Merge latest mindlessgen features into gp3_ipea

.github/CODEOWNERS

@@ -2,11 +2,11 @@
 # the repo. Unless a later match takes precedence,
 # @marcelmbn and @thfroitzheim will be requested for
 # review when someone opens a pull request.
-*  @marcelmbn @thfroitzheim
+*  @marcelmbn @jonathan-schoeps
 
 # These parts are specifically owned by some people
 /src/mindlessgen/cli @marcelmbn
 /src/mindlessgen/generator @marcelmbn
-/src/mindlessgen/molecules @marcelmbn
-/src/mindlessgen/prog @marcelmbn
+/src/mindlessgen/molecules @marcelmbn @jonathan-schoeps
+/src/mindlessgen/prog @marcelmbn @jonathan-schoeps
 /src/mindlessgen/qm @marcelmbn

CHANGELOG.md

@@ -7,26 +7,34 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 ### Changed
 - vdW radii scaling parameter can now be adjusted via `mindlessgen.toml` or CLI
-- The check_distance function now checks based on the sum of the van der Waals radii and a scaling factor acessible via `mindlessgen.toml` or CLI
+- check_distance function now checks based on the sum of the van der Waals radii and a scaling factor acessible via `mindlessgen.toml` or CLI
 - better type hints for `Callables`
-- A clearer differentiation between the distinct scaling factors for the van der Waals radii.
-- `README.md` with more detailed explanation of the element composition function.
+- clearer differentiation between the distinct scaling factors for the van der Waals radii
+- `README.md` with more detailed explanation of the element composition function
+- Default `max_cycles` for the generation & refinement set to 200
 
 ### Fixed
-- Unit conversion for (currenly unused) vdW radii from the original Fortran project
+- unit conversion for (currenly unused) vdW radii from the original Fortran project
 - minor print output issues (no new line breaks, more consistent verbosity differentiation, ...)
 - bug in `postprocess_mol` which led to an unassigned return variable in the single-point case
+- bug leading to `UnicodeDecodeError` when reading `xtb` output files
 - bug with all atom lists being initialized with a length of 102 instead of 103
+- inconsistent default values for the `mindlessgen.toml` and the `ConfigManager` class
+- legacy pseudo random number generation removed and replaced by `np.random.default_rng()` for avoiding interference with other packages
 
 ### Added
-- Support for the novel "g-xTB" method (working title: GP3-xTB)
-- A function which contracts the coordinates after the initial generation.
-- A function which is able to printout the xyz coordinates to the terminal similar to the `.xyz` layout.
-- Elements 87 to 103 are accessible via the element composition. If `xtb` is the engine, the elements will be replaced by their lighter homologues.
+- support for the novel "g-xTB" method (working title: GP3-xTB)
+- function which contracts the coordinates after the initial generation
+- function which is able to printout the xyz coordinates to the terminal similar to the `.xyz` layout
+- elements 87 to 103 are accessible via the element composition. If `xtb` is the engine, the elements will be replaced by their lighter homologues.
+- support for `python-3.13`
+- option to set a fixed molecular charge, while ensuring `uhf = 0`
 
 ### Breaking Changes
 - Removal of the `dist_threshold` flag and in the `-toml` file.
 - The number of unpaired electrons (`Molecule.uhf`) is now set to 0 if `xtb` is used as `QMMethod` and a lanthanide is within the molecule to match the `f-in-core` approximation.
+- "Contract Coordinates" functionality set to `true` by default in the `mindlessgen.toml` file.
+- `basename.UHF` and `basename.CHRG` are only written to disk if they differ from the default value (0 and 0, respectively).
 
