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
|
"""Database and utility functions for phenotypes."""
from typing import Optional
from functools import reduce
import MySQLdb as mdb
from MySQLdb.cursors import Cursor, DictCursor
from uploader.db_utils import debug_query
def datasets_by_population(
conn: mdb.Connection,
species_id: int,
population_id: int
) -> tuple[dict, ...]:
"""Retrieve all of a population's phenotype studies."""
with conn.cursor(cursorclass=DictCursor) as cursor:
cursor.execute(
"SELECT s.SpeciesId, pf.* FROM Species AS s "
"INNER JOIN InbredSet AS iset ON s.Id=iset.SpeciesId "
"INNER JOIN PublishFreeze AS pf ON iset.Id=pf.InbredSetId "
"WHERE s.Id=%s AND iset.Id=%s;",
(species_id, population_id))
return tuple(dict(row) for row in cursor.fetchall())
def dataset_by_id(conn: mdb.Connection,
species_id: int,
population_id: int,
dataset_id: int) -> dict:
"""Fetch dataset details by identifier"""
with conn.cursor(cursorclass=DictCursor) as cursor:
cursor.execute(
"SELECT s.SpeciesId, pf.* FROM Species AS s "
"INNER JOIN InbredSet AS iset ON s.Id=iset.SpeciesId "
"INNER JOIN PublishFreeze AS pf ON iset.Id=pf.InbredSetId "
"WHERE s.Id=%s AND iset.Id=%s AND pf.Id=%s",
(species_id, population_id, dataset_id))
return dict(cursor.fetchone())
def phenotypes_count(conn: mdb.Connection,
population_id: int,
dataset_id: int) -> int:
"""Count the number of phenotypes in the dataset."""
with conn.cursor(cursorclass=DictCursor) as cursor:
cursor.execute(
"SELECT COUNT(*) AS total_phenos FROM Phenotype AS pheno "
"INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId "
"INNER JOIN PublishFreeze AS pf ON pxr.InbredSetId=pf.InbredSetId "
"WHERE pxr.InbredSetId=%s AND pf.Id=%s",
(population_id, dataset_id))
return int(cursor.fetchone()["total_phenos"])
def dataset_phenotypes(conn: mdb.Connection,
population_id: int,
dataset_id: int,
offset: int = 0,
limit: Optional[int] = None) -> tuple[dict, ...]:
"""Fetch the actual phenotypes."""
_query = (
"SELECT pheno.*, pxr.Id, ist.InbredSetCode FROM Phenotype AS pheno "
"INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId "
"INNER JOIN PublishFreeze AS pf ON pxr.InbredSetId=pf.InbredSetId "
"INNER JOIN InbredSet AS ist ON pf.InbredSetId=ist.Id "
"WHERE pxr.InbredSetId=%s AND pf.Id=%s") + (
f" LIMIT {limit} OFFSET {offset}" if bool(limit) else "")
with conn.cursor(cursorclass=DictCursor) as cursor:
cursor.execute(_query, (population_id, dataset_id))
debug_query(cursor)
return tuple(dict(row) for row in cursor.fetchall())
def __phenotype_se__(cursor: Cursor,
species_id: int,
population_id: int,
dataset_id: int,
xref_id: str) -> dict:
"""Fetch standard-error values (if they exist) for a phenotype."""
_sequery = (
"SELECT pxr.Id AS xref_id, pxr.DataId, pse.error, nst.count "
"FROM Phenotype AS pheno "
"INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId "
"INNER JOIN PublishSE AS pse ON pxr.DataId=pse.DataId "
"INNER JOIN NStrain AS nst ON pse.DataId=nst.DataId "
"INNER JOIN Strain AS str ON nst.StrainId=str.Id "
"INNER JOIN StrainXRef AS sxr ON str.Id=sxr.StrainId "
"INNER JOIN PublishFreeze AS pf ON sxr.InbredSetId=pf.InbredSetId "
"INNER JOIN InbredSet AS iset ON pf.InbredSetId=iset.InbredSetId "
"WHERE (str.SpeciesId, pxr.InbredSetId, pf.Id, pxr.Id)=(%s, %s, %s, %s)")
cursor.execute(_sequery,
(species_id, population_id, dataset_id, xref_id))
return {row["xref_id"]: dict(row) for row in cursor.fetchall()}
def __organise_by_phenotype__(pheno, row):
"""Organise disparate data rows into phenotype 'objects'."""
