cool-seq-tool 0.14.4__tar.gz → 0.15.0__tar.gz

cool_seq_tool-0.15.0/.github/CODEOWNERS

@@ -0,0 +1 @@
+* @GenomicMedLab/cool-seq-tool-maintainers

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.14.4
+Version: 0.15.0
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -50,7 +50,7 @@ Requires-Dist: agct>=0.1.0-dev1
 Requires-Dist: polars~=1.0
 Requires-Dist: biocommons.seqrepo
 Requires-Dist: pydantic<3.0,>=2.0
-Requires-Dist: ga4gh.vrs<3.0,>=2.1.3
+Requires-Dist: ga4gh.vrs<3.0,>=2.1.4
 Requires-Dist: wags-tails~=0.4.0
 Requires-Dist: bioutils
 Provides-Extra: dev

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/pyproject.toml

@@ -30,7 +30,7 @@ dependencies = [
     "polars ~= 1.0",
     "biocommons.seqrepo",
     "pydantic >=2.0,<3.0",
-    "ga4gh.vrs >=2.1.3,<3.0",
+    "ga4gh.vrs >=2.1.4,<3.0",
     "wags-tails ~= 0.4.0",
     "bioutils",
 ]

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool/app.py

@@ -107,6 +107,7 @@ class CoolSeqTool:
         self.ex_g_coords_mapper = ExonGenomicCoordsMapper(
             self.seqrepo_access,
             self.uta_db,
+            self.mane_transcript,
             self.mane_transcript_mappings,
             self.liftover,
         )

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool/mappers/exon_genomic_coords.py

@@ -2,17 +2,21 @@
 
 import logging
 
+from ga4gh.core.models import Extension
 from ga4gh.vrs.models import SequenceLocation, SequenceReference
 from pydantic import ConfigDict, Field, StrictInt, StrictStr, model_validator
 
 from cool_seq_tool.handlers.seqrepo_access import SeqRepoAccess
 from cool_seq_tool.mappers.liftover import LiftOver
+from cool_seq_tool.mappers.mane_transcript import ManeTranscript
 from cool_seq_tool.schemas import (
+    AnnotationLayer,
     Assembly,
     BaseModelForbidExtra,
     CoordinateType,
     ServiceMeta,
     Strand,
+    TranscriptPriority,
 )
 from cool_seq_tool.sources.mane_transcript_mappings import ManeTranscriptMappings
 from cool_seq_tool.sources.uta_database import GenomicAlnData, UtaDatabase
@@ -65,9 +69,6 @@ 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
@@ -99,8 +100,8 @@ class TxSegment(BaseModelForbidExtra):
                         "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                     },
                     "end": 154192135,
+                    "extensions": [{"name": "is_exonic", "value": True}],
                 },
-                "is_exonic": True,
             }
         }
     )
@@ -115,6 +116,9 @@ class GenomicTxSeg(BaseModelForbidExtra):
     )
     genomic_ac: StrictStr | None = Field(None, description="RefSeq genomic accession.")
     tx_ac: StrictStr | None = Field(None, description="RefSeq transcript accession.")
+    tx_status: TranscriptPriority | None = Field(
+        None, description="Transcript priority for RefSeq transcript accession"
+    )
     strand: Strand | None = Field(
         None, description="The strand that the transcript accession exists on."
     )
@@ -146,6 +150,7 @@ class GenomicTxSeg(BaseModelForbidExtra):
                 "gene": "TPM3",
                 "genomic_ac": "NC_000001.11",
                 "tx_ac": "NM_152263.3",
+                "tx_status": "longest_compatible_remaining",
                 "strand": -1,
                 "seg": {
                     "exon_ord": 0,
@@ -157,8 +162,8 @@ class GenomicTxSeg(BaseModelForbidExtra):
                             "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                         },
                         "end": 154192135,
+                        "extensions": [{"name": "is_exonic", "value": True}],
                     },
-                    "is_exonic": True,
                 },
                 "errors": [],
             }
@@ -174,6 +179,9 @@ class GenomicTxSegService(BaseModelForbidExtra):
     )
     genomic_ac: StrictStr | None = Field(None, description="RefSeq genomic accession.")
     tx_ac: StrictStr | None = Field(None, description="RefSeq transcript accession.")
+    tx_status: TranscriptPriority | None = Field(
+        None, description="Transcript priority for RefSeq transcript accession"
+    )
     strand: Strand | None = Field(
         None, description="The strand that the transcript exists on."
     )
@@ -213,6 +221,7 @@ class GenomicTxSegService(BaseModelForbidExtra):
                 "gene": "TPM3",
                 "genomic_ac": "NC_000001.11",
                 "tx_ac": "NM_152263.3",
+                "tx_status": "longest_compatible_remaining",
                 "strand": -1,
                 "seg_start": {
                     "exon_ord": 0,
@@ -224,8 +233,8 @@ class GenomicTxSegService(BaseModelForbidExtra):
                             "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                         },
                         "end": 154192135,
+                        "extensions": [{"name": "is_exonic", "value": True}],
                     },
-                    "is_exonic": True,
                 },
                 "seg_end": {
                     "exon_ord": 7,
@@ -237,8 +246,8 @@ class GenomicTxSegService(BaseModelForbidExtra):
                             "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                         },
                         "start": 154170399,
+                        "extensions": [{"name": "is_exonic", "value": True}],
                     },
-                    "is_exonic": True,
                 },
             }
         }
@@ -266,6 +275,7 @@ class ExonGenomicCoordsMapper:
         self,
         seqrepo_access: SeqRepoAccess,
         uta_db: UtaDatabase,
+        mane_transcript: ManeTranscript,
         mane_transcript_mappings: ManeTranscriptMappings,
         liftover: LiftOver,
     ) -> None:
@@ -290,11 +300,13 @@ class ExonGenomicCoordsMapper:
 
