def fp_tt_std_mp(mol, mol_can, i, nBits, chiral):
fp_mol = Torsions.GetHashedTopologicalTorsionFingerprint(mol, nBits=nBits, includeChirality=chiral)
if id(mol) == id(mol_can):
fp_can = fp_mol
else:
fp_can = Torsions.GetHashedTopologicalTorsionFingerprint(mol_can, nBits=nBits, includeChirality=chiral)
return (i, fp_mol, fp_can)
def score_model(self, model_configuration: dict, fragments_file: str,
descriptors_file: str, output_file: str):
inputoutput_utils.create_parent_directory(output_file)
model_data = model_configuration["data"]
active_molecules_tt = []
nbits = model_configuration["configuration"]["nbits"]
for active_molecule in model_data["active"]:
molecule_smiles = active_molecule.strip("\"")
molecule = Chem.MolFromSmiles(molecule_smiles)
tt_fingerprint = Torsions.GetHashedTopologicalTorsionFingerprint(
molecule, nBits=nbits)
active_molecules_tt.append(tt_fingerprint)
first_line = True
with open(output_file, "w", encoding="utf-8") as output_stream:
with open(fragments_file, "r", encoding="utf-8") as input_stream:
for new_line in input_stream:
line = json.loads(new_line)
test_molecule_input = line["smiles"]
test_molecule_smiles = test_molecule_input.strip("\"")
test_molecule = Chem.MolFromSmiles(test_molecule_smiles)
test_mol_fingerprint = Torsions.GetHashedTopologicalTorsionFingerprint(
test_molecule, nBits=nbits)
max_sim = max([
DataStructs.TanimotoSimilarity(test_mol_fingerprint,
fingerprint)
for fingerprint in active_molecules_tt
])
score = {"name": line["name"], "score": max_sim}
if first_line:
first_line = False
else:
output_stream.write("\n")
json.dump(score, output_stream)
def fp_tt_std(mols, nBits, chiral):
for i in mols:
fp_mol = Torsions.GetHashedTopologicalTorsionFingerprint(mols[i]["mol"], nBits=nBits, includeChirality=chiral)
mols[i]["fp"] = fp_mol
if id(mols[i]["mol"]) == id(mols[i]["mol_can"]):
mols[i]["fp_can"] = fp_mol
else:
mols[i]["fp_can"] = Torsions.GetHashedTopologicalTorsionFingerprint(mols[i]["mol_can"], nBits=nBits,
includeChirality=chiral)
def _torsionsFingerprintsClustering(rdkit_mols):
"""
Returns the dice distance matrix based on torsionsfingerprints method
Parameters
----------
rdkit_mols: list
The list of rdkit.Chem.rdchem.Mol objects
Returns
-------
dicematrix: np.array
The numpy array containing the dice matrix
"""
from rdkit.Chem.AtomPairs import Torsions # Topological Torsions
fps = []
for m in tqdm(rdkit_mols):
fps.append(Torsions.GetHashedTopologicalTorsionFingerprint(m))
aprun = ParallelExecutor(n_jobs=-1) # _config['ncpus'])
dice_matrix = aprun(total=len(fps), desc='TorsionsFingerprints Distance') \
(delayed(DiceDistances)(fp1, fps) for fp1 in fps)
return np.array(dice_matrix)
def GetMolFingerprint(mol,maxPathLength):
FQuery = Chem.MolFromSmarts('F')
CF3Query= Chem.MolFromSmarts('[$(C(F)(F)F)]')
CF3Rxn = AllChem.ReactionFromSmarts('[*:1]-C(F)(F)F>>[*:1]-F')
hasCF3 = mol.HasSubstructMatch(CF3Query)
if hasCF3:
p = CF3Rxn.RunReactants((mol,))[0][0]
Chem.SanitizeMol(p)
for nm in mol.GetPropNames():
p.SetProp(nm,mol.GetProp(nm))
mol = p
match = mol.GetSubstructMatch(FQuery)
fp = Torsions.GetHashedTopologicalTorsionFingerprint(mol,nBits=9192,targetSize=maxPathLength,fromAtoms=match)
for i in range(2,maxPathLength):
nfp = Torsions.GetHashedTopologicalTorsionFingerprint(mol,nBits=9192,targetSize=i,fromAtoms=match)
for bit,v in nfp.GetNonzeroElements().iteritems():
fp[bit] = fp[bit]+v
return fp
def GetTorsionFPs(mol, nBits = 2048, binary = True):
'''
atompairs fingerprints
'''
fp = Torsions.GetHashedTopologicalTorsionFingerprint(mol, nBits = nBits)
if binary:
arr = np.zeros((0,), dtype=np.bool)
else:
arr = np.zeros((0,), dtype=np.int8)
DataStructs.ConvertToNumpyArray(fp, arr)
return arr
def fp_torsion(mols, key, nBits, chiral):
for i in mols:
fp = Torsions.GetHashedTopologicalTorsionFingerprint(
mols[i][key], nBits=nBits, includeChirality=chiral)
mols[i]["fp"] = fp
def fp_torsion_taut_mp(taut, i, k, nBits, chiral):
fp = Torsions.GetHashedTopologicalTorsionFingerprint(
taut, nBits=nBits, includeChirality=chiral)
return (i, fp, k)
def fp_torsion_mp(mol, i, nBits, chiral):
fp = Torsions.GetHashedTopologicalTorsionFingerprint(
mol, nBits=nBits, includeChirality=chiral)
return (i, fp)
def fp_torsion_taut(query, nBits, chiral):
for i in query:
for j in range(len(query[i]["tauts"])):
fp = Torsions.GetHashedTopologicalTorsionFingerprint(
query[i]["tauts"][j], nBits=nBits, includeChirality=chiral)
query[i][f"fp{j}"] = fp