seroverse 0.0.1__tar.gz

seroverse-0.0.1/.github/workflows/ci.yml

@@ -0,0 +1,94 @@
+name: CI
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+env:
+  FORCE_COLOR: "1"
+  UV_CACHE_DIR: /tmp/.uv-cache
+  NUMBA_CACHE_DIR: ${{ github.workspace }}/.numba_cache
+
+jobs:
+  quality:
+    name: Lint & Typecheck
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          python-version: "3.14"
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Install Python 3.14 & dependencies
+        run: uv sync --frozen --python 3.14 --group lint --group typing
+
+      - name: Run Ruff linter
+        run: uv run --no-sync ruff check --output-format=github .
+
+      - name: Check Ruff formatting
+        run: uv run --no-sync ruff format --check .
+
+      - name: Run ty static type checker
+        run: uv run --no-sync ty check src/
+
+  test:
+    name: Test (${{ matrix.os }}, py${{ matrix.python-version }})
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 20
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        python-version: ["3.14"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Restore Numba JIT cache
+        uses: actions/cache@v4
+        with:
+          path: ${{ env.NUMBA_CACHE_DIR }}
+          key: numba-jit-${{ runner.os }}-py${{ matrix.python-version }}-${{ hashFiles('src/**/*.py') }}
+          restore-keys: |
+            numba-jit-${{ runner.os }}-py${{ matrix.python-version }}-
+
+      - name: Install Python ${{ matrix.python-version }} & test dependencies
+        run: uv sync --frozen --python ${{ matrix.python-version }} --group test
+
+      - name: Run pytest suite with coverage
+        run: |
+          uv run --no-sync pytest \
+            -o addopts="-ra --tb=short --cov=src/seroverse --cov-report=term-missing --cov-report=xml --junitxml=pytest-report.xml"
+
+      - name: Publish test summary
+        if: always()
+        run: |
+          echo "### 🧪 Test Suite Results (${{ matrix.os }} / Python ${{ matrix.python-version }})" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "- **Runner**: \`${{ runner.os }} (${{ runner.arch }})\`" >> $GITHUB_STEP_SUMMARY
+          echo "- **Numba Cache**: \`${{ env.NUMBA_CACHE_DIR }}\`" >> $GITHUB_STEP_SUMMARY

seroverse-0.0.1/.github/workflows/docs.yml

@@ -0,0 +1,81 @@
+name: Documentation
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+    paths:
+      - "docs/**"
+      - "scripts/**"
+      - "src/**"
+      - "zensical.toml"
+      - "CODE_OF_CONDUCT.md"
+      - "CONTRIBUTING.md"
+      - "CHANGELOG.md"
+      - "pyproject.toml"
+      - "uv.lock"
+      - ".python-version"
+      - ".github/workflows/docs.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+jobs:
+  build:
+    name: Build Zensical Site
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          python-version: "3.14"
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Install documentation dependencies
+        run: uv sync --python 3.14 --group docs
+
+      - name: Fetch latest announcement from SeroVerse/.github
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: uv run --no-sync python scripts/fetch_announcement.py
+
+      - name: Build documentation with Zensical
+        run: uv run --no-sync zensical build --clean --strict
+
+      - name: Upload Pages artifact
+        if: github.event_name != 'pull_request'
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: site
+
+  deploy:
+    name: Deploy to GitHub Pages
+    if: github.event_name != 'pull_request' && (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/master')
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Configure GitHub Pages
+        uses: actions/configure-pages@v5
+
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

seroverse-0.0.1/.github/workflows/release.yml

@@ -0,0 +1,88 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - "v*"
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: "Build & verify distributions without publishing to PyPI"
+        required: false
+        default: true
+        type: boolean
+
+permissions:
+  contents: write
+  id-token: write
+
+jobs:
+  build:
+    name: Build Distribution Artifacts
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout repository with full history for hatch-vcs
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          python-version: "3.14"
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Build wheel and sdist
+        run: uv build
+
+      - name: Smoke-test built wheel in isolated environment
+        run: |
+          uv run --isolated --no-project --with dist/*.whl python -c "
+          import seroverse
+          "
+
+      - name: Upload distribution artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+          retention-days: 7
+
+  publish-pypi:
+    name: Publish to PyPI (Trusted Publishing)
+    if: startsWith(github.ref, 'refs/tags/v') && github.event.inputs.dry_run != 'true'
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/seroverse
+    steps:
+      - name: Download distribution artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    name: Create GitHub Release
+    if: startsWith(github.ref, 'refs/tags/v') && github.event.inputs.dry_run != 'true'
+    needs: [build, publish-pypi]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download distribution artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+          generate_release_notes: true

