def canonicalize(smi_list, showprogress=False):
mol_list = []
if showprogress:
print('Canonicalising mols')
for smi in tqdm(smi_list):
mol = MolFromSmiles(smi)
if mol is not None:
mol_list.append(MolToSmiles(mol))
else:
for smi in smi_list:
mol = MolFromSmiles(smi)
if mol is not None:
mol_list.append(MolToSmiles(mol))
mol_list = list(set(mol_list))
final_list = []
if showprogress:
print('Size of unfiltered final library: {}'.format(len(mol_list)))
print('Filtering by n_heavy and logP:')
for smi in tqdm(mol_list):
mol = MolFromSmiles(smi)
n_heavy = mol.GetNumHeavyAtoms()
if n_heavy > 17:
logP = Crippen.MolLogP(mol)
if logP <= 5:
final_list.append(smi)
else:
for smi in mol_list:
mol = MolFromSmiles(smi)
n_heavy = mol.GetNumHeavyAtoms()
if n_heavy > 17:
logP = Crippen.MolLogP(mol)
if logP <= 5:
final_list.append(smi)
return final_list
def canonicalize_and_filter(smi_list, showprogress=False):
"""
Function that returns the set of unique RDKit molecules from a list of input RDKit molecules
by turning them into canonical SMILES and checking the strings for uniqueness.
Also performs rudimentary Lipinski rule-of-5 filtering by dropping molecules with logP >5 and
more than 17 heavy atoms.
"""
mol_list = []
if showprogress:
print('Canonicalising mols')
for smi in tqdm(smi_list):
mol = MolFromSmiles(smi)
if mol is not None:
mol_list.append(MolToSmiles(mol))
else:
for smi in smi_list:
mol = MolFromSmiles(smi)
if mol is not None:
mol_list.append(mol)
mol_list = list(set(mol_list))
final_list = []
if showprogress:
print('Size of unfiltered final library: {}'.format(len(mol_list)))
print('Filtering by n_heavy and logP:')
for smi in tqdm(mol_list):
mol = MolFromSmiles(smi)
n_heavy = mol.GetNumHeavyAtoms()
if n_heavy > 17:
logP = Crippen.MolLogP(mol)
if logP <= 5:
final_list.append(smi)
else:
for smi in mol_list:
mol = MolFromSmiles(smi)
n_heavy = mol.GetNumHeavyAtoms()
if n_heavy > 17:
logP = Crippen.MolLogP(mol)
if logP <= 5:
final_list.append(smi)
return final_list
def worker(line):
smiles, cid = line.strip().split()[:2]
mol = MolFromSmiles(smiles)
if mol:
if '.' in smiles:
mol = remover.StripMol(mol)
logp = MolLogP(mol)
num_heavy_atoms = mol.GetNumHeavyAtoms()
if num_heavy_atoms > 99:
num_heavy_atoms = 99
sign = 'M' if logp < 0.0 else 'P'
return f'{smiles} {cid} H{num_heavy_atoms:02}{sign}{abs(scale_logp_value(logp)):03}\n'
def dataset_distribution(f_paths):
n_heavy = []
f_path = None
for f_path in glob(f_paths):
dataset = pd.read_csv(f_path)
for smiles in dataset["SMILES"]:
mol = MolFromSmiles(smiles)
n_heavy.append(mol.GetNumHeavyAtoms())
f_dir = osp.dirname(f_path)
f_base = osp.basename(f_path).split(".")[0]
plt.hist(n_heavy, bins=range(min(n_heavy), max(n_heavy) + 1))
plt.xlabel("num of heavy atoms")
plt.ylabel("count")
plt.title("dd_sol")
plt.savefig(osp.join(f_dir, f_base + "_mmff_dist.png"))
