sapiopycommons 2024.11.25a373__tar.gz → 2024.12.5a376__tar.gz

{sapiopycommons-2024.11.25a373 → sapiopycommons-2024.12.5a376}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: sapiopycommons
-Version: 2024.11.25a373
+Version: 2024.12.5a376
 Summary: Official Sapio Python API Utilities Package
 Project-URL: Homepage, https://github.com/sapiosciences
 Author-email: Jonathan Steck <jsteck@sapiosciences.com>, Yechen Qiao <yqiao@sapiosciences.com>

{sapiopycommons-2024.11.25a373 → sapiopycommons-2024.12.5a376}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sapiopycommons"
-version='2024.11.25a373'
+version='2024.12.05a376'
 authors = [
     { name="Jonathan Steck", email="jsteck@sapiosciences.com" },
     { name="Yechen Qiao", email="yqiao@sapiosciences.com" },

{sapiopycommons-2024.11.25a373 → sapiopycommons-2024.12.5a376}/src/sapiopycommons/chem/IndigoMolecules.py

@@ -10,7 +10,50 @@ indigo.setOption("render-stereo-style", "ext")
 indigo.setOption("aromaticity-model", "generic")
 indigo.setOption("render-coloring", True)
 indigo.setOption("molfile-saving-mode", "3000")
-indigo_inchi = IndigoInchi(indigo);
+indigo_inchi = IndigoInchi(indigo)
+
+
+# Function to process dative bonds in a molecule
+# Returns True if at least one dative bond (_BOND_COORDINATION) was removed
+def remove_dative_bonds_in_mol(molecule: IndigoObject) -> bool:
+    """
+    Remove all dative bonds in a molecule or a query molecule.
+    :param molecule: The molecule to remove.
+    :return: Whether there are any dative bonds in the molecule that were removed.
+    """
+    dative_bond_removed = False  # Flag to track if any dative bond was removed
+
+    bonds_idx_to_remove = []
+    for bond in molecule.iterateBonds():
+        # Check if the bond is of a dative type (_BOND_COORDINATION = 9)
+        if bond.bondOrder() == 9:  # _BOND_COORDINATION
+            atom1 = bond.source()
+            atom2 = bond.destination()
+
+            # Print bond details for debugging
+            print(f"Processing dative bond between atoms {atom1.index()} and {atom2.index()}")
+
+            # Cache bond information
+            # bond.setBondOrder(1)
+            bonds_idx_to_remove.append(bond.index())
+            dative_bond_removed = True  # Set flag to True
+
+    if not dative_bond_removed:
+        return False
+
+    molecule.removeBonds(bonds_idx_to_remove)
+    return True  # Return whether any dative bond was removed
+
+
+def remove_dative_in_reaction(reaction: IndigoObject) -> bool:
+    """
+    Remove all dative bonds in a reaction or a query reaction, from all reactants and products.
+    :param reaction: The reaction to remove dative bonds.
+    :return: Whether there are any dative bonds in the reaction that were removed.
+    """
+    reactant_dative_removed: bool = any(remove_dative_bonds_in_mol(reactant) for reactant in reaction.iterateReactants())
+    product_dative_removed: bool = any(remove_dative_bonds_in_mol(product) for product in reaction.iterateProducts())
+    return reactant_dative_removed or product_dative_removed
 
 
 def highlight_mol_substructure(query: IndigoObject, sub_match: IndigoObject):

{sapiopycommons-2024.11.25a373 → sapiopycommons-2024.12.5a376}/src/sapiopycommons/chem/Molecules.py

@@ -9,7 +9,8 @@ from rdkit.Chem import rdMolDescriptors
 from rdkit.Chem.EnumerateStereoisomers import StereoEnumerationOptions, EnumerateStereoisomers
 from rdkit.Chem.MolStandardize import rdMolStandardize
 from rdkit.Chem.SaltRemover import SaltRemover
-from rdkit.Chem.rdchem import Mol
+from rdkit.Chem.rdChemReactions import ChemicalReaction
+from rdkit.Chem.rdchem import Mol, RWMol, Bond
 
 from sapiopycommons.chem.IndigoMolecules import indigo, renderer, indigo_inchi
 
@@ -22,6 +23,24 @@ tautomer_params.tautomerRemoveIsotopicHs = True
 enumerator = rdMolStandardize.TautomerEnumerator(tautomer_params)
 
