rdworks 0.52.1__tar.gz → 0.53.1__tar.gz

{rdworks-0.52.1 → rdworks-0.53.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdworks
-Version: 0.52.1
+Version: 0.53.1
 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-0.52.1 → rdworks-0.53.1}/src/rdworks/__init__.py

@@ -1,11 +1,11 @@
-__version__ = '0.52.1'
+__version__ = '0.53.1'
 
 from rdworks.conf    import Conf
 from rdworks.mol     import Mol
 from rdworks.mollibr import MolLibr
 
-from rdworks.stereoisomers import complete_stereoisomers
-from rdworks.tautomers import complete_tautomers
+from rdworks.workflow import complete_stereoisomers, complete_tautomers
+
 from rdworks.ionized import IonizedStates
 
 from rdworks.readin import read_csv, merge_csv, read_dataframe, read_smi, read_sdf, read_mae 

{rdworks-0.52.1 → rdworks-0.53.1}/src/rdworks/mol.py

@@ -28,7 +28,6 @@ from rdkit.Chem import (
     Draw, rdDepictor, inchi,
     rdDistGeom, rdMolAlign, rdMolTransforms, rdmolops
     )
-from rdkit.Chem.Draw import rdMolDraw2D
 from rdkit.ML.Cluster import Butina
 from PIL import Image
 
@@ -43,6 +42,8 @@ from rdworks.autograph import NMRCLUST, DynamicTreeCut, RCKmeans, AutoGraph
 from rdworks.bitqt import BitQT
 from rdworks.torsion import create_torsion_fragment, get_torsion_atoms
 from rdworks.display import render_svg, render_png
+from rdworks.stereoisomers import enumerate_stereoisomers, enumerate_ring_bond_stereoisomers
+
 
 from scour.scour import scourString
 
@@ -329,6 +330,36 @@ class Mol:
         return self
 
 
+    def count_stereoisomers(self) -> int:
+        """Counts number of all possible stereoisomers ignoring the current stereochemistry.
+
+        Returns:
+            int: number of stereoisomers.
+        """
+
+        ring_bond_stereo_info = self.get_ring_bond_stereo()
+        mol = self.copy()
+        # remove stereochemistry
+        mol = mol.remove_stereo()
+        rdmols = enumerate_stereoisomers(mol.rdmol)
+        # ring bond stereo is not properly enumerated
+        # cis/trans information is lost if stereochemistry is removed,
+        # which cannot be enumerated by EnumerateStereoisomers() function
+        # so enumerate_ring_bond_stereoisomers() is introduced
+        if len(ring_bond_stereo_info) > 0:
+            ring_cis_trans = []
+            for rdmol in rdmols:
+                ring_cis_trans += enumerate_ring_bond_stereoisomers(rdmol,
+                                                        ring_bond_stereo_info,
+                                                        override=True)
+            if len(ring_cis_trans) > 0:
+                rdmols = ring_cis_trans
+        
+        unique_rdmols = set([Chem.MolToSmiles(rdmol) for rdmol in rdmols])
+        
+        return len(unique_rdmols)
+   
+
     def make_confs(self, n: int = 50, method: str = 'ETKDG', **kwargs) -> Self:
         """Generates 3D conformers.
 

