基于机器学习的密度泛函理论核磁共振计算在高通量计算机辅助药物设计中的应用：用于复杂生物碱的溶液结构验证和修正。
DU8ML: Machine Learning-Augmented Density Functional Theory Nuclear Magnetic Resonance Computations for High-Throughput In Silico Solution Structure Validation and Revision of Complex Alkaloids.
机构信息
Department of Chemistry and Biochemistry, University of Denver, Denver, Colorado 80208, United States.
出版信息
J Org Chem. 2022 Apr 1;87(7):4818-4828. doi: 10.1021/acs.joc.2c00169. Epub 2022 Mar 18.
PMID:35302771
Abstract
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.
摘要
机器学习 (ML) 极大地提高了快速 DU8+ 杂化密度泛函理论/参数计算核磁共振谱的准确性，使得复杂生物碱和其他天然产物的高通量计算机模拟验证和修正成为可能。在近 170 种调查的生物碱中，有 35 种结构使用新一代 ML 增强的 DU8 方法进行了修正，称为 DU8ML。
Zotero 插件