 ## [0.4.0] - 2024-09-19
 ### Changed

README.md

@@ -4,8 +4,8 @@
 <a href="http://www.apache.org/licenses/LICENSE-2.0">
   <img src="https://img.shields.io/badge/License-Apache%202.0-orange.svg" alt="Apache-2.0"/>
 </a>
-<a href="https://img.shields.io/badge/Python-3.10%20|%203.11%20|%203.12-blue.svg">
-  <img src="https://img.shields.io/badge/Python-3.10%20|%203.11|%203.12-blue.svg" alt="Python Versions"/>
+<a href="https://img.shields.io/badge/Python-3.10%20|%203.11%20|%203.12%20|%203.13-blue.svg">
+  <img src="https://img.shields.io/badge/Python-3.10%20|%203.11%20|%203.12%20|%203.13-blue.svg" alt="Python Versions"/>
 </a>
 <img align="right" src="assets/C1H2N1O2Te2Er1Lu2_89bd3e.png" height="150" />
 
@@ -49,10 +49,10 @@ Both installation methods work in principle also without a virtual environment,
 ### Development purposes
 
 For working on the code of `mindlessgen`, the following setup is recommended:
-```
+```bash
 mamba create -n mindlessgen python=3.12
 mamba activate mindlessgen
-git clone {link to the MindlessGen repository}
+git clone https://github.com/grimme-lab/MindlessGen.git # or the analogous SSH link
 pip install -e '.[dev]'
 ```
 Thereby, all necessary development tools (e.g., `ruff`, `mypy`, `tox`, `pytest`, and `pre-commit`) are installed.
@@ -82,11 +82,12 @@ If the path is not specified with `-c/--config`, `mindlessgen.toml` will be sear
 1. Current working directory (`$CWD`)
 2. Home directory (`$USER/`)
 
-The active configuration can be printed using `--print-config`.
+If neither a corresponding CLI command nor an entry in the configuration file is provided, the default values are used.
+The active configuration, including the default values, can be printed using `--print-config`.
 
 ### Element composition
 There are two related aspects of the element composition:
-1. _Which elements_ should occur within the generated molecule?
+1. **Which elements** should occur within the generated molecule?
 2. **How many atoms** of the specified element should occur?
 - **Example 1**: `C:1-3, O:1-1, H:1-*` would result in a molecule with 1, 2, or 3 carbon atoms, exactly 1 oxygen atom, and between 1 and an undefined number of hydrogen atoms (i.e., at least 1).
 - **Example 2**: `Na:10-10, In:10-10, O:20-20`. This example would result in a molecule with exactly 10 sodium atoms, 10 indium atoms, and 20 oxygen atoms. **For a fixed element composition, the number of atoms (40) has to be within the min_num_atoms and max_num_atom interval.** `mindlessgen` will consequently always return a molecule with exactly 40 atoms.
@@ -98,28 +99,46 @@ There are two related aspects of the element composition:
 
 ## Citation
 
-When using the program for academic purposes, please cite:
-
-_J. Chem. Theory Comput._ 2009, **5**, 4, 993–1003
-
-or in `BibTeX` format:
-```
-@article{doi:10.1021/ct800511q,
-author = {Korth, Martin and Grimme, Stefan},
-title = {“Mindless” DFT Benchmarking},
-journal = {Journal of Chemical Theory and Computation},
-volume = {5},
-number = {4},
-pages = {993-1003},
-year = {2009},
-doi = {10.1021/ct800511q},
-note ={PMID: 26609608},
-URL = {https://doi.org/10.1021/ct800511q},
-eprint = {https://doi.org/10.1021/ct800511q}
-}
-```
-
-## Acknowdledgements
+When using the program for academic purposes, please cite _i)_ the original idea and _ii)_ the new Python implementation.
+
+1.  _J. Chem. Theory Comput._ 2009, **5**, 4, 993–1003
+    ```
+    @article{korth_mindless_2009,
+    	title = {Mindless {DFT} benchmarking},
+    	volume = {5},
+    	issn = {15499618},
+    	url = {https://pubs.acs.org/doi/full/10.1021/ct800511q},
+    	doi = {10.1021/ct800511q},
+    	number = {4},
+    	urldate = {2022-11-07},
+    	journal = {J. Chem. Theo. Comp.},
+    	author = {Korth, Martin and Grimme, Stefan},
+    	month = apr,
+    	year = {2009},
