cool-seq-tool 0.4.0.dev3__py3-none-any.whl → 0.4.1__py3-none-any.whl

cool_seq_tool/sources/uta_database.py

@@ -1,9 +1,10 @@
 """Provide transcript lookup and metadata tools via the UTA database."""
+
 import ast
 import base64
 import logging
 from os import environ
-from typing import Any, Dict, List, Optional, Tuple, Type, TypeVar, Union
+from typing import Any, Literal, TypeVar
 from urllib.parse import ParseResult as UrlLibParseResult
 from urllib.parse import quote, unquote, urlparse
 
@@ -24,12 +25,43 @@ LIFTOVER_CHAIN_37_TO_38 = environ.get("LIFTOVER_CHAIN_37_TO_38")
 LIFTOVER_CHAIN_38_TO_37 = environ.get("LIFTOVER_CHAIN_38_TO_37")
 
 UTA_DB_URL = environ.get(
-    "UTA_DB_URL", "postgresql://uta_admin:uta@localhost:5433/uta/uta_20210129b"
+    "UTA_DB_URL", "postgresql://uta_admin:uta@localhost:5432/uta/uta_20210129b"
 )
 
 logger = logging.getLogger(__name__)
 
 
+def get_liftover(
+    chain_file_37_to_38: str | None = None, chain_file_38_to_37: str | None = None
+) -> tuple[Converter, Converter]:
+    """Fetch Converter instances between GRCh37 and 38.
+
+    Factored out of the UTA Database initialization method to support less expensive
+    status check-type operations.
+
+    :param chain_file_37_to_38: Optional path to chain file for 37 to 38 assembly.
+        This is used for ``agct``. If this is not provided, will check to see
+        if ``LIFTOVER_CHAIN_37_TO_38`` env var is set. If neither is provided, will
+        allow ``agct`` to download a chain file from UCSC
+    :param chain_file_38_to_37: Optional path to chain file for 38 to 37 assembly.
+        This 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
+    :return: converters (37->38, 38->37)
+    """
+    chain_file_37_to_38 = chain_file_37_to_38 or LIFTOVER_CHAIN_37_TO_38
+    if chain_file_37_to_38:
+        converter_37_to_38 = Converter(chainfile=chain_file_37_to_38)
+    else:
+        converter_37_to_38 = Converter(from_db=Genome.HG19, to_db=Genome.HG38)
+    chain_file_38_to_37 = chain_file_38_to_37 or LIFTOVER_CHAIN_38_TO_37
+    if chain_file_38_to_37:
+        converter_38_to_37 = Converter(chainfile=chain_file_38_to_37)
+    else:
+        converter_38_to_37 = Converter(from_db=Genome.HG38, to_db=Genome.HG19)
+    return (converter_37_to_38, converter_38_to_37)
+
+
 class UtaDatabase:
     """Provide transcript lookup and metadata tools via the Universal Transcript Archive
     (UTA) database.
@@ -46,8 +78,8 @@ class UtaDatabase:
     def __init__(
         self,
         db_url: str = UTA_DB_URL,
-        chain_file_37_to_38: Optional[str] = None,
-        chain_file_38_to_37: Optional[str] = None,
+        chain_file_37_to_38: str | None = None,
+        chain_file_38_to_37: str | None = None,
     ) -> None:
         """Initialize DB class. Should only be used by ``create()`` method, and not
         be called directly by a user.
@@ -68,20 +100,11 @@ class UtaDatabase:
         original_pwd = db_url.split("//")[-1].split("@")[0].split(":")[-1]
         self.db_url = db_url.replace(original_pwd, quote(original_pwd))
         self.args = self._get_conn_args()
+        self.liftover_37_to_38, self.liftover_38_to_37 = get_liftover(
+            chain_file_37_to_38, chain_file_38_to_37
+        )
 
