Data-driven and Physics Informed Modelling of Chinese Hamster Ovary Cell Bioreactors

TL;DR

This paper introduces a hybrid modeling approach combining physical laws and machine learning to accurately model CHO cell bioreactors, addressing limitations of traditional flux balance analysis.

Contribution

It proposes a physically-informed data-driven hybrid model that learns bioreactor dynamics, estimates unknown parameters, and models kinetic expressions using differentiable optimization layers.

Findings

Successfully integrates physical laws with ML for bioreactor modeling

Enables parameter estimation and kinetic expression learning

Improves model accuracy over traditional methods

Abstract

Fed-batch culture is an established operation mode for the production of biologics using mammalian cell cultures. Quantitative modeling integrates both kinetics for some key reaction steps and optimization-driven metabolic flux allocation, using flux balance analysis; this is known to lead to certain mathematical inconsistencies. Here, we propose a physically-informed data-driven hybrid model (a "gray box") to learn models of the dynamical evolution of Chinese Hamster Ovary (CHO) cell bioreactors from process data. The approach incorporates physical laws (e.g. mass balances) as well as kinetic expressions for metabolic fluxes. Machine learning (ML) is then used to (a) directly learn evolution equations (black-box modelling); (b) recover unknown physical parameters ("white-box" parameter fitting) or -- importantly -- (c) learn partially unknown kinetic expressions (gray-box modelling). We encode the convex optimization step of the overdetermined metabolic biophysical system as a differentiable, feed-forward layer into our architectures, connecting partial physical knowledge with data-driven machine learning.