cool-seq-tool 0.14.0__py3-none-any.whl → 0.14.2__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- cool_seq_tool/handlers/seqrepo_access.py +1 -3
- cool_seq_tool/mappers/__init__.py +8 -1
- cool_seq_tool/mappers/exon_genomic_coords.py +1 -1
- cool_seq_tool/mappers/feature_overlap.py +251 -0
- cool_seq_tool/mappers/mane_transcript.py +1 -1
- cool_seq_tool/resources/data_files.py +13 -1
- cool_seq_tool/schemas.py +35 -0
- cool_seq_tool/sources/uta_database.py +6 -6
- {cool_seq_tool-0.14.0.dist-info → cool_seq_tool-0.14.2.dist-info}/METADATA +7 -9
- {cool_seq_tool-0.14.0.dist-info → cool_seq_tool-0.14.2.dist-info}/RECORD +13 -12
- {cool_seq_tool-0.14.0.dist-info → cool_seq_tool-0.14.2.dist-info}/WHEEL +0 -0
- {cool_seq_tool-0.14.0.dist-info → cool_seq_tool-0.14.2.dist-info}/licenses/LICENSE +0 -0
- {cool_seq_tool-0.14.0.dist-info → cool_seq_tool-0.14.2.dist-info}/top_level.txt +0 -0
@@ -75,9 +75,7 @@ class SeqRepoAccess(SeqRepoDataProxy):
|
|
75
75
|
f"Start inter-residue coordinate ({start}) is out of index on {ac}"
|
76
76
|
)
|
77
77
|
elif error.startswith("stop out of range"):
|
78
|
-
msg = (
|
79
|
-
f"End inter-residue coordinate ({end}) is out of " f"index on {ac}"
|
80
|
-
)
|
78
|
+
msg = f"End inter-residue coordinate ({end}) is out of index on {ac}"
|
81
79
|
else:
|
82
80
|
msg = f"{e}"
|
83
81
|
_logger.warning(msg)
|
@@ -4,6 +4,13 @@ from .alignment import AlignmentMapper # noqa: I001
|
|
4
4
|
from .liftover import LiftOver
|
5
5
|
from .mane_transcript import ManeTranscript
|
6
6
|
from .exon_genomic_coords import ExonGenomicCoordsMapper
|
7
|
+
from .feature_overlap import FeatureOverlap
|
7
8
|
|
8
9
|
|
9
|
-
__all__ = [
|
10
|
+
__all__ = [
|
11
|
+
"AlignmentMapper",
|
12
|
+
"ExonGenomicCoordsMapper",
|
13
|
+
"FeatureOverlap",
|
14
|
+
"LiftOver",
|
15
|
+
"ManeTranscript",
|
16
|
+
]
|
@@ -776,7 +776,7 @@ class ExonGenomicCoordsMapper:
|
|
776
776
|
GRCh38 by default. Will attempt to liftover if starting assembly is GRCh37
|
777
777
|
:return: Data for a transcript segment boundary (inter-residue coordinates)
|
778
778
|
"""
|
779
|
-
params =
|
779
|
+
params = dict.fromkeys(GenomicTxSeg.model_fields)
|
780
780
|
|
781
781
|
# Validate inputs exist in UTA
|
782
782
|
if gene:
|
@@ -0,0 +1,251 @@
|
|
1
|
+
"""Module for getting feature (gene/exon) overlap"""
|
2
|
+
|
3
|
+
import re
|
4
|
+
from pathlib import Path
|
5
|
+
|
6
|
+
import polars as pl
|
7
|
+
from ga4gh.core import ga4gh_identify
|
8
|
+
from ga4gh.vrs.models import SequenceLocation, SequenceReference
|
9
|
+
|
10
|
+
from cool_seq_tool.handlers import SeqRepoAccess
|
11
|
+
from cool_seq_tool.resources.data_files import DataFile, get_data_file
|
12
|
+
from cool_seq_tool.schemas import Assembly, CdsOverlap, CoordinateType
|
13
|
+
|
14
|
+
# Pattern for chromosome
|
15
|
+
CHR_PATTERN = r"X|Y|([1-9]|1[0-9]|2[0-2])"
|
16
|
+
|
17
|
+
|
18
|
+
class FeatureOverlapError(Exception):
|
19
|
+
"""Custom exception for the Feature Overlap class"""
|
20
|
+
|
21
|
+
|
22
|
+
class FeatureOverlap:
|
23
|
+
"""The class for getting feature overlap"""
|
24
|
+
|
25
|
+
def __init__(
|
26
|
+
self,
|
27
|
+
seqrepo_access: SeqRepoAccess,
|
28
|
+
mane_refseq_genomic_path: Path | None = None,
|
29
|
+
from_local: bool = False,
|
30
|
+
) -> None:
|
31
|
+
"""Initialize the FeatureOverlap class. Will load RefSeq data and store as df.