_pheno = pheno.get(row["Id"])
return {
**pheno,
row["Id"]: {
"Id": row["Id"],
"Pre_publication_description": row["Pre_publication_description"],
"Post_publication_description": row["Post_publication_description"],
"Original_description": row["Original_description"],
"Units": row["Units"],
"Pre_publication_abbreviation": row["Pre_publication_abbreviation"],
"Post_publication_abbreviation": row["Post_publication_abbreviation"],
"data": {
#TOD0: organise these by DataId and StrainId
**(_pheno["data"] if bool(_pheno) else {}),
row["pxr.Id"]: {
"xref_id": row["pxr.Id"],
"DataId": row["DataId"],
"mean": row["mean"],
"Locus": row["Locus"],
"LRS": row["LRS"],
"additive": row["additive"],
"Sequence": row["Sequence"],
"comments": row["comments"],
"value": row["value"],
"StrainName": row["Name"],
"StrainName2": row["Name2"],
"StrainSymbol": row["Symbol"],
"StrainAlias": row["Alias"]
}
}
}
}
def __merge_pheno_data_and_se__(data, sedata) -> dict:
"""Merge phenotype data with the standard errors."""
return {
key: {**value, **sedata.get(key, {})}
for key, value in data.items()
}
def phenotype_by_id(
conn: mdb.Connection,
species_id: int,
population_id: int,
dataset_id: int,
xref_id
) -> Optional[dict]:
"""Fetch a specific phenotype."""
_dataquery = ("SELECT pheno.*, pxr.*, pd.*, str.*, iset.InbredSetCode "
"FROM Phenotype AS pheno "
"INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId "
"INNER JOIN PublishData AS pd ON pxr.DataId=pd.Id "
"INNER JOIN Strain AS str ON pd.StrainId=str.Id "
"INNER JOIN StrainXRef AS sxr ON str.Id=sxr.StrainId "
"INNER JOIN PublishFreeze AS pf ON sxr.InbredSetId=pf.InbredSetId "
"INNER JOIN InbredSet AS iset ON pf.InbredSetId=iset.InbredSetId "
"WHERE "
"(str.SpeciesId, pxr.InbredSetId, pf.Id, pxr.Id)=(%s, %s, %s, %s)")
with conn.cursor(cursorclass=DictCursor) as cursor:
cursor.execute(_dataquery,
(species_id, population_id, dataset_id, xref_id))
_pheno: dict = reduce(__organise_by_phenotype__, cursor.fetchall(), {})
if bool(_pheno) and len(_pheno.keys()) == 1:
_pheno = tuple(_pheno.values())[0]
return {
**_pheno,
"data": tuple(__merge_pheno_data_and_se__(
_pheno["data"],
__phenotype_se__(cursor,
species_id,
population_id,
dataset_id,
xref_id)).items())
}
if bool(_pheno) and len(_pheno.keys()) > 1:
raise Exception(
"We found more than one phenotype with the same identifier!")
return None
def phenotypes_data(conn: mdb.Connection,
population_id: int,
dataset_id: int,
offset: int = 0,
limit: Optional[int] = None) -> tuple[dict, ...]:
"""Fetch the data for the phenotypes."""
# — Phenotype -> PublishXRef -> PublishData -> Strain -> StrainXRef -> PublishFreeze
_query = ("SELECT pheno.*, pxr.*, pd.*, str.*, iset.InbredSetCode "
"FROM Phenotype AS pheno "
"INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId "
"INNER JOIN PublishData AS pd ON pxr.DataId=pd.Id "
"INNER JOIN Strain AS str ON pd.StrainId=str.Id "
"INNER JOIN StrainXRef AS sxr ON str.Id=sxr.StrainId "
"INNER JOIN PublishFreeze AS pf ON sxr.InbredSetId=pf.InbredSetId "
"INNER JOIN InbredSet AS iset ON pf.InbredSetId=iset.InbredSetId "
"WHERE pxr.InbredSetId=%s AND pf.Id=%s") + (
f" LIMIT {limit} OFFSET {offset}" if bool(limit) else "")
with conn.cursor(cursorclass=DictCursor) as cursor:
cursor.execute(_query, (population_id, dataset_id))
debug_query(cursor)
return tuple(dict(row) for row in cursor.fetchall())
|
