Regio-selectivity prediction with a machine-learned reaction representation and on-the-fly quantum mechanical descriptors

作者：Yanfei Guan, Connor W. Coley, Haoyang Wu, Duminda S. Ranasinghe, Esther Heid, Thomas J. Struble, Lagnajit Pattanaik, William H. Green, Klavs F. Jensen · 发表于：Chemical Science · 年份：2020 · DOI：10.1039/d0sc04823b · 被引用次数：166 · 研究领域：Machine Learning in Materials Science、Computational Drug Discovery Methods、Various Chemistry Research Topics

calculations of 130k organic molecules, and train a multi-task constrained model to calculate demanded descriptors on-the-fly. The proposed platform enhances the inter/extra-polated performance for regio-selectivity predictions and enables learning from small datasets with just hundreds of examples. Furthermore, the proposed protocol is demonstrated to be generally applicable to a diverse range of chemical spaces. For three general types of substitution reactions (aromatic C-H functionalization, aromatic C-X substitution, and other substitution reactions) curated from a commercial database, the fusion model achieves 89.7%, 96.7%, and 97.2% top-1 accuracy in predicting the major outcome, respectively, each using 5000 training reactions. Using predicted descriptors, the fusion model is end-to-end, and requires approximately only 70 ms per reaction to predict the selectivity from reaction SMILES strings.