-        chain_file_37_to_38 = chain_file_37_to_38 or LIFTOVER_CHAIN_37_TO_38
-        if chain_file_37_to_38:
-            self.liftover_37_to_38 = Converter(chainfile=chain_file_37_to_38)
-        else:
-            self.liftover_37_to_38 = Converter(from_db=Genome.HG19, to_db=Genome.HG38)
-
-        chain_file_38_to_37 = chain_file_38_to_37 or LIFTOVER_CHAIN_38_TO_37
-        if chain_file_38_to_37:
-            self.liftover_38_to_37 = Converter(chainfile=chain_file_38_to_37)
-        else:
-            self.liftover_38_to_37 = Converter(from_db=Genome.HG38, to_db=Genome.HG19)
-
-    def _get_conn_args(self) -> Dict:
+    def _get_conn_args(self) -> dict:
         """Return connection arguments.
 
         :param db_url: raw connection URL
@@ -99,9 +122,9 @@ class UtaDatabase:
             self.schema = schema
 
             environ["PGPASSWORD"] = password
-            environ[
-                "UTA_DB_URL"
-            ] = f"postgresql://{username}@{host}:{port}/{database}/{schema}"
+            environ["UTA_DB_URL"] = (
+                f"postgresql://{username}@{host}:{port}/{database}/{schema}"
+            )
             return {
                 "host": host,
                 "port": int(port),
@@ -145,7 +168,7 @@ class UtaDatabase:
 
     @classmethod
     async def create(
-        cls: Type[UTADatabaseType], db_url: str = UTA_DB_URL
+        cls: type[UTADatabaseType], db_url: str = UTA_DB_URL
     ) -> UTADatabaseType:
         """Manufacture a fully-initialized class instance (a la factory pattern). This
         method should be used instead of calling the class directly to create a new
@@ -173,7 +196,10 @@ class UtaDatabase:
         """
 
         async def _execute_query(q: str) -> Any:  # noqa: ANN401
-            async with self._connection_pool.acquire() as connection, connection.transaction():
+            async with (
+                self._connection_pool.acquire() as connection,
+                connection.transaction(),
+            ):
                 return await connection.fetch(q)
 
         if not self._connection_pool:
@@ -234,25 +260,22 @@ class UtaDatabase:
                 await self.execute_query(create_index)
 
     @staticmethod
-    def _transform_list(li: List) -> List[List[Any]]:
+    def _transform_list(li: list) -> list[list[Any]]:
         """Transform list to only contain field values
 
         :param li: List of asyncpg.Record objects
         :return: List of list of objects
         """
-        results = []
-        for item in li:
-            results.append(list(item))
-        return results
+        return [list(i) for i in li]
 
     async def get_genes_and_alt_acs(
         self,
         pos: int,
-        strand: Optional[Strand] = None,
-        chromosome: Optional[int] = None,
-        alt_ac: Optional[str] = None,
-        gene: Optional[str] = None,
-    ) -> Tuple[Optional[Dict], Optional[str]]:
+        strand: Strand | None = None,
+        chromosome: int | None = None,
+        alt_ac: str | None = None,
+        gene: str | None = None,
+    ) -> tuple[dict | None, str | None]:
         """Return genes and genomic accessions for a position on a chromosome or alt_ac
 
         :param pos: Genomic position
@@ -309,8 +332,8 @@ class UtaDatabase:
         return {"genes": genes, "alt_acs": alt_acs}, None
 
     async def get_tx_exons(
-        self, tx_ac: str, alt_ac: Optional[str] = None
-    ) -> Tuple[Optional[List[Tuple[int, int]]], Optional[str]]:
+        self, tx_ac: str, alt_ac: str | None = None
+    ) -> tuple[list[tuple[int, int]] | None, str | None]:
         """Get list of transcript exons start/end coordinates.
 
