A Graph to Graphs Framework for Retrosynthesis Prediction

TL;DR

The paper introduces G2Gs, a scalable, template-free graph transformation method for retrosynthesis prediction that outperforms existing approaches and approaches the accuracy of template-based methods.

Contribution

G2Gs is the first template-free framework that transforms target molecules into reactants via graph translation, improving scalability and accuracy.

Findings

G2Gs outperforms existing template-free methods by up to 63% in top-1 accuracy.

G2Gs achieves performance close to state-of-the-art template-based methods.

G2Gs does not require domain knowledge, enhancing scalability.

Abstract

A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a.k.a. retrosynthesis prediction. Existing state-of-the-art methods rely on matching the target molecule with a large set of reaction templates, which are very computationally expensive and also suffer from the problem of coverage. In this paper, we propose a novel template-free approach called G2Gs by transforming a target molecular graph into a set of reactant molecular graphs. G2Gs first splits the target molecular graph into a set of synthons by identifying the reaction centers, and then translates the synthons to the final reactant graphs via a variational graph translation framework. Experimental results show that G2Gs significantly outperforms existing template-free approaches by up to 63% in terms of the top-1 accuracy and achieves a performance close to that of state-of-the-art template based approaches, but does not require domain knowledge and is much more scalable.