cool-seq-tool 0.8.0__tar.gz → 0.9.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/PKG-INFO +15 -15
- cool_seq_tool-0.9.0/README.md +59 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/contributing.rst +1 -1
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/index.rst +4 -4
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/install.rst +1 -1
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/transcript_selection.rst +4 -3
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/usage.rst +1 -1
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/pyproject.toml +2 -2
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/mappers/exon_genomic_coords.py +21 -2
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool.egg-info/PKG-INFO +15 -15
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool.egg-info/SOURCES.txt +0 -1
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool.egg-info/requires.txt +2 -2
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/conftest.py +15 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/mappers/test_exon_genomic_coords.py +39 -1
- cool_seq_tool-0.8.0/.github/workflows/close_issue.yml +0 -18
- cool_seq_tool-0.8.0/README.md +0 -59
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.coveragerc +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.github/ISSUE_TEMPLATE/bug-report.yaml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.github/ISSUE_TEMPLATE/feature-request.yaml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.github/workflows/checks.yaml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.github/workflows/pr-priority-label.yaml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.github/workflows/release.yml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.github/workflows/stale.yaml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.gitignore +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.pre-commit-config.yaml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/.readthedocs.yaml +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/CITATION.cff +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/LICENSE +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/Makefile +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/make.bat +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/_static/img/biomart.png +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/_templates/module_summary.rst +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/changelog.rst +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/conf.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/license.rst +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/docs/source/reference/index.rst +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/setup.cfg +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/__init__.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/app.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/handlers/__init__.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/handlers/seqrepo_access.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/mappers/__init__.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/mappers/alignment.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/mappers/liftover.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/mappers/mane_transcript.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/resources/__init__.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/resources/data_files.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/resources/status.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/resources/transcript_mapping.tsv +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/schemas.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/sources/__init__.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/sources/mane_transcript_mappings.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/sources/transcript_mappings.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/sources/uta_database.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/utils.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool.egg-info/dependency_links.txt +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool.egg-info/top_level.txt +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/handlers/test_seqrepo_access.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/mappers/test_alignment.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/mappers/test_liftover.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/mappers/test_mane_transcript.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/sources/test_mane_transcript_mappings.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/sources/test_uta_database.py +0 -0
- {cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/tests/test_utils.py +0 -0
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: cool_seq_tool
|
3
|
-
Version: 0.
|
3
|
+
Version: 0.9.0
|
4
4
|
Summary: Common Operation on Lots of Sequences Tool
|
5
5
|
Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
|
6
6
|
License: MIT License
|
@@ -53,7 +53,7 @@ Requires-Dist: hgvs
|
|
53
53
|
Requires-Dist: biocommons.seqrepo
|
54
54
|
Requires-Dist: pydantic==2.*
|
55
55
|
Requires-Dist: ga4gh.vrs~=2.0.0a10
|
56
|
-
Requires-Dist: wags-tails~=0.
