Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks have achieved encouraging results. In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions. This unified perspective provides critical insights about EBM variants through a comprehensive assessment of performance. Additionally, we present a novel dual variant within the framework that performs consistent training over Bayesian forward- and backward-prediction by constraining the agreement between the two directions. This model improves state-of-the-art performance by 9.6% for template-free approaches where the reaction type is unknown.
@article{arxiv.2007.13437,
title = {Energy-based View of Retrosynthesis},
author = {Ruoxi Sun and Hanjun Dai and Li Li and Steven Kearnes and Bo Dai},
journal= {arXiv preprint arXiv:2007.13437},
year = {2021}
}