cool-seq-tool 0.3.0.dev0__tar.gz → 0.4.0.dev0__tar.gz

{cool_seq_tool-0.3.0.dev0 → cool_seq_tool-0.4.0.dev0}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2021 VICC
+Copyright (c) 2021-2023 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.dev0/PKG-INFO

@@ -0,0 +1,130 @@
+Metadata-Version: 2.1
+Name: cool_seq_tool
+Version: 0.4.0.dev0
+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
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/genomicmedlab/cool-seq-tool
+Project-URL: Documentation, https://coolseqtool.readthedocs.io/en/latest/index.html
+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
+Classifier: Development Status :: 3 - Alpha
+Classifier: Framework :: FastAPI
+Classifier: Framework :: Pydantic
+Classifier: Framework :: Pydantic :: 2
+Classifier: Intended Audience :: Science/Research
+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
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: asyncpg
+Requires-Dist: aiofiles
+Requires-Dist: boto3
+Requires-Dist: pyliftover
+Requires-Dist: polars
+Requires-Dist: hgvs
+Requires-Dist: biocommons.seqrepo
+Requires-Dist: pydantic==2.*
+Requires-Dist: uvicorn
+Requires-Dist: fastapi
+Requires-Dist: ga4gh.vrs
+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; extra == "dev"
+Provides-Extra: tests
+Requires-Dist: pytest; extra == "tests"
+Requires-Dist: pytest-cov; extra == "tests"
+Requires-Dist: pytest-asyncio==0.18.3; extra == "tests"
+Requires-Dist: mock; extra == "tests"
+Provides-Extra: docs
+Requires-Dist: sphinx==6.1.3; extra == "docs"
+Requires-Dist: sphinx-autodoc-typehints==1.22.0; extra == "docs"
+Requires-Dist: sphinx-autobuild==2021.3.14; extra == "docs"
+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"
+
+<h1 align="center">
+CoolSeqTool
+</h1>
+
+**[Documentation](https://coolseqtool.readthedocs.io/en/latest/)** · [Installation](https://coolseqtool.readthedocs.io/en/latest/install.html) · [Usage](https://coolseqtool.readthedocs.io/en/latest/usage.html) · [API reference](https://coolseqtool.readthedocs.io/en/latest/reference/index.html)
+
+## Overview
+
+<!-- description -->
+The **CoolSeqTool** provides:
+
+ - A Pythonic API on top of sequence data of interest to tertiary analysis tools, including mappings between gene names and transcripts, [MANE transcript](https://www.ncbi.nlm.nih.gov/refseq/MANE/) descriptions, and the [Universal Transcript Archive](https://github.com/biocommons/uta)
+ - Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
+ - Mapping tools that combine the above to support translation between references sequences, annotation layers, and MANE transcripts
+<!-- /description -->
+
+---
+
+## Install
+
+CoolSeqTool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
+
+```shell
+python3 -m pip install cool-seq-tool
+```
+
+See the [installation instructions](https://coolseqtool.readthedocs.io/en/latest/install.html) in the documentation for a description of dependency setup requirements.
+
+---
+
+## Usage
+
+All CoolSeqTool resources can be initialized by way of a top-level class instance:
+
+```pycon
+>>> from cool_seq_tool.app import CoolSeqTool
+>>> cst = CoolSeqTool()
+>>> result = await cst.mane_transcript.get_mane_transcript(
+...     "NP_004324.2",
+...     599,
+...     AnnotationLayer.PROTEIN,
+...     residue_mode=ResidueMode.INTER_RESIDUE,
+... )
+>>> result.gene, result.refseq, result.status
+('EGFR', 'NM_005228.5', <TranscriptPriority.MANE_SELECT: 'mane_select'>)
+```
+
+---
+
+## Feedback and contributing
+
+We welcome bug reports, feature requests, and code contributions from users and interested collaborators. The [documentation](https://coolseqtool.readthedocs.io/en/latest/contributing.html) contains guidance for submitting feedback and contributing new code.