rdworks-0.53.1/src/rdworks/stereoisomers.py

@@ -0,0 +1,67 @@
+from rdkit import Chem
+from rdkit.Chem.EnumerateStereoisomers import EnumerateStereoisomers, StereoEnumerationOptions
+
+
+def enumerate_stereoisomers(rdmol: Chem.Mol) -> list[Chem.Mol]:
+    """Returns enumerated stereoisomers.
+
+    Args:
+        rdmol (Chem.Mol): input molecule.
+
+    Returns:
+        List[Chem.Mol]: a list of enumerated stereoisomers.
+    """
+    return list(EnumerateStereoisomers(
+        rdmol, 
+        options=StereoEnumerationOptions(
+            tryEmbedding=False,
+            onlyUnassigned=True,
+            maxIsomers=1024,
+            rand=None,
+            unique=True,
+            onlyStereoGroups=False,
+            )))
+
+
+def enumerate_ring_bond_stereoisomers(rdmol: Chem.Mol, 
+                                      ring_bond_stereo_info: list[tuple],
+                                      override: bool = False) -> list[Chem.Mol]:
+    """Enumerates unspecified double bond stereochemistry (cis/trans).
+
+    <pre>
+    a1        a4  a1
+      \      /      \
+       a2=a3         a2=a3 
+                          \
+                          a4
+    </pre>
+
+    Args:
+        rdmol (Chem.Mol): input molecule.
+        ring_bond_stereo_info (List[Tuple]): 
+            ring_bond_stereo_info will be set when .remove_stereo() is called.
+            bond_stereo_info = [(bond_idx, bond_stereo_descriptor), ..] where
+            bond_stereo_descriptor is `Chem.StereoDescriptor.Bond_Cis` or
+            `Chem.StereoDescriptor.Bond_Trans`, or `Chem.StereoDescriptor.NoValue`.
+        override (bool, optional): _description_. Defaults to False.
+
+    Returns:
+        List[Chem.Mol]: list of enumerated stereoisomers.
+    """
+    isomers = []
+    for bond_idx, bond_stereo_desc in ring_bond_stereo_info:
+        if (bond_stereo_desc == Chem.StereoDescriptor.NoValue) or override:
+            bond = rdmol.GetBondWithIdx(bond_idx)
+            (a2,a3) = (bond.GetBeginAtom(), bond.GetEndAtom())
+            a2_idx = a2.GetIdx()
+            a3_idx = a3.GetIdx()
+            a1_idx = sorted([(a.GetIdx(), a.GetAtomicNum()) for a in a2.GetNeighbors() if a.GetIdx() != a3_idx], key=lambda x: x[1], reverse=True)[0][0]
+            a4_idx = sorted([(a.GetIdx(), a.GetAtomicNum()) for a in a3.GetNeighbors() if a.GetIdx() != a2_idx], key=lambda x: x[1], reverse=True)[0][0]
+            bond.SetStereoAtoms(a1_idx, a4_idx) # need to set reference atoms
+            # cis
+            bond.SetStereo(Chem.BondStereo.STEREOCIS)
+            isomers.append(Chem.Mol(rdmol))
+            # trans
+            bond.SetStereo(Chem.BondStereo.STEREOTRANS)
+            isomers.append(Chem.Mol(rdmol))
+    return isomers

rdworks-0.53.1/src/rdworks/workflow.py

@@ -0,0 +1,85 @@
+
+from rdworks.stereoisomers import enumerate_stereoisomers, enumerate_ring_bond_stereoisomers
+from rdworks.mol import Mol
+from rdworks.mollibr import MolLibr
+
+from rdkit import Chem
+from rdkit.Chem.MolStandardize import rdMolStandardize
+
+
+def complete_stereoisomers(molecular_input: str | Chem.Mol | Mol, 
+                           name: str | None = None, 
+                           std: bool = False, 
+                           override: bool = False, 
+                           **kwargs) -> MolLibr:
+    """Completes stereoisomers and returns a rdworks.MolLibr.
+
+    Args:
+        molecular_input (Union[Mol, str, Chem.Mol]): input molecule.
+        name (Optional[str], optional): name of the molecule. Defaults to None.
+        std (bool, optional): whether to standardize the input. Defaults to False.
+        override (bool, optional): whether to override input stereoisomers. Defaults to False.
+
+    Raises:
+        TypeError: if `molecular_input` is not rdworks.Mol, SMILES, or rdkit.Chem.Mol object.
+
+    Returns:
+        MolLibr: a library of complete stereoisomers.
+    """
+    if isinstance(molecular_input, Mol):
+        if name:
+            mol = molecular_input.rename(name)
+        else:
+            mol = molecular_input
+    elif isinstance(molecular_input, str) or isinstance(molecular_input, Chem.Mol):
+        mol = Mol(molecular_input, name, std)
+    else:
+        raise TypeError('complete_stereoisomers() expects rdworks.Mol, SMILES or rdkit.Chem.Mol object')
+    
+    ring_bond_stereo_info = mol.get_ring_bond_stereo()
+    
+    if override:
+        mol = mol.remove_stereo()
+    
+    rdmols = enumerate_stereoisomers(mol.rdmol)
+    # ring bond stereo is not properly enumerated
+    # cis/trans information is lost if stereochemistry is removed,
+    # which cannot be enumerated by EnumerateStereoisomers() function
+    # so enumerate_ring_bond_stereoisomers() is introduced
+    if len(ring_bond_stereo_info) > 0:
+        ring_cis_trans = []
+        for rdmol in rdmols:
+            ring_cis_trans += enumerate_ring_bond_stereoisomers(rdmol,
+                                                     ring_bond_stereo_info,
+                                                     override=override)
+        if len(ring_cis_trans) > 0:
+            rdmols = ring_cis_trans
+    
+    if len(rdmols) > 1:
+        libr = MolLibr(rdmols).unique().rename(mol.name, sep='.').compute(**kwargs)
+    else:
+        libr = MolLibr(rdmols).rename(mol.name).compute(**kwargs)
+    
+    for _ in libr:
+        _.props.update(mol.props)
+    
+    return libr
+
+
+
+def complete_tautomers(mol: Mol, **kwargs) -> MolLibr:
+    """Returns a library of enumerated tautomers.
+
+    Args:
+        mol (Mol): input molecule.
+
+    Returns:
+        MolLibr: a library of enumerated tautomers.
+    """
+    enumerator = rdMolStandardize.TautomerEnumerator()
+    rdmols = list(enumerator.Enumerate(mol.rdmol))
+    
+    if len(rdmols) > 1: 
+        return MolLibr(rdmols).unique().rename(mol.name, sep='.').compute(**kwargs)
+    
+    return MolLibr(rdmols).compute(**kwargs)

