loading page

A genome-scale metabolic network model and machine learning predict amino acid concentrations in Chinese Hamster Ovary cell cultures
  • +2
  • Song-Min Schinn,
  • Carly Morrison,
  • Wei Wei,
  • Lin Zhang,
  • Nathan Lewis
Song-Min Schinn
University of California San Diego

Corresponding Author:[email protected]

Author Profile
Carly Morrison
Pfizer Inc
Author Profile
Wei Wei
Pfizer Inc
Author Profile
Lin Zhang
Pfizer Inc
Author Profile
Nathan Lewis
University of California, San Diego
Author Profile

Abstract

The control of nutrient availability is critical to large-scale manufacturing of biotherapeutics. However, the quantification of proteinogenic amino acids is time-consuming and thus is difficult to implement for real-time in situ bioprocess control. Genome-scale metabolic models describe the metabolic conversion from media nutrients to proliferation and recombinant protein production, and therefore are a promising platform for in silico monitoring and prediction of amino acid concentrations. This potential has not been realized due to unresolved challenges: (1) the models assume an optimal and highly efficient metabolism, and therefore tend to underestimate amino acid consumption, and (2) the models assume a steady state, and therefore have a short forecast range. We address these challenges by integrating machine learning with the metabolic models. Through this we demonstrate accurate and time-course dependent prediction of individual amino acid concentration in culture medium throughout the production process. Thus, these models can be deployed to control nutrient feeding to avoid premature nutrient depletion or provide early predictions of failed bioreactor runs.
08 Sep 2020Submitted to Biotechnology and Bioengineering
09 Sep 2020Submission Checks Completed
09 Sep 2020Assigned to Editor
18 Sep 2020Reviewer(s) Assigned
12 Oct 2020Review(s) Completed, Editorial Evaluation Pending
12 Oct 2020Editorial Decision: Revise Major
24 Nov 20201st Revision Received
26 Nov 2020Submission Checks Completed
26 Nov 2020Assigned to Editor
29 Dec 2020Reviewer(s) Assigned
03 Feb 2021Review(s) Completed, Editorial Evaluation Pending
03 Feb 2021Editorial Decision: Accept
May 2021Published in Biotechnology and Bioengineering volume 118 issue 5 on pages 2118-2123. 10.1002/bit.27714