cool-seq-tool 0.4.0.dev3__py3-none-any.whl → 0.5.0__py3-none-any.whl

cool_seq_tool/mappers/mane_transcript.py

@@ -11,15 +11,17 @@ Steps:
 In addition to a mapper utility class, this module also defines several vocabulary
 constraints and data models for coordinate representation.
 """
+
 import logging
 import math
 from enum import Enum
-from typing import Dict, List, Optional, Set, Tuple, Union
+from typing import Literal
 
 import polars as pl
 from pydantic import BaseModel
 
 from cool_seq_tool.handlers.seqrepo_access import SeqRepoAccess
+from cool_seq_tool.mappers.liftover import LiftOver
 from cool_seq_tool.schemas import (
     AnnotationLayer,
     Assembly,
@@ -34,7 +36,7 @@ from cool_seq_tool.sources import (
 )
 from cool_seq_tool.utils import get_inter_residue_pos
 
-logger = logging.getLogger(__name__)
+_logger = logging.getLogger(__name__)
 
 
 class EndAnnotationLayer(str, Enum):
@@ -50,10 +52,10 @@ class EndAnnotationLayer(str, Enum):
 class DataRepresentation(BaseModel):
     """Define object model for final output representation"""
 
-    gene: Optional[str] = None
+    gene: str | None = None
     refseq: str
-    ensembl: Optional[str] = None
-    pos: Tuple[int, int]
+    ensembl: str | None = None
+    pos: tuple[int, int]
     strand: Strand
     status: TranscriptPriority
 
@@ -63,14 +65,14 @@ class CdnaRepresentation(DataRepresentation):
 
     coding_start_site: int
     coding_end_site: int
-    alt_ac: Optional[str] = None
+    alt_ac: str | None = None
 
 
 class GenomicRepresentation(BaseModel):
     """Define object model for genomic representation"""
 
     refseq: str
-    pos: Tuple[int, int]
+    pos: tuple[int, int]
     status: TranscriptPriority
     alt_ac: str
 
@@ -91,6 +93,7 @@ class ManeTranscript:
         transcript_mappings: TranscriptMappings,
         mane_transcript_mappings: ManeTranscriptMappings,
         uta_db: UtaDatabase,
+        liftover: LiftOver,
     ) -> None:
         """Initialize the ManeTranscript class.
 
@@ -105,7 +108,7 @@ class ManeTranscript:
 
         >>> import asyncio
         >>> result = asyncio.run(mane_mapper.g_to_grch38("NC_000001.11", 100, 200))
-        >>> result['ac']
+        >>> result["ac"]
         'NC_000001.11'
 
         See the :ref:`Usage section <async_note>` for more information.
@@ -116,11 +119,13 @@ class ManeTranscript:
         :param mane_transcript_mappings: Access to MANE Transcript accession mapping
             data
         :param uta_db: UtaDatabase instance to give access to query UTA database
+        :param liftover: Instance to provide mapping between human genome assemblies
         """
         self.seqrepo_access = seqrepo_access
         self.transcript_mappings = transcript_mappings
         self.mane_transcript_mappings = mane_transcript_mappings
         self.uta_db = uta_db
+        self.liftover = liftover
 
     @staticmethod
     def _get_reading_frame(pos: int) -> int:
@@ -135,7 +140,7 @@ class ManeTranscript:
         return pos_mod_3
 
     @staticmethod
-    def _p_to_c_pos(start: int, end: int) -> Tuple[int, int]:
+    def _p_to_c_pos(start: int, end: int) -> tuple[int, int]:
         """Return cDNA position given a protein position.
 
         :param start: Start protein position. Inter-residue coordinates
@@ -148,7 +153,7 @@ class ManeTranscript:
 
     async def _p_to_c(
         self, ac: str, start_pos: int, end_pos: int
-    ) -> Optional[Tuple[str, Tuple[int, int]]]:
+    ) -> tuple[str, tuple[int, int]] | None:
         """Convert protein (p.) annotation to cDNA (c.) annotation.
 
