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

Simplified molecular input line entry system (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...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of chemical information and modeling 2021-04, Vol.61 (4), p.1560-1569
Hauptverfasser:	Li, Xinhao, Fourches, Denis
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Datasets Deep learning Machine learning Machine Learning and Deep Learning Molecular structure Prediction models Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!