|
32
|
+
|
33
|
+
:param seqrepo_access: Client for accessing SeqRepo data
|
34
|
+
:param mane_refseq_genomic_path: Path to MANE RefSeq Genomic GFF data
|
35
|
+
:param from_local: if ``True``, don't check for or acquire latest version --
|
36
|
+
just provide most recent locally available file, if possible, and raise
|
37
|
+
error otherwise
|
38
|
+
"""
|
39
|
+
if not mane_refseq_genomic_path:
|
40
|
+
mane_refseq_genomic_path = get_data_file(
|
41
|
+
DataFile.MANE_REFSEQ_GENOMIC, from_local
|
42
|
+
)
|
43
|
+
self.seqrepo_access = seqrepo_access
|
44
|
+
self.mane_refseq_genomic_path = mane_refseq_genomic_path
|
45
|
+
self.df = self._load_mane_refseq_gff_data()
|
46
|
+
|
47
|
+
def _load_mane_refseq_gff_data(self) -> pl.DataFrame:
|
48
|
+
"""Load MANE RefSeq GFF data file into DataFrame.
|
49
|
+
|
50
|
+
:return: DataFrame containing MANE RefSeq Genomic GFF data for CDS. Columns
|
51
|
+
include `type`, `chromosome` (chromosome without 'chr' prefix), `cds_start`,
|
52
|
+
`cds_stop`, `info_name` (name of record), and `gene`. `cds_start` and
|
53
|
+
`cds_stop` use inter-residue coordinates.
|
54
|
+
"""
|
55
|
+
df = pl.read_csv(
|
56
|
+
self.mane_refseq_genomic_path,
|
57
|
+
separator="\t",
|
58
|
+
has_header=False,
|
59
|
+
skip_rows=9,
|
60
|
+
columns=[0, 2, 3, 4, 8],
|
61
|
+
)
|
62
|
+
df.columns = ["chromosome", "type", "cds_start", "cds_stop", "info"]
|
63
|
+
|
64
|
+
# Restrict to only feature of interest: CDS (which has gene info)
|
65
|
+
df = df.filter(pl.col("type") == "CDS")
|
66
|
+
|
67
|
+
# Get name from the info field
|
68
|
+
# Get gene from the info field
|
69
|
+
# Get chromosome names without prefix and without suffix for alternate transcripts
|
70
|
+
# Convert start and stop to ints
|
71
|
+
# Convert to inter-residue coordinates
|
72
|
+
# Only return certain columns
|
73
|
+
return df.with_columns(
|
74
|
+
(pl.col("info").str.extract(r"Name=([^;]+)", 1).alias("info_name")),
|
75
|
+
(pl.col("info").str.extract(r"gene=([^;]+)", 1).alias("gene")),
|
76
|
+
(pl.col("chromosome").str.extract(r"^chr?([^_]+)", 1).alias("chromosome")),
|
77
|
+
(pl.col("cds_start").cast(pl.Int64) - 1).alias("cds_start"),
|
78
|
+
(pl.col("cds_stop").cast(pl.Int64).alias("cds_stop")),
|
79
|
+
).select(
|
80
|
+
[
|
81
|
+
pl.col("type"),
|
82
|
+
pl.col("chromosome"),
|
83
|
+
pl.col("cds_start"),
|
84
|
+
pl.col("cds_stop"),
|
85
|
+
pl.col("info_name"),
|
86
|
+
pl.col("gene"),
|
87
|
+
]
|
88
|
+
)
|
89
|
+
|
90
|
+
def _get_chr_from_alt_ac(self, identifier: str) -> str:
|
91
|
+
"""Get chromosome given genomic identifier
|
92
|
+
|
93
|
+
:param identifier: Genomic identifier on GRCh38 assembly
|
94
|
+
:raises FeatureOverlapError: If unable to find associated GRCh38 chromosome
|
95
|
+
:return: Chromosome. 1..22, X, Y. No 'chr' prefix.
