ENH: Lay the groundwork fork for the Nano-CAT ligand branching workflow

CAT/__version__.py

@@ -1,3 +1,3 @@
 """The **CAT** version."""
 
-__version__ = '0.11.0'
+__version__ = '0.11.1'

CAT/base.py

@@ -59,6 +59,7 @@
     from nanoCAT.cdft import init_cdft
     if Version(nanoCAT.__version__) >= Version("0.7.2"):
         from nanoCAT.cone_angle import init_cone_angle
+        from nanoCAT.bulk.mol_graph2 import init_branch_distance
 
     NANO_CAT: Optional[ImportError] = None
 except ImportError as ex:
@@ -258,6 +259,7 @@ def prep_ligand(ligand_df: SettingsDataFrame) -> SettingsDataFrame:
     crs = ligand_df.settings.optional.ligand.crs
     cdft = ligand_df.settings.optional.ligand.cdft
     cone_angle = ligand_df.settings.optional.ligand.cone_angle
+    branch_distance = ligand_df.settings.optional.ligand.branch_distance
 
     # Identify functional groups within the ligand.
     ligand_df = init_ligand_anchoring(ligand_df)
@@ -278,6 +280,12 @@ def prep_ligand(ligand_df: SettingsDataFrame) -> SettingsDataFrame:
         for lig in ligand_df[MOL]:
             allign_axis(lig)
 
+    if branch_distance:
+        val_nano_cat("The ligand branch-distance workflow requires the nano-CAT package")
+        if Version(nanoCAT.__version__) < Version("0.7.2"):
+            raise ImportError("The `cone_angle` workflow require Nano-CAT 0.7.2")
+        init_branch_distance(ligand_df)
+
     # Perform a COSMO-RS calculation on the ligands
     if crs:
         val_nano_cat("Ligand COSMO-RS calculations require the nano-CAT package")

CAT/data_handling/validation_schemas.py

@@ -517,6 +517,12 @@ def _get_crsjob() -> type:
             And(bool, Use(lambda n: {'job1': 'ADFJob'} if n else False)),
             error='optional.ligand.cdft expects a boolean or dictionary'
         ),
+
+    Optional_('branch_distance', default=False):
+        Or(
+            bool,
+            error='optional.ligand.branch_distance expects a boolean'
+        ),
 })
 
 

CAT/workflows/__init__.pyi

@@ -42,3 +42,5 @@ SETTINGS_BDE2: Tuple[str, str] = ...
 SETTINGS_CDFT: Tuple[str, str] = ...
 V_BULK: Tuple[str, str] = ...
 CONE_ANGLE: Tuple[str, str] = ...
+BRANCH_DISTANCE: Tuple[str, str] = ...
+BRANCH_SIZE: Tuple[str, str] = ...

CAT/workflows/key_map.py

@@ -55,6 +55,8 @@
     'SETTINGS_CDFT': ('settings', 'cdft 1'),
     'V_BULK': ('V_bulk', ''),
     'CONE_ANGLE': ('cone_angle', 'dist=0.0'),
+    'BRANCH_DISTANCE': ('branch_distance', ''),
+    'BRANCH_SIZE': ('branch_size', ''),
 })
 
 globals().update(KEY_MAP)

CAT/workflows/key_map.pyi

@@ -41,3 +41,5 @@ SETTINGS_BDE2: Tuple[str, str] = ...
 SETTINGS_CDFT: Tuple[str, str] = ...
 V_BULK: Tuple[str, str] = ...
 CONE_ANGLE: Tuple[str, str] = ...
+BRANCH_DISTANCE: Tuple[str, str] = ...
+BRANCH_SIZE: Tuple[str, str] = ...

CAT/workflows/workflow.py

@@ -413,12 +413,12 @@ def __call__(self, func: Callable, df: pd.DataFrame,
             else:
                 try:
                     df.loc[slice2] = value
-                except ValueError as ex:
+                except ValueError:
                     logger.debug(f"df = {aNDRepr.repr(df)}")
                     logger.debug(f"index = {aNDRepr.repr(slice2[0])}")
                     logger.debug(f"columns = {aNDRepr.repr(slice2[1])}")
                     logger.debug(f"value = {aNDRepr.repr(value)}")
-                    raise ex
+                    raise
         logger.info(f"Finishing {self.description}\n")
 
     def from_db(self, df: pd.DataFrame, inplace: bool = True, get_mol: bool = False,
@@ -624,7 +624,7 @@ def _isnull(df: pd.DataFrame, columns: list) -> pd.DataFrame:
             np.dtype(bool): operator.invert,
             np.dtype(int): _lt_0,
             np.dtype(float): pd.isnull,
-            np.dtype(object): pd.isnull
+            np.dtype(object): lambda i: pd.isnull(i) | (i == ""),
         }
 
         ret = pd.DataFrame(index=df.index)

CAT/workflows/workflow_dicts.py

@@ -44,6 +44,8 @@
     CDFT_MU_MINUS,
     CDFT_MU_PLUS,
     CONE_ANGLE,
+    BRANCH_DISTANCE,
+    BRANCH_SIZE,
 )
 
 if TYPE_CHECKING:
@@ -113,6 +115,8 @@ def finalize_templates():
                                     CDFT_MU_MINUS, CDFT_MU_PLUS)},
         'cone_angle': {'import_columns': {CONE_ANGLE: np.nan},
                        'export_columns': (CONE_ANGLE,)},
+        'branch_distance': {'import_columns': {BRANCH_DISTANCE: "", BRANCH_SIZE: ""},
+                            'export_columns': (BRANCH_DISTANCE, BRANCH_SIZE)},
     }
 
     templates = _load_templates()

CAT/workflows/workflow_yaml.yaml

@@ -192,3 +192,13 @@ cdft:
         keep_files: [optional, ligand, cdft, keep_files]
         job1: [optional, ligand, cdft, job1]
         s1: [optional, ligand, cdft, s1]
+
+branch_distance:
+    description: Ligand branch size & distance computation
+    mol_type: ligand
+    template:
+        db: [optional, database, db]
+        read: [optional, database, read]
+        write: [optional, database, write]
+        overwrite: [optional, database, overwrite]
+        thread_safe: [optional, database, thread_safe]

CHANGELOG.rst

@@ -6,6 +6,11 @@ All notable changes to this project will be documented in this file.
 This project adheres to `Semantic Versioning <http://semver.org/>`_.
 
 
+0.11.1
+******
+* Lay the groundwork for the new Nano-CAT ligand branching workflow.
+
+
 0.11.0
 ******
 * Add the `remove_anchor_hydrogens` option to the cone-angle workflow

docs/4_optional.rst

@@ -36,6 +36,7 @@ Option                                    Description
 :attr:`optional.ligand.cosmo-rs`          Perform a property calculation with COSMO-RS on the ligand.
 :attr:`optional.ligand.cdft`              Perform a conceptual DFT calculation with ADF on the ligand.
 :attr:`optional.ligand.cone_angle`        Compute the smallest enclosing cone angle within a ligand.
+:attr:`optional.ligand.branch_distance`   Compute the size of branches and their distance w.r.t. to the anchor within a ligand.
 
 :attr:`optional.qd.dirname`               The name of the directory where all quantum dots will be stored.
 :attr:`optional.qd.construct_qd`          Whether or not the quantum dot should actually be constructed or not.
@@ -588,6 +589,7 @@ Ligand
                 cosmo-rs: False
                 cdft: False
                 cone_angle: False
+                branch_distance: False
 
 |
 
@@ -943,6 +945,14 @@ Ligand
 
         Accepts one or more distances.
 
+
+    .. attribute:: optional.ligand.branch_distance
+
+        :Parameter:     * **Type** - :class:`bool`
+                        * **Default value** – ``False``
+
+        Compute the size of branches and their distance w.r.t. to the anchor within a ligand.
+
 |
 
 QD