CAT 0.9.1 (#121)

* Added a new conceptual DFT (CDFT) workflow to Nano-CAT (nlesc-nano/nano-CAT#57).

CAT/__version__.py

@@ -1 +1 @@
-__version__ = '0.9.0'
+__version__ = '0.9.1'

CAT/base.py

@@ -60,16 +60,17 @@
     from nanoCAT.bde.bde_workflow import init_bde
     from nanoCAT.ligand_solvation import init_solv
     from nanoCAT.ff.ff_assignment import init_ff_assignment
+    from nanoCAT.cdft import init_cdft
 
     NANO_CAT: Optional[ImportError] = None
 except ImportError as ex:
-    NANO_CAT: Optional[ImportError] = ex
+    NANO_CAT = ex
 
 try:
     import dataCAT
     DATA_CAT: Optional[ImportError] = None
 except ImportError as ex:
-    DATA_CAT: Optional[ImportError] = ex
+    DATA_CAT = ex
 
 __all__ = ['prep']
 
@@ -261,6 +262,7 @@ def prep_ligand(ligand_df: SettingsDataFrame) -> SettingsDataFrame:
     * Ligand geometry optimization
     * Ligand bulkiness calculations
     * Ligand COSMO-RS calculations
+    * Ligand conceptual DFT calculations
 
     .. _Nano-CAT: https://github.com/nlesc-nano/nano-CAT
 
@@ -284,6 +286,7 @@ def prep_ligand(ligand_df: SettingsDataFrame) -> SettingsDataFrame:
     forcefield = ligand_df.settings.optional.forcefield
     optimize = ligand_df.settings.optional.ligand.optimize
     crs = ligand_df.settings.optional.ligand.crs
+    cdft = ligand_df.settings.optional.ligand.cdft
 
     # Identify functional groups within the ligand.
     ligand_df = init_ligand_anchoring(ligand_df)
@@ -310,6 +313,11 @@ def prep_ligand(ligand_df: SettingsDataFrame) -> SettingsDataFrame:
                      "(Multipurpose Atom-Typer for CHARMM) and the nano-CAT package")
         init_ff_assignment(ligand_df)
 
+    # Run conceptual DFT calculations
+    if cdft:
+        val_nano_cat("Ligand conceptual DFT calculations require the nano-CAT package")
+        init_cdft(ligand_df)
+
     return ligand_df
 
 

CAT/data_handling/validate_input.py

@@ -33,7 +33,8 @@
     asa_schema,
     ligand_opt_schema,
     subset_schema,
-    multi_ligand_schema
+    multi_ligand_schema,
+    cdft_schema
 )
 
 from .validate_ff import validate_ff, update_ff_jobs
@@ -111,12 +112,14 @@ def validate_input(s: Settings) -> None:
 
     if s.optional.ligand.optimize:
         s.optional.ligand.optimize = ligand_opt_schema.validate(s.optional.ligand.optimize)
+    if s.optional.ligand.cdft:
+        s.optional.ligand.cdft = cdft_schema.validate(s.optional.ligand.cdft)
     if s.optional.ligand['cosmo-rs']:
         crs = s.optional.ligand.pop('cosmo-rs')
         s.optional.ligand.crs = crs_schema.validate(crs)
+
     if s.optional.qd.optimize:
         s.optional.qd.optimize = qd_opt_schema.validate(s.optional.qd.optimize)
-
     if s.optional.qd.dissociate:
         s.optional.qd.dissociate = bde_schema.validate(s.optional.qd.dissociate)
     if s.optional.qd.activation_strain:

CAT/data_handling/validation_schemas.py

@@ -483,6 +483,13 @@ def _get_crsjob() -> type:
             And(bool, Use(lambda n: {'job1': 'AMSJob'} if n else False)),
             error='optional.ligand.cosmo-rs expects a boolean or dictionary'
         ),
+
+    Optional_('cdft', default=False):  # Settings specific to ligand conceptual dft calculations
+        Or(
+            dict,
+            And(bool, Use(lambda n: {'job1': 'ADFJob'} if n else False)),
+            error='optional.ligand.cdft expects a boolean or dictionary'
+        ),
 })
 
