Pushing the Limits of Surface-Enhanced Raman Spectroscopy (SERS) with Deep Learning: Identification of Multiple Species with Closely Related Molecular Structures

Abstract

Raman spectroscopy is a non-destructive and label-free molecular identification technique capable of producing highly specific spectra with various bands correlated to molecular structure. Moreover, the enhanced detection sensitivity offered by surface-enhanced Raman spectroscopy (SERS) allows analyzing mixtures of related chemical species in a relatively short measurement time. Combining SERS with deep learning algorithms allows in some cases to increase detection and classification capabilities even further. The present study evaluates the potential of applying deep learning algorithms to SERS spectroscopy to differentiate and classify different species of bile acids, a large family of molecules with low Raman cross sections and molecular structures that often differ by a single hydroxyl group. Moreover, the study of these molecules is of interest for the medical community since they have distinct pathological roles and are currently viewed as potential markers of gut microbiome imbalances. A convolutional neural network model was developed and used to classify SERS spectra from five bile acid species. The model succeeded in identifying the five analytes despite very similar molecular structures and was found to be reliable even at low analyte concentrations.