         :param tx_ac: Transcript accession
@@ -352,7 +375,7 @@ class UtaDatabase:
         self,
         tx_ac: str,
         alt_ac: str,
-    ) -> Tuple[Optional[Tuple[int, int, int, int, int]], Optional[str]]:
+    ) -> tuple[tuple[int, int, int, int, int] | None, str | None]:
         """Get exon number, transcript coordinates, and genomic coordinates
 
         :param tx_ac: Transcript accession
@@ -379,8 +402,8 @@ class UtaDatabase:
         return tx_exons_genomic_coords, None
 
     async def get_alt_ac_start_or_end(
-        self, tx_ac: str, tx_exon_start: int, tx_exon_end: int, gene: Optional[str]
-    ) -> Tuple[Optional[Tuple[str, str, int, int, int]], Optional[str]]:
+        self, tx_ac: str, tx_exon_start: int, tx_exon_end: int, gene: str | None
+    ) -> tuple[tuple[str, str, int, int, int] | None, str | None]:
         """Get genomic data for related transcript exon start or end.
 
         :param tx_ac: Transcript accession
@@ -420,7 +443,7 @@ class UtaDatabase:
         result = result[0]
         return (result[0], result[1], result[2], result[3], result[4]), None
 
-    async def get_cds_start_end(self, tx_ac: str) -> Optional[Tuple[int, int]]:
+    async def get_cds_start_end(self, tx_ac: str) -> tuple[int, int] | None:
         """Get coding start and end site
 
         :param tx_ac: Transcript accession
@@ -444,7 +467,7 @@ class UtaDatabase:
             )
             return None
 
-    async def get_newest_assembly_ac(self, ac: str) -> List[str]:
+    async def get_newest_assembly_ac(self, ac: str) -> list[str]:
         """Find accession associated to latest genomic assembly
 
         :param ac: Accession
@@ -489,7 +512,7 @@ class UtaDatabase:
         result = await self.execute_query(query)
         return result[0][0]
 
-    async def get_ac_descr(self, ac: str) -> Optional[str]:
+    async def get_ac_descr(self, ac: str) -> str | None:
         """Return accession description. This is typically available only for accessions
         from older (pre-GRCh38) builds.
 
@@ -524,10 +547,10 @@ class UtaDatabase:
         tx_ac: str,
         start_pos: int,
         end_pos: int,
-        alt_ac: Optional[str] = None,
+        alt_ac: str | None = None,
         use_tx_pos: bool = True,
         like_tx_ac: bool = False,
-    ) -> List:
+    ) -> list:
         """Return queried data from tx_exon_aln_v table.
 
         :param tx_ac: accession on c. coordinate
@@ -592,13 +615,10 @@ class UtaDatabase:
                 temp_ac,
                 alt_ac,
             )
-        results = []
-        for r in result:
-            results.append(list(r))
-        return results
+        return [list(r) for r in result]
 
     @staticmethod
-    def data_from_result(result: List) -> Optional[Dict]:
+    def data_from_result(result: list) -> dict | None:
         """Return data found from result.
 
         :param result: Data from tx_exon_aln_v table
@@ -631,8 +651,8 @@ class UtaDatabase:
         }
 
     async def get_mane_c_genomic_data(
-        self, ac: str, alt_ac: Optional[str], start_pos: int, end_pos: int
-    ) -> Optional[Dict]:
+        self, ac: str, alt_ac: str | None, start_pos: int, end_pos: int
+    ) -> dict | None:
         """Get MANE transcript and genomic data. Used when going from g. to MANE c.
         representation.
 
@@ -697,13 +717,12 @@ class UtaDatabase:
     async def get_genomic_tx_data(
         self,
         tx_ac: str,
-        pos: Tuple[int, int],
-        annotation_layer: Union[
-            AnnotationLayer.CDNA, AnnotationLayer.GENOMIC
-        ] = AnnotationLayer.CDNA,
-        alt_ac: Optional[str] = None,
+        pos: tuple[int, int],
+        annotation_layer: Literal[AnnotationLayer.CDNA]
+        | Literal[AnnotationLayer.GENOMIC] = AnnotationLayer.CDNA,
+        alt_ac: str | None = None,
         target_genome_assembly: Assembly = Assembly.GRCH38,
-    ) -> Optional[Dict]:
+    ) -> dict | None:
         """Get transcript mapping to genomic data.
 
