Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders.

Raman spectroscopy is widely used across scientific domains to characterize the chemical composition of samples in a nondestructive, label-free manner. Many applications entail the unmixing of signals from mixtures of molecular species to identify the individual components present and their proportions, yet conventional methods for chemometrics often struggle with complex mixture scenarios encountered in practice. Here, we develop hyperspectral unmixing algorithms based on autoencoder neural networks, and we systematically validate them using both synthetic and experimental benchmark datasets created in-house. Our results demonstrate that unmixing autoencoders provide improved accuracy, robustness, and efficiency compared to standard unmixing methods. We also showcase the applicability of autoencoders to complex biological settings by showing improved biochemical characterization of volumetric Raman imaging data from a monocytic cell.
Competing Interests: Competing interests statement:M.M.S. holds part-time appointments at Imperial College London and the Karolinska Institute. M.M.S. is founder of Sparta Biodiscovery Ltd. which commercializes a technology for single particle Raman spectroscopy. M.M.S. is inventor in a patent describing a technique for SPARTA, a technique for single particle Raman spectroscopy (1810010.7), and in a patent describing Raman tags (2314282.1/GB/PRV). M.M.S. invested in, consults for (or was on scientific advisory boards or boards of directors), and conducts sponsored research funded by companies related to the biomaterials field.