+    	note = {Publisher: American Chemical Society},
+    	pages = {993--1003},
+    }
+    ```
+
+2.  A new publication featuring all functionalities and improvements of `mindlessgen` is in preparation.
+    In the meantime, please refer to the original publication and to the following preprint, which uses the `mindlessgen` program for the first time:
+    Müller, M.; Froitzheim, T.; Hansen, A.; Grimme, S. _ChemRxiv_ October 28, 2024. https://doi.org/10.26434/chemrxiv-2024-h76ms.
+    ```
+    @misc{muller_advanced_2024,
+    	title = {Advanced {Charge} {Extended} {Hückel} ({CEH}) {Model} and a {Consistent} {Adaptive} {Minimal} {Basis} {Set} for the {Elements} {Z}=1-103},
+    	url = {https://chemrxiv.org/engage/chemrxiv/article-details/671a92581fb27ce1247466ad},
+    	doi = {10.26434/chemrxiv-2024-h76ms},
+    	urldate = {2024-10-28},
+    	publisher = {ChemRxiv},
+    	author = {Müller, Marcel and Froitzheim, Thomas and Hansen, Andreas and Grimme, Stefan},
+    	month = oct,
+    	year = {2024},
+    	keywords = {DFT, Basis sets, EHT, SQM},
+    }
+    ```
+
+## Acknowledgements
 
 [T. Gasevic](https://github.com/gasevic) for creating an initial `GitHub` [migration](https://github.com/gasevic/mlmgen) of the code and making important adjustments to the workflow.
 [S. Grimme](https://www.chemie.uni-bonn.de/grimme/de/grimme) and M. Korth for the original code written in Fortran associated to the publication in [J. Chem. Theory Comput.](https://pubs.acs.org/doi/full/10.1021/ct800511q).
+[T. Froitzheim](https://github.com/thfroitzheim) for helpful discussons during the development of the program.

mindlessgen.toml

@@ -1,21 +1,21 @@
-# Default configuration for the 'Mindless Molecule GENerator' (MindlessGen) package
-# Following file locations are searched for in the following order:
+# Default configuration for the 'Mindless Molecule Generator' (MindlessGen) package
+# The following file locations are searched for in ascending order:
 # 1. Location specified by the `--config < str | Path >` command-line argument
 # 2. Current working directory (`Path.cwd()`)
 # 3. User's home directory (`Path.home()`)
 
 [general]
-# > Verbosity level defining the printout: Options: 0 = silent, 1 = default, 2 = verbose, 3 = debug
+# > Verbosity level defining the printout: Options: -1 = super-silent, 0 = silent, 1 = default, 2 = verbose, 3 = debug
 verbosity = 1
 # > Number of parallel processes to use. Corresponds to the number of physical CPU cores used. Options: <int>
 parallel = 1
-# > Maximum number of generation/optimization try-and-error cycles per molecule. Options: <int>
-max_cycles = 100
+# > Maximum number of generation & optimization try-and-error cycles per molecule. Options: <int>
+max_cycles = 200
 # > Number of molecules to generate. Options: <int>
 num_molecules = 1
-# > Do post-processing (checking for HL gap, etc.) after the optimization. Options: <bool>
+# > Do post-processing after the optimization with another engine (e.g., `orca`). Default: false. Options: <bool>
 postprocess = false
-# > Switch molecule structure XYZ writing on and off (default: true). Options: <bool>
+# > Switch molecule structure XYZ writing on and off. Default: true. Options: <bool>
 write_xyz = true
 
 [generate]
@@ -26,22 +26,24 @@ max_num_atoms = 10
 # > Initial coordinate scaling factor. Options: <float>
 init_scaling = 3.0
 # > Increase in the coordinate scaling factor per trial after check_distance was not met. Options: <float>
-increase_scaling_factor = 1.3
+increase_scaling_factor = 1.1
 # > Scaling factor for the van der Waals radii employed for the fragment detection. Options: <float>
 scale_fragment_detection = 1.25
 # > Scaling factor for the minimal distance between two atoms based on the sum of the van der Waals radii. Options: <float>
 scale_minimal_distance = 0.8