|
96
|
+
"""
|
97
|
+
aliases, error_msg = self.seqrepo_access.translate_identifier(
|
98
|
+
identifier, Assembly.GRCH38.value
|
99
|
+
)
|
100
|
+
|
101
|
+
if error_msg:
|
102
|
+
raise FeatureOverlapError(str(error_msg))
|
103
|
+
|
104
|
+
if not aliases:
|
105
|
+
error_msg = (
|
106
|
+
f"Unable to find {Assembly.GRCH38.value} aliases for: {identifier}"
|
107
|
+
)
|
108
|
+
raise FeatureOverlapError(error_msg)
|
109
|
+
|
110
|
+
assembly_chr_pattern = (
|
111
|
+
rf"^{Assembly.GRCH38.value}:(?P<chromosome>{CHR_PATTERN})$"
|
112
|
+
)
|
113
|
+
for a in aliases:
|
114
|
+
chr_match = re.match(assembly_chr_pattern, a)
|
115
|
+
if chr_match:
|
116
|
+
break
|
117
|
+
|
118
|
+
if not chr_match:
|
119
|
+
error_msg = (
|
120
|
+
f"Unable to find {Assembly.GRCH38.value} chromosome for: {identifier}"
|
121
|
+
)
|
122
|
+
raise FeatureOverlapError(error_msg)
|
123
|
+
|
124
|
+
chr_groupdict = chr_match.groupdict()
|
125
|
+
return chr_groupdict["chromosome"]
|
126
|
+
|
127
|
+
def get_grch38_mane_gene_cds_overlap(
|
128
|
+
self,
|
129
|
+
start: int,
|
130
|
+
end: int,
|
131
|
+
chromosome: str | None = None,
|
132
|
+
identifier: str | None = None,
|
133
|
+
coordinate_type: CoordinateType = CoordinateType.RESIDUE,
|
134
|
+
) -> dict[str, list[CdsOverlap]] | None:
|
135
|
+
"""Given GRCh38 genomic data, find the overlapping MANE features (gene and cds).
|
136
|
+
The genomic data is specified as a sequence location by `chromosome`, `start`,
|
137
|
+
`end`. All CDS regions with which the input sequence location has nonzero base
|
138
|
+
pair overlap will be returned.
|
139
|
+
|
140
|
+
:param start: GRCh38 start position
|
141
|
+
:param end: GRCh38 end position
|
142
|
+
:param chromosome: Chromosome. 1..22, X, or Y. If not provided, must provide
|
143
|
+
`identifier`. If both `chromosome` and `identifier` are provided,
|
144
|
+
`chromosome` will be used.
|
145
|
+
:param identifier: Genomic identifier on GRCh38 assembly. If not provided, must
|
146
|
+
provide `chromosome`. If both `chromosome` and `identifier` are provided,
|
147
|
+
`chromosome` will be used.
|
148
|
+
:param coordinate_type: Coordinate type for ``start`` and ``end``
|
149
|
+
:raise FeatureOverlapError: If missing required fields or unable to find
|
150
|
+
associated ga4gh identifier
|
151
|
+
:return: MANE feature (gene/cds) overlap data represented as a dict. The
|
152
|
+
dictionary will be keyed by genes which overlap the input sequence location.