         :param tx_ac: Accession on c. coordinate
@@ -760,7 +779,7 @@ class UtaDatabase:
 
         return data
 
-    async def get_ac_from_gene(self, gene: str) -> List[str]:
+    async def get_ac_from_gene(self, gene: str) -> list[str]:
         """Return genomic accession(s) associated to a gene.
 
         :param gene: Gene symbol
@@ -784,14 +803,16 @@ class UtaDatabase:
 
     async def get_gene_from_ac(
         self, ac: str, start_pos: int, end_pos: int
-    ) -> Optional[List[str]]:
+    ) -> list[str] | None:
         """Get gene(s) within the provided coordinate range
 
         >>> import asyncio
         >>> from cool_seq_tool.sources import UtaDatabase
         >>> async def get_gene():
         ...     uta_db = await UtaDatabase.create()
-        ...     result = await uta_db.get_gene_from_ac("NC_000017.11", 43044296, 43045802)
+        ...     result = await uta_db.get_gene_from_ac(
+        ...         "NC_000017.11", 43044296, 43045802
+        ...     )
         ...     return result
         >>> asyncio.run(get_gene())
         ['BRCA1']
@@ -828,11 +849,11 @@ class UtaDatabase:
 
     async def get_transcripts(
         self,
-        start_pos: Optional[int] = None,
-        end_pos: Optional[int] = None,
-        gene: Optional[str] = None,
+        start_pos: int | None = None,
+        end_pos: int | None = None,
+        gene: str | None = None,
         use_tx_pos: bool = True,
-        alt_ac: Optional[str] = None,
+        alt_ac: str | None = None,
     ) -> pl.DataFrame:
         """Get transcripts for a given ``gene`` or ``alt_ac`` related to optional positions.
 
@@ -906,7 +927,7 @@ class UtaDatabase:
             results_df = results_df.unique()
         return results_df
 
-    async def get_chr_assembly(self, ac: str) -> Optional[Tuple[str, str]]:
+    async def get_chr_assembly(self, ac: str) -> tuple[str, str] | None:
         """Get chromosome and assembly for NC accession if not in GRCh38.
 
         :param ac: NC accession
@@ -929,7 +950,7 @@ class UtaDatabase:
 
         return chromosome, assembly
 
-    async def liftover_to_38(self, genomic_tx_data: Dict) -> None:
+    async def liftover_to_38(self, genomic_tx_data: dict) -> None:
         """Liftover genomic_tx_data to hg38 assembly.
 
         :param genomic_tx_data: Dictionary containing gene, nc_accession, alt_pos, and
@@ -985,7 +1006,7 @@ class UtaDatabase:
 
     def get_liftover(
         self, chromosome: str, pos: int, liftover_to_assembly: Assembly
-    ) -> Optional[Tuple[str, int]]:
+    ) -> tuple[str, int] | None:
         """Get new genome assembly data for a position on a chromosome.
 
         :param chromosome: The chromosome number. Must be prefixed with ``chr``
@@ -1012,7 +1033,7 @@ class UtaDatabase:
 
     def _set_liftover(
         self,
-        genomic_tx_data: Dict,
+        genomic_tx_data: dict,
         key: str,
         chromosome: str,
         liftover_to_assembly: Assembly,
@@ -1049,7 +1070,7 @@ class UtaDatabase:
 
         genomic_tx_data[key] = liftover_start_i[1], liftover_end_i[1]
 
-    async def p_to_c_ac(self, p_ac: str) -> List[str]:
+    async def p_to_c_ac(self, p_ac: str) -> list[str]:
         """Return cDNA reference sequence accession from protein reference sequence
         accession (i.e. ``p.`` to ``c.`` in HGVS syntax)
 
@@ -1079,7 +1100,7 @@ class UtaDatabase:
 
     async def get_transcripts_from_genomic_pos(
         self, alt_ac: str, g_pos: int
-    ) -> List[str]:
+    ) -> list[str]:
         """Get transcripts associated to a genomic ac and position.
 
