update PDB urls to avoid deprecated ftp (#364)

* update PDB urls to avoid deprecated ftp * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add CI for torch 2.2.0 * restict CI action triggers to only code files * install torch cluster from pip * resolve float equality check * revert to mamba install * switch CI to pip installs for torch, pyg and deps. * remove torch vision * install cpu pyg deps. * update changelog * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: Arian Jamasb <arian.jamasb@roche.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
a-r-j · Feb 7, 2024 · 53290a5 · 53290a5
1 parent e1ab15f
commit 53290a5
Show file tree

Hide file tree

Showing 7 changed files with 46 additions and 43 deletions.
diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml
@@ -4,11 +4,17 @@ on:
   push:
     paths-ignore:
       - "README.md"
+      - "CHANGELOG.md"
+      - "CONTRIBUTORS.md"
+      - "CONTRIBUTING.md"
       - "docs/**"
 
   pull_request:
     paths-ignore:
       - "README.md"
+      - "CHANGELOG.md"
+      - "CONTRIBUTORS.md"
+      - "CONTRIBUTING.md"
       - "docs/*"
 
 jobs:
@@ -17,25 +23,7 @@ jobs:
     strategy:
       matrix:
         python-version: [3.8, 3.9, "3.10"]
-        torch: [1.13.0, 2.0.0, 2.1.0]
-        #include:
-        #  - torch: 1.6.0
-        #    torchvision: 0.7.0
-        #  - torch: 1.7.0
-        #    torchvision: 0.8.1
-        #  - torch: 1.8.0
-        #    torchvision: 0.9.0
-        #  - torch: 1.9.0
-        #    torchvision: 0.10.0
-        #  - torch: 1.8.0
-        #    torchvision: 0.9.0
-        #    python-version: 3.9
-        #  - torch: 1.9.0
-        #    torchvision: 0.10.0
-        #    python-version: 3.8
-        #  - torch: 1.9.0
-        #    torchvision: 0.10.0
-        #    python-version: 3.9
+        torch: [1.13.0, 2.1.0, 2.2.0]
     # https://github.com/marketplace/actions/setup-miniconda#use-a-default-shell
     defaults:
       run:
@@ -52,27 +40,21 @@ jobs:
           channels: "conda-forge, salilab, pytorch, pyg"
           python-version: ${{ matrix.python-version }}
           use-mamba: true
-      #- name: Set up Python ${{ matrix.python-version }}
-      #  uses: actions/setup-python@v2
-      #  with:
-      #python-version: ${{ matrix.python-version }}
-      #- name: Setup conda environment
-      #  run: conda env create -n graphein-dev python=${{ matrix.python-version }}
-      #- name: Activate Conda Environment
-      #  run: source activate graphein-dev
       - 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 torchvision==${{matrix.torchvision}}+cpu -f https://download.pytorch.org/whl/torch_stable.html
+        #run: mamba install -c pytorch pytorch==${{matrix.torch}} cpuonly
+        run: pip install torch==${{matrix.torch}}+cpu -f https://download.pytorch.org/whl/torch_stable.html
       - name: Install PyG
-        run: mamba install -c pyg pyg
+        #run: mamba install -c pyg pyg
+        run: pip install torch_geometric
       - name: Install torch-cluster
-        run: mamba install pytorch-cluster -c pyg
+        #run: mamba install pytorch-cluster -c pyg
+        run: pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-${{matrix.torch}}+cpu.html
       - name: Install BLAST
         run: sudo apt install ncbi-blast+
       - name: Install Graphein

diff --git a/.github/workflows/minimal__install.yaml b/.github/workflows/minimal__install.yaml
@@ -5,6 +5,9 @@ on:
     paths-ignore:
       - "README.md"
       - "docs/**"
+      - "CHANGELOG.md"
+      - "CONTRIBUTORS.md"
+      - "CONTRIBUTING.md"
 
   pull_request:
     paths-ignore:

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,9 +1,11 @@
 ### 1.7.6 - UNRELEASED
 
 #### Bugfixes
--   Remove hydrogen isotopes as well in `graphein.protein.graphs.deprotonate_structure`. [#337](https://github.com/a-r-j/graphein/pull/337)
--   Fixes bug in sidechain torsion angle computation for structures containing `PYL`/other non-standard amino acids ([#357](https://github.com/a-r-j/graphein/pull/357)). Fixes [#356](https://github.com/a-r-j/graphein/issues/356).
-- In Pandas 1.2.0 and later, The default value of regex for `Series.str.replace()` will change from `True` to False. So we need use regular expressions explicitly now, to suppress a FutureWarning. By @StevenAZy ([#359](https://www.github.com/a-r-j/graphein/pull/359))
+
+*   Remove hydrogen isotopes as well in `graphein.protein.graphs.deprotonate_structure`. [#337](https://github.com/a-r-j/graphein/pull/337)
+*   Fixes bug in sidechain torsion angle computation for structures containing `PYL`/other non-standard amino acids ([#357](https://github.com/a-r-j/graphein/pull/357)). Fixes [#356](https://github.com/a-r-j/graphein/issues/356).
+*   Replaces RCSB PDB FTP urls with new API. [#364](https://github.com/a-r-j/graphein/pull/364)
+*   In Pandas `1.2.0` and later, The default value of regex for `Series.str.replace()` will change from `True` to `False`. So we need use regular expressions explicitly now, to suppress a FutureWarning. By @StevenAZy ([#359](https://www.github.com/a-r-j/graphein/pull/359))
 
