name,)
                )
                results = cursor.fetchone()

        if results:
            return str(results[0])
        return "None"

    def retrieve_other_names(self):
        """This method fetches the the dataset names in search_result.

        If the data set name parameter is not found in the 'Name' field of
        the data set table, check if it is actually the FullName or
        ShortName instead.

        This is not meant to retrieve the data set info if no name at
        all is passed.

        """
        with database_connection() as conn, conn.cursor() as cursor:
            try:
                if self.type == "ProbeSet":
                    cursor.execute(
                        "SELECT ProbeSetFreeze.Id, ProbeSetFreeze.Name, "
                        "ProbeSetFreeze.FullName, ProbeSetFreeze.ShortName, "
                        "ProbeSetFreeze.DataScale, Tissue.Name "
                        "FROM ProbeSetFreeze, ProbeFreeze, Tissue "
                        "WHERE ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id "
                        "AND ProbeFreeze.TissueId = Tissue.Id "
                        "AND (ProbeSetFreeze.Name = %s OR "
                        "ProbeSetFreeze.FullName = %s "
                        "OR ProbeSetFreeze.ShortName = %s)",
                        (self.name,)*3)
                    (self.id, self.name, self.fullname, self.shortname,
                    self.data_scale, self.tissue) = cursor.fetchone()
                else:
                    self.tissue = "N/A"
                    cursor.execute(
                        "SELECT Id, Name, FullName, ShortName "
                        f"FROM {self.type}Freeze "
                        "WHERE (Name = %s OR FullName = "
                        "%s OR ShortName = %s)",
                        (self.name,)*3)
                    (self.id, self.name, self.fullname,
                    self.shortname) = cursor.fetchone()
            except TypeError:
                pass

    def chunk_dataset(self, dataset, n):

        results = {}
        traits_name_dict = ()
        with database_connection() as conn, conn.cursor() as cursor:
            cursor.execute(
                "SELECT ProbeSetXRef.DataId,ProbeSet.Name "
                "FROM ProbeSet, ProbeSetXRef, ProbeSetFreeze "
                "WHERE ProbeSetFreeze.Name = %s AND "
                "ProbeSetXRef.ProbeSetFreezeId = ProbeSetFreeze.Id "
                "AND ProbeSetXRef.ProbeSetId = ProbeSet.Id",
                (self.name,))
            # should cache this
            traits_name_dict = dict(cursor.fetchall())

        for i in range(0, len(dataset), n):
            matrix = list(dataset[i:i + n])
            trait_name = traits_name_dict[matrix[0][0]]

            my_values = [value for (trait_name, strain, value) in matrix]
            results[trait_name] = my_values
        return results

    def get_probeset_data(self, sample_list=None, trait_ids=None):

        # improvement of get trait data--->>>
        if sample_list:
            self.samplelist = sample_list

        else:
            self.samplelist = self.group.samplelist

        if self.group.parlist != None and self.group.f1list != None:
            if (self.group.parlist + self.group.f1list) in self.samplelist:
                self.samplelist += self.group.parlist + self.group.f1list
        with database_connection() as conn, conn.cursor() as cursor:
            cursor.execute(
                "SELECT Strain.Name, Strain.Id FROM "
                "Strain, Species WHERE Strain.Name IN "
                f"{create_in_clause(self.samplelist)} "
                "AND Strain.SpeciesId=Species.Id AND "
                "Species.name = %s", (self.group.species,)
            )
            results = dict(cursor.fetchall())
            sample_ids = [results[item] for item in self.samplelist]

            sorted_samplelist = [strain_name for strain_name, strain_id in sorted(
                results.items(), key=lambda item: item[1])]

            cursor.execute(
                "SELECT * from ProbeSetData WHERE StrainID IN "
                f"{create_in_clause(sample_ids)} AND id IN "
                "(SELECT ProbeSetXRef.DataId FROM "
                "(ProbeSet, ProbeSetXRef, ProbeSetFreeze) "
                "WHERE ProbeSetXRef.ProbeSetFreezeId = ProbeSetFreeze.Id "
                "AND ProbeSetFreeze.Name = %s AND "
                "ProbeSet.Id = ProbeSetXRef.ProbeSetId)",
                (self.name,)
            )

