rdworks 0.53.1__tar.gz → 0.55.1__tar.gz

{rdworks-0.53.1 → rdworks-0.55.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdworks
-Version: 0.53.1
+Version: 0.55.1
 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-0.53.1 → rdworks-0.55.1}/src/rdworks/__init__.py

@@ -1,16 +1,15 @@
-__version__ = '0.53.1'
+__version__ = '0.55.1'
 
 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-0.53.1/src/rdworks/workflow.py → rdworks-0.55.1/src/rdworks/complete.py

@@ -1,8 +1,5 @@
-
+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
 
@@ -26,6 +23,8 @@ 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)

{rdworks-0.53.1 → rdworks-0.55.1}/src/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-0.53.1 → rdworks-0.55.1}/src/rdworks/microstates.py

@@ -1,11 +1,22 @@
 import numpy as np
 import math
 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__)
+
 
 kT = 0.001987 * 298.0 # (kcal/mol K), standard condition
 C = math.log(10) * kT
@@ -23,9 +34,10 @@ class Microstates():
         self.mols = []
         self.reference = None
     
-        # read QupKake results
+
+    def enumerate(self) -> None:
+        # Qu pKake results must be stored at .confs
         for conf in self.origin:
-            print(conf.props)
             pka = conf.props.get('pka', None)
             if pka is None:
                 # no protonation/deprotonation sites
@@ -49,7 +61,7 @@ class Microstates():
         
         for (p, d) in PD:
             conf = self.origin.confs[0].copy()
-            conf = conf.protonate(p).deprotonate(d).optimize(calculator=calculator)
+            conf = conf.protonate(p).deprotonate(d).optimize(calculator=self.calculator)
             charge = len(p) - len(d)
             self.states.append(SimpleNamespace(
                 charge=charge, 
@@ -83,7 +95,7 @@ class Microstates():
         return float(np.dot(p, pe_array))
 
 
-    def potential_energy(self) -> None:
+    def populate(self) -> None:
         for microstate in self.states:
             mol = Mol(microstate.conf).make_confs(n=4).optimize_confs()
             # mol = mol.drop_confs(similar=True, similar_rmsd=0.3, verbose=True)
@@ -94,23 +106,21 @@ class Microstates():
                 conf = conf.optimize(calculator=self.calculator, verbose=True)
                 # GFN2xTB requires 3D coordinates
                 # xtb = GFN2xTB(conf.rdmol).singlepoint(water='cpcmx', verbose=True)
-                xtb = GFN2xTB(conf.rdmol).singlepoint(verbose=True)
-                PE.append(xtb.PE)
+                PE.append(conf.potential_energy(calculator=self.calculator))
+                # xtb = GFN2xTB(conf.rdmol).singlepoint(verbose=True)
                 # SimpleNamespace(
                 #             PE = datadict['total energy'] * hartree2kcalpermol,
                 #             Gsolv = Gsolv,
                 #             charges = datadict['partial charges'],
                 #             wbo = Wiberg_bond_orders,
                 #             )
-            print("PE=", PE)
             microstate.PE = self.Boltzmann_weighted_average(PE)
-            print("Boltzmann weighted=", microstate.PE)
-            
+            logger.info(f"PE= {PE}")
+            logger.info(f"Boltzmann weighted= {microstate.PE}")            
             self.mols.append(mol)
-            print("microstate.energy", microstate)
 
 
-    def populations(self, pH: float) -> list[tuple]:
+    def get_populations(self, pH: float) -> list[tuple]:
         # set the lowest dG as the reference
         self.reference = self.states[np.argmin([microstate.PE for microstate in self.states])]
         for microstate in self.states:
@@ -120,7 +130,7 @@ class Microstates():
             dG.append((microstate.PE - self.reference.PE) + microstate.delta_m * C * pH)
         dG = np.array(dG)
 
-        print("dG=", dG)
+        logger.info(f"dG= {dG}")
         Boltzmann_factors = np.exp(-dG/kT)
         Z = np.sum(Boltzmann_factors)
         p = Boltzmann_factors/Z
@@ -128,11 +138,16 @@ class Microstates():
         # [(0, p0), (1, p1), ...]
 
