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

Hybridoma Technology01:31

Hybridoma Technology

17.1K
Hybridoma technology is used for the large-scale production of monoclonal antibodies. Monoclonal antibodies bind to only a single antigenic determinant or epitope. Such antibodies are used in research, diagnostics, and disease therapy. The hybridoma technology established in 1975 by Georges Köhler and Cesar Milstein was awarded the Nobel Prize in Medicine in 1984 for revolutionizing research and therapy.
Hybridoma Selection
Commonly used fusion techniques — electroporation,...
17.1K
Pharmacokinetic Models: Overview01:20

Pharmacokinetic Models: Overview

1.8K
Pharmacokinetic models utilize mathematical analysis to achieve a detailed quantitative understanding of a drug's life cycle within the body. They are instrumental in simulating a drug's pharmacokinetic parameters, predicting drug concentrations over time, optimizing dosage regimens, linking concentrations with pharmacologic activity, and estimating potential toxicity.
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
1.8K
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

223
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
223
Physiological Pharmacokinetic Models: Assumption with Protein Binding01:13

Physiological Pharmacokinetic Models: Assumption with Protein Binding

191
Physiological models with protein binding in pharmacokinetics offer a sophisticated approach to understanding drug disposition. These models consider drug-protein interactions, enabling them to effectively predict drug concentrations in different organs and tissues. This precision aids in accurate drug dosing, providing a significant advantage over conventional models. A key process within these models is equilibration, which ensures that drug concentrations achieve a steady state within the...
191

You might also read

Related Articles

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

Sort by
Same author

Dynamic model-based control for process variations in ion-exchange chromatography.

Journal of chromatography. A·2026
Same author

Hybrid AI/ML-mechanistic framework enables intelligent optimization of commercial biopharmaceutical downstream processing.

mAbs·2026
Same author

Modeling retention time distribution in continuous Protein A affinity capture for materials traceability and diversion: A case study with twin-column system.

Journal of chromatography. A·2026
Same author

Evolution of chromatographic modeling: From mechanistic models to hybrid models with physics-based deep learning.

Journal of chromatography. A·2025
Same author

Process optimization to remove immunoglobulin A, immunoglobulin M and prekallikrein activator for intravenous immunoglobulin G production.

Vox sanguinis·2025
Same author

[Effects of ginsenoside Rb_1 on liver FXR pathway and liver and fecal bile acid profiles in rats induced by high-fat diet based on targeted metabolomics].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2025
Same journal

Polycationic Peptide Engineering of Phage Endolysins Expands Host Range and Enhances Antibacterial and Antibiofilm Activities Against Bacillus Species.

Biotechnology and bioengineering·2026
Same journal

Artificial Intelligence-Powered Algal Biodiesel: The Future of Biofuel Production Through Data-Driven Biotechnology.

Biotechnology and bioengineering·2026
Same journal

Developing Anti-EGFR/Anti-HER2 Bifunctional Antibody for Solid Tumors by Protein Engineering.

Biotechnology and bioengineering·2026
Same journal

Bridging Organ-on-a-Chip and Omics: A Multi-Dimensional Frontier in Biomedical Research.

Biotechnology and bioengineering·2026
Same journal

Hemopexin Purification From Human Cohn Fraction IV Paste and Its Biophysical Characterization and Functional Evaluation in Sickle Cell Disease Mice.

Biotechnology and bioengineering·2026
Same journal

Characterization and Therapeutic Potential of a Novel Lytic Phage-Derived Endolysin PA16cLys Against Uropathogenic Pseudomonas aeruginosa Biofilms.

Biotechnology and bioengineering·2026
See all related articles

Related Experiment Video

Updated: Jan 7, 2026

Purification and Analytics of a Monoclonal Antibody from Chinese Hamster Ovary Cells Using an Automated Microbioreactor System
10:50

Purification and Analytics of a Monoclonal Antibody from Chinese Hamster Ovary Cells Using an Automated Microbioreactor System

Published on: May 1, 2019

15.2K

Real‑Time Model Predictive Control of Monoclonal Antibody Capture in Continuous Manufacturing Using Physics‑Informed

Si-Yuan Tang1, Yun-Hao Yuan1, Yan-Na Sun1

  • 1Manufacturing Science and Technology (MSAT), WuXi Biologics, Wuxi, Jiangsu, China.

