Abstract Developing machine learning models with high generalization capability for predicting chemical reaction yields is of significant interest and importance. The efficacy of such models depends heavily on the representation of chemical reactions, which has commonly been learned from SMILES or graphs of molecules using deep neural networks. However, the progression of chemical reactions is inherently determined by the molecular 3D geometric properties, which have been recently highlighted as crucial features in accurately predicting molecular properties and chemical reactions. Additionally, large-scale pre-training has been shown to be essential in enhancing the generalization capability of complex deep learning models. Based on these considerations, we propose the Reaction Multi-View Pre-training (ReaMVP) framework, which leverages self-supervised learning techniques and a two-stage pre-training strategy to predict chemical reaction yields. By incorporating multi-view learning with 3D geometric information, ReaMVP achieves state-of-the-art performance on two benchmark datasets. Notably, the experimental results indicate that ReaMVP has a significant advantage in predicting out-of-sample data, suggesting an enhanced generalization ability to predict new reactions. Scientific Contribution: This study presents the ReaMVP framework, which improves the generalization capability of machine learning models for predicting chemical reaction yields. By integrating sequential and geometric views and leveraging self-supervised learning techniques with a two-stage pre-training strategy, ReaMVP achieves state-of-the-art performance on benchmark datasets. The framework demonstrates superior predictive ability for out-of-sample data and enhances the prediction of new reactions.

Runhan Shi

Gufeng Yu

Xiaohong Huo

Yang Yang

Journal of Cheminformatics

JOURNAL OF CHEMINFORMATICS 是一本开放获取期刊，发表化学信息学和分子建模各个方面的原始同行评议研究。覆盖范围包括但不限于：化学信息系统、软件和数据库，以及分子建模化学结构表示及其在结构中的应用、化学物质和化学反应数据库的子结构和相似性搜索计算机和分子图形、计算机辅助分子设计、专家系统、QSAR 和数据挖掘技术。

The Journal of Cheminformatics is an open-access journal dedicated to original peer-reviewed research in all aspects of cheminformatics and molecular modeling. Its scope includes, but is not limited to: chemical information systems, software and databases, molecular modeling of chemical structure representations and their applications, substructure and similarity searching in chemical substance and reaction databases, computer and molecular graphics, computer-aided molecular design, expert systems, QSAR (Quantitative Structure-Activity Relationship), and data mining techniques.

《Journal of Cheminformatics》是一本开放获取的期刊，专注于化学信息学和分子建模领域的原创性同行评审研究。期刊的覆盖范围包括但不限于：化学信息系统、软件和数据库，以及分子建模中的化学结构表示及其应用、化学物质和化学反应数据库的子结构和相似性搜索、计算机和分子图形、计算机辅助分子设计、专家系统、QSAR（定量构效关系）和数据挖掘技术。

J Cheminform

Prediction of chemical reaction yields with large-scale multi-view pre-training

The ReaMVP framework improves the generalization capability of machine learning models for predicting chemical reaction yields by integrating sequential and geometric views and leveraging self-supervised learning techniques with a two-stage pre-training strategy, which achieves state-of-the-art performance on benchmark datasets.

Category	Quartile
化学	2
化学, 化学综合	2
化学, 计算机信息系统	2
化学, 计算机跨学科应用	3

Prediction of chemical reaction yields with large-scale multi-view pre-training

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS	1