|
56
|
+
Requires-Dist: wags-tails~=0.2.2
|
57
57
|
Requires-Dist: bioutils
|
58
58
|
Provides-Extra: dev
|
59
59
|
Requires-Dist: pre-commit>=3.7.1; extra == "dev"
|
@@ -61,11 +61,11 @@ Requires-Dist: ipython; extra == "dev"
|
|
61
61
|
Requires-Dist: ipykernel; extra == "dev"
|
62
62
|
Requires-Dist: psycopg2-binary; extra == "dev"
|
63
63
|
Requires-Dist: ruff==0.5.0; extra == "dev"
|
64
|
-
Provides-Extra:
|
65
|
-
Requires-Dist: pytest; extra == "
|
66
|
-
Requires-Dist: pytest-cov; extra == "
|
67
|
-
Requires-Dist: pytest-asyncio==0.18.3; extra == "
|
68
|
-
Requires-Dist: mock; extra == "
|
64
|
+
Provides-Extra: tests
|
65
|
+
Requires-Dist: pytest; extra == "tests"
|
66
|
+
Requires-Dist: pytest-cov; extra == "tests"
|
67
|
+
Requires-Dist: pytest-asyncio==0.18.3; extra == "tests"
|
68
|
+
Requires-Dist: mock; extra == "tests"
|
69
69
|
Provides-Extra: docs
|
70
70
|
Requires-Dist: sphinx==6.1.3; extra == "docs"
|
71
71
|
Requires-Dist: sphinx-autodoc-typehints==1.22.0; extra == "docs"
|
@@ -76,10 +76,10 @@ Requires-Dist: furo==2023.3.27; extra == "docs"
|
|
76
76
|
Requires-Dist: sphinx-github-changelog==1.2.1; extra == "docs"
|
77
77
|
|
78
78
|
<h1 align="center">
|
79
|
-
|
79
|
+
Cool-Seq-Tool
|
80
80
|
</h1>
|
81
81
|
|
82
|
-
[](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
|
82
|
+
[](https://pypi.python.org/pypi/cool-seq-tool) [](https://doi.org/10.5281/zenodo.14007783) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
|
83
83
|
|
84
84
|
---
|
85
85
|
|
@@ -90,18 +90,18 @@ CoolSeqTool
|
|
90
90
|
## Overview
|
91
91
|
|
92
92
|
<!-- description -->
|
93
|
-
The **
|
93
|
+
The Common Operations On Lots-Of Sequences Tool, **Cool-Seq-Tool**, provides:
|
94
94
|
|
95
|
-
|
96
|
-
|
97
|
-
|
95
|
+
- 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 transcript alignment data from the [Universal Transcript Archive](https://github.com/biocommons/uta)
|
96
|
+
- Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
|
97
|
+
- Mapping tools, including a transcript selection algorithm for selecting a representative transcript defined [here](https://coolseqtool.readthedocs.io/stable/transcript_selection.html), that combine the above to support translation between references sequences, annotation layers, and transcripts
|
98
98
|
<!-- /description -->
|
99
99
|
|
100
100
|
---
|
101
101
|
|
102
102
|
## Install
|
103
103
|
|
104
|
-
|
104
|
+
Cool-Seq-Tool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
|
105
105
|
|
106
106
|
```shell
|
107
107
|
python3 -m pip install cool-seq-tool
|
@@ -113,7 +113,7 @@ See the [installation instructions](https://coolseqtool.readthedocs.io/stable/in
|
|
113
113
|
|
114
114
|
## Usage
|
115
115
|
|
116
|
-
All
|
116
|
+
All Cool-Seq-Tool resources can be initialized by way of a top-level class instance:
|
117
117
|
|
118
118
|
```pycon
|
119
119
|
>>> from cool_seq_tool import CoolSeqTool
|
@@ -0,0 +1,59 @@
|
|
1
|
+
<h1 align="center">
|
2
|
+
Cool-Seq-Tool
|
3
|
+
</h1>
|
4
|
+
|
5
|
+
[](https://pypi.python.org/pypi/cool-seq-tool) [](https://doi.org/10.5281/zenodo.14007783) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
|
6
|
+
|
7
|
+
---
|
8
|
+
|
9
|
+
**[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)
|
10
|
+
|
11
|
+
---
|
12
|
+
|
13
|
+
## Overview
|
14
|
+
|
15
|
+
<!-- description -->
|
16
|
+
The Common Operations On Lots-Of Sequences Tool, **Cool-Seq-Tool**, provides:
|
17
|
+
|
18
|
+
- 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 transcript alignment data from the [Universal Transcript Archive](https://github.com/biocommons/uta)
|
19
|
+
- Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
|
20
|
+
- Mapping tools, including a transcript selection algorithm for selecting a representative transcript defined [here](https://coolseqtool.readthedocs.io/stable/transcript_selection.html), that combine the above to support translation between references sequences, annotation layers, and transcripts
|
21
|
+
<!-- /description -->
|
22
|
+
|
23
|
+
---
|
24
|
+
|
25
|
+
## Install
|
26
|
+
|
27
|
+
Cool-Seq-Tool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
|
28
|
+
|
29
|
+
```shell
|
30
|
+
python3 -m pip install cool-seq-tool
|
31
|
+
```
|
32
|
+
|
33
|
+
See the [installation instructions](https://coolseqtool.readthedocs.io/stable/install.html) in the documentation for a description of dependency setup requirements.
