Extensive evaluation of machine learning models and data preprocessings for Raman modeling in bioprocessing. (7th July 2022)

• Record Type: Journal Article
• Authors: Poth, Michaela; Magill, Gordon; Filgertshofer, Alois; Popp, Oliver; Großkopf, Tobias
• Is Part Of: Journal of Raman spectroscopy. Volume 53:Number 9(2022)
• Page Start: 1580
• Page End: 1591
• Publication Date: 2022-07-07
• Subjects: bioprocess analytics -- CHO metabolites -- data preprocessing -- machine learning -- Raman spectroscopy; Raman spectroscopy -- Periodicals; 535.846
• DOI: 10.1002/jrs.6402
• Languages: English
• ISSNs: 0377-0486

Abstract

Abstract: Raman spectroscopy is a very promising tool for monitoring key analytes in mammalian cell culture fermentations in real time. However, major challenges are associated with this promising technology in aqueous bioprocessing matrixes such as a strong background fluorescence, which is typically addressed by computational preprocessing of the raw Raman spectra. In this study, we present an extensive combinatorial assessment of various machine learning algorithms with numerous popular preprocessing methods on the performance and robustness of Raman‐based real‐time predictions of key analytes. We show that preprocessing methods have a large influence on algorithmic performance. Furthermore, there is a large variance across the various combinations of preprocessing steps and tested machine learning regression algorithms. We demonstrate that neural networks and random forest regression show very good performance and robustness across different, bioprocess relevant analytes. They significantly outperform partial least squares regression, the most widely used regression algorithm in the field. Overall, this extensive study provides a sound basis for building robust, next‐generation models for monitoring analytes in real time based on Raman spectroscopy. Abstract : We show that preprocessing methods have a large influence on algorithmic performance when analyzing Raman spectral data. Furthermore, there is a large variance across the various combinations of preprocessing steps and tested machine learning regression algorithms. We demonstrate that neural networks and random forest regression show very good performance and robustness across different, bioprocess relevant analytes and significantly outperform partial least squares regression, the most widely used regression algorithm in the field.