XspecT 0.1.2__tar.gz → 0.2.0__tar.gz

xspect-0.2.0/.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-0.2.0/.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-0.2.0/.github/workflows/pylint.yml

@@ -0,0 +1,13 @@
+name: pylint
+on: [push]
+jobs:
+  black:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Pylint Code Linter
+        run: |
+          python -m pip install --upgrade pip
+          pip install .
+          pip install pylint
+          pylint --fail-under=9.0 src/xspect

xspect-0.2.0/.github/workflows/pypi.yml

@@ -0,0 +1,61 @@
+name: Publish to PyPI
+
+on:
+  workflow_dispatch:
+  release:
+    types:
+      - published
+jobs:
+  release-build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+
+      - name: Build release distributions
+        run: |
+          python -m pip install build
+          python -m build
+
+      - name: Upload distributions
+        uses: actions/upload-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+
+  upload_testpypi:
+    needs: [release-build]
+    runs-on: ubuntu-latest
+    environment: testpypi
+    permissions:
+      id-token: write
+    if: github.event_name == 'release' && github.event.action == 'published' && github.event.release.prerelease
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+      - uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+
+  upload_pypi:
+    needs: [release-build]
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    if: github.event_name == 'release' && github.event.action == 'published' && !github.event.release.prerelease
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+      - uses: pypa/gh-action-pypi-publish@release/v1

xspect-0.2.0/.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-0.2.0/.gitignore

@@ -0,0 +1,181 @@
+# 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-data/
+
+.devcontainer/

{XspecT-0.1.2/src/XspecT.egg-info → xspect-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: XspecT
-Version: 0.1.2
+Version: 0.2.0
 Summary: Tool to monitor and characterize pathogens using Bloom filters.
 License: MIT License
         
@@ -32,26 +32,19 @@ Classifier: License :: OSI Approved :: MIT License
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: Flask
-Requires-Dist: Flask-WTF
-Requires-Dist: WTForms
-Requires-Dist: Werkzeug
 Requires-Dist: biopython
-Requires-Dist: bitarray
-Requires-Dist: mmh3
-Requires-Dist: numpy
-Requires-Dist: pandas
 Requires-Dist: requests
 Requires-Dist: scikit-learn
-Requires-Dist: Psutil
-Requires-Dist: Matplotlib
-Requires-Dist: Pympler
-Requires-Dist: H5py
 Requires-Dist: Bio
-Requires-Dist: wheel
 Requires-Dist: loguru
-Requires-Dist: Pympler
 Requires-Dist: click
+Requires-Dist: python-slugify
+Requires-Dist: cobs-reloaded
+Requires-Dist: rbloom
+Requires-Dist: xxhash
+Requires-Dist: fastapi
+Requires-Dist: uvicorn
+Requires-Dist: python-multipart
 Provides-Extra: docs
 Requires-Dist: sphinx; extra == "docs"
 Requires-Dist: furo; extra == "docs"
@@ -63,9 +56,13 @@ Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-cov; extra == "test"
 
 # XspecT - Acinetobacter Species Assignment Tool
-<img src="/src/xspect/static/Logo.png" height="50%" width="50%">
+![Test](https://github.com/bionf/xspect2/actions/workflows/test.yml/badge.svg)
+[![linting: pylint](https://img.shields.io/badge/linting-pylint-yellowgreen)](https://github.com/pylint-dev/pylint)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
+<img src="/src/docs/img/logo.png" height="50%" width="50%">
 <!-- start intro -->
-XspecT is a Python-based tool to taxonomically classify sequence-reads (or assembled genomes) on the species and/or sub-type level using [Bloom Filters](https://en.wikipedia.org/wiki/Bloom_filter) and a [Support Vector Machine](https://en.wikipedia.org/wiki/Support-vector_machine). It also identifies existing [blaOxa-genes](https://en.wikipedia.org/wiki/Beta-lactamase#OXA_beta-lactamases_(class_D)) and provides a list of relevant research papers for further information.
+XspecT is a Python-based tool to taxonomically classify sequence-reads (or assembled genomes) on the species and/or sub-type level using [Bloom Filters] and a [Support Vector Machine]. It also identifies existing [blaOxa-genes] and provides a list of relevant research papers for further information.
 <br/><br/>
 
 XspecT utilizes the uniqueness of kmers and compares extracted kmers from the input-data to a reference database. Bloom Filter ensure a fast lookup in this process. For a final prediction the results are classified using a Support Vector Machine. 
@@ -75,6 +72,10 @@ Local extensions of the reference database are supported.
 <br/>
 
 The tool is available as a web-based application and a smaller command line interface.
+
+[Bloom Filters]: https://en.wikipedia.org/wiki/Bloom_filter
+[Support Vector Machine]: https://en.wikipedia.org/wiki/Support-vector_machine
+[blaOxa-genes]: https://en.wikipedia.org/wiki/Beta-lactamase#OXA_beta-lactamases_(class_D)
 <!-- end intro -->
 
