kbank 0.0.1__tar.gz

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

@@ -0,0 +1,120 @@
+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: ${{ github.workspace }}/.numba_cache
+
+jobs:
+  quality:
+    name: Lint & Typecheck
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          python-version: "3.14"
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Configure uv to install serogen from GitHub
+        run: |
+          python3 -c '
+          from pathlib import Path
+          p = Path("pyproject.toml")
+          p.write_text(
+              p.read_text().replace(
+                  "serogen = { path = \"../SeroGen\", editable = true }",
+                  "serogen = { git = \"https://github.com/seroverse/serogen.git\" }",
+              )
+          )
+          '
+
+      - name: Install Python 3.14 & dependencies
+        run: uv sync --python 3.14 --group lint --group typing
+
+      - name: Run Ruff linter
+        run: uv run --no-sync ruff check --output-format=github .
+
+      - name: Check Ruff formatting
+        run: uv run --no-sync ruff format --check .
+
+      - name: Run ty static type checker
+        run: uv run --no-sync ty check src/
+
+  test:
+    name: Test (${{ 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: Configure uv to install serogen from GitHub
+        run: |
+          python3 -c '
+          from pathlib import Path
+          p = Path("pyproject.toml")
+          p.write_text(
+              p.read_text().replace(
+                  "serogen = { path = \"../SeroGen\", editable = true }",
+                  "serogen = { git = \"https://github.com/seroverse/serogen.git\" }",
+              )
+          )
+          '
+
+      - name: Install Python ${{ matrix.python-version }} & test dependencies
+        run: uv sync --python ${{ matrix.python-version }} --group test
+
+      - name: Run pytest suite with coverage
+        run: |
+          uv run --no-sync pytest \
+            -o addopts="-ra --tb=short --cov=src/kbank --cov-report=term-missing --cov-report=xml --junitxml=pytest-report.xml"
+
+      - name: Publish test summary
+        if: always()
+        run: |
+          echo "### 🧪 Test Suite Results (${{ 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

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

@@ -0,0 +1,172 @@
+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: Configure uv to install serogen from GitHub
+        run: |
+          python3 -c '
+          from pathlib import Path
+          p = Path("pyproject.toml")
+          p.write_text(
+              p.read_text().replace(
+                  "serogen = { path = \"../SeroGen\", editable = true }",
+                  "serogen = { git = \"https://github.com/seroverse/serogen.git\" }",
+              )
+          )
+          '
+
+      - name: Install documentation dependencies
+        run: uv sync --python 3.14 --group docs
+
+      - name: Export Marimo slide decks and interactive apps
+        run: |
+          uv run --no-sync python -c '
+          import json
+          import subprocess
+          import sys
+          from pathlib import Path
+          from marimo._config.manager import get_default_config_manager
+          from marimo._export.exporter import Exporter
+          from marimo._export.file import _resolve_and_inline_layout
+          from marimo._export.requests import HTMLExportRequest
+          from marimo._schemas.export_options import HTMLExportOptions, NotebookExportSnapshot
+          from marimo._session.notebook import load_notebook
+          from marimo._session.state.serialize import serialize_notebook
+          from marimo._session.state.session_view import SessionView
+          from marimo._utils.code import hash_code
+
+          out_dir = Path("docs/notebooks/assets")
+          out_dir.mkdir(parents=True, exist_ok=True)
+          exporter = Exporter()
+          for nb_path in sorted(Path("scripts").glob("*.py")):
+              session_path = Path("scripts/__marimo__/session") / f"{nb_path.name}.json"
+              if not session_path.exists():
+                  if "marimo.App(" in nb_path.read_text(encoding="utf-8"):
+                      out_html = out_dir / f"{nb_path.stem}.html"
+                      subprocess.run(
+                          [
+                              sys.executable,
+                              "-m",
+                              "marimo",
+                              "export",
+                              "html",
+                              "--no-sandbox",
+                              "--force",
+                              str(nb_path),
+                              "-o",
+                              str(out_html),
+                              "--no-include-code",
+                          ],
+                          check=True,
+                      )
+                      print(f"Executed & exported {out_html} ({out_html.stat().st_size:,} bytes)")
+                  continue
+              file_manager = load_notebook(str(nb_path.resolve()))
+              session_data = json.loads(session_path.read_text(encoding="utf-8"))
+              cell_datas = list(file_manager.app.cell_manager.cell_data())
+              session_cells = session_data.get("cells", [])
+              for idx, cd in enumerate(cell_datas):
+                  if idx < len(session_cells):
+                      session_cells[idx]["id"] = cd.cell_id
+                      session_cells[idx]["code_hash"] = hash_code(cd.code)
+              session_view = SessionView()
+              for cd in cell_datas:
+                  session_view.last_executed_code[cd.cell_id] = cd.code
+              layout = _resolve_and_inline_layout(file_manager.app)
+              config = get_default_config_manager(current_path=file_manager.path)
+              resolved = config.get_config()
+              snapshot = NotebookExportSnapshot(
+                  notebook=serialize_notebook(session_view, file_manager.app.cell_manager),
+                  session=session_data,
+                  model_notifications=(),
+              )
+              html, _ = exporter.export_as_html(
+                  HTMLExportRequest(
+                      filename=file_manager.filename,
+                      app_code=file_manager.app.to_py(),
+                      app_config=file_manager.app.config,
+                      snapshot=snapshot,
+                      display_config=resolved["display"],
+                      options=HTMLExportOptions(include_code=bool(layout is not None), files=()),
+                      layout=layout,
+                      sharing_config=resolved.get("sharing"),
+                  )
+              )
+              (out_dir / f"{nb_path.stem}.html").write_text(html, encoding="utf-8")
+              print(f"Exported {out_dir / nb_path.stem}.html ({len(html):,} bytes)")
+          '
+
+      - 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