|
34
|
+
|
35
|
+
---
|
36
|
+
|
37
|
+
## Usage
|
38
|
+
|
39
|
+
All Cool-Seq-Tool resources can be initialized by way of a top-level class instance:
|
40
|
+
|
41
|
+
```pycon
|
42
|
+
>>> from cool_seq_tool import CoolSeqTool
|
43
|
+
>>> from cool_seq_tool.schemas import AnnotationLayer, CoordinateType
|
44
|
+
>>> cst = CoolSeqTool()
|
45
|
+
>>> result = await cst.mane_transcript.get_mane_transcript(
|
46
|
+
... "NP_004324.2",
|
47
|
+
... 599,
|
48
|
+
... AnnotationLayer.PROTEIN,
|
49
|
+
... coordinate_type=CoordinateType.INTER_RESIDUE,
|
50
|
+
... )
|
51
|
+
>>> result.gene, result.refseq, result.status
|
52
|
+
('EGFR', 'NM_005228.5', <TranscriptPriority.MANE_SELECT: 'mane_select'>)
|
53
|
+
```
|
54
|
+
|
55
|
+
---
|
56
|
+
|
57
|
+
## Feedback and contributing
|
58
|
+
|
59
|
+
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.
|
@@ -17,7 +17,7 @@ Create a virtual environment and install :ref:`all dependency groups<dependency-
|
|
17
17
|
|
18
18
|
python3 -m venv venv
|
19
19
|
source venv/bin/activate
|
20
|
-
python3 -m pip install -e ".[dev,
|
20
|
+
python3 -m pip install -e ".[dev,tests,docs]"
|
21
21
|
|
22
22
|
We use `pre-commit <https://pre-commit.com/#usage>`_ to run conformance tests before commits. This provides checks for:
|
23
23
|
|
@@ -16,15 +16,15 @@ Cool-Seq-Tool |version|
|
|
16
16
|
:alt: tests status
|
17
17
|
:target: https://github.com/genomicmedlab/cool-seq-tool/actions/workflows/checks.yaml
|
18
18
|
|
19
|
-
The **
|
19
|
+
The Common Operations On Lots-Of Sequences Tool, **Cool-Seq-Tool**, provides:
|
20
20
|
|
21
|
-
* 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>`_
|
21
|
+
* 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 transcript alignment data from the `Universal Transcript Archive <https://github.com/biocommons/uta>`_
|
22
22
|
* Augmented access to the `SeqRepo <https://github.com/biocommons/biocommons.seqrepo>`_ database, including multiple additional methods and tools
|
23
|
-
* Mapping tools that combine the above to support translation between various references sequences and annotation layers, and
|
23
|
+
* Mapping tools, including a transcript selection algorithm for selecting a representative transcript defined :ref:`here <transcript_selection_policy>`, that combine the above to support translation between various references sequences and annotation layers, and transcripts
|
24
24
|
|
25
25
|
See the :ref:`Installation <installation>` and :ref:`Usage <usage>` pages for information on getting started. Individual classes and methods are documented within the :ref:`API reference <api_reference>`.
|
26
26
|
|
27
|
-
|
27
|
+
Cool-Seq-Tool was created to support the `Knowledgebase Integration Project <https://cancervariants.org/projects/integration/>`_ of the `Variant Interpretation for Cancer Consortium (VICC) <https://cancervariants.org/>`_. It is developed primarily by the `Wagner Lab <https://www.nationwidechildrens.org/specialties/institute-for-genomic-medicine/research-labs/wagner-lab>`_. Full source code is available on `GitHub <https://github.com/genomicmedlab/cool-seq-tool>`_.
