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
|
"""Load genotypes from R/qtl2 bundle into the database."""
import sys
import traceback
from pathlib import Path
from zipfile import ZipFile
from functools import reduce
from typing import Iterator, Optional
from logging import Logger, getLogger, StreamHandler
import MySQLdb as mdb
from MySQLdb.cursors import DictCursor
from r_qtl import r_qtl2 as rqtl2
from r_qtl import r_qtl2_qc as rqc
from functional_tools import take
from scripts.rqtl2.entry import build_main
from scripts.rqtl2.cli_parser import add_common_arguments
from scripts.cli_parser import init_cli_parser, add_global_data_arguments
def insert_markers(dbconn: mdb.Connection,
speciesid: int,
markers: tuple[str, ...],
pmapdata: Optional[Iterator[dict]]) -> int:
"""Insert genotype and genotype values into the database."""
mdata = reduce(#type: ignore[var-annotated]
lambda acc, row: ({#type: ignore[arg-type, return-value]
**acc, row["id"]: {
key: val
for key,val in row.items()
if key != "id"
}
}),
(pmapdata or tuple()),
{})
with dbconn.cursor() as cursor:
cursor.executemany(
"INSERT INTO Geno(SpeciesId, Name, Marker_Name, Chr, Mb) "
"VALUES (%(speciesid)s, %(marker)s, %(marker)s, %(chr)s, %(pos)s) "
"ON DUPLICATE KEY UPDATE SpeciesId=SpeciesId",
tuple({
"speciesid": speciesid,
"marker": marker,
"chr": mdata.get(marker, {}).get("chr"),
"pos": mdata.get(marker, {}).get("pos")
} for marker in markers))
return cursor.rowcount
def insert_individuals(dbconn: mdb.Connection,
speciesid: int,
individuals: tuple[str, ...]) -> int:
"""Insert individuals/samples into the database."""
with dbconn.cursor() as cursor:
cursor.executemany(
"INSERT INTO Strain(Name, Name2, SpeciesId) "
"VALUES(%(id)s, %(id)s, %(speciesid)s) "
"ON DUPLICATE KEY UPDATE Name=Name",
tuple({"speciesid": speciesid, "id": individual}
for individual in individuals))
return cursor.rowcount
def cross_reference_individuals(dbconn: mdb.Connection,
speciesid: int,
populationid: int,
individuals: tuple[str, ...]) -> int:
"""Cross reference any inserted individuals."""
with dbconn.cursor(cursorclass=DictCursor) as cursor:
paramstr = ", ".join(["%s"] * len(individuals))
cursor.execute("SELECT Id FROM Strain "
f"WHERE SpeciesId=%s AND Name IN ({paramstr})",
(speciesid,) + individuals)
ids = ({"popid": populationid, "indid": row["Id"]}
for row in cursor.fetchall())
cursor.executemany(
"INSERT INTO StrainXRef(InbredSetId, StrainId) "
"VALUES(%(popid)s, %(indid)s) "
"ON DUPLICATE KEY UPDATE InbredSetId=InbredSetId",
tuple(ids))
return cursor.rowcount
def insert_genotype_data(dbconn: mdb.Connection,
speciesid: int,
genotypes: tuple[dict, ...],
individuals: tuple[str, ...]) -> tuple[
int, tuple[dict, ...]]:
"""Insert the genotype data values into the database."""
with dbconn.cursor(cursorclass=DictCursor) as cursor:
paramstr = ", ".join(["%s"] * len(individuals))
cursor.execute(
f"SELECT Id, Name FROM Strain WHERE Name IN ({paramstr})",
individuals)
indids = {row["Name"]: row["Id"] for row in cursor.fetchall()}
markers = tuple(key for key in genotypes[0].keys() if key != "id")
paramstr = ", ".join(["%s"] * len(markers))
cursor.execute(
f"SELECT Id, Name FROM Geno WHERE SpeciesId=%s AND Name IN ({paramstr})",
(speciesid,)+markers)
markerids = {row["Name"]: row["Id"] for row in cursor.fetchall()}
cursor.execute("SELECT MAX(Id) AS lastid FROM GenoData")
lastid = cursor.fetchone()["lastid"]
data = tuple(item for item in (
{**row, "gid": gid}
for gid, row in enumerate(
({
"value": innerrow[marker],
"indid": indids[innerrow["id"]],
"markerid": markerids[marker]
} for innerrow in genotypes for marker in
(key for key in innerrow.keys() if key != "id")),
start=lastid+1))
if item["value"] is not None)
cursor.executemany(
"INSERT INTO GenoData(Id, StrainId, value) "
"VALUES(%(gid)s, %(indid)s, %(value)s)",
data)
return cursor.rowcount, tuple({
"dataid": row["gid"],
"markerid": row["markerid"]
} for row in data)
def cross_reference_genotypes(dbconn: mdb.Connection,
speciesid: int,
datasetid: int,
dataids: tuple[dict, ...],
gmapdata: Optional[Iterator[dict]]) -> int:
"""Cross-reference the data to the relevant dataset."""
