[1.1] add CI tests + new strain energy calculations and data for plots

.github/workflows/tests.yaml

@@ -0,0 +1,66 @@
+name: build
+
+on:
+  push:
+    paths-ignore:
+      - "README.md"
+      - "docs/**"
+
+  pull_request:
+    paths-ignore:
+      - "README.md"
+      - "docs/*"
+
+jobs:
+  build_cpu:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.8, 3.9, "3.10", "3.11"]
+        #torch: [1.12.0, 1.13.0, 2.0.0]
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      # Setup environment (conda, dependencies, etc.)
+      - name: Setup miniconda
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          auto-update-conda: true
+          miniforge-variant: Mambaforge
+          channels: "conda-forge, pytorch"
+          python-version: ${{ matrix['python-version'] }}
+          use-mamba: true
+
+      #- name: Install PyTorch
+      #  run: mamba install -c pytorch pytorch==${{matrix.torch}} cpuonly
+
+      - name: Install Extras
+        run: pip install -r requirements.txt
+
+      - name: Install OpenBabel
+        run: mamba install -c conda-forge openbabel
+
+      - name: Install reduce
+        run: mamba install -c speleo3 reduce
+
+      # Install coverage tool
+      - name: Install Coverage
+        run: pip install coverage
+
+      # # Run tests with coverage
+      # - name: Run unit tests and generate coverage report
+      #   run: |
+      #     coverage run --source=posecheck -m unittest discover -s tests -p "test_*.py"
+      #     coverage xml
+
+      # # Upload coverage to Codecov
+      # - name: Upload coverage to Codecov
+      #   uses: codecov/codecov-action@v2
+      #   with:
+      #     files: ./coverage.xml
+      #     fail_ci_if_error: true
+      #     token: ${{ secrets.CODECOV_TOKEN }} # not required for public repos

README.md

@@ -1,5 +1,13 @@
 # PoseCheck: Benchmarking Generated Poses
 
+
+[![arXiv](https://img.shields.io/badge/arXiv-2308.07413-b31b1b.svg)](https://arxiv.org/abs/2308.07413)
+![version](https://img.shields.io/badge/version-1.1-blue)
+[![python](https://img.shields.io/badge/-Python_3.8_%7C_3.9_%7C_3.10_%7C_3.11-blue?logo=python&logoColor=white)](https://github.com/pre-commit/pre-commit)
+[![build](https://github.com/cch1999/posecheck/actions/workflows/tests.yaml/badge.svg?branch=main)](https://github.com/cch1999/posecheck/actions/workflows/tests.yaml)
+[![Project Status: Active – The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
 <p align="center">
   <a href="">
     <img src="data/posecheck_logo.png" width="800"/>
@@ -78,7 +86,10 @@ print(f"Interactions of example molecule: {interactions}")
 
 ## Data from the paper
 
-WIP!
+
+The data for the paper can be found at the following Zenodo link and place in the `data` directory.
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.10208912.svg)](https://doi.org/10.5281/zenodo.10208912)
 
 
 ## Cite

changelog.md

@@ -0,0 +1,19 @@
+# Changelog
+
+## [1.1] - 18-01-2024
+
+### Changed
+- [IMPORTANT - PLEASE READ IF YOU INTEND TO PUBLISH] Changed the way strain energy is calculated. Previously, the strain energy was calculated as the difference between the energy of the raw output and a fully relaxed structure. This meant that the energy term of the raw output exploded due to slight imperfections in local bond lengths and angles and did not reflect global strain well. Now we perform a small bit of local relaxation (max displacement in the atom positions of 0.1 Å) and use the energy of this structure as the reference energy. This means that the strain energy is now a more accurate reflection of the global strain of the molecule.
+
+### Added
+- Data and notebooks needed to reproduce plots from the paper.
+- Validator that warms the user if `reduce` cannot be found.
+- CI tests
+- Full environment specs
+
+### Fixed
+- Improved doc string coverage
+
+## [1.0] - 24-09-2023
+
+Initial release of the software with basic features for chemical analysis.