|
153
|
+
Each gene contains a list of the overlapping CDS regions with the beginning
|
154
|
+
and end of the input sequence location's overlap with each
|
155
|
+
"""
|
156
|
+
ga4gh_seq_id = None
|
157
|
+
if chromosome:
|
158
|
+
if not re.match(f"^{CHR_PATTERN}$", chromosome):
|
159
|
+
error_msg = "`chromosome` must be 1, ..., 22, X, or Y"
|
160
|
+
raise FeatureOverlapError(error_msg)
|
161
|
+
else:
|
162
|
+
if identifier:
|
163
|
+
chromosome = self._get_chr_from_alt_ac(identifier)
|
164
|
+
if identifier.startswith("ga4gh:SQ."):
|
165
|
+
ga4gh_seq_id = identifier
|
166
|
+
else:
|
167
|
+
error_msg = "Must provide either `chromosome` or `identifier`"
|
168
|
+
raise FeatureOverlapError(error_msg)
|
169
|
+
|
170
|
+
# Convert residue to inter-residue
|
171
|
+
if coordinate_type == CoordinateType.RESIDUE:
|
172
|
+
start -= 1
|
173
|
+
|
174
|
+
# Get feature dataframe (df uses inter-residue)
|
175
|
+
feature_df = self.df.filter(
|
176
|
+
(pl.col("chromosome") == chromosome)
|
177
|
+
& (pl.col("cds_start") <= end)
|
178
|
+
& (pl.col("cds_stop") >= start)
|
179
|
+
)
|
180
|
+
|
181
|
+
if feature_df.is_empty():
|
182
|
+
return None
|
183
|
+
|
184
|
+
# Add overlap columns
|
185
|
+
feature_df = feature_df.with_columns(
|
186
|
+
[
|
187
|
+
pl.when(pl.col("cds_start") < start)
|
188
|
+
.then(start)
|
189
|
+
.otherwise(pl.col("cds_start"))
|
190
|
+
.alias("overlap_start"),
|
191
|
+
pl.when(pl.col("cds_stop") > end)
|
192
|
+
.then(end)
|
193
|
+
.otherwise(pl.col("cds_stop"))
|
194
|
+
.alias("overlap_stop"),
|
195
|
+
]
|
196
|
+
)
|
197
|
+
|
198
|
+
# Get ga4gh identifier for chromosome
|
199
|
+
if not ga4gh_seq_id:
|
200
|
+
grch38_chr = f"{Assembly.GRCH38.value}:{chromosome}"
|
201
|
+
ga4gh_aliases, error_msg = self.seqrepo_access.translate_identifier(
|
202
|
+
grch38_chr, "ga4gh"
|
203
|
+
)
|
204
|
+
|
205
|
+
# Errors should never happen but catching just in case
|
206
|
+
if error_msg:
|
207
|
+
raise FeatureOverlapError(str(error_msg))
|
208
|
+
|
209
|
+
if not ga4gh_aliases:
|
210
|
+
error_msg = f"Unable to find ga4gh identifier for: {grch38_chr}"
|
211
|
+
raise FeatureOverlapError(error_msg)
|
212
|
+
|
213
|
+
ga4gh_seq_id = ga4gh_aliases[0]
|
214
|
+
|
215
|
+
def _get_seq_loc(start_pos: int, stop_pos: int, refget_ac: str) -> dict:
|
216
|
+
"""Get VRS Sequence Location represented as a dict
|
217
|
+
|
218
|
+
:param start_pos: Start position
|
219
|
+
:param stop_pos: Stop position
|
220
|
+
:param refget_ac: Refget Accession (SQ.)
