Retrosynthetic planning aims to devise a complete multi-step synthetic route from starting materials to a target molecule. Current strategies use a decoupled approach of single-step retrosynthesis models and search algorithms, taking only the product as the input to predict the reactants for each planning step and ignoring valuable context information along the synthetic route. In this work, we propose a novel framework that utilizes context information for improved retrosynthetic planning. We view synthetic routes as reaction graphs and propose to incorporate context through three principled steps: encode molecules into embeddings, aggregate information over routes, and readout to predict reactants. Our approach is the first attempt to utilize in-context learning for retrosynthesis prediction in retrosynthetic planning. The entire framework can be efficiently optimized in an end-to-end fashion and produce more practical and accurate predictions. Comprehensive experiments demonstrate that by fusing in the context information over routes, our model significantly improves the performance of retrosynthetic planning over baselines that are not context-aware, especially for long synthetic routes. Code is available at https://github.com/SongtaoLiu0823/FusionRetro.

翻译：逆合成规划旨在设计从起始原料到目标分子的完整多步合成路线。当前策略采用单步逆合成模型与搜索算法的解耦方法，仅以产物作为每一步规划中预测反应物的输入，而忽略了合成路线上有价值的情境信息。在本工作中，我们提出一种利用情境信息改进逆合成规划的新框架。我们将合成路线视为反应图，并通过三个原理性步骤融入情境信息：将分子编码为嵌入向量、沿路线聚合信息、以及读出以预测反应物。我们的方法首次尝试在逆合成规划中利用情境学习进行逆合成预测。整个框架可以端到端高效优化，并产生更实用和准确的预测。综合实验表明，通过融合路径上的情境信息，我们的模型在逆合成规划性能上显著优于不感知情境的基线方法，尤其在长合成路线场景中表现突出。代码已开源至 https://github.com/SongtaoLiu0823/FusionRetro。