rdworks 0.54.2__py3-none-any.whl → 0.56.1__py3-none-any.whl

rdworks/__init__.py

@@ -1,16 +1,15 @@
-__version__ = '0.54.2'
+__version__ = '0.56.1'
 
 from rdworks.conf    import Conf
 from rdworks.mol     import Mol
 from rdworks.mollibr import MolLibr
 
-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 
 from rdworks.std import desalt_smiles, standardize_smiles, standardize
 
+from rdworks.complete import complete_stereoisomers, complete_tautomers
+from rdworks.ionized import IonizedStates
+
 from rdworks.rgroup import expand_rgroup, most_common, most_common_in_NP
 from rdworks.scaffold import scaffold_network, scaffold_tree, BRICS_fragmented, BRICS_fragment_indices
 from rdworks.matchedseries import MatchedSeries

rdworks/{workflow.py → complete.py}

@@ -1,10 +1,8 @@
-
+from rdworks import Mol, MolLibr
 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
+from rdkit.Chem.EnumerateStereoisomers import EnumerateStereoisomers, StereoEnumerationOptions
 
 
 def complete_stereoisomers(molecular_input: str | Chem.Mol | Mol, 
@@ -26,6 +24,8 @@ def complete_stereoisomers(molecular_input: str | Chem.Mol | Mol,
     Returns:
         MolLibr: a library of complete stereoisomers.
     """
+    from rdworks import Mol, MolLibr
+    
     if isinstance(molecular_input, Mol):
         if name:
             mol = molecular_input.rename(name)
@@ -66,6 +66,18 @@ def complete_stereoisomers(molecular_input: str | Chem.Mol | Mol,
     return libr
 
 
+def can_have_stereo(bond):
+    """Check if a double bond can have E/Z stereochemistry"""
+    atom1, atom2 = bond.GetBeginAtom(), bond.GetEndAtom()
+    
+    # Check if both atoms have at least 2 non-hydrogen neighbors
+    for atom in [atom1, atom2]:
+        non_h_neighbors = [n for n in atom.GetNeighbors() if n.GetAtomicNum() != 1]
+        if len(non_h_neighbors) < 2:
+            return False
+    
+    return True
+
 
 def complete_tautomers(mol: Mol, **kwargs) -> MolLibr:
     """Returns a library of enumerated tautomers.
@@ -77,9 +89,30 @@ def complete_tautomers(mol: Mol, **kwargs) -> MolLibr:
         MolLibr: a library of enumerated tautomers.
     """
     enumerator = rdMolStandardize.TautomerEnumerator()
-    rdmols = list(enumerator.Enumerate(mol.rdmol))
+    enumerator.SetRemoveSp3Stereo(False)
+    enumerator.SetRemoveBondStereo(False)  # Don't remove existing stereo
+    tautomers = list(enumerator.Enumerate(mol.rdmol))
+    
+    all_stereoisomers = []
+    
+    for tautomer in tautomers:
+        # Find unspecified double bonds that could have E/Z stereo
+        unspecified_bonds = []
+        for bond in tautomer.GetBonds():
+            if (bond.GetBondType() == Chem.BondType.DOUBLE and 
+                bond.GetStereo() == Chem.BondStereo.STEREONONE and
+                can_have_stereo(bond)):
+                unspecified_bonds.append(bond.GetIdx())
+        
+        if unspecified_bonds:
+            # Enumerate all possible stereoisomers
+            opts = StereoEnumerationOptions(onlyUnassigned=True, maxIsomers=50)
+            stereoisomers = list(EnumerateStereoisomers(tautomer, options=opts))
+            all_stereoisomers.extend(stereoisomers)
+        else:
+            all_stereoisomers.append(tautomer)
     
-    if len(rdmols) > 1: 
-        return MolLibr(rdmols).unique().rename(mol.name, sep='.').compute(**kwargs)
+    if len(all_stereoisomers) > 1: 
+        return MolLibr(all_stereoisomers).unique().rename(mol.name, sep='.').compute(**kwargs)
     
