XspecT 0.1.0__tar.gz → 0.1.3__tar.gz

XspecT-0.1.3/.github/workflows/black.yml

@@ -0,0 +1,11 @@
+name: black
+on: [push]
+jobs:
+  black:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Black Code Formatter
+        uses: lgeiger/black-action@master
+        with:
+          args: ". --check"

XspecT-0.1.3/.github/workflows/docs.yml

@@ -0,0 +1,33 @@
+name: sphinx
+
+on:
+  push:
+    branches: [main]
+
+permissions:
+  contents: write
+
+jobs:
+  docs:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+            python-version: "3.x"
+      - name: Install package with docs extras
+        run: |
+            python -m pip install --upgrade pip
+            pip install '.[docs]'
+      - name: Sphinx build
+        run: |
+          sphinx-build docs _build
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
+        with:
+          publish_branch: gh-pages
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: _build/
+          force_orphan: true

XspecT-0.1.3/.github/workflows/test.yml

@@ -0,0 +1,27 @@
+name: test
+on: [push]
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    steps:
+        - uses: actions/checkout@v4
+        - name: Set up Python
+          uses: actions/setup-python@v4
+          with:
+            python-version: "3.x"
+        - name: Install package
+          run: |
+            python -m pip install --upgrade pip
+            pip install '.[test]'
+        - name: Download filters
+          run: |
+            xspect download-filters
+        - name: Test with pytest
+          run: |
+            pytest --cov
+        - name: Upload coverage reports to Codecov
+          uses: codecov/codecov-action@v4
+          env:
+            CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        
+        

XspecT-0.1.3/.gitignore

@@ -0,0 +1,177 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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/
+
+# 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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.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
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+.conda/
+.vscode/
+.DS_Store
+genus_metadata/
+output
+filter/
+files/
+Training_data/
+
+tests/test_assemblies/
+string_list.txt
+saved_options.txt
+
+files/
+out.gv
+out.png

{XspecT-0.1.0/src/XspecT.egg-info → XspecT-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: XspecT
-Version: 0.1.0
+Version: 0.1.3
 Summary: Tool to monitor and characterize pathogens using Bloom filters.
 License: MIT License
         

XspecT-0.1.3/data/Results/Readme.txt

@@ -0,0 +1,54 @@
+These folders contain all the test-data.
+
+=== Folder Species-Assignment ===
+
+This Folder contains the results (Score-Vectors) from the taxonomic Assignment of over 3000 Genomes using different SVM-Parameters and Bloom Filters.
+File names explained:
+T1 = Training-Set 1 with up to 4 Genomes/BF
+T2 = Training-Set 2 with 1 Genome/BF
+poly = polynomial kernel-function
+rbf = radial basis-function
+1.0 and 1.5 refer to the Regulatory Parameter C of the SVM
+
+Further files with the name Test-Set_X contain the Score-Vectors of Tests with different amounts of used k-mers
+x = only every xth k-mer of the input-data was used
+
+The file Training_data_spec.csv contains the training-data (support vectors) of the SVM
+
+
+=== Folder Strain typing ===
+
+The Folder Strain-Typing contains the Score-vectors of both reference-datasets. Assembled Genomes and the
+Core-Genome of A. baumannii have been tested.
+Each dataset has been tested with the full-run (all k-mers of the Input-Sequence have been tested)
+and the quick-run (only every 10th k-mer has been tested). The used refernce is emntioned in the file-name.
+The Format is the following:
+
+NCBI Accession (GCF_...), Score IC1, Score IC2, Score IC3, ..., Score IC8
+
+The files with 'Reads as Input' are the results of tested non-overlapping read-samples.
+The Format is the following:
+
+Filename, number of tested reads, Score IC1, Score IC2, Score IC3, ..., Score IC8
+
+If the filename contains '...15% of the nucleotides changed', then ~15% of the nucleotides
+in a read have been changed in order to test sequencing-methods with high error rates.
+
+
+=== Folder OXA-Search ===
+
+The file 'OXA search in genomes' contains the results of the OXA-Search in genomes, the Format is the following:
+
+NCBI Accession (GCF_...), Score OXA-23, Score OXA-24, Score OXA-51, Score OXA-58
+
+
+The file 'OXA genes' contains the results of the OXA-Search used on other OXA-genes from the four families:
+
+correct OXA-Familie of the gene, OXA-Gene name, NCBI Accession, Score OXA-23, Score OXA-24, Score OXA-51, Score OXA-58
+
+
+The files 'OXA-search in assemblys' and 'OXA-search in reads' contain the results of OXA-Search in Sequence-reds and theiren 
+assemblys. 250.000 reads per .fq-file have been used. The format is:
+
+filename, Score OXA-23, Score OXA-24, Score OXA-51, Score OXA-58
+