Merge pull request #3 from ccdc-opensource/utility_scripts

Added Utility scripts and changed formatting

Author: Alex-AMC

README.md

@@ -5,11 +5,11 @@
 
 A repository containing scripts that have been created to leverage the toolkit found within
 the [CCDC portfolio](https://www.ccdc.cam.ac.uk/solutions/) that are accessible via
-the [CSD-Python API ](https://www.ccdc.cam.ac.uk/solutions/csd-core/components/csd-python-api/).
+the [CSD Python API](https://www.ccdc.cam.ac.uk/solutions/csd-core/components/csd-python-api/).
 
 The purpose of this platform is to distribute knowledge and allow for scientific collaborations. Scripts are provided on an as-is basis and while their use is not supported we do welcome feedback on potential improvements. All scripts are tested against the latest version of the CSD Python API as installed with the CSD Portfolio.
 
-> For feedback or to report any issues please contact [support@ccdc.cam.ac.uk](support@ccdc.cam.ac.uk)
+> For feedback or to report any issues please contact [support@ccdc.cam.ac.uk](mailto:support@ccdc.cam.ac.uk)
 
 ## Content 
 

scripts/concat_mol2/ReadMe.md

@@ -0,0 +1,39 @@
+# Concat Mol2
+
+## Summary
+
+Opens a set of mol2 files in the working directory and creates one concatenated multi-mol2 file.
+Optionally delete the individual mol2 files other than the new concat.mol2
+
+## Requirements
+
+- CSD Python API not required.
+- Mol2 files must be in the same directory.
+
+## Licensing Requirements
+
+No license required.
+
+## Instructions on running
+
+```cmd
+> python concat_mol2.py
+```
+
+Help output:
+```cmd
+python concat_mol2.py -h
+usage: concat_mol2.py [-h] [-d]
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -d, --delete_contributors
+                        Remove contributing individual mol2 files after
+                        concatenation
+```
+
+## Author
+
+_Peter Galek_ (2014)
+
+> For feedback or to report any issues please contact [support@ccdc.cam.ac.uk](mailto:support@ccdc.cam.ac.uk)

scripts/concat_mol2/concat_mol2.py

@@ -0,0 +1,45 @@
+#
+# This script can be used for any purpose without limitation subject to the
+# conditions at http://www.ccdc.cam.ac.uk/Community/Pages/Licences/v2.aspx
+#
+# This permission notice and the following statement of attribution must be
+# included in all copies or substantial portions of this script.
+#
+# 2014-08-11: created by Peter Galek, The Cambridge Crystallographic Data Centre
+# 2022-02-24: updated by Alex Moldovan, The Cambridge Crystallographic Data Centre
+#
+
+import glob
+import argparse
+import os
+
+
+def main(delete_separate_files):
+    mol2_files = glob.glob('*.mol2')
+    count = 0
+    with open('concat.mol2', 'w') as outfile:
+        for f in mol2_files:
+            if f == 'concat.mol2':
+                continue
+            with open(f, 'r') as infile:
+                outfile.write(infile.read())
+                count += 1
+    print(f"{count} files concatenated.")
+
+    if delete_separate_files == True:
+        count = 0
+        for f in mol2_files:
+            if f == 'concat.mol2':
+                continue
+            os.remove(f)
+            count += 1
+        print(f"{count} files removed.")
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument('-d', '--delete_contributors', action='store_true',
+                        help='Remove contributing individual mol2 files after concatenation')
+
+    args = parser.parse_args()
+    main(args.delete_contributors)

scripts/create_castep_input/ReadMe.md

@@ -0,0 +1,37 @@
+# Create CASTEP Input
+
+## Summary
+
+Allows the user to generate a set of CASTEP input files (.cell and .params) for a structure viewed in Mercury. 
+
+![img.png](assets/file_output.png)
+
+## Requirements
+
+Tested with CSD Python API 3.0.9
+
+Requires user to add script to Mercury interface. 
+
+## Licensing Requirements
+
+- CSD-Core
+
+If you wish to run CASTEP, you will need to acquire a licence for CASTEP, this is not supplied by the CCDC.
+
+## Instructions on running
+
+Add script with Folder to Mercury interface (Mercury -> CSD Python API-> Options -> Add Location)
+
+![img.png](assets/add_script_location.png)
+
+Select refcode of interest or load structure into Mercury. 
+
+Select script from CSD Python API dropdown. 
+
+![img.png](assets/select_script.png)
+
+## Author
+
+_Anthony Reilly_ (2016)
+
+> For feedback or to report any issues please contact [support@ccdc.cam.ac.uk](mailto:support@ccdc.cam.ac.uk)

