SynBridge: Bridging Reaction States via Discrete Flow for Bidirectional Reaction Prediction
Preprint
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.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant Transformers2024
- Large-scale chemical language representations capture molecular structure and propertiesNature Machine Intelligence, 2022
- Visual Prompt Tuning2022
- Learning to Prompt for Vision-Language ModelsInternational Journal of Computer Vision, 2022
- Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph EditsJournal of Chemical Information and Modeling, 2021
- Mapping the space of chemical reactions using attention-based neural networksNature Machine Intelligence, 2021
- Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction PredictionACS Central Science, 2019
- Planning chemical syntheses with deep neural networks and symbolic AINature, 2018
- Prediction of Organic Reaction Outcomes Using Machine LearningACS Central Science, 2017
- The Logic of Chemical Synthesis: Multistep Synthesis of Complex Carbogenic Molecules (Nobel Lecture)Angewandte Chemie International Edition, 1991