Resolves bugs in writing cif file and parity similarity calculation (#28

) * corrected the reversal of bondtype from zero to dative * use mol from sanitized result * enable parsing a subsets of ccds from components cif file * fix: fix error in writing cif file This fixes the error in generating inchikey while inchi is missing * style: formating * chore: removed unnecessary None * doc: add download badge and CLC feature * chore: add citation file * fix: write rdkit properties if it is present only * fix: correct use of length of list in python * fix: change bondtype from dative to zero for parity method SMARTS with dative bondtype fails to find substructures, hence dative bond types are changed to zero * test: add HEM for parity test * chore: linting and formatting * test: removed parity test using HEM to check if the segmentation fault in githubworkflow is due to this * fix: remove PDBe from unichem mapping sources * chore: Update dependencies and package management Update the project's dependencies and package management to use Poetry instead of pip. This includes installing Poetry and running `poetry install --with tests` to install the project dependencies. Remove the installation of `rdkit==2023.09.6` and `pre-commit`. * chore: Update pre-commit hooks and dependencies Update the pre-commit hooks to use the Ruff pre-commit hook repository and remove the black and flake8 hooks. Also, add the rST Formatter hook from the rstfmt repository. * chore: Update tests.yml to use Poetry for pre-commit and pytest commands Update the tests.yml file to use Poetry for the pre-commit and pytest commands. This ensures that the project's dependencies are installed correctly and that the pre-commit hooks are run using Poetry. The changes include replacing "pre-commit install" with "poetry run pre-commit install" and "pytest --cov=pdbeccdutils" with "poetry run pytest --cov=pdbeccdutils". * Minor formatting * chore: Install pre-commit package in tests.yml Add the installation of the pre-commit package in the tests.yml file to ensure that pre-commit hooks are run during the testing process. This will help catch and fix any code style or formatting issues before committing the changes. * chore: Update docs and publish pipelines to use poetry * test: add HEM to parity test * bump up version number * 🔥 remove __init__ file * 🔧 update documentation action to use poetry * 🔧 update publish action to use poetry * 🔧 update test action to use poetry * 🎨 move details from setup to pyproject.toml file * ♻️ use version information from pyproject.toml * 🩹 add CCDC to unichem resources * ✏️ fix typos * ✏️ fix typos * ♻️ refactor configs * 🎨 use single function to get properties of rdkit objects * 🎨 use rdkit_object_property function insted of get_componet_atom_id * ✨ get name of clc from entities * 🩹 import importlib.metadata * 🎨 linting and formatting * 🩹 removed "data" from the path * 🔧 add poetry.toml file * 🔧 update poetry.lock file * 🔧 remove pre-commit from test workflow * 🎨 linting and formatting * 📝 replace github downloads with pypi downloads * bump up version * 📝 update changelog for release 0.8.6 * 🔧 create hook to generate poetry.lock file * 📝 update readme with installation using poetry * 🔧 update the rdkit version number * 🔧 update poetry lock file --------- Co-authored-by: roshan <[email protected]> Co-authored-by: Sreenath Sasidharan Nair <[email protected]>
PDBeurope · Oct 30, 2024 · 618f680 · 618f680
1 parent dbe3b87
commit 618f680
Show file tree

Hide file tree

Showing 39 changed files with 1,626 additions and 235 deletions.
diff --git a/.github/workflows/documentation.yml b/.github/workflows/documentation.yml
@@ -20,12 +20,18 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: "3.10"
-      - run: |
-          pip install rdkit
-          pip install -e ".[docs]"
+      - name: Install poetry
+        uses: abatilo/actions-poetry@v2
+      - name: Define a cache for the virtual environment based on the dependencies lock file
+        uses: actions/cache@v3
+        with:
+          path: ./.venv
+          key: venv-${{ hashFiles('poetry.lock') }}
+      - name: Install the package with doc dependencies
+        run: poetry install --with docs
       - run: |
           cd doc
-          make html
+          poetry run sphinx-build -b html . _build/html
       - name: Deploy pages
         uses: peaceiris/actions-gh-pages@v3
         with:

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
@@ -25,14 +25,19 @@ jobs:
         uses: actions/setup-python@v3
         with:
           python-version: "3.10"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install build
+      - name: Install poetry
+        uses: abatilo/actions-poetry@v2
+      - name: Define a cache for the virtual environment based on the dependencies lock file
+        uses: actions/cache@v3
+        with:
+          path: ./.venv
+          key: venv-${{ hashFiles('poetry.lock') }}
+      - name: Install the package with doc dependencies
+        run: poetry install --without docs,tests
       - name: Build package
-        run: python -m build
+        run: poetry build
       - name: Publish package
-        uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+        uses: pypa/gh-action-pypi-publish@release/v1
         with:
           user: ${{ secrets.PYPI_USERNAME }}
           password: ${{ secrets.PYPI_PASSWORD }}
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -18,10 +18,13 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: "3.10"
-
+      - name: Install poetry
+        uses: abatilo/actions-poetry@v2
+      - name: Define a cache for the virtual environment based on the dependencies lock file
+        uses: actions/cache@v3
+        with:
+          path: ./.venv
+          key: venv-${{ hashFiles('poetry.lock') }}
       - run: |
-          pip install rdkit==2023.09.6
-          pip install -e ".[tests]"
-          pip install pre-commit
-          pre-commit install && pre-commit run --all
-      - run: pytest --cov=pdbeccdutils
+          poetry install --with tests
+          poetry run pytest --cov=pdbeccdutils
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -13,15 +13,25 @@ repos:
       - id: fix-byte-order-marker
       - id: end-of-file-fixer
       - id: check-ast
+      - id: no-commit-to-branch
 
-  - repo: https://github.com/ambv/black
-    rev: 22.3.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.3.5 # Ruff version.
     hooks:
-      - id: black
-
-  - repo: https://github.com/pycqa/flake8
-    rev: 3.9.1
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+  - repo: https://github.com/dzhu/rstfmt
+    rev: v0.0.14
     hooks:
-      - id: flake8
-        args: ["--max-line-length=88", "--ignore=E501,W503"]
-        exclude: \.cif$
+      - id: rstfmt
+        name: rST Formatter
+  - repo: https://github.com/python-poetry/poetry
+    rev: "1.8.2"
+    hooks:
+      - id: poetry-check
+      - id: poetry-lock
+        args:
+          - "--no-update"
+          - "--check"
+
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,12 @@
 # Changelog
 
+## RELEASE 0.8.6 - Oct 28, 2024
+
+### Features
+* Enable parsing of a subset of CCDs from the Chemical Component Dictionary
+* Added CCDC to UniChem resources
+
+
 ## RELEASE 0.8.5 - May 26, 2024
 