scripts/create_castep_input/assets/add_script_location.png

@@ -0,0 +1,89 @@
+#
+# This script can be used for any purpose without limitation subject to the
+# conditions at http://www.ccdc.cam.ac.uk/Community/Pages/Licences/v2.aspx
+#
+# This permission notice and the following statement of attribution must be
+# included in all copies or substantial portions of this script.
+#
+# 2016-12-06 - created by Anthony Reilly, The Cambridge Crystallographic Data Centre based on code from Andrew Maloney, CCDC
+# 2021-02-24 - updated by Alex Moldovan, The Cambridge Crystallographic Data Centre
+#
+
+import os
+from ccdc.utilities import ApplicationInterface
+
+
+def make_castep_input(crystal, kp_spacing=0.06, cut_off=750.000, task='SinglePoint', di_opt=False):
+    # cell file
+    with open('%s.cell' % crystal.identifier, 'w') as cell_file:
+        cell_file.write('%BLOCK LATTICE_ABC\n')
+        cell_file.write('  %11.7f  %11.7f  %11.7f\n' % crystal.cell_lengths)
+        cell_file.write('  %11.7f  %11.7f  %11.7f\n' % crystal.cell_angles)
+        cell_file.write('%ENDBLOCK LATTICE_ABC\n\n')
+        cell_file.write('%BLOCK POSITIONS_FRAC\n')
+        for op in crystal.symmetry_operators:
+            mol = crystal.symmetric_molecule(op, [0, 0, 0], force=False)
+            for atom in mol.atoms:
+                cell_file.write('  %s  %19.16f  %19.16f  %19.16f\n' % (atom.atomic_symbol,
+                                                                       atom.fractional_coordinates.x,
+                                                                       atom.fractional_coordinates.y,
+                                                                       atom.fractional_coordinates.z))
+        cell_file.write('%ENDBLOCK POSITIONS_FRAC\n\n')
+
+        cell_file.write('KPOINT_MP_SPACING ' + str(kp_spacing) + '\n\n')
+
+        cell_file.write('%BLOCK SYMMETRY_OPS\n')
+        for op in crystal.symmetry_operators:
+            rotation = crystal.symmetry_rotation(op)
+            trans = crystal.symmetry_translation(op)
+            cell_file.write('      %18.15f      %18.15f      %18.15f\n' % (rotation[0], rotation[1], rotation[2]))
+            cell_file.write('      %18.15f      %18.15f      %18.15f\n' % (rotation[3], rotation[4], rotation[5]))
+            cell_file.write('      %18.15f      %18.15f      %18.15f\n' % (rotation[6], rotation[7], rotation[8]))
+            cell_file.write('      %18.15f      %18.15f      %18.15f\n' % (trans[0], trans[1], trans[2]))
+            cell_file.write('###\n')
+        cell_file.write('%ENDBLOCK SYMMETRY_OPS\n\n')
+
+    # param file
+    with open('%s.param' % crystal.identifier, 'w') as param_file:
+        param_file.write('task : ' + task + '\n')
+        param_file.write('comment : CASTEP calculation for %s\n' % crystal.identifier)
+
+        param_file.write('xc_functional : PBE\n')
+        param_file.write('sedc_scheme : TS\n')
+
+        param_file.write('metals_method : dm\n')
+        param_file.write('mixing_scheme : Pulay\n')
+        param_file.write('spin_polarized : false\n')
+        param_file.write('opt_strategy : speed\n')
+        param_file.write('cut_off_energy :  ' + str(cut_off) + '\n')
+        param_file.write('grid_scale :        2.0\n')
+        param_file.write('fine_grid_scale :   3.0\n')
+        param_file.write('elec_energy_tol :   1.000e-008\n')
+        param_file.write('fix_occupancy : true\n')
+        if task != 'SinglePoint':
+            param_file.write('finite_basis_corr : 2\n')
+
+        param_file.write('geom_modulus_est : 50 GPa\n')
+        param_file.write('geom_max_iter : 200\n')
+        param_file.write('num_backup_iter : 1\n')
+
+        param_file.write('geom_energy_tol : 5E-06\n')
+        param_file.write('geom_stress_tol : 0.02\n')
+        param_file.write('geom_disp_tol : 1E-03\n')
+        param_file.write('geom_force_tol : 5E-03\n')
+        if di_opt:
+            param_file.write('geom_method : delocalised \n')
+
+        param_file.write('write_cif_structure : true\n')
+        param_file.write('write_cell_structure : true\n')
+        param_file.write('#continuation : default\n')
+
+    return True
+
+
+if __name__ == '__main__':
+    helper = ApplicationInterface()
+    entry = helper.current_entry
+    crystal = entry.crystal
+    os.chdir(helper.output_directory_path)
+    make_castep_input(crystal)