cool_seq_tool-0.4.0.dev0/README.md

@@ -0,0 +1,52 @@
+<h1 align="center">
+CoolSeqTool
+</h1>
+
+**[Documentation](https://coolseqtool.readthedocs.io/en/latest/)** · [Installation](https://coolseqtool.readthedocs.io/en/latest/install.html) · [Usage](https://coolseqtool.readthedocs.io/en/latest/usage.html) · [API reference](https://coolseqtool.readthedocs.io/en/latest/reference/index.html)
+
+## Overview
+
+<!-- description -->
+The **CoolSeqTool** provides:
+
+ - A Pythonic API on top of sequence data of interest to tertiary analysis tools, including mappings between gene names and transcripts, [MANE transcript](https://www.ncbi.nlm.nih.gov/refseq/MANE/) descriptions, and the [Universal Transcript Archive](https://github.com/biocommons/uta)
+ - Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
+ - Mapping tools that combine the above to support translation between references sequences, annotation layers, and MANE transcripts
+<!-- /description -->
+
+---
+
+## Install
+
+CoolSeqTool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
+
+```shell
+python3 -m pip install cool-seq-tool
+```
+
+See the [installation instructions](https://coolseqtool.readthedocs.io/en/latest/install.html) in the documentation for a description of dependency setup requirements.
+
+---
+
+## Usage
+
+All CoolSeqTool resources can be initialized by way of a top-level class instance:
+
+```pycon
+>>> from cool_seq_tool.app import CoolSeqTool
+>>> cst = CoolSeqTool()
+>>> result = await cst.mane_transcript.get_mane_transcript(
+...     "NP_004324.2",
+...     599,
+...     AnnotationLayer.PROTEIN,
+...     residue_mode=ResidueMode.INTER_RESIDUE,
+... )
+>>> result.gene, result.refseq, result.status
+('EGFR', 'NM_005228.5', <TranscriptPriority.MANE_SELECT: 'mane_select'>)
+```
+
+---
+
+## Feedback and contributing
+
+We welcome bug reports, feature requests, and code contributions from users and interested collaborators. The [documentation](https://coolseqtool.readthedocs.io/en/latest/contributing.html) contains guidance for submitting feedback and contributing new code.

cool_seq_tool-0.4.0.dev0/pyproject.toml

@@ -0,0 +1,122 @@
+[project]
+name = "cool_seq_tool"
+authors = [
+    {name = "Kori Kuzma"},
+    {name = "James Stevenson"},
+    {name = "Katie Stahl"},
+    {name = "Alex Wagner"},
+]
+readme = "README.md"
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Framework :: FastAPI",
+    "Framework :: Pydantic",
+    "Framework :: Pydantic :: 2",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+]
+requires-python = ">=3.8"
+description = "Common Operation on Lots of Sequences Tool"
+license = {file = "LICENSE"}
+dependencies = [
+    "asyncpg",
+    "aiofiles",
+    "boto3",
+    "pyliftover",
+    "polars",
+    "hgvs",
+    "biocommons.seqrepo",
+    "pydantic == 2.*",
+    "uvicorn",
+    "fastapi",
+    "ga4gh.vrs",
+]
+dynamic = ["version"]
+
+[project.optional-dependencies]
+dev = ["pre-commit", "ipython", "ipykernel", "psycopg2-binary", "ruff"]
+tests = ["pytest", "pytest-cov", "pytest-asyncio==0.18.3", "mock"]
+docs = [
+    "sphinx==6.1.3",
+    "sphinx-autodoc-typehints==1.22.0",
+    "sphinx-autobuild==2021.3.14",
+    "sphinx-copybutton==0.5.2",
+    "sphinxext-opengraph==0.8.2",
+    "furo==2023.3.27",
+]
+
+[project.urls]
+Homepage = "https://github.com/genomicmedlab/cool-seq-tool"
+Documentation = "https://coolseqtool.readthedocs.io/en/latest/index.html"
+Changelog = "https://github.com/genomicmedlab/cool-seq-tool/releases"
+Source = "https://github.com/genomicmedlab/cool-seq-tool"
+"Bug Tracker" = "https://github.com/genomicmedlab/cool-seq-tool/issues"
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.dynamic]
+version = {attr = "cool_seq_tool.version.__version__"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+addopts = "--cov=src --cov-report term-missing"
+testpaths = ["tests"]
+
+[tool.coverage.run]
+branch = true
+
+[tool.ruff]
+src = ["src"]
+exclude = ["docs/source/conf.py"]
+# pycodestyle (E, W)
+# Pyflakes (F)
+# flake8-annotations (ANN)
+# pydocstyle (D)
+# pep8-naming (N)
+# isort (I)
+select = ["E", "W", "F", "ANN", "D", "N", "I"]
+fixable = ["I", "F401"]
+
+# ANN101 - missing-type-self
+# ANN003 - missing-type-kwargs
+# D203 - one-blank-line-before-class
+# D205 - blank-line-after-summary
+# D206 - indent-with-spaces*
+# D213 - multi-line-summary-second-line
+# D300 - triple-single-quotes*
+# D400 - ends-in-period
+# D415 - ends-in-punctuation
+# E111 - indentation-with-invalid-multiple*
+# E114 - indentation-with-invalid-multiple-comment*
+# E117 - over-indented*
+# E501 - line-too-long*
+# W191 - tab-indentation*
+# *ignored for compatibility with formatter
+ignore = [
+    "ANN101", "ANN003",
+    "D203", "D205", "D206", "D213", "D300", "D400", "D415",
+    "E111", "E114", "E117", "E501",
+    "W191"
+]
+
+[tool.ruff.per-file-ignores]
+# ANN001 - missing-type-function-argument
+# ANN2 - missing-return-type
+# ANN102 - missing-type-cls
+# N805 - invalid-first-argument-name-for-method
+# F821 - undefined-name
+# F401 - unused-import
+"tests/*" = ["ANN001", "ANN2", "ANN102"]
+"*__init__.py" = ["F401"]
+"src/cool_seq_tool/schemas.py" = ["ANN201", "N805", "ANN001"]

