nerdd-module 0.3.39__tar.gz → 0.3.41__tar.gz

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nerdd-module
-Version: 0.3.39
+Version: 0.3.41
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/nerdd_module/config/models.py

@@ -51,15 +51,50 @@ class Choice(BaseModel):
     label: Optional[str] = None
 
 
+JobType = Literal["int", "integer", "float", "bool", "boolean", "str", "string"]
+
+
 class JobParameter(BaseModel):
     name: str
-    type: str
+    type: JobType
     visible_name: Optional[str] = None
     help_text: Optional[str] = None
     default: Any = None
     required: bool = False
     choices: Optional[List[Choice]] = None
 
+    def validate_value(self, value: Any) -> None:
+        if self.type == ["int", "integer"]:
+            if not isinstance(value, int):
+                raise ValueError(
+                    f"Parameter {self.name} must be an integer, got {type(value).__name__}."
+                )
+        elif self.type == "float":
+            if not isinstance(value, (int, float)):
+                raise ValueError(
+                    f"Parameter {self.name} must be a float, got {type(value).__name__}."
+                )
+        elif self.type in ["bool", "boolean"]:
+            if not isinstance(value, bool):
+                raise ValueError(
+                    f"Parameter {self.name} must be a boolean, got {type(value).__name__}."
+                )
+        elif self.type in ["str", "string"]:
+            if not isinstance(value, str):
+                raise ValueError(
+                    f"Parameter {self.name} must be a string, got {type(value).__name__}."
+                )
+        else:
+            raise ValueError(f"Unknown type for parameter {self.name}: {self.type}")
+
+        if self.choices:
+            choice_values = [choice.value for choice in self.choices]
+            if value not in choice_values:
+                raise ValueError(
+                    f"Invalid value for parameter {self.name}: {value}. "
+                    f"Expected one of {choice_values}."
+                )
+
 
 Task = Literal[
     "molecular_property_prediction",
@@ -207,3 +242,25 @@ class Module(BaseModel):
                 )
 
         return values
+
+    def validate_job_parameters(self, params: dict) -> None:
+        """
+        Validate the job parameters against the module's job parameters.
+        Raises an error if a parameter is missing or has an invalid type.
+        """
+        # make sure that all job parameters are present
+        for param in self.job_parameters:
+            if param.name not in params and param.required:
+                raise ValueError(f"Missing required job parameter: {param.name}")
+
+        # check that there are no additional parameters
+        param_names = {param.name for param in self.job_parameters}
+        for key in params.keys():
+            if key not in param_names:
+                raise ValueError(f"Unknown job parameter: {key}")
+
+        # validate all parameters
+        for param in self.job_parameters:
+            if param.name in params:
+                value = params[param.name]
+                param.validate_value(value)

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/nerdd_module/preprocessing/__init__.py

@@ -3,5 +3,6 @@ from .chembl_structure_pipeline import *
 from .filter_by_element import *
 from .filter_by_weight import *
 from .preprocessing_step import *
+from .remove_small_fragments import *
 from .remove_stereochemistry import *
 from .sanitize import *

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/nerdd_module/preprocessing/filter_by_weight.py

@@ -6,12 +6,14 @@ from rdkit.Chem.rdMolDescriptors import CalcExactMolWt
 from ..problem import InvalidWeightProblem, Problem
 from .preprocessing_step import PreprocessingStep
 
+__all__ = ["FilterByWeight"]
+
 
 class FilterByWeight(PreprocessingStep):
     def __init__(
         self,
-        min_weight: float,
-        max_weight: float,
+        min_weight: float = 0,
+        max_weight: float = float("inf"),
         remove_invalid_molecules: bool = False,
     ) -> None:
         super().__init__()

nerdd_module-0.3.41/nerdd_module/preprocessing/remove_small_fragments.py

@@ -0,0 +1,26 @@
+from typing import List, Optional, Tuple
+
+from rdkit.Chem import GetMolFrags, Mol
+from rdkit.Chem.rdMolDescriptors import CalcExactMolWt
+
+from ..problem import Problem
+from .preprocessing_step import PreprocessingStep
+
+__all__ = ["RemoveSmallFragments"]
+
+
+class RemoveSmallFragments(PreprocessingStep):
+    def __init__(
+        self,
+    ) -> None:
+        super().__init__()
+
+    def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
+        fragments = GetMolFrags(mol, asMols=True)
+        if len(fragments) > 1:
+            # select the largest fragment
+            largest_fragment = max(fragments, key=CalcExactMolWt)
+        else:
+            largest_fragment = mol
+
+        return largest_fragment, []