         :param alt_ac: Genomic accession
@@ -1145,13 +1166,13 @@ class ParseResult(UrlLibParseResult):
         return super(ParseResult, cls).__new__(cls, *pr)  # noqa: UP008
 
     @property
-    def database(self) -> Optional[str]:
+    def database(self) -> str | None:
         """Create database property."""
         path_elems = self.path.split("/")
         return path_elems[1] if len(path_elems) > 1 else None
 
     @property
-    def schema(self) -> Optional[str]:
+    def schema(self) -> str | None:
         """Create schema property."""
         path_elems = self.path.split("/")
         return path_elems[2] if len(path_elems) > 2 else None

cool_seq_tool/utils.py

@@ -1,7 +1,7 @@
 """Provide a small set of general helper functions."""
+
 import datetime
 import logging
-from typing import Tuple
 
 from cool_seq_tool.schemas import ResidueMode, ServiceMeta
 from cool_seq_tool.version import __version__
@@ -11,7 +11,7 @@ logger = logging.getLogger(__name__)
 
 def get_inter_residue_pos(
     start_pos: int, end_pos: int, residue_mode: ResidueMode
-) -> Tuple[int, int]:
+) -> tuple[int, int]:
     """Return equivalent inter-residue position.
 
     Generally, we prefer to work with inter-residue coordinates where possible. Our

cool_seq_tool/version.py

@@ -1,2 +1,3 @@
 """Define package version."""
-__version__ = "0.4.0-dev3"
+
+__version__ = "0.4.1"

{cool_seq_tool-0.4.0.dev3.dist-info → cool_seq_tool-0.4.1.dist-info}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2021-2023 Wagner Lab
+Copyright (c) 2021-2024 Wagner Lab
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

{cool_seq_tool-0.4.0.dev3.dist-info → cool_seq_tool-0.4.1.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.1
 Name: cool_seq_tool
-Version: 0.4.0.dev3
+Version: 0.4.1
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
         
-        Copyright (c) 2021-2023 Wagner Lab
+        Copyright (c) 2021-2024 Wagner Lab
         
         Permission is hereby granted, free of charge, to any person obtaining a copy
         of this software and associated documentation files (the "Software"), to deal
@@ -26,7 +26,7 @@ License: MIT License
         SOFTWARE.
         
 Project-URL: Homepage, https://github.com/genomicmedlab/cool-seq-tool
-Project-URL: Documentation, https://coolseqtool.readthedocs.io/en/latest/index.html
+Project-URL: Documentation, https://coolseqtool.readthedocs.io/
 Project-URL: Changelog, https://github.com/genomicmedlab/cool-seq-tool/releases
 Project-URL: Source, https://github.com/genomicmedlab/cool-seq-tool
 Project-URL: Bug Tracker, https://github.com/genomicmedlab/cool-seq-tool/issues
@@ -39,30 +39,30 @@ 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 :: 3.8
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Python: >=3.8
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: asyncpg
 Requires-Dist: aiofiles
 Requires-Dist: boto3
 Requires-Dist: agct >=0.1.0-dev1
-Requires-Dist: polars
+Requires-Dist: polars ~=1.0
 Requires-Dist: hgvs
 Requires-Dist: biocommons.seqrepo
 Requires-Dist: pydantic ==2.*
 Requires-Dist: uvicorn
 Requires-Dist: fastapi
 Requires-Dist: ga4gh.vrs
+Requires-Dist: wags-tails ~=0.1.3
 Provides-Extra: dev
 Requires-Dist: pre-commit ; extra == 'dev'
 Requires-Dist: ipython ; extra == 'dev'
 Requires-Dist: ipykernel ; extra == 'dev'
 Requires-Dist: psycopg2-binary ; extra == 'dev'
-Requires-Dist: ruff ==0.2.0 ; extra == 'dev'
+Requires-Dist: ruff ==0.5.0 ; extra == 'dev'
 Provides-Extra: docs
 Requires-Dist: sphinx ==6.1.3 ; extra == 'docs'
 Requires-Dist: sphinx-autodoc-typehints ==1.22.0 ; extra == 'docs'
@@ -81,8 +81,14 @@ Requires-Dist: mock ; extra == 'tests'
 CoolSeqTool
 </h1>
 
