Highly Accurate Prediction of NMR Chemical Shifts from Low-Level Quantum Mechanics Calculations Using Machine Learning

TL;DR

This paper introduces iShiftML, a machine learning approach that predicts NMR chemical shifts with high accuracy using low-cost quantum calculations and active learning, enabling efficient analysis of complex molecules.

Contribution

The study presents a novel feature representation and active learning workflow for machine learning prediction of NMR chemical shifts, reducing computational costs and improving generalization.

Findings

iShiftML achieves high accuracy in predicting NMR chemical shifts.

The model effectively differentiates subtle diastereomers.

Error estimates correlate well with actual prediction errors.

Abstract

Theoretical predictions of NMR chemical shifts from first-principles can greatly facilitate experimental interpretation and structure identification. However, accurate prediction of chemical shifts using the best coupled cluster methods can be prohibitively expensive for systems larger than ten to twenty non-hydrogen atoms on today's computers. By contrast machine learning methods offer inexpensive alternatives but are hampered by generalization to molecules outside the original training set. Here we propose a novel machine learning feature representation informed by intermediate calculations of atomic chemical shielding tensors within a molecular environment using an inexpensive quantum mechanics method, and training it to predict NMR chemical shieldings of a high-level composite theory that is comparable to CCSD(T) in the complete basis set limit. The inexpensive shift machine learning (iShiftML) algorithm is trained through a new progressive active learning workflow that reduces the total number of expensive calculations required when constructing the dataset, while allowing the model to continuously improve on data it has never seen. Furthermore, we show that the error estimations from our model correlate quite well with actual errors to provide confidence values on new predictions. We illustrate the predictive capacity of iShiftML across gas phase experimental chemical shifts for small organic molecules and much larger and more complex natural products in which we can accurately differentiate between subtle diastereomers based on chemical shift assignments.