|
28
28
|
|
29
29
|
.. toctree::
|
30
30
|
:hidden:
|
@@ -24,7 +24,7 @@ Install Cool-Seq-Tool from `PyPI <https://pypi.org/project/cool-seq-tool/>`_:
|
|
24
24
|
Cool-Seq-Tool provides extra dependency groups for development and testing purposes. Most users won't need to install them.
|
25
25
|
|
26
26
|
* ``dev`` includes packages for linting and performing other kinds of quality checks
|
27
|
-
* ``
|
27
|
+
* ``tests`` includes packages for running tests
|
28
28
|
* ``docs`` includes packages for writing and building documentation
|
29
29
|
|
30
30
|
Set up UTA
|
@@ -28,8 +28,9 @@ All compatible transcripts are evaluated and ordered against the below criteria.
|
|
28
28
|
#. Transcript is annotated as a `MANE Select` transcript
|
29
29
|
#. Transcript is annotated as a `MANE Plus Clinical` transcript
|
30
30
|
#. Transcript is the longest-compatible remaining transcript
|
31
|
-
#. Transcript is the first-published (lowest-numbered RefSeq/Ensembl accession) remaining transcript
|
32
31
|
|
33
|
-
|
32
|
+
#. If there is a tie, choose the first-published (lowest-numbered RefSeq/Ensembl accession) transcript
|
34
33
|
|
35
|
-
|
34
|
+
.. note::
|
35
|
+
|
36
|
+
We always prefer the most recent version of a transcript associated with an assembly.
|
@@ -30,7 +30,7 @@ Descriptions and examples of functions can be found in the :ref:`API Reference <
|
|
30
30
|
|
31
31
|
.. note::
|
32
32
|
|
33
|
-
Many component classes in
|
33
|
+
Many component classes in Cool-Seq-Tool, including :py:class:`UtaDatabase <cool_seq_tool.sources.uta_database.UtaDatabase>`, :py:class:`ExonGenomicCoordsMapper <cool_seq_tool.mappers.exon_genomic_coords.ExonGenomicCoordsMapper>`, and :py:class:`ManeTranscript <cool_seq_tool.mappers.mane_transcript>`, define public methods as ``async``. This means that, when used inside another function, they must be called with ``await``:
|
34
34
|
|
35
35
|
.. code-block:: python
|
36
36
|
|
@@ -33,14 +33,14 @@ dependencies = [
|
|
33
33
|
"biocommons.seqrepo",
|
34
34
|
"pydantic == 2.*",
|
35
35
|
"ga4gh.vrs ~= 2.0.0a10",
|
36
|
-
"wags-tails ~= 0.
