cortado-ms 0.16.2__tar.gz

cortado_ms-0.16.2/.github/workflows/black.yml

@@ -0,0 +1,11 @@
+name: Lint
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+      - uses: psf/black@stable

cortado_ms-0.16.2/.github/workflows/publish.yml

@@ -0,0 +1,90 @@
+# This workflows will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Deploy Packages
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  codeartifact-deploy:
+    name: Upload release to CodeArtifact
+    if: ${{ github.event_name == 'release' }}
+    runs-on: [self-hosted, aws-master, X64]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        pip config unset global.index-url || true
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine build 'awscli>=1.18.83'
+        aws codeartifact login --tool twine --repository seer_ds --domain seer --domain-owner 718843040700 --region us-west-2
+    - name: Build and publish
+      run: |
+        python -m build --sdist --wheel .
+        twine upload --repository codeartifact dist/*
+
+  pypi-deploy:
+    name: Upload release to PyPI
+    if: ${{ github.event_name == 'release' }}
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+    environment:
+      name: pypi
+      url: https://pypi.org/p/cortado-ms
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.x'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel twine build
+      - name: Build package
+        run: python -m build --sdist --wheel .
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  build-docs:
+    runs-on: ubuntu-latest
+    needs: pypi-deploy
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.x'
+      - name: Set up Sphinx + AutoAPI
+        run: pip install sphinx sphinx-autoapi
+      - name: Render documentation
+        run: |
+          make -C docs html
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/_build/html/
+
+  deploy-docs:
+    runs-on: ubuntu-latest
+    needs: build-docs
+    environment:
+      name: github-pages
+      url: ${{steps.deployment.outputs.page_url}}
+    permissions:
+      pages: write
+      id-token: write
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

cortado_ms-0.16.2/.github/workflows/tests.yml

@@ -0,0 +1,41 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  schedule:
+  - cron: "0 0 1 1/1 *" # Run monthly
+
+jobs:
+  build:
+    runs-on: [self-hosted, aws-master, X64]
+#    strategy:
+#      matrix:
+#        os: [ubuntu-latest, windows-latest, macos-latest]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 pytest wheel
+        aws codeartifact login --tool pip --repository seer_ds --domain seer --domain-owner 718843040700 --region us-west-2
+        pip install '.[test]'
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        pytest

cortado_ms-0.16.2/.gitignore

@@ -0,0 +1,160 @@
+.idea
+_build
+
+
+# Sphinx generated docs
+docs/_build/
+docs/_autosummary/
+
+
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+pytestdebug.log
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+doc/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+# .env
+.env/
+.venv/
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pythonenv*
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# operating system-related files
+*.DS_Store #file properties cache/storage on macOS
+Thumbs.db #thumbnail cache on Windows
+
+# profiling data
+.prof
+
+
+# End of https://www.toptal.com/developers/gitignore/api/python

cortado_ms-0.16.2/.pre-commit-config.yaml

@@ -0,0 +1,6 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: stable # Replace by any tag/version: https://github.com/psf/black/tags
+    hooks:
+      - id: black
+        language_version: python3 # Should be a command that runs python3.6+

cortado_ms-0.16.2/CONTRIBUTING.md

@@ -0,0 +1,58 @@
+## Contributing to `cortado`
+
+### Setting up for development
+
+1. Clone the repository
+
+    ```shell
+    git clone git@github.com:seerbio/cortado.git
+    cd cortado
+    ```
+
+    Alternatively, create a fork through GitHub and clone that repository.
+
+2. Set up `pre-commit` hook (for code formatting):
+
+    ```shell
+    pip install pre-commit
+    pre-commit install
+    ```
+
+    This will ensure all Python sources are consistently formatted whenever
+    you commit to the repository.
+
+### Developing changes
+
+1. Create a branch
+
+    ```shell
+    git checkout main
+    git pull --ff-only --tags origin main
+    git checkout -b my-feature-branch main
+    ```
+
+2. Develop your changes. Commit often, with meaningful messages for each commit.
+   Be sure to develop unit tests and ensure that all existing tests pass:
+
+    ```shell
+    pytest
+    ```
+
+3. Push changes back to the repository (or your fork).
+4. Create a pull request through GitHub. Assign yourself to it and add appropriate
+   reviewers.
+
+### Releasing `cortado`
+
+After changes are developed, reviewed, and merged, it's possible to create a
+release automatically using GitHub.
+
+1. Determine the appropriate [semantic version](https://semver.org/) for the
+   new release. Check the GitHub repo's "Releases" section to see what the most
+   recent release number is and consider the changes made.
+2. Create a Release through the GitHub UI. Choose to create a new tag targeting
+   the `main` branch and name it for the new version number, i.e. `v3.4.5`.
+   Use the same string as the release title. Click "generate release notes" to
+   automatically create a list of PRs since the last release.
+3. After creating the release, the package will be automatically built and
+   deployed with the new version number.

