cool-seq-tool 0.14.2__py3-none-any.whl → 0.14.4__py3-none-any.whl

cool_seq_tool/mappers/alignment.py

@@ -106,7 +106,7 @@ class AlignmentMapper:
         c_end_pos: int,
         cds_start: int | None = None,
         coordinate_type: CoordinateType = CoordinateType.RESIDUE,
-        target_genome_assembly: bool = Assembly.GRCH38,
+        target_genome_assembly: Assembly = Assembly.GRCH38,
     ) -> tuple[dict | None, str | None]:
         """Translate cDNA representation to genomic representation
 

cool_seq_tool/mappers/exon_genomic_coords.py

@@ -65,6 +65,27 @@ class TxSegment(BaseModelForbidExtra):
     genomic_location: SequenceLocation = Field(
         ..., description="The genomic position of a transcript segment."
     )
+    is_exonic: bool = Field(
+        default=True, description="If the position occurs on an exon"
+    )
+
+    @model_validator(mode="before")
+    def check_seg_pos(cls, values: dict) -> dict:  # noqa: N805
+        """Ensure that only one of `start` or `end` is set in the
+        genomic_location field
+
+        :param values: The values in the TxSegment class
+        :raises ValueError: If `start` and `end` are both set in
+            `genomic_location`
+        :return: Values in model
+        """
+        loc = values.get("genomic_location")
+        start = getattr(loc, "start", None)
+        end = getattr(loc, "end", None)
+        if start and end:
+            err_msg = "Only one of `start` or `end` may be set as this describes the start or end of a transcript segment"
+            raise ValueError(err_msg)
+        return values
 
     model_config = ConfigDict(
         json_schema_extra={
@@ -79,6 +100,7 @@ class TxSegment(BaseModelForbidExtra):
                     },
                     "end": 154192135,
                 },
+                "is_exonic": True,
             }
         }
     )
@@ -136,6 +158,7 @@ class GenomicTxSeg(BaseModelForbidExtra):
                         },
                         "end": 154192135,
                     },
+                    "is_exonic": True,
                 },
                 "errors": [],
             }
@@ -202,6 +225,7 @@ class GenomicTxSegService(BaseModelForbidExtra):
                         },
                         "end": 154192135,
                     },
+                    "is_exonic": True,
                 },
                 "seg_end": {
                     "exon_ord": 7,
@@ -214,6 +238,7 @@ class GenomicTxSegService(BaseModelForbidExtra):
                         },
                         "start": 154170399,
                     },
+                    "is_exonic": True,
                 },
             }
         }
@@ -895,6 +920,7 @@ class ExonGenomicCoordsMapper:
         # Check if breakpoint occurs on an exon.
         # If not, determine the adjacent exon given the selected transcript
         if not self._is_exonic_breakpoint(genomic_pos, tx_exons):
+            is_exonic = False
             exon_num = self._get_adjacent_exon(
                 tx_exons_genomic_coords=tx_exons,
                 strand=strand,
@@ -902,6 +928,7 @@ class ExonGenomicCoordsMapper:
                 end=genomic_pos if not is_seg_start else None,
             )
         else:
+            is_exonic = True
             exon_data = await self.uta_db.get_tx_exon_aln_v_data(
                 transcript,
                 genomic_pos,
@@ -934,6 +961,7 @@ class ExonGenomicCoordsMapper:
                 exon_ord=exon_num,
                 offset=offset,
                 genomic_location=genomic_location,
+                is_exonic=is_exonic,
             ),
         )
 

cool_seq_tool/mappers/feature_overlap.py

@@ -212,14 +212,15 @@ class FeatureOverlap:
 
             ga4gh_seq_id = ga4gh_aliases[0]
 
-        def _get_seq_loc(start_pos: int, stop_pos: int, refget_ac: str) -> dict:
-            """Get VRS Sequence Location represented as a dict
+        def _get_seq_loc(
+            start_pos: int, stop_pos: int, refget_ac: str
+        ) -> SequenceLocation:
+            """Get VRS Sequence Location
 
             :param start_pos: Start position
             :param stop_pos: Stop position
             :param refget_ac: Refget Accession (SQ.)
-            :return: VRS Sequence Location represented as dictionary with the ga4gh ID
-                included
+            :return: VRS Sequence Location
             """
             _sl = SequenceLocation(
                 sequenceReference=SequenceReference(
@@ -229,7 +230,7 @@ class FeatureOverlap:
                 end=stop_pos,
             )
             ga4gh_identify(_sl)
-            return _sl.model_dump(exclude_none=True)
+            return _sl
 
         resp = {}
         refget_ac = ga4gh_seq_id.split("ga4gh:")[-1]

cool_seq_tool/mappers/mane_transcript.py

@@ -55,7 +55,7 @@ class DataRepresentation(BaseModel):
     """Define object model for final output representation"""
 
     gene: str | None = None
-    refseq: str
+    refseq: str | None = None
     ensembl: str | None = None
     pos: tuple[int, int]
     strand: Strand
@@ -447,7 +447,7 @@ class ManeTranscript:
 