|
36
|
+
"wags-tails ~= 0.2.2",
|
37
37
|
"bioutils",
|
38
38
|
]
|
39
39
|
dynamic = ["version"]
|
40
40
|
|
41
41
|
[project.optional-dependencies]
|
42
42
|
dev = ["pre-commit>=3.7.1", "ipython", "ipykernel", "psycopg2-binary", "ruff==0.5.0"]
|
43
|
-
|
43
|
+
tests = ["pytest", "pytest-cov", "pytest-asyncio==0.18.3", "mock"]
|
44
44
|
docs = [
|
45
45
|
"sphinx==6.1.3",
|
46
46
|
"sphinx-autodoc-typehints==1.22.0",
|
{cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/mappers/exon_genomic_coords.py
RENAMED
@@ -1169,14 +1169,32 @@ class ExonGenomicCoordsMapper:
|
|
1169
1169
|
:param end: Genomic coordinate of breakpoint
|
1170
1170
|
:return: Exon number corresponding to adjacent exon. Will be 0-based
|
1171
1171
|
"""
|
1172
|
-
|
1172
|
+
# If a transcript has only one exon, return 0
|
1173
|
+
if len(tx_exons_genomic_coords) == 1:
|
1174
|
+
return 0
|
1175
|
+
|
1176
|
+
# Check if a breakpoint occurs before/after the transcript boundaries
|
1177
|
+
bp = start if start else end
|
1178
|
+
exon_list_len = len(tx_exons_genomic_coords) - 1
|
1179
|
+
|
1180
|
+
if strand == Strand.POSITIVE:
|
1181
|
+
if bp < tx_exons_genomic_coords[0].alt_start_i:
|
1182
|
+
return 0
|
1183
|
+
if bp > tx_exons_genomic_coords[exon_list_len].alt_end_i:
|
1184
|
+
return exon_list_len
|
1185
|
+
if strand == Strand.NEGATIVE:
|
1186
|
+
if bp > tx_exons_genomic_coords[0].alt_end_i:
|
1187
|
+
return 0
|
1188
|
+
if bp < tx_exons_genomic_coords[exon_list_len].alt_start_i:
|
1189
|
+
return exon_list_len
|
1190
|
+
|
1191
|
+
for i in range(exon_list_len):
|
1173
1192
|
exon = tx_exons_genomic_coords[i]
|
1174
1193
|
if start == exon.alt_start_i:
|
1175
1194
|
break
|
1176
1195
|
if end == exon.alt_end_i:
|
1177
1196
|
break
|
1178
1197
|
next_exon = tx_exons_genomic_coords[i + 1]
|
1179
|
-
bp = start if start else end
|
1180
1198
|
if strand == Strand.POSITIVE:
|
1181
1199
|
lte_exon = exon
|
1182
1200
|
gte_exon = next_exon
|
@@ -1185,6 +1203,7 @@ class ExonGenomicCoordsMapper:
|
|
1185
1203
|
gte_exon = exon
|
1186
1204
|
if bp >= lte_exon.alt_end_i and bp <= gte_exon.alt_start_i:
|
1187
1205
|
break
|
1206
|
+
|
1188
1207
|
# Return current exon if end position is provided, next exon if start position
|
1189
1208
|
# is provided.
|
1190
1209
|
return exon.ord if end else exon.ord + 1
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: cool_seq_tool
|
3
|
-
Version: 0.
|
3
|
+
Version: 0.9.0
|
4
4
|
Summary: Common Operation on Lots of Sequences Tool
|
5
5
|
Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
|
6
6
|
License: MIT License
|
@@ -53,7 +53,7 @@ Requires-Dist: hgvs
|
|
53
53
|
Requires-Dist: biocommons.seqrepo
|
54
54
|
Requires-Dist: pydantic==2.*
|
55
55
|
Requires-Dist: ga4gh.vrs~=2.0.0a10
|
56
|
-
Requires-Dist: wags-tails~=0.