 
@@ -962,3 +969,35 @@ def _get_crsjob() -> type:
             And(val_float, lambda n: 0 <= float(n) <= 1, Use(float))
         )
 })
+
+
+#: Schema for validating the ``['optional']['ligand']['cdft']`` block.
+cdft_schema: Schema = Schema({
+    # Delete files after the calculations are finished
+    Optional_('keep_files', default=True):
+        And(bool, error='optional.ligand.cdft.keep_files expects a boolean'),
+
+    # The Job type for the final geometry optimization
+    Optional_('job1', default=lambda n: ADFJob):
+        Or(
+            And(
+                And(type, lambda n: issubclass(n, Job), Use(val_job_type)),
+                error=('optional.ligand.cdft.job1 expects a type object '
+                       'that is a subclass of plams.Job')
+            ),
+            And(
+                str, Use(str_to_job_type),
+                error=('optional.ligand.cdft.job1 expects a string '
+                       'that is a valid plams.Job alias')
+            ),
+        ),
+
+    # The Job Settings for the final geometry optimization
+    Optional_('s2', default=Settings):
+        Or(
+            None,
+            dict,
+            And(str, Use(lambda n: get_template(n, from_cat_data=False))),
+            error='optional.ligand.cdft.s1 expects a string or a dictionary'
+        ),
+})

CAT/jobs.py

@@ -108,8 +108,11 @@ def pre_process_settings(mol: Molecule, s: Settings,
         ret.input.ams.system.bondorders._1 = adf_connectivity(mol)
         if 'uff' not in s.input:
             ret.input.ams.system.charge = sum(
-                [at.properties.charge for at in mol if 'charge' in at.properties]
+                [at.properties.get('charge', 0) for at in mol]
             )
+    elif job_type is ADFJob:
+        if not s.input.charge:
+            s.input.charge = int(sum(at.properties.get('charge', 0) for at in mol))
     return ret
 
 

CAT/recipes.py

@@ -18,8 +18,6 @@
 
 """
 
-import warnings
-
 try:
     from nanoCAT import recipes as _recipes
     from nanoCAT.recipes import *
@@ -28,17 +26,19 @@
     del _recipes
 
 except ImportError as ex:
+    import warnings as _warnings
+
     __all__ = []
 
     _warning = ImportWarning(str(ex))
     _warning.__cause__ = ex
-    warnings.warn(_warning)
+    _warnings.warn(_warning)
     del _warning
+    del _warnings
 
 finally:
     from . import dye as _dye
     from .dye import *
 
     __all__ += _dye.__all__
     del _dye
-    del warnings

CAT/workflows/__init__.pyi

@@ -13,6 +13,22 @@ JOB_SETTINGS_QD_OPT: Tuple[str, str] = ...
 JOB_SETTINGS_CRS: Tuple[str, str] = ...
 JOB_SETTINGS_BDE: Tuple[str, str] = ...
 JOB_SETTINGS_ASA: Tuple[str, str] = ...
+JOB_SETTINGS_CDFT: Tuple[str, str] = ...
+CDFT_MU: Tuple[str, str] = ...
+CDFT_CHI: Tuple[str, str] = ...
+CDFT_ETA: Tuple[str, str] = ...
+CDFT_S: Tuple[str, str] = ...
+CDFT_GAMMA: Tuple[str, str] = ...
+CDFT_OMEGA: Tuple[str, str] = ...
+CDFT_NUCLEOFUGE: Tuple[str, str] = ...
+CDFT_ELECTROFUGE: Tuple[str, str] = ...
+CDFT_W_MINUS: Tuple[str, str] = ...
+CDFT_W_PLUS: Tuple[str, str] = ...
+CDFT_ELECTROPHILICITY: Tuple[str, str] = ...
+CDFT_DELTAF_MINUS: Tuple[str, str] = ...
+CDFT_DELTAF_PLUS: Tuple[str, str] = ...
+CDFT_MU_MINUS: Tuple[str, str] = ...
+CDFT_MU_PLUS: Tuple[str, str] = ...
 ASA_INT: Tuple[str, str] = ...
 ASA_STRAIN: Tuple[str, str] = ...
 ASA_E: Tuple[str, str] = ...
@@ -23,4 +39,5 @@ SETTINGS_SOLV2: Tuple[str, str] = ...
 SETTINGS_ASA: Tuple[str, str] = ...
 SETTINGS_BDE1: Tuple[str, str] = ...
 SETTINGS_BDE2: Tuple[str, str] = ...
+SETTINGS_CDFT: Tuple[str, str] = ...
 V_BULK: Tuple[str, str] = ...

CAT/workflows/key_map.py

@@ -30,6 +30,22 @@
     'JOB_SETTINGS_CRS': ('job_settings_crs', ''),
     'JOB_SETTINGS_BDE': ('job_settings_BDE', ''),
     'JOB_SETTINGS_ASA': ('job_settings_ASA', ''),
+    'JOB_SETTINGS_CDFT': ('job_settings_cdft', ''),
+    'CDFT_MU': ('cdft', 'Electronic chemical potential (mu)'),
+    'CDFT_CHI': ('cdft', 'Electronegativity (chi=-mu)'),
+    'CDFT_ETA': ('cdft', 'Hardness (eta)'),
+    'CDFT_S': ('cdft', 'Softness (S)'),
+    'CDFT_GAMMA': ('cdft', 'Hyperhardness (gamma)'),
+    'CDFT_OMEGA': ('cdft', 'Electrophilicity index (w=omega)'),
+    'CDFT_NUCLEOFUGE': ('cdft', 'Dissocation energy (nucleofuge)'),
+    'CDFT_ELECTROFUGE': ('cdft', 'Dissociation energy (electrofuge)'),
+    'CDFT_W_MINUS': ('cdft', 'Electrodonating power (w-)'),
+    'CDFT_W_PLUS': ('cdft', 'Electroaccepting power(w+)'),
+    'CDFT_ELECTROPHILICITY': ('cdft', 'Net Electrophilicity'),
+    'CDFT_DELTAF_MINUS': ('cdft', 'Global Dual Descriptor Deltaf-'),
+    'CDFT_DELTAF_PLUS': ('cdft', 'Global Dual Descriptor Deltaf+'),
+    'CDFT_MU_MINUS': ('cdft', 'Electronic chemical potential (mu-)'),
+    'CDFT_MU_PLUS': ('cdft', 'Electronic chemical potential (mu+)'),
     'ASA_INT': ('ASA', 'E_int'),
     'ASA_STRAIN': ('ASA', 'E_strain'),
     'ASA_E': ('ASA', 'E'),
@@ -40,6 +56,7 @@
     'SETTINGS_ASA': ('settings', 'ASA 1'),
     'SETTINGS_BDE1': ('settings', 'BDE 1'),
     'SETTINGS_BDE2': ('settings', 'BDE 2'),
+    'SETTINGS_CDFT': ('settings', 'cdft 1'),
     'V_BULK': ('V_bulk', '')
 })
 

CAT/workflows/key_map.pyi

@@ -12,6 +12,22 @@ JOB_SETTINGS_QD_OPT: Tuple[str, str] = ...
 JOB_SETTINGS_CRS: Tuple[str, str] = ...
 JOB_SETTINGS_BDE: Tuple[str, str] = ...
 JOB_SETTINGS_ASA: Tuple[str, str] = ...
+JOB_SETTINGS_CDFT: Tuple[str, str] = ...
+CDFT_MU: Tuple[str, str] = ...
+CDFT_CHI: Tuple[str, str] = ...
+CDFT_ETA: Tuple[str, str] = ...
+CDFT_S: Tuple[str, str] = ...
+CDFT_GAMMA: Tuple[str, str] = ...
+CDFT_OMEGA: Tuple[str, str] = ...
+CDFT_NUCLEOFUGE: Tuple[str, str] = ...
+CDFT_ELECTROFUGE: Tuple[str, str] = ...
+CDFT_W_MINUS: Tuple[str, str] = ...
+CDFT_W_PLUS: Tuple[str, str] = ...
+CDFT_ELECTROPHILICITY: Tuple[str, str] = ...
+CDFT_DELTAF_MINUS: Tuple[str, str] = ...
+CDFT_DELTAF_PLUS: Tuple[str, str] = ...
+CDFT_MU_MINUS: Tuple[str, str] = ...
+CDFT_MU_PLUS: Tuple[str, str] = ...
 ASA_INT: Tuple[str, str] = ...
 ASA_STRAIN: Tuple[str, str] = ...
 ASA_E: Tuple[str, str] = ...
@@ -22,4 +38,5 @@ SETTINGS_SOLV2: Tuple[str, str] = ...
 SETTINGS_ASA: Tuple[str, str] = ...
 SETTINGS_BDE1: Tuple[str, str] = ...
 SETTINGS_BDE2: Tuple[str, str] = ...
+SETTINGS_CDFT: Tuple[str, str] = ...
 V_BULK: Tuple[str, str] = ...

