Merge branch 'master' into hetatm_parsing

Author: a-r-j

.github/workflows/build.yaml

@@ -22,8 +22,8 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.8, 3.9, "3.10"]
-        torch: [1.13.0, 2.1.0, 2.2.0]
+        python-version: [3.8, 3.9, "3.10", "3.11"]
+        torch: [1.13.0, 2.1.0, 2.2.0, 2.3.0, 2.4.0]
     # https://github.com/marketplace/actions/setup-miniconda#use-a-default-shell
     defaults:
       run:
@@ -33,28 +33,33 @@ jobs:
         uses: actions/checkout@v3
         # See: https://github.com/marketplace/actions/setup-miniconda
       - name: Setup miniconda
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
         with:
           auto-update-conda: true
           miniforge-variant: Mambaforge
           channels: "conda-forge, salilab, pytorch, pyg"
           python-version: ${{ matrix.python-version }}
           use-mamba: true
+      - name: Install setuptools
+        run: pip install setuptools==69.5.1
       - name: Install Boost 1.7.3 (for DSSP)
         run: conda install -c anaconda libboost=1.73.0
       - name: Install DSSP
         run: conda install dssp -c salilab
       - name: Install mmseqs
         run: mamba install -c conda-forge -c bioconda mmseqs2
-      - name: Install PyTorch
-        #run: mamba install -c pytorch pytorch==${{matrix.torch}} cpuonly
-        run: pip install torch==${{matrix.torch}}+cpu -f https://download.pytorch.org/whl/torch_stable.html
+      - name: Install PyTorch (1.13.0)
+        if: matrix.torch == '1.13.0'
+        run: pip install torch==${{matrix.torch}}+cpu --extra-index-url https://download.pytorch.org/whl/cpu
+      - name: Install PyTorch (2.0+)
+        if: matrix.torch != '1.13.0'
+        run: pip install torch==${{matrix.torch}} -f https://download.pytorch.org/whl/cpu
       - name: Install PyG
         #run: mamba install -c pyg pyg
         run: pip install torch_geometric
       - name: Install torch-cluster
         #run: mamba install pytorch-cluster -c pyg
-        run: pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-${{matrix.torch}}+cpu.html
+        run: pip install torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-${{matrix.torch}}+cpu.html
       - name: Install BLAST
         run: sudo apt install ncbi-blast+
       - name: Install Graphein
@@ -68,4 +73,4 @@ jobs:
       - 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/datasets_and_dataloaders.ipynb" --ignore-glob="notebooks/foldcomp.ipynb"
+        run: pytest --nbval-lax notebooks/ --current-env --ignore-glob="notebooks/dataloader_tutorial.ipynb" --ignore-glob="notebooks/datasets_and_dataloaders.ipynb" --ignore-glob="notebooks/foldcomp.ipynb" --ignore-glob="notebooks/grn_tutorial.ipynb"

.github/workflows/minimal__install.yaml

@@ -34,7 +34,7 @@ jobs:
         uses: actions/checkout@v3
         # See: https://github.com/marketplace/actions/setup-miniconda
       - name: Setup miniconda
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
         with:
           auto-update-conda: true
           miniforge-variant: Mambaforge
@@ -50,4 +50,4 @@ jobs:
       - name: Run unit tests and generate coverage report
         run: pytest . --ignore-glob="tests/protein/tensor" --ignore="tests/ml/test_conversion.py" --ignore="tests/ml/test_torch_geometric_dataset.py"
       - 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" --ignore-glob="notebooks/protein_tensors.ipynb" --ignore-glob="notebooks/datasets_and_dataloaders.ipynb" --ignore-glob="notebooks/foldcomp.ipynb" --ignore-glob="notebooks/creating_datasets_from_the_pdb.ipynb"
+        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" --ignore-glob="notebooks/protein_tensors.ipynb" --ignore-glob="notebooks/datasets_and_dataloaders.ipynb" --ignore-glob="notebooks/foldcomp.ipynb" --ignore-glob="notebooks/creating_datasets_from_the_pdb.ipynb" --ignore-glob="notebooks/grn_tutorial.ipynb"

.requirements/base.in

@@ -1,5 +1,5 @@
 pandas<2.0.0
-biopandas>=0.5.0.dev0
+biopandas>=0.5.1
 biopython
 bioservices>=1.10.0
 deepdiff

