Merge branch 'master' into high-throughput

.readthedocs.yaml

@@ -9,7 +9,7 @@ version: 2
 build:
   os: ubuntu-22.04
   tools:
-    python: "miniconda3-4.7"
+    python: "mambaforge-latest"
     # You can also specify other tool versions:
     # nodejs: "19"
     # rust: "1.64"
@@ -20,7 +20,7 @@ sphinx:
   configuration: docs/source/conf.py
 
 conda:
-  environment: cosolvkit_env.yml
+  environment: docs/source/environment.yml
 
 # Optionally build your docs in additional formats such as PDF and ePub
 # formats:

MANIFEST.in

@@ -0,0 +1,5 @@
+include README.md
+include LICENSE
+include docs/*
+include example/*
+include cosolvkit/data/*

README.md

@@ -1,5 +1,11 @@
-[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/) [![License: LGPL v2.1](https://img.shields.io/badge/License-LGPL_v2.1-green.svg)](https://www.gnu.org/licenses/old-licenses/lgpl-2.1.en.html) [![PyPI - Version](https://img.shields.io/pypi/v/cosolvkit)](https://pypi.org/project/cosolvkit/0.4.1/) [![Powered by RDKit](https://img.shields.io/badge/Powered%20by-RDKit-3838ff.svg?logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQBAMAAADt3eJSAAAABGdBTUEAALGPC/xhBQAAACBjSFJNAAB6JgAAgIQAAPoAAACA6AAAdTAAAOpgAAA6mAAAF3CculE8AAAAFVBMVEXc3NwUFP8UPP9kZP+MjP+0tP////9ZXZotAAAAAXRSTlMAQObYZgAAAAFiS0dEBmFmuH0AAAAHdElNRQfmAwsPGi+MyC9RAAAAQElEQVQI12NgQABGQUEBMENISUkRLKBsbGwEEhIyBgJFsICLC0iIUdnExcUZwnANQWfApKCK4doRBsKtQFgKAQC5Ww1JEHSEkAAAACV0RVh0ZGF0ZTpjcmVhdGUAMjAyMi0wMy0xMVQxNToyNjo0NyswMDowMDzr2J4AAAAldEVYdGRhdGU6bW9kaWZ5ADIwMjItMDMtMTFUMTU6MjY6NDcrMDA6MDBNtmAiAAAAAElFTkSuQmCC)](https://www.rdkit.org/)
+[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/) 
+[![License: LGPL v2.1](https://img.shields.io/badge/License-LGPL_v2.1-green.svg)](https://www.gnu.org/licenses/old-licenses/lgpl-2.1.en.html) 
 [![Documentation Status](https://readthedocs.org/projects/cosolvkit/badge/?version=latest)](https://cosolvkit.readthedocs.io/en/latest/?badge=latest)
+![Conda Version](https://img.shields.io/conda/vn/conda-forge/cosolvkit)
+![Conda Platform](https://img.shields.io/conda/pn/conda-forge/cosolvkit)
+![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/cosolvkit)
+[![PyPI - Version](https://img.shields.io/pypi/v/cosolvkit)](https://pypi.org/project/cosolvkit/0.4.7/) 
+[![Powered by RDKit](https://img.shields.io/badge/Powered%20by-RDKit-3838ff.svg?logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQBAMAAADt3eJSAAAABGdBTUEAALGPC/xhBQAAACBjSFJNAAB6JgAAgIQAAPoAAACA6AAAdTAAAOpgAAA6mAAAF3CculE8AAAAFVBMVEXc3NwUFP8UPP9kZP+MjP+0tP////9ZXZotAAAAAXRSTlMAQObYZgAAAAFiS0dEBmFmuH0AAAAHdElNRQfmAwsPGi+MyC9RAAAAQElEQVQI12NgQABGQUEBMENISUkRLKBsbGwEEhIyBgJFsICLC0iIUdnExcUZwnANQWfApKCK4doRBsKtQFgKAQC5Ww1JEHSEkAAAACV0RVh0ZGF0ZTpjcmVhdGUAMjAyMi0wMy0xMVQxNToyNjo0NyswMDowMDzr2J4AAAAldEVYdGRhdGU6bW9kaWZ5ADIwMjItMDMtMTFUMTU6MjY6NDcrMDA6MDBNtmAiAAAAAElFTkSuQmCC)](https://www.rdkit.org/)
 
 
 
@@ -12,20 +18,27 @@ Pre-print version of the original paper is freely accessible at the link https:/
 The installation instructions, documentation and tutorials can be found on http://cosolvkit.readthedocs.io/.
 
 ## Installation
-I highly recommend you to install the Anaconda distribution (https://www.continuum.io/downloads) if you want a clean python environnment with nearly all the prerequisites already installed. To install everything properly, you just have to do this:
+`Cosolvkit` package is available via `conda` and can be installed:
 ```bash
-$ conda create -n cosolvkit -c conda-forge -f cosolvkit_env.yml
+$ conda install --channel conda-forge::cosolvkit
+```
+
+or via `mamba`:
+```bash
+$ mamba install -c conda-forge cosolvkit
 ```
-For faster installation, use `mamba` or `micromamba` instead of `conda`.
 