cool_seq_tool-0.4.0.dev0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

{cool_seq_tool-0.3.0.dev0 → cool_seq_tool-0.4.0.dev0/src}/cool_seq_tool/api.py

@@ -24,16 +24,16 @@ def custom_openapi() -> Dict:
     if app.openapi_schema:
         return app.openapi_schema
     openapi_schema = get_openapi(
-        title="The GenomicMedLab Cool Seq Tool",
+        title="The GenomicMedLab Cool-Seq-Tool",
         version=__version__,
-        description="Common Operations On Lots-of Sequences Tool.",
+        description="Common Operations On Lots of Sequences Tool.",
         routes=app.routes,
     )
 
     openapi_schema["info"]["contact"] = {
         "name": "Alex H. Wagner",
         "email": "Alex.Wagner@nationwidechildrens.org",
-        "url": "https://www.nationwidechildrens.org/specialties/institute-for-genomic-medicine/research-labs/wagner-lab",  # noqa: E501
+        "url": "https://www.nationwidechildrens.org/specialties/institute-for-genomic-medicine/research-labs/wagner-lab",
     }
     app.openapi_schema = openapi_schema
     return app.openapi_schema

cool_seq_tool-0.4.0.dev0/src/cool_seq_tool/app.py

@@ -0,0 +1,90 @@
+"""Provides core CoolSeqTool class, which non-redundantly initializes all Cool-Seq-Tool
+data handler and mapping resources for straightforward access.
+"""
+import logging
+from pathlib import Path
+from typing import Optional
+
+from biocommons.seqrepo import SeqRepo
+
+from cool_seq_tool.handlers.seqrepo_access import SeqRepoAccess
+from cool_seq_tool.mappers import (
+    AlignmentMapper,
+    ExonGenomicCoordsMapper,
+    ManeTranscript,
+)
+from cool_seq_tool.paths import (
+    LRG_REFSEQGENE_PATH,
+    MANE_SUMMARY_PATH,
+    SEQREPO_ROOT_DIR,
+    TRANSCRIPT_MAPPINGS_PATH,
+)
+from cool_seq_tool.sources.mane_transcript_mappings import ManeTranscriptMappings
+from cool_seq_tool.sources.transcript_mappings import TranscriptMappings
+from cool_seq_tool.sources.uta_database import UTA_DB_URL, UtaDatabase
+
+logger = logging.getLogger(__name__)
+
+
+class CoolSeqTool:
+    """Non-redundantly initialize all Cool-Seq-Tool data resources, available under the
+    following attribute names:
+
+    * ``self.seqrepo_access``: :py:class:`SeqRepoAccess <cool_seq_tool.handlers.seqrepo_access.SeqRepoAccess>`
+    * ``self.transcript_mappings``: :py:class:`TranscriptMappings <cool_seq_tool.sources.transcript_mappings.TranscriptMappings>`
+    * ``self.mane_transcript_mappings``: :py:class:`ManeTranscriptMappings <cool_seq_tool.sources.mane_transcript_mappings.ManeTranscriptMappings>`
+    * ``self.uta_db``: :py:class:`UtaDatabase <cool_seq_tool.sources.uta_database.UtaDatabase>`
+    * ``self.alignment_mapper``: :py:class:`AlignmentMapper <cool_seq_tool.mappers.alignment.AlignmentMapper>`
+    * ``self.mane_transcript``: :py:class:`ManeTranscript <cool_seq_tool.mappers.mane_transcript.ManeTranscript>`