scripts/create_castep_input/assets/file_output.png

@@ -0,0 +1,34 @@
+# Create Gaussian Input
+
+## Summary
+
+Allows the user to generate a Gaussian input file (.gjf) for a given CSD refcode or .mol2. If you wish to run different keywords the script will need to be changed manually. 
+
+
+## Requirements
+
+Tested with CSD Python API 3.0.9
+
+
+## Licensing Requirements
+
+CSD-Core
+
+If you wish to run Gaussian, you will need to acquire a licence for Gaussian, this is not supplied by the CCDC.
+
+## Instructions on running
+
+To create an input file for the 
+```cmd
+>python create_gaussian_input.py HXACAN
+```
+
+```cmd
+>python create_gaussian_input.py HXACAN.mol2
+```
+
+## Author
+
+_Andrew Maloney_(2015)
+
+> For feedback or to report any issues please contact [support@ccdc.cam.ac.uk](mailto:support@ccdc.cam.ac.uk)

scripts/create_castep_input/assets/select_script.png

@@ -0,0 +1,84 @@
+#
+# This script can be used for any purpose without limitation subject to the
+# conditions at http://www.ccdc.cam.ac.uk/Community/Pages/Licences/v2.aspx
+#
+# This permission notice and the following statement of attribution must be
+# included in all copies or substantial portions of this script.
+#
+# 2015-06-17: created by Andrew Maloney the Cambridge Crystallographic Data Centre
+#
+
+from __future__ import division, absolute_import, print_function
+
+"""
+This script will generate a generic Gaussian input file
+Input: CSD Identifier as a string or .mol2 
+Output: GJF input file
+"""
+
+import sys
+import os
+import ccdc.io
+
+
+def fatal(*args):
+    """Generates an error message if necessary to smoothly exit the program."""
+    print('ERROR:', ' '.join(map(str, args)))
+    sys.exit(1)
+
+
+def file_writer(molecule, name):
+    """Writes a standard Gaussian input file for all molecules contained in the structure files."""
+    if not mol.all_atoms_have_sites:
+        fatal(entry_id, 'has some atoms without coordinates')
+    mol.normalise_hydrogens()
+
+    for i, component in enumerate(molecule.components):
+
+        file_name = '%s_molecule%d.gjf' % (name, i)
+        f = open(file_name, 'w')
+
+        f.write('#B3LYP/6-31G**  opt\n')
+        f.write('\n')
+        f.write('Standard Gaussian Input File for %s, molecule %d\n' % (name, i))
+        f.write('\n')
+        f.write('0 1\n')
+
+        for atom in component.atoms:
+            f.write('%2s  %9.6f  %9.6f  %9.6f\n' % (atom.atomic_symbol,
+                                                    atom.coordinates.x,
+                                                    atom.coordinates.y,
+                                                    atom.coordinates.z))
+
+        f.write('\n')
+        f.write('--Link1--')
+        f.write('\n')
+        f.write('\n')
+        f.write('\n')
+
+        f.close()
+
+
+if __name__ == '__main__':
+    # Get the relevant structure typed by user
+    if len(sys.argv) != 2:
+        fatal('you must supply a structure identifier.')
+    entry_id = sys.argv[1]
+
+    # Checking the current directory for user cif file
+    filepath = '%s' % entry_id
+    if os.path.isfile(filepath):
+        reader = ccdc.io.MoleculeReader(filepath)
+        for mol in reader:
+            identifier = mol.identifier
+            file_writer(mol, identifier)
+
+    else:
+        # Read molecule from database
+        reader = ccdc.io.MoleculeReader('CSD')
+        identifier = entry_id
+        try:
+            mol = reader.molecule(entry_id)
+            file_writer(mol, identifier)
+        except RuntimeError:
+            fatal(entry_id, '- structure not found')