DU8ML: Machine Learning-Augmented Density Functional Theory Nuclear Magnetic Resonance Computations for High-Throughput In Silico Solution Structure Validation and Revision of Complex Alkaloids

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.

Automated summary

Machine learning greatly enhances the accuracy of fast DU8+ hybrid density functional theory/parametric computations of nuclear magnetic resonance spectra, enabling high-throughput in silico validation and revision of complex alkaloids and other natural products. 35 structures of nearly 170 alkaloids are revised using the next-generation ML-augmented DU8 method, DU8ML.