Impact of noise on inverse design: The case of NMR spectra matching

TL;DR

This paper investigates how noise impacts the effectiveness of inverse NMR spectra matching for chemical structure elucidation, emphasizing the importance of constraining search spaces and combining spectral data to improve accuracy and reduce data requirements.

Contribution

It systematically analyzes the effect of search space constraints and spectral data combination on NMR spectra matching accuracy, providing insights for more robust inverse structure elucidation algorithms.

Findings

Constrained search spaces improve matching accuracy.

Combining $^{13}$C and $^{1}$H shifts enhances performance.

Reducing ambiguity decreases machine learning data needs.

Abstract

Despite its fundamental importance and widespread use for assessing reaction success in organic chemistry, deducing chemical structures from nuclear magnetic resonance (NMR) measurements has remained largely manual and time consuming. To keep up with the accelerated pace of automated synthesis in self driving laboratory settings, robust computational algorithms are needed to rapidly perform structure elucidations. We analyse the effectiveness of solving the NMR spectra matching task encountered in this inverse structure elucidation problem by systematically constraining the chemical search space, and correspondingly reducing the ambiguity of the matching task. Numerical evidence collected for the twenty most common stoichiometries in the QM9-NMR data base indicate systematic trends of more permissible machine learning prediction errors in constrained search spaces. Results suggest that compounds with multiple heteroatoms are harder to characterize than others. Extending QM9 by $\sim$10 times more constitutional isomers with 3D structures generated by Surge, ETKDG and CREST, we used ML models of chemical shifts trained on the QM9-NMR data to test the spectra matching algorithms. Combining both $^{13}\mathrm{C}$ and $^{1}\mathrm{H}$ shifts in the matching process suggests twice as permissible machine learning prediction errors than for matching based on $^{13}\mathrm{C}$ shifts alone. Performance curves demonstrate that reducing ambiguity and search space can decrease machine learning training data needs by orders of magnitude.