A Graph to Graphs Framework for Retrosynthesis Prediction

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.

ICML 2020

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• MolecularRNN: Generating realistic molecular graphs with optimized properties
• Retrosynthesis Prediction with Conditional Graph Logic Network

Cited by in corpus (9)

• Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction
• Learning Graph Models for Retrosynthesis Prediction
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• RetroGraph: Retrosynthetic Planning with Graph Search
• Energy-based View of Retrosynthesis
• DirectMultiStep: Direct Route Generation for Multistep Retrosynthesis
• RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
• Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction
• Self-Improved Retrosynthetic Planning