         :param seqrepo_access: SeqRepo instance to give access to query SeqRepo database
         :param uta_db: UtaDatabase instance to give access to query UTA database
+        :param mane_transcript: ManeTranscript instance to give access to ManeTranscript class
         :param mane_transcript_mappings: Instance to provide access to ManeTranscriptMappings class
         :param liftover: Instance to provide mapping between human genome assemblies
         """
         self.seqrepo_access = seqrepo_access
         self.uta_db = uta_db
+        self.mane_transcript = mane_transcript
         self.mane_transcript_mappings = mane_transcript_mappings
         self.liftover = liftover
 
@@ -433,6 +445,7 @@ class ExonGenomicCoordsMapper:
             gene=gene,
             genomic_ac=genomic_ac,
             tx_ac=transcript,
+            tx_status=self.mane_transcript_mappings.get_transcript_status(transcript),
             strand=strand,
             seg_start=seg_start,
             seg_end=seg_end,
@@ -524,6 +537,7 @@ 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["tx_status"] = start_tx_seg_data.tx_status
             params["strand"] = start_tx_seg_data.strand
             params["seg_start"] = start_tx_seg_data.seg
         else:
@@ -559,6 +573,7 @@ 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["tx_status"] = end_tx_seg_data.tx_status
                 params["strand"] = end_tx_seg_data.strand
 
             params["seg_end"] = end_tx_seg_data.seg
@@ -730,7 +745,12 @@ class ExonGenomicCoordsMapper:
         ), None
 
