Adding Unit Tests for next release

.github/workflows/pre-commit.yml

@@ -12,8 +12,8 @@ jobs:
   pre-commit:
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ["3.10", "3.11", "3.12"]
+        os: [ubuntu-latest]
+        python-version: ["3.10"]
 
     runs-on: ${{ matrix.os }}
 
@@ -27,43 +27,15 @@ jobs:
           python-version: ${{ matrix.python-version }}
           check-latest: true
 
-      - name: Cache pip dependencies
-        uses: actions/cache@v3
-        with:
-          path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt', '**/requirements-dev.txt') }}
-          restore-keys: ${{ runner.os }}-pip-
-
-      - name: Install Python dependencies
+      - name: Install pre-commit
         run: |
-          python -m pip install --upgrade pip
-          pip install -r requirements.txt
-          pip install -r requirements-dev.txt
-          pip install torch
-          pip install torch_geometric
-        shell: bash
-
-      # - name: Install R
-      #   uses: r-lib/actions/setup-r@v2
-      #   with:
-      #     r-version: "latest"
-
-      # - name: Install R packages
-      #   run: |
-      #     Rscript -e "if (!requireNamespace('BiocManager', quietly = TRUE)) install.packages('BiocManager', repos='https://cran.r-project.org')"
-      #     Rscript -e "install.packages(c('dplyr', 'jsonlite'), repos='https://cran.r-project.org')"
-      #     Rscript -e "BiocManager::install(c('impute', 'preprocessCore', 'GO.db', 'AnnotationDbi'), update=FALSE, ask=FALSE)"
-      #     Rscript -e "install.packages('SmCCNet', repos='https://cran.r-project.org')"
-      #     Rscript -e "install.packages('WGCNA', repos='https://cran.r-project.org')"
-      #   shell: bash
+          pip install --upgrade pip
+          pip install pre-commit
+          pip install black flake8 mypy
 
       - name: Cache pre-commit hooks
         uses: actions/cache@v3
         with:
           path: ~/.cache/pre-commit
           key: pre-commit-${{ runner.os }}-${{ hashFiles('.pre-commit-config.yaml') }}
           restore-keys: pre-commit-${{ runner.os }}-
-
-      - name: Run Pre-Commit Checks
-        if: matrix.os != 'ubuntu-latest'
-        run: pre-commit run --all-files --show-diff-on-failure

.github/workflows/publish.yml

@@ -0,0 +1,43 @@
+name: Publish to PyPI and GitHub Packages
+
+on:
+  push:
+    tags:
+      - "v*.*.*"
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Install build tools
+        run: |
+          python -m pip install --upgrade pip setuptools wheel twine
+
+      - name: Build source & wheel
+        run: |
+          python setup.py sdist bdist_wheel
+
+      - name: Publish to GitHub Packages
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          twine upload \
+            --repository-url https://upload.pypi.github.io/UCD-BDLab/BioNeuralNet \
+            dist/*
+
+      - name: Publish to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+        run: |
+          twine upload dist/*

.github/workflows/python-app.yml

@@ -41,6 +41,9 @@ jobs:
           pip install torch_geometric
         shell: bash
 
+      - name: Run pytest
+        run: pytest tests/
+
       # - name: Install R
       #   uses: r-lib/actions/setup-r@v2
       #   with:
@@ -54,16 +57,3 @@ jobs:
       #     Rscript -e "install.packages('SmCCNet', repos='https://cran.r-project.org')"
       #     Rscript -e "install.packages('WGCNA', repos='https://cran.r-project.org')"
       #   shell: bash
-
-      # - name: Run tests with pytest
-      #   run: |
-      #     find . -name ".coverage*" -delete
-      #     pytest --cov=bioneuralnet --cov-report=xml tests/
-
-      # - name: Upload coverage to Codecov
-      #   uses: codecov/codecov-action@v3
-      #   with:
-      #     token: ${{ secrets.CODECOV_TOKEN }}
-      #     files: ./coverage.xml
-      #     flags: unittests
-      #     name: codecov-umbrella

.gitignore

@@ -25,7 +25,7 @@ doc_examples_outdated
 dpmon_output
 .enviroment
 TCGA-BRCA_Dataset_testing*.ipynb
-
+testsOLD
 # Other example data and tests not needed in the repo.
 
