RSscore: Reaction superiority learned from reaction mapping hypergraph

Abstract

The selection of chemical reactions is directly related to the quality of synthesis pathways, so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways. Since reaction conditions also need to be considered in synthesis pathway design, a reaction metric that combines reaction time, temperature, and yield is required for chemical reactions of different reaction agents. In this study, a chemical reaction graph descriptor which includes the atom-atom mapping relationship is proposed to effectively describe reactions. Then, through pre-training using graph contrastive learning and fine-tuning through supervised learning, we establish a model for generating the probability of reaction superiority (RSscore). Finally, to validate the effectiveness of the current evaluation index, RSscore is applied in two applications, namely reaction evaluation and synthesis routes analysis, which proves that the RSscore provides an important agents-considered evaluation criterion for Computer-Aided Synthesis Planning (CASP).