 <!-- start quickstart -->
@@ -83,11 +84,7 @@ To install Xspect, please download the lastest 64 bit Python version and install
 ```
 pip install xspect
 ```
-If you would like to train filters yourself, you need to install Jellyfish, which is used to count distinct k-meres in the assemblies. It can be installed using bioconda:
-```
-conda install -c bioconda jellyfish
-```
-On Apple Silicon, it is possible that this command installs an incorrect Jellyfish package. Please refer to the official [Jellyfish project](https://github.com/gmarcais/Jellyfish) for installation guidance.
+Please note that Apple Silicon is currently not supported.
 
 ## Usage
 ### Get the Bloomfilters
@@ -101,9 +98,9 @@ xspect train you-ncbi-genus-name
 ```
 
 ### How to run the web app
-Run the following command lines in a console, a browser window will open automatically after the application is fully loaded.
+To run the web app, install and run [XspecT Web](https://github.com/aromberg/xspect-web). Additionally, run XspecT in API mode:
 ```
-xspect web
+xspect api
 ```
 
 ### How to use the XspecT command line interface
@@ -111,13 +108,9 @@ Run xspect with the configuration you want to run it with as arguments.
 ```
 xspect classify your-genus path/to/your/input-set
 ```
-For further instructions on how to use the command line interface, execute:
+For further instructions on how to use the command line interface, please refer to the [documentation] or execute:
 ```
 xspect --help
 ```
+[documentation]: https://bionf.github.io/XspecT2/cli.html
 <!-- end quickstart -->
-
-## Input Data
-XspecT is able to use either raw sequence-reads (FASTQ-format .fq/.fastq) or already assembled genomes (FASTA-format .fasta/.fna). Using sequence-reads saves up the assembly process but high-quality reads with a low error-rate are needed (e.g. Illumina-reads).
-
-The amount of reads that will be used has to be set by the user when using sequence-reads. The minimum amount is 5000 reads for species classification and 500 reads for sub-type classification. The maximum number of reads is limited by the browser and is usually around ~8 million reads. Using more reads will lead to a increased runtime (xsec./1mio reads).

xspect-0.2.0/README.md

@@ -0,0 +1,59 @@
+# XspecT - Acinetobacter Species Assignment Tool
+![Test](https://github.com/bionf/xspect2/actions/workflows/test.yml/badge.svg)
+[![linting: pylint](https://img.shields.io/badge/linting-pylint-yellowgreen)](https://github.com/pylint-dev/pylint)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
+<img src="/src/docs/img/logo.png" height="50%" width="50%">
+<!-- start intro -->
+XspecT is a Python-based tool to taxonomically classify sequence-reads (or assembled genomes) on the species and/or sub-type level using [Bloom Filters] and a [Support Vector Machine]. It also identifies existing [blaOxa-genes] and provides a list of relevant research papers for further information.
+<br/><br/>
+
+XspecT utilizes the uniqueness of kmers and compares extracted kmers from the input-data to a reference database. Bloom Filter ensure a fast lookup in this process. For a final prediction the results are classified using a Support Vector Machine. 
+<br/>
+
+Local extensions of the reference database are supported.
+<br/>
+
+The tool is available as a web-based application and a smaller command line interface.
+
+[Bloom Filters]: https://en.wikipedia.org/wiki/Bloom_filter
+[Support Vector Machine]: https://en.wikipedia.org/wiki/Support-vector_machine
+[blaOxa-genes]: https://en.wikipedia.org/wiki/Beta-lactamase#OXA_beta-lactamases_(class_D)
+<!-- end intro -->
+
+<!-- start quickstart -->
+## Installation
+To install Xspect, please download the lastest 64 bit Python version and install the package using pip:
+```
+pip install xspect
+```
+Please note that Apple Silicon is currently not supported.
+
+## Usage
+### Get the Bloomfilters
+To download basic pre-trained filters, you can use the built-in command:
+```
+xspect download-filters
+```
+Additional species filters can be trained using:
+```
+xspect train you-ncbi-genus-name
+```
+
+### How to run the web app
+To run the web app, install and run [XspecT Web](https://github.com/aromberg/xspect-web). Additionally, run XspecT in API mode:
+```
+xspect api
+```
+
+### How to use the XspecT command line interface
+Run xspect with the configuration you want to run it with as arguments.
+```
+xspect classify your-genus path/to/your/input-set
+```
+For further instructions on how to use the command line interface, please refer to the [documentation] or execute:
+```
+xspect --help
+```
+[documentation]: https://bionf.github.io/XspecT2/cli.html
+<!-- end quickstart -->

xspect-0.2.0/docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)