 Output**

.pre-commit-config.yaml

@@ -35,7 +35,7 @@ repos:
 
       - id: clean-coverage-files
         name: Remove stale .coverage files
-        entry: bash -c "find . -name '.coverage*' -delete"
+        entry: bash -c "find . -name '.coverage*' -exec rm -f {} + 2>/dev/null || true"
         language: system
         stages: [pre-commit]
 
@@ -56,8 +56,8 @@ repos:
         language: system
         stages: [pre-commit]
 
-#      - id: run-tests
-#        name: Run Tests with Pytest
-#        entry: pytest --ignore=docs/source/examples --cov=bioneuralnet --cov-report=term-missing || true
-#        language: system
-#        types: [python]
+      - id: run-tests
+        name: Run Tests with Pytest
+        entry: bash -c "pytest tests"
+        language: system
+        types: [python]

CHANGELOG.md

@@ -66,7 +66,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 - **Updated Tutorials and Documentation**: New end to end jupiter notebook example.
 - **Updated Test**: All test have been updated and new ones have been added.
 
-## [1.0.1] to [1.0.8] - 2025-04-24
+## [1.0.1] to [1.0.9] - 2025-04-24
 
 - **BUG**: A bug related to rdata files missing
 - **New realease**: A new release will include documentation for the other updates. (1.1.0)

README.md

@@ -1,4 +1,4 @@
-# BioNeuralNet: Multi-Omics Integration with Graph Neural Networks
+# BioNeuralNet: A Graph Neural Network based Multi-Omics Network Data Analysis Tool
 
 [![License](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/UCD-BDLab/BioNeuralNet/blob/main/LICENSE)
 [![PyPI](https://img.shields.io/pypi/v/bioneuralnet)](https://pypi.org/project/bioneuralnet/)
@@ -8,7 +8,7 @@
 [![Documentation](https://img.shields.io/badge/docs-read%20the%20docs-blue.svg)](https://bioneuralnet.readthedocs.io/en/latest/)
 
 
-## Welcome to BioNeuralNet 1.0.8
+## Welcome to BioNeuralNet 1.0.9
 
 ![BioNeuralNet Logo](assets/LOGO_WB.png)
 

bioneuralnet/__init__.py

@@ -29,7 +29,7 @@
     - `datasets`: Contains example (synthetic) datasets for testing and demonstration purposes.
 """
 
-__version__ = "1.0.8"
+__version__ = "1.0.9"
 
 from .network_embedding import GNNEmbedding
 from .downstream_task import SubjectRepresentation

bioneuralnet/downstream_task/subject_representation.py

@@ -62,14 +62,17 @@ def __init__(
         if omics_data is None or omics_data.empty:
             raise ValueError("Omics data must be non-empty.")
 
-        if embeddings is None or embeddings.empty:
-            self.logger.info(
-                "No embeddings provided, please review documentation to see how to generate embeddings.")
+        if embeddings is None:
+            self.logger.warning("No embeddings provided, please review documentation to see how to generate embeddings.")
             raise ValueError("Embeddings must be non-empty.")
 
         if not isinstance(embeddings, pd.DataFrame):
             raise ValueError("Embeddings must be provided as a pandas DataFrame.")
 
+        if embeddings.empty:
+            self.logger.warning("No embeddings provided, please review documentation to see how to generate embeddings.")
+            raise ValueError("Embeddings must be non-empty.")
+
         if tune and phenotype_data is None:
             raise ValueError("Phenotype data must be provided for classification-based tuning.")
 
@@ -260,6 +263,9 @@ def _integrate_embeddings(self, reduced: pd.DataFrame, method="multiply", alpha=
 
         This is so at least 50% of the final output is influenced by the computed weight
         """
+        if not isinstance(reduced, (pd.DataFrame, pd.Series)):
+            raise ValueError("Reduced embeddings must be a pandas DataFrame or Series.")
+
         missing_features = set(self.omics_data.columns) - set(reduced.index)
         if missing_features:
             self.logger.warning(f"Missing {len(missing_features)} features in reduced embeddings: {list(missing_features)[:5]}")
@@ -277,8 +283,6 @@ def _integrate_embeddings(self, reduced: pd.DataFrame, method="multiply", alpha=
                 weight_series = reduced.mean(axis=1)
             elif isinstance(reduced, pd.Series):
                 weight_series = (reduced - reduced.min()) / (reduced.max() - reduced.min())
-            else:
-                raise ValueError("Reduced embeddings must be a pandas DataFrame or Series.")
 
             weight_series = weight_series.fillna(0)
             ranks = weight_series.rank(method="average")

bioneuralnet/network_embedding/gnn_embedding.py

@@ -89,7 +89,8 @@ def __init__(
         if omics_data.empty:
             raise ValueError("Omics data cannot be empty.")
         if clinical_data is not None and clinical_data.empty:
-            raise ValueError("Clinical data was provided but is empty.")
+            self.logger.warning("Clinical data was provided but is empty, setting to None.")
+            clinical_data = None
 
         if adjacency_matrix.shape[0] != adjacency_matrix.shape[1]:
             raise ValueError("Adjacency matrix must be square.")

