Monitoring Spectrometer Drift with Unsupervised Machine Learning

Published

November 20, 2023

Author(s)

Benjamin Harding, Ziling Hu, Ashley Hiett, Frank Delaglio, Katherine Henzler- Wildman, Chad Rienstra

Abstract

Solid-state NMR spectroscopy (SSNMR) is a powerful technique to probe structural and dynamic properties of molecules at an atomic level. Modern SSNMR methods employ multidimensional pulse sequences requiring data collection over a period of days to weeks. Variations in signal intensity or frequency due to environmental fluctuation introduce artifacts into the spectra. Therefore, it is critical to actively monitor instrumentation subject to fluctuations. Here, we demonstrate a method rooted in the unsupervised machine learning algorithm principal component analysis (PCA) to evaluate the impact of environmental parameters that affect sensitivity, resolution and peak positions (chemical shifts) in multidimensional SSNMR protein spectra. PCA loading spectra illustrate the unique features associated with each drifting parameter, while the PCA scores quantify the magnitude of parameter drift. We apply this methodology to validate instrumental stability over the course of multiple weeks of data collection of a large membrane protein, the asymmetric homodimer membrane protein EmrE in lipid bilayers. We envision that these approaches will enable automated monitoring of NMR spectrometers and the approaches will be broadly applicable to other types of multidimensional spectroscopy.

Citation

Journal of Physical Chemistry B

Pub Type

Journals

Keywords

nuclear magnetic resonance spectroscopy (NMR), solid state NMR

Citation

Harding, B. , Hu, Z. , Hiett, A. , Delaglio, F. , Henzler- Wildman, K. and Rienstra, C. (2023), Monitoring Spectrometer Drift with Unsupervised Machine Learning, Journal of Physical Chemistry B (Accessed November 21, 2024)