         :param ac: Protein accession
@@ -167,16 +172,16 @@ class ManeTranscript:
                 elif ac.startswith("ENSP"):
                     ac = self.transcript_mappings.ensp_to_enst[ac]
                 else:
-                    logger.warning("Unable to find accession: %s", ac)
+                    _logger.warning("Unable to find accession: %s", ac)
                     return None
             except KeyError:
-                logger.warning("%s not found in transcript_mappings", ac)
+                _logger.warning("%s not found in transcript_mappings", ac)
                 return None
 
         pos = self._p_to_c_pos(start_pos, end_pos)
         return ac, pos
 
-    async def _c_to_g(self, ac: str, pos: Tuple[int, int]) -> Optional[Dict]:
+    async def _c_to_g(self, ac: str, pos: tuple[int, int]) -> dict | None:
         """Get g. annotation from c. annotation.
 
         :param ac: cDNA accession
@@ -195,7 +200,7 @@ class ManeTranscript:
                     0
                 ]
             ):
-                logger.warning("Ensembl transcript not found: %s", ac)
+                _logger.warning("Ensembl transcript not found: %s", ac)
                 return None
 
             temp_ac = ac.split(".")[0]
@@ -205,7 +210,7 @@ class ManeTranscript:
         # c. coordinate does not contain cds start, so we need to add it
         cds_start_end = await self.uta_db.get_cds_start_end(temp_ac)
         if not cds_start_end:
-            logger.warning("Accession %s not found in UTA", temp_ac)
+            _logger.warning("Accession %s not found in UTA", temp_ac)
             return None
         coding_start_site = cds_start_end[0]
         pos = pos[0] + coding_start_site, pos[1] + coding_start_site
@@ -214,16 +219,108 @@ class ManeTranscript:
             ac, pos, AnnotationLayer.CDNA, coding_start_site=coding_start_site
         )
 
+    async def _liftover_to_38(self, genomic_tx_data: dict) -> None:
+        """Liftover genomic_tx_data to hg38 assembly.
+
+        :param genomic_tx_data: Dictionary containing gene, nc_accession, alt_pos, and
+            strand. This will be mutated in-place if not GRCh38 assembly.
+        """
+        descr = await self.uta_db.get_chr_assembly(genomic_tx_data["alt_ac"])
+        if descr is None:
+            # already grch38
+            return
+        chromosome, _ = descr
+
+        query = f"""
+            SELECT DISTINCT alt_ac
+            FROM {self.uta_db.schema}.tx_exon_aln_v
+            WHERE tx_ac = '{genomic_tx_data['tx_ac']}';
+            """  # noqa: S608
+        nc_acs = await self.uta_db.execute_query(query)
+        nc_acs = [nc_ac[0] for nc_ac in nc_acs]
+        if nc_acs == [genomic_tx_data["alt_ac"]]:
+            _logger.warning(
+                "UTA does not have GRCh38 assembly for %s",
+                genomic_tx_data["alt_ac"].split(".")[0],
+            )
+            return
+
+        # Get most recent assembly version position
+        # Liftover range
+        self._set_liftover(
+            genomic_tx_data, "alt_pos_range", chromosome, Assembly.GRCH38
+        )
+
+        # Liftover changes range
+        self._set_liftover(
+            genomic_tx_data, "alt_pos_change_range", chromosome, Assembly.GRCH38
+        )
+
+        # Change alt_ac to most recent
+        if genomic_tx_data["alt_ac"].startswith("EN"):
+            order_by_cond = "ORDER BY alt_ac DESC;"
+        else:
+            order_by_cond = """
+            ORDER BY CAST(SUBSTR(alt_ac, position('.' in alt_ac) + 1,
+            LENGTH(alt_ac)) AS INT) DESC;
+            """
+        query = f"""
+            SELECT alt_ac
+            FROM {self.uta_db.schema}.genomic
+            WHERE alt_ac LIKE '{genomic_tx_data['alt_ac'].split('.')[0]}%'
+            {order_by_cond}
+            """  # noqa: S608
+        nc_acs = await self.uta_db.execute_query(query)
+        genomic_tx_data["alt_ac"] = nc_acs[0][0]
+
+    def _set_liftover(
+        self,
+        genomic_tx_data: dict,
+        key: str,
+        chromosome: str,
+        liftover_to_assembly: Assembly,
+    ) -> None:
+        """Update genomic_tx_data to have coordinates for given assembly.
+
+        :param genomic_tx_data: Dictionary containing gene, nc_accession, alt_pos, and
+            strand
+        :param key: Key to access coordinate positions
+        :param chromosome: Chromosome, must be prefixed with ``chr``
+        :param liftover_to_assembly: Assembly to liftover to
+        """
+        liftover_start_i = self.liftover.get_liftover(
+            chromosome, genomic_tx_data[key][0], liftover_to_assembly
+        )
+        if liftover_start_i is None:
+            _logger.warning(
+                "Unable to liftover position %s on %s",
+                genomic_tx_data[key][0],
+                chromosome,
+            )
+            return
+
+        liftover_end_i = self.liftover.get_liftover(
+            chromosome, genomic_tx_data[key][1], liftover_to_assembly
+        )
+        if liftover_end_i is None:
+            _logger.warning(
+                "Unable to liftover position %s on %s",
+                genomic_tx_data[key][1],
+                chromosome,
+            )
+            return
+
+        genomic_tx_data[key] = liftover_start_i[1], liftover_end_i[1]
+
     async def _get_and_validate_genomic_tx_data(
         self,
         tx_ac: str,
-        pos: Tuple[int, int],
-        annotation_layer: Union[
-            AnnotationLayer.CDNA, AnnotationLayer.GENOMIC
-        ] = AnnotationLayer.CDNA,
-        coding_start_site: Optional[int] = None,
-        alt_ac: Optional[str] = None,
-    ) -> Optional[Dict]:
+        pos: tuple[int, int],
+        annotation_layer: Literal[AnnotationLayer.CDNA]
+        | Literal[AnnotationLayer.GENOMIC] = AnnotationLayer.CDNA,
+        coding_start_site: int | None = None,
+        alt_ac: str | None = None,
+    ) -> dict | None:
         """Get and validate genomic_tx_data
 
