cool-seq-tool 0.13.0__py3-none-any.whl → 0.14.0__py3-none-any.whl

cool_seq_tool/mappers/__init__.py

@@ -6,4 +6,4 @@ from .mane_transcript import ManeTranscript
 from .exon_genomic_coords import ExonGenomicCoordsMapper
 
 
-__all__ = ["AlignmentMapper", "LiftOver", "ManeTranscript", "ExonGenomicCoordsMapper"]
+__all__ = ["AlignmentMapper", "ExonGenomicCoordsMapper", "LiftOver", "ManeTranscript"]

cool_seq_tool/mappers/exon_genomic_coords.py

@@ -93,6 +93,9 @@ class GenomicTxSeg(BaseModelForbidExtra):
     )
     genomic_ac: StrictStr | None = Field(None, description="RefSeq genomic accession.")
     tx_ac: StrictStr | None = Field(None, description="RefSeq transcript accession.")
+    strand: Strand | None = Field(
+        None, description="The strand that the transcript accession exists on."
+    )
     errors: list[StrictStr] = Field([], description="Error messages.")
 
     @model_validator(mode="before")
@@ -121,6 +124,7 @@ class GenomicTxSeg(BaseModelForbidExtra):
                 "gene": "TPM3",
                 "genomic_ac": "NC_000001.11",
                 "tx_ac": "NM_152263.3",
+                "strand": -1,
                 "seg": {
                     "exon_ord": 0,
                     "offset": 0,
@@ -147,6 +151,9 @@ class GenomicTxSegService(BaseModelForbidExtra):
     )
     genomic_ac: StrictStr | None = Field(None, description="RefSeq genomic accession.")
     tx_ac: StrictStr | None = Field(None, description="RefSeq transcript accession.")
+    strand: Strand | None = Field(
+        None, description="The strand that the transcript exists on."
+    )
     seg_start: TxSegment | None = Field(None, description="Start transcript segment.")
     seg_end: TxSegment | None = Field(None, description="End transcript segment.")
     errors: list[StrictStr] = Field([], description="Error messages.")
@@ -183,6 +190,7 @@ class GenomicTxSegService(BaseModelForbidExtra):
                 "gene": "TPM3",
                 "genomic_ac": "NC_000001.11",
                 "tx_ac": "NM_152263.3",
+                "strand": -1,
                 "seg_start": {
                     "exon_ord": 0,
                     "offset": 0,
@@ -400,6 +408,7 @@ class ExonGenomicCoordsMapper:
             gene=gene,
             genomic_ac=genomic_ac,
             tx_ac=transcript,
+            strand=strand,
             seg_start=seg_start,
             seg_end=seg_end,
         )
@@ -490,6 +499,7 @@ class ExonGenomicCoordsMapper:
             params["gene"] = start_tx_seg_data.gene
             params["genomic_ac"] = start_tx_seg_data.genomic_ac
             params["tx_ac"] = start_tx_seg_data.tx_ac
+            params["strand"] = start_tx_seg_data.strand
             params["seg_start"] = start_tx_seg_data.seg
         else:
             start_tx_seg_data = None
@@ -524,6 +534,7 @@ class ExonGenomicCoordsMapper:
                 params["gene"] = end_tx_seg_data.gene
                 params["genomic_ac"] = end_tx_seg_data.genomic_ac
                 params["tx_ac"] = end_tx_seg_data.tx_ac
+                params["strand"] = end_tx_seg_data.strand
 
             params["seg_end"] = end_tx_seg_data.seg
 
@@ -865,16 +876,21 @@ 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 between the first and last exon for the selected transcript
+        # Validate that the breakpoint occurs within 150 bp of the first and last exon for the selected transcript.
+        # A breakpoint beyond this range is likely erroneous.
         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 {transcript}"
-                ]
+            msg = (
+                f"{genomic_pos} on {genomic_ac} occurs more than 150 bp outside the "
+                f"exon boundaries of the {transcript} transcript, indicating this may not "
+                f"be a chimeric transcript junction and is unlikely to represent a "
+                f"contiguous coding sequence. Confirm that the genomic position "
+                f"{genomic_pos} is being used to represent transcript junction and not "
+                f"DNA breakpoint."
             )
+            _logger.warning(msg)
 