Biotechnology and Bioengineering
|December 29, 2025
PubMed
Summary
This summary is machine-generated.

Distilled physics-informed neural networks (PINNs) accelerate Protein A chromatography optimization for continuous biomanufacturing. This AI approach enhances process control and productivity in monoclonal antibody production.

Keywords:
continuous chromatographycontinuous manufacturingmodel predictive controlperiodic counter‐current chromatographyphysics‐informed neural network

More Related Videos

Use of High-Throughput Automated Microbioreactor System for Production of Model IgG1 in CHO Cells
08:15

Use of High-Throughput Automated Microbioreactor System for Production of Model IgG1 in CHO Cells

Published on: September 28, 2018

11.4K
Activated Cross-linked Agarose for the Rapid Development of Affinity Chromatography Resins - Antibody Capture as a Case Study
07:53

Activated Cross-linked Agarose for the Rapid Development of Affinity Chromatography Resins - Antibody Capture as a Case Study

Published on: August 16, 2019

9.8K

Related Experiment Videos

Last Updated: Jan 7, 2026

Purification and Analytics of a Monoclonal Antibody from Chinese Hamster Ovary Cells Using an Automated Microbioreactor System
10:50

Purification and Analytics of a Monoclonal Antibody from Chinese Hamster Ovary Cells Using an Automated Microbioreactor System

Published on: May 1, 2019

15.2K
Use of High-Throughput Automated Microbioreactor System for Production of Model IgG1 in CHO Cells
08:15

Use of High-Throughput Automated Microbioreactor System for Production of Model IgG1 in CHO Cells

Published on: September 28, 2018

11.4K
Activated Cross-linked Agarose for the Rapid Development of Affinity Chromatography Resins - Antibody Capture as a Case Study
07:53

Activated Cross-linked Agarose for the Rapid Development of Affinity Chromatography Resins - Antibody Capture as a Case Study

Published on: August 16, 2019

9.8K

Area of Science:

  • Biotechnology
  • Chemical Engineering
  • Artificial Intelligence

Background:

  • Continuous bioprocessing using Protein A affinity chromatography offers significant advantages for monoclonal antibody (mAb) production, including increased productivity and reduced costs.
  • Real-time optimization and control of multi-column periodic counter-current chromatography (PCC) present challenges due to the computational demands of mechanistic models.

Purpose of the Study:

  • To develop and validate distilled physics-informed neural networks (PINNs) for accelerated breakthrough curve fitting and four-column PCC (4C-PCC) optimization.
  • To enhance the computational efficiency and accuracy of process optimization for continuous biomanufacturing.

Main Methods:

  • Implementation of distilled PINNs based on the general rate model (GRM) to model Protein A chromatography.
  • Comparison of PINN performance against traditional numerical methods for breakthrough curve fitting and 4C-PCC optimization.
  • Integration of PINN-accelerated GRM with model predictive control (MPC) for a lab-scale continuous manufacturing process.

Main Results:

  • Distilled PINNs achieved a ~10x speedup in optimization with a ~40% accuracy improvement compared to numerical methods.
  • A smaller PINN model offered a 22x acceleration, reducing optimization time to 1.44 seconds.
  • PINN-based MPC demonstrated robust control, achieving 35 g/L resin/h productivity and 90% resin capacity utilization under dynamic conditions.

Conclusions:

  • Distilled PINNs provide a computationally efficient and physically consistent framework for real-time optimization and control of continuous bioprocesses.
  • Integrating mechanistic models with neural networks enhances process understanding, robustness, and supports the advancement of continuous biomanufacturing.
  • This AI-driven approach is crucial for optimizing complex chromatographic processes in therapeutic protein production.