         :param tx_ac: Accession on c. coordinate
@@ -237,7 +334,7 @@ class ManeTranscript:
             tx_ac, pos, annotation_layer, alt_ac=alt_ac
         )
         if not genomic_tx_data:
-            logger.warning(
+            _logger.warning(
                 "Unable to find genomic_tx_data for %s at position %s on annotation layer %s",
                 alt_ac,
                 pos,
@@ -250,12 +347,12 @@ class ManeTranscript:
             # Only want to liftover if alt_ac not provided. If alt_ac is provided,
             # it means user wants to stick with the queried assembly
             og_alt_exon_id = genomic_tx_data["alt_exon_id"]
-            await self.uta_db.liftover_to_38(genomic_tx_data)
+            await self._liftover_to_38(genomic_tx_data)
             liftover_alt_exon_id = genomic_tx_data["alt_exon_id"]
 
             # Validation check: Exon structure
             if og_alt_exon_id != liftover_alt_exon_id:
-                logger.warning(
+                _logger.warning(
                     "Original alt_exon_id %s does not match liftover alt_exon_id %s",
                     og_alt_exon_id,
                     liftover_alt_exon_id,
@@ -266,14 +363,14 @@ class ManeTranscript:
 
     @staticmethod
     def _get_c_data(
-        cds_start_end: Tuple[int, int],
-        c_pos_change: Tuple[int, int],
+        cds_start_end: tuple[int, int],
+        c_pos_change: tuple[int, int],
         strand: Strand,
         status: TranscriptPriority,
         refseq_c_ac: str,
-        gene: Optional[str] = None,
-        ensembl_c_ac: Optional[str] = None,
-        alt_ac: Optional[str] = None,
+        gene: str | None = None,
+        ensembl_c_ac: str | None = None,
+        alt_ac: str | None = None,
     ) -> CdnaRepresentation:
         """Return transcript data on c. coordinate.
 
