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

21 May 2020, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


SMILES-based deep learning models are slowly emerging as an important research topic in cheminformatics. In this study, we introduce SMILES Pair Encoding (SPE), a data-driven tokenization algorithm. SPE first learns a vocabulary of high frequency SMILES substrings from a large chemical dataset (e.g., ChEMBL) and then tokenizes SMILES based on the learned vocabulary for deep learning models. As a result, SPE augments the widely used atom-level tokenization by adding human-readable and chemically explainable SMILES substrings as tokens. Case studies show that SPE can achieve superior performances for both molecular generation and property prediction tasks. In molecular generation task, SPE can boost the validity and novelty of generated SMILES. Herein, the molecular property prediction models were evaluated using 24 benchmark datasets where SPE consistently either did match or outperform atom-level tokenization. Therefore SPE could be a promising tokenization method for SMILES-based deep learning models. An open source Python package SmilesPE was developed to implement this algorithm and is now available at


Deep learning
Data-driven tokenization
Molecular Generation
QSAR Modeling


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.