Learning Graph Models for Retrosynthesis Prediction

TL;DR

This paper presents a graph-based neural model for retrosynthesis prediction that predicts graph edits to generate precursor molecules, achieving state-of-the-art accuracy and offering interpretability and manual correction capabilities.

Contribution

It introduces a novel graph topology-based approach that simplifies retrosynthesis prediction by focusing on graph edits, improving accuracy and interpretability.

Findings

Achieves 53.7% top-1 accuracy, outperforming previous methods.

Predicts graph edits to transform target molecules into synthons.

Enables manual correction due to interpretable predictions.

Abstract

Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule. A key consideration in building neural models for this task is aligning model design with strategies adopted by chemists. Building on this viewpoint, this paper introduces a graph-based approach that capitalizes on the idea that the graph topology of precursor molecules is largely unaltered during a chemical reaction. The model first predicts the set of graph edits transforming the target into incomplete molecules called synthons. Next, the model learns to expand synthons into complete molecules by attaching relevant leaving groups. This decomposition simplifies the architecture, making its predictions more interpretable, and also amenable to manual correction. Our model achieves a top-1 accuracy of $53.7\%$, outperforming previous template-free and semi-template-based methods.