cool-seq-tool 0.10.0__tar.gz → 0.12.0__tar.gz

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: cool_seq_tool
-Version: 0.10.0
+Version: 0.12.0
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/src/cool_seq_tool/mappers/exon_genomic_coords.py

@@ -865,14 +865,14 @@ class ExonGenomicCoordsMapper:
         if use_alt_start_i and coordinate_type == CoordinateType.RESIDUE:
             genomic_pos = genomic_pos - 1  # Convert residue coordinate to inter-residue
 
-        # Validate that the breakpoint occurs on a transcript given a gene
-        coordinate_check = await self._validate_gene_coordinates(
-            pos=genomic_pos, genomic_ac=genomic_ac, gene=gene
+        # Validate that the breakpoint between the first and last exon for the selected transcript
+        coordinate_check = await self._validate_genomic_breakpoint(
+            pos=genomic_pos, genomic_ac=genomic_ac, tx_ac=transcript
         )
         if not coordinate_check:
             return GenomicTxSeg(
                 errors=[
-                    f"{genomic_pos} on {genomic_ac} does not occur within the exons for {gene}"
+                    f"{genomic_pos} on {genomic_ac} does not occur within the exons for {transcript}"
                 ]
             )
 
@@ -943,38 +943,32 @@ class ExonGenomicCoordsMapper:
         )
         return liftover_data[1] if liftover_data else None
 
-    async def _validate_gene_coordinates(
+    async def _validate_genomic_breakpoint(
         self,
         pos: int,
         genomic_ac: str,
-        gene: str,
+        tx_ac: str,
     ) -> bool:
         """Validate that a genomic coordinate falls within the first and last exon
-            given a gene and accession
+            for a transcript on a given accession
 
         :param pos: Genomic position on ``genomic_ac``
         :param genomic_ac: RefSeq genomic accession, e.g. ``"NC_000007.14"``
-        :param gene: A valid, case-sensitive HGNC gene symbol
+        :param transcript: A transcript accession
         :return: ``True`` if the coordinate falls within the first and last exon
-            for the gene, ``False`` if not
+            for the transcript, ``False`` if not
         """
         query = f"""
             WITH tx_boundaries AS (
-                    SELECT
-                    tx_ac,
-                    hgnc,
-                    MIN(alt_start_i) as min_start,
-                    MAX(alt_end_i) as max_end
+                SELECT
+                MIN(alt_start_i) AS min_start,
+                MAX(alt_end_i) AS max_end
                 FROM {self.uta_db.schema}.tx_exon_aln_v
-                WHERE hgnc = '{gene}'
+                WHERE tx_ac = '{tx_ac}'
                 AND alt_ac = '{genomic_ac}'
-                GROUP BY tx_ac, hgnc
             )
-            SELECT DISTINCT hgnc
-            FROM tx_boundaries
+            SELECT * FROM tx_boundaries
             WHERE {pos} between tx_boundaries.min_start and tx_boundaries.max_end
-            ORDER BY hgnc
-            LIMIT 1;
             """  # noqa: S608
         results = await self.uta_db.execute_query(query)
         return bool(results)

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/src/cool_seq_tool/schemas.py

@@ -43,11 +43,18 @@ class Assembly(str, Enum):
         return [item.value for item in cls]
 
 
+class ManeStatus(str, Enum):
+    """Define constraints for mane status"""
+
+    SELECT = "mane_select"
+    PLUS_CLINICAL = "mane_plus_clinical"
+
+
 class TranscriptPriority(str, Enum):
     """Create Enum for Transcript Priority labels"""
 
-    MANE_SELECT = "mane_select"
-    MANE_PLUS_CLINICAL = "mane_plus_clinical"
+    MANE_SELECT = ManeStatus.SELECT.value
+    MANE_PLUS_CLINICAL = ManeStatus.PLUS_CLINICAL.value
     LONGEST_COMPATIBLE_REMAINING = "longest_compatible_remaining"
     GRCH38 = "grch38"
 
@@ -137,6 +144,7 @@ class ManeGeneData(BaseModel, extra="forbid"):
     ncbi_gene_id: StrictInt
     hgnc_id: StrictInt | None
     symbol: StrictStr
+    status: list[ManeStatus]
 
 
 class ServiceMeta(BaseModelForbidExtra):

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/src/cool_seq_tool/sources/mane_transcript_mappings.py

