SynBridge: Bridging Reaction States via Discrete Flow for Bidirectional Reaction Prediction

TL;DR

SynBridge is a novel bidirectional generative model that uses discrete flow and graph transformers to accurately predict chemical reactions and their reverse processes, outperforming existing methods on benchmark datasets.

Contribution

The paper introduces SynBridge, a discrete flow-based generative model with graph transformers for multi-task reaction prediction, capturing bidirectional transformations between reactants and products.

Findings

Achieves state-of-the-art results on USPTO datasets.

Effectively models bidirectional chemical transformations.

Structured diffusion over discrete spaces improves prediction accuracy.

Abstract

The essence of a chemical reaction lies in the redistribution and reorganization of electrons, which is often manifested through electron transfer or the migration of electron pairs. These changes are inherently discrete and abrupt in the physical world, such as alterations in the charge states of atoms or the formation and breaking of chemical bonds. To model the transition of states, we propose SynBridge, a bidirectional flow-based generative model to achieve multi-task reaction prediction. By leveraging a graph-to-graph transformer network architecture and discrete flow bridges between any two discrete distributions, SynBridge captures bidirectional chemical transformations between graphs of reactants and products through the bonds' and atoms' discrete states. We further demonstrate the effectiveness of our method through extensive experiments on three benchmark datasets (USPTO-50K, USPTO-MIT, Pistachio), achieving state-of-the-art performance in both forward and retrosynthesis tasks. Our ablation studies and noise scheduling analysis reveal the benefits of structured diffusion over discrete spaces for reaction prediction.