     def _get_vrs_seq_loc(
-        self, genomic_ac: str, genomic_pos: int, is_seg_start: bool, strand: Strand
+        self,
+        genomic_ac: str,
+        genomic_pos: int,
+        is_seg_start: bool,
+        strand: Strand,
+        is_exonic: bool = True,
     ) -> tuple[SequenceLocation | None, str | None]:
         """Create VRS Sequence Location for genomic position where transcript segment
         occurs
@@ -740,6 +760,8 @@ class ExonGenomicCoordsMapper:
         :param is_seg_start: ``True`` if ``genomic_pos`` is where the transcript segment
             starts. ``False`` if ``genomic_pos`` is where the transcript segment ends.
         :param strand: Strand
+        :param is_exonic: A boolean indicating if the genomic breakpoint occurs
+            on an exon. By default, this is set to ``True``.
         :return: Tuple containing VRS location (if successful) and error message (if
             unable to get GA4GH identifier for ``genomic_ac``).
         """
@@ -759,6 +781,7 @@ class ExonGenomicCoordsMapper:
             ),
             start=genomic_pos if use_start else None,
             end=genomic_pos if not use_start else None,
+            extensions=[Extension(name="is_exonic", value=is_exonic)],
         ), None
 
     async def _genomic_to_tx_segment(
@@ -852,14 +875,18 @@ class ExonGenomicCoordsMapper:
             if mane_transcripts:
                 transcript = mane_transcripts[0]["RefSeq_nuc"]
             else:
-                # Attempt to find a coding transcript if a MANE transcript
+                # Attempt to find longest compatible transcript if a MANE transcript
                 # cannot be found
-                results = await self.uta_db.get_transcripts(
-                    gene=gene, alt_ac=genomic_ac
+                results = await self.mane_transcript.get_longest_compatible_transcript(
+                    start_pos=genomic_pos,
+                    end_pos=genomic_pos,
+                    gene=gene,
+                    alt_ac=genomic_ac,
+                    start_annotation_layer=AnnotationLayer.GENOMIC,
                 )
 
-                if not results.is_empty():
-                    transcript = results[0]["tx_ac"][0]
+                if results:
+                    transcript = results.refseq
                 else:
                     # Run if gene is for a noncoding transcript
                     query = f"""
@@ -947,7 +974,7 @@ class ExonGenomicCoordsMapper:
         )
 
         genomic_location, err_msg = self._get_vrs_seq_loc(
-            genomic_ac, genomic_pos, is_seg_start, strand
+            genomic_ac, genomic_pos, is_seg_start, strand, is_exonic
         )
         if err_msg:
             return GenomicTxSeg(errors=[err_msg])
@@ -956,12 +983,12 @@ class ExonGenomicCoordsMapper:
             gene=gene,
             genomic_ac=genomic_ac,
             tx_ac=transcript,
+            tx_status=self.mane_transcript_mappings.get_transcript_status(transcript),
             strand=strand,
             seg=TxSegment(
                 exon_ord=exon_num,
                 offset=offset,
                 genomic_location=genomic_location,
-                is_exonic=is_exonic,
             ),
         )
 

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool/resources/status.py

@@ -3,6 +3,7 @@
 import logging
 from collections import namedtuple
 from pathlib import Path
+from urllib.parse import urlparse
 
 from agct._core import ChainfileError
 from asyncpg import InvalidCatalogNameError, UndefinedTableError
@@ -11,7 +12,7 @@ from biocommons.seqrepo import SeqRepo
 from cool_seq_tool.handlers.seqrepo_access import SEQREPO_ROOT_DIR, SeqRepoAccess
 from cool_seq_tool.mappers.liftover import LiftOver
 from cool_seq_tool.resources.data_files import DataFile, get_data_file
-from cool_seq_tool.sources.uta_database import UTA_DB_URL, UtaDatabase
+from cool_seq_tool.sources.uta_database import UTA_DB_URL, ParseResult, UtaDatabase
 
 _logger = logging.getLogger(__name__)
 
@@ -119,14 +120,20 @@ async def check_status(
     else:
         status["liftover"] = True
 
