rdworks 0.47.1__py3-none-any.whl → 0.48.1__py3-none-any.whl

rdworks/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.47.1'
+__version__ = '0.48.1'
 
 from rdworks.conf    import Conf
 from rdworks.mol     import Mol

rdworks/ionized.py

@@ -1,4 +1,5 @@
 import importlib.resources
+from types import SimpleNamespace
 import pandas as pd
 
 from rdkit import Chem
@@ -6,6 +7,11 @@ from rdkit import Chem
 # adapted from https://github.com/dptech-corp/Uni-pKa/enumerator
 
 class IonizedStates:
+    """Knowledge-based enumeration of (de)protonated states"""
+
+    smarts_path = importlib.resources.files('rdworks.predefined.ionized')
+    ionization_patterns = pd.read_csv(smarts_path / 'simple_smarts_pattern.csv')
+    
     # Unreasonable chemical structures
     unreasonable_patterns = [
         Chem.MolFromSmarts(s) for s in [
@@ -31,67 +37,38 @@ class IonizedStates:
             "[N+1](=O)-[O]-[H]",
         ]]
 
-    smarts_path = importlib.resources.files('rdworks.predefined.ionized')
-    protonation_patterns = pd.read_csv(smarts_path / 'simple_smarts_pattern.csv')
 
-    def __init__(self, smiles:str):
+    def __init__(self, smiles: str, charge_min: int = -2, charge_max: int = 2):
         self.smiles = Chem.CanonSmiles(smiles)
+        self.charge_max = charge_max
+        self.charge_min = charge_min
+
         self.rdmol = Chem.MolFromSmiles(self.smiles)
         self.rdmol_H = Chem.AddHs(self.rdmol)
         self.charge = Chem.GetFormalCharge(self.rdmol_H)
-        self.charge_max =  2
-        self.charge_min = -2
+        
         # initial states
         self.states = {self.smiles : (self.rdmol_H, self.charge)}
-        # initial protonation sites
-        self.protonation_sites = {self.smiles : self.set_protonation_sites(self.smiles)}
-        # generate initial states
-        self.protonate(self.smiles)
+        
+        # initial ionization sites
+        self.sites = {self.smiles: self.set_ionization_sites(self.smiles)}
 
-    
-    def get_protonation_sites(self) -> dict:
-        return self.protonation_sites
+        # pKa pairs: 
+        # HA(acid) + H2O == A-(base) + H3O+ or HA+(acid) + H2O == A(base) + H3O+
+        self.pairs = []
 
-    
-    def get_states_by_charge(self) -> dict:
+        # iteratively build an ensemble of ionized states
         self.ensemble()
-        data = {}
-        for smiles, (romol, charge) in self.states.items():
-            if charge in data:
-                data[charge].append(smiles)
-            else:
-                data[charge] = [smiles]
 
-        return data
-
-    def get_states(self) -> list:
-        return [smiles for smiles in self.states]
-    
-
-    def get_states_mol(self) -> list[Chem.Mol]:
-        return [romol for smiles, (romol, charge) in self.states.items()]
-    
-
-    def get_num_states(self) -> int:
-        return len(self.states)
 