         return idx_p
+
+
+    def get_ensemble(self) -> list[Mol]:
+        return self.mols
+
+
+    def get_mol(self, idx: int) -> Mol:
+        return self.mols[idx]
     
 
     def count(self) -> int:
         return len(self.states)
     
-
-    def get_mol(self, idx: int) -> Mol:
-        return self.mols[idx]

{rdworks-0.53.1 → rdworks-0.55.1}/src/rdworks/xtb/wrapper.py

@@ -79,7 +79,8 @@ class GFN2xTB:
                 proc = subprocess.run(['xtb', test_geometry, '--opt'],
                                       cwd=temp_dir,
                                       capture_output=True, 
-                                      text=True)
+                                      text=True,
+                                      encoding='utf-8')
                 assert proc.returncode == 0
 
             return True
@@ -122,7 +123,7 @@ $ cp -r xtb-dist/share      /usr/local/ """)
         if GFN2xTB.is_xtb_ready():
             with tempfile.TemporaryDirectory() as temp_dir: # tmpdir is a string
                 cmd = ['xtb', '--cpcmx']
-                proc = subprocess.run(cmd, cwd=temp_dir, capture_output=True, text=True)
+                proc = subprocess.run(cmd, cwd=temp_dir, capture_output=True, text=True, encoding='utf-8')
                 # we are expecting an error because no input file is given
                 assert proc.returncode != 0
                 for line in proc.stdout.split('\n'):
@@ -156,7 +157,7 @@ $ cp -r xtb-dist/share      /usr/local/ """)
         if GFN2xTB.is_xtb_ready():
             with tempfile.TemporaryDirectory() as temp_dir: # tmpdir is a string
                 cmd = ['xtb', '--version']
-                proc = subprocess.run(cmd, cwd=temp_dir, capture_output=True, text=True)
+                proc = subprocess.run(cmd, cwd=temp_dir, capture_output=True, text=True, encoding='utf-8')
                 assert proc.returncode == 0, "GFN2xTB() Error: xtb not available"
                 match = re.search('xtb\s+version\s+(?P<version>[\d.]+)', proc.stdout)
                 if match:
@@ -358,7 +359,7 @@ $ cp -r xtb-dist/share      /usr/local/ """)
 
             # 'xtbout.json', 'xtbrestart', 'xtbtopo.mol', 'charges', and 'wbo' files will be 
             # created in the current working directory.
-            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True)
+            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True, encoding='utf-8')
             # if proc.returncode == 0:
             #     print("Standard Output:")
             #     print(proc.stdout)
@@ -461,7 +462,7 @@ $ cp -r xtb-dist/share      /usr/local/ """)
             if verbose:
                 logger.info(f"optimize() {' '.join(cmd+options)}")
 
-            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True)
+            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True, encoding='utf-8')
 
             if proc.returncode == 0 and xtbout_path.is_file():
                 with open(xtbout_path, 'r') as f:
@@ -527,7 +528,7 @@ $ cp -r xtb-dist/share      /usr/local/ """)
                 elif water == 'alpb':
                     options += ['--alpb', 'water']
 
-            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True)
+            proc = subprocess.run(cmd + options, cwd=temp_dir, capture_output=True, text=True, encoding='utf-8')
             # output files: xtb_esp.cosmo, xtb_esp.dat, xtb_esp_profile.dat
 
             if proc.returncode == 0 and xtb_esp_dat.is_file():

{rdworks-0.53.1 → rdworks-0.55.1}/src/rdworks.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdworks
-Version: 0.53.1
+Version: 0.55.1
 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-0.53.1 → rdworks-0.55.1}/src/rdworks.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ LICENSE
 README.md
 pyproject.toml
 src/rdworks/__init__.py
+src/rdworks/complete.py
 src/rdworks/conf.py
 src/rdworks/descriptor.py
 src/rdworks/display.py
@@ -10,7 +11,6 @@ src/rdworks/matchedseries.py
 src/rdworks/microstates.py
 src/rdworks/mol.py
 src/rdworks/mollibr.py
-src/rdworks/pka.py
 src/rdworks/readin.py
 src/rdworks/rgroup.py
 src/rdworks/scaffold.py
@@ -20,7 +20,6 @@ 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-0.53.1 → rdworks-0.55.1}/tests/test_basics.py

