fix: MANE Summary data >= v1.1 updated GRCh38_chr (#149) (#150)

- < v1.1 used 1...22, X, Y. >= v1.1 uses NC accessions
GenomicMedLab · May 1, 2023 · a5617d0 · a5617d0
1 parent 28f3e9c
commit a5617d0
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 15 deletions.
diff --git a/cool_seq_tool/data_sources/mane_transcript_mappings.py b/cool_seq_tool/data_sources/mane_transcript_mappings.py
@@ -52,17 +52,17 @@ def get_mane_from_transcripts(self, transcripts: List[str]) -> List[Dict]:
             return []
         return result.to_dict("records")
 
-    def get_mane_data_from_chr_pos(self, chromosome: str, start: int,
-                                   end: int) -> List[Dict]:
+    def get_mane_data_from_chr_pos(
+        self, alt_ac: str, start: int, end: int
+    ) -> List[Dict]:
         """Get MANE data given chromosome, start pos, end end pos. Assumes GRCh38.
-        :param str chromosome: Chromosome. Case sensitive for X, Y chromosomes.
-            Do not prefix. Valid examples: "1" ... "22", "X", "Y"
+        :param str alt_ac: NC Accession
         :param int start: Start genomic position. Assumes residue coordinates.
         :param int end: End genomic position. Assumes residue coordinates.
         :return: List of MANE data. Will return sorted list:
             MANE Select then MANE Plus Clinical.
         """
-        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
+        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
         if len(mane_rows) == 0:
             return []
         mane_rows = mane_rows.sort_values("MANE_status", ascending=False)

diff --git a/cool_seq_tool/version.py b/cool_seq_tool/version.py
@@ -1 +1 @@
-__version__ = "0.1.12"
+__version__ = "0.1.13"
diff --git a/tests/unit/test_mane_transcript_mappings.py b/tests/unit/test_mane_transcript_mappings.py
@@ -24,7 +24,7 @@ def braf_select():
         "Ensembl_nuc": "ENST00000646891.2",
         "Ensembl_prot": "ENSP00000493543.1",
         "MANE_status": "MANE Select",
-        "GRCh38_chr": "7",
+        "GRCh38_chr": "NC_000007.14",
         "chr_start": 140730665,
         "chr_end": 140924929,
         "chr_strand": "-"
@@ -45,7 +45,7 @@ def braf_plus_clinical():
         "Ensembl_nuc": "ENST00000644969.2",
         "Ensembl_prot": "ENSP00000496776.1",
         "MANE_status": "MANE Plus Clinical",
-        "GRCh38_chr": "7",
+        "GRCh38_chr": "NC_000007.14",
         "chr_start": 140719337,
         "chr_end": 140924929,
         "chr_strand": "-"
@@ -66,7 +66,7 @@ def ercc6_plus_clinical():
         "Ensembl_nuc": "ENST00000447839.7",
         "Ensembl_prot": "ENSP00000387966.2",
         "MANE_status": "MANE Plus Clinical",
-        "GRCh38_chr": "10",
+        "GRCh38_chr": "NC_000010.11",
         "chr_start": 49515198,
         "chr_end": 49539121,
         "chr_strand": "-"
@@ -87,7 +87,7 @@ def ercc6_select():
         "Ensembl_nuc": "ENST00000355832.10",
         "Ensembl_prot": "ENSP00000348089.5",
         "MANE_status": "MANE Select",
-        "GRCh38_chr": "10",
+        "GRCh38_chr": "NC_000010.11",
         "chr_start": 49454470,
         "chr_end": 49539121,
         "chr_strand": "-"
@@ -159,12 +159,12 @@ def test_get_mane_data_from_chr_pos(test_mane_transcript_mappings, braf_select,
                                     braf_plus_clinical):
     """Test that get_mane_data_from_chr_pos method works correctly"""
     resp = test_mane_transcript_mappings.get_mane_data_from_chr_pos(
-        "7", 140753336, 140753336)
+        "NC_000007.14", 140753336, 140753336)
     assert len(resp) == 2
     assert resp == [braf_select, braf_plus_clinical]
 
     resp = test_mane_transcript_mappings.get_mane_data_from_chr_pos(
-        "X", 37994300, 37994310)
+        "NC_000023.11", 37994300, 37994310)
     assert len(resp) == 1
     assert resp == [{
         "#NCBI_GeneID": "GeneID:115482686",
@@ -177,13 +177,13 @@ def test_get_mane_data_from_chr_pos(test_mane_transcript_mappings, braf_select,
         "Ensembl_nuc": "ENST00000448797.3",
         "Ensembl_prot": "ENSP00000498087.1",
         "MANE_status": "MANE Select",
-        "GRCh38_chr": "X",
+        "GRCh38_chr": "NC_000023.11",
         "chr_start": 37994272,
         "chr_end": 37994904,
         "chr_strand": "+"
     }]
 
-    # Invalid chromosome
+    # Invalid alt_ac (no version)
     resp = test_mane_transcript_mappings.get_mane_data_from_chr_pos(
-        "x", 37994300, 37994310)
+        "NC_000023", 37994300, 37994310)
     assert resp == []