pytoml

.github/workflows/python-publish.yml

@@ -0,0 +1,53 @@
+name: Upload Python Package
+
+on:
+  workflow_run:
+    workflows: ["Create Release with Images"]
+    types:
+      - completed
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install pypa/build
+        run: >-
+          python3 -m
+          pip install
+          build
+          --user
+      - name: Build a binary wheel and a source tarball
+        run: python3 -m build
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/kegg-pathways-completeness
+    permissions:
+      id-token: write # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v3
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/tests.yml

@@ -0,0 +1,28 @@
+name: Tests
+
+on:
+  push:
+    branches: [master, pypi-release]
+  pull_request:
+    branches: [master]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [ '3.8', '3.11' ]
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: pip install .[test]
+
+    - name: Run pytest
+      run: pytest

README.md

@@ -3,40 +3,24 @@
 ![Coverage.py coverage](badges/coverage.svg)
 
 EukCC is a completeness and contamination estimator for metagenomic assembled
-microbial eukaryotic genomes. 
-
-With version 2, EukCC should provide a better experience than
-version 1. We aim at creating a stable package with long term support.
-
-**Note**: Version 2 is not compatible with previous versions, most commandline arguments changed.
-So version 2 is **not** a drop in replacement.
+microbial eukaryotic genomes.
 
 ## Documentation
 Head over to https://eukcc.readthedocs.io/ to check out the documentation.
 
+## Run
 
-## Quickstart
-
-Here a super fast overview on how to get started using singularity. For more information
-please see the documentation.
-
+### Download EukCC2 database from [FTP](http://ftp.ebi.ac.uk/pub/databases/metagenomics/eukcc/)
 ```
 # create a folder were to keep the database
 mkdir eukccdb
 cd eukccdb
 wget http://ftp.ebi.ac.uk/pub/databases/metagenomics/eukcc/eukcc2_db_ver_1.2.tar.gz
 tar -xzvf eukcc2_db_ver_1.2.tar.gz
 export EUKCC2_DB=$(realpath eukcc2_db_ver_1.2)
-
-# fetch and launch container
-singularity pull docker://quay.io/microbiome-informatics/eukcc
-
-singularity exec eukcc_latest.sif eukcc single -h
 ```
 
-Alternatively you can install EukCC using pip, but we recommend using the container.
-
-## Get the container
+### Quickstart using container
 
 Get EukCC quickly by fetching the container. 
 
@@ -46,9 +30,19 @@ https://quay.io/repository/microbiome-informatics/eukcc
 docker pull quay.io/microbiome-informatics/eukcc
 singularity pull docker://quay.io/microbiome-informatics/eukcc
 ```
-If you installed version 2: make sure to also fetch the database for version 2:
 
-http://ftp.ebi.ac.uk/pub/databases/metagenomics/eukcc/
+### Bioconda / pip
+
+Alternatively you can install EukCC using conda or pip. 
+
+In addition, you need to install mandatory requirements:
+- metaeuk=4.a0f584d
+- pplacer
+- epa-ng=0.3.8
+- hmmer=3.3
+- minimap2
+- bwa
+- samtools
 
 
 ## Outputs explanation
@@ -89,6 +83,11 @@ EukCC also uses metaEUK, hmmer, pplacer, ete3 and epa-ng.
 
 
 ## Changed compared to EukCC 1
+**Note**: 
+With version 2, EukCC should provide a better experience than
+version 1. Version 2 is not compatible with previous versions, most commandline arguments changed.
+So version 2 is **not** a drop in replacement.
+
 - Users can set the prevalence threshold  for marker sets. In EukCC 1 
   this was fixed to 98% single copy prevalence.  Now users could change that to be more strict.
   We find that often 100% single copy prevalence can be found. 

pyproject.toml

@@ -0,0 +1,62 @@
+[project]
+name = "eukcc"
+version = "2.1.3"
+readme = "README.md"
+license = {text = "GPLv3"}
+authors = [
+    { name = "Paul Saary", email = "[email protected]" },
+    { name = "MGnify team", email = "[email protected]" },
+]
+keywords = ["bioinformatics", "mags", "eukaryotic", "completeness", "contamination"]
+description = "Check eukaryotic genomes or MAGs for completeness and contamination"
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Python :: 3.6",
+    "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+    "Operating System :: Unix",
+]
+
+dependencies = [
+    "ete3>=3.1.3",
+    "numpy>=1.24.4",
+    "jsonpickle>=4.0.0",
+    "biopython==1.83",
+    "pysam==0.21.0"
+]
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = [
+    "eukcc",
+    "scripts",
+]
+
+[project.scripts]
+# eukcc
+eukcc = "eukcc.__main__:main"
+shared_markers = "eukcc.find_markerset:main"
+# scripts
+binlinks = "scripts.binlinks:main"
+filter_euk_bins = "scripts.filter_euk_bins:main"
+
+[project.optional-dependencies]
+tests = [
+    "pytest==7.4.0",
+    "pytest-md==0.2.0",
+    "pytest-workflow==2.0.1",
+    "ete3>=3.1.3",
+    "numpy>=1.24.4",
+    "jsonpickle>=4.0.0",
+    "biopython==1.83",
+    "pysam==0.21.0"
+]
+
+dev = [
+    "pre-commit==3.8.0",
+    "black==24.8.0",
+    "flake8==7.1.1",
+    "pep8-naming==0.14.1"
+]

requirements.txt

@@ -1,4 +1,7 @@
-ete3
-six
-numpy
-jsonpickle
+metaeuk==4.a0f584d
+pplacer
+epa-ng==0.3.8
+hmmer==3.3
+minimap2
+bwa
+samtools==1.12

tests/test_basic.py

@@ -1,6 +1,6 @@
 import unittest
 import os
-from eukcc.base import union_sets, load_SCMGs, percentage_sets, load_tax_info
+from .eukcc.base import union_sets, load_SCMGs, percentage_sets, load_tax_info
 
 TESTDATA_SCMG = os.path.join(os.path.dirname(__file__), "testfiles", "SCMG_TEST.csv")
 TESTDATA_SCMG_GZ = os.path.join(os.path.dirname(__file__), "testfiles", "SCMG_TEST.csv.gz")