 
 ### 1.7.5 - 27/10/2024

diff --git a/graphein/ml/datasets/foldcomp_dataset.py b/graphein/ml/datasets/foldcomp_dataset.py
@@ -204,7 +204,9 @@ def processed_file_names(self):
     def download(self):
         """Downloads foldcomp database if not already downloaded."""
 
-        if not all(os.path.exists(self.root / f) for f in self._database_files):
+        if not all(
+            os.path.exists(self.root / f) for f in self._database_files
+        ):
             log.info(f"Downloading FoldComp dataset {self.database}...")
             curr_dir = os.getcwd()
             os.chdir(self.root)
@@ -249,7 +251,9 @@ def _get_indices(self):
             ]
         # Sub sample
         log.info(f"Sampling fraction: {self.fraction}...")
-        accessions = random.sample(accessions, int(len(accessions) * self.fraction))
+        accessions = random.sample(
+            accessions, int(len(accessions) * self.fraction)
+        )
         self.ids = accessions
         log.info("Creating index...")
         indices = dict(enumerate(accessions))
@@ -382,7 +386,9 @@ def __init__(
         self.val_split = val_split
         self.test_split = test_split
         self.transform = (
-            self._compose_transforms(transform) if transform is not None else None
+            self._compose_transforms(transform)
+            if transform is not None
+            else None
         )
 
         if (
@@ -421,7 +427,9 @@ def _get_indices(self):
         self.ids = ds.ids
         ds.db.close()
 
-    def _split_data(self, train_split: float, val_split: float, test_split: float):
+    def _split_data(
+        self, train_split: float, val_split: float, test_split: float
+    ):
         """Split the database into non-overlapping train, validation and test"""
         if not hasattr(self, "ids"):
             self._get_indices()

diff --git a/graphein/ml/datasets/pdb_data.py b/graphein/ml/datasets/pdb_data.py
@@ -1,4 +1,5 @@
 import gzip
+import math
 import os
 import shutil
 import subprocess
@@ -122,8 +123,8 @@ def __init__(
                 assert len(splits) == len(
                     split_ratios
                 ), f"Number of splits ({splits}) must match number of split ratios ({split_ratios})."
-                assert (
-                    sum(split_ratios) == 1.0
+                assert math.isclose(
+                    sum(split_ratios), 1.0
                 ), f"Split ratios must sum to 1.0: {split_ratios}."
                 self.split_ratios = split_ratios
             # Time-based splits

diff --git a/graphein/protein/utils.py b/graphein/protein/utils.py
@@ -10,7 +10,6 @@
 import tempfile
 from functools import lru_cache, partial
 from pathlib import Path
-from shutil import which
 from typing import Any, Dict, List, Optional, Tuple, Type, Union
 from urllib.error import HTTPError
 from urllib.request import urlopen
@@ -48,7 +47,9 @@ def get_obsolete_mapping() -> Dict[str, str]:
     """
     obs_dict: Dict[str, str] = {}
 
-    response = urlopen("ftp://ftp.wwpdb.org/pub/pdb/data/status/obsolete.dat")
+    response = urlopen(
+        "https://files.wwpdb.org/pub/pdb/data/status/obsolete.dat"
+    )
     for line in response:
         entry = line.split()
         if len(entry) == 4:
@@ -146,7 +147,7 @@ def download_pdb(
     Download PDB structure from PDB.
 
     If no structure is found, we perform a lookup against the record of
-    obsolete PDB codes (ftp://ftp.wwpdb.org/pub/pdb/data/status/obsolete.dat)
+    obsolete PDB codes (https://files.wwpdb.org/pub/pdb/data/status/obsolete.dat)
 
     :param pdb_code: 4 character PDB accession code.
     :type pdb_code: str

diff --git a/tests/protein/test_utils.py b/tests/protein/test_utils.py
@@ -11,6 +11,7 @@
 from graphein.protein.utils import (
     download_pdb,
     download_pdb_multiprocessing,
+    get_obsolete_mapping,
     save_graph_to_pdb,
     save_pdb_df_to_pdb,
     save_rgroup_df_to_pdb,
@@ -98,6 +99,11 @@ def test_download_structure_multi():
         assert str(path).endswith("4hhb.pdb")
 
 
+def test_download_obsolete_map():
+    mapping = get_obsolete_mapping()
+    assert len(mapping) > 100
+
+
 if __name__ == "__main__":
     test_save_graph_to_pdb()
     test_save_pdb_df_to_pdb()