 
+def remove_dative_bonds_from_mol(mol: Mol) -> RWMol:
+    """
+    Create a new copy of RWMol molecule and remove all dative bonds in the molecule.
+    :param mol: The original molecule
+    :return: The new molecule with dative bonds removed.
+    """
+    ret: RWMol = Chem.RWMol(mol)
+    bonds_to_remove = []
+    bond: Bond
+    for bond in ret.GetBonds():
+        if bond.GetBondType() in [Chem.BondType.DATIVER, Chem.BondType.DATIVE, Chem.BondType.DATIVEL,
+                                  Chem.BondType.DATIVEONE]:
+            bonds_to_remove.append((bond.GetBeginAtomIdx(), bond.GetEndAtomIdx()))
+    for atom1_idx, atom2_idx in bonds_to_remove:
+        ret.RemoveBond(atom1_idx, atom2_idx)
+    return ret
+
+
 def get_enhanced_stereo_reg_hash(mol: Mol, enhanced_stereo: bool) -> str:
     """
     Get the Registration Hash for the molecule by the current registration configuration.
@@ -217,7 +236,9 @@ def mol_to_sapio_substance(mol: Mol, include_stereoisomers=False,
     # This is number of H-Bond Donor
     molecule["numHBonds"] = rdMolDescriptors.CalcNumHBD(mol)
     molecule["molBlock"] = molBlock
-    rdkit_inchi = MolToInchi(mol)
+    # Create a copy of molecule before modifying it for InChI generation.
+    inchi_mol: Mol = remove_dative_bonds_from_mol(mol)
+    rdkit_inchi = MolToInchi(inchi_mol)
     # If INCHI is completely invalid, we fail this molecule.
     if not rdkit_inchi:
         MolToInchi(mol, treatWarningAsError=True)
@@ -231,13 +252,13 @@ def mol_to_sapio_substance(mol: Mol, include_stereoisomers=False,
     indigo_mol.aromatize()
     if enhanced_stereo:
         # Remove enhanced stereo layer when generating InChI as the stereo hash is generated separately for reg.
-        mol_copy: Mol = Chem.Mol(mol)
-        Chem.CanonicalizeEnhancedStereo(mol_copy)
-        molecule["inchi"] = Chem.MolToInchi(mol_copy)
-        molecule["inchiKey"] = Chem.MolToInchiKey(mol_copy)
+        Chem.CanonicalizeEnhancedStereo(inchi_mol)
+        molecule["inchi"] = Chem.MolToInchi(inchi_mol)
+        molecule["inchiKey"] = Chem.MolToInchiKey(inchi_mol)
     else:
         indigo_inchi.resetOptions()
-        indigo_inchi_str = indigo_inchi.getInchi(indigo_mol)
+        indigo_inchi_mol = indigo.loadMolecule(Chem.MolToMolBlock(inchi_mol, forceV3000=True))
+        indigo_inchi_str = indigo_inchi.getInchi(indigo_inchi_mol)
         molecule["inchi"] = indigo_inchi_str
         indigo_inchi_key_str = indigo_inchi.getInchiKey(indigo_inchi_str)
         molecule["inchiKey"] = indigo_inchi_key_str
@@ -245,7 +266,6 @@ def mol_to_sapio_substance(mol: Mol, include_stereoisomers=False,
     molecule["reg_hash"] = get_enhanced_stereo_reg_hash(mol, enhanced_stereo=enhanced_stereo)
     molecule["cxsmiles_hash"] = get_cxs_smiles_hash(mol, enhanced_stereo=enhanced_stereo)
     molecule["has_or_group"] = get_has_or_group(mol, enhanced_stereo=enhanced_stereo)
-
     return molecule
 
 

{sapiopycommons-2024.11.25a373 → sapiopycommons-2024.12.5a376}/src/sapiopycommons/eln/experiment_handler.py

@@ -824,7 +824,7 @@ class ExperimentHandler:
             The record to remove from the given step.
             The record may be provided as either a DataRecord, PyRecordModel, or WrappedRecordModel.
         """
-        self.remove_eln_row(step, [record])
+        self.remove_eln_rows(step, [record])
 
     def add_sample_details(self, step: Step, samples: list[RecordModel], wrapper_type: type[WrappedType]) \
             -> list[PyRecordModel | WrappedType]:

{sapiopycommons-2024.11.25a373 → sapiopycommons-2024.12.5a376}/src/sapiopycommons/general/time_util.py

@@ -2,9 +2,12 @@ from __future__ import annotations
 
 import time
 from datetime import datetime
+from typing import Any
 
 import pytz
 
+from sapiopycommons.general.exceptions import SapioException
+
 __timezone = None
 """The default timezone. Use TimeUtil.set_default_timezone in a global context before making use of TimeUtil."""
 
@@ -26,7 +29,7 @@ class TimeUtil:
     with static date fields, use "UTC" as your input timezone.
     """
     @staticmethod
-    def get_default_timezone():
+    def get_default_timezone() -> Any:
         """
         Returns the timezone that TimeUtil is currently using as its default.
         """
@@ -45,7 +48,7 @@ class TimeUtil:
         __timezone = TimeUtil.__to_tz(new_timezone)
 