|
221
|
+
:return: VRS Sequence Location represented as dictionary with the ga4gh ID
|
222
|
+
included
|
223
|
+
"""
|
224
|
+
_sl = SequenceLocation(
|
225
|
+
sequenceReference=SequenceReference(
|
226
|
+
refgetAccession=refget_ac,
|
227
|
+
),
|
228
|
+
start=start_pos,
|
229
|
+
end=stop_pos,
|
230
|
+
)
|
231
|
+
ga4gh_identify(_sl)
|
232
|
+
return _sl.model_dump(exclude_none=True)
|
233
|
+
|
234
|
+
resp = {}
|
235
|
+
refget_ac = ga4gh_seq_id.split("ga4gh:")[-1]
|
236
|
+
for gene, group in feature_df.group_by("gene"):
|
237
|
+
gene = gene[0]
|
238
|
+
_gene_overlap_data = [
|
239
|
+
CdsOverlap(
|
240
|
+
cds=_get_seq_loc(
|
241
|
+
cds_row["cds_start"], cds_row["cds_stop"], refget_ac
|
242
|
+
),
|
243
|
+
overlap=_get_seq_loc(
|
244
|
+
cds_row["overlap_start"], cds_row["overlap_stop"], refget_ac
|
245
|
+
),
|
246
|
+
).model_dump(by_alias=True, exclude_none=True)
|
247
|
+
for cds_row in group.iter_rows(named=True)
|
248
|
+
]
|
249
|
+
resp[gene] = _gene_overlap_data
|
250
|
+
|
251
|
+
return resp
|
@@ -268,7 +268,7 @@ class ManeTranscript:
|
|
268
268
|
query = f"""
|
269
269
|
SELECT alt_ac
|
270
270
|
FROM {self.uta_db.schema}.genomic
|
271
|
-
WHERE alt_ac LIKE '{genomic_tx_data.alt_ac.split(
|
271
|
+
WHERE alt_ac LIKE '{genomic_tx_data.alt_ac.split(".")[0]}%'
|
272
272
|
{order_by_cond}
|
273
273
|
""" # noqa: S608
|
274
274
|
nc_acs = await self.uta_db.execute_query(query)
|
@@ -6,7 +6,11 @@ from importlib import resources
|
|
6
6
|
from os import environ
|
7
7
|
from pathlib import Path
|
8
8
|
|
9
|
-
from wags_tails import
|
9
|
+
from wags_tails import (
|
10
|
+
NcbiLrgRefSeqGeneData,
|
11
|
+
NcbiManeRefSeqGenomicData,
|
12
|
+
NcbiManeSummaryData,
|
13
|
+
)
|
10
14
|
|
11
15
|
_logger = logging.getLogger(__name__)
|
12
16
|
|
@@ -16,6 +20,7 @@ class DataFile(str, Enum):
|
|
16
20
|
|
17
21
|
TRANSCRIPT_MAPPINGS = "transcript_mappings"
|
18
22
|
MANE_SUMMARY = "mane_summary"
|
23
|
+
MANE_REFSEQ_GENOMIC = "mane_refseq_genomic"
|
19
24
|
LRG_REFSEQGENE = "lrg_refseqgene"
|
20
25
|
|
21
26
|
def lower(self) -> str:
|
@@ -37,6 +42,12 @@ _resource_acquisition_params = {
|
|
37
42
|
from_local=from_local
|
38
43
|
)[0],
|
39
44
|
),
|
45
|
+
DataFile.MANE_REFSEQ_GENOMIC: (
|
46
|
+
"MANE_REFSEQ_GENOMIC_PATH",
|
47
|
+
lambda from_local: NcbiManeRefSeqGenomicData(silent=True).get_latest(
|
48
|
+
from_local=from_local
|
49
|
+
)[0],
|
50
|
+
),
|
40
51
|
DataFile.LRG_REFSEQGENE: (
|
41
52
|
"LRG_REFSEQGENE_PATH",
|
42
53
|
lambda from_local: NcbiLrgRefSeqGeneData(silent=True).get_latest(
|
@@ -53,6 +64,7 @@ def get_data_file(resource: DataFile, from_local: bool = False) -> Path:
|
|
53
64
|
|
54
65
|
* ``Resource.TRANSCRIPT_MAPPINGS`` -> ``TRANSCRIPT_MAPPINGS_PATH``
|
55
66
|
* ``Resource.MANE_SUMMARY`` -> ``MANE_SUMMARY_PATH``
|
67
|
+
* ``Resource.MANE_REFSEQ_GENOMIC`` -> ``MANE_REFSEQ_GENOMIC_PATH``
|
56
68
|
* ``Resource.LRG_REFSEQGENE`` -> ``LRG_REFSEQGENE_PATH``
|
57
69
|
|
58
70
|
Otherwise, this function falls back on default expected locations:
|
cool_seq_tool/schemas.py
CHANGED
@@ -4,6 +4,7 @@ import datetime
|
|
4
4
|
from enum import Enum, IntEnum
|
5
5
|
from typing import Literal
|
6
6
|
|
7
|
+
from ga4gh.vrs.models import SequenceLocation
|
7
8
|
from pydantic import (
|
8
9
|
BaseModel,
|
9
10
|
ConfigDict,
|