kbank-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 kbank
+          "
+
+      - 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/kbank
+    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

kbank-0.0.1/.gitignore

@@ -0,0 +1,230 @@
+# 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
+.hypothesis/
+.pytest_cache/
+cover/
+.karva/
+.karva_cache/
+
+# 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
+
+# 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 documentation
+/site
+
+# 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 & IDE files (keep cached notebook session snapshots in scripts/)
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+!scripts/__marimo__/
+scripts/__marimo__/*
+!scripts/__marimo__/session/
+.DS_Store
+
+# Documentation build output
+docs/notebooks/assets/
+docs/overrides/announcement.html
+
+# Local scratch directories
+/notebooks/
+/data/
+src/kbank/app/

kbank-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

kbank-0.0.1/.python-version

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

kbank-0.0.1/CHANGELOG.md

@@ -0,0 +1,22 @@
+# Release Notes
+
+All notable changes to **`KBank`** 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
+
+- **CSR Chemical Glycan Graphs & Monosaccharide Registry (`kbank.glycan`, `kbank.sugars`)**:
+  - Structure-of-Arrays (SoA) `Sugars` chemical registry encoding monosaccharide base rings, stereochemistry (`Anomer`, `Chirality`), ring forms, and non-stoichiometric substituents.
+  - Compressed Sparse Row (CSR) directed multigraphs (`Glycan`, `Glycans`) with canonical root-invariant topological hashing and Weisfeiler-Lehman graph kernels.
+- **Structural Parsers & Multi-Database Curation (`kbank.io`, `kbank.db`)**:
+  - `CSDBParser`, `IUPACParser`, and `KEGGParser` for bidirectional chemical graph parsing and serialization.
+  - Multi-database curation pipeline (`build_curated_glycan_records`) uniting **1,530** bacterial surface polysaccharide structures across CSDB, KEGG, ECODAB, EPS-DB, EK3D, and GlyTouCan paired *de novo* with `SeroGen` biosynthetic gene clusters (`GlycanRecords`).
+- **Biosynthetic Alignment & De Novo Structure Prediction (`kbank.biosynthesis`)**:
+  - `BiosyntheticAssigner` and `PanGraphConsensusPrior` Expectation-Maximization homology priors for bipartite enzyme-to-linkage assignment.
+  - 10-head factorized 1D-CNN `BiosyntheticClassifierSuite` (`ClusterClassifier`) predicting donor, acceptor, anomer, linkage position, and substituent specificity from protein sequences.
+  - `GlycanPredictor` combining `RelationalMPNN` message passing with a branch-and-bound Constrained Spanning Arborescence solver for *de novo* repeating-unit structure reconstruction.
+- **Interactive Benchmarks & Documentation**:
+  - Reproducible 16:9 Marimo slide decks (`curate_glycans.py`, `train_cluster_classifier.py`, `train_glycan_predictor.py`) and unified SeroVerse Zensical documentation.

kbank-0.0.1/CITATION.cff

@@ -0,0 +1,18 @@
+cff-version: 1.2.0
+message: "If you use KBank in your work, please cite it using the following metadata."
+title: "KBank: Geno-glycomic database for bacterial glycans"
+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/KBank"
+url: "https://seroverse.github.io/KBank/"
+license: "GPL-3.0-only"
+keywords:
+  - bioinformatics
+  - genomics
+  - serotyping
+  - microbiology