arXiv：cs.LG（机器学习，全量分类）· Xiaozhuang Song, Xuemin Chen, Xinjian Zhao, Yaoyao Xu, Tianshu Yu·· 5 小时前AI 评分31
RetroGEF：面向单步逆合成的动态图编辑流模型
RetroGEF: Dynamic Graph Edit Flow for Single-Step Retrosynthesis
AI 导读
RetroGEF 是一种基于流的生成模型，用于单步逆合成，可从目标分子出发，通过添加原子和改变化学键直接构建可能的反应物。它无需固定大小的图画布，也无需预设编辑顺序，即可在同一生成过程中建模分子变换与图规模变化。在代表性逆合成基准上，RetroGEF 取得了 SOTA 性能。
正文
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.
| Comments: | 25 pages, 10 figures |
| Subjects: | Machine Learning (cs.LG); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2609.38484 [cs.LG] |
| (or arXiv:2609.38484v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.38484 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaozhuang Song [view email]
[v1]
Tue, 29 Sep 2026 20:12:48 UTC (477 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org