|
56
|
+
Requires-Dist: wags-tails~=0.2.2
|
57
57
|
Requires-Dist: bioutils
|
58
58
|
Provides-Extra: dev
|
59
59
|
Requires-Dist: pre-commit>=3.7.1; extra == "dev"
|
@@ -61,11 +61,11 @@ Requires-Dist: ipython; extra == "dev"
|
|
61
61
|
Requires-Dist: ipykernel; extra == "dev"
|
62
62
|
Requires-Dist: psycopg2-binary; extra == "dev"
|
63
63
|
Requires-Dist: ruff==0.5.0; extra == "dev"
|
64
|
-
Provides-Extra:
|
65
|
-
Requires-Dist: pytest; extra == "
|
66
|
-
Requires-Dist: pytest-cov; extra == "
|
67
|
-
Requires-Dist: pytest-asyncio==0.18.3; extra == "
|
68
|
-
Requires-Dist: mock; extra == "
|
64
|
+
Provides-Extra: tests
|
65
|
+
Requires-Dist: pytest; extra == "tests"
|
66
|
+
Requires-Dist: pytest-cov; extra == "tests"
|
67
|
+
Requires-Dist: pytest-asyncio==0.18.3; extra == "tests"
|
68
|
+
Requires-Dist: mock; extra == "tests"
|
69
69
|
Provides-Extra: docs
|
70
70
|
Requires-Dist: sphinx==6.1.3; extra == "docs"
|
71
71
|
Requires-Dist: sphinx-autodoc-typehints==1.22.0; extra == "docs"
|
@@ -76,10 +76,10 @@ Requires-Dist: furo==2023.3.27; extra == "docs"
|
|
76
76
|
Requires-Dist: sphinx-github-changelog==1.2.1; extra == "docs"
|
77
77
|
|
78
78
|
<h1 align="center">
|
79
|
-
|
79
|
+
Cool-Seq-Tool
|
80
80
|
</h1>
|
81
81
|
|
82
|
-
[](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
|
82
|
+
[](https://pypi.python.org/pypi/cool-seq-tool) [](https://doi.org/10.5281/zenodo.14007783) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
|
83
83
|
|
84
84
|
---
|
85
85
|
|
@@ -90,18 +90,18 @@ CoolSeqTool
|
|
90
90
|
## Overview
|
91
91
|
|
92
92
|
<!-- description -->
|
93
|
-
The **
|
93
|
+
The Common Operations On Lots-Of Sequences Tool, **Cool-Seq-Tool**, provides:
|
94
94
|
|
95
|
-
|
96
|
-
|
97
|
-
|
95
|
+
- 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 transcript alignment data from the [Universal Transcript Archive](https://github.com/biocommons/uta)
|
96
|
+
- Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
|
97
|
+
- Mapping tools, including a transcript selection algorithm for selecting a representative transcript defined [here](https://coolseqtool.readthedocs.io/stable/transcript_selection.html), that combine the above to support translation between references sequences, annotation layers, and transcripts
|
98
98
|
<!-- /description -->
|
99
99
|
|
100
100
|
---
|
101
101
|
|
102
102
|
## Install
|
103
103
|
|
104
|
-
|
104
|
+
Cool-Seq-Tool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
|
105
105
|
|
106
106
|
```shell
|
107
107
|
python3 -m pip install cool-seq-tool
|
@@ -113,7 +113,7 @@ See the [installation instructions](https://coolseqtool.readthedocs.io/stable/in
|
|
113
113
|
|
114
114
|
## Usage
|
115
115
|
|
116
|
-
All
|
116
|
+
All Cool-Seq-Tool resources can be initialized by way of a top-level class instance:
|
117
117
|
|
118
118
|
```pycon
|
119
119
|
>>> from cool_seq_tool import CoolSeqTool
|
@@ -9,7 +9,6 @@ pyproject.toml
|
|
9
9
|
.github/ISSUE_TEMPLATE/bug-report.yaml
|
10
10
|
.github/ISSUE_TEMPLATE/feature-request.yaml
|
11
11
|
.github/workflows/checks.yaml
|
12
|
-
.github/workflows/close_issue.yml
|
13
12
|
.github/workflows/pr-priority-label.yaml
|
14
13
|
.github/workflows/release.yml
|
15
14
|
.github/workflows/stale.yaml
|
@@ -7,7 +7,7 @@ hgvs
|
|
7
7
|
biocommons.seqrepo
|
8
8
|
pydantic==2.*
|
9
9
|
ga4gh.vrs~=2.0.0a10
|
10
|
-
wags-tails~=0.
