Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Bioreactor Controls-III01:22

Bioreactor Controls-III

Strain improvement is a foundational strategy in industrial microbiology aimed at maximizing microbial productivity, particularly because natural isolates typically yield commercially valuable products in very low concentrations. Although optimizing the culture medium and environmental conditions can improve yields, these adjustments are inherently limited by the organism’s genetic potential. As a result, the focus shifts toward genetic modifications to enhance biosynthetic capacity. The...
Upstream Processing01:27

Upstream Processing

Upstream processing represents a critical phase in biomanufacturing, wherein biological systems such as microorganisms, mammalian cells, or insect cells are cultivated to produce therapeutic proteins, vaccines, enzymes, or other biologically derived products. This phase encompasses all steps from the selection and genetic manipulation of the production organism to the cultivation of cells in bioreactors under tightly controlled environmental conditions.Host Selection and Genetic OptimizationThe...
Batch vs Continuous Culture01:14

Batch vs Continuous Culture

Fermentation is a foundational biotechnological process used to produce pharmaceuticals, biofuels, enzymes, and food additives. Among industrial strategies, batch and continuous fermentation are the two most widely applied. Although both rely on microbial conversion of substrates into desired products, they differ markedly in operation, productivity, and suitability for specific applications.Batch fermentation occurs in a closed system in which nutrient media and inoculum are added at the...
Fed-Batch Culture01:23

Fed-Batch Culture

Fed-batch culture is a widely used bioprocessing strategy combining aspects of batch culture with controlled substrate feeding to optimize cell growth and product formation. In this semi-closed system, nutrients are strategically added during fermentation, while the accumulated products and biomass remain within the bioreactor until the end of the operation. This controlled addition of substrates allows for better management of growth kinetics, nutrient limitation, and metabolite...
Enzyme Kinetics01:19

Enzyme Kinetics

Enzymes speed up reactions by lowering the activation energy of the reactants. The speed at which the enzyme turns reactants into products is called the rate of reaction. Several factors impact the rate of reaction, including the number of available reactants. Enzyme kinetics is the study of how an enzyme changes the rate of a reaction.
Scientists typically study enzyme kinetics with a fixed amount of enzyme in the controlled environment of a test tube. When more reactant, or substrate, is...
Designing Growth Media for Bioreactors01:30

Designing Growth Media for Bioreactors

Growth media provide essential nutrients that support cell growth and metabolism, thereby enhancing the yield of valuable products such as enzymes, antibiotics, and biomass. Designing an effective growth medium involves balancing all components to prevent nutrient limitations or toxic excesses, both of which can impair growth and reduce product yields.Composition of a Typical Growth MediumA typical growth medium contains carbon and nitrogen sources, salts, vitamins, trace elements, and...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Rapid Affinity Characterization of Cell-Free Expressed Nanobodies Directly in Lysate with Biolayer Interferometry via Antigen-Immobilized Biosensors.

ACS synthetic biology·2026
Same author

High-Throughput FRET Affinity Screening Technique (HTFAST) For Cell-Free Expressed Binding Protein Characterization.

bioRxiv : the preprint server for biology·2026
Same author

SMART sensors for cell growth monitoring in closed system G-Rex for scalable, cost-conscious cell and gene therapy manufacturing.

Cytotherapy·2026
Same author

Rapid Cell-Free Combinatorial Mutagenesis Workflow Using Small Oligos Suitable for High-Iteration, Active Learning-Guided Protein Engineering.

bioRxiv : the preprint server for biology·2025
Same author

Conjugation Strategies for Low Solubility Proteins to Single-Walled Carbon Nanotubes as a Sensitive Fluorescent Assay to Protease Activity.

Advanced materials interfaces·2025
Same author

Single-Walled Carbon Nanotube Probes for Protease Characterization Directly in Cell-Free Expression Reactions.