+[![image](https://img.shields.io/pypi/v/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![image](https://img.shields.io/pypi/l/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![image](https://img.shields.io/pypi/pyversions/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![Actions status](https://github.com/genomicmedlab/cool-seq-tool/actions/workflows/checks.yaml/badge.svg)](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
+
+---
+
 **[Documentation](https://coolseqtool.readthedocs.io/latest/)** · [Installation](https://coolseqtool.readthedocs.io/latest/install.html) · [Usage](https://coolseqtool.readthedocs.io/latest/usage.html) · [API reference](https://coolseqtool.readthedocs.io/latest/reference/index.html)
 
+---
+
 ## Overview
 
 <!-- description -->
@@ -113,6 +119,7 @@ All CoolSeqTool resources can be initialized by way of a top-level class instanc
 
 ```pycon
 >>> from cool_seq_tool.app import CoolSeqTool
+>>> from cool_seq_tool.schemas import AnnotationLayer, ResidueMode
 >>> cst = CoolSeqTool()
 >>> result = await cst.mane_transcript.get_mane_transcript(
 ...     "NP_004324.2",

cool_seq_tool-0.4.1.dist-info/RECORD

@@ -0,0 +1,29 @@
+cool_seq_tool/__init__.py,sha256=BTfkS0bkMtxBL4yGHc4Z7ubmNhdhY2WALfadnk8N1lw,280
+cool_seq_tool/api.py,sha256=AbCmdUVH8ltwqH8k7DiVsHpujMzb6c5pyAKY12iIC0U,1210
+cool_seq_tool/app.py,sha256=5dBmzTf5SeIF90y_ZyI0K6AMSKgchC33eW_ABN6D8_s,4790
+cool_seq_tool/schemas.py,sha256=8xGrP0rAcKLXtZYEe_DJcNp4zapjhN0StRq8uCjoobE,16720
+cool_seq_tool/utils.py,sha256=lckkyFKxMAqG79SYO3p28q6BWgEjlQP7CumE2TDP1zc,1601
+cool_seq_tool/version.py,sha256=hs3N9Wl67casrrQa2sGIAcpcaUySVk4oLE7JffoQuCI,53
+cool_seq_tool/handlers/__init__.py,sha256=KalQ46vX1MO4SJz2SlspKoIRy1n3c3Vp1t4Y2pIfqow,78
+cool_seq_tool/handlers/seqrepo_access.py,sha256=JB3cg7YiV2JKa7ImJXz4WtP9XWShk9qYvhCCrZnBQ6M,8983
+cool_seq_tool/mappers/__init__.py,sha256=SMSf6sPcu7mdQNuJ4Cj1mbOwFUPuMdFSf0noY4XvTxE,262
+cool_seq_tool/mappers/alignment.py,sha256=6Vk4XEar54ivuH8N7oBqa9gUa8E5GjWCI9hC1HCkM18,9552
+cool_seq_tool/mappers/exon_genomic_coords.py,sha256=tOmo6kFGcFIRmLBQwSsIZUSiratiyACf946YKV_IU78,38544
+cool_seq_tool/mappers/mane_transcript.py,sha256=RrVRUS4IqxxX-HyamNLqpQ_WVWABgiLqwmmIh92uny8,49264
+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=ENsLiwSxzJOLOsY5IKDM805UWbQAOV3w9s7Rv_FLAUs,5761
+cool_seq_tool/resources/transcript_mapping.tsv,sha256=AO3luYQAbFiCoRgiiPXotakb5pAwx1jDCeXpvGdIuac,24138769
+cool_seq_tool/routers/__init__.py,sha256=7SqhLv6_mDPpK1Q0L9aykmjhCmsymFqgbSWZH8LuCW0,437
+cool_seq_tool/routers/default.py,sha256=zqeQmHmfGUvV32xLbN-fUfYnK_UI1gpqIL8Eu5Y8KzY,3928
+cool_seq_tool/routers/mane.py,sha256=boZKP5PH0BAcqEeTBBr9Z3EMY4lhvLLX-pJxUqjBZQ0,3508
+cool_seq_tool/routers/mappings.py,sha256=UJaip0QvRfK3Lk3eVuwofUwg2XJqMV5OVY9OLcpnWS4,6061
+cool_seq_tool/sources/__init__.py,sha256=51QiymeptF7AeVGgV-tW_9f4pIUr0xtYbyzpvHOCneM,304