|
10
|
+
wags-tails~=0.2.2
|
11
11
|
bioutils
|
12
12
|
|
13
13
|
[dev]
|
@@ -26,7 +26,7 @@ sphinxext-opengraph==0.8.2
|
|
26
26
|
furo==2023.3.27
|
27
27
|
sphinx-github-changelog==1.2.1
|
28
28
|
|
29
|
-
[
|
29
|
+
[tests]
|
30
30
|
pytest
|
31
31
|
pytest-cov
|
32
32
|
pytest-asyncio==0.18.3
|
@@ -277,6 +277,21 @@ def nm_001105539_exons_genomic_coords():
|
|
277
277
|
]
|
278
278
|
|
279
279
|
|
280
|
+
@pytest.fixture(scope="session")
|
281
|
+
def mm_001005183_1_exons():
|
282
|
+
"""Create test fixture for NM_001005183.1 exons and genomic coordinates"""
|
283
|
+
return [
|
284
|
+
_ExonCoord(
|
285
|
+
ord=0,
|
286
|
+
tx_start_i=0,
|
287
|
+
tx_end_i=939,
|
288
|
+
alt_start_i=55426253,
|
289
|
+
alt_end_i=55427192,
|
290
|
+
alt_strand=Strand.POSITIVE,
|
291
|
+
)
|
292
|
+
]
|
293
|
+
|
294
|
+
|
280
295
|
@pytest.fixture(scope="session")
|
281
296
|
def tpm3_1_8_start_genomic():
|
282
297
|
"""Create test fixture for genomic data for exon 1, 8"""
|
@@ -806,7 +806,10 @@ async def test_get_start_end_exon_coords(test_egc_mapper):
|
|
806
806
|
|
807
807
|
@pytest.mark.asyncio()
|
808
808
|
async def test_get_adjacent_exon(
|
809
|
-
test_egc_mapper,
|
809
|
+
test_egc_mapper,
|
810
|
+
nm_152263_exons_genomic_coords,
|
811
|
+
nm_001105539_exons_genomic_coords,
|
812
|
+
mm_001005183_1_exons,
|
810
813
|
):
|
811
814
|
"""Test that get_adjacent_exon works properly"""
|
812
815
|
resp = test_egc_mapper._get_adjacent_exon(
|
@@ -840,6 +843,41 @@ async def test_get_adjacent_exon(
|
|
840
843
|
)
|
841
844
|
assert resp == 4
|
842
845
|
|
846
|
+
# Check cases where breakpoint occurs in before/after transcript boundaries
|
847
|
+
resp = test_egc_mapper._get_adjacent_exon(
|
848
|
+
tx_exons_genomic_coords=nm_001105539_exons_genomic_coords,
|
849
|
+
start=80486220,
|
850
|
+
strand=Strand.POSITIVE,
|
851
|
+
)
|
852
|
+
assert resp == 0
|
853
|
+
resp = test_egc_mapper._get_adjacent_exon(
|
854
|
+
tx_exons_genomic_coords=nm_001105539_exons_genomic_coords,
|
855
|
+
start=80526285,
|
856
|
+
strand=Strand.POSITIVE,
|
857
|
+
)
|
858
|
+
assert resp == 5
|
859
|
+
resp = test_egc_mapper._get_adjacent_exon(
|
860
|
+
tx_exons_genomic_coords=nm_152263_exons_genomic_coords,
|
861
|
+
end=154192110,
|
862
|
+
strand=Strand.NEGATIVE,
|
863
|
+
)
|
864
|
+
assert resp == 0
|
865
|
+
resp = test_egc_mapper._get_adjacent_exon(
|
866
|
+
tx_exons_genomic_coords=nm_152263_exons_genomic_coords,
|
867
|
+
end=154161809,
|
868
|
+
strand=Strand.NEGATIVE,
|
869
|
+
)
|
870
|
+
assert resp == 9
|
871
|
+
|
872
|
+
# Check cases where transcript only has one exon and breakpoint does not occur
|
873
|
+
# exon
|
874
|
+
resp = test_egc_mapper._get_adjacent_exon(
|
875
|
+
tx_exons_genomic_coords=mm_001005183_1_exons,
|
876
|
+
start=55411058,
|
877
|
+
strand=Strand.POSITIVE,
|
878
|
+
)
|
879
|
+
assert resp == 0
|
880
|
+
|
843
881
|
|
844
882
|
def test_is_exonic_breakpoint(test_egc_mapper, nm_001105539_exons_genomic_coords):
|
845
883
|
"""Test is breakpoint occurs on exon"""
|
@@ -1,18 +0,0 @@
|
|
1
|
-
name: Close issues related to a merged pull request based on staging branch.
