Linear discriminant analysis, partial least squares discriminant analysis, and soft independent modeling of class analogy of experimental and simulated near-infrared spectra of a cultivation medium for mammalian cells

Currently, the qualification and control of medium formulations are performed based on simple methods (eg, pH and osmolality measurement of medium solutions), expensive and time-consuming cell culture tests, and the quantification of certain critical compounds by liquid chromatography. In addition to traditional medium qualification tools, relatively new spectroscopic techniques, such as fluorescence spectroscopy, nuclear magnetic resonance, Raman and near-infrared spectroscopies, and combinations of these techniques are increasingly being applied to medium powder investigation. A chemically defined medium powder for Chinese hamster ovary cell cultivation was investigated in this study to determine its response to heat treatments at different temperatures (30 degrees C, 50 degrees C, and 70 degrees C). Because the low availability and high costs of medium powders limit the sample sizes for such experiments, 5 groups of simulated data sets were generated based on the experimental spectra to compare the efficiencies of 3 classification methods: linear discriminant analysis (LDA) based on principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA), and soft independent modeling of class analogy (SIMCA). In case of these data sets, PCA-LDA showed better results for the classification of experimental spectra than PLS-DA and SIMCA. Moreover, the PLS-DA and SIMCA models yielded different results for different training set groups, while the PCA-LDA model yielded similar results for all training sets.