A Graph to Graphs Framework for Retrosynthesis Prediction

Chence Shi, Minkai Xu, Hongyu Guo, Ming Zhang, Jian Tang
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:8818-8827, 2020.

Abstract

A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a.k.a. retrosynthesis prediction. Existing state-of-the-art methods rely on matching the target molecule with a large set of reaction templates, which are very computationally expensive and also suffer from the problem of coverage. In this paper, we propose a novel template-free approach called G2Gs by transforming a target molecular graph into a set of reactant molecular graphs. G2Gs first splits the target molecular graph into a set of synthons by identifying the reaction centers, and then translates the synthons to the final reactant graphs via a variational graph translation framework. Experimental results show that G2Gs significantly outperforms existing template-free approaches by up to 63% in terms of the top-1 accuracy and achieves a performance close to that of state-of-the-art template-based approaches, but does not require domain knowledge and is much more scalable.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-shi20d, title = {A Graph to Graphs Framework for Retrosynthesis Prediction}, author = {Shi, Chence and Xu, Minkai and Guo, Hongyu and Zhang, Ming and Tang, Jian}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {8818--8827}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/shi20d/shi20d.pdf}, url = {https://proceedings.mlr.press/v119/shi20d.html}, abstract = {A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a.k.a. retrosynthesis prediction. Existing state-of-the-art methods rely on matching the target molecule with a large set of reaction templates, which are very computationally expensive and also suffer from the problem of coverage. In this paper, we propose a novel template-free approach called G2Gs by transforming a target molecular graph into a set of reactant molecular graphs. G2Gs first splits the target molecular graph into a set of synthons by identifying the reaction centers, and then translates the synthons to the final reactant graphs via a variational graph translation framework. Experimental results show that G2Gs significantly outperforms existing template-free approaches by up to 63% in terms of the top-1 accuracy and achieves a performance close to that of state-of-the-art template-based approaches, but does not require domain knowledge and is much more scalable.} }
Endnote
%0 Conference Paper %T A Graph to Graphs Framework for Retrosynthesis Prediction %A Chence Shi %A Minkai Xu %A Hongyu Guo %A Ming Zhang %A Jian Tang %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-shi20d %I PMLR %P 8818--8827 %U https://proceedings.mlr.press/v119/shi20d.html %V 119 %X A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a.k.a. retrosynthesis prediction. Existing state-of-the-art methods rely on matching the target molecule with a large set of reaction templates, which are very computationally expensive and also suffer from the problem of coverage. In this paper, we propose a novel template-free approach called G2Gs by transforming a target molecular graph into a set of reactant molecular graphs. G2Gs first splits the target molecular graph into a set of synthons by identifying the reaction centers, and then translates the synthons to the final reactant graphs via a variational graph translation framework. Experimental results show that G2Gs significantly outperforms existing template-free approaches by up to 63% in terms of the top-1 accuracy and achieves a performance close to that of state-of-the-art template-based approaches, but does not require domain knowledge and is much more scalable.
APA
Shi, C., Xu, M., Guo, H., Zhang, M. & Tang, J.. (2020). A Graph to Graphs Framework for Retrosynthesis Prediction. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:8818-8827 Available from https://proceedings.mlr.press/v119/shi20d.html.

Related Material