coprinet/pricePrediction/preprocessData/smilesToDescriptors.py

import torch
import numpy as np
from rdkit import Chem
from rdkit.Chem import rdMolDescriptors
from rdkit.Chem.Descriptors import ExactMolWt
from rdkit.ML.Descriptors.CompoundDescriptors import GetAllDescriptorNames
from torch_geometric.data import Data as GraphData
from rdkit.ML.Descriptors.MoleculeDescriptors import MolecularDescriptorCalculator




calculator = {}
def smiles_to_graph(smi):
    mol = Chem.MolFromSmiles(smi)
    if mol is None:
        return None
    if not calculator:
        chosen_descriptors = ['BertzCT',
 'Chi0',
 'Chi0n',
 'Chi0v',
 'Chi1',
 'Chi1n',
 'Chi1v',
 'Chi2n',
 'Chi2v',
 'Chi3n',
 'Chi3v',
 'Chi4n',
 'Chi4v',
 'EState_VSA1',
 'EState_VSA10',
 'EState_VSA11',
 'EState_VSA2',
 'EState_VSA3',
 'EState_VSA4',
 'EState_VSA5',
 'EState_VSA6',
 'EState_VSA7',
 'EState_VSA8',
 'EState_VSA9',
 'ExactMolWt',
 'FpDensityMorgan1',
 'FpDensityMorgan2',
 'FpDensityMorgan3',
 'FractionCSP3',
 'HallKierAlpha',
 'HeavyAtomCount',
 'HeavyAtomMolWt',
 'Kappa1',
 'Kappa2',
 'Kappa3',
 'LabuteASA',
 'MaxAbsEStateIndex',
 'MaxEStateIndex',
 'MinAbsEStateIndex',
 'MinAbsPartialCharge',
 'MinEStateIndex',
 'MinPartialCharge',
 'MolLogP',
 'MolMR',
 'MolWt',
 'NHOHCount',
 'NOCount',
 'NumAliphaticCarbocycles',
 'NumAliphaticHeterocycles',
 'NumAliphaticRings',
 'NumAromaticCarbocycles',
 'NumAromaticHeterocycles',
 'NumAromaticRings',
 'NumHAcceptors',
 'NumHDonors',
 'NumHeteroatoms',
 'NumRotatableBonds',
 'NumSaturatedCarbocycles',
 'NumSaturatedHeterocycles',
 'NumSaturatedRings',
 'NumValenceElectrons',
 'PEOE_VSA1',
 'PEOE_VSA10',
 'PEOE_VSA11',
 'PEOE_VSA12',
 'PEOE_VSA13',
 'PEOE_VSA14',
 'PEOE_VSA2',
 'PEOE_VSA3',
 'PEOE_VSA4',
 'PEOE_VSA5',
 'PEOE_VSA6',
 'PEOE_VSA7',
 'PEOE_VSA8',
 'PEOE_VSA9',
 'RingCount',
 'SMR_VSA1',
 'SMR_VSA10',
 'SMR_VSA2',
 'SMR_VSA3',
 'SMR_VSA4',
 'SMR_VSA5',
 'SMR_VSA6',
 'SMR_VSA7',
 'SMR_VSA9',
 'SlogP_VSA1',
 'SlogP_VSA10',
 'SlogP_VSA11',
 'SlogP_VSA12',
 'SlogP_VSA2',
 'SlogP_VSA3',
 'SlogP_VSA4',
 'SlogP_VSA5',
 'SlogP_VSA6',
 'SlogP_VSA7',
 'SlogP_VSA8',
 'TPSA',
 'VSA_EState1',
 'VSA_EState10',
 'VSA_EState2',
 'VSA_EState3',
 'VSA_EState4',
 'VSA_EState5',
 'VSA_EState6',
 'VSA_EState7',
 'VSA_EState8',
 'VSA_EState9',
 'fr_Al_COO',
 'fr_Al_OH',
 'fr_Al_OH_noTert',
 'fr_ArN',
 'fr_Ar_COO',
 'fr_Ar_N',
 'fr_Ar_NH',
 'fr_Ar_OH',
 'fr_COO',
 'fr_COO2',
 'fr_C_O',
 'fr_C_O_noCOO',
 'fr_C_S',
 'fr_HOCCN',
 'fr_Imine',
 'fr_NH0',
 'fr_NH1',
 'fr_NH2',
 'fr_N_O',
 'fr_Ndealkylation1',
 'fr_Ndealkylation2',
 'fr_Nhpyrrole',
 'fr_SH',
 'fr_aldehyde',
 'fr_alkyl_carbamate',
 'fr_alkyl_halide',
 'fr_allylic_oxid',
 'fr_amide',
 'fr_amidine',
 'fr_aniline',
 'fr_aryl_methyl',
 'fr_azide',
 'fr_azo',
 'fr_barbitur',
 'fr_benzene',
 'fr_benzodiazepine',
 'fr_bicyclic',
 'fr_dihydropyridine',
 'fr_epoxide',
 'fr_ester',
 'fr_ether',
 'fr_furan',
 'fr_guanido',
 'fr_halogen',
 'fr_hdrzine',
 'fr_hdrzone',
 'fr_imidazole',
 'fr_imide',
 'fr_isothiocyan',
 'fr_ketone',
 'fr_ketone_Topliss',
 'fr_lactam',
 'fr_lactone',
 'fr_methoxy',
 'fr_morpholine',
 'fr_nitrile',
 'fr_nitro',
 'fr_nitro_arom',
 'fr_nitro_arom_nonortho',
 'fr_nitroso',
 'fr_oxazole',
 'fr_oxime',
 'fr_para_hydroxylation',
 'fr_phenol',
 'fr_phenol_noOrthoHbond',
 'fr_phos_acid',
 'fr_phos_ester',
 'fr_piperdine',
 'fr_piperzine',
 'fr_priamide',
 'fr_pyridine',
 'fr_quatN',
 'fr_sulfide',
 'fr_sulfonamd',
 'fr_sulfone',
 'fr_term_acetylene',
 'fr_tetrazole',
 'fr_thiazole',
 'fr_thiocyan',
 'fr_thiophene',
 'fr_unbrch_alkane',
 'fr_urea',
 'qed']