{rdworks-0.52.1 → rdworks-0.53.1}/src/rdworks.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdworks
-Version: 0.52.1
+Version: 0.53.1
 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-0.52.1 → rdworks-0.53.1}/src/rdworks.egg-info/SOURCES.txt

@@ -16,11 +16,11 @@ src/rdworks/rgroup.py
 src/rdworks/scaffold.py
 src/rdworks/std.py
 src/rdworks/stereoisomers.py
-src/rdworks/tautomers.py
 src/rdworks/testdata.py
 src/rdworks/torsion.py
 src/rdworks/units.py
 src/rdworks/utils.py
+src/rdworks/workflow.py
 src/rdworks/xml.py
 src/rdworks.egg-info/PKG-INFO
 src/rdworks.egg-info/SOURCES.txt

rdworks-0.52.1/src/rdworks/stereoisomers.py

@@ -1,127 +0,0 @@
-from typing import List, Tuple, Union, Optional
-
-from rdkit import Chem
-from rdkit.Chem.EnumerateStereoisomers import EnumerateStereoisomers, StereoEnumerationOptions
-
-from .mol import Mol
-from .mollibr import MolLibr
-
-
-def _enum_stereoisomers(rdmol:Chem.Mol) -> List[Chem.Mol]:
-    """Returns enumerated stereoisomers.
-
-    Args:
-        rdmol (Chem.Mol): input molecule.
-
-    Returns:
-        List[Chem.Mol]: a list of enumerated stereoisomers.
-    """
-    return list(EnumerateStereoisomers(
-        rdmol, 
-        options=StereoEnumerationOptions(
-            tryEmbedding=False,
-            onlyUnassigned=True,
-            maxIsomers=1024,
-            rand=None,
-            unique=True,
-            onlyStereoGroups=False,
-            )))
-
-
-def _enum_ring_bond_stereo(rdmol:Chem.Mol, ring_bond_stereo_info:List[Tuple], 
-                           override:bool=False) -> List[Chem.Mol]:
-    """Enumerates unspecified double bond stereochemistry (cis/trans).
-
-    <pre>
-    a1        a4  a1
-      \      /      \
-       a2=a3         a2=a3 
-                          \
-                          a4
-    </pre>
-
-    Args:
-        rdmol (Chem.Mol): input molecule.
-        ring_bond_stereo_info (List[Tuple]): 
-            ring_bond_stereo_info will be set when .remove_stereo() is called.
-            bond_stereo_info = [(bond_idx, bond_stereo_descriptor), ..] where
-            bond_stereo_descriptor is `Chem.StereoDescriptor.Bond_Cis` or
-            `Chem.StereoDescriptor.Bond_Trans`, or `Chem.StereoDescriptor.NoValue`.
-        override (bool, optional): _description_. Defaults to False.
-
-    Returns:
-        List[Chem.Mol]: list of enumerated stereoisomers.
-    """
-    isomers = []
-    for bond_idx, bond_stereo_desc in ring_bond_stereo_info:
-        if (bond_stereo_desc == Chem.StereoDescriptor.NoValue) or override:
-            bond = rdmol.GetBondWithIdx(bond_idx)
-            (a2,a3) = (bond.GetBeginAtom(), bond.GetEndAtom())
-            a2_idx = a2.GetIdx()
-            a3_idx = a3.GetIdx()
-            a1_idx = sorted([(a.GetIdx(), a.GetAtomicNum()) for a in a2.GetNeighbors() if a.GetIdx() != a3_idx], key=lambda x: x[1], reverse=True)[0][0]
-            a4_idx = sorted([(a.GetIdx(), a.GetAtomicNum()) for a in a3.GetNeighbors() if a.GetIdx() != a2_idx], key=lambda x: x[1], reverse=True)[0][0]
-            bond.SetStereoAtoms(a1_idx, a4_idx) # need to set reference atoms
-            # cis
