cool-seq-tool 0.10.0__py3-none-any.whl → 0.12.0__py3-none-any.whl

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/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/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.dist-info → cool_seq_tool-0.12.0.dist-info}/METADATA

@@ -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.dist-info → cool_seq_tool-0.12.0.dist-info}/RECORD

@@ -1,12 +1,12 @@
 cool_seq_tool/__init__.py,sha256=pJyVj7Z275BBAwpeFMm-WEn_tp-y1_ihRl1sLc4FFZY,400
 cool_seq_tool/app.py,sha256=vyqlQRffC8sWZXMm-f_f-8WuTTWo3oRNfPUa_qdPV2M,4944
-cool_seq_tool/schemas.py,sha256=HInmKpsujybVR6pRmkKNOIzPCBqk9Ni5q1ZKNFtip50,3945
+cool_seq_tool/schemas.py,sha256=D0DsYAR1ZX7RONuc7X4hsPMKcZct7_2LlnE1KKVNre0,4139
 cool_seq_tool/utils.py,sha256=kesu7UnOplDzvNBg_G-_m1xMM22979nmsi4yWtweetU,2959
 cool_seq_tool/handlers/__init__.py,sha256=KalQ46vX1MO4SJz2SlspKoIRy1n3c3Vp1t4Y2pIfqow,78
 cool_seq_tool/handlers/seqrepo_access.py,sha256=Jd19jbdUvPRPn_XWozL67ph-nSIxpb4_UUimapDrsm4,9162
 cool_seq_tool/mappers/__init__.py,sha256=O0JRxNFk8nWxD4v5ij47xelhvfVLdEXS43l2tzRuiUE,305
 cool_seq_tool/mappers/alignment.py,sha256=nV6PS3mhkQ2MD1GcpNBujBOqd3AKxYSYA9BCusFOa1o,9636
-cool_seq_tool/mappers/exon_genomic_coords.py,sha256=uOJGy8HFoe1mjoxnaKP9x60hcgQm03vINJpUzJfxE0A,43948
+cool_seq_tool/mappers/exon_genomic_coords.py,sha256=ORYjBVaX1HO6ln0gRJyRKxUCjZrBDi4JfYQEYebxIAc,43824
 cool_seq_tool/mappers/liftover.py,sha256=lltx9zxfkrb5PHtJlKp3a39JCwPP4e0Zft-mQc1jXL8,3367
 cool_seq_tool/mappers/mane_transcript.py,sha256=C9eKEj8qhVg878oUhBKPYAZS7gpLM5aaQ0HhSkUg-2g,54365
 cool_seq_tool/resources/__init__.py,sha256=VwUC8YaucTS6SmRirToulZTF6CuvuLQRSxFfSfAovCc,77
@@ -14,11 +14,11 @@ cool_seq_tool/resources/data_files.py,sha256=3lhu28tzlSoTs4vHZNu-hhoAWRrPGuZj_oI
 cool_seq_tool/resources/status.py,sha256=L0KM-VG3N4Yuaqh3AKZd_2KPDLR0Y7rvW_OD6x8mF7A,5717
 cool_seq_tool/resources/transcript_mapping.tsv,sha256=AO3luYQAbFiCoRgiiPXotakb5pAwx1jDCeXpvGdIuac,24138769
 cool_seq_tool/sources/__init__.py,sha256=51QiymeptF7AeVGgV-tW_9f4pIUr0xtYbyzpvHOCneM,304
-cool_seq_tool/sources/mane_transcript_mappings.py,sha256=Q6J57O2lLWXlgKT0zq3BIwkwFawySnORHOX-UxzfyDE,5399
+cool_seq_tool/sources/mane_transcript_mappings.py,sha256=C5puIA1xuEzBaSvs8VtSxVb2OIDGUg5no8v6Ma2QSdw,6597
 cool_seq_tool/sources/transcript_mappings.py,sha256=903RKTMBO2rbKh6iTQ1BEWnY4C7saBFMPw2_4ATuudg,10054
 cool_seq_tool/sources/uta_database.py,sha256=s7BkFplD_b2AmvXq8vZSCiBuZLy8RlxAqNyf-6QtR8w,36112
-cool_seq_tool-0.10.0.dist-info/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
-cool_seq_tool-0.10.0.dist-info/METADATA,sha256=EOIMJIeXl9Om4LrUrr2ccPED68ou52_4lqTCrkWHzHQ,6557
-cool_seq_tool-0.10.0.dist-info/WHEEL,sha256=A3WOREP4zgxI0fKrHUG8DC8013e3dK3n7a6HDbcEIwE,91
-cool_seq_tool-0.10.0.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
-cool_seq_tool-0.10.0.dist-info/RECORD,,
+cool_seq_tool-0.12.0.dist-info/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
+cool_seq_tool-0.12.0.dist-info/METADATA,sha256=Nt7O4bD59cQqje3eH_sKPkP8uvPz9ApxjKMvS6so0HE,6557
+cool_seq_tool-0.12.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+cool_seq_tool-0.12.0.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
+cool_seq_tool-0.12.0.dist-info/RECORD,,

{cool_seq_tool-0.10.0.dist-info → cool_seq_tool-0.12.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.7.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any