cool-seq-tool 0.6.0__tar.gz → 0.7.1__tar.gz

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cool_seq_tool
-Version: 0.6.0
+Version: 0.7.1
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -52,7 +52,7 @@ Requires-Dist: polars~=1.0
 Requires-Dist: hgvs
 Requires-Dist: biocommons.seqrepo
 Requires-Dist: pydantic==2.*
-Requires-Dist: ga4gh.vrs
+Requires-Dist: ga4gh.vrs~=2.0.0a10
 Requires-Dist: wags-tails~=0.1.3
 Requires-Dist: bioutils
 Provides-Extra: dev
@@ -83,7 +83,7 @@ CoolSeqTool
 
 ---
 
-**[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)
+**[Documentation](https://coolseqtool.readthedocs.io/stable/)** · [Installation](https://coolseqtool.readthedocs.io/stable/install.html) · [Usage](https://coolseqtool.readthedocs.io/stable/usage.html) · [API reference](https://coolseqtool.readthedocs.io/stable/reference/index.html)
 
 ---
 
@@ -107,7 +107,7 @@ CoolSeqTool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
 python3 -m pip install cool-seq-tool
 ```
 
-See the [installation instructions](https://coolseqtool.readthedocs.io/latest/install.html) in the documentation for a description of dependency setup requirements.
+See the [installation instructions](https://coolseqtool.readthedocs.io/stable/install.html) in the documentation for a description of dependency setup requirements.
 
 ---
 
@@ -116,14 +116,14 @@ See the [installation instructions](https://coolseqtool.readthedocs.io/latest/in
 All CoolSeqTool resources can be initialized by way of a top-level class instance:
 
 ```pycon
->>> from cool_seq_tool.app import CoolSeqTool
->>> from cool_seq_tool.schemas import AnnotationLayer, ResidueMode
+>>> from cool_seq_tool import CoolSeqTool
+>>> from cool_seq_tool.schemas import AnnotationLayer, CoordinateType
 >>> cst = CoolSeqTool()
 >>> result = await cst.mane_transcript.get_mane_transcript(
 ...     "NP_004324.2",
 ...     599,
 ...     AnnotationLayer.PROTEIN,
-...     residue_mode=ResidueMode.INTER_RESIDUE,
+...     coordinate_type=CoordinateType.INTER_RESIDUE,
 ... )
 >>> result.gene, result.refseq, result.status
 ('EGFR', 'NM_005228.5', <TranscriptPriority.MANE_SELECT: 'mane_select'>)
@@ -133,4 +133,4 @@ All CoolSeqTool resources can be initialized by way of a top-level class instanc
 
 ## Feedback and contributing
 
-We welcome bug reports, feature requests, and code contributions from users and interested collaborators. The [documentation](https://coolseqtool.readthedocs.io/latest/contributing.html) contains guidance for submitting feedback and contributing new code.
+We welcome bug reports, feature requests, and code contributions from users and interested collaborators. The [documentation](https://coolseqtool.readthedocs.io/stable/contributing.html) contains guidance for submitting feedback and contributing new code.

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/README.md

@@ -6,7 +6,7 @@ CoolSeqTool
 
 ---
 
-**[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)
+**[Documentation](https://coolseqtool.readthedocs.io/stable/)** · [Installation](https://coolseqtool.readthedocs.io/stable/install.html) · [Usage](https://coolseqtool.readthedocs.io/stable/usage.html) · [API reference](https://coolseqtool.readthedocs.io/stable/reference/index.html)
 
 ---
 
@@ -30,7 +30,7 @@ CoolSeqTool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
 python3 -m pip install cool-seq-tool
 ```
 
-See the [installation instructions](https://coolseqtool.readthedocs.io/latest/install.html) in the documentation for a description of dependency setup requirements.
+See the [installation instructions](https://coolseqtool.readthedocs.io/stable/install.html) in the documentation for a description of dependency setup requirements.
 
 ---
 
@@ -39,14 +39,14 @@ See the [installation instructions](https://coolseqtool.readthedocs.io/latest/in
 All CoolSeqTool resources can be initialized by way of a top-level class instance:
 
