An updated version that supports all Workflomics tools (disregarding the topicID)

.github/workflows/build.yml

@@ -3,37 +3,40 @@ name: Python package
 on:
   push:
     branches:
-    - main
+      - main
   pull_request:
     branches:
-    - main
+      - main
 
 jobs:
-
   build:
     name: Build for (${{ matrix.python-version }}, ${{ matrix.os }})
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
       matrix:
-        os: ['ubuntu-latest'] # ['ubuntu-latest', 'macos-latest', 'windows-latest']
-        python-version: ['3.9'] # ['3.7', '3.8', '3.9', '3.10', '3.11']
+        os: ["ubuntu-latest"]
+        python-version: ["3.11"]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Python info
-        shell: bash -l {0}
+
+      # Installation
+      - name: Install dependencies
         run: |
-          which python3
-          python3 --version
-      - name: Upgrade pip and install dependencies
+          python -m pip install poetry
+          poetry install
+
+      # Testing
+      - name: Test with pytest
         run: |
-          python3 -m pip install --upgrade pip setuptools
-          python3 -m pip install .[test]
-      - name: Run unit tests
-        run: pytest -v
-      - name: Verify that we can build the package
-        run: python3 setup.py sdist bdist_wheel
+          poetry run pytest
+      # Type checking
+      # - name: Type check
+      #   run: |
+      #     poetry run pytype .

.github/workflows/publish-docker.yml

@@ -0,0 +1,70 @@
+name: "Build and Publish docker image"
+
+on:
+  workflow_dispatch:  # This line adds the manual trigger
+  push:
+    branches: [ "main" ]
+  pull_request: # This should be removed once testing is complete
+    branches:
+      - main
+
+env:
+  REGISTRY: ghcr.io
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: downcase REPO name
+        run: |
+          echo "REPO=${GITHUB_REPOSITORY,,}" >>${GITHUB_ENV}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.REPO }}
+          tags: |
+            type=raw,value=latest,enable={{is_default_branch}}
+            type=ref,event=pr
+            type=semver,pattern={{version}}
+            type=sha,enable=true,priority=100,prefix=sha-,suffix=,format=short
+
+      - name: Install Arial font
+        run: |
+          sudo apt-get update
+          sudo apt install ttf-mscorefonts-installer
+          sudo apt-get install -y ttf-mscorefonts-installer
+          sudo fc-cache -f
+
+      - name: Build Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: false  # Do not push at this stage
+          tags: ${{ steps.meta.outputs.tags }}
+
+      - name: Push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: |
+            org.opencontainers.image.source=${{ github.event.repository.clone_url }}
+            org.opencontainers.image.created=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
+            org.opencontainers.image.revision=${{ github.sha }}

.gitignore

@@ -309,4 +309,4 @@ tags
 
 # Output files
 
-out_*
+out/out_*

CONTRIBUTING.md

@@ -13,13 +13,13 @@ The sections below outline the steps in each case.
 
 ## You have a question
 
-1. use the search functionality [here](git@github.com:Workflomics/workflomics-QCmetric/issues) to see if someone already filed the same issue;
+1. use the search functionality [here](git@github.com:Workflomics/pubmetric/issues) to see if someone already filed the same issue;
 2. if your issue search did not yield any relevant results, make a new issue;
 3. apply the "Question" label; apply other labels when relevant.
 
 ## You think you may have found a bug
 
-1. use the search functionality [here](git@github.com:Workflomics/workflomics-QCmetric/issues) to see if someone already filed the same issue;
+1. use the search functionality [here](git@github.com:Workflomics/pubmetric/issues) to see if someone already filed the same issue;
 1. if your issue search did not yield any relevant results, make a new issue, making sure to provide enough information to the rest of the community to understand the cause and context of the problem. Depending on the issue, you may want to include:
     - the [SHA hashcode](https://help.github.com/articles/autolinked-references-and-urls/#commit-shas) of the commit that is causing your problem;
     - some identifying information (name and version number) for dependencies you're using;

Dockerfile

@@ -0,0 +1,27 @@
+# Use an official Python runtime as a parent image
+FROM python:3.11-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install Poetry
+RUN pip install poetry
+
+# Copy the pyproject.toml and poetry.lock files
+COPY pyproject.toml poetry.lock /app/
+
+# Copy the application code before installing dependencies
+COPY . /app
+
+# Set the PYTHONPATH environment variable
+ENV PYTHONPATH=/app/src
+
+# Install the dependencies using Poetry without creating a virtual environment
+RUN poetry config virtualenvs.create false \
+    && poetry install --no-dev --no-interaction --no-ansi
+
+# Expose the port where the FastAPI app will run
+EXPOSE 8000
+
+# Command to run the FastAPI app using Uvicorn
+CMD ["poetry", "run", "uvicorn", "src.pubmetric.api_controller:app", "--host", "0.0.0.0", "--port", "8000"]

README.md

@@ -2,25 +2,46 @@
 
 This code is currently under development.
 
-
 ## Overview
 
 pubmetric is a library for benchmarking workflows based on the co-citation network connectivity of the publications describing the tools making up the workflow.
 
-
 ## Usage
 
 First start Cytoscape, then open your notebook environment and run the code.
 
-
 ## Dependencies
 
-Python packages listed in the `setup.py` file. You can install them using the following command: `pip install .`
-For the development, you can include the test dependencies by running `pip install .[test]`
+Python packages listed in the `pyproject.toml` file. You can install them using the following command:
+
+```bash
+    poetry install
+```
+
+If you're setting up the project for development and need the test dependencies, you can include them by running:
+
+```bash
+    poetry install --with dev
+```
 
 Cytoscape software, which can be downloaded from [https://cytoscape.org/](https://cytoscape.org/). Please make sure Cytoscape is open and running when executing the code.
 