-    return MolLibr(rdmols).compute(**kwargs)
+    return MolLibr(all_stereoisomers).compute(**kwargs)

rdworks/conf.py

@@ -546,9 +546,9 @@ class Conf:
                 conf = frag_conf.copy()
                 conf.set_torsion(*frag_ijkl, angle) # atoms bonded to `l` move.
                 conf = conf.optimize(calculator, fmax, **kwargs)
+                data['angle'].append(angle)
                 # conf.optimize() updates coordinates and conf.props: 
                 #   `E_tot_init(kcal/mol)`, `E_tot(kcal/mol)`, `Converged`.
-                data['angle'].append(angle)
                 data['init'].append(conf.props['E_tot_init(kcal/mol)'])
                 data['last'].append(conf.props['E_tot(kcal/mol)'])
                 data['Converged'].append(conf.props['Converged'])
@@ -562,9 +562,9 @@ class Conf:
                 conf = ref_conf.copy()
                 conf.set_torsion(*indices, angle) # atoms bonded to `l` move.
                 conf = conf.optimize(calculator, fmax, **kwargs)
+                data['angle'].append(angle)
                 # conf.optimize() updates coordinates and conf.props: 
                 #   `E_tot_init(kcal/mol)`, `E_tot(kcal/mol)`, `Converged`.
-                data['angle'].append(conf.props['angle'])
                 data['init'].append(conf.props['E_tot_init(kcal/mol)'])
                 data['last'].append(conf.props['E_tot(kcal/mol)'])
                 data['Converged'].append(conf.props['Converged'])

rdworks/microstates.py

@@ -4,9 +4,16 @@ import itertools
 import logging
 
 from types import SimpleNamespace
+from pathlib import Path
 from rdworks import Conf, Mol
 from rdworks.xtb.wrapper import GFN2xTB
 
+from rdkit import Chem
+from rdkit.Chem import (
+    AllChem, RemoveHs, CanonSmiles, MolFromSmarts,
+    GetFormalCharge, RWMol, AddHs, SanitizeMol, 
+    MolToSmiles, MolFromSmiles,
+    )
 
 logger = logging.getLogger(__name__)
 

{rdworks-0.54.2.dist-info → rdworks-0.56.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdworks
-Version: 0.54.2
+Version: 0.56.1
 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-0.54.2.dist-info → rdworks-0.56.1.dist-info}/RECORD

@@ -1,13 +1,13 @@
-rdworks/__init__.py,sha256=wn52g1WQn_aTo2WLF-sBenvSluTfnH2dgZRIB3cjDVI,1358
-rdworks/conf.py,sha256=eH_a3ywmmJiPtnvgk86ykurYOx879AHg80-Dn8z1X70,36379
+rdworks/__init__.py,sha256=d-zUnWFkFgiYgKXi2hBDA6KX99RDMX4c8RJqrCpQozw,1356
+rdworks/complete.py,sha256=MGNw3O66tPN4I2PIrrjz2ufMako0D1KezvHSNjfpRf8,4642
+rdworks/conf.py,sha256=_4SxHJiaOdK_4KY9adxvQTfzJFudvAQoHRgvejmfyGc,36365
 rdworks/descriptor.py,sha256=34T_dQ6g8v3u-ym8TLKbQtxIIV5TEo-d3pdedq3o-cg,2106
 rdworks/display.py,sha256=JR0gR26UpH-JCxVOaqXZCUj2MiGZSrx9Me87FncspVI,13469
 rdworks/ionized.py,sha256=_t-Ajssv1rytV4Y_KsSbxfnsBKqy-EusbhNUtaWcV6o,7681
 rdworks/matchedseries.py,sha256=A3ON4CUpQV159mu9VqgNiJ8uoQ9ePOry9d3ra4NCAgc,10377
-rdworks/microstates.py,sha256=V1xhMPxAB06_WrB71NEMJjKHI9pPMUuZVswpSmdnSBM,5285
+rdworks/microstates.py,sha256=hf_5UDDgZxJGnrqRiv2fbS1j3zq7LMccHSOJbpEgjX8,5503
 rdworks/mol.py,sha256=4gNjs_ryNNWThMekV794uwjjBE-JLGGWcdyMaS9-xP8,71369
 rdworks/mollibr.py,sha256=X4UBO6Ga-QmNS7RwUiaDYAx0Q5hnWs71yTkEpH02Qb4,37696
-rdworks/pka.py,sha256=NVJVfpcNEMlX5QRyLBgUM7GIT7VMjO-llAR4LWc8J2c,1656
 rdworks/readin.py,sha256=b1BHchQMC5EgQd3C05n72t_aa_9u0iKQWyyIqjyfkPc,11809
 rdworks/rgroup.py,sha256=ivF2gzmRtt339rxEnkv2KfnCs0CUdBbnSje7Y54rtFI,57996
 rdworks/scaffold.py,sha256=60T5YacyxZsEpDo_J5Qxulm2YNQO4EQR8PcNUwjn1QU,22026
@@ -17,7 +17,6 @@ rdworks/testdata.py,sha256=TmbNPA-ju6nTBt_Yts4EJUFmL9Cd6DCVXrDF42QLlHw,1732
 rdworks/torsion.py,sha256=UUaYOvNS89SlLFauYiAboUqysy32EN0_Gktc4xxuDQI,18788
 rdworks/units.py,sha256=nljKPHcr6IWoAp0CkL7y1gSNDd6a07NeVfxXwSMuHQM,365
 rdworks/utils.py,sha256=d2Sio8WTlGPsmBOHIYDCMWg_7X4rTWjJQAqzd7ywo2A,14191
-rdworks/workflow.py,sha256=MtP9QUGgCKMyI3G4vp8sokos_UyaQvTHFOEPUJresZU,3139
 rdworks/xml.py,sha256=aaMhwVRGvt1VzasaKDnkYnZ4kp2cIgvGb1CsmMgwQ_c,10704
 rdworks/autograph/__init__.py,sha256=0Qfjwo0h4Q0n08zsqHRbuNOZms6MuNXnWErnQpQ6Px0,140
 rdworks/autograph/autograph.py,sha256=frjsUaCTOD-Z1lYPzOxRoTtqMMiYroWAy6tSwKn3CUA,8769
@@ -67,8 +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=YpZY8SJ9Lrp3I3_GAVawSb_4_Zc8hcJtF5l7-I-Wbys,22048
-rdworks-0.54.2.dist-info/licenses/LICENSE,sha256=UOkJSBqYyQUvtCp7a-vdCANeEcLE2dnTie_eB1By5SY,1074
-rdworks-0.54.2.dist-info/METADATA,sha256=qwcHC-qMQQQwes5UKUJtbwpFRUr9aEr5wdBuCJ5HWOQ,1967
-rdworks-0.54.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rdworks-0.54.2.dist-info/top_level.txt,sha256=05C98HbvBK2axUBogC_hAT_CdpOeQYGnQ6vRAgawr8s,8
-rdworks-0.54.2.dist-info/RECORD,,
+rdworks-0.56.1.dist-info/licenses/LICENSE,sha256=UOkJSBqYyQUvtCp7a-vdCANeEcLE2dnTie_eB1By5SY,1074
+rdworks-0.56.1.dist-info/METADATA,sha256=4jemVgYRM_UDuGjLUOK8vbboQZiqctnx-rrZgnvAg5k,1967
+rdworks-0.56.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rdworks-0.56.1.dist-info/top_level.txt,sha256=05C98HbvBK2axUBogC_hAT_CdpOeQYGnQ6vRAgawr8s,8
+rdworks-0.56.1.dist-info/RECORD,,