+    parsed_result = ParseResult(urlparse(db_url))
+    sanitized_url = parsed_result.sanitized_url
     try:
         await UtaDatabase.create(db_url)
+    except ValueError:
+        _logger.exception("Database URL is not valid")
     except (OSError, InvalidCatalogNameError, UndefinedTableError):
-        _logger.exception("Encountered error instantiating UTA at URI %s", UTA_DB_URL)
+        _logger.exception(
+            "Encountered error instantiating UTA at URI %s", sanitized_url
+        )
     except Exception as e:
         _logger.critical(
             "Encountered unexpected error instantiating UTA from URI %s: %s",
-            UTA_DB_URL,
+            sanitized_url,
             e,
         )
     else:

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool/sources/mane_transcript_mappings.py

@@ -8,7 +8,7 @@ from pathlib import Path
 import polars as pl
 
 from cool_seq_tool.resources.data_files import DataFile, get_data_file
-from cool_seq_tool.schemas import ManeGeneData
+from cool_seq_tool.schemas import ManeGeneData, TranscriptPriority
 
 _logger = logging.getLogger(__name__)
 
@@ -85,6 +85,22 @@ class ManeTranscriptMappings:
             return []
         return mane_rows.to_dicts()
 
+    def get_transcript_status(self, tx_ac: str) -> TranscriptPriority:
+        """Get MANE status for a transcript
+
+        :param tx_ac: A RefSeq transcript accession
+        :return: A TranscriptPriority object
+        """
+        mane_info = self.get_mane_from_transcripts([tx_ac])
+        if not mane_info:
+            return TranscriptPriority.LONGEST_COMPATIBLE_REMAINING
+        mane_info = mane_info[0]["MANE_status"]
+        return (
+            TranscriptPriority.MANE_SELECT
+            if mane_info == "MANE Select"
+            else TranscriptPriority.MANE_PLUS_CLINICAL
+        )
+
     def get_mane_data_from_chr_pos(
         self, alt_ac: str, start: int, end: int
     ) -> list[dict]:

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool/sources/uta_database.py

@@ -5,7 +5,7 @@ import logging
 from os import environ
 from typing import Any, Literal, TypeVar
 from urllib.parse import ParseResult as UrlLibParseResult
-from urllib.parse import quote, unquote, urlparse
+from urllib.parse import unquote, urlparse, urlunparse
 
 import asyncpg
 import boto3
@@ -101,8 +101,7 @@ class UtaDatabase:
         """
         self.schema = None
         self._connection_pool = None
-        original_pwd = db_url.split("//")[-1].split("@")[0].split(":")[-1]
-        self.db_url = db_url.replace(original_pwd, quote(original_pwd))
+        self.db_url = db_url
         self.args = self._get_conn_args()
 
     def _get_conn_args(self) -> DbConnectionArgs:
@@ -954,3 +953,28 @@ class ParseResult(UrlLibParseResult):
         """Create schema property."""
         path_elems = self.path.split("/")
         return path_elems[2] if len(path_elems) > 2 else None
+
+    @property
+    def sanitized_url(self) -> str:
+        """Sanitized DB URL with the password masked"""
+        netloc = ""
+        if self.username:
+            netloc += self.username
+            if self.password is not None and self.password != "":
+                netloc += ":***"
+            netloc += "@"
+        if self.hostname:
+            netloc += f"{self.hostname}"
+        if self.port:
+            netloc += f":{self.port}"
+
+        return urlunparse(
+            (
+                self.scheme,
+                netloc,
+                self.path,
+                self.params,
+                self.query,
+                self.fragment,
+            )
+        )

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.14.4
+Version: 0.15.0
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -50,7 +50,7 @@ Requires-Dist: agct>=0.1.0-dev1
 Requires-Dist: polars~=1.0
 Requires-Dist: biocommons.seqrepo
 Requires-Dist: pydantic<3.0,>=2.0
-Requires-Dist: ga4gh.vrs<3.0,>=2.1.3
+Requires-Dist: ga4gh.vrs<3.0,>=2.1.4
 Requires-Dist: wags-tails~=0.4.0
 Requires-Dist: bioutils
 Provides-Extra: dev