            query_results = list(cursor.fetchall())
            data_results = self.chunk_dataset(query_results, len(sample_ids))
            self.samplelist = sorted_samplelist
            self.trait_data = data_results

    def get_trait_data(self, sample_list=None):
        if sample_list:
            self.samplelist = sample_list
        else:
            self.samplelist = self.group.samplelist

        if self.group.parlist != None and self.group.f1list != None:
            if (self.group.parlist + self.group.f1list) in self.samplelist:
                self.samplelist += self.group.parlist + self.group.f1list

        with database_connection() as conn, conn.cursor() as cursor:
            cursor.execute(
                "SELECT Strain.Name, Strain.Id FROM Strain, Species "
                f"WHERE Strain.Name IN {create_in_clause(self.samplelist)} "
                "AND Strain.SpeciesId=Species.Id "
                "AND Species.name = %s",
                (self.group.species,)
            )
            results = dict(cursor.fetchall())
            sample_ids = [
                sample_id for sample_id in
                (results.get(item) for item in self.samplelist
                 if item is not None)
                if sample_id is not None
            ]

            # MySQL limits the number of tables that can be used in a join to 61,
            # so we break the sample ids into smaller chunks
            # Postgres doesn't have that limit, so we can get rid of this after we transition
            chunk_size = 50
            number_chunks = int(math.ceil(len(sample_ids) / chunk_size))

            cached_results = fetch_cached_results(self.name, self.type, self.samplelist)

            if cached_results is None:
                trait_sample_data = []
                for sample_ids_step in chunks.divide_into_chunks(sample_ids, number_chunks):
                    if self.type == "Publish":
                        dataset_type = "Phenotype"
                    else:
                        dataset_type = self.type
                    temp = ['T%s.value' % item for item in sample_ids_step]
                    if self.type == "Publish":
                        query = "SELECT {}XRef.Id".format(escape(self.type))
                    else:
                        query = "SELECT {}.Name".format(escape(dataset_type))
                    data_start_pos = 1
                    if len(temp) > 0:
                        query = query + ", " + ', '.join(temp)
                    query += ' FROM ({}, {}XRef, {}Freeze) '.format(*mescape(dataset_type,
                                                                             self.type,
                                                                             self.type))

                    for item in sample_ids_step:
                        query += """
                                left join {}Data as T{} on T{}.Id = {}XRef.DataId
                                and T{}.StrainId={}\n
                                """.format(*mescape(self.type, item, item, self.type, item, item))

                    if self.type == "Publish":
                        query += """
                                WHERE {}XRef.InbredSetId = {}Freeze.InbredSetId
                                and {}Freeze.Name = '{}'
                                and {}.Id = {}XRef.{}Id
                                order by {}.Id
                                """.format(*mescape(self.type, self.type, self.type, self.name,
                                                    dataset_type, self.type, dataset_type, dataset_type))
                    else:
                        query += """
                                WHERE {}XRef.{}FreezeId = {}Freeze.Id
                                and {}Freeze.Name = '{}'
                                and {}.Id = {}XRef.{}Id
                                order by {}.Id
                                """.format(*mescape(self.type, self.type, self.type, self.type,
                                                    self.name, dataset_type, self.type, self.type, dataset_type))
                    cursor.execute(query)
                    results = cursor.fetchall()
                    trait_sample_data.append([list(result) for result in results])

                trait_count = len(trait_sample_data[0])
                self.trait_data = collections.defaultdict(list)

                data_start_pos = 1
                for trait_counter in range(trait_count):
                    trait_name = trait_sample_data[0][trait_counter][0]
                    for chunk_counter in range(int(number_chunks)):
                        self.trait_data[trait_name] += (
                            trait_sample_data[chunk_counter][trait_counter][data_start_pos:])

                cache_dataset_results(
                    self.name, self.type, self.samplelist, self.trait_data)
            else:
                self.trait_data = cached_results