RetroGEF: Dynamic Graph Edit Flow for Single-Step Retrosynthesis

2026-09-29

AI Summary

This study addresses the modeling challenge of dynamically changing molecular graph connectivity and size in retrosynthesis, where existing methods are constrained by fixed-size graph canvases. We propose RetroGEF, a flow-based generative model that leverages dynamic graph neural networks within a flow-matching framework to directly simulate atom additions and bond transformations via dynamic graph editing flows, thereby unifying the modeling of structural transitions and graph size variations. By eliminating the need for predefined editing orders and removing reliance on fixed canvases, our approach enables end-to-end, single-step retrosynthesis prediction. Experimental results demonstrate that RetroGEF achieves state-of-the-art performance across multiple representative retrosynthesis benchmarks.

Abstract

Retrosynthesis enables the discovery of viable synthetic routes to target molecules. It plays a central role in modern drug discovery and materials design. Retrosynthesis involves molecular graph transformations that can change both connectivity and graph size. These transformations may introduce reactant components absent from the target while revising the product-derived structure. To model these transformations, we propose RetroGEF, a flow-based generative model for single-step retrosynthesis. Starting from the target molecule, it constructs possible reactants by adding atoms and changing bonds in the molecular graph. RetroGEF models molecular transformations and changes in graph size within the same generative process, rather than relying on a fixed-size graph canvas. It learns this process directly from product--reactant pairs without requiring a prescribed edit order. Experiments on representative retrosynthesis benchmarks demonstrate that RetroGEF achieves state-of-the-art performance.

Problem

• Retrosynthesis
• Molecular graph transformation
• Graph edit flow
• Single-step retrosynthesis
• Generative model

Innovation

• Retrosynthesis
• Flow-based generative model
• Graph edit flow
• Molecular graph transformation
• Single-step retrosynthesis