dev.ipynb

@@ -0,0 +1,44 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mRunning cells with '/Users/charlie/micromamba/envs/posecheck/bin/python' requires the ipykernel package.\n",
+      "\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
+      "\u001b[1;31mCommand: 'conda install -p /Users/charlie/micromamba/envs/posecheck ipykernel --update-deps --force-reinstall'"
+     ]
+    }
+   ],
+   "source": [
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

environment.yml

@@ -1,16 +1,105 @@
-name: posecheck
+name: poses
 channels:
-  - conda-forge
-  - defaults
+- conda-forge
+- speleo3
 dependencies:
-  - openbabel
-  - pip:
-    - pandas
-    - seaborn
-    - matplotlib
-    - rdkit
-    - datamol
-    - prolif
-    - tqdm
-
+- _libgcc_mutex=0.1=conda_forge
+- _openmp_mutex=4.5=2_gnu
+- asttokens=2.2.1=pyhd8ed1ab_0
+- backcall=0.2.0=pyh9f0ad1d_0
+- backports=1.0=pyhd8ed1ab_3
+- backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
+- bzip2=1.0.8=h7f98852_4
+- ca-certificates=2023.7.22=hbcca054_0
+- cairo=1.16.0=hbbf8b49_1016
+- comm=0.1.4=pyhd8ed1ab_0
+- debugpy=1.6.8=py311hb755f60_0
+- decorator=5.1.1=pyhd8ed1ab_0
+- executing=1.2.0=pyhd8ed1ab_0
+- expat=2.5.0=hcb278e6_1
+- font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+- font-ttf-inconsolata=3.000=h77eed37_0
+- font-ttf-source-code-pro=2.038=h77eed37_0
+- font-ttf-ubuntu=0.83=hab24e00_0
+- fontconfig=2.14.2=h14ed4e7_0
+- fonts-conda-ecosystem=1=0
+- fonts-conda-forge=1=0
+- freetype=2.12.1=hca18f0e_1
+- gettext=0.21.1=h27087fc_0
+- icu=72.1=hcb278e6_0
+- importlib-metadata=6.8.0=pyha770c72_0
+- importlib_metadata=6.8.0=hd8ed1ab_0
+- ipykernel=6.25.1=pyh71e2992_0
+- ipython=8.14.0=pyh41d4057_0
+- jedi=0.19.0=pyhd8ed1ab_0
+- jupyter_client=8.3.0=pyhd8ed1ab_0
+- jupyter_core=5.3.1=py311h38be061_0
+- ld_impl_linux-64=2.40=h41732ed_0
+- libexpat=2.5.0=hcb278e6_1
+- libffi=3.4.2=h7f98852_5
+- libgcc-ng=13.1.0=he5830b7_0
+- libglib=2.76.4=hebfc3b9_0
+- libgomp=13.1.0=he5830b7_0
+- libiconv=1.17=h166bdaf_0
+- libnsl=2.0.0=h7f98852_0
+- libpng=1.6.39=h753d276_0
+- libsodium=1.0.18=h36c2ea0_1
+- libsqlite=3.42.0=h2797004_0
+- libstdcxx-ng=13.1.0=hfd8a6a1_0
+- libuuid=2.38.1=h0b41bf4_0
+- libxcb=1.15=h0b41bf4_0
+- libxml2=2.11.5=h0d562d8_0
+- libzlib=1.2.13=hd590300_5
+- matplotlib-inline=0.1.6=pyhd8ed1ab_0
+- ncurses=6.4=hcb278e6_0
+- nest-asyncio=1.5.6=pyhd8ed1ab_0
+- openbabel=3.1.1=py311ha3c2874_7
+- openssl=3.1.2=hd590300_0
+- packaging=23.1=pyhd8ed1ab_0
+- parso=0.8.3=pyhd8ed1ab_0
+- pcre2=10.40=hc3806b6_0
+- pexpect=4.8.0=pyh1a96a4e_2
+- pickleshare=0.7.5=py_1003
+- pip=23.2.1=pyhd8ed1ab_0
+- pixman=0.40.0=h36c2ea0_0
+- platformdirs=3.10.0=pyhd8ed1ab_0
+- prompt-toolkit=3.0.39=pyha770c72_0
+- prompt_toolkit=3.0.39=hd8ed1ab_0
+- psutil=5.9.5=py311h2582759_0
+- pthread-stubs=0.4=h36c2ea0_1001
+- ptyprocess=0.7.0=pyhd3deb0d_0
+- pure_eval=0.2.2=pyhd8ed1ab_0
+- pygments=2.16.1=pyhd8ed1ab_0
+- python=3.11.4=hab00c5b_0_cpython
+- python-dateutil=2.8.2=pyhd8ed1ab_0
+- python_abi=3.11=3_cp311
+- pyzmq=25.1.1=py311h75c88c4_0
+- readline=8.2=h8228510_1
+- reduce=3.16.111118=h6bb024c_0
+- setuptools=68.0.0=pyhd8ed1ab_0
+- six=1.16.0=pyh6c4a22f_0
+- stack_data=0.6.2=pyhd8ed1ab_0
+- tk=8.6.12=h27826a3_0
+- tornado=6.3.2=py311h459d7ec_0
+- traitlets=5.9.0=pyhd8ed1ab_0
+- typing-extensions=4.7.1=hd8ed1ab_0
+- typing_extensions=4.7.1=pyha770c72_0
+- tzdata=2023c=h71feb2d_0
+- wcwidth=0.2.6=pyhd8ed1ab_0
+- wheel=0.41.1=pyhd8ed1ab_0
+- xorg-kbproto=1.0.7=h7f98852_1002
+- xorg-libice=1.1.1=hd590300_0
+- xorg-libsm=1.2.4=h7391055_0
+- xorg-libx11=1.8.6=h8ee46fc_0
+- xorg-libxau=1.0.11=hd590300_0
+- xorg-libxdmcp=1.1.3=h7f98852_0
+- xorg-libxext=1.3.4=h0b41bf4_2
+- xorg-libxrender=0.9.11=hd590300_0
+- xorg-renderproto=0.11.1=h7f98852_1002
+- xorg-xextproto=7.3.0=h0b41bf4_1003
+- xorg-xproto=7.0.31=h7f98852_1007
+- xz=5.2.6=h166bdaf_0
+- zeromq=4.3.4=h9c3ff4c_1
+- zipp=3.16.2=pyhd8ed1ab_0
+- zlib=1.2.13=hd590300_5
 