@@ -293,7 +390,7 @@ class ManeTranscript:
         gt_cds_end = c_pos_change[1] > cds_end and c_pos_change[1] > cds_end
 
         if lt_cds_start or gt_cds_end:
-            logger.info(
+            _logger.info(
                 "%s with position %s is not within CDS start/end",
                 refseq_c_ac,
                 c_pos_change,
@@ -311,7 +408,7 @@ class ManeTranscript:
             alt_ac=alt_ac,
         )
 
-    def _c_to_p_pos(self, c_pos: Tuple[int, int]) -> Tuple[int, int]:
+    def _c_to_p_pos(self, c_pos: tuple[int, int]) -> tuple[int, int]:
         """Get protein position from cdna position
 
         :param c_pos: cdna position. inter-residue coordinates
@@ -325,7 +422,7 @@ class ManeTranscript:
         return start, end
 
     def _get_mane_p(
-        self, mane_data: Dict, mane_c_pos_range: Tuple[int, int]
+        self, mane_data: dict, mane_c_pos_range: tuple[int, int]
     ) -> DataRepresentation:
         """Translate MANE Transcript c. annotation to p. annotation
 
@@ -349,13 +446,13 @@ class ManeTranscript:
 
     async def _g_to_c(
         self,
-        g: Dict,
+        g: dict,
         refseq_c_ac: str,
         status: TranscriptPriority,
-        ensembl_c_ac: Optional[str] = None,
-        alt_ac: Optional[str] = None,
+        ensembl_c_ac: str | None = None,
+        alt_ac: str | None = None,
         found_result: bool = False,
-    ) -> Optional[CdnaRepresentation]:
+    ) -> CdnaRepresentation | None:
         """Get transcript c. annotation data from g. annotation.
 
         :param g: Genomic data
@@ -381,7 +478,7 @@ class ManeTranscript:
             )
 
             if not result:
-                logger.warning(
+                _logger.warning(
                     "Unable to find transcript, %s, position change", refseq_c_ac
                 )
                 return None
@@ -438,7 +535,7 @@ class ManeTranscript:
                 new_rf = self._get_reading_frame(transcript_data.pos[pos_index])
 
                 if og_rf != new_rf:
-                    logger.warning(
+                    _logger.warning(
                         "%s original reading frame (%s) does not match new %s, %s reading frame (%s)",
                         ac,
                         og_rf,
@@ -449,7 +546,7 @@ class ManeTranscript:
                     return False
             else:
                 if pos_index == 0:
-                    logger.warning("%s must having start position", ac)
+                    _logger.warning("%s must having start position", ac)
                     return False
         return True
 
@@ -459,9 +556,9 @@ class ManeTranscript:
         coding_start_site: int,
         start_pos: int,
         end_pos: int,
-        mane_transcript: Union[
-            DataRepresentation, CdnaRepresentation, GenomicRepresentation
-        ],
+        mane_transcript: DataRepresentation
+        | CdnaRepresentation
+        | GenomicRepresentation,
         expected_ref: str,
         anno: AnnotationLayer,
         residue_mode: ResidueMode,
@@ -503,10 +600,10 @@ class ManeTranscript:
                 residue_mode=residue_mode,
             )
             if not mane_ref:
-                logger.info("Unable to validate reference for MANE Transcript")
+                _logger.info("Unable to validate reference for MANE Transcript")
 
             if expected_ref != mane_ref:
-                logger.info(
+                _logger.info(
                     "Expected ref, %s, but got %s on MANE accession, %s",
                     expected_ref,
                     mane_ref,
@@ -514,7 +611,7 @@ class ManeTranscript:
                 )
 
         if expected_ref != ref:
-            logger.warning(
+            _logger.warning(
                 "Expected ref, %s, but got %s on accession, %s", expected_ref, ref, ac
             )
             return False
@@ -522,7 +619,7 @@ class ManeTranscript:
         return True
 
     def _validate_index(
-        self, ac: str, pos: Tuple[int, int], coding_start_site: int
+        self, ac: str, pos: tuple[int, int], coding_start_site: int
     ) -> bool:
         """Validate that positions actually exist on accession
 
@@ -533,13 +630,13 @@ class ManeTranscript:
         """
         start_pos = pos[0] + coding_start_site
         end_pos = pos[1] + coding_start_site
-        if self.seqrepo_access.get_reference_sequence(
-            ac, start=start_pos, end=end_pos, residue_mode=ResidueMode.INTER_RESIDUE
-        )[0]:
-            return True
-        return False
+        return bool(
+            self.seqrepo_access.get_reference_sequence(
+                ac, start=start_pos, end=end_pos, residue_mode=ResidueMode.INTER_RESIDUE
+            )[0]
+        )
 