seroverse-0.0.1/.gitignore

@@ -0,0 +1,221 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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
+*.lcov
+.hypothesis/
+.pytest_cache/
+cover/
+
+# 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/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# uv
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi/*
+!.pixi/config.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule*
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs/Zensical documentation
+/site
+docs/overrides/announcement.html
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore that
+#   can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, you
+#   could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

seroverse-0.0.1/.pre-commit-config.yaml

@@ -0,0 +1,23 @@
+repos:
+  - repo: local
+    hooks:
+      - id: ruff-check
+        name: ruff check
+        entry: uv run --no-sync ruff check --fix
+        language: system
+        types: [python]
+        require_serial: true
+
+      - id: ruff-format
+        name: ruff format
+        entry: uv run --no-sync ruff format
+        language: system
+        types: [python]
+        require_serial: true
+
+      - id: ty
+        name: ty check
+        entry: uv run --no-sync ty check src/
+        language: system
+        types: [python]
+        pass_filenames: false

seroverse-0.0.1/.python-version

@@ -0,0 +1 @@
+3.14

seroverse-0.0.1/CHANGELOG.md

@@ -0,0 +1,23 @@
+# Release Notes
+
+All notable changes to **`SeroVerse`** and the SeroVerse ecosystem are documented on this page. This project adheres to [Semantic Versioning](https://semver.org/) and the [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) specification.
+
+---
+
+## [Unreleased]
+
+### Added
+
+- **Structure-of-Arrays & Graph Core (`seroverse.core`)**:
+  - `BatchedContainer` and `RaggedArrayContainer` zero-copy memory protocols (`seroverse.core.collections`).
+  - `Intervals` (`seroverse.core.interval`) and `GenomeAssembly` (`seroverse.core.genome`, `seroverse.core.io.fasta`).
+  - 2-bit DNA/RNA (`Alphabet.DNA`) and `MMSEQS12` reduced amino-acid alphabets with ragged translation across NCBI translation tables (`seroverse.core.seq.alphabet`).
+  - `RandstrobeIndex` ($O(1)$ strobemer seeding) and `FracMinHashIndex` k-mer indices (`seroverse.core.seq.kmers`).
+  - Vectorized unbanded/banded Smith-Waterman-Gotoh local and semi-global alignment (`PairwiseAligner` in `seroverse.core.seq.pairwise`).
+  - Hybrid sequence + motif-rescued protein clustering (`Clusterer` supporting greedy incremental and sparse Markov Clustering `MCL` modes in `seroverse.core.seq.clustering`).
+  - Packed CSR directed multigraphs (`Graph`, `Graphs`), Consensus Pan-Graph compression (`GraphBatch.as_pan_graph`), Hungarian + L2-QP `GraphAligner`, branch-and-bound `maximum_spanning_arborescence`, `RelationalMPNN`, and Fruchterman-Reingold `LayoutEngine` (`seroverse.core.graph`).
+- **Async Repository & Metadata Clients (`seroverse.client`)**:
+  - Async token-bucket rate-limited HTTP client (`Client`) and `msgspec` cassette serialization (`cassette_context`, `encode_msgpack`, `decode_msgpack`, `load_msgpack`, `save_msgpack` in `seroverse.client.base`).
+  - `NCBIClient` (`seroverse.client.ncbi`), `ENAClient` (`seroverse.client.ena`), `BacDiveClient` & `StrainInfoClient` (`seroverse.client.dsmz`), and `PathogenwatchBaseClient` (`seroverse.client.pathogenwatch`).
+- **Unified Ecosystem Documentation**:
+  - Unified Zensical documentation hub for `SeroVerse`, `SeroRef`, `KBank`, `SeroGen`, and `SeroEpi` with organization-wide GitHub Discussions announcements and Giscus comments.

seroverse-0.0.1/CITATION.cff

@@ -0,0 +1,20 @@
+cff-version: 1.2.0
+message: "If you use SeroVerse in your work, please cite it using the following metadata."
+title: "SeroVerse: Core data structures, graph algorithms, and async database clients for bacterial genomics, glycomics, and sero-epidemiology"
+type: software
+authors:
+  - family-names: "Stanton"
+    given-names: "Thomas David"
+    email: "tomdstanton@gmail.com"
+    orcid: "https://orcid.org/0000-0002-8898-4432"
+    affiliation: "Monash University"
+repository-code: "https://github.com/SeroVerse/SeroVerse"
+url: "https://seroverse.github.io/SeroVerse/"
+license: "GPL-3.0-only"
+keywords:
+  - bioinformatics
+  - genomics
+  - glycomics
+  - epidemiology
+  - serotyping
+  - microbiology

seroverse-0.0.1/CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+tomdstanton@gmail.com.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.