Timezone: »

FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Songtao Liu · Zhengkai Tu · Minkai Xu · Zuobai Zhang · Lu Lin · ZHITAO YING · Jian Tang · Peilin Zhao · Dinghao Wu

Wed Jul 26 02:00 PM -- 03:30 PM (PDT) @ Exhibit Hall 1 #207
Event URL: https://github.com/SongtaoLiu0823/FusionRetro »

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.

Author Information

Songtao Liu (Penn State)
Zhengkai Tu (Massachusetts Institute of Technology)
Minkai Xu (Stanford University)
Zuobai Zhang (Mila)
Lu Lin (Pennsylvania State University)
ZHITAO YING (Yale University)
Jian Tang (Mila)
Peilin Zhao (Artificial Intelligence Department, Ant ​Financial)
Dinghao Wu (Pennsylvania State University)

More from the Same Authors