-    def _get_prioritized_transcripts_from_gene(self, df: pl.DataFrame) -> List:
+    def _get_prioritized_transcripts_from_gene(self, df: pl.DataFrame) -> list:
         """Sort and filter transcripts from gene to get priority list
 
         :param df: Data frame containing transcripts from gene
@@ -550,7 +647,7 @@ class ManeTranscript:
             most recent version of a transcript associated with an assembly will be kept
         """
         copy_df = df.clone()
-        copy_df = copy_df.drop(columns="alt_ac").unique()
+        copy_df = copy_df.drop("alt_ac").unique()
         copy_df = copy_df.with_columns(
             [
                 pl.col("tx_ac")
@@ -590,15 +687,13 @@ class ManeTranscript:
         start_pos: int,
         end_pos: int,
         start_annotation_layer: AnnotationLayer,
-        gene: Optional[str] = None,
-        ref: Optional[str] = None,
+        gene: str | None = None,
+        ref: str | None = None,
         residue_mode: ResidueMode = ResidueMode.RESIDUE,
-        mane_transcripts: Optional[Set] = None,
-        alt_ac: Optional[str] = None,
-        end_annotation_layer: Optional[EndAnnotationLayer] = None,
-    ) -> Optional[
-        Union[DataRepresentation, CdnaRepresentation, ProteinAndCdnaRepresentation]
-    ]:
+        mane_transcripts: set | None = None,
+        alt_ac: str | None = None,
+        end_annotation_layer: EndAnnotationLayer | None = None,
+    ) -> DataRepresentation | CdnaRepresentation | ProteinAndCdnaRepresentation | None:
         """Get longest compatible transcript from a gene. See the documentation for
         the :ref:`transcript compatibility policy <transcript_compatibility>` for more
         information.
@@ -613,14 +708,16 @@ class ManeTranscript:
         ...     "NM_004333.6",
         ...     "ENST00000644969.2",
         ... }
-        >>> result = asyncio.run(mane_mapper.get_longest_compatible_transcript(
-        ...     599,
-        ...     599,
-        ...     gene="BRAF",
-        ...     start_annotation_layer=AnnotationLayer.PROTEIN,
-        ...     residue_mode=ResidueMode.INTER_RESIDUE,
-        ...     mane_transcripts=mane_transcripts,
-        ... ))
+        >>> result = asyncio.run(
+        ...     mane_mapper.get_longest_compatible_transcript(
+        ...         599,
+        ...         599,
+        ...         gene="BRAF",
+        ...         start_annotation_layer=AnnotationLayer.PROTEIN,
+        ...         residue_mode=ResidueMode.INTER_RESIDUE,
+        ...         mane_transcripts=mane_transcripts,
+        ...     )
+        ... )
         >>> result.refseq
         'NP_001365396.1'
 
@@ -645,9 +742,9 @@ class ManeTranscript:
         """
 
         def _get_protein_rep(
-            gene: Optional[str],
+            gene: str | None,
             pro_ac: str,
-            lcr_c_data_pos: Tuple[int, int],
+            lcr_c_data_pos: tuple[int, int],
             strand: Strand,
             status: TranscriptPriority,
         ) -> DataRepresentation:
@@ -692,7 +789,7 @@ class ManeTranscript:
             )
 
         if df.is_empty():
-            logger.warning("Unable to get transcripts from gene %s", gene)
+            _logger.warning("Unable to get transcripts from gene %s", gene)
             return lcr_result
 
         prioritized_tx_acs = self._get_prioritized_transcripts_from_gene(df)
@@ -731,7 +828,7 @@ class ManeTranscript:
 
