DU8ML: Machine Learning-Augmented Density Functional Theory Nuclear Magnetic Resonance Computations for High-Throughput In Silico Solution Structure Validation and Revision of Complex Alkaloids
DU8ML: Machine Learning-Augmented Density Functional Theory Nuclear Magnetic Resonance Computations for High-Throughput In Silico Solution Structure Validation and Revision of Complex Alkaloids
复制标题
DOI：
10.1021/acs.joc.2c00169
复制
发表时间：
2022-04-01
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.
机器学习（ML）深刻地提高了快速DU 8+混合密度泛函理论/核磁共振谱参数计算的准确性，允许复杂生物碱和其他天然产物的高通量计算机验证和修订。在调查的近170种生物碱中，有35种结构用下一代ML增强的DU 8方法进行了修订，称为DU 8 ML。
Machine learning (ML) profoundly improves the accuracy of the fast DU8+ hybrid density functional theory/parametric computations of nuclear magnetic resonance spectra, allowing for high throughput in silico validation and revision of complex alkaloids and other natural products. Of nearly 170 alkaloids surveyed, 35 structures are revised with the next-generation ML-augmented DU8 method, termed DU8ML.