     
     @staticmethod
-    def clean_smiles(rdmol:Chem.Mol) -> str:
-        Chem.SanitizeMol(rdmol)
-        rdmol = Chem.MolFromSmiles(Chem.MolToSmiles(rdmol))
-        rdmol_H = Chem.AddHs(rdmol)
-        rdmol = Chem.RemoveHs(rdmol_H)
-        return Chem.CanonSmiles(Chem.MolToSmiles(rdmol))
-
-
-    @staticmethod
-    def set_protonation_sites(smiles:str) -> tuple:
+    def set_ionization_sites(smiles: str) -> tuple:
         subject = Chem.MolFromSmiles(smiles)
         subject = Chem.AddHs(subject)
         charge = Chem.GetFormalCharge(subject)        
         indices = [] # atom indices of protonation/deprotonation site(s)
-        for i, name, smarts, smarts_index, acid_or_base in IonizedStates.protonation_patterns.itertuples():
+        for i, name, smarts, smarts_index, acid_or_base in IonizedStates.ionization_patterns.itertuples():
             pattern = Chem.MolFromSmarts(smarts)
             matches = subject.GetSubstructMatches(pattern)
             # returns a list of tuples, where each tuple contains the indices 
@@ -100,21 +77,34 @@ class IonizedStates:
             if len(matches) > 0:
                 smarts_index = int(smarts_index)
                 indices += [(match[smarts_index], acid_or_base) for match in matches]
+        
         return (list(set(indices)), subject, charge)
+    
+
+    @staticmethod
+    def clean_smiles(rdmol: Chem.Mol) -> str:
+        Chem.SanitizeMol(rdmol)
+        rdmol = Chem.MolFromSmiles(Chem.MolToSmiles(rdmol))
+        rdmol_H = Chem.AddHs(rdmol)
+        rdmol = Chem.RemoveHs(rdmol_H)
+        return Chem.CanonSmiles(Chem.MolToSmiles(rdmol))
 
 
     @staticmethod
-    def reasonable(romol:Chem.Mol) -> bool:
+    def reasonable(romol: Chem.Mol) -> bool:
         return all([len(romol.GetSubstructMatches(p)) == 0 for p in IonizedStates.unreasonable_patterns])
+    
 
-        
-    def protonate(self, smiles:str) -> int:
+    def ionize(self, smiles: str | None = None) -> int:
         num_added_states = 0
         
-        if smiles not in self.protonation_sites:
-            self.protonation_sites[smiles] = self.set_protonation_sites(smiles)   
+        if smiles is None:
+            smiles = self.smiles
+
+        if smiles not in self.sites:
+            self.sites[smiles] = self.set_ionization_sites(smiles)
         
-        (indices, subject, charge) = self.protonation_sites[smiles]
+        (indices, subject, charge) = self.sites[smiles]
         
         if (charge >= self.charge_max) or (charge <= self.charge_min):
             # formal charge will be increased or decreased by protonation/deprotonation
@@ -149,22 +139,56 @@ class IonizedStates:
                 edmol = Chem.AddHs(edmol)
             
             # Clean up and save SMILES
-            state_smiles = IonizedStates.clean_smiles(edmol)
-            state_mol = Chem.MolFromSmiles(state_smiles)
-            state_mol = Chem.AddHs(state_mol)
-            state_charge = Chem.GetFormalCharge(state_mol)
-            if self.reasonable(state_mol):
-                if state_smiles in self.states:
+            ionized_smiles = IonizedStates.clean_smiles(edmol)
+            ionized_mol = Chem.MolFromSmiles(ionized_smiles)
+            ionized_mol = Chem.AddHs(ionized_mol)
+            ionized_charge = Chem.GetFormalCharge(ionized_mol)
+            if self.reasonable(ionized_mol):
+                if ionized_smiles in self.states:
                     continue
-                self.states[state_smiles] = (state_mol, state_charge)
+                self.states[ionized_smiles] = (ionized_mol, ionized_charge)
                 num_added_states += 1
+            
+                # store acid-base pair information for pKa
+                if acid_or_base == 'A':
+                    self.pairs.append((i, smiles, ionized_smiles))
+                elif acid_or_base == 'B':
+                    self.pairs.append((i, ionized_smiles, smiles))
 
         return num_added_states
-
+    
     
     def ensemble(self) -> None:
+        # populate initial states
+        self.ionize()
+
+        # propagate
         num_added_states = None       
         while num_added_states is None or num_added_states > 0:
-            states = self.states.copy()
+            states = self.states.copy() # dictionary
+            # self.ionize(smiles) below will change self.states
+            # so we cannot iterate self.states. Instead we will
+            # iterate over a copy of the self.states
             for smiles in states:
-                num_added_states = self.protonate(smiles)
+                num_added_states = self.ionize(smiles) 
+                
+    
+    def count(self) -> int:
+        return len(self.states)
+
+
+    def get_sites(self) -> dict:
+        return self.sites
+    
+    
+    def get_smiles(self) -> list[str]:
+        return [smiles for smiles in self.states]
+    
+
+    def get_rdmol(self) -> list[Chem.Mol]:
+        return [romol for smiles, (romol, charge) in self.states.items()]
+    
+
+    def get_pairs(self) -> list:
+        return self.pairs
+    

