Merge pull request #71 from drorlab/70-update-to-python-312-and-mdana…

…lysis-28 Update to MDAnalysis 2.8 and Python 3.10
drorlab · Jan 27, 2025 · 1e5100d · 1e5100d
2 parents 7c67c45 + e0c43a7
commit 1e5100d
Show file tree

Hide file tree

Showing 13 changed files with 115 additions and 102 deletions.
diff --git a/.github/workflows/python-package-conda.yml b/.github/workflows/python-package-conda.yml
@@ -12,10 +12,10 @@ jobs:
         shell: bash -l {0}
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python 3.9
+    - name: Set up Python 3.10
       uses: actions/setup-python@v4
       with:
-        python-version: 3.9
+        python-version: '3.10'
     - name: Lint with flake8
       run: |
         pip install flake8

diff --git a/.readthedocs.yml b/.readthedocs.yml
@@ -7,9 +7,9 @@ version: 2
 
 # Set the OS, Python version and other tools you might need
 build:
-  os: ubuntu-22.04
+  os: ubuntu-24.04
   tools:
-    python: "3.9"
+    python: "3.10"
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:

diff --git a/LICENSE b/LICENSE
@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2020-2022 Martin Vögele, Neil Thomson, Sang Truong, Jasper McAvity
+Copyright (c) 2020-2025 Martin Vögele, Neil Thomson, Sang Truong, Jasper McAvity
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

diff --git a/docs/about.rst b/docs/about.rst
@@ -27,14 +27,14 @@ All functionality is available as a python package.
 Citation
 ********
 
-If you publish about work for which PENSA was useful, please cite our preprint:
+If you publish about work for which PENSA was useful, please cite our publication:
 
-    M. Vögele, N. J. Thomson, S. T. Truong, J. McAvity, U. Zachariae, R. O. Dror:
-    *Systematic Analysis of Biomolecular Conformational Ensembles with PENSA*.
-    `arXiv:2212.02714 [q-bio.BM] 2022 <https://arxiv.org/abs/2212.02714>`_.
+    M. Vögele, N. J. Thomson, S. T. Truong, J. McAvity, U. Zachariae, R. O. Dror: 
+    *Systematic analysis of biomolecular conformational ensembles with PENSA*. 
+    `J. Chem. Phys. 162, 014101 (2025) <https://doi.org/10.1063/5.0235544>`_.
 
 The reference for the software implementation itself is the following:
 
-    Martin Vögele, Neil Thomson, Sang Truong, Jasper McAvity: *PENSA*. Zenodo, 2024. http://doi.org/10.5281/zenodo.4362136
+    Martin Vögele, Neil Thomson, Sang Truong, Jasper McAvity: *PENSA*. Zenodo, 2025. http://doi.org/10.5281/zenodo.4362136
 
 To get the citation and DOI for a particular version, see `Zenodo <https://zenodo.org/record/4362136>`_.
diff --git a/docs/conf.py b/docs/conf.py
@@ -21,7 +21,7 @@
 # -- Project information -----------------------------------------------------
 
 project = 'PENSA'
-copyright = '2020-2024, Martin Vögele, Neil Thomson, Sang Truong, Jasper McAvity'
+copyright = '2020-2025, Martin Vögele, Neil Thomson, Sang Truong, Jasper McAvity'
 author = 'Martin Vögele, Neil Thomson, Sang Truong, Jasper McAvity'
 
 

diff --git a/docs/installation.rst b/docs/installation.rst
@@ -8,7 +8,7 @@ Create and activate a conda environment:
 
   .. code:: bash
 
-    conda create --name pensa python=3.9 numpy==1.22 scipy==1.9 pandas==1.4 matplotlib==3.5 MDAnalysis==2.2 cython biotite -c conda-forge -c conda-forge
+    conda create --name pensa python==3.10 scipy numpy pandas matplotlib MDAnalysis==2.8 deeptime biotite pip -c conda-forge
     conda activate pensa
 
 If you want to use PENSA with Jupyter notebooks:

diff --git a/docs/requirements.txt b/docs/requirements.txt
@@ -7,12 +7,12 @@ sphinxcontrib-htmlhelp
 sphinxcontrib-jsmath
 sphinxcontrib-qthelp
 sphinxcontrib-serializinghtml
-numpy==1.22
-scipy==1.9
-pandas==1.4
-matplotlib==3.5
+numpy
+scipy
+pandas
+matplotlib
 deeptime
-MDAnalysis==2.2
+MDAnalysis==2.8
 cython
 biotite
-pensa==0.3.0
+pensa
diff --git a/docs/tut-2-preprocessing.rst b/docs/tut-2-preprocessing.rst
@@ -10,19 +10,19 @@ Preprocessing
         extract_aligned_coordinates, extract_combined_grid
 
 
-Coordinates
-***********
+To work with the biomolecule's coordinates, it is often easier to first extract 
+them from the simulation, i.e., remove the solvent, lipids etc. If you would like 
+to calculate water or ion features, you need to calculate the corresponding density.
+This kind of preprocessing steps can be cumbersome but you usually only do it 
+once and can then play with your data.
 