 ```pycon
->>> from cool_seq_tool.app import CoolSeqTool
->>> from cool_seq_tool.schemas import AnnotationLayer, ResidueMode
+>>> from cool_seq_tool import CoolSeqTool
+>>> from cool_seq_tool.schemas import AnnotationLayer, CoordinateType
 >>> cst = CoolSeqTool()
 >>> result = await cst.mane_transcript.get_mane_transcript(
 ...     "NP_004324.2",
 ...     599,
 ...     AnnotationLayer.PROTEIN,
-...     residue_mode=ResidueMode.INTER_RESIDUE,
+...     coordinate_type=CoordinateType.INTER_RESIDUE,
 ... )
 >>> result.gene, result.refseq, result.status
 ('EGFR', 'NM_005228.5', <TranscriptPriority.MANE_SELECT: 'mane_select'>)
@@ -56,4 +56,4 @@ All CoolSeqTool resources can be initialized by way of a top-level class instanc
 
 ## Feedback and contributing
 
-We welcome bug reports, feature requests, and code contributions from users and interested collaborators. The [documentation](https://coolseqtool.readthedocs.io/latest/contributing.html) contains guidance for submitting feedback and contributing new code.
+We welcome bug reports, feature requests, and code contributions from users and interested collaborators. The [documentation](https://coolseqtool.readthedocs.io/stable/contributing.html) contains guidance for submitting feedback and contributing new code.

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/docs/source/conf.py

@@ -72,7 +72,7 @@ def linkcode_resolve(domain, info):
     if not info["module"]:
         return None
     filename = info["module"].replace(".", "/")
-    return f"https://github.com/genomicmedlab/cool-seq-tool/blob/main/{filename}.py"  # noqa: E501
+    return f"https://github.com/genomicmedlab/cool-seq-tool/blob/main/src/{filename}.py"
 
 
 # -- code block style --------------------------------------------------------
@@ -87,16 +87,16 @@ from sphinx.ext.autodoc import Options
 
 
 def _clip_rst_tables(app: Sphinx, what: str, name: str, obj: ModuleType, options: Options, lines: List[str]):
-    """The ResidueMode docstring contains an RST table and an ASCII table because
+    """The CoordinateType docstring contains an RST table and an ASCII table because
     the former gets omitted in IDEs like VSCode and the latter won't render properly in
     Sphinx docs. This chops out the ASCII table when rendering autodocs.
     """
-    if what == "class" and name == "cool_seq_tool.schemas.ResidueMode":
+    if what == "class" and name == "cool_seq_tool.schemas.CoordinateType":
         for i in range(len(lines) -1, -1, -1):
             line = lines[i]
             if line.count("|") >= 8:
                 del lines[i]
-        print("Running preprocessing on ResidueMode docstring...")
+        print("Running preprocessing on CoordinateType docstring...")
 
 def setup(app: Sphinx):
     app.connect("autodoc-process-docstring", _clip_rst_tables)

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/docs/source/usage.rst

@@ -15,7 +15,7 @@ The core :py:class:`CoolSeqTool <cool_seq_tool.app.CoolSeqTool>` class encapsula
 
 .. code-block:: pycon
 
-   >>> from cool_seq_tool.app import CoolSeqTool
+   >>> from cool_seq_tool import CoolSeqTool
    >>> cst = CoolSeqTool()
    >>> cst.seqrepo_access.translate_alias("NM_002529.3")[0][-1]
    'ga4gh:SQ.RSkww1aYmsMiWbNdNnOTnVDAM3ZWp1uA'
@@ -34,7 +34,7 @@ Descriptions and examples of functions can be found in the :ref:`API Reference <
 
