Peculiar Reaction Products and Mechanisms Revisited with Machine Learning-Augmented Computational NMR
Peculiar Reaction Products and Mechanisms Revisited with Machine Learning-Augmented Computational NMR
复制标题
DOI：
10.1021/acs.joc.2c00749
复制
发表时间：
2022-06-18
影响因子：
3.6
通讯作者：
Kutateladze, Andrei G.
中科院分区：
文献类型：
--
作者：
Novitskiy, Ivan M.;Kutateladze, Andrei G.
DU8ML是一种用于计算核磁共振（NMR）谱的快速准确的机器学习增强密度泛函理论（DFT）方法，被证明对错误分配的天然产物的高通量修正是有效的。在本文中，我们揭示了它的应用的另一个重要方面：纠正不寻常的反应机制，最初提出的，因为不正确的产品结构。
DU8ML, a fast and accurate machine learning-augmented density functional theory (DFT) method for computing nuclear magnetic resonance (NMR) spectra, proved effective for high-throughput revision of misassigned natural products. In this paper, we disclose another important aspect of its application: correction of unusual reaction mechanisms originally proposed because of incorrect product structures.