Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Ruoxi Sun, Hanjun Dai, Li Li, Steven Kearnes, Bo Dai• 2020

Related benchmarks

TaskDatasetResultRank
RetrosynthesisUSPTO-50k Reaction type unknown (test)
Top-1 Accuracy53.6
59
RetrosynthesisUSPTO-50k Reaction type known (test)
Top-1 Accuracy65.7
50
Retrosynthesis predictionUSPTO-50k (test)
Top-1 Accuracy64.7
39
Retrosynthesis predictionUSPTO-50K
Top-1 Acc (Unknown)55.2
22
Showing 4 of 4 rows

Other info

Follow for update