@@ -117,26 +117,58 @@ class ManeTranscriptMappings:
         :param end: Genomic end position. Assumes residue coordinates.
         :return: Unique MANE gene(s) found for a genomic location
         """
+        # Only interested in rows where genomic location lives
         mane_rows = self.df.filter(
             (start >= pl.col("chr_start"))
             & (end <= pl.col("chr_end"))
             & (pl.col("GRCh38_chr") == ac)
-        ).unique(subset=["#NCBI_GeneID"])
+        )
 
-        if len(mane_rows) == 0:
+        if mane_rows.is_empty():
             return []
 
-        mane_rows = mane_rows.with_columns(
-            pl.col("#NCBI_GeneID")
-            .str.split_exact(":", 1)
-            .struct.field("field_1")
-            .cast(pl.Int32)
-            .alias("ncbi_gene_id"),
-            pl.col("HGNC_ID")
-            .str.split_exact(":", 1)
-            .struct.field("field_1")
-            .cast(pl.Int32)
-            .alias("hgnc_id"),
+        # Group rows by NCBI ID, transform values to representation we want, MANE status
+        # will be converted to list with DESC order
+        mane_rows = mane_rows.group_by("#NCBI_GeneID").agg(
+            [
+                pl.col("#NCBI_GeneID")
+                .first()
+                .str.split_exact(":", 1)
+                .struct.field("field_1")
+                .cast(pl.Int32)
+                .alias("ncbi_gene_id"),
+                pl.col("HGNC_ID")
+                .first()
+                .str.split_exact(":", 1)
+                .struct.field("field_1")
+                .cast(pl.Int32)
+                .alias("hgnc_id"),
+                pl.col("MANE_status")
+                .unique()
+                .str.to_lowercase()
+                .str.replace_all(" ", "_")
+                .alias("status")
+                .sort(descending=True),
+                pl.col("symbol").first(),
+            ]
+        )
+
+        # Sort final rows based on MANE status
+        # First by length (which means gene has both select and plus clinical)
+        # Then by DESC order
+        # Then by NCBI ID ASC order
+        mane_rows = (
+            mane_rows.with_columns(
+                [
+                    pl.col("status").list.len().alias("status_count"),
+                    pl.col("status").list.join("_").alias("status_str"),
+                    pl.col("ncbi_gene_id"),
+                ]
+            )
+            .sort(
+                ["status_count", "status_str", "ncbi_gene_id"],
+                descending=[True, True, False],
+            )
+            .drop(["status_count", "status_str", "#NCBI_GeneID"])
         )
-        mane_rows = mane_rows.select(["ncbi_gene_id", "hgnc_id", "symbol"])
         return [ManeGeneData(**mane_gene) for mane_gene in mane_rows.to_dicts()]

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/src/cool_seq_tool.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: cool_seq_tool
-Version: 0.10.0
+Version: 0.12.0
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/tests/conftest.py

@@ -340,10 +340,19 @@ def genomic_tx_data():
 @pytest.fixture(scope="session")
 def egfr_mane_gene():
     """Create test fixture for EGFR MANE gene"""
-    return ManeGeneData(ncbi_gene_id=1956, hgnc_id=3236, symbol="EGFR")
+    return ManeGeneData(
+        ncbi_gene_id=1956, hgnc_id=3236, symbol="EGFR", status=["mane_select"]
+    )
 
 
 @pytest.fixture(scope="session")
-def braf_mane_gene():
+def braf_mane_genes():
     """Create test fixture for BRAF MANE gene"""
-    return ManeGeneData(ncbi_gene_id=673, hgnc_id=1097, symbol="BRAF")
+    return [
+        ManeGeneData(
+            ncbi_gene_id=673,
+            hgnc_id=1097,
+            symbol="BRAF",
+            status=["mane_select", "mane_plus_clinical"],
+        ),
+    ]

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/tests/mappers/test_exon_genomic_coords.py

@@ -1516,7 +1516,7 @@ async def test_invalid(test_egc_mapper):
     )
     genomic_tx_seg_service_checks(resp, is_valid=False)
     assert resp.errors == [
-        "9999999999998 on NC_000001.11 does not occur within the exons for TPM3"
+        "9999999999998 on NC_000001.11 does not occur within the exons for NM_152263.3"
     ]
 
     # Must supply either gene or transcript

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/tests/mappers/test_mane_transcript.py

@@ -143,13 +143,13 @@ def grch38_egfr(egfr_mane_gene):
 
