Abstract
An accurate prediction of chemical shifts (δ) to elucidate molecular structures has been a challenging problem. Recently, noble machine learning architectures achieve accurate prediction performance, but the difficulty of building a huge chemical database limits the applicability of machine learning approaches. In this work, we demonstrate that the prior knowledge gained from the simulation database is successfully transferred into the problem of predicting an experimentally measured δ. Although both simulation and experimental databases are vastly different in chemical perspectives, reliable accuracy for δ is achieved by additional training with randomly sampled small numbers of experimental data. Furthermore, the prior knowledge allows us to successfully train the model on the more focused chemical space that the experimental database sparsely covers. The proposed approach, the knowledge transfer from the simulation database, can be utilized to enhance the usability of the local experimental database.
Highlights
An accurate prediction of chemical shifts (δ) to elucidate molecular structures has been a challenging problem
E lucidating nuclear magnetic resonance (NMR) spectroscopic results is frequently employed with the help of fast and accurate prediction of chemical shifts (δ).[1−8] A quantum mechanical (QM) simulation provides accurate isotropic magnetic shielding constants (σ), which are utilized to estimate δ within a manageable computational cost
Instead of computing σ values based on the quantum theory, direct inferences of δ from accumulated NMR results by a machine learning (ML) model are actively studied.[4−8] In the field of NMR spectrum prediction, the methods to utilize the existing database have been proposed even before the introduction of ML by searching the chemical shifts of atoms that have the same local chemical environment to the target atom.[3,11]
Summary
An accurate prediction of chemical shifts (δ) to elucidate molecular structures has been a challenging problem. We describe the construction and training of ML models to predict chemical shifts only with a small amount of experimental data by utilizing transfer learning.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