 ### Features

diff --git a/CITATION.cff b/CITATION.cff
@@ -0,0 +1,53 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+- family-names: "Kunnakkattu"
+  given-names: "Ibrahim Roshan"
+  orcid: "https://orcid.org/0000-0002-8646-0969"
+- family-names: "Pravda"
+  given-names: "Lukas"
+- family-names: "Yuan"
+  given-names: "Qi"
+- family-names: "S.Smart"
+  given-names: "Oliver"
+- family-names: "Nadzirin"
+  given-names: "Nurul"
+- family-names: "Anyango"
+  given-names: "Stephen"
+- family-names: "Nair"
+  given-names: "Sreenath"
+
+title: "PDBe CCDUtils"
+version: 0.8.5
+date-released: 22/05/2024
+url: "https://github.com/PDBeurope/ccdutils"
+preferred-citation:
+  type: article
+  authors:
+  - family-names: "Kunnakkattu"
+    given-names: "Ibrahim Roshan"
+    orcid: "https://orcid.org/0000-0002-8646-0969"
+  - family-names: "Choudhary"
+    given-names: "Preeti"
+    orcid: "https://orcid.org/0000-0003-2340-3278"
+  - family-names: "Pravda"
+    given-names: "Lukas"
+  - family-names: "Yuan"
+    given-names: "Qi"
+  - family-names: "S.Smart"
+    given-names: "Oliver"
+  - family-names: "Nadzirin"
+    given-names: "Nurul"
+  - family-names: "Anyango"
+    given-names: "Stephen"
+  - family-names: "Nair"
+    given-names: "Sreenath"
+  - family-names: "Velankar"
+    given-names: "Sameer"
+    orcid: "https://orcid.org/0000-0002-8439-5964"
+  doi: "10.1186/s13321-023-00786-w"
+  journal: "Journal of Cheminformatics"
+  month: 12
+  title: "PDBe CCDUtils: an RDKit-based toolkit for handling and analysing small molecules in the Protein Data Bank"
+  volume: 15
+  year: 2023
diff --git a/README.md b/README.md
@@ -1,76 +1,83 @@
-[![CodeFactor](https://www.codefactor.io/repository/github/pdbeurope/ccdutils/badge/master)](https://www.codefactor.io/repository/github/pdbeurope/ccdutils/overview/master)  ![PYPi](https://img.shields.io/pypi/v/pdbeccdutils?color=green&style=flat)  ![GitHub](https://img.shields.io/github/license/pdbeurope/ccdutils)   ![ccdutils documentation](https://github.com/PDBeurope/ccdutils/workflows/ccdutils%20documentation/badge.svg) ![ccdutils tests](https://github.com/PDBeurope/ccdutils/workflows/ccdutils%20tests/badge.svg)
+[![CodeFactor](https://www.codefactor.io/repository/github/PDBeurope/ccdutils/badge/master)](https://www.codefactor.io/repository/github/PDBeurope/ccdutils/overview/master)  ![PYPi](https://img.shields.io/pypi/v/pdbeccdutils?color=green&style=flat)  ![GitHub](https://img.shields.io/github/license/PDBeurope/ccdutils)   ![ccdutils documentation](https://github.com/PDBeurope/ccdutils/workflows/ccdutils%20documentation/badge.svg) ![ccdutils tests](https://github.com/PDBeurope/ccdutils/workflows/ccdutils%20tests/badge.svg) ![PyPI Downloads](https://img.shields.io/pypi/dm/pdbeccdutils)
+
 
 # pdbeccdutils
 
-* A set of python tools to deal with PDB chemical components definitions
-  for small molecules, taken from the [wwPDB Chemical Component Dictionary](https://www.wwpdb.org/data/ccd) and [wwPDB The Biologically Interesting Molecule Reference Dictionary](https://www.wwpdb.org/data/bird)
+An RDKit-based python toolkit for parsing and processing small molecule definitions in [wwPDB Chemical Component Dictionary](https://www.wwpdb.org/data/ccd) and [wwPDB The Biologically Interesting Molecule Reference Dictionary](https://www.wwpdb.org/data/bird).`pdbeccdutils` provides streamlined access to all metadata of small molecules in the PDB and offers a set of convenient methods to compute various properties of small molecules using RDKIt such as 2D depictions, 3D conformers, physicochemical properties, matching common fragments and scaffolds, mapping to small-molecule databases using UniChem.
+
+## Features
 