    .. code-block:: python
 
-       from cool_seq_tool.app import CoolSeqTool
+       from cool_seq_tool import CoolSeqTool
 
        async def do_thing():
            mane_mapper = CoolSeqTool().mane_transcript
@@ -50,7 +50,7 @@ Descriptions and examples of functions can be found in the :ref:`API Reference <
    .. code-block:: pycon
 
       >>> import asyncio
-      >>> from cool_seq_tool.app import cool_seq_tool
+      >>> from cool_seq_tool import cool_seq_tool
       >>> mane_mapper = CoolSeqTool().mane_transcript
       >>> result = asyncio.run(mane_mapper.g_to_grch38("NC_000001.11", 100, 200))
       >>> print(result)
@@ -85,8 +85,3 @@ Individual classes will accept arguments upon initialization to set parameters r
      - A path to a `chainfile <https://genome.ucsc.edu/goldenPath/help/chain.html>`_ for lifting from GRCh37 to GRCh38. Used by the :py:class:`LiftOver <cool_seq_tool.mappers.liftover.LiftOver>` class as input to `agct <https://pypi.org/project/agct/>`_. If not provided, agct will fetch it automatically from UCSC.
    * - ``LIFTOVER_CHAIN_38_TO_37``
      - A path to a `chainfile <https://genome.ucsc.edu/goldenPath/help/chain.html>`_ for lifting from GRCh38 to GRCh37. Used by the :py:class:`LiftOver <cool_seq_tool.mappers.liftover.LiftOver>` class as input to `agct <https://pypi.org/project/agct/>`_. If not provided, agct will fetch it automatically from UCSC.
-
-Schema support
---------------
-
-Many genomic data objects produced by Cool-Seq-Tool are structured in conformance with the `Variation Representation Specification <https://vrs.ga4gh.org/en/stable/>`_, courtesy of the `VRS-Python <https://github.com/ga4gh/vrs-python>`_ library.

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/pyproject.toml

@@ -32,7 +32,7 @@ dependencies = [
     "hgvs",
     "biocommons.seqrepo",
     "pydantic == 2.*",
-    "ga4gh.vrs",
+    "ga4gh.vrs ~= 2.0.0a10",
     "wags-tails ~= 0.1.3",
     "bioutils",
 ]

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/src/cool_seq_tool/__init__.py

@@ -8,3 +8,9 @@ except PackageNotFoundError:
     __version__ = "unknown"
 finally:
     del version, PackageNotFoundError
+
+
+# must import after __version__ declaration to prevent ImportError
+from cool_seq_tool.app import CoolSeqTool
+
+__all__ = ["CoolSeqTool", "__version__"]

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/src/cool_seq_tool/app.py

@@ -48,7 +48,7 @@ class CoolSeqTool:
 
         Initialization with default resource locations is straightforward:
 
-        >>> from cool_seq_tool.app import CoolSeqTool
+        >>> from cool_seq_tool import CoolSeqTool
         >>> cst = CoolSeqTool()
 
         By default, this will attempt to fetch the latest versions of static resources,
@@ -107,7 +107,6 @@ 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-0.6.0 → cool_seq_tool-0.7.1}/src/cool_seq_tool/handlers/seqrepo_access.py

@@ -8,7 +8,7 @@ from pathlib import Path
 
 from ga4gh.vrs.dataproxy import SeqRepoDataProxy
 
-from cool_seq_tool.schemas import Assembly, ResidueMode
+from cool_seq_tool.schemas import Assembly, CoordinateType
 from cool_seq_tool.utils import get_inter_residue_pos, process_chromosome_input
 