cortado_ms-0.16.2/LICENSE.md

@@ -0,0 +1,209 @@
+**LICENSE**
+
+Use of the Fulcrum Pipeline™ framework software, including any portion
+thereof, is licensed under a Mandatory Grant-Back Apache 2.0 license, as
+modified by the Commons Clause (collectively, the "**License**").
+
+You may not use the Fulcrum Pipeline™ software, including any portion
+thereof, except in compliance with the License. See the entire License
+for specific language governing permissions and limitations under the
+License.
+
+------------------------------------------------------------------------
+
+**Mandatory Grant-Back** **Apache 2.0 License, as modified by the Commons Clause May 2026**
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+**1. Definitions**.
+
+"**License**" shall mean the terms and conditions for use,
+reproduction, and distribution as defined by Sections 1 through 10 of
+this document.
+
+"**Licensor**" shall mean the copyright owner or entity authorized by
+the copyright owner that is granting the License.
+
+"**Original Licensor**" shall mean Seer, Inc., or any assignee of or
+successor in interest to Seer, Inc.
+
+"**Legal Entity**" shall mean the union of the acting entity and all
+other entities that control, are controlled by, or are under common
+control with that entity. For the purposes of this definition,
+"**control**" means (i) the power, direct or indirect, to cause the
+direction or management of such entity, whether by contract or
+otherwise, or (ii) ownership of fifty percent (50%) or more of the
+outstanding shares, or (iii) beneficial ownership of such entity.
+
+"**You**" (or "**Your**") shall mean an individual or Legal Entity
+exercising permissions granted by this License.
+
+"**Source**" form shall mean the preferred form for making
+modifications, including but not limited to software source code,
+documentation source, and configuration files.
+
+"**Object**" form shall mean any form resulting from mechanical
+transformation or translation of a Source form, including but not
+limited to compiled object code, generated documentation, and
+conversions to other media types.
+
+"**Work**" shall mean the work of authorship, whether in Source or
+Object form, made available under the License, as indicated by a
+copyright notice that is included in or attached to the work.
+
+"**Derivative Works**" shall mean any work, whether in Source or
+Object form, that is based on (or derived from) the Work and for which
+the editorial revisions, annotations, elaborations, or other
+modifications represent, as a whole, an original work of authorship. For
+the purposes of this License, Derivative Works shall not include works,
+including known or novel plugins, that remain separable from, or merely
+link (or bind by name) to the interfaces of, the Work and Derivative
+Works thereof.
+
+"**Contribution**" shall mean any work of authorship, including the
+original version of the Work and any modifications or additions to that
+Work or Derivative Works thereof, that is intentionally submitted to
+Licensor for inclusion in the Work by the copyright owner or by an
+individual or Legal Entity authorized to submit on behalf of the
+copyright owner. For the purposes of this definition, "**submitted**"
+means any form of electronic, verbal, or written communication sent to
+the Licensor or its representatives, including but not limited to
+communication on electronic mailing lists, source code control systems,
+and issue tracking systems that are managed by, or on behalf of, the
+Licensor for the purpose of discussing and improving the Work.
+
+"**Contributor**" shall mean Licensor and any individual or Legal
+Entity on behalf of whom a Contribution has been received by Licensor
+and subsequently incorporated within the Work.
+
+"**Sell**" shall mean practicing any or all of the rights granted to
+You under the License to provide to third parties, for a fee or other
+consideration (including without limitation fees for hosting or
+consulting/ support services related to the Work or modified Work,
+including Derivative Work(s) thereof), a product or service whose value
+derives, entirely or substantially, from the functionality of the Work,
+modified Work, or Derivative Work(s).
+
+**2. Grant of Copyright License**. Subject to the terms and conditions
+of this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright
+license to reproduce, prepare Derivative Works of, publicly display,
+publicly perform, sublicense, and distribute the Work and such
+Derivative Works in Source or Object form.
+
+**3. Grant of Patent License**. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except
+as stated in this section) patent license to make, have made, use, offer
+to sell, sell, import, and otherwise transfer the Work, where such
+license applies only to those patent claims licensable by such
+Contributor that are necessarily infringed by their Contribution(s)
+alone or by combination of their Contribution(s) with the Work to which
+such Contribution(s) was submitted. If You institute patent litigation
+against any entity (including a cross-claim or counterclaim in a
+lawsuit) alleging that the Work or a Contribution incorporated within
+the Work constitutes direct or contributory patent infringement, then
+any patent licenses granted to You under this License for that Work
+shall terminate as of the date such litigation is filed.
+
+**4. Redistribution**. You may reproduce and distribute copies of the
+Work or Derivative Works thereof in any medium, with or without
+modifications, and in Source or Object form, provided that You meet the
