Machine Learning (ML) and Artificial Intelligence (AI) have advanced all aspects of bioprocessing, including cell culture, process optimization, downstream processing, and digital technologies (Process Analytical Technology, control automation systems, etc) associated with the process. From chemometrics to deep learning, the advancement of AI technologies has deeply transformed bioprocess development from research labs to industry. Moreover, hybrid methods are increasingly applied to complement mechanistic bioprocess models (hydrodynamics, mass transfer) with data-driven research (material properties, adsorption isotherms, cell metabolism, etc).
The aim of this Research Topic is to explore the most recent technological advances (e.g. software libraries, Process Analytical Technologies (PAT) integration) and methodological developments (e.g. surrogate modeling, Bayesian optimization, reduced-order modeling) in the use of AI and ML in bioprocessing. Specifically, this Research Topic covers the AI and ML applications in the following aspects, Quality by Design (QbD), Digital Twins and model predictive control, host selection and design, process development and optimization, scale-up and integration, monitoring and control to enhance industrial bioprocesses. We further welcome contributions that involve the development of hybrid mechanistic/data-driven approaches and the application of AI for enabling the shift to continuous biomanufacturing, such as in the context of fault detection and continuous process verification.
This Research Topic welcomes Original Research and Review articles that cover themes including, but not limited to, the following areas:
• Machine learning algorithm development from conventional chemometrics to state-of-the-art deep learning and natural language processing
• Hybrid mechanistic and data-driven modeling
• Applications of AI in various areas of bioprocessing including cell line development and engineering, cell culture and media design, upstream process design and optimization, automation control, downstream processing and online monitoring of products and strains.
• Applications of ML and AI on industrial scale bioprocesses
• Use of AI and ML with other digital technologies (QbD, Digital Twins, Model-predictive control)
• Integration of PAT, algorithms for PAT signal processing and analytical design space identification
• Application of AI/ML technologies in automated data annotation and processing in the context of Critical Process Parameter (CPP) and critical quality attribute (CQA) fingerprinting.
(Dr Mengxing Li is employed by InsightIn Health, Baltimore, USA and Dr Christos Varsakelis is employed by Janssen Pharmaceuticals, Belgium. The Topic Editors declare no competing interests in regards to the Research Topic subject.)
Machine Learning (ML) and Artificial Intelligence (AI) have advanced all aspects of bioprocessing, including cell culture, process optimization, downstream processing, and digital technologies (Process Analytical Technology, control automation systems, etc) associated with the process. From chemometrics to deep learning, the advancement of AI technologies has deeply transformed bioprocess development from research labs to industry. Moreover, hybrid methods are increasingly applied to complement mechanistic bioprocess models (hydrodynamics, mass transfer) with data-driven research (material properties, adsorption isotherms, cell metabolism, etc).
The aim of this Research Topic is to explore the most recent technological advances (e.g. software libraries, Process Analytical Technologies (PAT) integration) and methodological developments (e.g. surrogate modeling, Bayesian optimization, reduced-order modeling) in the use of AI and ML in bioprocessing. Specifically, this Research Topic covers the AI and ML applications in the following aspects, Quality by Design (QbD), Digital Twins and model predictive control, host selection and design, process development and optimization, scale-up and integration, monitoring and control to enhance industrial bioprocesses. We further welcome contributions that involve the development of hybrid mechanistic/data-driven approaches and the application of AI for enabling the shift to continuous biomanufacturing, such as in the context of fault detection and continuous process verification.
This Research Topic welcomes Original Research and Review articles that cover themes including, but not limited to, the following areas:
• Machine learning algorithm development from conventional chemometrics to state-of-the-art deep learning and natural language processing
• Hybrid mechanistic and data-driven modeling
• Applications of AI in various areas of bioprocessing including cell line development and engineering, cell culture and media design, upstream process design and optimization, automation control, downstream processing and online monitoring of products and strains.
• Applications of ML and AI on industrial scale bioprocesses
• Use of AI and ML with other digital technologies (QbD, Digital Twins, Model-predictive control)
• Integration of PAT, algorithms for PAT signal processing and analytical design space identification
• Application of AI/ML technologies in automated data annotation and processing in the context of Critical Process Parameter (CPP) and critical quality attribute (CQA) fingerprinting.
(Dr Mengxing Li is employed by InsightIn Health, Baltimore, USA and Dr Christos Varsakelis is employed by Janssen Pharmaceuticals, Belgium. The Topic Editors declare no competing interests in regards to the Research Topic subject.)