        calculator["calculator"] = MolecularDescriptorCalculator(chosen_descriptors)

    x = np.array(calculator["calculator"].CalcDescriptors(mol))
    x = x.reshape((1,-1))
    x = torch.FloatTensor(x)
    if torch.isnan(x).any():
        return None
    graph = GraphData(x=x, edge_index=torch.zeros(2,0, dtype=torch.long), edge_attr=torch.zeros(0,1))
    return graph

def test(smi = "C1=CC=C(C=C1)CC(C(=O)O)N"):

    mol = Chem.MolFromSmiles(smi)
    # print(mol)
    graph = smiles_to_graph(smi)
    print(graph.keys)
    print(graph.x)
    print(graph.edge_index)
    print( graph.edge_attr )
    print( graph.x.shape, graph.edge_index.shape, graph.edge_attr.shape)
    print(graph.x.max(), graph.x.min())
    for idx in range(mol.GetNumAtoms()):
        mol.GetAtomWithIdx(idx).SetProp('molAtomMapNumber', str(mol.GetAtomWithIdx(idx).GetIdx()))
    from matplotlib import pyplot as plt; from rdkit.Chem import Draw; plt.imshow(Draw.MolsToGridImage([mol], molsPerRow=2)); plt.show()


if __name__ == "__main__":
    smis_list = ["[C@H](C)1CCCO1", "O[C@@H](N)C", "C1=CC=C(C=C1)CC(C(=O)O)N"]
    for smi in smis_list:
        test(smi)