+following conditions:
+
+a)  You must give any other recipients of the Work or Derivative Works a
+    copy of this License; and
+
+b)  You must cause any modified files to carry prominent notices stating
+    that You changed the files; and
+
+c)  You must retain, in the Source form of any Derivative Works that You
+    distribute, all copyright, patent, trademark, and attribution
+    notices from the Source form of the Work, excluding those notices
+    that do not pertain to any part of the Derivative Works; and
+
+d)  If the Work includes a "**NOTICE**" text file as part of its
+    distribution, then any Derivative Works that You distribute must
+    include a readable copy of the attribution notices contained within
+    such NOTICE file, excluding those notices that do not pertain to any
+    part of the Derivative Works, in at least one of the following
+    places: within a NOTICE text file distributed as part of the
+    Derivative Works; within the Source form or documentation, if
+    provided along with the Derivative Works; or, within a display
+    generated by the Derivative Works, if and wherever such third-party
+    notices normally appear. The contents of the NOTICE file are for
+    informational purposes only and do not modify the License. You may
+    add Your own attribution notices within Derivative Works that You
+    distribute, alongside or as an addendum to the NOTICE text from the
+    Work, provided that such additional attribution notices cannot be
+    construed as modifying the License.
+
+e)  To the extent that You generate any Derivative Works or otherwise
+    modify the Work, You must submit such modified Work or Derivative
+    Work(s) to the Original Licensor and such submitted modified Work or
+    Derivative Work(s) shall constitute a Contribution as defined
+    herein.
+
+You may add Your own copyright statement to Your modifications and may
+provide additional or different license terms and conditions for use,
+reproduction, or distribution of Your modifications, provided Your use,
+reproduction, and distribution of the modified Work (or Derivative Work)
+otherwise complies with the conditions stated in this License.
+
+**5. Submission of Contributions**. Unless You explicitly state
+otherwise, any Contribution intentionally submitted for inclusion in the
+Work by You to the Licensor shall be under the terms and conditions of
+this License, without any additional terms or conditions; provided that
+(a) any Contribution to Original Licensor shall carry with it a
+perpetual, worldwide, non-exclusive, no-charge, royalty-free,
+irrevocable copyright license to reproduce, prepare Derivative Works of,
+publicly display, publicly perform, sublicense, and distribute such
+Contribution in Source or Object form, and (b) Original Licensor's use
+of such Contribution shall not be subject to Section 10 of this License.
+
+**6. Trademarks**. This License does not grant permission to use the
+trade names, trademarks, service marks, or product names of the
+Licensor, except as required for reasonable and customary use in
+describing the origin of the Work and reproducing the content of the
+NOTICE file.
+
+**7. Disclaimer of Warranty**. Unless required by applicable law or
+agreed to in writing, Licensor provides the Work (and each Contributor
+provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied, including, without
+limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT,
+MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely
+responsible for determining the appropriateness of using or
+redistributing the Work and assume any risks associated with Your
+exercise of permissions under this License.
+
+**8. Limitation of Liability**. In no event and under no legal theory,
+whether in tort (including negligence), contract, or otherwise, unless
+required by applicable law (such as deliberate and grossly negligent
+acts) or agreed to in writing, shall any Contributor be liable to You
+for damages, including any direct, indirect, special, incidental, or
+consequential damages of any character arising as a result of this
+License or out of the use or inability to use the Work (including but
+not limited to damages for loss of goodwill, work stoppage, computer
+failure or malfunction, or any and all other commercial damages or
+losses), even if such Contributor has been advised of the possibility of
+such damages.
+
+**9. Accepting Warranty or Additional Liability**. While redistributing
+the Work or Derivative Works thereof, You may choose to offer, and
+charge a fee for, acceptance of support, warranty, indemnity, or other
+liability obligations and/or rights consistent with this License.
+However, in accepting such obligations, You may act only on Your own
+behalf and on Your sole responsibility, not on behalf of any other
+Contributor, and only if You agree to indemnify, defend, and hold each
+Contributor harmless for any liability incurred by, or claims asserted
+against, such Contributor by reason of your accepting any such warranty
+or additional liability.
+
+**10. "Commons Clause" License Condition.** The Work is provided to You
+by the Licensor under the License, subject to the following condition.
+Without limiting other conditions in the License, the grant of rights
+under the License will not include, and the License does not grant to
+You, the right to Sell the Work or Derivative Works thereof. Any license
+notice or attribution required by the License must also include this
+Commons Clause License Condition.

