Modeling the effects of media formulated with various yeast extracts on heterologous protein production by Escherichia coli using machine learning

Abstract

This a preprint and has not been peer reviewed. Data may be preliminary.

Combined multivariate statistical and flux balance analyses uncover media bottlenecks to the growth and productivity of Chinese hamster ovary cell cultures

“…More recently, high‐throughput innovations, such as micro‐bioreactor arrays and small‐scale fully‐automated reactors, have been adopted to speed up medium development (Delouvroy et al, 2015; Rameez et al, 2014; Wilson, 2007), while real‐time analytics and diagnosis further enabled online medium adjustment (Ritacco et al, 2018). To enable a more targeted tuning of specific nutrients, metabolic flux analysis (MFA) (Xing et al, 2011) and mathematical optimization (Jones et al, 2016) have been applied, while the emergence of artificial intelligence and machine learning‐based approaches have enabled the optimization of entire medium composition (Grzesik & Warth, 2021; Zheng et al, 2017) as well as the screening of desirable supplements and components (Gosai et al, 2018; Tachibana et al, 2021). Machine learning has been further combined with genome‐scale metabolic modeling to predict the dynamic medium formulation required during cell culture (Schinn et al, 2021).…”