cool-seq-tool 0.13.1__py3-none-any.whl → 0.14.1__py3-none-any.whl

cool_seq_tool/handlers/seqrepo_access.py

@@ -75,9 +75,7 @@ class SeqRepoAccess(SeqRepoDataProxy):
                     f"Start inter-residue coordinate ({start}) is out of index on {ac}"
                 )
             elif error.startswith("stop out of range"):
-                msg = (
-                    f"End inter-residue coordinate ({end}) is out of " f"index on {ac}"
-                )
+                msg = f"End inter-residue coordinate ({end}) is out of index on {ac}"
             else:
                 msg = f"{e}"
             _logger.warning(msg)

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
 
@@ -765,7 +776,7 @@ class ExonGenomicCoordsMapper:
             GRCh38 by default. Will attempt to liftover if starting assembly is GRCh37
         :return: Data for a transcript segment boundary (inter-residue coordinates)
         """
-        params = {key: None for key in GenomicTxSeg.model_fields}
+        params = dict.fromkeys(GenomicTxSeg.model_fields)
 
         # Validate inputs exist in UTA
         if gene:
@@ -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)

cool_seq_tool/mappers/mane_transcript.py

@@ -268,7 +268,7 @@ class ManeTranscript:
         query = f"""
             SELECT alt_ac
             FROM {self.uta_db.schema}.genomic
-            WHERE alt_ac LIKE '{genomic_tx_data.alt_ac.split('.')[0]}%'
+            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)

cool_seq_tool/sources/uta_database.py

@@ -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 = [
@@ -325,13 +325,13 @@ class UtaDatabase:
         cds_start_end = await self.execute_query(query)
         if cds_start_end:
             cds_start_end = cds_start_end[0]
-            if cds_start_end[0] is not None and cds_start_end[1] is not None:  # noqa: RET503
+            if cds_start_end[0] is not None and cds_start_end[1] is not None:
                 return cds_start_end[0], cds_start_end[1]
         else:
             _logger.warning(
                 "Unable to get coding start/end site for accession: %s", tx_ac
             )
-            return None
+        return None
 
     async def get_newest_assembly_ac(self, ac: str) -> list[str]:
         """Find accession associated to latest genomic assembly
@@ -352,7 +352,7 @@ class UtaDatabase:
         query = f"""
             SELECT ac
             FROM {self.schema}._seq_anno_most_recent
-            WHERE ac LIKE '{ac.split('.')[0]}%'
+            WHERE ac LIKE '{ac.split(".")[0]}%'
             AND ((descr IS NULL) OR (descr = ''))
             {order_by_cond}
             """  # noqa: S608
@@ -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)

{cool_seq_tool-0.13.1.dist-info → cool_seq_tool-0.14.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.13.1
+Version: 0.14.1
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -51,16 +51,16 @@ Requires-Dist: agct>=0.1.0-dev1
 Requires-Dist: polars~=1.0
 Requires-Dist: hgvs
 Requires-Dist: biocommons.seqrepo
-Requires-Dist: pydantic==2.*
-Requires-Dist: ga4gh.vrs~=2.0.0a10
+Requires-Dist: pydantic<3.0,>=2.0
+Requires-Dist: ga4gh.vrs<3.0,>=2.1.3
 Requires-Dist: wags-tails~=0.3.2
 Requires-Dist: bioutils
 Provides-Extra: dev
-Requires-Dist: pre-commit>=4.0.1; extra == "dev"
+Requires-Dist: pre-commit>=4.2.0; extra == "dev"
 Requires-Dist: ipython; extra == "dev"
 Requires-Dist: ipykernel; extra == "dev"
 Requires-Dist: psycopg2-binary; extra == "dev"
-Requires-Dist: ruff==0.8.6; extra == "dev"
+Requires-Dist: ruff==0.12.1; extra == "dev"
 Provides-Extra: tests
 Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"

{cool_seq_tool-0.13.1.dist-info → cool_seq_tool-0.14.1.dist-info}/RECORD

@@ -3,12 +3,12 @@ cool_seq_tool/app.py,sha256=vyqlQRffC8sWZXMm-f_f-8WuTTWo3oRNfPUa_qdPV2M,4944
 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/handlers/seqrepo_access.py,sha256=lRzPc8V0eZJTlefbHuVKeZTEC8-KcyPzpqX7vx3amu8,9118
 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=MPp1cMfaTYZRJ-T9cP8SvICJbTlTCL5Yze3J1VT-oQQ,43790
+cool_seq_tool/mappers/exon_genomic_coords.py,sha256=t36NhWo2Rl84dgZY6qO7XFmGpfisjAqC-1ZOTRZxWvg,44757
 cool_seq_tool/mappers/liftover.py,sha256=lltx9zxfkrb5PHtJlKp3a39JCwPP4e0Zft-mQc1jXL8,3367
-cool_seq_tool/mappers/mane_transcript.py,sha256=C9eKEj8qhVg878oUhBKPYAZS7gpLM5aaQ0HhSkUg-2g,54365
+cool_seq_tool/mappers/mane_transcript.py,sha256=2cAYi0Y_gGdPI40weH9Ud1uVBCTKuwMT0M7KFUyjzU0,54365
 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=9LYSO2mOzVmoSQwllzq1mGChjtDA6j3I0S372N89clA,5683
@@ -16,9 +16,9 @@ cool_seq_tool/resources/transcript_mapping.tsv,sha256=AO3luYQAbFiCoRgiiPXotakb5p
 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=UHFLeiuk8H29CF1tNjE8T22-QaPs_fDUaqQO6Hu18yg,36175
-cool_seq_tool-0.13.1.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
-cool_seq_tool-0.13.1.dist-info/METADATA,sha256=ZhMjXeb_uT0a9hITKtjhUzVDJtlCJKLLPpOf2Cg8GpI,6579
-cool_seq_tool-0.13.1.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
-cool_seq_tool-0.13.1.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
-cool_seq_tool-0.13.1.dist-info/RECORD,,
+cool_seq_tool/sources/uta_database.py,sha256=zzRzmYuybqzEg7zeuQjhK46SPK5GfbiWWNRGNJju8AI,36197
+cool_seq_tool-0.14.1.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
+cool_seq_tool-0.14.1.dist-info/METADATA,sha256=TZHF8lDyidXRdGWUoBWfYAToUdQ7H6yO-gkpUhBdOe4,6587
+cool_seq_tool-0.14.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cool_seq_tool-0.14.1.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
+cool_seq_tool-0.14.1.dist-info/RECORD,,

{cool_seq_tool-0.13.1.dist-info → cool_seq_tool-0.14.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (79.0.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any