refactor!: get_gene_mane_data sorted by desc MANE_Status

* Now returns MANE Select and then MANE Plus Clinical

cool_seq_tool/mappers/mane_transcript.py

@@ -737,7 +737,6 @@ async def get_mane_transcript(
             mane_data = self.mane_transcript_mappings.get_gene_mane_data(g["gene"])
             if not mane_data:
                 return None
-            mane_data_len = len(mane_data)
 
             # Transcript Priority (Must pass validation checks):
             #  1. MANE Select
@@ -746,9 +745,7 @@ async def get_mane_transcript(
             #     a. If there is a tie, choose the first-published transcript among
             #        those transcripts meeting criterion
             mane_transcripts = set()
-            for i in range(mane_data_len):
-                index = mane_data_len - i - 1
-                current_mane_data = mane_data[index]
+            for current_mane_data in mane_data:
                 mane_transcripts |= set(
                     (current_mane_data["RefSeq_nuc"], current_mane_data["Ensembl_nuc"])
                 )
@@ -957,11 +954,8 @@ async def g_to_mane_c(
         mane_data = self.mane_transcript_mappings.get_gene_mane_data(gene)
         if not mane_data:
             return None
-        mane_data_len = len(mane_data)
 
-        for i in range(mane_data_len):
-            index = mane_data_len - i - 1
-            current_mane_data = mane_data[index]
+        for current_mane_data in mane_data:
             mane_c_ac = current_mane_data["RefSeq_nuc"]
 
             # Liftover to GRCh38

cool_seq_tool/sources/mane_transcript_mappings.py

@@ -29,8 +29,9 @@ def _load_mane_transcript_data(self) -> pl.DataFrame:
     def get_gene_mane_data(self, gene_symbol: str) -> Optional[List[Dict]]:
         """Return MANE Transcript data for a gene.
         :param str gene_symbol: HGNC Gene Symbol
-        :return: MANE Transcript data (Transcript accessions,
-            gene, and location information)
+        :return: List of MANE Transcript data (Transcript accessions,
+            gene, and location information). Sorted list: MANE Select and then MANE Plus
+            Clinical
         """
         data = self.df.filter(pl.col("symbol") == gene_symbol.upper())
 
@@ -40,8 +41,7 @@ def get_gene_mane_data(self, gene_symbol: str) -> Optional[List[Dict]]:
             )
             return None
 
-        # Ordering: MANE Plus Clinical (If it exists), MANE Select
-        data = data.sort(by="MANE_status", descending=False)
+        data = data.sort(by="MANE_status", descending=True)
         return data.to_dicts()
 
     def get_mane_from_transcripts(self, transcripts: List[str]) -> List[Dict]:

tests/sources/test_mane_transcript_mappings.py

@@ -97,23 +97,23 @@ def test_get_gene_mane_data(
     # MANE Select
     actual = test_mane_transcript_mappings.get_gene_mane_data("BRAF")
     assert len(actual) == 2
-    assert actual[0] == braf_plus_clinical
-    assert actual[1] == braf_select
+    assert actual[0] == braf_select
+    assert actual[1] == braf_plus_clinical
 
     actual = test_mane_transcript_mappings.get_gene_mane_data("braf")
     assert len(actual) == 2
-    assert actual[0] == braf_plus_clinical
-    assert actual[1] == braf_select
+    assert actual[0] == braf_select
+    assert actual[1] == braf_plus_clinical
 
     # MANE Select and MANE Plus Clinical
     actual = test_mane_transcript_mappings.get_gene_mane_data("ERCC6")
     assert len(actual) == 2
-    assert actual[0] == ercc6_plus_clinical
-    assert actual[1] == ercc6_select
+    assert actual[0] == ercc6_select
+    assert actual[1] == ercc6_plus_clinical
 
     actual = test_mane_transcript_mappings.get_gene_mane_data("ercc6")
-    assert actual[0] == ercc6_plus_clinical
-    assert actual[1] == ercc6_select
+    assert actual[0] == ercc6_select
+    assert actual[1] == ercc6_plus_clinical
 
     # No Matches
     actual = test_mane_transcript_mappings.get_gene_mane_data("BRAFF")