Merge branch 'master' into insertion

.github/workflows/changelog.yaml

@@ -13,4 +13,4 @@ jobs:
       - uses: actions/checkout@v3
       - uses: dangoslen/changelog-enforcer@v3
         with:
-          skipLabels: 'skip-changelog'
+          skipLabels: 'skip-changelog'

.github/workflows/minimal__install.yaml

@@ -0,0 +1,43 @@
+name: minimal_install
+
+on:
+  push:
+    paths-ignore:
+      - "README.md"
+      - "docs/**"
+
+  pull_request:
+    paths-ignore:
+      - "README.md"
+      - "docs/*"
+      - "CHANGELOG.md"
+      - "CONTRIBUTORS.md"
+      - "CONTRIBUTING.md"
+      - "imgs/"
+
+jobs:
+  build_cpu:
+    runs-on: ubuntu-18.04
+    strategy:
+      matrix:
+        python-version: [3.7, 3.8, 3.9, 3.11]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+        # See: https://github.com/marketplace/actions/setup-conda
+      - name: Setup anaconda
+        uses: s-weigand/setup-conda@v1
+        with:
+          python-version: ${{ matrix.python-version }}
+          conda-channels: "conda-forge"
+
+      - name: Install Graphein
+        run: pip install -e .
+      - name: Install Extras
+        run: pip install -r .requirements/extras.in
+      - name: Install Dev Dependencies
+        run: pip install -r .requirements/dev.in
+      - name: Run unit tests and generate coverage report
+        run: pytest .
+      - name: Test notebook execution
+        run: pytest --nbval-lax notebooks/ --current-env --ignore-glob="notebooks/dataloader_tutorial.ipynb" --ignore-glob="notebooks/higher_order_graphs.ipynb" --ignore-glob="notebooks/protein_graph_analytics.ipynb" --ignore-glob="notebooks/subgraphing_tutorial.ipynb" --ignore-glob="notebooks/splitting_a_dataset.ipynb"

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.4.0
     hooks:
     -   id: trailing-whitespace
     -   id: end-of-file-fixer
@@ -19,4 +19,4 @@ repos:
 -   repo: https://github.com/pycqa/isort
     rev: 5.10.1
     hooks:
-    - id: isort
+    - id: isort

.readthedocs.yml

@@ -25,4 +25,4 @@ python:
   version: 3.8
   install:
     - method: setuptools
-      path: .
+      path: .

.requirements/base.in

@@ -15,7 +15,7 @@ rich-click
 seaborn
 pyyaml>=5.1,<6.*
 scikit-learn
-scipy 
+scipy
 tqdm
 typing_extensions
 wget

.requirements/extras.in

@@ -2,6 +2,6 @@ biovec
 propy3
 pyaaisc
 mpl_chord_diagram==0.3.2
-rdkit-pypi
+rdkit
 selfies
-smilite
+smilite

CHANGELOG.md

@@ -6,6 +6,7 @@
 #### Protein
 
 * [Bugfix] - [#223](https://github.com/a-r-j/graphein/pull/220) Fix handling of insertions in protein graphs. Insertions are now given IDs like: `A:SER:12:A`. Contribution by @manonreau.
+* [Bugfix] - [#226](https://github.com/a-r-j/graphein/pull/226) Catches failed AF2 structure downloads [#225](https://github.com/a-r-j/graphein/issues/225)
 * [Feature] - [#229](https://github.com/a-r-j/graphein/pull/220) Adds support for filtering KNN edges based on self-loops and chain membership. Contribution by @anton-bushuiev.
 * [Bugfix] - [#229](https://github.com/a-r-j/graphein/pull/220) Fixes bug in KNN edge computation. Contribution by @anton-bushuiev.
 * [Bugfix] - [#220](https://github.com/a-r-j/graphein/pull/220) Fixes edge metadata conversion to PyG. Contribution by @manonreau.