cortado_ms-0.16.2/PKG-INFO

@@ -0,0 +1,96 @@
+Metadata-Version: 2.4
+Name: cortado-ms
+Version: 0.16.2
+Summary: Confidence estimation for extreme-scale proteomics experiments
+Home-page: https://github.com/seerbio/cortado
+Author: Seth Just
+Author-email: sjust@seer.bio
+Project-URL: Bug Tracker, https://github.com/seerbio/cortado/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+Requires-Dist: numpy>=1.18.1
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: pyspark[sql]<4,>=3.3.1
+Requires-Dist: wheely-mammoth<2.0.0,>=0.16.1
+Requires-Dist: crema-ms<2.0.0,>=0.0.6
+Requires-Dist: importlib-metadata>=5.1.0
+Requires-Dist: scipy<2.0.0
+Provides-Extra: docs
+Requires-Dist: numpydoc>=1.0.0; extra == "docs"
+Requires-Dist: sphinx-argparse>=0.2.5; extra == "docs"
+Requires-Dist: sphinx-rtd-theme>=0.5.0; extra == "docs"
+Requires-Dist: nbsphinx>=0.7.1; extra == "docs"
+Requires-Dist: ipykernel>=5.3.0; extra == "docs"
+Requires-Dist: recommonmark>=0.5.0; extra == "docs"
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: polars; extra == "test"
+Provides-Extra: dev
+Requires-Dist: pre-commit>=2.7.1; extra == "dev"
+Requires-Dist: black>=20.8b1; extra == "dev"
+Dynamic: license-file
+
+<img alt="cortado logo" src="./docs/_static/cortado_logo.png" height="128" align="left" style="margin: 8px">
+
+**cortado** is a Python package that implements various methods to estimate
+false discovery rates (FDR) in extreme-scale mass spectrometry proteomics
+experiments. cortado is focused on gathering and reducing datasets to enable
+applying efficient implementations to estimate FDR. An additional focus is
+supporting peptide-centric searching through the "mixture-maximum" (MixMax)
+approach, which also supports spectrum-centric searches.
+
+Cortado is designed to be easy-to-use and flexible. Currently the following modes
+are supported:
+- Global PSM FDR
+- Global peptide or precursor FDR
+- MixMax _q_-value estimation
+- Protein scoring by rolling up PSM scores
+- Protein _q_-value estimation
+
+## Installation  
+
+cortado requires Python 3.8+ and can be installed with pip:  
+
+```shell
+pip install cortado-ms
+```
+
+## Basic Usage  
+
+Using `cortado` requires that you collect a dataset of PSMs, which can easily be
+accomplished with the
+[`wheely-mammoth` library](https://github.com/seerbio/wheely-mammoth), which is
+installed when you install `cortado-ms`:
+
+```pycon
+>>> from wheely.mammoth.parsers import read_encyclopedia_features
+>>> ds = read_encyclopedia_features("data/*.features.txt")
+```
+
+You can then compute _q_-values using the `assign_confidence` function:
+
+```pycon
+>>> from cortado import assign_confidence
+>>> conf = assign_confidence(ds, "primary", desc=False)
+>>> print(f"pi0={100*conf.pi0:.2f}%")
+pi0=36.74%
+>>> conf.data.toPandas()[["primary", "sequence", "q-value"]]
+       primary                                           sequence   q-value
+0    43.783160                             -.LSLEGDHSTPPSAYGSVK.-  0.000000
+1    41.212322                           -.NGPLEVAGAAVSAGHGLPAK.-  0.000000
+2    36.081665                               -.IMDPNIVGSEHYDVAR.-  0.000000
+3    34.730186                  -.TTHYTPLAC[+57.0214635]GSNPLKR.-  0.000000
+4    34.666630                             -.SGPKPFSAPKPQTSPSPK.-  0.000000
+..         ...                                                ...       ...
+827   8.150498                                     -.FGVEQDRMDK.-  0.414025
+828   8.065474                                     -.QYYYSADGSR.-  0.416572
+829   8.028464                                     -.APHDFQFVQK.-  0.416572
+830   7.946067                                     -.KLYEDAQMAR.-  0.417337
+831   7.632076  -.LTC[+57.0214635]PC[+57.0214635]C[+57.0214635...  0.420368
+
+[832 rows x 3 columns]
+```