             # Get prioritized transcript data for gene
             # grch38 -> c
-            lcr_c_data: Optional[CdnaRepresentation] = await self._g_to_c(
+            lcr_c_data: CdnaRepresentation | None = await self._g_to_c(
                 g=g,
                 refseq_c_ac=tx_ac,
                 status=TranscriptPriority.LONGEST_COMPATIBLE_REMAINING,
@@ -814,7 +911,7 @@ class ManeTranscript:
                 pos = lcr_result.pos
 
                 if not self._validate_index(ac, pos, coding_start_site):
-                    logger.warning(
+                    _logger.warning(
                         "%s are not valid positions on %s with coding start site %s",
                         pos,
                         ac,
@@ -841,7 +938,7 @@ class ManeTranscript:
                 pos = lcr_result_dict[k]["pos"]
                 if not self._validate_index(ac, pos, cds):
                     valid = False
-                    logger.warning(
+                    _logger.warning(
                         "%s are not valid positions on %s with coding start site %s",
                         pos,
                         ac,
@@ -859,25 +956,26 @@ class ManeTranscript:
         start_pos: int,
         end_pos: int,
         start_annotation_layer: AnnotationLayer,
-        gene: Optional[str] = None,
-        ref: Optional[str] = None,
+        gene: str | None = None,
+        ref: str | None = None,
         try_longest_compatible: bool = False,
-        residue_mode: Union[
-            ResidueMode.RESIDUE, ResidueMode.INTER_RESIDUE
-        ] = ResidueMode.RESIDUE,
-    ) -> Optional[Union[DataRepresentation, CdnaRepresentation]]:
+        residue_mode: Literal[ResidueMode.RESIDUE]
+        | Literal[ResidueMode.INTER_RESIDUE] = ResidueMode.RESIDUE,
+    ) -> DataRepresentation | CdnaRepresentation | None:
         """Return MANE transcript.
 
         >>> from cool_seq_tool.app import CoolSeqTool
         >>> from cool_seq_tool.schemas import AnnotationLayer, ResidueMode
         >>> import asyncio
         >>> mane_mapper = CoolSeqTool().mane_transcript
-        >>> result = asyncio.run(mane_mapper.get_mane_transcript(
-        ...     "NP_004324.2",
-        ...     599,
-        ...     AnnotationLayer.PROTEIN,
-        ...     residue_mode=ResidueMode.INTER_RESIDUE,
-        ... ))
+        >>> result = asyncio.run(
+        ...     mane_mapper.get_mane_transcript(
+        ...         "NP_004324.2",
+        ...         599,
+        ...         AnnotationLayer.PROTEIN,
+        ...         residue_mode=ResidueMode.INTER_RESIDUE,
+        ...     )
+        ... )
         >>> result.gene, result.refseq, result.status
         ('BRAF', 'NP_004324.2', <TranscriptPriority.MANE_SELECT: 'mane_select'>)
 
@@ -930,7 +1028,7 @@ class ManeTranscript:
                     current_mane_data["RefSeq_nuc"],
                     current_mane_data["Ensembl_nuc"],
                 }
-                mane: Optional[CdnaRepresentation] = await self._g_to_c(
+                mane: CdnaRepresentation | None = await self._g_to_c(
                     g=g,
                     refseq_c_ac=current_mane_data["RefSeq_nuc"],
                     status=TranscriptPriority(
@@ -998,12 +1096,10 @@ class ManeTranscript:
             return await self.g_to_mane_c(
                 ac, start_pos, end_pos, gene=gene, residue_mode=residue_mode
             )
-        logger.warning("Annotation layer not supported: %s", start_annotation_layer)
+        _logger.warning("Annotation layer not supported: %s", start_annotation_layer)
         return None
 
-    async def g_to_grch38(
-        self, ac: str, start_pos: int, end_pos: int
-    ) -> Optional[Dict]:
+    async def g_to_grch38(self, ac: str, start_pos: int, end_pos: int) -> dict | None:
         """Return genomic coordinate on GRCh38 when not given gene context.
 