bioneuralnet/utils/graph.py

@@ -4,6 +4,9 @@
 from typing import Optional
 import torch.nn.functional as F
 from sklearn.covariance import GraphicalLasso
+from .logger import get_logger
+
+logger = get_logger(__name__)
 
 def gen_similarity_graph(X:pd.DataFrame, k:int = 15, metric:str = "cosine", mutual:bool = False, per_node:bool = True, self_loops:bool = True) -> pd.DataFrame:
     """
@@ -30,6 +33,7 @@ def gen_similarity_graph(X:pd.DataFrame, k:int = 15, metric:str = "cosine", mutu
         raise TypeError("X must be a pandas.DataFrame")
 
     N = x_torch.size(0)
+    k = min(k, N-1)
 
     # full similarity matrix
     if metric == "cosine":
@@ -280,18 +284,25 @@ def gen_lasso_graph(X: pd.DataFrame, alpha: float = 0.01, self_loops: bool = Tru
     """
     if isinstance(X, pd.DataFrame):
         nodes = X.index
-        x_numpy = X.values
+        x_numpy = X.values.T
     else:
         raise TypeError("X must be a pandas.DataFrame")
 
-    model = GraphicalLasso(alpha=alpha, max_iter=200)
-    model.fit(x_numpy)
+    try:
+        model = GraphicalLasso(alpha=alpha, max_iter=1000)
+        model.fit(x_numpy)
+
+        P = torch.from_numpy(model.precision_).abs()
+        W = (P + P.t()) / 2
 
-    P = torch.from_numpy(model.precision_).abs()
-    W = (P + P.t()) / 2
+    except FloatingPointError:
+        logger.warning("Graphical Lasso failed to converge, using identity matrix instead.")
+        N = len(nodes)
+        W = torch.eye(N, dtype=torch.float32)
 
     if self_loops:
-        W.fill_diagonal_(W.diagonal() + 1.0)
+        diag_indices = torch.arange(W.size(0), device=W.device)
+        W[diag_indices, diag_indices] += 1.0
 
     W = F.normalize(W, p=1, dim=1)
     final_graph = pd.DataFrame(W.cpu().numpy(), index=nodes, columns=nodes)

docs/jupyter_execute/Quick_Start.ipynb

@@ -913,7 +913,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "BioNeuralNet version: 1.0.8\n"
+      "BioNeuralNet version: 1.0.9\n"
      ]
     }
    ],

docs/source/Quick_Start.ipynb

@@ -913,7 +913,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "BioNeuralNet version: 1.0.8\n"
+      "BioNeuralNet version: 1.0.9\n"
      ]
     }
    ],

docs/source/TCGA-BRCA_Dataset.ipynb

@@ -60,27 +60,6 @@
     "- [Direct Download BRCA](http://firebrowse.org/?cohort=BRCA&download_dialog=true)\n"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "60a6b53c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# adjusting global pandas options for better display on web documentation\n",
-    "import pandas as pd\n",
-    "import warnings\n",
-    "import logging\n",
-    "\n",
-    "pd.set_option(\"display.max_columns\", 5)\n",
-    "pd.set_option(\"display.expand_frame_repr\", False)\n",
-    "warnings.filterwarnings(\"ignore\", category=UserWarning)\n",
-    "warnings.filterwarnings(\"ignore\", category=DeprecationWarning)\n",
-    "logging.getLogger(\"ray\").setLevel(logging.ERROR)\n",
-    "logging.getLogger(\"ray.tune\").setLevel(logging.ERROR)\n",
-    "logging.getLogger(\"torch_geometric\").setLevel(logging.ERROR)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "c9698b74",

docs/source/conf.py

@@ -7,7 +7,7 @@
 try:
     release = metadata.version("bioneuralnet")
 except metadata.PackageNotFoundError:
-    release = "1.0.8"
+    release = "1.0.9"
 
 project = "BioNeuralNet"
 version = release

docs/source/index.rst

@@ -1,5 +1,5 @@
-BioNeuralNet - Multi-Omics Integration with Graph Neural Networks
-=================================================================
+BioNeuralNet: A Graph Neural Network based Multi-Omics Network Data Analysis Tool
+=================================================================================
 
 .. image:: https://img.shields.io/badge/license-MIT-blue.svg
    :target: https://github.com/UCD-BDLab/BioNeuralNet/blob/main/LICENSE

requirements-dev.txt

@@ -32,10 +32,10 @@ build
 
 #others
 ipywidgets
-cptac
+#cptac
 dtt
 tensorboardX
 debugpy
 PyYAML
-node2vec
+#node2vec
 wheel

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = bioneuralnet
-version = 1.0.8
+version = 1.0.9
 author = Vicente Ramos
 author_email = vicente.ramos@ucdenver.edu
 description = A comprehensive framework for integrating multi-omics data with neural network embeddings.