SVR Chemometrics to Quantify ß-Lactoglobulin and α-Lactalbumin in Milk Using MIR.

Protein content variation in milk can impact the quality and consistency of dairy products, necessitating access to in-line real time monitoring. Here, we present a chemometric approach for the qualitative and quantitative monitoring of ß-lactoglobulin and α-lactalbumin, using mid-infrared spectroscopy (MIR). In this study, we employed Hotelling T2 and Q-residual for outlier detection, automated preprocessing using nippy, conducted wavenumber selection with genetic algorithms, and evaluated four chemometric models, including partial least squares, support vector regression (SVR), ridge, and logistic regression to accurately predict the concentrations of ß-lactoglobulin and α-lactalbumin in milk. For the quantitative analysis of these two whey proteins, SVR performed the best to interpret protein concentration from 197 MIR spectra originating from 42 Cornell University samples of preserved pasteurized modified milk. The R2 values obtained for ß-lactoglobulin and α-lactalbumin using leave one out cross-validation (LOOCV) are 92.8% and 92.7%, respectively, which is the highest correlation reported to date. Our approach introduced a combination of preprocessing automation, genetic algorithm-based wavenumber selection, and used Optuna to optimize the framework for tuning hyperparameters of the chemometric models, resulting in the best chemometric analysis of MIR data to quantitate ß-lactoglobulin and α-lactalbumin to date.

Whey Protein Powder Analysis by Mid-Infrared Spectroscopy.

There is an ever-expanding number of high protein dietary supplements marketed as beneficial to athletes, body builders, infant formulas, elder care, and animal feed. Consumers will pay more for products with high protein per serving data on their nutritional labels, making the accurate reporting of protein content critical to customer confidence. The Kjeldahl method (KM) is the industry standard to quantitate dairy proteins, but the result is based on nitrogen content, which is an approximation of nitrogen attributable to protein in milk. Product tampering by third-party manufacturers is an issue, due to the lack of United States Food and Drug Administration regulation of nutraceutical products, permitting formulators to add low-cost nitrogen-containing components to artificially inflate the KM approximated protein content in products. Optical spectroscopy is commonly used for quality control measurements and has been identified as having the potential to complement the KM as a more nuanced testing measure of dairy protein. Mid-infrared (MIR) spectroscopy spectra of eight protein standards provided qualitative characterization of each protein by amide I and amide II peak absorbance wavenumber. Protein doping experiments revealed that as protein amounts were increased, the amide I/II peak shape changed from the broad protein powder peaks to the narrower peaks characteristic of the individual protein. Amino acid doping experiments with lysine, glutamic acid, and glycine, determined the limit of detection by MIR spectroscopy as 25%, suggesting that MIR spectroscopy can provide product quality assurance complementary to dairy protein measurement by the KM.