-To work with the biomolecule's coordinates, we first need to extract them from
-the simulation, i.e., remove the solvent, lipids etc. This is the hardest part 
-but you usually only have to do it once and can then play with your data. 
-Preprocessing can handle many common trajectory formats as it is based on 
-MDAnalysis. You can start by using the scripts provided in the PENSA repository. 
-Once you know how PENSA works, you can write your own scripts.
+Based on MDAnalysis, PENSA's preprocessing functions can handle many common formats
+of molecular simulation trajectories. You can start by using the scripts provided 
+in the PENSA repository. Once you know how PENSA works, you can write your own scripts.
 
 
 Files and Directories
----------------------
+**********************
 
 In the following, we define the necessary files. For each simulation, we
 need a reference file (.psf for AMBER), a PDB file, and the trajetory.
@@ -71,8 +71,8 @@ will generate.
             os.makedirs(subdir)
 
 
-Extracting Coordinates
-----------------------
+Coordinates
+***********
 
 We have to ensure that from both simulations, we use the exact same
 parts of the receptor for the analysis. Often, this will be easy and you
@@ -91,14 +91,24 @@ In the first case, we will extract all protein residues, assuming
     extract_coordinates(ref_file_a, pdb_file_a, trj_file_a, out_name_a+"_receptor", sel_base_a)
     extract_coordinates(ref_file_b, pdb_file_b, trj_file_b, out_name_b+"_receptor", sel_base_b)
 
-In many cases, you probably have several runs of the same simulation
-that you want to combine to one structural ensemble. This is why the
-trajectory argument takes a list as arguments, e.g.
+In some cases, you may have only one trajectory while in others, 
+you may have several runs of the same simulation that you want 
+to combine to one structural ensemble. 
+This is why the trajectory argument can be either a single string
+
+.. code:: python
+
+    extract_coordinates(
+        'system.psf', 'system.pdb', 'run1.nc', 
+        'receptor', 'protein', start_frame=1000
+    )
+
+... or a list of strings.
 
 .. code:: python
 
     extract_coordinates(
-        'system.psf', 'system.pdb', ['run1.nc','run2.nc','run3.nc'], 
+        'system.psf', 'system.pdb', ['run1.nc','run2.nc','run3.nc'],
         'receptor', 'protein', start_frame=1000
     )
                                 
@@ -129,8 +139,8 @@ Here, we use selections based on the definitions of transmembrane helices in the
     sel_string_b = "protein and resnum "+resnums
     print('Selection B:\n', sel_string_b, '\n')
     # Extract the coordinates of the transmembrane region from the trajectory
-    extract_coordinates(ref_file_a, pdb_file_a, [trj_file_a], out_name_a+"_tm", sel_string_a)
-    extract_coordinates(ref_file_b, pdb_file_b, [trj_file_b], out_name_b+"_tm", sel_string_b)
+    extract_coordinates(ref_file_a, pdb_file_a, trj_file_a, out_name_a+"_tm", sel_string_a)
+    extract_coordinates(ref_file_b, pdb_file_b, trj_file_b, out_name_b+"_tm", sel_string_b)
 
 
 Loading from Multiple Simulations

diff --git a/environment.yml b/environment.yml
@@ -3,11 +3,12 @@ channels:
   - conda-forge
   - defaults
 dependencies: 
-  - python==3.9
-  - scipy==1.9
-  - numpy==1.22
-  - pandas==1.4
-  - matplotlib==3.5
-  - MDAnalysis==2.2
+  - python==3.10
+  - scipy
+  - numpy
+  - pandas
+  - matplotlib
+  - MDAnalysis==2.8
   - deeptime
   - biotite
+  - pip
diff --git a/pyproject.toml b/pyproject.toml
@@ -0,0 +1,63 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pensa"
+version = "0.6.0"
+description = "exploratory analysis and comparison of biomolecular conformational ensembles."
+authors = [
+    {name = "Martin Voegele, Neil Thomson, Sang Truong, Jasper McAvity", email = "martinvoegele1989@gmail.com"}
+]
+license = {text = "MIT"}
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Topic :: Scientific/Engineering :: Chemistry",
+    "Topic :: Scientific/Engineering :: Physics",
+    "Topic :: Scientific/Engineering :: Visualization",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Mathematics",
+    "Topic :: Scientific/Engineering :: Medical Science Apps.",
+    "Topic :: Scientific/Engineering :: Molecular Dynamics",
+    "Topic :: Scientific/Engineering :: Computational Biology",
+]
+dependencies = [
+    "numpy>=1.23",
+    "scipy",
+    "pandas",
+    "matplotlib",
+    "deeptime",
+    "MDAnalysis==2.8",
+    "biotite",
+    "gpcrmining",
+]
+requires-python = "==3.10.*"
+
+[project.urls]
+Documentation = "https://pensa.readthedocs.io/en/latest/"
+Source = "http://github.com/drorlab/pensa"
+
+[metadata]
+# Include the license file in the wheel.
+license_files = ["LICENSE"]
+
+[tool.setuptools.packages.find]
+include = [
+    "pensa",
+    "pensa.preprocessing",
+    "pensa.features", 
+    "pensa.comparison",
+    "pensa.dimensionality",
+    "pensa.clusters",
+    "pensa.statesinfo"
+]
+
+
+
+
diff --git a/run-test.sb b/run-test.sb
diff --git a/setup.cfg b/setup.cfg
diff --git a/setup.py b/setup.py