CHANGELOG.md

@@ -8,6 +8,8 @@
 * Fix cluster file loading bug in `pdb_data.py` [#396](https://github.com/a-r-j/graphein/pull/396)
 
 #### Misc
+* set logging to false by default and added mmcif support [#402](https://github.com/a-r-j/graphein/pull/402)
+* add metadata options for uniprot, ecnumber and CATH code to pdb manager [#398](https://github.com/a-r-j/graphein/pull/398)
 * bumped logging level down from `INFO` to `DEBUG` at several places to reduced output length [#391](https://github.com/a-r-j/graphein/pull/391)
 * exposed `fill_value` and `bfactor` option to `protein_to_pyg` function. [#385](https://github.com/a-r-j/graphein/pull/385) and [#388](https://github.com/a-r-j/graphein/pull/388)
 * Updated Foldcomp datasets with improved setup function and updated database choices such as ESMAtlas. [#382](https://github.com/a-r-j/graphein/pull/382)

graphein/__init__.py

@@ -21,6 +21,8 @@
     ]
 )
 
+logger.disable("graphein")
+
 
 def verbose(enabled: bool = False):
     """Enable/Disable logging.

graphein/grn/parse_regnetwork.py

@@ -18,9 +18,12 @@
 import wget
 from loguru import logger as log
 
-from graphein.utils.utils import filter_dataframe, ping
+from graphein.utils.utils import deprecated, filter_dataframe, ping
 
 
+@deprecated(
+    "RegNetwork appears to be down. This warning will be removed in a future release if the service is restored."
+)
 def _download_RegNetwork(
     root_dir: Optional[Path] = None, network_type: str = "human"
 ) -> str:
@@ -86,6 +89,9 @@ def _download_RegNetwork(
     return file
 
 
+@deprecated(
+    "RegNetwork appears to be down. This warning will be removed in a future release if the service is restored."
+)
 def _download_RegNetwork_regtypes(root_dir: Optional[Path] = None) -> str:
     """
     Downloads RegNetwork regulatory interactions types to the root directory.
@@ -124,6 +130,9 @@ def _download_RegNetwork_regtypes(root_dir: Optional[Path] = None) -> str:
     return file
 
 
+@deprecated(
+    "RegNetwork appears to be down. This warning will be removed in a future release if the service is restored."
+)
 @functools.lru_cache()
 def load_RegNetwork_interactions(
     root_dir: Optional[Path] = None,
@@ -144,6 +153,9 @@ def load_RegNetwork_interactions(
     )
 
 
+@deprecated(
+    "RegNetwork appears to be down. This warning will be removed in a future release if the service is restored."
+)
 @functools.lru_cache()
 def load_RegNetwork_regulation_types(
     root_dir: Optional[Path] = None,
@@ -168,6 +180,9 @@ def load_RegNetwork_regulation_types(
     )
 
 
+@deprecated(
+    "RegNetwork appears to be down. This warning will be removed in a future release if the service is restored."
+)
 def parse_RegNetwork(
     gene_list: List[str], root_dir: Optional[Path] = None
 ) -> pd.DataFrame:
@@ -244,6 +259,9 @@ def standardise_RegNetwork(df: pd.DataFrame) -> pd.DataFrame:
     return df
 
 
+@deprecated(
+    "RegNetwork appears to be down. This warning will be removed in a future release if the service is restored."
+)
 def RegNetwork_df(
     gene_list: List[str],
     root_dir: Optional[Path] = None,

graphein/ml/clustering.py

@@ -85,7 +85,7 @@ def get_seq_records(
             "Alphabet given. Only checking for terminating *!\n"
         )
         check_sequences = False
-    with open(filename, "rU") as handle:
+    with open(filename, "r") as handle:
         records = list(SeqIO.parse(handle, file_format, alphabet=alphabet))
     del handle
     if check_sequences:

graphein/ml/datasets/foldcomp_dataset.py

@@ -236,10 +236,6 @@ def download(self):
                 asyncio.run(_)
             os.chdir(curr_dir)
             log.info("Download complete.")
-            # log.info("Moving files to raw directory...")
-
-            # for f in self._database_files:
-            #    shutil.move(f, self.root)
         else:
             log.info(f"FoldComp database already downloaded: {self.root}.")