@@ -400,7 +400,19 @@ def test_complete_stereoisomers():
     for mol in MolLibr(drug_smiles, drug_names):
         isomer_libr += rdworks.complete_stereoisomers(mol)
     assert isomer_libr.count() >= 25
-   
+
+
+def test_count_stereoisomers():
+    """count all possible stereoisomers ignoring current stereochemistry assignment"""
+    m = Mol('Cc1nc2c(-c3ccc(Cl)cc3F)nc(N3CCN(C(=O)C(F)F)CC3)cn2c(=O)c1C')
+    assert m.count_stereoisomers() == 1
+    m = Mol('CN1C=C([C@H]2CN(C3=NC(C4=CC=C(Cl)C=C4F)=C4N=C5CCCCN5C(=O)C4=C3)CCO2)C=N1')
+    assert m.count_stereoisomers() == 2
+    m = Mol('Cc1nc2c(-c3ccc(Cl)cc3F)nc(N3CCN(S(=O)(=O)N4C[C@@H](C)O[C@@H](C)C4)CC3)cn2c(=O)c1C')
+    assert m.count_stereoisomers() == 3
+    m = Mol('Cc1cc([C@H]2CN(c3cc4nc(C)c(C)c(=O)n4c(-c4ccc(Cl)cc4F)n3)C[C@@H](C)O2)ccn1')
+    assert m.count_stereoisomers() == 4
+
 
 def test_cluster():
     libr = rdworks.read_smi(datadir / "cdk2.smi.gz", progress=False)

{rdworks-0.53.1 → rdworks-0.55.1}/tests/test_ionized.py

@@ -36,31 +36,31 @@ def test_ionizedstate():
     assert set(expected).intersection(set(results)) == set(expected)
 
 
-def test_gypsum_dl():
-    import gypsum_dl
-    smiles = 'O=C(NCCCC)[C@H](CCC1)N1[C@@H](CC)C2=NN=C(CC3=CC=C(C)C=C3)O2'
-    state_smiles = list(
-        gypsum_dl.GypsumDL(smiles,
-            min_ph=6.4,
-            max_ph=8.4,
-            pka_precision=1.0,
-            thoroughness=3,
-            max_variants_per_compound=5,
-            second_embed=False,
-            skip_optimize_geometry=False,
-            skip_alternate_ring_conformations=False,
-            skip_adding_hydrogen=False,
-            skip_making_tautomers=False,
-            skip_enumerate_chiral_mol=False,
-            skip_enumerate_double_bonds=False,
-            let_tautomers_change_chirality=False,
-            use_durrant_lab_filters=True,
-            job_manager='serial',
-            num_processors=1,
-            ))
-    for smi in state_smiles:
-        print(smi)
+# def test_gypsum_dl():
+#     import gypsum_dl
+#     smiles = 'O=C(NCCCC)[C@H](CCC1)N1[C@@H](CC)C2=NN=C(CC3=CC=C(C)C=C3)O2'
+#     state_smiles = list(
+#         gypsum_dl.GypsumDL(smiles,
+#             min_ph=6.4,
+#             max_ph=8.4,
+#             pka_precision=1.0,
+#             thoroughness=3,
+#             max_variants_per_compound=5,
+#             second_embed=False,
+#             skip_optimize_geometry=False,
+#             skip_alternate_ring_conformations=False,
+#             skip_adding_hydrogen=False,
+#             skip_making_tautomers=False,
+#             skip_enumerate_chiral_mol=False,
+#             skip_enumerate_double_bonds=False,
+#             let_tautomers_change_chirality=False,
+#             use_durrant_lab_filters=True,
+#             job_manager='serial',
+#             num_processors=1,
+#             ))
+#     for smi in state_smiles:
+#         print(smi)
     
 if __name__ == '__main__':
     test_ionizedstate()
-    test_gypsum_dl()
+    # test_gypsum_dl()

rdworks-0.53.1/src/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