Self-Driving Development of Perfusion Processes for Monoclonal Antibody Production DOI

Claudio Müller,

Thomas Vuillemin,

Chethana Janardhana Gadiyar

et al.

Published: Sept. 30, 2024

It is essential to increase the number of autonomous agents bioprocess development for biopharma innovation shorten time and resource utilization in path from product process. While robotics machine learning have significantly accelerated drug discovery initial screening, later stages seen improvement only experimental automation but lack advanced computational tools planning execution. For instance, during new monoclonal antibodies, search optimal upstream conditions (feeding strategy, pH, temperature, media composition, etc.) often performed highly high-throughput (HT) mini-bioreactor systems. However, integration experiment design operation these systems remains underdeveloped. In this study, we introduce an integrated framework composed by a Bayesian algorithm, cognitive digital twin cultivation system, 24 parallel perfusion setup. The result capable 1. embedding existing process knowledge, 2. experimentation, 3. Using information similar processes, 4. Notifying events near future, 5. Autonomously operating setup reach challenging objectives. As proof concept, present results 27 days long cultivations operated software agent reaching goals as are increasing VCV maximizing viability up its end.

Language: Английский

Development of the autonomous lab system to support biotechnology research DOI Creative Commons
Keiji Fushimi, Yusuke Nakai,

Akiko Nishi

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 24, 2025

In this study, we developed the autonomous lab (ANL), which is a system based on robotics and artificial intelligence (AI) to conduct biotechnology experiments formulate scientific hypotheses. This was designed with modular devices Bayesian optimization algorithms, allowing it effectively run closed loop from culturing preprocessing, measurement, analysis, hypothesis formulation. As case used ANL optimize medium conditions for recombinant Escherichia coli strain, overproduces glutamic acid. The results demonstrated that our successfully replicated experimental techniques, such as sample preparation data improved both cell growth rate maximum growth. offers versatile scalable solution various applications in field of bioproduction, potential improve efficiency reliability processes future.

Language: Английский

Citations

0
Automated regression of bioreactor models using a Bayesian approach for parallel cultivations in robotic platforms DOI Creative Commons
Martin F. Luna, Federico M. Mione, Lucas Kaspersetz

et al.

Biochemical Engineering Journal, Journal Year: 2025, Volume and Issue: unknown, P. 109729 - 109729

Published: March 1, 2025

Language: Английский

Citations

0
Self-driving development of perfusion processes for monoclonal antibody production DOI

Claudio Müller,

Thomas Vuillemin,

Chethana Janardhana Gadiyar

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 6, 2024

Abstract It is essential to increase the number of autonomous agents bioprocess development for biopharma innovation shorten time and resource utilization in path from product process. While robotics machine learning have significantly accelerated drug discovery initial screening, later stages seen improvement only experimental automation but lack advanced computational tools planning execution. For instance, during new monoclonal antibodies, search optimal upstream conditions (feeding strategy, pH, temperature, media composition, etc.) often performed highly high-throughput (HT) mini-bioreactor systems. However, integration experiment design operation these systems remains underdeveloped. In this study, we introduce an integrated framework composed by a Bayesian algorithm, cognitive digital twin cultivation system, 24 parallel perfusion setup. The result capable 1. embedding existing process knowledge, 2. experimentation, 3. Using information similar processes, 4. Notifying events near future, 5. Autonomously operating setup reach challenging objectives. As proof concept, present results 27 days long cultivations operated software agent reaching goals as are increasing VCV maximizing viability up its end.

Language: Английский

Citations

0
Self-Driving Development of Perfusion Processes for Monoclonal Antibody Production DOI

Claudio Müller,

Thomas Vuillemin,

Chethana Janardhana Gadiyar

et al.

Published: Sept. 30, 2024

It is essential to increase the number of autonomous agents bioprocess development for biopharma innovation shorten time and resource utilization in path from product process. While robotics machine learning have significantly accelerated drug discovery initial screening, later stages seen improvement only experimental automation but lack advanced computational tools planning execution. For instance, during new monoclonal antibodies, search optimal upstream conditions (feeding strategy, pH, temperature, media composition, etc.) often performed highly high-throughput (HT) mini-bioreactor systems. However, integration experiment design operation these systems remains underdeveloped. In this study, we introduce an integrated framework composed by a Bayesian algorithm, cognitive digital twin cultivation system, 24 parallel perfusion setup. The result capable 1. embedding existing process knowledge, 2. experimentation, 3. Using information similar processes, 4. Notifying events near future, 5. Autonomously operating setup reach challenging objectives. As proof concept, present results 27 days long cultivations operated software agent reaching goals as are increasing VCV maximizing viability up its end.

Language: Английский

Citations

0