Developing global regression models for metabolite concentration prediction regardless of cell line

Abstract

Following the Process Analytical Technology (PAT) of the Food and Drug Administration (FDA), drug manufacturers are encouraged to develop innovative techniques in order to monitor and understand their processes in a better way. Within this framework, it has been demonstrated that Raman spectroscopy coupled with chemometric tools allow to predict critical parameters of mammalian cell cultures in-line and in real time. However, the development of robust and predictive regression models clearly requires many batches in order to take into account inter-batch variability and enhance models accuracy. Nevertheless, this heavy procedure has to be repeated for every new line of cell culture involving many resources. This is why we propose in this paper to develop global regression models taking into account different cell lines. Such models are finally transferred to any culture of the cells involved. This article first demonstrates the feasibility of developing regression models, not only for mammalian cell lines (CHO and HeLa cell cultures), but also for insect cell lines (Sf9 cell cultures). Then global regression models are generated, based on CHO cells, HeLa cells, and Sf9 cells. Finally, these models are evaluated considering a fourth cell line(HEK cells). In addition to suitable predictions of glucose and lactate concentration of HEK cell cultures, we expose that by adding a single HEK-cell culture to the calibration set, the predictive ability of the regression models are substantially increased. In this way, we demonstrate that using global models, it is not necessary to consider many cultures of a new cell line in order to obtain accurate models. Biotechnol. Bioeng. 2017;114: 2550-2559. © 2017 Wiley Periodicals, Inc.

Development of an on-line Raman spectral analytical method for monitoring and endpoint determination of the Cornu Caprae Hircus hydrolysis process

“…Amino acids such as Gly, His, Lys, Met, Phe, Pro, Ser, Thr and Val had bands in the region of 1025–1065 cm −1 . In addition, Raman shifts with VIP values larger than 1 were also observed in the fingerprint region of organic compounds (350–1775 cm −1 ) . However, due to the physicochemical complexity of the hydrolysis process samples, there is still possibility that these calibration models did not rely on direct spectral information from the analytes (i.e.…”

A machine‐learning approach to calibrate generic Raman models for real‐time monitoring of cell culture processes

“…While the VCD predictions for the new cell line were accurate, glucose, and lactate predictions exhibited offsets at higher concentrations (see figure in Mehdizadeh et al, ). Recently, André et al () proposed a generic model for multiple cell hosts by calibrating a glucose and a lactate on three host cells–CHO, Spodoptera frugiperda Sf9, and HeLa. The calibrated models were then validated on a fourth host cell, HEK‐293.…”

Automatic real‐time calibration, assessment, and maintenance of generic Raman models for online monitoring of cell culture processes

“…For example, Whelan et al () and Berry et al () proposed Raman models for metabolite concentrations that are independent of the volume of the bioreactor used in cell culture experiments. Similarly, Mehdizadeh et al () proposed Raman models that are generic with respect to cell lines and André et al () and Webster et al () proposed Raman models that are generic with respect to cell hosts.…”