SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep Learning

https://chemrxiv.org/articles/SMILES_Pair_Encoding_A_Data-Driven_Substructure_Tokenization_Algorithm_for_Deep_Learning/12339368?fbclid=IwAR1np44cDBp20v3PlfkNZzT-LjQrAvRkWBl0ZieSsuBRpA87emg1w3EdOlo

https://github.com/XinhaoLi74/SmilesPE