 _logger = logging.getLogger(__name__)
@@ -29,7 +29,7 @@ class SeqRepoAccess(SeqRepoDataProxy):
         ac: str,
         start: int | None = None,
         end: int | None = None,
-        residue_mode: ResidueMode = ResidueMode.RESIDUE,
+        coordinate_type: CoordinateType = CoordinateType.RESIDUE,
     ) -> tuple[str, str | None]:
         """Get reference sequence for an accession given a start and end position. If
         ``start`` and ``end`` are not given, returns the entire reference sequence.
@@ -46,7 +46,7 @@ class SeqRepoAccess(SeqRepoDataProxy):
         :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 coordinate_type: Coordinate type for ``start`` and ``end``
         :return: Sequence at position (if accession and positions actually
             exist, else return empty string), warning if any
         """
@@ -55,11 +55,11 @@ class SeqRepoAccess(SeqRepoDataProxy):
                 msg = f"start ({start}) cannot be greater than end ({end})"
                 return "", msg
 
-            start, end = get_inter_residue_pos(start, end, residue_mode)
+            start, end = get_inter_residue_pos(start, end, coordinate_type)
             if start == end:
                 end += 1
         else:
-            if start is not None and residue_mode == ResidueMode.RESIDUE:
+            if start is not None and coordinate_type == CoordinateType.RESIDUE:
                 start -= 1
 
         try:

{cool_seq_tool-0.6.0 → cool_seq_tool-0.7.1}/src/cool_seq_tool/mappers/alignment.py

@@ -3,7 +3,7 @@ reference sequences.
 """
 
 from cool_seq_tool.handlers.seqrepo_access import SeqRepoAccess
-from cool_seq_tool.schemas import AnnotationLayer, Assembly, ResidueMode
+from cool_seq_tool.schemas import AnnotationLayer, Assembly, CoordinateType
 from cool_seq_tool.sources import TranscriptMappings, UtaDatabase
 
 
@@ -32,14 +32,14 @@ class AlignmentMapper:
         p_ac: str,
         p_start_pos: int,
         p_end_pos: int,
-        residue_mode: ResidueMode = ResidueMode.RESIDUE,
+        coordinate_type: CoordinateType = CoordinateType.RESIDUE,
     ) -> tuple[dict | None, str | None]:
         """Translate protein representation to cDNA representation.
 
         :param p_ac: Protein RefSeq accession
         :param p_start_pos: Protein start position
         :param p_end_pos: Protein end position
-        :param residue_mode: Residue mode for ``p_start_pos`` and ``p_end_pos``
+        :param coordinate_type: Coordinate type for ``p_start_pos`` and ``p_end_pos``
         :return: Tuple containing:
 
         * cDNA representation (accession, codon range positions for corresponding
@@ -66,7 +66,7 @@ class AlignmentMapper:
         # 1 amino acid maps to 3 nucleotides in the codon
         # Since we have the end of the codon, we will subtract 2 to get the start of the
         # codon. We want to return inter-residue (0-based), so we subtract 1 from this.
-        if residue_mode == ResidueMode.RESIDUE:
+        if coordinate_type == CoordinateType.RESIDUE:
             c_pos = (p_start_pos * 3) - 3, p_end_pos * 3
         else:
             if p_start_pos == p_end_pos:
@@ -79,7 +79,7 @@ class AlignmentMapper:
             "c_start_pos": c_pos[0],
             "c_end_pos": c_pos[1],
             "cds_start": cds_start,
-            "residue_mode": ResidueMode.INTER_RESIDUE.value,
+            "coordinate_type": CoordinateType.INTER_RESIDUE.value,
         }, None
 