rdworks/pka.py

@@ -1,38 +0,0 @@
-"""This module is an implementation in progress of the decision tree method for pKa prediction.
-
-Crippen, J. Chem. Inf. Model., Vol. 48, No. 10, 2008, 2042-2053.
-
-The SMARTS patterns and pKa values were taken from the supporting information of the paper.
-These "MOE SMARTS" were converted to generic SMARTS which relied on use of some recursive SMARTS patterns.  
-The first data row then describes nodes 1, and then the tree expands out based on decisions of SMARTS-matching:
-    if node 2 is yes to pattern [#8,#16,#34,#52,#84;H]C(=O) - giving pKa 3.68 and range 5.96
-    node 3 is no to the same pattern - giving pKa 7.21 and range 17.32
-Then nodes 4,5 are under 2 and 6,7 are under 3, etc, etc until the leaf nodes are reached
-"""
-
-
-import importlib.resources
-from collections import namedtuple
-from typing import Union
-
-from rdkit import Chem
-from rdkit.Chem import AllChem
-
-datadir = importlib.resources.files('rdworks.predefined')
-DecisionTreeNode = namedtuple('DecisionTree', ('node', 'parent', 'child', 'FP', 'SMARTS', 'YN', 'pKa', 'pKa_range'))
-decision_tree = []
-with open(datadir / "pKa_decision_tree.ext", "r") as f: 
-    for line in f:
-        if (not line) or line.startswith('#'):
-            continue
-        decision_tree.append(DecisionTreeNode(line.strip().split()))
-        
-
-def decision_tree_pKa(rdmol:Chem.Mol) -> Union[float, None]:
-    pKa = None
-    for _ in decision_tree:
-        patt = Chem.MolFromSmarts(_.SMARTS) # make an RDKit query molecule
-        match = rdmol.HasSubstructMatch(patt) # check if we have a match for our test molecule
-        # pKa = float(values[6])
-        # pKa_range = float(values[7])
-    return pKa