Template-Free Retrosynthesis with Graph-Prior Augmented Transformers
This addresses the problem of improving accuracy and robustness in computer-aided organic synthesis for chemists, though it is incremental as it builds on existing Transformer-based approaches.
The paper tackles retrosynthesis reaction prediction by introducing a template-free Transformer framework that incorporates molecular graph information and data augmentation, achieving state-of-the-art performance among template-free methods on the USPTO-50K benchmark.
Retrosynthesis reaction prediction aims to infer plausible reactant molecules for a given product and is a important problem in computer-aided organic synthesis. Despite recent progress, many existing models still fall short of the accuracy and robustness required for practical deployment. In this paper, we present a template-free, Transformer-based framework that removes the need for handcrafted reaction templates or additional chemical rule engines. Our model injects molecular graph information into the attention mechanism to jointly exploit SMILES sequences and structural cues, and further applies a paired data augmentation strategy to enhance training diversity and scale. Extensive experiments on the USPTO-50K benchmark demonstrate that our approach achieves state-of-the-art performance among template-free methods and substantially outperforms a vanilla Transformer baseline.