+    * ``self.ex_g_coords_mapper``: :py:class:`ExonGenomicCoordsMapper <cool_seq_tool.mappers.exon_genomic_coords.ExonGenomicCoordsMapper>`
+
+    Initialization with default resource locations is straightforward:
+
+    .. code-block:: pycon
+
+       >>> from cool_seq_tool.app import CoolSeqTool
+       >>> cst = CoolSeqTool()
+
+    See the :ref:`configuration <configuration>` section for more information.
+    """
+
+    def __init__(
+        self,
+        transcript_file_path: Path = TRANSCRIPT_MAPPINGS_PATH,
+        lrg_refseqgene_path: Path = LRG_REFSEQGENE_PATH,
+        mane_data_path: Path = MANE_SUMMARY_PATH,
+        db_url: str = UTA_DB_URL,
+        sr: Optional[SeqRepo] = None,
+    ) -> None:
+        """Initialize CoolSeqTool class
+
+        :param transcript_file_path: The path to ``transcript_mapping.tsv``
+        :param lrg_refseqgene_path: The path to the LRG_RefSeqGene file
+        :param mane_data_path: Path to RefSeq MANE summary data
+        :param db_url: PostgreSQL connection URL
+            Format: ``driver://user:password@host/database/schema``
+        :param sr: SeqRepo instance. If this is not provided, will create a new instance
+        """
+        if not sr:
+            sr = SeqRepo(root_dir=SEQREPO_ROOT_DIR)
+        self.seqrepo_access = SeqRepoAccess(sr)
+        self.transcript_mappings = TranscriptMappings(
+            transcript_file_path=transcript_file_path,
+            lrg_refseqgene_path=lrg_refseqgene_path,
+        )
+        self.mane_transcript_mappings = ManeTranscriptMappings(
+            mane_data_path=mane_data_path
+        )
+        self.uta_db = UtaDatabase(db_url=db_url)
+        self.alignment_mapper = AlignmentMapper(
+            self.seqrepo_access, self.transcript_mappings, self.uta_db
+        )
+        self.mane_transcript = ManeTranscript(
+            self.seqrepo_access,
+            self.transcript_mappings,
+            self.mane_transcript_mappings,
+            self.uta_db,
+        )
+        self.ex_g_coords_mapper = ExonGenomicCoordsMapper(
+            self.uta_db, self.mane_transcript
+        )

{cool_seq_tool-0.3.0.dev0 → cool_seq_tool-0.4.0.dev0/src}/cool_seq_tool/data/data_downloads.py

@@ -1,4 +1,4 @@
-"""Module for handling downloadable data files."""
+"""Handle acquisition of external data."""
 import datetime
 import gzip
 import logging
@@ -15,8 +15,11 @@ logger = logging.getLogger("cool_seq_tool")
 
 
 class DataDownload:
-    """Class for managing downloadable data files. Responsible for checking if files
-    are available under default locations, and fetching them if not.
+    """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:
@@ -25,7 +28,7 @@ class DataDownload:
 
     def get_mane_summary(self) -> Path:
         """Identify latest MANE summary data. If unavailable locally, download from
-        source.
+        `NCBI FTP server <https://ftp.ncbi.nlm.nih.gov/refseq/MANE/MANE_human/current/>`_.
 
