Learning Chemical Rules of Retrosynthesis with Pre-training
Yinjie Jiang, Ying WEI, Fei Wu, Zhengxing Huang, Kun Kuang, Zhihua Wang
Abstract
Retrosynthesis aided by artificial intelligence has been a very active and bourgeoning area of research, for its critical role in drug discovery as well as material science. Three categories of solutions, i.e., template-based, template-free, and semi-template methods, constitute mainstream solutions to this problem. In this paper, we focus on template-free methods which are known to be less bothered by the template generalization issue and the atom mapping challenge. Among several remaining problems regarding template-free methods, failing to conform to chemical rules is pronounced. To address the issue, we seek for a pre-training solution to empower the pre-trained model with chemical rules encoded. Concretely, we enforce the atom conservation rule via a molecule reconstruction pre-training task, and the reaction rule that dictates reaction centers via a reaction type guided contrastive pre-training task. In our empirical evaluation, the proposed pre-training solution substantially improves the single-step retrosynthesis accuracies in three downstream datasets.
BibTeX
@article{Jiang_WEI_Wu_Huang_Kuang_Wang_2023, title={Learning Chemical Rules of Retrosynthesis with Pre-training}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25640}, DOI={10.1609/aaai.v37i4.25640}, abstractNote={Retrosynthesis aided by artificial intelligence has been a very active and bourgeoning area of research, for its critical role in drug discovery as well as material science. Three categories of solutions, i.e., template-based, template-free, and semi-template methods, constitute mainstream solutions to this problem. In this paper, we focus on template-free methods which are known to be less bothered by the template generalization issue and the atom mapping challenge. Among several remaining problems regarding template-free methods, failing to conform to chemical rules is pronounced. To address the issue, we seek for a pre-training solution to empower the pre-trained model with chemical rules encoded. Concretely, we enforce the atom conservation rule via a molecule reconstruction pre-training task, and the reaction rule that dictates reaction centers via a reaction type guided contrastive pre-training task. In our empirical evaluation, the proposed pre-training solution substantially improves the single-step retrosynthesis accuracies in three downstream datasets.}, number={4}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Jiang, Yinjie and WEI, Ying and Wu, Fei and Huang, Zhengxing and Kuang, Kun and Wang, Zhihua}, year={2023}, month={Jun.}, pages={5113-5121} }