     async def _g_to_c(
         self,
-        g: dict,
+        g: GenomicTxMetadata,
         refseq_c_ac: str,
         status: TranscriptPriority,
         ensembl_c_ac: str | None = None,
@@ -590,16 +590,23 @@ class ManeTranscript:
         if mane_transcript:
             mane_start_pos = mane_transcript.pos[0]
             mane_end_pos = mane_transcript.pos[1]
-            if anno == AnnotationLayer.CDNA:
+            if anno == AnnotationLayer.CDNA and isinstance(
+                mane_transcript, CdnaRepresentation
+            ):
                 mane_cds = mane_transcript.coding_start_site
                 mane_start_pos += mane_cds
                 mane_end_pos += mane_cds
-            mane_ref, _ = self.seqrepo_access.get_reference_sequence(
-                mane_transcript.refseq,
-                start=mane_start_pos,
-                end=mane_end_pos if mane_start_pos != mane_end_pos else None,
-                coordinate_type=coordinate_type,
-            )
+
+            if mane_transcript.refseq:
+                mane_ref, _ = self.seqrepo_access.get_reference_sequence(
+                    mane_transcript.refseq,
+                    start=mane_start_pos,
+                    end=mane_end_pos if mane_start_pos != mane_end_pos else None,
+                    coordinate_type=coordinate_type,
+                )
+            else:
+                mane_ref = None
+
             if not mane_ref:
                 _logger.info("Unable to validate reference for MANE Transcript")
 
@@ -1330,7 +1337,7 @@ class ManeTranscript:
         gene: str | None = None,
         coordinate_type: CoordinateType = CoordinateType.RESIDUE,
         try_longest_compatible: bool = False,
-    ) -> dict | None:
+    ) -> ProteinAndCdnaRepresentation | None:
         """Given GRCh38 genomic representation, return protein representation.
 
         Will try MANE Select and then MANE Plus Clinical. If neither is found and

cool_seq_tool/resources/status.py

@@ -24,6 +24,7 @@ ResourceStatus = namedtuple(
         DataFile.TRANSCRIPT_MAPPINGS.lower(),
         DataFile.MANE_SUMMARY.lower(),
         DataFile.LRG_REFSEQGENE.lower(),
+        DataFile.MANE_REFSEQ_GENOMIC.lower(),
         "liftover",
     ),
 )
@@ -37,6 +38,7 @@ async def check_status(
     sr: SeqRepo | None = None,
     chain_file_37_to_38: str | None = None,
     chain_file_38_to_37: str | None = None,
+    mane_refseq_genomic_path: str | None = None,
 ) -> ResourceStatus:
     """Perform basic status checks on availability of required data resources.
 
@@ -62,6 +64,7 @@ async def check_status(
         is used for ``agct``. If this is not provided, will check to see if
         ``LIFTOVER_CHAIN_38_TO_37`` env var is set. If neither is provided, will allow
         ``agct`` to download a chain file from UCSC
+    :param mane_refseq_genomic_path: Optional path to MANE RefSeq Genomic GFF data
     :return: boolean description of availability of each resource, given current
         environment configurations
     """
@@ -69,19 +72,21 @@ async def check_status(
         DataFile.TRANSCRIPT_MAPPINGS.lower(): transcript_file_path,
         DataFile.LRG_REFSEQGENE.lower(): lrg_refseqgene_path,
         DataFile.MANE_SUMMARY.lower(): mane_data_path,
+        DataFile.MANE_REFSEQ_GENOMIC.lower(): mane_refseq_genomic_path,
     }
 
     status = {
         DataFile.TRANSCRIPT_MAPPINGS.lower(): False,
         DataFile.LRG_REFSEQGENE.lower(): False,
         DataFile.MANE_SUMMARY.lower(): False,
+        DataFile.MANE_REFSEQ_GENOMIC.lower(): False,
         "liftover": False,
         "uta": False,
         "seqrepo": False,
     }
     for r in list(DataFile):
         name_lower = r.lower()
-        declared_path = file_path_params[name_lower]
+        declared_path = file_path_params.get(name_lower)
         if declared_path and declared_path.exists() and declared_path.is_file():
             status[name_lower] = True
             continue

cool_seq_tool/schemas.py

@@ -14,7 +14,7 @@ from pydantic import (
 
 from cool_seq_tool import __version__
 
-_now = str(datetime.datetime.now(tz=datetime.timezone.utc))
+_now = str(datetime.datetime.now(tz=datetime.UTC))
 
 
 class AnnotationLayer(str, Enum):

cool_seq_tool/utils.py

@@ -47,7 +47,7 @@ def service_meta() -> ServiceMeta:
     """
     return ServiceMeta(
         version=__version__,
-        response_datetime=datetime.datetime.now(tz=datetime.timezone.utc),
+        response_datetime=datetime.datetime.now(tz=datetime.UTC),
     )
 
 