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool.egg-info/SOURCES.txt

@@ -6,6 +6,7 @@ CITATION.cff
 LICENSE
 README.md
 pyproject.toml
+.github/CODEOWNERS
 .github/ISSUE_TEMPLATE/bug-report.yaml
 .github/ISSUE_TEMPLATE/feature-request.yaml
 .github/workflows/checks.yaml

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/src/cool_seq_tool.egg-info/requires.txt

@@ -4,7 +4,7 @@ agct>=0.1.0-dev1
 polars~=1.0
 biocommons.seqrepo
 pydantic<3.0,>=2.0
-ga4gh.vrs<3.0,>=2.1.3
+ga4gh.vrs<3.0,>=2.1.4
 wags-tails~=0.4.0
 bioutils
 

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/tests/mappers/test_exon_genomic_coords.py

@@ -172,6 +172,7 @@ def tpm3_exon1():
         "gene": "TPM3",
         "genomic_ac": "NC_000001.11",
         "tx_ac": "NM_152263.3",
+        "tx_status": "longest_compatible_remaining",
         "strand": -1,
         "seg": {
             "exon_ord": 0,
@@ -183,8 +184,8 @@ def tpm3_exon1():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "end": 154192135,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
-            "is_exonic": True,
         },
     }
     return GenomicTxSeg(**params)
@@ -197,6 +198,7 @@ def tpm3_exon8():
         "gene": "TPM3",
         "genomic_ac": "NC_000001.11",
         "tx_ac": "NM_152263.3",
+        "tx_status": "longest_compatible_remaining",
         "strand": -1,
         "seg": {
             "exon_ord": 7,
@@ -208,8 +210,8 @@ def tpm3_exon8():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "start": 154170399,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
-            "is_exonic": True,
         },
     }
     return GenomicTxSeg(**params)
@@ -222,6 +224,7 @@ def tpm3_exon1_g(tpm3_exon1):
         "gene": tpm3_exon1.gene,
         "genomic_ac": tpm3_exon1.genomic_ac,
         "tx_ac": tpm3_exon1.tx_ac,
+        "tx_status": tpm3_exon1.tx_status,
         "strand": tpm3_exon1.strand,
         "seg_start": tpm3_exon1.seg,
     }
@@ -235,6 +238,7 @@ def tpm3_exon8_g(tpm3_exon8):
         "gene": tpm3_exon8.gene,
         "genomic_ac": tpm3_exon8.genomic_ac,
         "tx_ac": tpm3_exon8.tx_ac,
+        "tx_status": tpm3_exon8.tx_status,
         "strand": tpm3_exon8.strand,
         "seg_end": tpm3_exon8.seg,
     }
@@ -248,6 +252,7 @@ def tpm3_exon1_exon8(tpm3_exon1, tpm3_exon8):
         "gene": tpm3_exon8.gene,
         "genomic_ac": tpm3_exon8.genomic_ac,
         "tx_ac": tpm3_exon8.tx_ac,
+        "tx_status": tpm3_exon8.tx_status,
         "strand": tpm3_exon8.strand,
         "seg_start": tpm3_exon1.seg,
         "seg_end": tpm3_exon8.seg,
@@ -269,6 +274,7 @@ def tpm3_exon1_exon8_offset(tpm3_exon1, tpm3_exon8):
         "gene": "TPM3",
         "genomic_ac": "NC_000001.11",
         "tx_ac": "NM_152263.3",
+        "tx_status": "longest_compatible_remaining",
         "strand": -1,
         "seg_start": tpm3_exon1_cpy.seg,
         "seg_end": tpm3_exon8_cpy.seg,
@@ -283,6 +289,7 @@ def mane_braf():
         "gene": "BRAF",
         "genomic_ac": "NC_000007.14",
         "tx_ac": "NM_004333.6",
+        "tx_status": "mane_select",
         "strand": -1,
         "seg_start": {
             "exon_ord": 5,
@@ -294,8 +301,8 @@ def mane_braf():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "end": 140801559,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
-            "is_exonic": True,
         },
         "seg_end": {
             "exon_ord": 14,
@@ -307,8 +314,8 @@ def mane_braf():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "start": 140753336,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
-            "is_exonic": True,
         },
     }
     return GenomicTxSegService(**params)
@@ -321,6 +328,7 @@ def wee1_exon2_exon11():
         "gene": "WEE1",
         "genomic_ac": "NC_000011.10",
         "tx_ac": "NM_003390.3",
+        "tx_status": "longest_compatible_remaining",
         "strand": 1,
         "seg_start": {
             "exon_ord": 1,
@@ -332,6 +340,7 @@ def wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "start": 9576092,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -344,6 +353,7 @@ def wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "end": 9588449,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -357,6 +367,7 @@ def mane_wee1_exon2_exon11():
         "gene": "WEE1",
         "genomic_ac": "NC_000011.10",
         "tx_ac": "NM_003390.4",
+        "tx_status": "mane_select",
         "strand": 1,
         "seg_start": {
             "exon_ord": 1,
@@ -368,6 +379,7 @@ def mane_wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "start": 9576092,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -380,6 +392,7 @@ def mane_wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "end": 9588449,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -393,6 +406,7 @@ def ntrk1_exon10_exon17():
         "gene": "NTRK1",
         "genomic_ac": "NC_000001.11",