     async def _get_cds_start(self, c_ac: str) -> tuple[int | None, str | None]:
@@ -105,7 +105,7 @@ class AlignmentMapper:
         c_start_pos: int,
         c_end_pos: int,
         cds_start: int | None = None,
-        residue_mode: ResidueMode = ResidueMode.RESIDUE,
+        coordinate_type: CoordinateType = CoordinateType.RESIDUE,
         target_genome_assembly: bool = Assembly.GRCH38,
     ) -> tuple[dict | None, str | None]:
         """Translate cDNA representation to genomic representation
@@ -125,9 +125,9 @@ class AlignmentMapper:
         if any(
             (
                 c_start_pos == c_end_pos,
-                (residue_mode == ResidueMode.INTER_RESIDUE)
+                (coordinate_type == CoordinateType.INTER_RESIDUE)
                 and ((c_end_pos - c_start_pos) % 3 != 0),
-                (residue_mode == ResidueMode.RESIDUE)
+                (coordinate_type == CoordinateType.RESIDUE)
                 and ((c_end_pos - (c_start_pos - 1)) % 3 != 0),
             )
         ):
@@ -146,7 +146,7 @@ class AlignmentMapper:
                 return None, warning
 
         # Change to inter-residue
-        if residue_mode == ResidueMode.RESIDUE:
+        if coordinate_type == CoordinateType.RESIDUE:
             c_start_pos -= 1
 
         # Get aligned genomic and transcript data
@@ -163,7 +163,7 @@ class AlignmentMapper:
                 f"position ({c_start_pos}, {c_end_pos})"
             )
         else:
-            alt_ac = genomic_tx_data["alt_ac"]
+            alt_ac = genomic_tx_data.alt_ac
 
             # Validate that genomic accession assembly == target_genome_assembly
             aliases, _ = self.seqrepo_access.translate_identifier(alt_ac)
@@ -180,7 +180,7 @@ class AlignmentMapper:
                             f"{target_genome_assembly}"
                         )
                     else:
-                        g_pos = genomic_tx_data["alt_pos_change_range"]
+                        g_pos = genomic_tx_data.alt_pos_change_range
 
                         # start pos should be less than end pos in response
                         if g_pos[0] > g_pos[1]:
@@ -194,7 +194,7 @@ class AlignmentMapper:
                             "g_ac": alt_ac,
                             "g_start_pos": g_start_pos,
                             "g_end_pos": g_end_pos,
-                            "residue_mode": ResidueMode.INTER_RESIDUE.value,
+                            "coordinate_type": CoordinateType.INTER_RESIDUE.value,
                         }
             else:
                 warning = (
@@ -209,7 +209,7 @@ class AlignmentMapper:
         p_ac: str,
         p_start_pos: int,
         p_end_pos: int,
-        residue_mode: ResidueMode = ResidueMode.INTER_RESIDUE,
+        coordinate_type: CoordinateType = CoordinateType.INTER_RESIDUE,
         target_genome_assembly: Assembly = Assembly.GRCH38,
     ) -> tuple[dict | None, str | None]:
         """Translate protein representation to genomic representation, by way of
@@ -218,7 +218,7 @@ class AlignmentMapper:
         :param p_ac: Protein RefSeq accession
         :param p_start_pos: Protein start position
         :param p_end_pos: Protein end position
-        :param residue_mode: Residue mode for ``p_start_pos`` and ``p_end_pos``.
+        :param coordinate_type: Coordinate type for ``p_start_pos`` and ``p_end_pos``.
         :param target_genome_assembly: Genome assembly to get genomic data for
         :return: Tuple containing:
 
@@ -227,7 +227,7 @@ class AlignmentMapper:
         * Warnings, if conversion to cDNA or genomic coordinates fails.
         """
         c_data, warning = await self.p_to_c(
-            p_ac, p_start_pos, p_end_pos, residue_mode=residue_mode
+            p_ac, p_start_pos, p_end_pos, coordinate_type=coordinate_type
         )
         if not c_data:
             return None, warning
@@ -238,7 +238,7 @@ class AlignmentMapper:
             c_data["c_start_pos"],
             c_data["c_end_pos"],
             c_data["cds_start"],
-            residue_mode=ResidueMode.INTER_RESIDUE,
+            coordinate_type=CoordinateType.INTER_RESIDUE,
             target_genome_assembly=target_genome_assembly,
         )
         return g_data, warning