-* The tools use:
-  * [RDKit](http://www.rdkit.org/) for chemistry. Presently tested with `2022.09.4`
+* `gemmi` CCD read/write.
+* Generation of 2D depictions (`No image available` generated if the flattening cannot be done) along with the quality check.
+* Generation of 3D conformations.
+* Fragment library search (PDBe hand-curated library, ENAMINE, DSI).
+* Chemical scaffolds (Murcko scaffold, Murcko general, BRICS).
+* Lightweight implementation of [parity method](https://doi.org/10.1016/j.str.2018.02.009) by Jon Tyzack.
+* RDKit molecular properties per component.
+* UniChem mapping.
+* Generating complete representation of multiple [Covalently Linked Components (CLC)](https://www.ebi.ac.uk/pdbe/news/introducing-covalently-linked-components)
+
+## Dependencies
+
+  * [RDKit](http://www.rdkit.org/) for small molecule representation. Presently tested with `2023.9.6`
   * [GEMMI](https://gemmi.readthedocs.io/en/latest/index.html) for parsing mmCIF files.
   * [scipy](https://www.scipy.org/) for depiction quality check.
   * [numpy](https://www.numpy.org/) for molecular scaling.
   * [networkx](https://networkx.org/) for bound-molecules.
 
-* Please note that the project is under active development.
 
-## Installation instructions
+## Installation
 
-* `pdbeccdutils` requires RDKit to be installed.
-  The official RDKit documentation has [installation instructions for a variety of platforms](http://www.rdkit.org/docs/Install.html).
-  For Linux/macOS this is most easily done using the Anaconda Python with commands similar to:
+create a [virtual environment](https://packaging.python.org/en/latest/guides/installing-using-pip-and-virtual-environments/#create-and-use-virtual-environments) and install using pip
 
-  ```console
-  conda create -n rdkit-env rdkit python=3.9
-  conda activate rdkit-env
-  ```
-
-* Once you have installed RDKit, as described above then install `pdbeccdutils` using `pip`:
-
-  ```console
+  ```bash
   pip install pdbeccdutils
   ```
 
-## Features
+## Contribution
+We encourage you to contribute to this project. The package uses [poetry](https://python-poetry.org/) for packaging and dependency management. You can develop locally using:
 
-* `gemmi` CCD read/write.
-* Generation of 2D depictions (`No image available` generated if the flattening cannot be done) along with the quality check.
-* Generation of 3D conformations.
-* Fragment library search (PDBe hand-curated library, ENAMINE, DSI).
-* Chemical scaffolds (Murcko scaffold, Murcko general, BRICS).
-* Lightweight implementation of [parity method](https://doi.org/10.1016/j.str.2018.02.009) by Jon Tyzack.
-* RDKit molecular properties per component.
-* UniChem mapping.
+```bash
+git clone https://github.com/PDBeurope/ccdutils.git
+cd ccdutils
+pip install poetry
+poetry install --with tests,docs
+pre-commit install
+```
 
-## TODO list
+The pre-commit hook will run linting, formatting and update `poetry.lock`. The `poetry.lock` file will lock all dependencies and ensure that they match pyproject.toml versions.
 
-* Add more unit/regression tests to get higher code coverage.
-* Further improvements of the documentation.
+To add a new dependency
 
+```bash
+# Latest resolvable version
+poetry add <package>
 
-## Documentation
+# Optionally fix a version
+poetry add <package>@<version>
+```
+
+To change a version of a dependency, either edit pyproject.toml and run:
 
-The documentation depends on the following packages:
+```bash
+poetry sync --with dev
+```
 
-* `sphinx`
-* `sphinx_rtd_theme`
-* `myst-parser`
-* `sphinx-autodoc-typehints`
+or
 
-Note that `sphinx` needs to be a part of the virtual environment, if you want to generate documentation by yourself.
-Otherwise it cannot pick `rdkit` module. `sphinx_rtd_theme` is a theme providing nice `ReadtheDocs` mobile friendly style.
+```bash
+poetry add <package>@<version>
+```
 
-* Generate *.rst* files to be included as a part of the documentation. Inside the directory `pdbeccdutils/doc` run the following commands to generate documentation.
-* Alternatively, use the `myst-parser` package to get the Markdown working.
 
- Use the following to generate initial markup files to be used by sphinx.  This needs to be used when adding another sub-packages.
+## Documentation
 
-```console
-sphinx-apidoc -f -o /path/to/output/dir ../pdbeccdutils/
-```
+The documentation is generated using `sphinx` in `sphinx_rtd_theme` and hosted on GitHub Pages. To generate the documentation locally,
 
-Use this to re-generate the documentation from the doc/ directory:
+```bash
+cd doc
+poetry run sphinx-build -b html . _build/html
 
-```console
-make html
+# See the documentation at http://localhost:8080.
+python -m http.server 8080 -d _build/html
 ```
diff --git a/doc/conf.py b/doc/conf.py
@@ -13,17 +13,17 @@
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
 