@@ -167,3 +168,37 @@ class ServiceMeta(BaseModelForbidExtra):
|
|
167
168
|
}
|
168
169
|
}
|
169
170
|
)
|
171
|
+
|
172
|
+
|
173
|
+
class CdsOverlap(BaseModelForbidExtra):
|
174
|
+
"""Create model for representing CDS start/stop and Overlap start/stop"""
|
175
|
+
|
176
|
+
cds: SequenceLocation
|
177
|
+
overlap: SequenceLocation
|
178
|
+
|
179
|
+
model_config = ConfigDict(
|
180
|
+
json_schema_extra={
|
181
|
+
"example": {
|
182
|
+
"cds": {
|
183
|
+
"id": "ga4gh:SL.fYRYzNIAoe6UQF9MT1XaYsFscoU68ZJv",
|
184
|
+
"type": "SequenceLocation",
|
185
|
+
"sequenceReference": {
|
186
|
+
"refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
|
187
|
+
"type": "SequenceReference",
|
188
|
+
},
|
189
|
+
"start": 140726493,
|
190
|
+
"end": 140726516,
|
191
|
+
},
|
192
|
+
"overlap": {
|
193
|
+
"id": "ga4gh:SL.fYRYzNIAoe6UQF9MT1XaYsFscoU68ZJv",
|
194
|
+
"type": "SequenceLocation",
|
195
|
+
"sequenceReference": {
|
196
|
+
"refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
|
197
|
+
"type": "SequenceReference",
|
198
|
+
},
|
199
|
+
"start": 140726493,
|
200
|
+
"end": 140726516,
|
201
|
+
},
|
202
|
+
}
|
203
|
+
}
|
204
|
+
)
|
@@ -221,7 +221,7 @@ class UtaDatabase:
|
|
221
221
|
WHERE table_schema = '{self.schema}'
|
222
222
|
AND table_name = 'genomic'
|
223
223
|
);
|
224
|
-
"""
|
224
|
+
""" # noqa: S608
|
225
225
|
genomic_table_exists = await self.execute_query(check_table_exists)
|
226
226
|
genomic_table_exists = genomic_table_exists[0].get("exists")
|
227
227
|
if genomic_table_exists is None:
|
@@ -250,7 +250,7 @@ class UtaDatabase:
|
|
250
250
|
LEFT JOIN {self.schema}.exon_aln ea ON
|
251
251
|
(((te.exon_id = ea.tx_exon_id) AND
|
252
252
|
(ae.exon_id = ea.alt_exon_id))));
|
253
|
-
"""
|
253
|
+
""" # noqa: S608
|
254
254
|
await self.execute_query(create_genomic_table)
|
255
255
|
|
256
256
|
indexes = [
|
@@ -325,13 +325,13 @@ class UtaDatabase:
|
|
325
325
|
cds_start_end = await self.execute_query(query)
|
326
326
|
if cds_start_end:
|
327
327
|
cds_start_end = cds_start_end[0]
|
328
|
-
if cds_start_end[0] is not None and cds_start_end[1] is not None:
|
328
|
+
if cds_start_end[0] is not None and cds_start_end[1] is not None:
|
329
329
|
return cds_start_end[0], cds_start_end[1]
|
330
330
|
else:
|
331
331
|
_logger.warning(
|
332
332
|
"Unable to get coding start/end site for accession: %s", tx_ac
|
333
333
|
)
|
334
|
-
|
334
|
+
return None
|
335
335
|
|
336
336
|
async def get_newest_assembly_ac(self, ac: str) -> list[str]:
|
337
337
|
"""Find accession associated to latest genomic assembly
|
@@ -352,7 +352,7 @@ class UtaDatabase:
|
|
352
352
|
query = f"""
|
353
353
|
SELECT ac
|
354
354
|
FROM {self.schema}._seq_anno_most_recent
|
355
|
-
WHERE ac LIKE '{ac.split(
|
355
|
+
WHERE ac LIKE '{ac.split(".")[0]}%'
|
356
356
|
AND ((descr IS NULL) OR (descr = ''))
|
357
357
|
{order_by_cond}
|
358
358
|
""" # noqa: S608
|
@@ -499,7 +499,7 @@ class UtaDatabase:
|
|
499
499
|
AND {start_pos} BETWEEN {pos_q}
|
500
500
|
AND {end_pos} BETWEEN {pos_q}
|
501
501
|
{order_by_cond}
|
502
|
-
"""
|
502
|
+
""" # noqa: S608
|
503
503
|
result = await self.execute_query(query)
|
504
504
|
if not result:
|
505
505
|
_logger.warning("Unable to find transcript alignment for query: %s", query)
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: cool_seq_tool
|
3
|
-
Version: 0.14.