{rdworks-0.47.1.dist-info → rdworks-0.48.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdworks
-Version: 0.47.1
+Version: 0.48.1
 Summary: Routine tasks built on RDKit and other tools
 Author-email: Sung-Hun Bae <sunghun.bae@gmail.com>
 Maintainer-email: Sung-Hun Bae <sunghun.bae@gmail.com>

{rdworks-0.47.1.dist-info → rdworks-0.48.1.dist-info}/RECORD

@@ -1,8 +1,8 @@
-rdworks/__init__.py,sha256=CkKXxGhqvK8jzCxjOXnj2IOOvdHKpHE6ekjM5ZECSUw,1368
+rdworks/__init__.py,sha256=TjR6uygQrAgURJ2d1zoPHmai8uJLNF0oFmG5s8Q6TJI,1368
 rdworks/conf.py,sha256=iQLb3Qg3pjGiiMVMJ5-d57BC1id3zxEhEGlhhrLrA_c,34162
 rdworks/descriptor.py,sha256=34T_dQ6g8v3u-ym8TLKbQtxIIV5TEo-d3pdedq3o-cg,2106
 rdworks/display.py,sha256=JR0gR26UpH-JCxVOaqXZCUj2MiGZSrx9Me87FncspVI,13469
-rdworks/ionized.py,sha256=5oIjMRpkX792RIpEEE2Ir96icfFaN_h21mSihhfQPAw,6713
+rdworks/ionized.py,sha256=LQLApkskhPPMZCmFMbStJXS-ugVTDSzZJD7pQbJTe8E,7425
 rdworks/matchedseries.py,sha256=A3ON4CUpQV159mu9VqgNiJ8uoQ9ePOry9d3ra4NCAgc,10377
 rdworks/mol.py,sha256=e62DYV8XeqLL1mBydbS881pSUfJjaeHxalG64CIant8,68133
 rdworks/mollibr.py,sha256=X4UBO6Ga-QmNS7RwUiaDYAx0Q5hnWs71yTkEpH02Qb4,37696
@@ -66,8 +66,8 @@ rdworks/predefined/misc/reactive-part-3.xml,sha256=LgWHSEbRTVmgBoIO45xbTo1xQJs0X
 rdworks/predefined/misc/reactive.xml,sha256=syedoQ6VYUfRLnxy99ObuDniJ_a_WhrWAJbTKFfJ6VY,11248
 rdworks/xtb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 rdworks/xtb/wrapper.py,sha256=NQgkdRKN5YEtv_UPYKWDijzMEs5v2kFrhUWHqiro7bE,22174
-rdworks-0.47.1.dist-info/licenses/LICENSE,sha256=UOkJSBqYyQUvtCp7a-vdCANeEcLE2dnTie_eB1By5SY,1074
-rdworks-0.47.1.dist-info/METADATA,sha256=w8BCgsWZ6AqzjSjZL1z4ker0-mwca09u5XiBsXa0ycw,1967
-rdworks-0.47.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rdworks-0.47.1.dist-info/top_level.txt,sha256=05C98HbvBK2axUBogC_hAT_CdpOeQYGnQ6vRAgawr8s,8
-rdworks-0.47.1.dist-info/RECORD,,
+rdworks-0.48.1.dist-info/licenses/LICENSE,sha256=UOkJSBqYyQUvtCp7a-vdCANeEcLE2dnTie_eB1By5SY,1074
+rdworks-0.48.1.dist-info/METADATA,sha256=op0QbvR5pScMsbe112ZrEUmSoT77msXNuZCd-zhTOF8,1967
+rdworks-0.48.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rdworks-0.48.1.dist-info/top_level.txt,sha256=05C98HbvBK2axUBogC_hAT_CdpOeQYGnQ6vRAgawr8s,8
+rdworks-0.48.1.dist-info/RECORD,,