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/nerdd_module/preprocessing/remove_stereochemistry.py

@@ -6,6 +6,8 @@ from rdkit.Chem import RemoveStereochemistry as remove_stereochemistry
 from ..problem import Problem
 from .preprocessing_step import PreprocessingStep
 
+__all__ = ["RemoveStereochemistry"]
+
 
 class RemoveStereochemistry(PreprocessingStep):
     def __init__(self) -> None:

nerdd_module-0.3.41/nerdd_module/preprocessing/sanitize.py

@@ -0,0 +1,31 @@
+import logging
+from typing import List, Optional, Tuple
+
+from rdkit.Chem import AtomKekulizeException, KekulizeException, Mol, SanitizeMol
+
+from ..problem import Problem
+from .preprocessing_step import PreprocessingStep
+
+__all__ = ["Sanitize"]
+
+
+logger = logging.getLogger(__name__)
+
+
+class Sanitize(PreprocessingStep):
+    def __init__(self) -> None:
+        super().__init__()
+
+    def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
+        try:
+            SanitizeMol(mol)
+            return mol, []
+        except KekulizeException:
+            return None, [Problem("kekulization_error", "Failed kekulizing the molecule.")]
+        except AtomKekulizeException:
+            return None, [
+                Problem("atom_kekulization_error", "Failed kekulizing an atom in the molecule.")
+            ]
+        except Exception as e:
+            logger.exception(e)
+            return None, [Problem("sanitization_error", "Failed sanitizing the molecule.")]

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/nerdd_module/tests/predictions.py

@@ -48,6 +48,12 @@ def predictions_atomic_mass_model(representations, version, multiplier):
         output_format="record_list",
     )
 
+@when(
+    "all results are considered",
+    target_fixture="subset",
+)
+def subset_without_none(predictions):
+    return predictions
 
 @when(
     "the subset of the result where the input was not None is considered",

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/nerdd_module.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nerdd-module
-Version: 0.3.39
+Version: 0.3.41
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/nerdd_module.egg-info/SOURCES.txt

@@ -75,6 +75,7 @@ nerdd_module/preprocessing/chembl_structure_pipeline.py
 nerdd_module/preprocessing/filter_by_element.py
 nerdd_module/preprocessing/filter_by_weight.py
 nerdd_module/preprocessing/preprocessing_step.py
+nerdd_module/preprocessing/remove_small_fragments.py
 nerdd_module/preprocessing/remove_stereochemistry.py
 nerdd_module/preprocessing/sanitize.py
 nerdd_module/steps/__init__.py

{nerdd_module-0.3.39 → nerdd_module-0.3.41}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nerdd-module"
-version = "0.3.39"
+version = "0.3.41"
 description = "Base package to create NERDD modules"
 readme = "README.md"
 license = "BSD-3-Clause"

nerdd_module-0.3.39/nerdd_module/preprocessing/sanitize.py

@@ -1,21 +0,0 @@
-from typing import List, Optional, Tuple
-
-from rdkit.Chem import Mol, SanitizeMol
-
-from ..problem import Problem
-from .preprocessing_step import PreprocessingStep
-
-__all__ = ["Sanitize"]
-
-
-class Sanitize(PreprocessingStep):
-    def __init__(self) -> None:
-        super().__init__()
-
-    def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
-        problems: List[Problem] = []
-
-        # sanitize molecule
-        SanitizeMol(mol)
-
-        return mol, problems