def test_monomer_importer(json_importer, independent_importers):
monomer_importer = importers.MonomerImporter(json_importer)
ids = monomer_importer.import_data()
monomer_repo = repo.create_monomer_repository()
backbone_repo = repo.create_backbone_repository()
monomer_data = list(monomer_repo.load(ids))
monomer_docs = json_importer.load(monomer_importer.saver.TYPE.STRING)
backbone_data = list(backbone_repo.load())
kekules = [doc['kekule'] for doc in monomer_docs]
backbones = [mol.to_reduced_dict() for mol in backbone_data]
assert(len(monomer_data) == 4)
for mol in monomer_data:
rdkit_mol = mol.mol
assert(mol._id != None)
assert(mol.required == bool(AllChem.CalcNumAromaticRings(rdkit_mol)))
assert(mol.backbone in backbones)
assert(mol.sidechain is None)
assert(mol.connection is None)
assert(mol.proline == bool(AllChem.CalcNumAliphaticRings(
rdkit_mol) and rdkit_mol.HasSubstructMatch(PROLINE_N_TERM)))
assert(mol.imported == True)
assert(mol.kekule in kekules)
kekules.remove(mol.kekule)
def featurize(aa):
mol = Chem.MolFromFASTA(aa)
mol = Chem.AddHs(mol)
descriptors = {
'MolWT': AllChem.CalcExactMolWt(mol),
'LogP': Chem.Crippen.MolLogP(mol),
'HBondDonors': AllChem.CalcNumLipinskiHBD(mol),
'HBondAcceptors': AllChem.CalcNumLipinskiHBA(mol),
'nAromaticRings': AllChem.CalcNumAromaticRings(mol),
'nHeteroAtoms': AllChem.CalcNumHeteroatoms(mol),
'nRotatableBonds': AllChem.CalcNumRotatableBonds(mol)
}
def PhyChem(smiles):
""" Calculating the 19D physicochemical descriptors for each molecules,
the value has been normalized with Gaussian distribution.
Arguments:
smiles (list): list of SMILES strings.
Returns:
props (ndarray): m X 19 matrix as normalized PhysChem descriptors.
m is the No. of samples
"""
props = []
for smile in smiles:
mol = Chem.MolFromSmiles(smile)
try:
MW = desc.MolWt(mol)
LOGP = Crippen.MolLogP(mol)
HBA = Lipinski.NumHAcceptors(mol)
HBD = Lipinski.NumHDonors(mol)
rotable = Lipinski.NumRotatableBonds(mol)
amide = AllChem.CalcNumAmideBonds(mol)
bridge = AllChem.CalcNumBridgeheadAtoms(mol)
heteroA = Lipinski.NumHeteroatoms(mol)
heavy = Lipinski.HeavyAtomCount(mol)
spiro = AllChem.CalcNumSpiroAtoms(mol)
FCSP3 = AllChem.CalcFractionCSP3(mol)
ring = Lipinski.RingCount(mol)
Aliphatic = AllChem.CalcNumAliphaticRings(mol)
aromatic = AllChem.CalcNumAromaticRings(mol)
saturated = AllChem.CalcNumSaturatedRings(mol)
heteroR = AllChem.CalcNumHeterocycles(mol)
TPSA = MolSurf.TPSA(mol)
valence = desc.NumValenceElectrons(mol)
mr = Crippen.MolMR(mol)
# charge = AllChem.ComputeGasteigerCharges(mol)
prop = [
MW, LOGP, HBA, HBD, rotable, amide, bridge, heteroA, heavy,
spiro, FCSP3, ring, Aliphatic, aromatic, saturated, heteroR,
TPSA, valence, mr
]
except Exception:
print(smile)
prop = [0] * 19
props.append(prop)
props = np.array(props)
props = Scaler().fit_transform(props)
return props
def is_required(monomer):
return bool(
AllChem.CalcNumAromaticRings(Chem.MolFromSmiles(monomer['kekule'])))
def is_required(mol):
return bool(AllChem.CalcNumAromaticRings(mol))
