BARTReact: SELFIES-driven precision in reaction modeling

Abstract

We introduce Bidirectional and Auto-Regressive Transformer for Reactions (BARTReact), a self-supervised deep learning model designed to predict chemical reactions. Built on the powerful Bidirectional and Auto-Regressive Transformer (BART) architecture, BARTReact is trained using the SELF-referencIng Embedded Strings (SELFIES), a molecular representation that ensures the production of only viable molecules, achieving an outstanding accuracy of 98.6 %.

Keywords

• SELFIES
• NLP
• Biochemical reactions