Uncertainty-aware prediction of chemical reaction yields with graph neural networks

Journal of Cheminformatics

Seokho Kang¹  Youn-Suk Choi²  Dongseon Lee²  Youngchun Kwon² 

[1] Department of Industrial Engineering, Sungkyunkwan University;Samsung Advanced Institute of Technology, Samsung Electronics Co. Ltd.;

关键词: Chemical reaction yield prediction;    Uncertainty-aware prediction;    Graph neural network;    Deep learning;   

DOI  :  10.1186/s13321-021-00579-z

来源: DOAJ

【 摘 要 】

Abstract In this paper, we present a data-driven method for the uncertainty-aware prediction of chemical reaction yields. The reactants and products in a chemical reaction are represented as a set of molecular graphs. The predictive distribution of the yield is modeled as a graph neural network that directly processes a set of graphs with permutation invariance. Uncertainty-aware learning and inference are applied to the model to make accurate predictions and to evaluate their uncertainty. We demonstrate the effectiveness of the proposed method on benchmark datasets with various settings. Compared to the existing methods, the proposed method improves the prediction and uncertainty quantification performance in most settings.

【 授权许可】

Unknown