         :param ac: Genomic accession
@@ -1025,11 +1121,11 @@ class ManeTranscript:
         is_same_pos = start_pos == end_pos
 
         # Coordinate liftover
-        if assembly < "GRCh37":
-            logger.warning("Liftover only supported for GRCh37")
+        if assembly < Assembly.GRCH37:
+            _logger.warning("Liftover only supported for GRCh37")
             return None
 
-        liftover_start_i = self.uta_db.get_liftover(
+        liftover_start_i = self.liftover.get_liftover(
             chromosome, start_pos, Assembly.GRCH38
         )
         if liftover_start_i is None:
@@ -1037,7 +1133,7 @@ class ManeTranscript:
         start_pos = liftover_start_i[1]
 
         if not is_same_pos:
-            liftover_end_i = self.uta_db.get_liftover(
+            liftover_end_i = self.liftover.get_liftover(
                 chromosome, end_pos, Assembly.GRCH38
             )
             if liftover_end_i is None:
@@ -1055,8 +1151,8 @@ class ManeTranscript:
 
     @staticmethod
     def get_mane_c_pos_change(
-        mane_tx_genomic_data: Dict, coding_start_site: int
-    ) -> Tuple[int, int]:
+        mane_tx_genomic_data: dict, coding_start_site: int
+    ) -> tuple[int, int]:
         """Get mane c position change
 
         :param mane_tx_genomic_data: MANE transcript and genomic data
@@ -1080,9 +1176,9 @@ class ManeTranscript:
         ac: str,
         start_pos: int,
         end_pos: int,
-        gene: Optional[str] = None,
+        gene: str | None = None,
         residue_mode: ResidueMode = ResidueMode.RESIDUE,
-    ) -> Optional[Union[GenomicRepresentation, CdnaRepresentation]]:
+    ) -> GenomicRepresentation | CdnaRepresentation | None:
         """Return MANE Transcript on the c. coordinate.
 
         If an arg for ``gene`` is provided, lifts to GRCh38, then gets MANE cDNA
@@ -1091,12 +1187,11 @@ class ManeTranscript:
         >>> import asyncio
         >>> from cool_seq_tool.app import CoolSeqTool
         >>> cst = CoolSeqTool()
-        >>> result = asyncio.run(cst.mane_transcript.g_to_mane_c(
-        ...     "NC_000007.13",
-        ...     55259515,
-        ...     None,
-        ...     gene="EGFR"
-        ... ))
+        >>> result = asyncio.run(
+        ...     cst.mane_transcript.g_to_mane_c(
+        ...         "NC_000007.13", 55259515, None, gene="EGFR"
+        ...     )
+        ... )
         >>> type(result)
         <class 'cool_seq_tool.mappers.mane_transcript.CdnaRepresentation'>
         >>> result.status
@@ -1132,7 +1227,7 @@ class ManeTranscript:
             )
 
         if not await self.uta_db.validate_genomic_ac(ac):
-            logger.warning("Genomic accession does not exist: %s", ac)
+            _logger.warning("Genomic accession does not exist: %s", ac)
             return None
 
         mane_data = self.mane_transcript_mappings.get_gene_mane_data(gene)
@@ -1158,7 +1253,7 @@ class ManeTranscript:
                 )
                 if not mane_tx_genomic_data:
                     continue
-                logger.info("Not using most recent assembly")
+                _logger.info("Not using most recent assembly")
 
             coding_start_site = mane_tx_genomic_data["coding_start_site"]
             coding_end_site = mane_tx_genomic_data["coding_end_site"]
@@ -1169,7 +1264,7 @@ class ManeTranscript:
             if not self._validate_index(
                 mane_c_ac, mane_c_pos_change, coding_start_site
             ):
-                logger.warning(
+                _logger.warning(
                     "%s are not valid positions on %s with coding start site %s",
                     mane_c_pos_change,
                     mane_c_ac,
@@ -1198,10 +1293,10 @@ class ManeTranscript:
         alt_ac: str,
         start_pos: int,
         end_pos: int,
-        gene: Optional[str] = None,
+        gene: str | None = None,
         residue_mode: ResidueMode = ResidueMode.RESIDUE,
         try_longest_compatible: bool = False,
-    ) -> Optional[Dict]:
+    ) -> dict | None:
         """Given GRCh38 genomic representation, return protein representation.
 
         Will try MANE Select and then MANE Plus Clinical. If neither is found and
@@ -1259,7 +1354,7 @@ class ManeTranscript:
             if not self._validate_index(
                 mane_c_ac, mane_c_pos_change, coding_start_site
             ):
-                logger.warning(
+                _logger.warning(
                     "%s are not valid positions on %s with coding start site %s",
                     mane_c_pos_change,
                     mane_c_ac,