-import pdbeccdutils
+import importlib.metadata
 
 # region Project information
 project = "pdbeccdutils"
 copyright = "2020, Protein Data Bank in Europe"
 author = "Protein Data Bank in Europe"
 
 # The short X.Y version
-version = pdbeccdutils.__version__
+version = importlib.metadata.version("pdbeccdutils")
 # The full version, including alpha/beta/rc tags
-release = pdbeccdutils.__version__
+release = importlib.metadata.version("pdbeccdutils")
 
 # endregion
 

diff --git a/pdbeccdutils/__init__.py b/pdbeccdutils/__init__.py
diff --git a/pdbeccdutils/computations/parity_method.py b/pdbeccdutils/computations/parity_method.py
@@ -5,6 +5,8 @@
 from rdkit import Chem
 from rdkit.Chem import rdFMCS
 
+from pdbeccdutils.helpers import mol_tools
+from rdkit.Chem import BondType
 from pdbeccdutils.core.models import ParityResult
 
 
@@ -88,8 +90,17 @@ def compare_molecules(template, query, thresh=0.01, exact_match=False):
         ParityResult: Result of the PARITY comparison.
     """
 
-    template_atoms = template.GetNumAtoms()
-    query_atoms = query.GetNumAtoms()
+    template_copy = Chem.RWMol(template)
+    query_copy = Chem.RWMol(query)
+
+    # changing bondtype from DATIVE to ZERO as the SMARTS with DATIVE bondtype were missing
+    # substructures using GetSubstructMatches (e.g. HEM)
+    # refer rdkit github issue https://github.com/rdkit/rdkit/issues/7280
+    mol_tools.change_bonds_type(template_copy, BondType.DATIVE, BondType.ZERO)
+    mol_tools.change_bonds_type(query_copy, BondType.DATIVE, BondType.ZERO)
+
+    template_atoms = template_copy.GetNumAtoms()
+    query_atoms = query_copy.GetNumAtoms()
 
     min_num_atoms = min(template_atoms, query_atoms)
     max_sim_score = float(min_num_atoms) / float(
@@ -101,15 +112,15 @@ def compare_molecules(template, query, thresh=0.01, exact_match=False):
 
     if not exact_match:
         mcs_graph = rdFMCS.FindMCS(
-            [template, query],
+            [template_copy, query_copy],
             bondCompare=rdFMCS.BondCompare.CompareAny,
             atomCompare=rdFMCS.AtomCompare.CompareAny,
             timeout=40,
             completeRingsOnly=True,
         )
     else:
         mcs_graph = rdFMCS.FindMCS(
-            [template, query],
+            [template_copy, query_copy],
             bondCompare=rdFMCS.BondCompare.CompareOrderExact,
             atomCompare=rdFMCS.AtomCompare.CompareElements,
             timeout=40,

diff --git a/pdbeccdutils/core/boundmolecule.py b/pdbeccdutils/core/boundmolecule.py
@@ -46,7 +46,7 @@ def infer_bound_molecules(structure, to_discard, assembly=False):
         bm = BoundMolecule(subgraph)
         bound_molecules.append(bm)
 
-    bound_molecules = sorted(bound_molecules, key=lambda l: -len(l.graph.nodes))
+    bound_molecules = sorted(bound_molecules, key=lambda item: -len(item.graph.nodes))
     return bound_molecules