{cool_seq_tool-0.14.2.dist-info → cool_seq_tool-0.14.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.14.2
+Version: 0.14.4
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -38,10 +38,10 @@ Classifier: Intended Audience :: Developers
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.10
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: asyncpg

{cool_seq_tool-0.14.2.dist-info → cool_seq_tool-0.14.4.dist-info}/RECORD

@@ -1,25 +1,25 @@
 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=ueEq7cVKyGWVDvsV9JAzg7Cp2Nni3F9musCkWEtW26g,5365
-cool_seq_tool/utils.py,sha256=kesu7UnOplDzvNBg_G-_m1xMM22979nmsi4yWtweetU,2959
+cool_seq_tool/schemas.py,sha256=6c87iuA6v7BX7a8nkWEqFbJTksFysuuIeuYxkNCrAsI,5356
+cool_seq_tool/utils.py,sha256=jra2ZHS7HUqXqabSvyqd5imf6kkhYL8nQd20BWNLpb8,2950
 cool_seq_tool/handlers/__init__.py,sha256=KalQ46vX1MO4SJz2SlspKoIRy1n3c3Vp1t4Y2pIfqow,78
 cool_seq_tool/handlers/seqrepo_access.py,sha256=lRzPc8V0eZJTlefbHuVKeZTEC8-KcyPzpqX7vx3amu8,9118
 cool_seq_tool/mappers/__init__.py,sha256=tavpwkNogg_nF1J_kb6Q9jk7ezqdRz063v7BMZ4koLM,390
-cool_seq_tool/mappers/alignment.py,sha256=nV6PS3mhkQ2MD1GcpNBujBOqd3AKxYSYA9BCusFOa1o,9636
-cool_seq_tool/mappers/exon_genomic_coords.py,sha256=t36NhWo2Rl84dgZY6qO7XFmGpfisjAqC-1ZOTRZxWvg,44757
-cool_seq_tool/mappers/feature_overlap.py,sha256=_MMEuZh48dHDPKliQV2C14bwziScE46uWl9utnAHOZo,9845
+cool_seq_tool/mappers/alignment.py,sha256=kWgYssM8YL-Z13H9GdpL77P7simNcbxltAs9YDXHE54,9640
+cool_seq_tool/mappers/exon_genomic_coords.py,sha256=fV4LyrpHPLRrx6AtV15g93q5XCH3i-y3Wj9tl-Cg8mM,45845
+cool_seq_tool/mappers/feature_overlap.py,sha256=X5UFClaH6ixRsO2fDLxqjywp-Z0bvNx4uzgBICy394U,9758
 cool_seq_tool/mappers/liftover.py,sha256=lltx9zxfkrb5PHtJlKp3a39JCwPP4e0Zft-mQc1jXL8,3367
-cool_seq_tool/mappers/mane_transcript.py,sha256=2cAYi0Y_gGdPI40weH9Ud1uVBCTKuwMT0M7KFUyjzU0,54365
+cool_seq_tool/mappers/mane_transcript.py,sha256=IluiLBxPQoY-CxkpqpjEBcMlHvrNLa34wdKdQxtKgDY,54613
 cool_seq_tool/resources/__init__.py,sha256=VwUC8YaucTS6SmRirToulZTF6CuvuLQRSxFfSfAovCc,77
 cool_seq_tool/resources/data_files.py,sha256=6d1M5WjeFHdTQpzxqjQ78auQRZvIBVqH8QNCrmRRDXw,4205
-cool_seq_tool/resources/status.py,sha256=9LYSO2mOzVmoSQwllzq1mGChjtDA6j3I0S372N89clA,5683
+cool_seq_tool/resources/status.py,sha256=5UKx5FIQuyIY7FU4kSinDIM4MhLpr9_MiQDDBNt9kRo,5990
 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=C5puIA1xuEzBaSvs8VtSxVb2OIDGUg5no8v6Ma2QSdw,6597
 cool_seq_tool/sources/transcript_mappings.py,sha256=903RKTMBO2rbKh6iTQ1BEWnY4C7saBFMPw2_4ATuudg,10054
 cool_seq_tool/sources/uta_database.py,sha256=zzRzmYuybqzEg7zeuQjhK46SPK5GfbiWWNRGNJju8AI,36197
-cool_seq_tool-0.14.2.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
-cool_seq_tool-0.14.2.dist-info/METADATA,sha256=qtjqeUzTDsOnTlil7dVW7Uzg50mQ_-Lu8sKwR95ExGs,6535
-cool_seq_tool-0.14.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cool_seq_tool-0.14.2.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
-cool_seq_tool-0.14.2.dist-info/RECORD,,
+cool_seq_tool-0.14.4.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
+cool_seq_tool-0.14.4.dist-info/METADATA,sha256=gPz48irXCwNUecTcgpKrdrHiBhi8R_Is55S2UYs9Qtk,6535
+cool_seq_tool-0.14.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cool_seq_tool-0.14.4.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
+cool_seq_tool-0.14.4.dist-info/RECORD,,