 
 @pytest.fixture(scope="module")
-def grch38_braf(braf_mane_gene):
+def grch38_braf(braf_mane_genes):
     """Create a test fixture for grch38 responses BRAF V600E (genomic)."""
     params = {
         "pos": (140753335, 140753336),
         "status": TranscriptPriority.GRCH38.value,
         "ac": "NC_000007.14",
-        "mane_genes": [braf_mane_gene],
+        "mane_genes": braf_mane_genes,
     }
     return GenomicRepresentation(**params)
 

{cool_seq_tool-0.10.0 → cool_seq_tool-0.12.0}/tests/sources/test_mane_transcript_mappings.py

@@ -209,28 +209,75 @@ def test_get_mane_data_from_chr_pos(
 
 
 def test_get_genomic_mane_genes(
-    test_mane_transcript_mappings, braf_mane_gene, egfr_mane_gene
+    test_mane_transcript_mappings, braf_mane_genes, egfr_mane_gene
 ):
     """Test that get_genomic_mane_genes method works correctly"""
     new_df = pl.DataFrame(
         {
-            "#NCBI_GeneID": ["GeneID:673", "GeneID:673", "GeneID:1956", "GeneID:1"],
+            "#NCBI_GeneID": [
+                "GeneID:673",
+                "GeneID:673",
+                "GeneID:1956",
+                "GeneID:1",
+                "GeneID:2",
+                "GeneID:2",
+                "GeneID:3",
+            ],
             "Ensembl_Gene": [
                 "ENSG00000157764.14",
                 "ENSG00000157764.14",
                 "ENSG00000146648.21",
                 "ENSG1.1",
+                "ENSG1.1",
+                "ENSG1.1",
+                "ENSG1.1",
+            ],
+            "HGNC_ID": [
+                "HGNC:1097",
+                "HGNC:1097",
+                "HGNC:3236",
+                "HGNC:1",
+                "HGNC:2",
+                "HGNC:2",
+                "HGNC:3",
             ],
-            "HGNC_ID": ["HGNC:1097", "HGNC:1097", "HGNC:3236", "HGNC:2"],
-            "symbol": ["BRAF", "BRAF", "EGFR", "Dummy"],
+            "symbol": ["BRAF", "BRAF", "EGFR", "Dummy1", "Dummy2", "Dummy2", "Dummy3"],
             "GRCh38_chr": [
                 "NC_000007.14",
                 "NC_000007.14",
                 "NC_000007.14",
                 "NC_000007.14",
+                "NC_000007.14",
+                "NC_000007.14",
+                "NC_000007.14",
+            ],
+            "chr_start": [
+                140719337,
+                140730665,
+                55019017,
+                55019017,
+                55019017,
+                55019017,
+                55019017,
+            ],
+            "chr_end": [
+                140924929,
+                140924929,
+                55211628,
+                55211628,
+                55211628,
+                55211628,
+                55211628,
+            ],
+            "MANE_status": [
+                "MANE Plus Clinical",
+                "MANE Select",
+                "MANE Select",
+                "MANE Plus Clinical",
+                "MANE Select",
+                "MANE Plus Clinical",
+                "MANE Select",
             ],
-            "chr_start": [140719337, 140730665, 55019017, 55019017],
-            "chr_end": [140924929, 140924929, 55211628, 55211628],
         }
     )
 
@@ -238,14 +285,29 @@ def test_get_genomic_mane_genes(
         mane_genes = test_mane_transcript_mappings.get_genomic_mane_genes(
             "NC_000007.14", 140753336, 140753336
         )
-        assert mane_genes == [braf_mane_gene]
+        assert mane_genes == braf_mane_genes
 
         mane_genes = test_mane_transcript_mappings.get_genomic_mane_genes(
             "NC_000007.14", 55191822, 55191822
         )
-        assert len(mane_genes) == 2
-        assert egfr_mane_gene in mane_genes
-        assert ManeGeneData(ncbi_gene_id=1, hgnc_id=2, symbol="Dummy") in mane_genes
+        assert mane_genes == [
+            ManeGeneData(
+                ncbi_gene_id=2,
+                hgnc_id=2,
+                symbol="Dummy2",
+                status=["mane_select", "mane_plus_clinical"],
+            ),
+            ManeGeneData(
+                ncbi_gene_id=3, hgnc_id=3, symbol="Dummy3", status=["mane_select"]
+            ),
+            egfr_mane_gene,
+            ManeGeneData(
+                ncbi_gene_id=1,
+                hgnc_id=1,
+                symbol="Dummy1",
+                status=["mane_plus_clinical"],
+            ),
+        ]
 
         # No MANE genes found for given genomic location
         mane_genes = test_mane_transcript_mappings.get_genomic_mane_genes(