-# > Contract the coordinates after the initial generation. Leads to more cluster-like and less extended structures. Options: <bool>
-contract_coords = false
+# > Contract the coordinates after the initial generation. Leads to more cluster-like and less extended structures
+# and can speed-up the generation for larger molecules significantly. Options: <bool>
+contract_coords = true
 # > Atom types and their minimum and maximum occurrences. Format: "<element>:<min_count>-<max_count>"
 # > Elements that are not specified are only added by random selection.
 # > A star sign (*) can be used as a wildcard for integer value.
 element_composition = "C:2-3, H:1-2, O:1-2, N:1-*"
 # > Atom types that are not chosen for random selection. Format: "<element1>, <element2>, ..."
 # > CAUTION: This option is overridden by the 'element_composition' option.
 # > I.e., if an element is specified in 'element_composition' with an occurrence > 0, it will be added to the molecule anyway.
-# > Example: forbidden_elements = "18,57-*"
 forbidden_elements = "57-71, 81-*"
+# > Set a charge for the molecule generation. Options: "none" (random charge assignment), "int" or <int> (fixed charge assignment)
+molecular_charge = "none"
 
 [refine]
 # > Maximum number of fragment optimization cycles. Options: <int>

pyproject.toml

@@ -6,17 +6,19 @@ build-backend = "setuptools.build_meta"
 name = "mindlessgen"
 authors = [
     { name = "Marcel Müller", email = "marcel.mueller@thch.uni-bonn.de" },
+    { name = "Jonathan Schöps", email = "s6jtscho@uni-bonn.de" },
 ]
-description = "Mindless Molecule GENerator"
+description = "Mindless Molecule Generator"
 readme = "README.md"
 requires-python = ">=3.10"
 license = { file = "LICENSE.md" }
 classifiers = [
-    "License :: OSI Approved :: MIT License",
+    "License :: OSI Approved :: Apache-2.0 License",
     "Programming Language :: Python :: 3 :: Only",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Topic :: Scientific/Engineering",
     "Typing :: Typed",
 ]

src/mindlessgen/cli/cli_parser.py

@@ -143,6 +143,12 @@ def cli_parser(argv: Sequence[str] | None = None) -> dict:
         required=False,
         help="Contract the coordinates of the molecule after the coordinats generation.",
     )
+    parser.add_argument(
+        "--molecular-charge",
+        type=str,
+        required=False,
+        help="Define the charge of the molecule.",
+    )
 
     ### Refinement arguments ###
     parser.add_argument(
@@ -280,6 +286,7 @@ def cli_parser(argv: Sequence[str] | None = None) -> dict:
         "scale_fragment_detection": args_dict["scale_fragment_detection"],
         "scale_minimal_distance": args_dict["scale_minimal_distance"],
         "contract_coords": args_dict["contract_coords"],
+        "molecular_charge": args_dict["molecular_charge"],
     }
     # XTB specific arguments
     rev_args_dict["xtb"] = {"xtb_path": args_dict["xtb_path"]}

src/mindlessgen/generator/main.py

@@ -173,6 +173,12 @@ def single_molecule_generator(
                 print(e)
         stop_event.set()
         return None
+    except RuntimeError as e:
+        if config.general.verbosity > 0:
+            print(f"Generation failed for cycle {cycle + 1}.")
+            if config.general.verbosity > 1:
+                print(e)
+        return None
 
     try:
         #    ____        _   _           _

src/mindlessgen/molecules/__init__.py

@@ -2,7 +2,7 @@
 This module contains all molecule-related functionality.
 """
 
-from .molecule import Molecule, PSE_NUMBERS, PSE_SYMBOLS
+from .molecule import Molecule, PSE_NUMBERS, PSE_SYMBOLS, ati_to_atlist, atlist_to_ati
 from .generate_molecule import (
     generate_random_molecule,
     generate_coordinates,
@@ -40,5 +40,7 @@
     "get_alkaline_earth_metals",
     "PSE_NUMBERS",
     "PSE_SYMBOLS",
+    "ati_to_atlist",
+    "atlist_to_ati",
     "postprocess_mol",
 ]