def benchmark_fprinting(smiles, sdf_file, name, fprint_params={}):
mol = mol_from_sdf(sdf_file, conf_num=fprint_params.get('first', None))
num_confs = mol.GetNumConformers()
num_rot = AllChem.CalcNumRotatableBonds(mol)
num_heavy = mol.GetNumHeavyAtoms()
start_time = time.time()
Chem.rdMolDescriptors.GetMorganFingerprintAsBitVect(mol, 2, 1024)
fprint_2d_time = time.time() - start_time
start_time = time.time()
fprints_from_mol(mol, fprint_params=fprint_params, save=False)
fprint_3d_time = time.time() - start_time
return (fprint_2d_time, fprint_3d_time, num_heavy, num_confs, num_rot)
def native_tuples_from_mol(mol, fprint_params={}, save=False):
"""Fingerprint molecule and convert to native encoding."""
if not mol.HasProp("_Name"):
raise ValueError(
"mol must have a '_Name' property or `name` must be provided")
fprints_list = fprints_from_mol(mol,
fprint_params=fprint_params,
save=save)
native_tuples = list(map(fprint_to_native_tuple, fprints_list))
return native_tuples
def get_e3fp(mol, bits, smiles=None):
"""
Get an E3FP fingerprint from an RDKit mol.
Args:
mol (rdkit.Chem.rdchem.Mol): RDKit mol object
bits (int): Number of bits in fingerprint
Returns:
fp (np.array): fingerprint as numpy array
"""
if smiles is None:
smiles = Chem.MolToSmiles(mol)
mol.SetProp("_Name", smiles)
fprint_params = {"bits": bits}
fp = (fprints_from_mol(
mol, fprint_params=fprint_params)[0].to_vector().toarray().astype(int)
).reshape(-1)
return fp
def gen_mol_blocks_from_confs(mols, num_confs, ref, ref_mol_block):
# fprint_params = {'bits': 4096, 'radius_multiplier': 1.5, 'rdkit_invariants': True}
# ref_fprint = fprints_from_mol(ref_mol, fprint_params=fprint_params)
# ref = ref_fprint[0].fold().to_rdkit()
mols_b = copy.deepcopy(mols)
names = []
mol_blocks = []
fps = []
ref_mol_block = []
for mol in mols_b:
mol = AllChem.AddHs(mol)
AllChem.EmbedMultipleConfs(mol,
numConfs=num_confs,
ignoreSmoothingFailures=True,
pruneRmsThresh=-1.0,
maxAttempts=10 * num_confs,
randomSeed=0xf00d)
fprint_params = {
'bits': 4096,
'first': num_confs,
'radius_multiplier': 1.5,
'rdkit_invariants': True
}
fprints = fprints_from_mol(mol, fprint_params=fprint_params)
binfp = [fp.fold().to_rdkit() for fp in fprints]
similarity_efcp4 = [
DataStructs.FingerprintSimilarity(ref, x) for x in binfp
]
for i in range(num_confs):
sub_name = mol.GetProp('_Name')
name = f'{sub_name}_confnum_{i}'
names.append(name)
mol_blocks.append(Chem.MolToMolBlock(mol, confId=i))
fps.append(similarity_efcp4[i])
ref_mol_block.append(ref_mol_block)
df = pd.DataFrame(list(zip(names, mol_blocks, fps, ref_mol_block)),
columns=['name', 'mol_blocks', 'fps', 'ref_mol_block'])
return df
def get_e3fp_tc(mol):
fprints = fprints_from_mol(mol, fprint_params=FPRINT_PARAMS)
return tanimoto(fprints[0], fprints[1])
chunksize = 1048576 / 10000
chunks = 10
suppl = [
m for m in AllChem.SDMolSupplier(
'/Users/tom/code_test_repository/arrow_testing/cdk2.sdf',
removeHs=False)
]
ref_mol = suppl[0]
ref_mol_block = Chem.MolToMolBlock(ref_mol)
fprint_params = {
'bits': 4096,
'radius_multiplier': 1.5,
'rdkit_invariants': True
}
fprints = fprints_from_mol(ref_mol, fprint_params=fprint_params)
binfp = [fp.fold().to_rdkit() for fp in fprints]
arr = np.zeros((0, ), dtype=np.int8)
DataStructs.ConvertToNumpyArray(binfp[0], arr)
# ref_fprint = fprints_from_mol(ref_mol, fprint_params=fprint_params)
# ref = ref_fprint[0].fold().to_rdkit()
# ref_smiles = 'CCC1=CC(Cl)=C(OC)C(C(NC[C@H]2C[C@H](OC)CN2CC)=O)=C1O'
include_columns = ['SMILES', 'Name']
table_list = csv_chunk_extractor(chunks, chunksize, include_columns, arr,
ref_mol_block)
ray.shutdown()
print('finished alignment')
# table = Chem.MolFromMolBlock(mol_block_array[0])
# print(f' the mol from the array is not a mol true or false: {m_out_of_array is None}')