|
2
|
-
|
3
|
-
on:
|
4
|
-
pull_request:
|
5
|
-
types: [closed]
|
6
|
-
branches:
|
7
|
-
- staging
|
8
|
-
|
9
|
-
jobs:
|
10
|
-
closeIssueOnPrMergeTrigger:
|
11
|
-
|
12
|
-
runs-on: ubuntu-latest
|
13
|
-
|
14
|
-
steps:
|
15
|
-
- name: Closes issues related to a merged pull request.
|
16
|
-
uses: ldez/gha-mjolnir@v1.0.3
|
17
|
-
env:
|
18
|
-
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
cool_seq_tool-0.8.0/README.md
DELETED
@@ -1,59 +0,0 @@
|
|
1
|
-
<h1 align="center">
|
2
|
-
CoolSeqTool
|
3
|
-
</h1>
|
4
|
-
|
5
|
-
[](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://pypi.python.org/pypi/cool-seq-tool) [](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
|
6
|
-
|
7
|
-
---
|
8
|
-
|
9
|
-
**[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)
|
10
|
-
|
11
|
-
---
|
12
|
-
|
13
|
-
## Overview
|
14
|
-
|
15
|
-
<!-- description -->
|
16
|
-
The **CoolSeqTool** provides:
|
17
|
-
|
18
|
-
- 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)
|
19
|
-
- Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
|
20
|
-
- Mapping tools that combine the above to support translation between references sequences, annotation layers, and MANE transcripts
|
21
|
-
<!-- /description -->
|
22
|
-
|
23
|
-
---
|
24
|
-
|
25
|
-
## Install
|
26
|
-
|
27
|
-
CoolSeqTool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
|
28
|
-
|
29
|
-
```shell
|
30
|
-
python3 -m pip install cool-seq-tool
|
31
|
-
```
|
32
|
-
|
33
|
-
See the [installation instructions](https://coolseqtool.readthedocs.io/stable/install.html) in the documentation for a description of dependency setup requirements.
|
34
|
-
|
35
|
-
---
|
36
|
-
|
37
|
-
## Usage
|
38
|
-
|
39
|
-
All CoolSeqTool resources can be initialized by way of a top-level class instance:
|
40
|
-
|
41
|
-
```pycon
|
42
|
-
>>> from cool_seq_tool import CoolSeqTool
|
43
|
-
>>> from cool_seq_tool.schemas import AnnotationLayer, CoordinateType
|
44
|
-
>>> cst = CoolSeqTool()
|
45
|
-
>>> result = await cst.mane_transcript.get_mane_transcript(
|
46
|
-
... "NP_004324.2",
|
47
|
-
... 599,
|
48
|
-
... AnnotationLayer.PROTEIN,
|
49
|
-
... coordinate_type=CoordinateType.INTER_RESIDUE,
|
50
|
-
... )
|
51
|
-
>>> result.gene, result.refseq, result.status
|
52
|
-
('EGFR', 'NM_005228.5', <TranscriptPriority.MANE_SELECT: 'mane_select'>)
|
53
|
-
```
|
54
|
-
|
55
|
-
---
|
56
|
-
|
57
|
-
## Feedback and contributing
|
58
|
-
|
59
|
-
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.
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/resources/transcript_mapping.tsv
RENAMED
File without changes
|
File without changes
|
File without changes
|
{cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/sources/mane_transcript_mappings.py
RENAMED
File without changes
|
{cool_seq_tool-0.8.0 → cool_seq_tool-0.9.0}/src/cool_seq_tool/sources/transcript_mappings.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|