cool-seq-tool 0.14.2__tar.gz → 0.14.4__tar.gz

{cool_seq_tool-0.14.2 → cool_seq_tool-0.14.4}/.gitignore

@@ -135,3 +135,6 @@ docs/source/reference/api
 
 # Files created by doctests
 tpm3.fasta
+
+# VSCode
+.vscode

{cool_seq_tool-0.14.2 → cool_seq_tool-0.14.4}/PKG-INFO

@@ -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 → cool_seq_tool-0.14.4}/docs/source/install.rst

@@ -6,7 +6,7 @@ Installation
 Prerequisites
 -------------
 
-* Python 3.10+
+* Python 3.11+
 * A UNIX-like environment (e.g. MacOS, WSL, Ubuntu)
 * A recent version of PostgreSQL (ideally at least 11+)
 

{cool_seq_tool-0.14.2 → cool_seq_tool-0.14.4}/pyproject.toml

@@ -16,11 +16,11 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Bio-Informatics",
     "License :: OSI Approved :: MIT License",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
 ]
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 description = "Common Operation on Lots of Sequences Tool"
 license = {file = "LICENSE"}
 dependencies = [

{cool_seq_tool-0.14.2 → cool_seq_tool-0.14.4}/src/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-0.14.2 → cool_seq_tool-0.14.4}/src/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-0.14.2 → cool_seq_tool-0.14.4}/src/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-0.14.2 → cool_seq_tool-0.14.4}/src/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-0.14.2 → cool_seq_tool-0.14.4}/src/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-0.14.2 → cool_seq_tool-0.14.4}/src/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-0.14.2 → cool_seq_tool-0.14.4}/src/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 → cool_seq_tool-0.14.4}/src/cool_seq_tool.egg-info/PKG-INFO

@@ -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 → cool_seq_tool-0.14.4}/tests/mappers/test_exon_genomic_coords.py

@@ -184,6 +184,7 @@ def tpm3_exon1():
                 },
                 "end": 154192135,
             },
+            "is_exonic": True,
         },
     }
     return GenomicTxSeg(**params)
@@ -208,6 +209,7 @@ def tpm3_exon8():
                 },
                 "start": 154170399,
             },
+            "is_exonic": True,
         },
     }
     return GenomicTxSeg(**params)
@@ -293,6 +295,7 @@ def mane_braf():
                 },
                 "end": 140801559,
             },
+            "is_exonic": True,
         },
         "seg_end": {
             "exon_ord": 14,
@@ -305,6 +308,7 @@ def mane_braf():
                 },
                 "start": 140753336,
             },
+            "is_exonic": True,
         },
     }
     return GenomicTxSegService(**params)
@@ -438,6 +442,7 @@ def zbtb10_exon3_end():
                 },
                 "end": 80514010,
             },
+            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -462,6 +467,7 @@ def zbtb10_exon5_start():
                 },
                 "start": 80518580,
             },
+            "is_exonic": False,
         },
         "seg_end": None,
     }
@@ -488,6 +494,7 @@ def tpm3_exon6_end():
                 },
                 "start": 154171410,
             },
+            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -512,6 +519,7 @@ def tpm3_exon5_start():
                 },
                 "end": 154173080,
             },
+            "is_exonic": False,
         },
         "seg_end": None,
     }
@@ -538,6 +546,7 @@ def gusbp3_exon2_end():
                 },
                 "start": 69680764,
             },
+            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -562,6 +571,7 @@ def eln_grch38_intronic():
                 },
                 "start": 74028173,
             },
+            "is_exonic": True,
         },
         "seg_end": {
             "exon_ord": 7,
@@ -574,6 +584,7 @@ def eln_grch38_intronic():
                 },
                 "end": 74043599,
             },
+            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -598,6 +609,7 @@ def gusbp3_exon5_start():
                 },
                 "end": 69645878,
             },
+            "is_exonic": False,
         },
         "seg_end": None,
     }
@@ -648,6 +660,7 @@ def genomic_tx_seg_service_checks(actual, expected=None, is_valid=True):
                 assert (
                     actual_seg.genomic_location.end == expected_seg.genomic_location.end
                 )
+                assert actual_seg.is_exonic == expected_seg.is_exonic
 
         assert actual.errors == expected.errors
     else:
@@ -715,6 +728,7 @@ def genomic_tx_seg_checks(actual, expected=None, is_valid=True):
                 actual_seg.genomic_location.start == expected_seg.genomic_location.start
             )
             assert actual_seg.genomic_location.end == expected_seg.genomic_location.end
+            assert actual_seg.is_exonic == expected_seg.is_exonic
 
         assert actual.errors == expected.errors
     else: