Energy-based View of Retrosynthesis
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Retrosynthesis | USPTO-50k Reaction type unknown (test) | Top-1 Accuracy53.6 | 59 | |
| Retrosynthesis | USPTO-50k Reaction type known (test) | Top-1 Accuracy65.7 | 50 | |
| Retrosynthesis prediction | USPTO-50k (test) | Top-1 Accuracy64.7 | 39 | |
| Retrosynthesis prediction | USPTO-50K | Top-1 Acc (Unknown)55.2 | 22 |