 Finally, we can install the `CosolvKit` package via `pip`:
 ```bash
 $ pip instal cosolvkit
 ```
 
 or directly download and install the source code from git: 
+I highly recommend you to install the Anaconda distribution (https://www.continuum.io/downloads) if you want a clean python environnment with nearly all the prerequisites already installed. To install everything properly, you just have to do this (for faster installation, use `mamba` or `micromamba` instead of `conda`):
 
 ```bash
+$ conda create -n cosolvkit -c conda-forge -f environment.yml
+
 $ git clone https://github.com/forlilab/cosolvkit
 $ cd cosolvkit
 $ pip install -e .

scripts/create_cosolvent_system.py → cosolvkit/cli/create_cosolvent_system.py

@@ -40,7 +40,7 @@ def cmd_lineparser():
 
     return parser.parse_args()
 
-if __name__ == "__main__":
+def main():
     args = cmd_lineparser()
     config_file = args.config
     config = Config.from_config(config_file)
@@ -174,3 +174,8 @@ def cmd_lineparser():
                         seed=None
         )
         print(f"Simulation finished after {(time.time() - start)/60:.2f} min.")
+    return
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/post_simulation_processing.py → cosolvkit/cli/post_simulation_processing.py

@@ -1,3 +1,4 @@
+import sys
 import argparse
 from cosolvkit.analysis import Report
 
@@ -17,8 +18,7 @@ def cmd_lineparser():
                         action='store', help='path to the json file containing cosolvents used for the simulation')
     return parser.parse_args()
 
-
-if __name__ == "__main__":
+def main():
     args = cmd_lineparser()
     log_file = args.log_file
     traj_file = args.traj_file
@@ -33,4 +33,9 @@ def cmd_lineparser():
                                   report.trajectory, 
                                   density_files=densities, 
                                   selection_string='', 
-                                  out_path=out_path)
+                                  out_path=out_path)
+    return
+
+
+if __name__ == "__main__":
+    sys.exit(main())

cosolvkit/cosolvent_system.py

@@ -3,6 +3,7 @@
 import sys
 import io
 from collections import defaultdict
+from typing import Union, Tuple
 import numpy as np
 from scipy import spatial
 from scipy.stats import qmc
@@ -673,11 +674,11 @@ def add_cosolvents(self,
         :param cosolvents: keys are cosolvent molecules and values are 3D coordinates of the molecule
         :type cosolvents: dict
         :param vectors: vectors defining the simulation box
-        :type vectors: tuple[openmm.Vec3, openmm.Vec3, openmm.Vec3]
+        :type vectors: Tuple[openmm.Vec3, openmm.Vec3, openmm.Vec3]
         :param lowerBound: lower bound of the simulation box
-        :type lowerBound: openmm.unit.Quantity | Vec3
+        :type lowerBound: Union[openmm.unit.Quantity, Vec3]
         :param upperBound: upper bound of the simulation box
-        :type upperBound: openmm.unit.Quantity | Vec3
+        :type upperBound: [openmm.unit.Quantity, Vec3]
         :param receptor_positions: list of 3D coordinates of the receptor
         :type receptor_positions: list
         :param max_attempts_per_mol: the maximum number of times we attempt to insert a single molecule
@@ -932,15 +933,15 @@ def accept_reject(self,
         :param valid_ids: valid halton indices
         :type valid_ids: list
         :param lowerBound: lower bound of the box
-        :type lowerBound: openmm.unit.Quantity | Vec3
+        :type lowerBound: Union[openmm.unit.Quantity, Vec3]
         :param upperBound: upper bound of the box
-        :type upperBound: openmm.unit.Quantity | Vec3
+        :type upperBound: Union[openmm.unit.Quantity, Vec3]
         :param protein_kdtree: tree of the protein's positions
         :type protein_kdtree: spatial.cKDTree
         :param max_num_trials: the maximum number of halton moves to make
         :param max_num_trials: int 
         :return: accepted coordinates for the cosolvent and the used halton ids
-        :rtype: tuple[np.ndarray, list]
+        :rtype: Tuple[np.ndarray, list]
         """        
         num_trials = 0
         accepted = False
@@ -970,16 +971,16 @@ def accept_reject(self,
 
     def is_in_box(self, 
                   xyzs: np.ndarray, 
-                  lowerBound: openmmunit.Quantity | Vec3, 
-                  upperBound: openmmunit.Quantity | Vec3) -> bool:
+                  lowerBound: Union[openmmunit.Quantity, Vec3], 
+                  upperBound: Union[openmmunit.Quantity, Vec3]) -> bool:
         """Checks if the coordinates are in the box or not
 
         :param xyzs: coordinates to check
         :type xyzs: np.ndarray
         :param lowerBound: lower bound of the box
-        :type lowerBound: openmmunit.Quantity | Vec3
+        :type lowerBound: Union[openmmunit.Quantity, Vec3]
         :param upperBound: upper bound of the box
-        :type upperBound: openmmunit.Quantity | Vec3
+        :type upperBound: Union[openmmunit.Quantity, Vec3]
