Hybrid deep modeling of a CHO-K1 fed-batch process: combining first-principles with deep neural networks

• Published in: Frontiers in bioengineering and biotechnology Vol. 11; p. 1237963
• Main Authors: Pinto, José, Ramos, João R. C., Costa, Rafael S., Rossell, Sergio, Dumas, Patrick, Oliveira, Rui
• Format: Journal Article
• Language: English
• Published: Frontiers Media S.A 08-09-2023
• Subjects: ADAM; Bioengineering and Biotechnology; CHO-K1 cells; deep neural networks; first-principles; hybrid modeling; stochastic regularization
• ISSN: 2296-4185; 2296-4185
• DOI: 10.3389/fbioe.2023.1237963

Introduction:
Hybrid modeling combining First-Principles with machine learning is becoming a pivotal methodology for Biopharma 4.0 enactment. Chinese Hamster Ovary (CHO) cells, being the workhorse for industrial glycoproteins production, have been the object of several hybrid modeling studies. Most previous studies pursued a shallow hybrid modeling approach based on three-layered Feedforward Neural Networks (FFNNs) combined with macroscopic material balance equations. Only recently, the hybrid modeling field is incorporating deep learning into its framework with significant gains in descriptive and predictive power.
Methods:
This study compares, for the first time, deep and shallow hybrid modeling in a CHO process development context. Data of 24 fed-batch cultivations of a CHO-K1 cell line expressing a target glycoprotein, comprising 30 measured state variables over time, were used to compare both methodologies. Hybrid models with varying FFNN depths (3-5 layers) were systematically compared using two training methodologies. The classical training is based on the Levenberg-Marquardt algorithm, indirect sensitivity equations and cross-validation. The deep learning is based on the Adaptive Moment Estimation Method (ADAM), stochastic regularization and semidirect sensitivity equations.
Results and conclusion:
The results point to a systematic generalization improvement of deep hybrid models over shallow hybrid models. Overall, the training and testing errors decreased by 14.0% and 23.6% respectively when applying the deep methodology. The Central Processing Unit (CPU) time for training the deep hybrid model increased by 31.6% mainly due to the higher FFNN complexity. The final deep hybrid model is shown to predict the dynamics of the 30 state variables within the error bounds in every test experiment. Notably, the deep hybrid model could predict the metabolic shifts in key metabolites (e.g., lactate, ammonium, glutamine and glutamate) in the test experiments. We expect deep hybrid modeling to accelerate the deployment of high-fidelity digital twins in the biopharma sector in the near future.