2. SMILES

SmilesPE

pip install SmilesPE

from SmilesPE.pretokenizer import atomwise_tokenizer

smi = 'CC[N+](C)(C)Cc1ccccc1Br'
toks = atomwise_tokenizer(smi)
print(toks)

1. K-mer Tokenzier

from SmilesPE.pretokenizer import kmer_tokenizer

smi = 'CC[N+](C)(C)Cc1ccccc1Br'
toks = kmer_tokenizer(smi, ngram=4)
print(toks)