G‐MATT: Single‐step retrosynthesis prediction using molecular grammar tree transformer

Abstract

Various template‐based and template‐free approaches have been proposed for single‐step retrosynthesis prediction in recent years. While these approaches demonstrate strong performance from a data‐driven metrics standpoint, many model architectures do not incorporate underlying chemistry principles. Here, we propose a novel chemistry‐aware retrosynthesis prediction framework that combines powerful data‐driven models with prior domain knowledge. We present a tree‐to‐sequence transformer architecture that utilizes hierarchical SMILES grammar‐based trees, incorporating crucial chemistry information that is often overlooked by SMILES text‐based representations, such as local structures and functional groups. The proposed framework, grammar‐based molecular attention tree transformer (G‐MATT), achieves significant performance improvements compared to baseline retrosynthesis models. G‐MATT achieves a promising top‐1 accuracy of 51% (top‐10 accuracy of 79.1%), an invalid rate of 1.5%, and a bioactive similarity rate of 74.8% on the USPTO‐50K dataset. Additional analyses of G‐MATT attention maps demonstrate the ability to retain chemistry knowledge without relying on excessively complex model architectures.

Artificial Intelligence Methods and Models for Retro-Biosynthesis: A Scoping Review

“…While the top-n metric is widely used for reaction prediction, its relevance has been questioned, 22 as many molecules can be built from more than one set of reactants, i.e., there are several "true" answers for a given product. Less common metrics in this context include fractional accuracy, 35 balanced accuracy, 26,55 weighted precision, 54 and ROC curve. 38,43 Metrics have also been used to assess the quality of ranking.…”

“…To that end, the maximum fragment (MaxFrag) accuracy was applied to the predictions 39,44 to consider the similarity between molecules to reflect their bioactivity. 35 Perspectives in Retro-Biosynthesis. Although many approaches have been developed for retrosynthesis, only a few have been specifically designed for retro-biosynthesis.…”

“…The transformer model retroformer associates local and global attention heads to identify the reactive region in molecules. Another possibility is to customize the transformer model with a tree representation of the SMILES, use a set of predefined compounds, or add information to the reaction using byproducts or a reaction graph . Transformer architectures have also been used to predict atom environments of the reactants knowing the products and to translate the reactants back …”

“…In retro(-bio)synthesis, one or more reactants are involved in a reaction, and the largest molecule better reflects the reaction type and is more susceptible to having an important reaction site, avoiding unambiguous reactions. To that end, the maximum fragment (MaxFrag) accuracy was applied to the predictions , to consider the similarity between molecules to reflect their bioactivity …”