         # Check if breakpoint occurs on an exon.
         # If not, determine the adjacent exon given the selected transcript
@@ -913,6 +929,7 @@ class ExonGenomicCoordsMapper:
             gene=gene,
             genomic_ac=genomic_ac,
             tx_ac=transcript,
+            strand=strand,
             seg=TxSegment(
                 exon_ord=exon_num,
                 offset=offset,
@@ -955,8 +972,9 @@ class ExonGenomicCoordsMapper:
         :param pos: Genomic position on ``genomic_ac``
         :param genomic_ac: RefSeq genomic accession, e.g. ``"NC_000007.14"``
         :param transcript: A transcript accession
-        :return: ``True`` if the coordinate falls within the first and last exon
-            for the transcript, ``False`` if not
+        :return: ``True`` if the coordinate falls within 150bp of the first and last exon
+            for the transcript, ``False`` if not. Breakpoints past this threshold
+            are likely erroneous.
         """
         query = f"""
             WITH tx_boundaries AS (
@@ -968,7 +986,7 @@ class ExonGenomicCoordsMapper:
                 AND alt_ac = '{genomic_ac}'
             )
             SELECT * FROM tx_boundaries
-            WHERE {pos} between tx_boundaries.min_start and tx_boundaries.max_end
+            WHERE {pos} between (tx_boundaries.min_start - 150) and (tx_boundaries.max_end + 150)
             """  # noqa: S608
         results = await self.uta_db.execute_query(query)
         return bool(results)
@@ -1022,11 +1040,8 @@ class ExonGenomicCoordsMapper:
         :return ``True`` if alt_start_i should be used, ``False`` if alt_end_i should
         be used
         """
-        return (
-            is_seg_start
-            and strand == Strand.POSITIVE
-            or not is_seg_start
-            and strand == Strand.NEGATIVE
+        return (is_seg_start and strand == Strand.POSITIVE) or (
+            not is_seg_start and strand == Strand.NEGATIVE
         )
 
     @staticmethod

cool_seq_tool/resources/status.py

@@ -88,11 +88,11 @@ async def check_status(
         try:
             get_data_file(r)
         except FileNotFoundError:
-            _logger.error(
+            _logger.exception(
                 "%s does not exist at configured location %s", name_lower, declared_path
             )
         except ValueError:
-            _logger.error(
+            _logger.exception(
                 "%s configured at %s is not a valid file.", name_lower, declared_path
             )
         except Exception as e:
@@ -107,8 +107,8 @@ async def check_status(
             chain_file_37_to_38=chain_file_37_to_38,
             chain_file_38_to_37=chain_file_38_to_37,
         )
-    except (FileNotFoundError, ChainfileError) as e:
-        _logger.error("agct converter setup failed: %s", e)
+    except (FileNotFoundError, ChainfileError):
+        _logger.exception("agct converter setup failed")
     except Exception as e:
         _logger.critical("Encountered unexpected error setting up agct: %s", e)
     else:
@@ -116,10 +116,8 @@ async def check_status(
 
     try:
         await UtaDatabase.create(db_url)
-    except (OSError, InvalidCatalogNameError, UndefinedTableError) as e:
-        _logger.error(
-            "Encountered error instantiating UTA at URI %s: %s", UTA_DB_URL, e
-        )
+    except (OSError, InvalidCatalogNameError, UndefinedTableError):
+        _logger.exception("Encountered error instantiating UTA at URI %s", UTA_DB_URL)
     except Exception as e:
         _logger.critical(
             "Encountered unexpected error instantiating UTA from URI %s: %s",
@@ -134,10 +132,10 @@ async def check_status(
             sr = SeqRepo(root_dir=SEQREPO_ROOT_DIR)
         sra = SeqRepoAccess(sr)
         sra.sr["NC_000001.11"][1000:1001]
-    except OSError as e:
-        _logger.error("Encountered error while instantiating SeqRepo: %s", e)
+    except OSError:
+        _logger.exception("Encountered error while instantiating SeqRepo")
     except KeyError:
-        _logger.error("SeqRepo data fetch test failed -- is it populated?")
+        _logger.exception("SeqRepo data fetch test failed -- is it populated?")
     except Exception as e:
         _logger.critical("Encountered unexpected error setting up SeqRepo: %s", e)
     else:

cool_seq_tool/sources/uta_database.py

@@ -162,11 +162,11 @@ class UtaDatabase:
                     database=self.args.database,
                 )
             except InterfaceError as e:
-                _logger.error(
-                    "While creating connection pool, encountered exception %s", e
+                _logger.exception(
+                    "While creating connection pool, encountered exception"
                 )
                 msg = "Could not create connection pool"
-                raise Exception(msg) from e
+                raise Exception(msg) from e  # noqa: TRY002
 
     @classmethod
     async def create(
@@ -221,7 +221,7 @@ class UtaDatabase:
                WHERE table_schema = '{self.schema}'
                AND table_name = 'genomic'
             );
-            """  # noqa: S608
+            """
         genomic_table_exists = await self.execute_query(check_table_exists)
         genomic_table_exists = genomic_table_exists[0].get("exists")
         if genomic_table_exists is None:
@@ -250,7 +250,7 @@ class UtaDatabase:
                         LEFT JOIN {self.schema}.exon_aln ea ON
                             (((te.exon_id = ea.tx_exon_id) AND
                             (ae.exon_id = ea.alt_exon_id))));
-                """  # noqa: S608
+                """
             await self.execute_query(create_genomic_table)
 
             indexes = [
@@ -499,7 +499,7 @@ class UtaDatabase:
             AND {start_pos} BETWEEN {pos_q}
             AND {end_pos} BETWEEN {pos_q}
             {order_by_cond}
-            """  # noqa: S608
+            """
         result = await self.execute_query(query)
         if not result:
             _logger.warning("Unable to find transcript alignment for query: %s", query)
@@ -852,8 +852,8 @@ class UtaDatabase:
 
