From titer to quality: exploring reinforcement learning for bioprocess control in silico
File(s)
Published version
Author(s)
Monteiro, Mariana
Flevaris, Konstantinos
Kontoravdi, Cleo
Type
Journal Article
Abstract
The production of monoclonal antibodies in mammalian cells is a highly
complex and nonlinear process. The industry standard for controlling this
process fails to capture its complex dynamics, leading to batch-to-batch vari ability. This inherent complexity makes bioprocesses challenging to model
purely mechanistically, while the lack of rich experimental datasets and the
need for interpretability in control policies further prevent the use of fully
data-driven solutions. We propose a hybrid methodology for optimising the
nutrient feeding strategy that leverages Reinforcement Learning (RL) with
mechanistic models of cellular metabolism and glycosylation. The RL agent
is trained using an off-policy method for data efficiency and is capable of
learning from partial observations of the state, which allows for improved
generalization. The controller is adaptable to processes with or without addi tional product quality considerations, such as glycosylation. We demonstrate
that accounting for product glycosylation yields different control strategies
whereas neglecting it to focus on titer alone can compromise product quality.
The continuous learning abilities of the proposed method ensure adaptability
in response to process changes, while the inclusion of a mechanistic model in
the environment aids in the interpretability of the learned control actions.
complex and nonlinear process. The industry standard for controlling this
process fails to capture its complex dynamics, leading to batch-to-batch vari ability. This inherent complexity makes bioprocesses challenging to model
purely mechanistically, while the lack of rich experimental datasets and the
need for interpretability in control policies further prevent the use of fully
data-driven solutions. We propose a hybrid methodology for optimising the
nutrient feeding strategy that leverages Reinforcement Learning (RL) with
mechanistic models of cellular metabolism and glycosylation. The RL agent
is trained using an off-policy method for data efficiency and is capable of
learning from partial observations of the state, which allows for improved
generalization. The controller is adaptable to processes with or without addi tional product quality considerations, such as glycosylation. We demonstrate
that accounting for product glycosylation yields different control strategies
whereas neglecting it to focus on titer alone can compromise product quality.
The continuous learning abilities of the proposed method ensure adaptability
in response to process changes, while the inclusion of a mechanistic model in
the environment aids in the interpretability of the learned control actions.
Date Issued
2026-02-01
Date Acceptance
2025-10-12
Citation
Computers and Chemical Engineering, 2026, 205 (Part 1)
ISSN
0098-1354
Publisher
Elsevier
Journal / Book Title
Computers and Chemical Engineering
Volume
205
Issue
Part 1
Copyright Statement
© 2025 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
License URL
Publication Status
Published
Article Number
109452
Date Publish Online
2025-10-15