_rows, markers, mdata = reduce(#type: ignore[var-annotated]
lambda acc, row: (#type: ignore[return-value,arg-type]
(acc[0] + (row,)), (acc[1] + (row["id"],)),
{
**acc[2], row["id"]: {
key: val
for key,val in row.items()
if key != "id"
}
}),
(gmapdata or tuple()),
(tuple(), tuple(), {}))
with dbconn.cursor(cursorclass=DictCursor) as cursor:
paramstr = ", ".join(["%s"] * len(markers))
cursor.execute("SELECT Id, Name FROM Geno "
f"WHERE SpeciesId=%s AND Name IN ({paramstr})",
(speciesid,) + markers)
markersdict = {row["Id"]: row["Name"] for row in cursor.fetchall()}
cursor.executemany(
"INSERT INTO GenoXRef(GenoFreezeId, GenoId, DataId, cM) "
"VALUES(%(datasetid)s, %(markerid)s, %(dataid)s, %(pos)s) "
"ON DUPLICATE KEY UPDATE GenoFreezeId=GenoFreezeId",
tuple({
**row,
"datasetid": datasetid,
"pos": mdata.get(markersdict.get(
row.get("markerid"), {}), {}).get("pos")
} for row in dataids))
return cursor.rowcount
def install_genotypes(#pylint: disable=[too-many-arguments, too-many-locals]
dbconn: mdb.Connection,
speciesid: int,
populationid: int,
datasetid: int,
rqtl2bundle: Path,
logger: Logger = getLogger()) -> int:
"""Load any existing genotypes into the database."""
count = 0
with ZipFile(str(rqtl2bundle.absolute()), "r") as zfile:
try:
logger.info("Validating bundle")
rqc.validate_bundle(zfile)
logger.info("Bundle validated successfully.")
logger.info(("Loading genotypes. This could take a while. "
"Please be patient."))
cdata = rqtl2.control_data(zfile)
genotypes = rqtl2.genotype_data(zfile)
while True:
batch = tuple(take(genotypes, 1000))
if len(batch) == 0:
logger.info("Loading Genotypes complete!")
logger.info(
"Total rows processed: %s", count)
break
insert_markers(
dbconn,
speciesid,
tuple(key for key in batch[0].keys() if key != "id"),
(rqtl2.file_data(zfile, "pmap", cdata) if "pmap" in cdata
else None))
individuals = tuple(row["id"] for row in batch)
insert_individuals(dbconn, speciesid, individuals)
cross_reference_individuals(
dbconn, speciesid, populationid, individuals)
_num_rows, dataids = insert_genotype_data(
dbconn, speciesid, batch, individuals)
cross_reference_genotypes(
dbconn,
speciesid,
datasetid,
dataids,
(rqtl2.file_data(zfile, "gmap", cdata)
if "gmap" in cdata else None))
count = count + len(batch)
except rqtl2.InvalidFormat as exc:
logger.error(str(exc))
logger.info("There are no genotypes to load.")
except Exception as _exc:# pylint: disable=[broad-except]
# Narrow this exception with time.
logger.error("Failing with exception: %s", traceback.format_exc())
return 3
return 0
if __name__ == "__main__":
def cli_args():
"""Process command-line arguments for install_genotypes"""
parser = add_common_arguments(add_global_data_arguments(init_cli_parser(
"install_genotypes",
"Parse genotypes from R/qtl2 bundle into the database.")))
return parser.parse_args()
thelogger = getLogger("install_genotypes")
thelogger.addHandler(StreamHandler(stream=sys.stderr))
main = build_main(
cli_args(),
lambda dbconn, args: install_genotypes(dbconn,
args.speciesid,
args.populationid,
args.datasetid,
args.rqtl2bundle),
thelogger,
"INFO")
sys.exit(main())
|