+cool_seq_tool/sources/mane_transcript_mappings.py,sha256=9Rd_tRCrTk9i9Urp-pMMttq4cCbIJaEJ0n8rM9y9-7I,4077
+cool_seq_tool/sources/transcript_mappings.py,sha256=903RKTMBO2rbKh6iTQ1BEWnY4C7saBFMPw2_4ATuudg,10054
+cool_seq_tool/sources/uta_database.py,sha256=GJHhYbH130YJo9FIRroR8eavlbaziMwI0JVNP8IPGPM,45636
+cool_seq_tool-0.4.1.dist-info/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
+cool_seq_tool-0.4.1.dist-info/METADATA,sha256=CnZwl-rVLfY6kcVkQKYsYziT19q48qHRkYFQ96-OCx0,6262
+cool_seq_tool-0.4.1.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+cool_seq_tool-0.4.1.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
+cool_seq_tool-0.4.1.dist-info/RECORD,,

{cool_seq_tool-0.4.0.dev3.dist-info → cool_seq_tool-0.4.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: setuptools (70.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

cool_seq_tool/data/__init__.py

@@ -1,2 +0,0 @@
-"""Module for data"""
-from .data_downloads import DataDownload

cool_seq_tool/data/data_downloads.py

@@ -1,89 +0,0 @@
-"""Handle acquisition of external data."""
-import datetime
-import gzip
-import logging
-import shutil
-from ftplib import FTP
-from pathlib import Path
-
-from dateutil import parser
-
-from cool_seq_tool import APP_ROOT
-
-logger = logging.getLogger("cool_seq_tool")
-
-
-class DataDownload:
-    """Manage downloadable data files. Responsible for checking if files are available
-    under expected locations, and fetching them if not.
-
-    Relevant methods are called automatically by data classes; users should not have
-    to interact with this class under normal circumstances.
-    """
-
-    def __init__(self) -> None:
-        """Initialize downloadable data locations."""
-        self._data_dir = APP_ROOT / "data"
-
-    def get_mane_summary(self) -> Path:
-        """Identify latest MANE summary data. If unavailable locally, download from
-        `NCBI FTP server <https://ftp.ncbi.nlm.nih.gov/refseq/MANE/MANE_human/current/>`_.
-
-        :return: path to MANE summary file
-        """
-        with FTP("ftp.ncbi.nlm.nih.gov") as ftp:
-            ftp.login()
-            ftp.cwd("/refseq/MANE/MANE_human/current")
-            files = ftp.nlst()
-            mane_summary_file = [f for f in files if f.endswith(".summary.txt.gz")]
-            if not mane_summary_file:
-                msg = "Unable to download MANE summary data"
-                raise Exception(msg)
-            mane_summary_file = mane_summary_file[0]
-            self._mane_summary_path = self._data_dir / mane_summary_file[:-3]
-            mane_data_path = self._data_dir / mane_summary_file
-            if not self._mane_summary_path.exists():
-                logger.info("Downloading MANE summary file from NCBI.")
-                with mane_data_path.open("wb") as fp:
-                    ftp.retrbinary(f"RETR {mane_summary_file}", fp.write)
-                with gzip.open(
-                    mane_data_path, "rb"
-                ) as f_in, self._mane_summary_path.open("wb") as f_out:
-                    shutil.copyfileobj(f_in, f_out)
-                mane_data_path.unlink()
-                logger.info("MANE summary file download complete.")
-        return self._mane_summary_path
-
-    def get_lrg_refseq_gene_data(self) -> Path:
-        """Identify latest LRG RefSeq Gene file. If unavailable locally, download from
-        `NCBI FTP server <https://ftp.ncbi.nlm.nih.gov/refseq/H_sapiens/RefSeqGene/>`_.
-
-        :return: path to acquired LRG RefSeq Gene data file
-        """
-        with FTP("ftp.ncbi.nlm.nih.gov") as ftp:
-            ftp.login()
-            lrg_refseqgene_file = "LRG_RefSeqGene"
-            ftp_dir_path = "/refseq/H_sapiens/RefSeqGene/"
-            ftp_file_path = f"{ftp_dir_path}{lrg_refseqgene_file}"
-            timestamp = ftp.voidcmd(f"MDTM {ftp_file_path}")[4:].strip()
-            date = str(parser.parse(timestamp)).split()[0]
-            version = (
-                datetime.datetime.strptime(date, "%Y-%m-%d")
-                .astimezone(tz=datetime.timezone.utc)
-                .strftime("%Y%m%d")
-            )
-            fn_versioned = f"{lrg_refseqgene_file}_{version}"
-            lrg_refseqgene_path = self._data_dir / lrg_refseqgene_file
-            self._lrg_refseqgene_path = self._data_dir / fn_versioned
-            if not self._lrg_refseqgene_path.exists():
-                logger.info("Downloading LRG RefSeq data from NCBI.")
-                ftp.cwd(ftp_dir_path)
-                with lrg_refseqgene_path.open("wb") as fp:
-                    ftp.retrbinary(f"RETR {lrg_refseqgene_file}", fp.write)
-                with lrg_refseqgene_path.open(
-                    "rb"
-                ) as f_in, self._lrg_refseqgene_path.open("wb") as f_out:
-                    shutil.copyfileobj(f_in, f_out)
-                lrg_refseqgene_path.unlink()
-                logger.info("LRG RefSeq data download complete.")
-        return self._lrg_refseqgene_path

cool_seq_tool/paths.py

@@ -1,28 +0,0 @@
-"""Provide paths to shared files, and trigger data acquisition if unavailable."""
-from os import environ
-from pathlib import Path
-
-from cool_seq_tool.data.data_downloads import DataDownload
-
-APP_ROOT = Path(__file__).resolve().parents[0]
-
-TRANSCRIPT_MAPPINGS_PATH = Path(
-    environ.get("TRANSCRIPT_MAPPINGS_PATH", f"{APP_ROOT}/data/transcript_mapping.tsv")
-)
-
-d = DataDownload()
-
-provided_mane_summary_path = environ.get("MANE_SUMMARY_PATH", "")
-if provided_mane_summary_path:
-    MANE_SUMMARY_PATH = Path(provided_mane_summary_path)
-else:
-    MANE_SUMMARY_PATH = d.get_mane_summary()
-
-provided_lrg_refseq_path = environ.get("LRG_REFSEQGENE_PATH", "")
-if provided_lrg_refseq_path:
-    LRG_REFSEQGENE_PATH = Path(provided_lrg_refseq_path)
-else:
-    LRG_REFSEQGENE_PATH = d.get_lrg_refseq_gene_data()
-
-
-SEQREPO_ROOT_DIR = environ.get("SEQREPO_ROOT_DIR", "/usr/local/share/seqrepo/latest")