         "tx_ac": "NM_002529.3",
+        "tx_status": "longest_compatible_remaining",
         "strand": 1,
         "seg_start": {
             "exon_ord": 9,
@@ -404,6 +418,7 @@ def ntrk1_exon10_exon17():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "start": 156874570,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -416,6 +431,7 @@ def ntrk1_exon10_exon17():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "end": 156881850,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -429,6 +445,7 @@ def zbtb10_exon3_end():
         "gene": "ZBTB10",
         "genomic_ac": "NC_000008.11",
         "tx_ac": "NM_001105539.3",
+        "tx_status": "mane_select",
         "strand": 1,
         "seg_start": None,
         "seg_end": {
@@ -441,8 +458,8 @@ def zbtb10_exon3_end():
                     "refgetAccession": "SQ.209Z7zJ-mFypBEWLk4rNC6S_OxY5p7bs",
                 },
                 "end": 80514010,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
-            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -455,6 +472,7 @@ def zbtb10_exon5_start():
         "gene": "ZBTB10",
         "genomic_ac": "NC_000008.11",
         "tx_ac": "NM_001105539.3",
+        "tx_status": "mane_select",
         "strand": 1,
         "seg_start": {
             "exon_ord": 4,
@@ -466,8 +484,8 @@ def zbtb10_exon5_start():
                     "refgetAccession": "SQ.209Z7zJ-mFypBEWLk4rNC6S_OxY5p7bs",
                 },
                 "start": 80518580,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
-            "is_exonic": False,
         },
         "seg_end": None,
     }
@@ -481,6 +499,7 @@ def tpm3_exon6_end():
         "gene": "TPM3",
         "genomic_ac": "NC_000001.11",
         "tx_ac": "NM_152263.4",
+        "tx_status": "mane_select",
         "strand": -1,
         "seg_start": None,
         "seg_end": {
@@ -493,8 +512,8 @@ def tpm3_exon6_end():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "start": 154171410,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
-            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -507,6 +526,7 @@ def tpm3_exon5_start():
         "gene": "TPM3",
         "genomic_ac": "NC_000001.11",
         "tx_ac": "NM_152263.4",
+        "tx_status": "mane_select",
         "strand": -1,
         "seg_start": {
             "exon_ord": 4,
@@ -518,8 +538,8 @@ def tpm3_exon5_start():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "end": 154173080,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
-            "is_exonic": False,
         },
         "seg_end": None,
     }
@@ -533,6 +553,7 @@ def gusbp3_exon2_end():
         "gene": "GUSBP3",
         "genomic_ac": "NC_000005.10",
         "tx_ac": "NR_027386.2",
+        "tx_status": "longest_compatible_remaining",
         "strand": -1,
         "seg_start": None,
         "seg_end": {
@@ -545,8 +566,8 @@ def gusbp3_exon2_end():
                     "refgetAccession": "SQ.aUiQCzCPZ2d0csHbMSbh2NzInhonSXwI",
                 },
                 "start": 69680764,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
-            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -559,6 +580,7 @@ def eln_grch38_intronic():
         "gene": "ELN",
         "genomic_ac": "NC_000007.14",
         "tx_ac": "NM_000501.4",
+        "tx_status": "mane_select",
         "strand": 1,
         "seg_start": {
             "exon_ord": 0,
@@ -570,8 +592,8 @@ def eln_grch38_intronic():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "start": 74028173,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
-            "is_exonic": True,
         },
         "seg_end": {
             "exon_ord": 7,
@@ -583,8 +605,8 @@ def eln_grch38_intronic():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "end": 74043599,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
-            "is_exonic": False,
         },
     }
     return GenomicTxSegService(**params)
@@ -597,6 +619,7 @@ def gusbp3_exon5_start():
         "gene": "GUSBP3",
         "genomic_ac": "NC_000005.10",
         "tx_ac": "NR_027386.2",
+        "tx_status": "longest_compatible_remaining",
         "strand": -1,
         "seg_start": {
             "exon_ord": 4,
@@ -608,8 +631,8 @@ def gusbp3_exon5_start():
                     "refgetAccession": "SQ.aUiQCzCPZ2d0csHbMSbh2NzInhonSXwI",
                 },
                 "end": 69645878,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
-            "is_exonic": False,
         },
         "seg_end": None,
     }
@@ -639,6 +662,7 @@ def genomic_tx_seg_service_checks(actual, expected=None, is_valid=True):
         assert actual.gene == expected.gene
         assert actual.genomic_ac == expected.genomic_ac
         assert actual.tx_ac == expected.tx_ac
+        assert actual.tx_status == expected.tx_status
         assert actual.strand == expected.strand
 