         try:
             assembly = Assembly(assembly)
-        except ValueError as e:
-            _logger.error(e)
+        except ValueError:
+            _logger.exception("Unable to parse %s as an Assembly", assembly)
             return None
 
         return chromosome, assembly
@@ -924,11 +924,11 @@ class UtaDatabase:
 
         try:
             get_secret_value_response = client.get_secret_value(SecretId=secret_name)
-        except ClientError as e:
+        except ClientError:
             # For a list of exceptions thrown, see
             # https://docs.aws.amazon.com/secretsmanager/latest/apireference/API_GetSecretValue.html
-            _logger.error(e)
-            raise e
+            _logger.exception("Encountered AWS client error fetching UTA DB secret")
+            raise
         else:
             return get_secret_value_response["SecretString"]
 

{cool_seq_tool-0.13.0.dist-info → cool_seq_tool-0.14.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.13.0
+Version: 0.14.0
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -53,14 +53,14 @@ Requires-Dist: hgvs
 Requires-Dist: biocommons.seqrepo
 Requires-Dist: pydantic==2.*
 Requires-Dist: ga4gh.vrs~=2.0.0a10
-Requires-Dist: wags-tails~=0.2.2
+Requires-Dist: wags-tails~=0.3.2
 Requires-Dist: bioutils
 Provides-Extra: dev
-Requires-Dist: pre-commit>=3.7.1; extra == "dev"
+Requires-Dist: pre-commit>=4.0.1; extra == "dev"
 Requires-Dist: ipython; extra == "dev"
 Requires-Dist: ipykernel; extra == "dev"
 Requires-Dist: psycopg2-binary; extra == "dev"
-Requires-Dist: ruff==0.5.0; extra == "dev"
+Requires-Dist: ruff==0.8.6; extra == "dev"
 Provides-Extra: tests
 Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"
@@ -74,6 +74,7 @@ Requires-Dist: sphinx-copybutton==0.5.2; extra == "docs"
 Requires-Dist: sphinxext-opengraph==0.8.2; extra == "docs"
 Requires-Dist: furo==2023.3.27; extra == "docs"
 Requires-Dist: sphinx-github-changelog==1.2.1; extra == "docs"
+Dynamic: license-file
 
 <h1 align="center">
 Cool-Seq-Tool

{cool_seq_tool-0.13.0.dist-info → cool_seq_tool-0.14.0.dist-info}/RECORD

@@ -4,21 +4,21 @@ 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/__init__.py,sha256=4_YNwNyw_QrlhRNu1nly8Dezv81XjCIiNa7crVXEh38,305
 cool_seq_tool/mappers/alignment.py,sha256=nV6PS3mhkQ2MD1GcpNBujBOqd3AKxYSYA9BCusFOa1o,9636
-cool_seq_tool/mappers/exon_genomic_coords.py,sha256=ORYjBVaX1HO6ln0gRJyRKxUCjZrBDi4JfYQEYebxIAc,43824
+cool_seq_tool/mappers/exon_genomic_coords.py,sha256=uPBlI9K_IUV3xN9unnCwd6bPmqpfIWB5I-dksN_JZSw,44765
 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
 cool_seq_tool/resources/data_files.py,sha256=3lhu28tzlSoTs4vHZNu-hhoAWRrPGuZj_oIjqk2sYQM,3837
-cool_seq_tool/resources/status.py,sha256=L0KM-VG3N4Yuaqh3AKZd_2KPDLR0Y7rvW_OD6x8mF7A,5717
+cool_seq_tool/resources/status.py,sha256=9LYSO2mOzVmoSQwllzq1mGChjtDA6j3I0S372N89clA,5683
 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=V8cuog35-5BtOODu_vreDlBaP_PgBv8r7pYeTXmGsio,36111
-cool_seq_tool-0.13.0.dist-info/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
-cool_seq_tool-0.13.0.dist-info/METADATA,sha256=JiQMP8y83nsS7tx2oJ7nWv34gY_2iW8TR0NsXPDrn_8,6557
-cool_seq_tool-0.13.0.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-cool_seq_tool-0.13.0.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
-cool_seq_tool-0.13.0.dist-info/RECORD,,
+cool_seq_tool/sources/uta_database.py,sha256=UHFLeiuk8H29CF1tNjE8T22-QaPs_fDUaqQO6Hu18yg,36175
+cool_seq_tool-0.14.0.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
+cool_seq_tool-0.14.0.dist-info/METADATA,sha256=1BpHtcCsaCUBvpmp1Qe1TVoZFHVvUir685EsH925PJ0,6579
+cool_seq_tool-0.14.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cool_seq_tool-0.14.0.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
+cool_seq_tool-0.14.0.dist-info/RECORD,,

{cool_seq_tool-0.13.0.dist-info → cool_seq_tool-0.14.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.0.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any