CAT/workflows/workflow_dicts.py

@@ -21,6 +21,7 @@
     JOB_SETTINGS_CRS,
     JOB_SETTINGS_BDE,
     JOB_SETTINGS_ASA,
+    JOB_SETTINGS_CDFT,
     ASA_INT,
     ASA_STRAIN,
     ASA_E,
@@ -31,20 +32,33 @@
     SETTINGS_ASA,
     SETTINGS_BDE1,
     SETTINGS_BDE2,
-    V_BULK
+    SETTINGS_CDFT,
+    V_BULK,
+    CDFT_MU,
+    CDFT_CHI,
+    CDFT_ETA,
+    CDFT_S,
+    CDFT_GAMMA,
+    CDFT_OMEGA,
+    CDFT_NUCLEOFUGE,
+    CDFT_ELECTROFUGE,
+    CDFT_W_MINUS,
+    CDFT_W_PLUS,
+    CDFT_ELECTROPHILICITY,
+    CDFT_DELTAF_MINUS,
+    CDFT_DELTAF_PLUS,
+    CDFT_MU_MINUS,
+    CDFT_MU_PLUS
 )
 
 if TYPE_CHECKING:
-    if sys.version_info >= (3, 8):
-        from typing import TypedDict
-    else:
-        from typing_extensions import TypedDict
+    from nanoutils import TypedDict
 
     class _TemplateMapping(TypedDict):
         description: str
         mol_type: str
         template: Mapping[str, Tuple[str, ...]]
-        import_columns: Mapping[Tuple[str, str], float]
+        import_columns: Mapping[Tuple[str, str], Any]
         export_columns: Tuple[Tuple[str, str], ...]
 
 else:
@@ -89,6 +103,18 @@ def finalize_templates():
                       'export_columns': (V_BULK,)},
         'multi_ligand': {'import_columns': {HDF5_INDEX: -1, OPT: False},
                          'export_columns': (HDF5_INDEX, OPT)},
+        'cdft': {'import_columns': {CDFT_MU: np.nan, CDFT_CHI: np.nan, CDFT_ETA: np.nan,
+                                    CDFT_S: np.nan, CDFT_GAMMA: np.nan, CDFT_OMEGA: np.nan,
+                                    CDFT_NUCLEOFUGE: np.nan, CDFT_ELECTROFUGE: np.nan,
+                                    CDFT_W_MINUS: np.nan, CDFT_W_PLUS: np.nan,
+                                    CDFT_ELECTROPHILICITY: np.nan, CDFT_DELTAF_MINUS: np.nan,
+                                    CDFT_DELTAF_PLUS: np.nan, CDFT_MU_MINUS: np.nan,
+                                    CDFT_MU_PLUS: np.nan},
+                 'export_columns': (JOB_SETTINGS_CDFT, SETTINGS_CDFT, CDFT_MU, CDFT_CHI, CDFT_ETA,
+                                    CDFT_S, CDFT_GAMMA, CDFT_OMEGA, CDFT_NUCLEOFUGE,
+                                    CDFT_ELECTROFUGE, CDFT_W_MINUS, CDFT_W_PLUS,
+                                    CDFT_ELECTROPHILICITY, CDFT_DELTAF_MINUS, CDFT_DELTAF_PLUS,
+                                    CDFT_MU_MINUS, CDFT_MU_PLUS)},
     }
 
     templates = _load_templates()

CAT/workflows/workflow_yaml.yaml

@@ -152,3 +152,17 @@ multi_ligand:
         cluster_size: [optional, qd, multi_ligand, cluster_size]
         weight: [optional, qd, multi_ligand, weight]
         randomness: [optional, qd, multi_ligand, randomness]
+
+cdft:
+    description: Conceptual DFT property calculation
+    mol_type: ligand
+    template:
+        db: [optional, database, db]
+        read: [optional, database, read]
+        write: [optional, database, write]
+        overwrite: [optional, database, overwrite]
+
+        path: [optional, ligand, dirname]
+        keep_files: [optional, ligand, cdft, keep_files]
+        job1: [optional, ligand, cdft, job1]
+        s1: [optional, ligand, cdft, s1]

CHANGELOG.rst

@@ -11,6 +11,12 @@ This project adheres to `Semantic Versioning <http://semver.org/>`_.
 * WiP: Added an option the import pre-built quantum dots.
 
 
+0.9.1
+*****
+* Added a new conceptual DFT (CDFT) workflow to Nano-CAT
+  (https://github.com/nlesc-nano/nano-CAT/pull/57).
+
+
 0.9.0
 *****
 * Moved a number of functions to the `nanoutils <https://github.com/nlesc-nano/Nano-Utils>`_ package.

README.rst

@@ -16,7 +16,7 @@
 
 
 ##############################
-Compound Attachment Tool 0.9.0
+Compound Attachment Tool 0.9.1
 ##############################
 
 **CAT** is a collection of tools designed for the construction of various chemical compounds.