rdworks 0.25.7__py3-none-any.whl

rdworks/stereoisomers.py

@@ -0,0 +1,127 @@
+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/tautomers.py

@@ -0,0 +1,20 @@
+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)

rdworks/units.py

@@ -0,0 +1,63 @@
+from types import SimpleNamespace
+
+# In ASE, the default energy unit is eV (electron volt).
+# It will be converted to kcal/mol
+#CODATA 2018 energy conversion factor
+hartree2ev = 27.211386245988
+hartree2kcalpermol = 627.50947337481
+ev2kcalpermol = 23.060547830619026
+
+periodictable = SimpleNamespace(
+    symbol = {
+        1: 'H', 2: 'He', 3: 'Li', 4: 'Be', 5: 'B', 6: 'C', 7: 'N', 8: 'O', 9: 'F', 10: 'Ne', 
+        11: 'Na', 12: 'Mg', 13: 'Al', 14: 'Si', 15: 'P', 16: 'S', 17: 'Cl', 18: 'Ar', 19: 'K', 20: 'Ca', 
+        21: 'Sc', 22: 'Ti', 23: 'V', 24: 'Cr', 25: 'Mn', 26: 'Fe', 27: 'Co', 28: 'Ni', 29: 'Cu', 30: 'Zn', 
+        31: 'Ga', 32: 'Ge', 33: 'As', 34: 'Se', 35: 'Br', 36: 'Kr', 37: 'Rb', 38: 'Sr', 39: 'Y', 40: 'Zr', 
+        41: 'Nb', 42: 'Mo', 43: 'Tc', 44: 'Ru', 45: 'Rh', 46: 'Pd', 47: 'Ag', 48: 'Cd', 49: 'In', 50: 'Sn', 
+        51: 'Sb', 52: 'Te', 53: 'I', 54: 'Xe', 55: 'Cs', 56: 'Ba', 57: 'La', 58: 'Ce', 59: 'Pr', 60: 'Nd', 
+        61: 'Pm', 62: 'Sm', 63: 'Eu', 64: 'Gd', 65: 'Tb', 66: 'Dy', 67: 'Ho', 68: 'Er', 69: 'Tm', 70: 'Yb', 
+        71: 'Lu', 72: 'Hf', 73: 'Ta', 74: 'W', 75: 'Re', 76: 'Os', 77: 'Ir', 78: 'Pt', 79: 'Au', 80: 'Hg', 
+        81: 'Tl', 82: 'Pb', 83: 'Bi', 84: 'Po', 85: 'At', 86: 'Rn', 87: 'Fr', 88: 'Ra', 89: 'Ac', 90: 'Th', 
+        91: 'Pa', 92: 'U', 93: 'Np', 94: 'Pu', 95: 'Am', 96: 'Cm', 97: 'Bk', 98: 'Cf', 99: 'Es', 100: 'Fm', 
+        101: 'Md', 102: 'No', 103: 'Lr', 104: 'Rf', 105: 'Db', 106: 'Sg', 107: 'Bh', 108: 'Hs', 109: 'Mt', 110: 'Ds', 
+        111: 'Rg', 112: 'Cn', 113: 'Nh', 114: 'Fl', 115: 'Mc', 116: 'Lv', 117: 'Ts', 118: 'Og'
+        },
+    long_symbol = {
+        1: 'Hydrogen', 2: 'Helium', 3: 'Lithium', 4: 'Beryllium', 5: 'Boron', 
+        6: 'Carbon', 7: 'Nitrogen', 8: 'Oxygen', 9: 'Fluorine', 10: 'Neon', 
+        11: 'Sodium', 12: 'Magnesium', 13: 'Aluminum', 14: 'Silicon', 15: 'Phosphorus', 
+        16: 'Sulfur', 17: 'Chlorine', 18: 'Argon', 19: 'Potassium', 20: 'Calcium', 
+        21: 'Scandium', 22: 'Titanium', 23: 'Vanadium', 24: 'Chromium', 25: 'Manganese', 
+        26: 'Iron', 27: 'Cobalt', 28: 'Nickel', 29: 'Copper', 30: 'Zinc', 
+        31: 'Gallium', 32: 'Germanium', 33: 'Arsenic', 34: 'Selenium', 35: 'Bromine', 
+        36: 'Krypton', 37: 'Rubidium', 38: 'Strontium', 39: 'Yttrium', 40: 'Zirconium', 
+        41: 'Niobium', 42: 'Molybdenum', 43: 'Technetium', 44: 'Ruthenium', 45: 'Rhodium', 
+        46: 'Palladium', 47: 'Silver', 48: 'Cadmium', 49: 'Indium', 50: 'Tin', 
+        51: 'Antimony', 52: 'Tellurium', 53: 'Iodine', 54: 'Xenon', 55: 'Cesium', 
+        56: 'Barium', 57: 'Lanthanum', 58: 'Cerium', 59: 'Praseodymium', 60: 'Neodymium', 
+        61: 'Promethium', 62: 'Samarium', 63: 'Europium', 64: 'Gadolinium', 65: 'Terbium', 
+        66: 'Dysprosium', 67: 'Holmium', 68: 'Erbium', 69: 'Thulium', 70: 'Ytterbium', 
+        71: 'Lutetium', 72: 'Hafnium', 73: 'Tantalum', 74: 'Tungsten', 75: 'Rhenium', 
+        76: 'Osmium', 77: 'Iridium', 78: 'Platinum', 79: 'Gold', 80: 'Mercury', 
+        81: 'Thallium', 82: 'Lead', 83: 'Bismuth', 84: 'Polonium', 85: 'Astatine', 
+        86: 'Radon', 87: 'Francium', 88: 'Radium', 89: 'Actinium', 90: 'Thorium', 
+        91: 'Protactinium', 92: 'Uranium', 93: 'Neptunium', 94: 'Plutonium', 95: 'Americium', 
+        96: 'Curium', 97: 'Berkelium', 98: 'Californium', 99: 'Einsteinium', 100: 'Fermium', 
+        101: 'Mendelevium', 102: 'Nobelium', 103: 'Lawrencium', 104: 'Rutherfordium', 105: 'Dubnium', 
+        106: 'Seaborgium', 107: 'Bohrium', 108: 'Hassium', 109: 'Meitnerium', 110: 'Darmstadtium', 
+        111: 'Roentgenium', 112: 'Copernicium', 113: 'Nihonium', 114: 'Flerovium', 115: 'Moscovium', 
+        116: 'Livermorium', 117: 'Tennessine', 118: 'Oganesson'
+        },
+    )
+
+
+# Initialize UFF bond radii (Rappe et al. JACS 1992)
+# Units of angstroms 
+# These radii neglect the bond-order and electronegativity corrections in the original paper. 
+# Where several values exist for the same atom, the largest was used. 
+radii = { 
+    1:0.354,  5:0.838,  6:0.757,  7:0.700,  8:0.658,  9:0.668,
+    14:1.117, 15:1.117, 16:1.064, 17:1.044,
+    32:1.197, 33:1.211, 34:1.190, 35:1.192,
+    51:1.407, 52:1.386, 53:1.382,
+    }