feat: extend NetworkCommons toward perturbation biology with LEMBAS integration

.gitattributes

@@ -0,0 +1,2 @@
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true -diff

.github/workflows/sphinx_autodoc.yaml

@@ -15,29 +15,15 @@ jobs:
         -   name: Install Pandoc
             run: |
               sudo apt-get install -y pandoc
-        -   name: Setup Python
-            uses: actions/setup-python@v5
+        -   name: Install uv
+            uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
             with:
-              python-version: '3.11'
-        -   name: Install Poetry
-            uses: snok/install-poetry@v1
-            with:
-                virtualenvs-create: true
-                virtualenvs-in-project: true
-                installer-parallel: true
-        -   name: Load cached venv
-            id: cached-poetry-dependencies
-            uses: actions/cache@v4
-            with:
-                path: .venv
-                key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
+                enable-cache: true
+                python-version: "3.11"
         -   name: Install dependencies
-            if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-            run: poetry install --no-interaction --no-root
-        -   name: Install library
-            run: poetry install --no-interaction
+            run: uv sync --locked --group docs
         -   name: Build documentation
-            run: poetry run make html --directory docs/
+            run: uv run make html --directory docs/
         -   name: Commit files
             run: |
                 git config --local user.email "action@github.com"

.github/workflows/test.yaml

@@ -42,39 +42,22 @@ jobs:
               echo "PATH=\"$(brew --prefix graphviz)/bin:$PATH\"" >> "$GITHUB_ENV"
               echo "CFLAGS=\"-I$(brew --prefix graphviz)/include\"" >> "$GITHUB_ENV"
               echo "LDFLAGS=\"-L$(brew --prefix graphviz)/lib\"" >> "$GITHUB_ENV"
-        -   name: Setup Python ${{ matrix.python }}
-            uses: actions/setup-python@v5
+        -   name: Install uv
+            uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
             with:
-              python-version: ${{ matrix.python }}
-        -   name: Install Poetry
-            uses: snok/install-poetry@v1
-            with:
-                virtualenvs-create: true
-                virtualenvs-in-project: true
-                installer-parallel: true
-        -   name: Load cached venv
-            id: cached-poetry-dependencies
-            uses: actions/cache@v4
-            with:
-                path: .venv
-                key: venv-${{ runner.os }}-${{ matrix.python }}-${{ hashFiles('**/poetry.lock') }}
+                enable-cache: true
+                python-version: ${{ matrix.python }}
         -   name: Install dependencies
-            if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-            run: |
-              poetry install --no-interaction --no-root
-        -   name: Install library
-            run: poetry install --no-interaction -E corneto-backends
+            run: uv sync --frozen --group test --extra corneto-backends
         -   name: Tests and coverage
             if: ${{ github.event_name == 'push' }}
-            run: |
-                poetry run pytest -v --cov --color=yes --durations=0
+            run: uv run pytest -v --cov --color=yes --durations=0
         -   name: Tests
             if: ${{ github.event_name == 'pull_request' }}
-            run: |
-                poetry run pytest -v --cov --color=yes --durations=0
+            run: uv run pytest -v --cov --color=yes --durations=0
         -   name: Upload coverage reports to Codecov
             if: ${{ github.event_name == 'push' }}
             env:
                 CODECOV_NAME: ${{ matrix.python }}-${{ matrix.os }}
             run: |
-                poetry run codecovcli --verbose upload-process -t ${{ secrets.CODECOV_TOKEN }} -n 'fast'-${{ github.run_id }} -F fast
+                uv run codecovcli --verbose upload-process -t ${{ secrets.CODECOV_TOKEN }} -n 'fast'-${{ github.run_id }} -F fast

.gitignore

@@ -38,4 +38,7 @@ work/
 test.ipynb
 flop.png
 *.h5ad
-.venv
+.venv
+.envrc
+requirements-local.txt
+flop_repo/

.pre-commit-config.yaml

@@ -14,37 +14,12 @@ repos:
     -   id: unexport
         args: [--refactor, --single_quotes]
         exclude: __init__.py$
--   repo: https://github.com/google/yapf
-    rev: v0.32.0
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.0
     hooks:
-    -   id: yapf
-        additional_dependencies: [toml]
-        stages: [manual]
--   repo: https://github.com/psf/black
-    rev: 23.3.0
-    hooks:
-    -   id: black
-        additional_dependencies: [toml]
-        stages: [manual]
--   repo: https://github.com/Instagram/Fixit
-    rev: 9d59f968e84bd2773f34b0069eeeaad3ce783254
-    hooks:
-    -   id: fixit-run-rules
-        stages: [manual]
--   repo: https://github.com/timothycrosley/isort
-    rev: 5.12.0
-    hooks:
-    -   id: isort
-        additional_dependencies: [toml]
--   repo: https://github.com/snok/pep585-upgrade
-    rev: v1.0.1
-    hooks:
-    -   id: upgrade-type-hints
-        args: [--futures=true]
--   repo: https://github.com/asottile/add-trailing-comma
-    rev: v2.4.0
-    hooks:
-    -   id: add-trailing-comma
+    -   id: ruff
+        args: [--fix]
+    -   id: ruff-format
 -   repo: https://github.com/myint/unify
     rev: v0.5
     hooks:
@@ -67,19 +42,9 @@ repos:
     -   id: check-symlinks
     -   id: check-yaml
         args: [--unsafe]
-    -   id: check-ast
     -   id: fix-encoding-pragma
-        args: [--remove] # for Python3 codebase, it's not necessary
+        args: [--remove]
     -   id: requirements-txt-fixer
--   repo: https://github.com/john-hen/Flake8-pyproject
-    rev: 1.2.3
-    hooks:
-    -   id: Flake8-pyproject
-        additional_dependencies:
-        -   flake8-docstrings
-        -   flake8-comprehensions
-        -   flake8-bugbear
-        -   git+https://github.com/saezlab/flake8-kwargs-spaces.git
 -   repo: https://github.com/rstcheck/rstcheck
     rev: v6.1.2
     hooks:
@@ -89,11 +54,6 @@ repos:
     rev: 1.13.0
     hooks:
     -   id: blacken-docs
--   repo: https://github.com/asottile/pyupgrade
-    rev: v3.3.1
-    hooks:
-    -   id: pyupgrade
-        args: [--py3-plus, --py38-plus, --keep-runtime-typing]
 -   repo: https://github.com/macisamuele/language-formatters-pre-commit-hooks
     rev: v2.8.0
     hooks:
@@ -103,7 +63,6 @@ repos:
     rev: v1.10.0
     hooks:
     -   id: python-use-type-annotations
-    -   id: python-check-blanket-noqa
     -   id: rst-backticks
     -   id: rst-directive-colons
     -   id: rst-inline-touching-normal