|
3
|
+
Version: 0.14.2
|
4
4
|
Summary: Common Operation on Lots of Sequences Tool
|
5
5
|
Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
|
6
6
|
License: MIT License
|
@@ -45,26 +45,24 @@ Requires-Python: >=3.10
|
|
45
45
|
Description-Content-Type: text/markdown
|
46
46
|
License-File: LICENSE
|
47
47
|
Requires-Dist: asyncpg
|
48
|
-
Requires-Dist: aiofiles
|
49
48
|
Requires-Dist: boto3
|
50
49
|
Requires-Dist: agct>=0.1.0-dev1
|
51
50
|
Requires-Dist: polars~=1.0
|
52
|
-
Requires-Dist: hgvs
|
53
51
|
Requires-Dist: biocommons.seqrepo
|
54
|
-
Requires-Dist: pydantic
|
55
|
-
Requires-Dist: ga4gh.vrs
|
56
|
-
Requires-Dist: wags-tails~=0.
|
52
|
+
Requires-Dist: pydantic<3.0,>=2.0
|
53
|
+
Requires-Dist: ga4gh.vrs<3.0,>=2.1.3
|
54
|
+
Requires-Dist: wags-tails~=0.4.0
|
57
55
|
Requires-Dist: bioutils
|
58
56
|
Provides-Extra: dev
|
59
|
-
Requires-Dist: pre-commit>=4.0
|
57
|
+
Requires-Dist: pre-commit>=4.2.0; extra == "dev"
|
60
58
|
Requires-Dist: ipython; extra == "dev"
|
61
59
|
Requires-Dist: ipykernel; extra == "dev"
|
62
60
|
Requires-Dist: psycopg2-binary; extra == "dev"
|
63
|
-
Requires-Dist: ruff==0.
|
61
|
+
Requires-Dist: ruff==0.12.1; extra == "dev"
|
64
62
|
Provides-Extra: tests
|
65
63
|
Requires-Dist: pytest; extra == "tests"
|
66
64
|
Requires-Dist: pytest-cov; extra == "tests"
|
67
|
-
Requires-Dist: pytest-asyncio
|
65
|
+
Requires-Dist: pytest-asyncio; extra == "tests"
|
68
66
|
Requires-Dist: mock; extra == "tests"
|
69
67
|
Provides-Extra: docs
|
70
68
|
Requires-Dist: sphinx==6.1.3; extra == "docs"
|
@@ -1,24 +1,25 @@
|
|
1
1
|
cool_seq_tool/__init__.py,sha256=pJyVj7Z275BBAwpeFMm-WEn_tp-y1_ihRl1sLc4FFZY,400
|
2
2
|
cool_seq_tool/app.py,sha256=vyqlQRffC8sWZXMm-f_f-8WuTTWo3oRNfPUa_qdPV2M,4944
|
3
|
-
cool_seq_tool/schemas.py,sha256=
|
3
|
+
cool_seq_tool/schemas.py,sha256=ueEq7cVKyGWVDvsV9JAzg7Cp2Nni3F9musCkWEtW26g,5365
|
4
4
|
cool_seq_tool/utils.py,sha256=kesu7UnOplDzvNBg_G-_m1xMM22979nmsi4yWtweetU,2959
|
5
5
|
cool_seq_tool/handlers/__init__.py,sha256=KalQ46vX1MO4SJz2SlspKoIRy1n3c3Vp1t4Y2pIfqow,78
|
6
|
-
cool_seq_tool/handlers/seqrepo_access.py,sha256=
|
7
|
-
cool_seq_tool/mappers/__init__.py,sha256=
|
6
|
+
cool_seq_tool/handlers/seqrepo_access.py,sha256=lRzPc8V0eZJTlefbHuVKeZTEC8-KcyPzpqX7vx3amu8,9118