     @staticmethod
-    def __to_tz(timezone: str | int = None):
+    def __to_tz(timezone: str | int = None) -> Any:
         """
         :param timezone: Either the name of a timezone, a UTC offset in seconds, or None if the default should be used.
         :return: The timezone object to use for the given input. If the input is None, uses the default timezone.
@@ -55,11 +58,28 @@ class TimeUtil:
             # because pytz may return timezones from strings in Local Mean Time instead of a timezone with a UTC offset.
             # LMT may be a few minutes off of the actual time in that timezone right now.
             # https://stackoverflow.com/questions/35462876
-            offset: int = int(datetime.now(pytz.timezone(timezone)).utcoffset().total_seconds() / 60)
-            return pytz.FixedOffset(offset)
+            offset: int = TimeUtil.__get_timezone_offset(timezone)
+            # This function takes an offset in minutes, so divide the provided offset seconds by 60.
+            return pytz.FixedOffset(offset // 60)
         if isinstance(timezone, int):
             return pytz.FixedOffset(timezone // 60)
-        return TimeUtil.get_default_timezone()
+        if timezone is None:
+            return TimeUtil.get_default_timezone()
+        raise SapioException(f"Unhandled timezone object of type {type(timezone)}: {timezone}")
+
+    @staticmethod
+    def __get_timezone_offset(timezone: str | int | None) -> int:
+        """
+        :param timezone: Either the name of a timezone, a UTC offset in seconds, or None if the default should be used.
+        :return: The UTC offset in seconds of the provided timezone.
+        """
+        if isinstance(timezone, int):
+            return timezone
+        if isinstance(timezone, str):
+            timezone = pytz.timezone(timezone)
+        if timezone is None:
+            timezone = TimeUtil.get_default_timezone()
+        return int(datetime.now(timezone).utcoffset().total_seconds())
 
     @staticmethod
     def current_time(timezone: str | int = None) -> datetime:
@@ -127,6 +147,64 @@ class TimeUtil:
         tz = TimeUtil.__to_tz(timezone)
         return int(datetime.strptime(time_point, time_format).replace(tzinfo=tz).timestamp() * 1000)
 
+    # FR-47296: Provide functions for shifting between timezones.
+    @staticmethod
+    def shift_now(to_timezone: str = "UTC", from_timezone: str | None = None) -> int:
+        """
+        Take the current time in from_timezone and output the epoch timestamp that would display that same time in
+        to_timezone. A use case for this is when dealing with static date fields to convert a provided timestamp to the
+        value necessary to display that timestamp in the same way when viewed in the static date field.
+
+        :param to_timezone: The timezone to shift to. If not provided, uses UTC.
+        :param from_timezone: The timezone to shift from. If no timezone is provided, uses the global
+            timezone variable set by the TimeUtil. A list of valid timezones can be found at
+            https://en.wikipedia.org/wiki/List_of_tz_database_time_zones. May also accept a UTC offset in seconds.
+        :return: The epoch timestamp that would display as the same time in to_timezone as the current time in
+            from_timezone.
+        """
+        millis: int = TimeUtil.now_in_millis()
+        return TimeUtil.shift_millis(millis, to_timezone, from_timezone)
+
+    @staticmethod
+    def shift_millis(millis: int, to_timezone: str = "UTC", from_timezone: str | None = None) -> int:
+        """
+        Take a number of milliseconds for a time in from_timezone and output the epoch timestamp that would display that
+        same time in to_timezone. A use case for this is when dealing with static date fields to convert a provided
+        timestamp to the value necessary to display that timestamp in the same way when viewed in the static date field.
+
+        :param millis: The time in milliseconds to convert from.
+        :param to_timezone: The timezone to shift to. If not provided, uses UTC.
+        :param from_timezone: The timezone to shift from. If no timezone is provided, uses the global
+            timezone variable set by the TimeUtil. A list of valid timezones can be found at
+            https://en.wikipedia.org/wiki/List_of_tz_database_time_zones. May also accept a UTC offset in seconds.
+        :return: The epoch timestamp that would display as the same time in to_timezone as the given time in
+            from_timezone.
+        """
+        to_offset: int = TimeUtil.__get_timezone_offset(to_timezone) * 1000
+        from_offset: int = TimeUtil.__get_timezone_offset(from_timezone) * 1000
+        return millis + from_offset - to_offset
+
+    @staticmethod
+    def shift_format(time_point: str, time_format: str, to_timezone: str = "UTC", from_timezone: str | None = None) \
+            -> int:
+        """
+        Take a timestamp for a time in from_timezone and output the epoch timestamp that would display that same time
+        in to_timezone. A use case for this is when dealing with static date fields to convert a provided timestamp to
+        the value necessary to display that timestamp in the same way when viewed in the static date field.
+
+        :param time_point: The time in some date/time format to convert from.
+        :param time_format: The format that the time_point is in. Documentation for how the time formatting works
+            can be found at https://docs.python.org/3.10/library/datetime.html#strftime-and-strptime-behavior
+        :param to_timezone: The timezone to shift to. If not provided, uses UTC.
+        :param from_timezone: The timezone to shift from. If no timezone is provided, uses the global
+            timezone variable set by the TimeUtil. A list of valid timezones can be found at
+            https://en.wikipedia.org/wiki/List_of_tz_database_time_zones. May also accept a UTC offset in seconds.
+        :return: The epoch timestamp that would display as the same time in to_timezone as the given time in
+            from_timezone.
+        """
+        millis: int = TimeUtil.format_to_millis(time_point, time_format, from_timezone)
+        return TimeUtil.shift_millis(millis, to_timezone, from_timezone)
+
     # FR-46154: Create a function that determines if a string matches a time format.
     @staticmethod
     def str_matches_format(time_point: str, time_format: str) -> bool: