Monitoring of complex industrial bioprocesses for metabolite concentrations using modern spectroscopies and machine learning: Application to gibberellic acid production

Abstract

Two rapid vibrational spectroscopic approaches (diffuse re¯ectance±absorbance Fourier transform infrared [FT-IR] and dispersive Raman spectroscopy), and one mass spectrometric method based on in vacuo Curie-point pyrolysis (PyMS), were investigated in this study. A diverse range of unprocessed, industrial fedbatch fermentation broths containing the fungus Gibberella fujikuroi producing the natural product gibberellic acid, were analyzed directly without a priori chromatographic separation. Partial least squares regression (PLSR) and arti®cial neural networks (ANNs) were applied to all of the information-rich spectra obtained by each of the methods to obtain quantitative information on the gibberellic acid titer. These estimates were of good precision, and the typical root-meansquare error for predictions of concentrations in an independent test set was <10% over a very wide titer range from 0 to 4925 ppm. However, although PLSR and ANNs are very powerful techniques they are often described as`b lack box'' methods because the information they use to construct the calibration model is largely inaccessible. Therefore, a variety of novel evolutionary computationbased methods, including genetic algorithms and genetic programming, were used to produce models that allowed the determination of those input variables that contributed most to the models formed, and to observe that these models were predominantly based on the concentration of gibberellic acid itself. This is the ®rst time that these three modern analytical spectroscopies, in combination with advanced chemometric data analysis, have been compared for their ability to analyze a real commercial bioprocess. The results demonstrate unequivocally that all methods provide very rapid and accurate estimates of the progress of industrial fermentations, and indicate that, of the three methods studied, Raman spectroscopy is the ideal bioprocess monitoring method because it can be adapted for on-line analysis.

Quick generation of Raman spectroscopy based in-process glucose control to influence biopharmaceutical protein product quality during mammalian cell culture

“…8,12,13,[31][32][33][34][35] Additionally, PLS multivariate modeling has been used for spectroscopic calibration in suspension mammalian and bacterial cell culture due to its ability to robustly correlate multi-value spectral data with discrete offline measurements. [36][37][38] However this work lacks evaluation of potential feedback control approaches [36][37][38] and resulting protein product quality attributes. 37,38 Multiple researchers have also shown promising applications of the technology by evaluating the prediction accuracy and model transferability across various production scales of Raman PLS models for nutrient, waste metabolite, and cell growth profiles but mainly focus on aspects of prediction model performance, scalability and tech transfer between production environments.…”

Performance monitoring of a mammalian cell based bioprocess using Raman spectroscopy

“…Raman spectroscopy is generally implemented using excitation sources in the visible to NIR regions of the spectrum which allows for the use of fiber optic probes for remote or in-situ analysis [18,19]. The use of Raman spectroscopy for the analysis of complex systems like in-reactor bioprocess monitoring is a rapidly expanding [20][21][22].…”

Rapid monitoring of recombinant antibody production by mammalian cell cultures using fourier transform infrared spectroscopy and chemometrics

“…Among its advantages are minimal sample preparation time, high throughput automation (usually in batches of 96 or 384), low cost per sample and spectra that can be acquired in less than a minute. IR spectroscopy has previously been used for offline monitoring of cell biomass (Vaidyanathan et al, 1999), recombinant protein production in batch cultures of Escherichia coli (Gross-Selbeck et al, 2007;McGovern et al, 1999), and for quantification of secondary metabolite production (McGovern et al, 2002) as well as nutrient supply (Brimmer and Hall, 1993). FT-IR has also been used as a tool for monitoring temperature-dependent unfolding of purified proteins including an IgG1 antibody (Matheus et al, 2006) and for efficient classification of microorganisms when combined with chemometrics (Timmins et al, 1998;Winder et al, 2004).…”