posecheck/posecheck.py

@@ -10,7 +10,8 @@
 from posecheck.utils.interactions import generate_interaction_df
 from posecheck.utils.loading import (load_mols_from_rdkit, load_mols_from_sdf,
                                load_protein_from_pdb, read_pdbqt)
-from posecheck.utils.strain import get_strain_energy
+from posecheck.utils.strain import calculate_strain_energy
+from posecheck.utils.validators import is_reduce_installed, print_reduce_warning
 
 
 class PoseCheck(object):
@@ -41,6 +42,10 @@ def __init__(
         """
         self.reduce_path = reduce_path
         self.clash_tolerance = clash_tolerance
+
+        # Check if reduce is installed
+        if not is_reduce_installed(reduce_path):
+            print_reduce_warning()
 
     def load_protein_from_pdb(self, pdb_path: str) -> None:
         """Load a protein from a PDB file.
@@ -113,7 +118,7 @@ def calculate_clashes(self) -> int:
 
     def calculate_strain_energy(self) -> float:
         """Calculate the strain energy of the ligand."""
-        return [get_strain_energy(mol) for mol in self.ligands]
+        return [calculate_strain_energy(mol) for mol in self.ligands]
 
     def calculate_interactions(self) -> pd.DataFrame:
         """Calculate the interactions between the protein and the ligand."""