Skip to content

Commit a5617d0

Browse files
authored
fix: MANE Summary data >= v1.1 updated GRCh38_chr (#149) (#150)
- < v1.1 used 1...22, X, Y. >= v1.1 uses NC accessions
1 parent 28f3e9c commit a5617d0

File tree

3 files changed

+15
-15
lines changed

3 files changed

+15
-15
lines changed

cool_seq_tool/data_sources/mane_transcript_mappings.py

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -52,17 +52,17 @@ def get_mane_from_transcripts(self, transcripts: List[str]) -> List[Dict]:
5252
return []
5353
return result.to_dict("records")
5454

55-
def get_mane_data_from_chr_pos(self, chromosome: str, start: int,
56-
end: int) -> List[Dict]:
55+
def get_mane_data_from_chr_pos(
56+
self, alt_ac: str, start: int, end: int
57+
) -> List[Dict]:
5758
"""Get MANE data given chromosome, start pos, end end pos. Assumes GRCh38.
58-
:param str chromosome: Chromosome. Case sensitive for X, Y chromosomes.
59-
Do not prefix. Valid examples: "1" ... "22", "X", "Y"
59+
:param str alt_ac: NC Accession
6060
:param int start: Start genomic position. Assumes residue coordinates.
6161
:param int end: End genomic position. Assumes residue coordinates.
6262
:return: List of MANE data. Will return sorted list:
6363
MANE Select then MANE Plus Clinical.
6464
"""
65-
mane_rows = self.df[(start >= self.df["chr_start"].astype(int)) & (end <= self.df["chr_end"].astype(int)) & (self.df["GRCh38_chr"] == chromosome)] # noqa: E501
65+
mane_rows = self.df[(start >= self.df["chr_start"].astype(int)) & (end <= self.df["chr_end"].astype(int)) & (self.df["GRCh38_chr"] == alt_ac)] # noqa: E501
6666
if len(mane_rows) == 0:
6767
return []
6868
mane_rows = mane_rows.sort_values("MANE_status", ascending=False)

cool_seq_tool/version.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
__version__ = "0.1.12"
1+
__version__ = "0.1.13"

tests/unit/test_mane_transcript_mappings.py

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ def braf_select():
2424
"Ensembl_nuc": "ENST00000646891.2",
2525
"Ensembl_prot": "ENSP00000493543.1",
2626
"MANE_status": "MANE Select",
27-
"GRCh38_chr": "7",
27+
"GRCh38_chr": "NC_000007.14",
2828
"chr_start": 140730665,
2929
"chr_end": 140924929,
3030
"chr_strand": "-"
@@ -45,7 +45,7 @@ def braf_plus_clinical():
4545
"Ensembl_nuc": "ENST00000644969.2",
4646
"Ensembl_prot": "ENSP00000496776.1",
4747
"MANE_status": "MANE Plus Clinical",
48-
"GRCh38_chr": "7",
48+
"GRCh38_chr": "NC_000007.14",
4949
"chr_start": 140719337,
5050
"chr_end": 140924929,
5151
"chr_strand": "-"
@@ -66,7 +66,7 @@ def ercc6_plus_clinical():
6666
"Ensembl_nuc": "ENST00000447839.7",
6767
"Ensembl_prot": "ENSP00000387966.2",
6868
"MANE_status": "MANE Plus Clinical",
69-
"GRCh38_chr": "10",
69+
"GRCh38_chr": "NC_000010.11",
7070
"chr_start": 49515198,
7171
"chr_end": 49539121,
7272
"chr_strand": "-"
@@ -87,7 +87,7 @@ def ercc6_select():
8787
"Ensembl_nuc": "ENST00000355832.10",
8888
"Ensembl_prot": "ENSP00000348089.5",
8989
"MANE_status": "MANE Select",
90-
"GRCh38_chr": "10",
90+
"GRCh38_chr": "NC_000010.11",
9191
"chr_start": 49454470,
9292
"chr_end": 49539121,
9393
"chr_strand": "-"
@@ -159,12 +159,12 @@ def test_get_mane_data_from_chr_pos(test_mane_transcript_mappings, braf_select,
159159
braf_plus_clinical):
160160
"""Test that get_mane_data_from_chr_pos method works correctly"""
161161
resp = test_mane_transcript_mappings.get_mane_data_from_chr_pos(
162-
"7", 140753336, 140753336)
162+
"NC_000007.14", 140753336, 140753336)
163163
assert len(resp) == 2
164164
assert resp == [braf_select, braf_plus_clinical]
165165

166166
resp = test_mane_transcript_mappings.get_mane_data_from_chr_pos(
167-
"X", 37994300, 37994310)
167+
"NC_000023.11", 37994300, 37994310)
168168
assert len(resp) == 1
169169
assert resp == [{
170170
"#NCBI_GeneID": "GeneID:115482686",
@@ -177,13 +177,13 @@ def test_get_mane_data_from_chr_pos(test_mane_transcript_mappings, braf_select,
177177
"Ensembl_nuc": "ENST00000448797.3",
178178
"Ensembl_prot": "ENSP00000498087.1",
179179
"MANE_status": "MANE Select",
180-
"GRCh38_chr": "X",
180+
"GRCh38_chr": "NC_000023.11",
181181
"chr_start": 37994272,
182182
"chr_end": 37994904,
183183
"chr_strand": "+"
184184
}]
185185

186-
# Invalid chromosome
186+
# Invalid alt_ac (no version)
187187
resp = test_mane_transcript_mappings.get_mane_data_from_chr_pos(
188-
"x", 37994300, 37994310)
188+
"NC_000023", 37994300, 37994310)
189189
assert resp == []

0 commit comments

Comments
 (0)