         :return: path to MANE summary file
         """
@@ -52,7 +55,7 @@ class DataDownload:
 
     def get_lrg_refseq_gene_data(self) -> Path:
         """Identify latest LRG RefSeq Gene file. If unavailable locally, download from
-        source.
+        `NCBI FTP server <https://ftp.ncbi.nlm.nih.gov/refseq/H_sapiens/RefSeqGene/>`_.
 
         :return: path to acquired LRG RefSeq Gene data file
         """

{cool_seq_tool-0.3.0.dev0 → cool_seq_tool-0.4.0.dev0/src}/cool_seq_tool/handlers/seqrepo_access.py

@@ -1,4 +1,6 @@
-"""A module for accessing SeqRepo."""
+"""Wrap SeqRepo to provide additional lookup and identification methods on top of basic
+dereferencing functions.
+"""
 import logging
 from os import environ
 from pathlib import Path
@@ -13,7 +15,9 @@ logger = logging.getLogger(__name__)
 
 
 class SeqRepoAccess(SeqRepoDataProxy):
-    """The SeqRepoAccess class."""
+    """Provide a wrapper around the base SeqRepoDataProxy class from ``VRS-Python`` to
+    provide additional lookup and identification methods.
+    """
 
     environ["SEQREPO_LRU_CACHE_MAXSIZE"] = "none"
 
@@ -24,25 +28,37 @@ class SeqRepoAccess(SeqRepoDataProxy):
         end: Optional[int] = None,
         residue_mode: ResidueMode = ResidueMode.RESIDUE,
     ) -> Tuple[str, Optional[str]]:
-        """Get reference sequence for an accession given a start and end position.
-        If `start` and `end` are not given, it will return the entire reference sequence
+        """Get reference sequence for an accession given a start and end position. If
+        ``start`` and ``end`` are not given, returns the entire reference sequence.
+
+        >>> from cool_seq_tool.handlers import SeqRepoAccess
+        >>> from biocommons.seqrepo import SeqRepo
+        >>> sr = SeqRepoAccess(SeqRepo("/usr/local/share/seqrepo/latest"))
+        >>> sr.get_reference_sequence("NM_002529.3", 1, 10)[0]
+        'TGCAGCTGG'
+        >>> sr.get_reference_sequence("NP_001341538.1", 1, 10)[0]
+        'MAALSGGGG'
 
         :param ac: Accession
         :param start: Start pos change
-        :param end: End pos change. If `None` assumes both `start` and `end` have same
-            values, if `start` exists.
-        :param residue_mode: Residue mode for `start` and `end`
+        :param end: End pos change. If ``None`` assumes both ``start`` and ``end`` have
+            same values, if ``start`` exists.
+        :param residue_mode: Residue mode for ``start`` and ``end``
         :return: Sequence at position (if accession and positions actually
             exist, else return empty string), warning if any
         """
-        if start or end:
-            pos, warning = get_inter_residue_pos(start, residue_mode, end_pos=end)
-            if pos is None:
-                return "", warning
-            else:
-                start, end = pos
-                if start == end:
-                    end += 1
+        if start and end:
+            if start > end:
+                msg = f"start ({start}) cannot be greater than end ({end})"
+                return "", msg
+
+            start, end = get_inter_residue_pos(start, end, residue_mode)
+            if start == end:
+                end += 1
+        else:
+            if start is not None and residue_mode == ResidueMode.RESIDUE:
+                start -= 1
+
         try:
             sequence = self.sr.fetch(ac, start=start, end=end)
         except KeyError:
@@ -53,18 +69,12 @@ class SeqRepoAccess(SeqRepoDataProxy):
             error = str(e)
             if error.startswith("start out of range"):
                 msg = (
-                    f"Start inter-residue coordinate ({start}) is out of "
-                    f"index on {ac}"
+                    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}"
                 )
-            elif error.startswith("invalid coordinates") and ">" in error:
-                msg = (
-                    f"Invalid inter-residue coordinates: start ({start}) "
-                    f"cannot be greater than end ({end})"
-                )
             else:
                 msg = f"{e}"
             logger.warning(msg)
@@ -78,8 +88,7 @@ class SeqRepoAccess(SeqRepoDataProxy):
                 if len(sequence) != expected_len_of_seq:
                     return (
                         "",
-                        f"End inter-residue coordinate ({end})"
-                        f" is out of index on {ac}",
+                        f"End inter-residue coordinate ({end}) is out of index on {ac}",
                     )
             return sequence, None
 
@@ -88,6 +97,14 @@ class SeqRepoAccess(SeqRepoDataProxy):
     ) -> Tuple[List[str], Optional[str]]:
         """Return list of identifiers for accession.
 
