pip install git+https://github.com/sergsb/LegoGram.git

from legogram import LegoGram, pretrained
model = LegoGram(load=pretrained.M_250k_kekulized_grammar)

encoded = model.encode("COC(=O)CC1=CSC(NC(=O)CC2=COC3=CC(C)=CC=C23)=N1")
model.decode(encoded) == "COC(=O)CC1=CSC(NC(=O)CC2=COC3=CC(C)=CC=C23)=N1" #It's a toy example. In production compare by InChI
>>True

mol = 'COC(=O)Cc1csc(NC(=O)Cc2coc3cc(C)ccc23)n1'
noncompressed = model.encode(mol)
compressed    = model.encode(mol,optimize=True)
print("SMILES len = {}, uncomressed grammar = {}, comressed grammar = {}".format(len(mol),len(noncompressed),len(compressed))
>> SMILES len = 40, uncomressed grammar = 26, comressed grammar = 14

model = legogram.LegoGram(smiles="legogram/data/250k_rndm_zinc_drugs_clean.smi", optimize_limit=100)