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.
@article{arxiv.2209.15315,
title = {FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning},
author = {Songtao Liu and Zhengkai Tu and Minkai Xu and Zuobai Zhang and Lu Lin and Rex Ying and Jian Tang and Peilin Zhao and Dinghao Wu},
journal= {arXiv preprint arXiv:2209.15315},
year = {2023}
}