+        >>> from cool_seq_tool.handlers import SeqRepoAccess
+        >>> from biocommons.seqrepo import SeqRepo
+        >>> sr = SeqRepoAccess(SeqRepo("/usr/local/share/seqrepo/latest"))
+        >>> sr.translate_identifier("NM_002529.3")[0]
+        ['MD5:18f0a6e3af9e1bbd8fef1948c7156012', 'NCBI:NM_002529.3', 'refseq:NM_002529.3', 'SEGUID:dEJQBkga9d9VeBHTyTbg6JEtTGQ', 'SHA1:74425006481af5df557811d3c936e0e8912d4c64', 'VMC:GS_RSkww1aYmsMiWbNdNnOTnVDAM3ZWp1uA', 'sha512t24u:RSkww1aYmsMiWbNdNnOTnVDAM3ZWp1uA', 'ga4gh:SQ.RSkww1aYmsMiWbNdNnOTnVDAM3ZWp1uA']
+        >>> sr.translate_identifier("NM_002529.3", "ga4gh")[0]
+        ['ga4gh:SQ.RSkww1aYmsMiWbNdNnOTnVDAM3ZWp1uA']
+
         :param ac: Identifier accession
         :param target_namespace: The namespace(s) of identifier to return
         :return: List of identifiers, warning
@@ -123,7 +140,7 @@ class SeqRepoAccess(SeqRepoDataProxy):
     ) -> Tuple[Optional[List[str]], Optional[str]]:
         """Get accessions for a chromosome
 
-        :param str chromosome: Chromosome number. Must be either 1-22, X, or Y
+        :param chromosome: Chromosome number. Must be either 1-22, X, or Y
         :return: Accessions for chromosome (ordered by latest assembly)
         """
         acs = []
@@ -160,9 +177,20 @@ class SeqRepoAccess(SeqRepoDataProxy):
 
     def get_fasta_file(self, sequence_id: str, outfile_path: Path) -> None:
         """Retrieve FASTA file containing sequence for requested sequence ID.
-        :param sequence_id: accession ID, sans namespace, eg `NM_152263.3`
+
+        >>> from pathlib import Path
+        >>> from cool_seq_tool.handlers import SeqRepoAccess
+        >>> from biocommons.seqrepo import SeqRepo
+        >>> sr = SeqRepoAccess(SeqRepo("/usr/local/share/seqrepo/latest"))
+        >>> # write to local file tpm3.fasta:
+        >>> sr.get_fasta_file("NM_002529.3", Path("tpm3.fasta"))
+
+        FASTA file headers will include GA4GH sequence digest, Ensembl accession ID,
+        and RefSeq accession ID.
+
+        :param sequence_id: accession ID, sans namespace, eg ``NM_152263.3``
         :param outfile_path: path to save file to
-        :return: None, but saves sequence data to `outfile_path` if successful
+        :return: None, but saves sequence data to ``outfile_path`` if successful
         :raise: KeyError if SeqRepo doesn't have sequence data for the given ID
         """
         sequence = self.get_reference_sequence(sequence_id)[0]

{cool_seq_tool-0.3.0.dev0 → cool_seq_tool-0.4.0.dev0/src}/cool_seq_tool/mappers/__init__.py

@@ -1,4 +1,7 @@
 """Module for mapping data"""
 from .alignment import AlignmentMapper  # noqa: I001
-from .mane_transcript import MANETranscript
+from .mane_transcript import ManeTranscript
 from .exon_genomic_coords import ExonGenomicCoordsMapper
+
+
+__all__ = ["AlignmentMapper", "ManeTranscript", "ExonGenomicCoordsMapper"]