CODE_OF_CONDUCT.md

@@ -73,4 +73,4 @@ available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.ht
 [homepage]: https://www.contributor-covenant.org
 
 For answers to common questions about this code of conduct, see
-https://www.contributor-covenant.org/faq
+https://www.contributor-covenant.org/faq

Dockerfile

@@ -52,7 +52,7 @@ RUN export CUDA=$(python -c "import torch; print('cu'+torch.version.cuda.replace
     && pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-${TORCH}+${CUDA}.html --no-cache-dir \
     && pip install torch-geometric --no-cache-dir
 
-RUN pip install jupyter_contrib_nbextensions 
+RUN pip install jupyter_contrib_nbextensions
 RUN jupyter nbextension enable --py widgetsnbextension
 
 # Testing

MANIFEST.in

@@ -4,4 +4,4 @@ include versioneer.py
 include README.md
 include .requirements/*
 include graphein/protein/features/nodes/amino_acid_properties.csv
-include graphein/protein/features/nodes/meiler_embeddings.csv
+include graphein/protein/features/nodes/meiler_embeddings.csv

datasets/proteins_ligands/parse_dataset.ipynb

@@ -409,4 +409,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

datasets/proteins_metal/parse_dataset.ipynb

@@ -311,4 +311,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

datasets/proteins_nucleic/parse_dataset.ipynb

@@ -300,4 +300,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

datasets/proteins_nucleotides/parse_dataset.ipynb

@@ -313,4 +313,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

datasets/pscdb/process_data.ipynb

@@ -1894,4 +1894,4 @@
     },
     "nbformat": 4,
     "nbformat_minor": 4
-}
+}

docs/source/dataset_readme.rst

@@ -1 +1 @@
-.. mdinclude:: ../../datasets/README.md
+.. mdinclude:: ../../datasets/README.md

docs/source/datasets.rst

@@ -16,4 +16,3 @@ Summaries
    notebooks/pscdb_processing.nblink
    notebooks/pscdb_baselines.nblink
    datasets/ppisp
-

docs/source/datasets/ppisp.rst

@@ -17,4 +17,4 @@ The dataset can be viewed here: `a-r-j/graphein/datasets/pscdb <https://www.gith
 Reference
 ----------
 [1] Min Zeng, Fuhao Zhang, Fang-Xiang Wu, Yaohang Li, Jianxin Wang, Min Li. Protein-protein interaction site prediction
-through combining local and global features with deep neural networks. Bioinformatics. DOI:10.1093/bioinformatics/btz699
+through combining local and global features with deep neural networks. Bioinformatics. DOI:10.1093/bioinformatics/btz699

docs/source/datasets/pscdb.rst

@@ -11,4 +11,4 @@ The dataset can be viewed here: `a-r-j/graphein/datasets/pscdb <https://www.gith
 Reference
 ----------
 [1] Amemiya, T., Koike, R., Kidera, A., & Ota, M. (2011). PSCDB: a database for protein structural change upon ligand
-binding. Nucleic Acids Research, 40(D1), D554–D558. https://doi.org/10.1093/nar/gkr966
+binding. Nucleic Acids Research, 40(D1), D554–D558. https://doi.org/10.1093/nar/gkr966

docs/source/getting_started/introduction.rst

@@ -4,4 +4,3 @@ Graphein
 Graphein  is  a  python  library  for  constructing graph   and   surface-mesh   representations   of protein  structures  for  computational  analysis. The  library  interfaces  with  popular  geometric deep learning libraries: `DGL <https://www.dgl.ai/>`_ (and `DGL-LifeSci <https://lifesci.dgl.ai/>`_), `PyTorch Geometric <https://pytorch-geometric.readthedocs.io/en/latest/>`_ and `PyTorch3D <https://pytorch3d.org/>`_.
 
 As feature engineering is a vital step in a machine learning project, the library is designed to be highly flexible, allowing the user to parameterise the graph construction, scalable to facilitate working with large protein complexes,and containing useful pre-processing tools  for preparing experimental structure files. Graphein is also designed to facilitate network-based and graph-theoretic  analyses  of  protein  structures in  a  high-throughput  manner.
-

docs/source/license.rst

@@ -21,4 +21,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+SOFTWARE.

docs/source/modules/graphein.ml.rst

@@ -24,4 +24,4 @@ Dataset Splitting
 Utils
 -------
 .. automodule:: graphein.ml.utils
-    :members:
+    :members:

docs/source/modules/graphein.ppi.rst

@@ -46,4 +46,4 @@ BioGrid
 STRINGDB
 ^^^^^^^^^
 .. automodule:: graphein.ppi.parse_stringdb
-    :members:
+    :members:

docs/source/molecule_notebooks.rst

@@ -6,4 +6,4 @@ Molecules
     :glob:
 
     notebooks/molecule_tutorial.nblink
-    notebooks/molecules_from_zinc_and_chembl.nblink
+    notebooks/molecules_from_zinc_and_chembl.nblink