add python distribution build workflow

.github/workflows/pypackage_build.yml

@@ -0,0 +1,92 @@
+name: Build and publish python package
+
+on:
+  push:
+    tags:
+      - "*"
+
+# Define permissions needed for the workflow GITHUB_TOKEN
+permissions:
+  contents: read # Allow checkout
+  packages: write # Allow publishing to GitHub Packages
+
+
+jobs:
+  build:
+    strategy:
+      matrix:
+        operating-system: [ macos-latest, ubuntu-latest, windows-latest ]
+        python-version: [ "3.10", "3.11", "3.12", "3.13" ]
+
+    name: Build Python Package (${{ matrix.operating-system }}, Python ${{ matrix.python-version }})
+    runs-on: ${{ matrix.operating-system }}
+
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.ref }}
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Hatch
+        run: pip install hatch
+
+      - name: Build distributions
+        run: hatch build # Uses pyproject.toml to build sdist and wheel into dist/
+
+      - name: Upload distributions artifact
+        uses: actions/upload-artifact@v4 # Action to save artifacts between jobs
+        with:
+          name: como-distribution-package-${{ matrix.operating-system }}-${{ matrix.python-version }}  # Name for the artifact
+          path: dist/ # Path to the directory to upload
+
+  publish:
+    strategy:
+      matrix:
+        python-version: [ "3.10", "3.11", "3.12", "3.13" ]
+        operating-system: [ macos-latest, windows-latest, ubuntu-latest ]
+
+    name: Publish to GitHub Packages
+    runs-on: ubuntu-latest
+    needs: build # Depends on the build job succeeding
+
+    # IMPORTANT: Only run the publish job when a tag starting with 'v' is pushed
+    if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v')
+
+
+    permissions: # Explicit permissions needed for this job
+      packages: write # Required to write to GitHub Packages registry
+      contents: read # Needed if accessing repo content (e.g., for download artifact)
+
+    steps:
+      - name: Download distributions artifact
+        uses: actions/download-artifact@v4 # Action to retrieve artifacts from previous job.
+        with:
+          name: como-distribution-package-${{ matrix.operating-system }}-${{ matrix.python-version }}
+          path: dist/
+
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Twine
+        run: pip install twine
+
+      - name: Publish package to GitHub Packages
+        env:
+          # Use __token__ as username and the automatically generated GITHUB_TOKEN as password
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          echo "Uploading to GitHub Packages for repository: ${{ github.repository }}"
+          # Construct the repository URL dynamically using the repository owner
+          TWINE_REPOSITORY_URL="https://pypi.pkg.github.com/${{ github.repository_owner }}"
+          python -m twine upload --verbose --repository-url ${TWINE_REPOSITORY_URL} dist/*
+
+
+

main/como/create_context_specific_model.py

@@ -172,7 +172,7 @@ def _gene_rule_logical(gpr_expression: str, level: int = 0) -> str:
         inner_string = inner_string.replace("[", "")
         inner_string = inner_string.replace("]", "")
 
-    expression_out = f"{gpr_expression[:loc_l]}{inner_string}{gpr_expression[loc_r + 1:]}"
+    expression_out = f"{gpr_expression[:loc_l]}{inner_string}{gpr_expression[loc_r + 1 :]}"
     expression_out = _gene_rule_logical(expression_out, level + 1)
 
     return expression_out
@@ -384,7 +384,7 @@ def _map_expression_to_reaction(
             continue
         for gid in gene_ids:
             if gid in gene_expressions.index:
-                rep_val = f' {gene_expressions.at[gid, "active"]} '
+                rep_val = f" {gene_expressions.at[gid, 'active']} "
             else:
                 rep_val = f" {unknown_val!s} "
             gene_reaction_rule = f" {gene_reaction_rule} "  # pad white space to prevent gene matches inside floats

main/como/rnaseq.py

@@ -10,7 +10,7 @@
 from functools import partial
 from multiprocessing.pool import Pool
 from pathlib import Path
 from typing import Callable, NamedTuple
 
 import numpy as np
 import numpy.typing as npt
@@ -418,13 +418,12 @@
     cores = multiprocessing.cpu_count() - 2
     logger.debug(f"Processing {total:,} samples through zFPKM transform using {cores} cores")
     logger.debug(
-        f"Will update every {update_per_step:,} steps as this is approximately "
-        f"{update_every_percent:.1%} of {total:,}"
+        f"Will update every {update_per_step:,} steps as this is approximately {update_every_percent:.1%} of {total:,}"
     )
 
     with Pool(processes=cores) as pool:
         kernel = KernelDensity(kernel="gaussian", bandwidth=bandwidth)
         chunksize = int(math.ceil(len(fpkm_df.columns) / (4 * cores)))
         partial_func = partial(_zfpkm_calculation, kernel=kernel, peak_parameters=peak_parameters)
         chunk_time = time.time()
         start_time = time.time()
@@ -606,13 +605,13 @@
         top_genes: npt.NDArray[bool] = genefilter(boolean_expression, top_func)
 
         # Only keep `entrez_gene_ids` that pass `min_genes`
         metric.entrez_gene_ids = [gene for gene, keep in zip(entrez_ids, min_genes) if keep]
         metric.gene_sizes = [gene for gene, keep in zip(gene_size, min_genes) if keep]
         metric.count_matrix = metric.count_matrix.iloc[min_genes, :]
         metric.normalization_matrix = metrics[sample].normalization_matrix.iloc[min_genes, :]
 
         keep_top_genes = [gene for gene, keep in zip(entrez_ids, top_genes) if keep]
         metric.high_confidence_entrez_gene_ids = [gene for gene, keep in zip(entrez_ids, keep_top_genes) if keep]
 
     metrics = calculate_z_score(metrics)
 

pyproject.toml

@@ -13,10 +13,11 @@ dependencies = [
     "loguru>=0.7.2",
     "pandas>=1.3.5",
     "plotly>=5.24.1",
-    "scanpy>=1.9.8",
+    "scanpy>=1.11.1",
     "scipy>=1.7.3",
     "scikit-learn>=1.5.2",
     "setuptools<60.0",
+    "statsmodels>=0.14",
     "openpyxl>=3.1.5",
     "aiofiles>=24.1.0",
     "aioftp>=0.23.1",
@@ -49,4 +50,4 @@ packages = ["main/como"]
 allow-direct-references = true
 
 [tool.pytest.ini_options]
-pythonpath = [ "main/src" ]
+pythonpath = [ "main/src" ]