         for seg_attr in ["seg_start", "seg_end"]:
@@ -660,13 +684,17 @@ 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_seg.genomic_location.extensions
+                    == expected_seg.genomic_location.extensions
+                )
 
         assert actual.errors == expected.errors
     else:
         assert actual.gene is None
         assert actual.genomic_ac is None
         assert actual.tx_ac is None
+        assert actual.tx_status is None
         assert actual.strand is None
         assert actual.seg_start is None
         assert actual.seg_end is None
@@ -711,6 +739,7 @@ def genomic_tx_seg_checks(actual, expected=None, is_valid=True):
         assert actual.gene == expected.gene
         assert actual.genomic_ac == expected.genomic_ac
         assert actual.tx_ac == expected.tx_ac
+        assert actual.tx_status == expected.tx_status
         assert actual.strand == expected.strand
 
         expected_seg = expected.seg
@@ -728,13 +757,17 @@ 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_seg.genomic_location.extensions
+                == expected_seg.genomic_location.extensions
+            )
 
         assert actual.errors == expected.errors
     else:
         assert actual.gene is None
         assert actual.genomic_ac is None
         assert actual.tx_ac is None
+        assert actual.tx_status is None
         assert actual.strand is None
         assert actual.seg is None
         assert len(actual.errors) > 0
@@ -1038,6 +1071,17 @@ async def test_genomic_to_transcript_fusion_context(
     resp = await test_egc_mapper.genomic_to_tx_segment(**inputs)
     genomic_tx_seg_service_checks(resp, gusbp3_exon5_start)
 