         :return: True if all the coordinates are in the box, Flase otherwise
         :rtype: bool
         """
@@ -1060,13 +1061,13 @@ def calculate_mol_volume(self, mol_positions: np.ndarray) -> float:
         points = np.unique(np.hstack(query)).astype(int)
         return round(len(points)*mesh_step**3, 2)
 
-    def fitting_checks(self) -> float | None:
+    def fitting_checks(self) -> Union[float, None]:
         """Checks if the required cosolvents can fit in the box and 
         do not exceed the 50% of the available fillable volume 
         (volume not occupied by the receptor, if present).
 
         :return: available volume if the cosolvents can fit, None otherwise
-        :rtype: float | None
+        :rtype: Union[float, None]
         """
         prot_volume = 0
         if self.receptor:
@@ -1086,11 +1087,11 @@ def fitting_checks(self) -> float | None:
             return None
         return empty_available_volume
 
-    def liters_to_cubic_nanometers(self, liters: float | openmmunit.Quantity) -> float:
+    def liters_to_cubic_nanometers(self, liters: Union[float, openmmunit.Quantity]) -> float:
         """Converts liters in cubic nanometers
 
         :param liters: volume to convert
-        :type liters: float | openmm.unit.Quantity
+        :type liters: Union[float, openmm.unit.Quantity]
         :return: converted volume
         :rtype: float
         """
@@ -1162,10 +1163,10 @@ def _parametrize_cosolvents(self, cosolvents: dict, small_molecule_ff="espaloma"
     def _build_box(self, 
                    positions: np.ndarray, 
                    padding: openmmunit.Quantity, 
-                   radius: openmmunit.Quantity = None) -> tuple[tuple[Vec3, Vec3, Vec3], 
+                   radius: openmmunit.Quantity = None) -> Tuple[Tuple[Vec3, Vec3, Vec3], 
                                                                 Vec3, 
-                                                                openmmunit.Quantity | Vec3,
-                                                                openmmunit.Quantity | Vec3]:
+                                                                Union[openmmunit.Quantity, Vec3],
+                                                                Union[openmmunit.Quantity, Vec3]]:
         """Builds the simulation box. If a receptor is passed it is used alongside with the padding
         parameter to build the box automatically, otherwise a radius has to be passed. If no receptor
         the box is centered on the point [0, 0, 0].
@@ -1179,7 +1180,7 @@ def _build_box(self,
         :return: The first element returned is a tuple containing the three vectors describing the simulation box.
                 The second element is the box itself.
                 Third and fourth elements are the lower and upper bound of the simulation box.
-        :rtype: tuple[tuple[Vec3, Vec3, Vec3], Vec3, openmmunit.Quantity | Vec3, openmmunit.Quantity | Vec3]
+        :rtype: tuple[tuple[Vec3, Vec3, Vec3], Vec3, Union[openmmunit.Quantity, Vec3], Union[openmmunit.Quantity, Vec3]]
         """
         padding = padding.value_in_unit(openmmunit.nanometer)
         if positions is not None:

cosolvkit/data/config.json

@@ -1,9 +1,9 @@
 {
-  "cosolvents": "data/cosolvents.json",
-  "forcefields": "data/forcefields.json",
+  "cosolvents": "cosolvkit/data/cosolvents.json",
+  "forcefields": "cosolvkit/data/forcefields.json",
   "md_format": "openmm",
   "receptor": true,
-  "protein_path": "/path/to/protein/structure",
+  "protein_path": "example/protein.pdb",
   "clean_protein": true,
   "keep_heterogens": false,
   "variants_d": {},
@@ -19,7 +19,7 @@
   "cosolvent_placement": 0,
   "waters_to_keep": [],
   "radius": null,
-  "output": "/path/to/where/to/save/results",
+  "output": "results",
   "run_cosolvent_system": true,
   "run_md": false
 }

cosolvkit/utils.py

@@ -12,6 +12,7 @@
 import shutil
 import subprocess
 import importlib
+from typing import List, Tuple
 from collections import defaultdict
 
 import numpy as np
@@ -89,7 +90,7 @@ class MutuallyExclusiveParametersError(Exception):
 
 #     simulation.context.setParameter('k', k)
 
-def fix_pdb(pdbfile: str, pdbxfile: str, keep_heterogens: bool=False) -> tuple[Topology, list]:
+def fix_pdb(pdbfile: str, pdbxfile: str, keep_heterogens: bool=False) -> Tuple[Topology, List]:
     """Fixes common problems in PDB such as:
             - missing atoms
             - missing residues
@@ -123,7 +124,7 @@ def fix_pdb(pdbfile: str, pdbxfile: str, keep_heterogens: bool=False) -> tuple[T
     fixer.addMissingHydrogens(7)
     return fixer.topology, fixer.positions
 
-def add_variants(topology: Topology, positions: list, variants: list=list()) -> tuple[Topology, list]:
+def add_variants(topology: Topology, positions: list, variants: list=list()) -> Tuple[Topology, List]:
     """Adds variants for specific protonation states.
 
     :param topology: openmm topology