|
7
|
+
cool_seq_tool/mappers/__init__.py,sha256=tavpwkNogg_nF1J_kb6Q9jk7ezqdRz063v7BMZ4koLM,390
|
8
8
|
cool_seq_tool/mappers/alignment.py,sha256=nV6PS3mhkQ2MD1GcpNBujBOqd3AKxYSYA9BCusFOa1o,9636
|
9
|
-
cool_seq_tool/mappers/exon_genomic_coords.py,sha256=
|
9
|
+
cool_seq_tool/mappers/exon_genomic_coords.py,sha256=t36NhWo2Rl84dgZY6qO7XFmGpfisjAqC-1ZOTRZxWvg,44757
|
10
|
+
cool_seq_tool/mappers/feature_overlap.py,sha256=_MMEuZh48dHDPKliQV2C14bwziScE46uWl9utnAHOZo,9845
|
10
11
|
cool_seq_tool/mappers/liftover.py,sha256=lltx9zxfkrb5PHtJlKp3a39JCwPP4e0Zft-mQc1jXL8,3367
|
11
|
-
cool_seq_tool/mappers/mane_transcript.py,sha256=
|
12
|
+
cool_seq_tool/mappers/mane_transcript.py,sha256=2cAYi0Y_gGdPI40weH9Ud1uVBCTKuwMT0M7KFUyjzU0,54365
|
12
13
|
cool_seq_tool/resources/__init__.py,sha256=VwUC8YaucTS6SmRirToulZTF6CuvuLQRSxFfSfAovCc,77
|
13
|
-
cool_seq_tool/resources/data_files.py,sha256=
|
14
|
+
cool_seq_tool/resources/data_files.py,sha256=6d1M5WjeFHdTQpzxqjQ78auQRZvIBVqH8QNCrmRRDXw,4205
|
14
15
|
cool_seq_tool/resources/status.py,sha256=9LYSO2mOzVmoSQwllzq1mGChjtDA6j3I0S372N89clA,5683
|
15
16
|
cool_seq_tool/resources/transcript_mapping.tsv,sha256=AO3luYQAbFiCoRgiiPXotakb5pAwx1jDCeXpvGdIuac,24138769
|
16
17
|
cool_seq_tool/sources/__init__.py,sha256=51QiymeptF7AeVGgV-tW_9f4pIUr0xtYbyzpvHOCneM,304
|
17
18
|
cool_seq_tool/sources/mane_transcript_mappings.py,sha256=C5puIA1xuEzBaSvs8VtSxVb2OIDGUg5no8v6Ma2QSdw,6597
|
18
19
|
cool_seq_tool/sources/transcript_mappings.py,sha256=903RKTMBO2rbKh6iTQ1BEWnY4C7saBFMPw2_4ATuudg,10054
|
19
|
-
cool_seq_tool/sources/uta_database.py,sha256=
|
20
|
-
cool_seq_tool-0.14.
|
21
|
-
cool_seq_tool-0.14.
|
22
|
-
cool_seq_tool-0.14.
|
23
|
-
cool_seq_tool-0.14.
|
24
|
-
cool_seq_tool-0.14.
|
20
|
+
cool_seq_tool/sources/uta_database.py,sha256=zzRzmYuybqzEg7zeuQjhK46SPK5GfbiWWNRGNJju8AI,36197
|
21
|
+
cool_seq_tool-0.14.2.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
|
22
|
+
cool_seq_tool-0.14.2.dist-info/METADATA,sha256=qtjqeUzTDsOnTlil7dVW7Uzg50mQ_-Lu8sKwR95ExGs,6535
|
23
|
+
cool_seq_tool-0.14.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
24
|
+
cool_seq_tool-0.14.2.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
|
25
|
+
cool_seq_tool-0.14.2.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|