+    # Test case where gene does not have a MANE transcript. We are looking
+    # to check that the same transcript accession is returned across runs
+    inputs = {
+        "genomic_ac": "NC_000001.11",
+        "seg_end_genomic": 156421555,
+        "gene": "MIR9-1HG",
+    }
+    resp = await test_egc_mapper.genomic_to_tx_segment(**inputs)
+    assert resp.tx_ac == "NM_001320454.2"
+    assert resp.tx_status == "longest_compatible_remaining"
+
 
 @pytest.mark.asyncio
 async def test_get_alt_ac_start_and_end(

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/tests/sources/test_mane_transcript_mappings.py

@@ -5,7 +5,7 @@ from unittest.mock import patch
 import polars as pl
 import pytest
 
-from cool_seq_tool.schemas import ManeGeneData
+from cool_seq_tool.schemas import ManeGeneData, TranscriptPriority
 
 
 @pytest.fixture(scope="module")
@@ -168,6 +168,15 @@ def test_get_mane_from_transcripts(
     assert resp == []
 
 
+def test_get_transcript_status(test_mane_transcript_mappings):
+    """Test that get_transcript_status works correctly"""
+    actual = test_mane_transcript_mappings.get_transcript_status("NM_152263.4")
+    assert actual == TranscriptPriority.MANE_SELECT
+
+    actual = test_mane_transcript_mappings.get_transcript_status("NM_152263.3")
+    assert actual == TranscriptPriority.LONGEST_COMPATIBLE_REMAINING
+
+
 def test_get_mane_data_from_chr_pos(
     test_mane_transcript_mappings, braf_select, braf_plus_clinical
 ):

{cool_seq_tool-0.14.4 → cool_seq_tool-0.15.0}/tests/sources/test_uta_database.py

@@ -1,11 +1,14 @@
 """Test UTA data source."""
 
+from urllib.parse import urlparse
+
 import pytest
 
 from cool_seq_tool.schemas import Strand
 from cool_seq_tool.sources.uta_database import (
     GenomicTxData,
     GenomicTxMetadata,
+    ParseResult,
     TxExonAlnData,
 )
 
@@ -360,3 +363,98 @@ async def test_get_mane_transcripts_from_genomic_pos(test_db):
     # invalid ac
     resp = await test_db.get_transcripts_from_genomic_pos("NC_000007.14232", 140753336)
     assert resp == []
+
+
+@pytest.mark.parametrize(
+    ("raw_url", "expected"),
+    [
+        # Username + password
+        (
+            "postgresql://user:pass@localhost:5432/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "pass",
+                "hostname": "localhost",
+                "port": 5432,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user:***@localhost:5432/dbname",
+            },
+        ),
+        # Username with null password
+        (
+            "postgresql://user@localhost/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": None,
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user@localhost/dbname",
+            },
+        ),
+        # Password is "0"
+        (
+            "postgresql://user:0@localhost/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "0",
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user:***@localhost/dbname",
+            },
+        ),
+        # Empty password
+        (
+            "postgresql://user:@localhost/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "",
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user@localhost/dbname",
+            },
+        ),
+        # No username
+        (
+            "postgresql://localhost:5432/dbname",
+            {
+                "scheme": "postgresql",
+                "username": None,
+                "password": None,
+                "hostname": "localhost",
+                "port": 5432,
+                "database": "dbname",
+                "sanitized_url": "postgresql://localhost:5432/dbname",
+            },
+        ),
+        # With query params
+        (
+            "postgresql://user:secret@localhost/dbname?query#fragment",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "secret",
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user:***@localhost/dbname?query#fragment",
+            },
+        ),
+    ],
+)
+async def test_parsed_url(raw_url, expected):
+    parsed_result = ParseResult(urlparse(raw_url))
+
+    assert parsed_result.scheme == expected["scheme"]
+    assert parsed_result.username == expected["username"]
+    assert parsed_result.password == expected["password"]
+    assert parsed_result.hostname == expected["hostname"]
+    assert parsed_result.port == expected["port"]
+    assert parsed_result.database == expected["database"]
+    assert parsed_result.sanitized_url == expected["sanitized_url"]