+## For Developers
+
+Build the Docker image:
+
+```bash
+    sudo docker build -t pubmetric_v0.2 -f Dockerfile .
+```
+
+You can run the Docker image with the following command:
+
+```bash
+    sudo docker run -p 8000:8000 pubmetric_v0.2
+```
+
+This will start the FastAPI server on port 8000. For example you can access the OpenAPI specification (Swagger UI) at http://localhost:8000/docs.
 
 ## License
 
-This project is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). 
+This project is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).

data/out_default/doi_pmid_library.json

@@ -0,0 +1 @@
+{"10.1002/pmic.201200439": "23148064", "10.1038/nbt.2377": "23051804", "10.1093/nar/gkz369": "31066453", "10.1093/bioinformatics/bth092": "14976030", "10.1038/nmeth.4256": "28394336"}

data/out_default/tool_metadata.json

@@ -0,0 +1 @@
+{"creation_date": "2024-10-16 06:14:52.344396", "topic": "", "total_nr_tools": 15, "biotools_wo_pmid": 5, "pmid_from_doi": 5, "tools": [{"name": "PeptideProphet", "doi": null, "topics": ["Proteomics", "Proteomics experiment", "Statistics and probability"], "nr_publications": 1, "all_publications": ["12403597"], "publication_date": 2002, "pmid": "12403597"}, {"name": "ProteinProphet", "doi": null, "topics": ["Proteomics", "Proteomics experiment", "Statistics and probability"], "nr_publications": 1, "all_publications": ["14632076"], "publication_date": 2003, "pmid": "14632076"}, {"name": "StPeter", "doi": "10.1021/acs.jproteome.7b00786", "topics": ["Proteomics", "Proteomics experiment"], "nr_publications": 1, "all_publications": ["29400476"], "publication_date": 2018, "pmid": "29400476"}, {"name": "mzRecal", "doi": "10.1093/bioinformatics/btab056", "topics": ["Proteomics"], "nr_publications": 1, "all_publications": ["33538780"], "publication_date": 2021, "pmid": "33538780"}, {"name": "MS Amanda", "doi": "10.1021/pr500202e", "topics": ["Proteomics", "Protein modifications"], "nr_publications": 3, "all_publications": ["24909410", "33759252", "29863353"], "publication_date": 2014, "pmid": "24909410"}, {"name": "Comet", "doi": "10.1002/pmic.201200439", "topics": ["Proteomics", "Protein modifications"], "nr_publications": 2, "all_publications": [null, null], "publication_date": 2013, "pmid": "23148064"}, {"name": "idconvert", "doi": "10.1038/nbt.2377", "topics": ["Proteomics", "Proteomics experiment"], "nr_publications": 1, "all_publications": [null], "publication_date": 2012, "pmid": "23051804"}, {"name": "XTandem", "doi": "10.1093/bioinformatics/bth092", "topics": ["Proteomics", "Proteomics experiment"], "nr_publications": 1, "all_publications": [null], "publication_date": 2004, "pmid": "14976030"}, {"name": "MSFragger", "doi": "10.1038/nmeth.4256", "topics": ["Proteomics experiment", "Proteomics", "Protein modifications"], "nr_publications": 1, "all_publications": [null], "publication_date": 2017, "pmid": "28394336"}]}

dev-viz-notebooks/ML_metric_eval.ipynb

@@ -20,7 +20,7 @@
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "import seaborn as sns\n",
-    "import wfqc.network as nw\n",
+    "import pumetric.network as nw\n",
     "from scipy.stats import ttest_rel, spearmanr\n",
     "from sklearn.metrics import confusion_matrix, mean_squared_error\n",
     "from sklearn.model_selection import train_test_split\n",
@@ -30,7 +30,7 @@
     "from sklearn.svm import SVR\n",
     "from sklearn.preprocessing import KBinsDiscretizer\n",
     "from sklearn import tree\n",
-    "from wfqc.metrics import *\n",
+    "from pumetric.metrics import *\n",
     "from datetime import datetime"
    ]
   },

dev-viz-notebooks/TTP_data.ipynb

@@ -22,8 +22,8 @@
     "\n",
     "sys.path.insert(0, os.path.abspath(os.path.join(os.getcwd(), '../src')))\n",
     "\n",
-    "from wfqc.metrics import *\n",
-    "from wfqc.network import create_network\n"
+    "from pumetric.metrics import *\n",
+    "from pumetric.network import create_network\n"
    ]
   },
   {
@@ -471,7 +471,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/broken_dataset_gen.ipynb

@@ -953,7 +953,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/graph_statistics.ipynb

@@ -869,7 +869,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/metric_dev.ipynb

@@ -1344,7 +1344,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/network_dev.ipynb

@@ -412,7 +412,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/random_dataset_gen.ipynb

@@ -535,7 +535,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/rated_dataset_expanded.ipynb

@@ -298,7 +298,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/rated_dataset_parsing.ipynb

@@ -420,7 +420,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/thresholding.ipynb

@@ -238,7 +238,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },

dev-viz-notebooks/workflow_length_stats.ipynb

@@ -22,8 +22,8 @@
     "\n",
     "sys.path.insert(0, os.path.abspath(os.path.join(os.getcwd(), '../src')))\n",
     "\n",
-    "from wfqc.metrics import *\n",
-    "from wfqc.network import create_network\n"
+    "from pumetric.metrics import *\n",
+    "from pumetric.network import create_network\n"
    ]
   },
   {
@@ -125,7 +125,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "WFQC",
+   "display_name": "pumetric",
    "language": "python",
    "name": "python3"
   },