cool-seq-tool 0.14.5__py3-none-any.whl → 0.15.1__py3-none-any.whl

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/mappers/exon_genomic_coords.py

@@ -8,12 +8,15 @@ 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
@@ -113,6 +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."
     )
@@ -144,6 +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,
@@ -172,6 +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."
     )
@@ -211,6 +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,
@@ -264,6 +275,7 @@ class ExonGenomicCoordsMapper:
         self,
         seqrepo_access: SeqRepoAccess,
         uta_db: UtaDatabase,
+        mane_transcript: ManeTranscript,
         mane_transcript_mappings: ManeTranscriptMappings,
         liftover: LiftOver,
     ) -> None:
@@ -288,11 +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
 
@@ -431,6 +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,
@@ -522,6 +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:
@@ -557,6 +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
@@ -858,14 +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"""
@@ -962,6 +983,7 @@ class ExonGenomicCoordsMapper:
             gene=gene,
             genomic_ac=genomic_ac,
             tx_ac=transcript,
+            tx_status=self.mane_transcript_mappings.get_transcript_status(transcript),
             strand=strand,
             seg=TxSegment(
                 exon_ord=exon_num,

cool_seq_tool/mappers/liftover.py

@@ -6,7 +6,8 @@ Currently only supports GRCh37 <-> GRCh38
 import logging
 from os import environ
 
-from agct import Converter, Genome
+from agct import Assembly as AgctAssembly
+from agct import Converter
 
 from cool_seq_tool.schemas import Assembly
 from cool_seq_tool.utils import process_chromosome_input
@@ -43,13 +44,13 @@ class LiftOver:
         """
         self.from_37_to_38 = Converter(
             chainfile=chain_file_37_to_38 or LIFTOVER_CHAIN_37_TO_38,
-            from_db=Genome.HG19,
-            to_db=Genome.HG38,
+            from_assembly=AgctAssembly.HG19,
+            to_assembly=AgctAssembly.HG38,
         )
         self.from_38_to_37 = Converter(
             chainfile=chain_file_38_to_37 or LIFTOVER_CHAIN_38_TO_37,
-            from_db=Genome.HG38,
-            to_db=Genome.HG19,
+            from_assembly=AgctAssembly.HG38,
+            to_assembly=AgctAssembly.HG19,
         )
 
     def get_liftover(
@@ -77,9 +78,9 @@ class LiftOver:
         """
         chromosome = process_chromosome_input(chromosome, "LiftOver.get_liftover()")
         if liftover_to_assembly == Assembly.GRCH38:
-            liftover = self.from_37_to_38.convert_coordinate(chromosome, pos)
+            liftover = self.from_37_to_38.convert_coordinate(chromosome, pos, pos)
         elif liftover_to_assembly == Assembly.GRCH37:
-            liftover = self.from_38_to_37.convert_coordinate(chromosome, pos)
+            liftover = self.from_38_to_37.convert_coordinate(chromosome, pos, pos)
         else:
             _logger.warning("%s assembly not supported", liftover_to_assembly)
             liftover = None

cool_seq_tool/resources/status.py

@@ -114,9 +114,9 @@ async def check_status(
             chain_file_38_to_37=chain_file_38_to_37,
         )
     except (FileNotFoundError, ChainfileError):
-        _logger.exception("agct converter setup failed")
+        _logger.exception("`agct` converter setup failed")
     except Exception as e:
-        _logger.critical("Encountered unexpected error setting up agct: %s", e)
+        _logger.critical("Encountered unexpected error setting up `agct`: %s", e)
     else:
         status["liftover"] = True
 

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-0.14.5.dist-info → cool_seq_tool-0.15.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.14.5
+Version: 0.15.1
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -46,11 +46,11 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: asyncpg
 Requires-Dist: boto3
-Requires-Dist: agct>=0.1.0-dev1
+Requires-Dist: agct>=0.2.0rc1
 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-0.14.5.dist-info → cool_seq_tool-0.15.1.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/app.py,sha256=ThdumeXtLNrrGkQW9wwLT3Zm_Fc1wzg88ZxLIwMzcJU,4978
 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=kWgYssM8YL-Z13H9GdpL77P7simNcbxltAs9YDXHE54,9640
-cool_seq_tool/mappers/exon_genomic_coords.py,sha256=N6Wi7D8hs6gZi-BC4ICuWQEGeqUbBysqxG18EtIIgSk,46187
+cool_seq_tool/mappers/exon_genomic_coords.py,sha256=I59vvswLbXk1fOWLNyNd8NTVT39f5yxTCv20utlTCpo,47361
 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/liftover.py,sha256=vQ2BcSE43ZbY4eCJJqDL6dPPE0UclK7f7NoP2WtEHuA,3459
 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=iP-4NiSmqV-D--gypZyrSqVbOWQvyBZICKQb-VinTik,6241
+cool_seq_tool/resources/status.py,sha256=W1iINKqHi_YWSbJi1c-vUIVCAnQCzNgO8A34bQcRmz0,6245
 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/mane_transcript_mappings.py,sha256=PLJymduwvG1pt9mravE58BfJsGXdAYXcZYZdHPy12z0,7211
 cool_seq_tool/sources/transcript_mappings.py,sha256=903RKTMBO2rbKh6iTQ1BEWnY4C7saBFMPw2_4ATuudg,10054
 cool_seq_tool/sources/uta_database.py,sha256=38CQ0QHHh0kA87tdgsJHJiHdJHQc06ylBYfemGFUlZc,36759
-cool_seq_tool-0.14.5.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
-cool_seq_tool-0.14.5.dist-info/METADATA,sha256=tgWwlBS_2Z71zUJpmO7MjDE3cNFy6GYH7W8YyJrTo0I,6535
-cool_seq_tool-0.14.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cool_seq_tool-0.14.5.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
-cool_seq_tool-0.14.5.dist-info/RECORD,,
+cool_seq_tool-0.15.1.dist-info/licenses/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
+cool_seq_tool-0.15.1.dist-info/METADATA,sha256=QEHrmJL33DUq1R71GYN5mbBPOdMsCfJImYlvG3TC4U8,6533
+cool_seq_tool-0.15.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cool_seq_tool-0.15.1.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
+cool_seq_tool-0.15.1.dist-info/RECORD,,