-            bond.SetStereo(Chem.BondStereo.STEREOCIS)
-            isomers.append(Chem.Mol(rdmol))
-            # trans
-            bond.SetStereo(Chem.BondStereo.STEREOTRANS)
-            isomers.append(Chem.Mol(rdmol))
-    return isomers
-
-
-def complete_stereoisomers(molecular_input:Union[Mol, str, Chem.Mol], name:Optional[str]=None, 
-                           std:bool=False, override:bool=False, **kwargs) -> MolLibr:
-    """Completes stereoisomers and returns a rdworks.MolLibr.
-
-    Args:
-        molecular_input (Union[Mol, str, Chem.Mol]): input molecule.
-        name (Optional[str], optional): name of the molecule. Defaults to None.
-        std (bool, optional): whether to standardize the input. Defaults to False.
-        override (bool, optional): whether to override input stereoisomers. Defaults to False.
-
-    Raises:
-        TypeError: if `molecular_input` is not rdworks.Mol, SMILES, or rdkit.Chem.Mol object.
-
-    Returns:
-        MolLibr: a library of complete stereoisomers.
-    """
-    if isinstance(molecular_input, Mol):
-        if name:
-            mol = molecular_input.rename(name)
-        else:
-            mol = molecular_input
-    elif isinstance(molecular_input, str) or isinstance(molecular_input, Chem.Mol):
-        mol = Mol(molecular_input, name, std)
-    else:
-        raise TypeError('complete_stereoisomers() expects rdworks.Mol, SMILES or rdkit.Chem.Mol object')
-    
-    ring_bond_stereo_info = mol.get_ring_bond_stereo()
-    
-    if override:
-        mol = mol.remove_stereo()
-    
-    rdmols = _enum_stereoisomers(mol.rdmol)
-    # ring bond stereo is not properly enumerated
-    # cis/trans information is lost if stereochemistry is removed,
-    # which cannot be enumerated by EnumerateStereoisomers() function
-    # so _enum_bond_stereo() is introduced
-    if len(ring_bond_stereo_info) > 0:
-        ring_cis_trans = []
-        for rdmol in rdmols:
-            ring_cis_trans += _enum_ring_bond_stereo(rdmol,
-                                                     ring_bond_stereo_info,
-                                                     override=override)
-        if len(ring_cis_trans) > 0:
-            rdmols = ring_cis_trans
-    
-    if len(rdmols) > 1:
-        libr = MolLibr(rdmols).unique().rename(mol.name, sep='.').compute(**kwargs)
-    else:
-        libr = MolLibr(rdmols).rename(mol.name).compute(**kwargs)
-    
-    for _ in libr:
-        _.props.update(mol.props)
-    
-    return libr

rdworks-0.52.1/src/rdworks/tautomers.py

@@ -1,20 +0,0 @@
-from rdkit.Chem.MolStandardize import rdMolStandardize
-
-from .mol import Mol
-from .mollibr import MolLibr
-
-
-def complete_tautomers(mol:Mol, **kwargs) -> MolLibr:
-    """Returns a library of enumerated tautomers.
-
-    Args:
-        mol (Mol): input molecule.
-
-    Returns:
-        MolLibr: a library of enumerated tautomers.
-    """
-    enumerator = rdMolStandardize.TautomerEnumerator()
-    rdmols = list(enumerator.Enumerate(mol.rdmol))
-    if len(rdmols) > 1: 
-        return MolLibr(rdmols).unique().rename(mol.name, sep='.').compute(**kwargs)
-    return MolLibr(rdmols).compute(**kwargs)