Analytical chemistry·2025

Related Experiment Video

Updated: May 14, 2026

Generic Protocol for Optimization of Heterologous Protein Production Using Automated Microbioreactor Technology
06:24

Generic Protocol for Optimization of Heterologous Protein Production Using Automated Microbioreactor Technology

Published on: December 15, 2017

Dynamic, Unconstrained Optimization of Secreted Enzyme Production in Fed-Batch Fermentation Using Reinforcement

Sai Harish Uthravalli1, Sakib Ferdous2, J Michael Hess3

  • 1Department of Computer Science, College of Liberal Arts and Sciences, Iowa State University, Ames, Iowa, USA.

Biotechnology and Bioengineering
|May 13, 2026
PubMed
Summary
This summary is machine-generated.

Reinforcement learning (RL) enhances fed-batch fermentation control for maximizing enzyme production. The Soft Actor-Critic algorithm proved more effective than Proximal Policy Optimization, showing robustness against process variations.

Keywords:
Aspergillus nigerPPOSACfed‐Batch fermentationfermentationglucoamylasein‐silico simulationreinforcement learningΜonod model

More Related Videos

Light-Controlled Fermentations for Microbial Chemical and Protein Production
08:37

Light-Controlled Fermentations for Microbial Chemical and Protein Production

Published on: March 22, 2022

Procedure for Adaptive Laboratory Evolution of Microorganisms Using a Chemostat
06:03

Procedure for Adaptive Laboratory Evolution of Microorganisms Using a Chemostat

Published on: September 20, 2016

Related Experiment Videos

Last Updated: May 14, 2026

Generic Protocol for Optimization of Heterologous Protein Production Using Automated Microbioreactor Technology
06:24

Generic Protocol for Optimization of Heterologous Protein Production Using Automated Microbioreactor Technology

Published on: December 15, 2017

Light-Controlled Fermentations for Microbial Chemical and Protein Production
08:37

Light-Controlled Fermentations for Microbial Chemical and Protein Production

Published on: March 22, 2022

Procedure for Adaptive Laboratory Evolution of Microorganisms Using a Chemostat
06:03

Procedure for Adaptive Laboratory Evolution of Microorganisms Using a Chemostat

Published on: September 20, 2016

Area of Science:

  • Biotechnology
  • Biochemical Engineering
  • Artificial Intelligence

Background:

  • Fed-batch fermentation is crucial for producing enzymes like glucoamylase but is sensitive to process variations and initial conditions.
  • Traditional control methods struggle with unconstrained product maximization and process perturbations.
  • Reinforcement learning (RL) offers a promising approach for dynamic process control in complex biological systems.

Purpose of the Study:

  • To develop and evaluate a reinforcement learning (RL) agent for unconstrained product maximization in Aspergillus niger fed-batch fermentation.
  • To compare the performance of different RL algorithms (PPO and SAC) and assess their robustness to process perturbations.
  • To benchmark the RL controller against traditional model-free methods and evaluate its adaptability to new cell types.

Main Methods:

  • A digital twin of Aspergillus niger fed-batch fermentation was created using the Monod model and literature parameters.
  • Reinforcement learning agents (PPO and SAC) were trained on this digital environment, using state variables like run time, cell concentration, and enzyme activity.
  • The RL controller's performance was compared to a Bayesian optimization-based model-free controller and tested against simulated process perturbations and new cell types.

Main Results:

  • Soft Actor-Critic (SAC) demonstrated superior performance, reaching 95% of maximum quality within 2400 episodes, outperforming Proximal Policy Optimization (PPO).
  • The RL controller maintained higher enzyme production than the traditional controller, even when faced with simulated process perturbations like faulty pumps or variations in cell growth.
  • The in silico trained RL agent showed good performance on new cell types without updates and improved with retraining, indicating adaptability.

Conclusions:

  • Reinforcement learning, particularly the SAC algorithm, provides a robust and effective method for optimizing fed-batch fermentation and maximizing enzyme production.
  • RL controllers exhibit greater resilience to process variations and perturbations compared to traditional model-free controllers.
  • In silico training followed by targeted experimental updates allows for the development of adaptable and high-performing RL agents for bioprocess control.