.readthedocs.yaml

@@ -1,15 +1,17 @@
 version: 2
 
-sphinx:
-    configuration: docs/src/conf.py
-
 build:
-    os: ubuntu-22.04
+    os: ubuntu-24.04
     tools:
-        python: "3.10"
+        python: "3.12"
+        uv: "latest"
 
 python:
     install:
-    -   method: pip
-        path: .
-    -   requirements: docs/src/requirements.txt
+        - method: uv
+          command: sync
+          groups:
+              - docs
+
+sphinx:
+    configuration: docs/src/conf.py

docs/src/api.rst

@@ -93,6 +93,24 @@ SignalingProfiler
 
     methods.run_signalingprofiler
 
+.. _api-perturbation:
+
+Perturbation response
+=====================
+.. module::networkcommons.methods
+.. currentmodule:: networkcommons
+
+.. autosummary::
+    :toctree: api
+    :recursive:
+
+    methods.network_to_perturbation_table
+    methods.split_perturbation_data
+    methods.evaluate_predictions
+    methods.run_mean_response_baseline
+    methods.run_ridge_baseline
+    methods.run_lembas_rnn
+
 .. _api-pk:
 
 Prior Knowledge
@@ -223,6 +241,23 @@ Phospho-EGF meta-analysis
     data.omics.phospho_egf_datatypes
     data.omics.phospho_egf_tables
 
+.. _api-lembas:
+
+LEMBAS
+~~~~~~
+.. module::networkcommons.data.omics
+.. currentmodule:: networkcommons
+
+.. autosummary::
+    :toctree: api
+    :recursive:
+
+    data.omics.lembas_datasets
+    data.omics.lembas_network
+    data.omics.lembas_ligands
+    data.omics.lembas_tfs
+    data.omics.lembas_annotation
+
 .. _api-eval:
 
 Evaluation and description
@@ -300,6 +335,7 @@ Utilities
     utils.to_networkx
     utils.read_network_from_file
     utils.network_from_df
+    utils.lembas_format_network
     utils.get_subnetwork
     utils.decoupler_formatter
     utils.targetlayer_formatter

docs/src/conf.py

@@ -23,7 +23,6 @@
     'sphinx_autodoc_typehints',
     'sphinx.ext.autosectionlabel',
     'sphinx_copybutton',
-    'numpydoc',
     'nbsphinx',
     'IPython.sphinxext.ipython_console_highlighting'
 ]
@@ -39,6 +38,8 @@
 # -- Options for HTML output
 master_doc = 'contents'
 
+nbsphinx_execute = 'never'
+
 autosummary_generate = True
 autosummary_imported_members = False
 autodoc_member_order = "alphabetical"

docs/src/contents.rst

@@ -45,4 +45,5 @@ NetworkCommons: Table of Contents
    :caption: Additional resources
 
    vignettes/A_moon
-   vignettes/B_pertpy
+   vignettes/B_pertpy
+   vignettes/C_lembas

docs/src/datasets.rst

@@ -108,6 +108,28 @@ Phosphoproteomics in response to EGF
 
 **Functions:** See API documentation for :ref:`Phospho-EGF meta-analysis<api-phosphoegf>`.
 
+.. _details-lembas:
+
+LEMBAS
+------
+
+**Alias:** lembas_macrophage, lembas_ligand_screen
+
+**Description:** Signaling network, ligand concentration and TF activity data from the LEMBAS resource
+
+**Publication Link:** `Nilsson, A. et al. Artificial neural networks enable genome-scale simulations of intracellular signaling. Nat Commun 13, 3069 (2022). <https://doi.org/10.1038/s41467-022-30684-y>`_
+
+**Data location:** `Zenodo (macrophage) <https://zenodo.org/records/10815391>`_ / `GitHub — Lauffenburger-Lab/LEMBAS (ligand screen) <https://github.com/Lauffenburger-Lab/LEMBAS>`_
+
+**Detailed Description:** Two experimental datasets used in the LEMBAS paper to train and evaluate the signaling network RNN model.
+The **macrophage dataset** (low-coverage) contains ~10 extracellular ligands across ~170 stimulation conditions in macrophages.
+The **ligand screen dataset** (high-coverage) contains ~60 extracellular ligands across ~500 conditions.
+Each dataset includes three components: a prior knowledge signaling network (protein–protein interactions with stimulating/inhibiting annotations),
+a ligand input matrix (binary presence/absence per condition), and a TF activity matrix (DoRothEA/VIPER scores normalised to [0, 1]).
+Node identifiers are UniProt IDs throughout.
+
+**Functions:** See API documentation for :ref:`LEMBAS <api-lembas>`.
+
 .. _details-pk: