Hybrid Models for the simulation and prediction of chromatographic processes for protein capture

Autores
Narayanan, Harini; Seidler, Tobias; Luna, Martín Francisco; Sokolov, Michael; Morbidelli, Massimo; Butté, Alessandro
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The biopharmaceutical industries are continuously faced with the pressure to reduce the development costs and accelerate development time scales. The traditional approach of heuristic-based or platform process-based optimization is soon getting obsolete, and more generalized tools for process development and optimization are required to keep pace with the emerging trends. Thus, advanced model-based methods that can reduce the can ensure accelerated development of robust processes with minimal experiments are necessary. Though mechanistic models for chromatography are quite popular, their success is limited by the need to have accurate knowledge of adsorption isotherms and mass transfer kinetics. As an alternative, in this work, a hybrid modeling approach is proposed. Thereby, the chromatographic unit behavior is learned by a combination of neural network and mechanistic model while fitting suitable experimental breakthrough curves. Since this approach does not require identifying suitable mechanistic assumptions for all the phenomena, it can be developed with lower effort. Thus, allowing the scientists to concentrate their focus on process development. The performance of the hybrid model is compared with the mechanistic Lumped kinetic Model for in-silico data and experiments conducted on a system of industrial relevance. The flexibility of the hybrid modeling approach results in about three times higher accuracies compared to Lumped Kinetic Model. This is validated for five different isotherm models used to simulate data, with the hybrid model showing about two to three times lower prediction errors in all the cases. Not only in prediction, but we could also show that the hybrid model is more robust in extrapolating across process conditions with about three times lower error than the LKM. Additionally, it could be demonstrated that an appropriately tailored formulation of the hybrid model can be used to generate representations for the underlying principles such as adsorption equilibria and mass transfer kinetics.
Fil: Narayanan, Harini. Institute of Chemical and Bioengineering; Suiza
Fil: Seidler, Tobias. Institute of Chemical and Bioengineering; Suiza
Fil: Luna, Martín Francisco. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina. Institute of Chemical and Bioengineering; Suiza
Fil: Sokolov, Michael. No especifíca;
Fil: Morbidelli, Massimo. Politecnico di Milano; Italia
Fil: Butté, Alessandro. No especifíca;
Materia
ARTIFICIAL NEURAL NETWORK
CAPTURE
CHROMATOGRAPHY
HYBRID MODELS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/154013

id CONICETDig_980a62ac4239fc78e909bbe59c611bc9
oai_identifier_str oai:ri.conicet.gov.ar:11336/154013
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Hybrid Models for the simulation and prediction of chromatographic processes for protein captureNarayanan, HariniSeidler, TobiasLuna, Martín FranciscoSokolov, MichaelMorbidelli, MassimoButté, AlessandroARTIFICIAL NEURAL NETWORKCAPTURECHROMATOGRAPHYHYBRID MODELShttps://purl.org/becyt/ford/2.9https://purl.org/becyt/ford/2The biopharmaceutical industries are continuously faced with the pressure to reduce the development costs and accelerate development time scales. The traditional approach of heuristic-based or platform process-based optimization is soon getting obsolete, and more generalized tools for process development and optimization are required to keep pace with the emerging trends. Thus, advanced model-based methods that can reduce the can ensure accelerated development of robust processes with minimal experiments are necessary. Though mechanistic models for chromatography are quite popular, their success is limited by the need to have accurate knowledge of adsorption isotherms and mass transfer kinetics. As an alternative, in this work, a hybrid modeling approach is proposed. Thereby, the chromatographic unit behavior is learned by a combination of neural network and mechanistic model while fitting suitable experimental breakthrough curves. Since this approach does not require identifying suitable mechanistic assumptions for all the phenomena, it can be developed with lower effort. Thus, allowing the scientists to concentrate their focus on process development. The performance of the hybrid model is compared with the mechanistic Lumped kinetic Model for in-silico data and experiments conducted on a system of industrial relevance. The flexibility of the hybrid modeling approach results in about three times higher accuracies compared to Lumped Kinetic Model. This is validated for five different isotherm models used to simulate data, with the hybrid model showing about two to three times lower prediction errors in all the cases. Not only in prediction, but we could also show that the hybrid model is more robust in extrapolating across process conditions with about three times lower error than the LKM. Additionally, it could be demonstrated that an appropriately tailored formulation of the hybrid model can be used to generate representations for the underlying principles such as adsorption equilibria and mass transfer kinetics.Fil: Narayanan, Harini. Institute of Chemical and Bioengineering; SuizaFil: Seidler, Tobias. Institute of Chemical and Bioengineering; SuizaFil: Luna, Martín Francisco. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina. Institute of Chemical and Bioengineering; SuizaFil: Sokolov, Michael. No especifíca;Fil: Morbidelli, Massimo. Politecnico di Milano; ItaliaFil: Butté, Alessandro. No especifíca;Elsevier Science2021-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/154013Narayanan, Harini; Seidler, Tobias; Luna, Martín Francisco; Sokolov, Michael; Morbidelli, Massimo; et al.; Hybrid Models for the simulation and prediction of chromatographic processes for protein capture; Elsevier Science; Journal of Chromatography - A; 1650; 8-2021; 1-120021-96731873-3778CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.chroma.2021.462248info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S0021967321003721info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:10:05Zoai:ri.conicet.gov.ar:11336/154013instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:10:05.277CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
title Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
spellingShingle Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
Narayanan, Harini
ARTIFICIAL NEURAL NETWORK
CAPTURE
CHROMATOGRAPHY
HYBRID MODELS
title_short Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
title_full Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
title_fullStr Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
title_full_unstemmed Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
title_sort Hybrid Models for the simulation and prediction of chromatographic processes for protein capture
dc.creator.none.fl_str_mv Narayanan, Harini
Seidler, Tobias
Luna, Martín Francisco
Sokolov, Michael
Morbidelli, Massimo
Butté, Alessandro
author Narayanan, Harini
author_facet Narayanan, Harini
Seidler, Tobias
Luna, Martín Francisco
Sokolov, Michael
Morbidelli, Massimo
Butté, Alessandro
author_role author
author2 Seidler, Tobias
Luna, Martín Francisco
Sokolov, Michael
Morbidelli, Massimo
Butté, Alessandro
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv ARTIFICIAL NEURAL NETWORK
CAPTURE
CHROMATOGRAPHY
HYBRID MODELS
topic ARTIFICIAL NEURAL NETWORK
CAPTURE
CHROMATOGRAPHY
HYBRID MODELS
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.9
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv The biopharmaceutical industries are continuously faced with the pressure to reduce the development costs and accelerate development time scales. The traditional approach of heuristic-based or platform process-based optimization is soon getting obsolete, and more generalized tools for process development and optimization are required to keep pace with the emerging trends. Thus, advanced model-based methods that can reduce the can ensure accelerated development of robust processes with minimal experiments are necessary. Though mechanistic models for chromatography are quite popular, their success is limited by the need to have accurate knowledge of adsorption isotherms and mass transfer kinetics. As an alternative, in this work, a hybrid modeling approach is proposed. Thereby, the chromatographic unit behavior is learned by a combination of neural network and mechanistic model while fitting suitable experimental breakthrough curves. Since this approach does not require identifying suitable mechanistic assumptions for all the phenomena, it can be developed with lower effort. Thus, allowing the scientists to concentrate their focus on process development. The performance of the hybrid model is compared with the mechanistic Lumped kinetic Model for in-silico data and experiments conducted on a system of industrial relevance. The flexibility of the hybrid modeling approach results in about three times higher accuracies compared to Lumped Kinetic Model. This is validated for five different isotherm models used to simulate data, with the hybrid model showing about two to three times lower prediction errors in all the cases. Not only in prediction, but we could also show that the hybrid model is more robust in extrapolating across process conditions with about three times lower error than the LKM. Additionally, it could be demonstrated that an appropriately tailored formulation of the hybrid model can be used to generate representations for the underlying principles such as adsorption equilibria and mass transfer kinetics.
Fil: Narayanan, Harini. Institute of Chemical and Bioengineering; Suiza
Fil: Seidler, Tobias. Institute of Chemical and Bioengineering; Suiza
Fil: Luna, Martín Francisco. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina. Institute of Chemical and Bioengineering; Suiza
Fil: Sokolov, Michael. No especifíca;
Fil: Morbidelli, Massimo. Politecnico di Milano; Italia
Fil: Butté, Alessandro. No especifíca;
description The biopharmaceutical industries are continuously faced with the pressure to reduce the development costs and accelerate development time scales. The traditional approach of heuristic-based or platform process-based optimization is soon getting obsolete, and more generalized tools for process development and optimization are required to keep pace with the emerging trends. Thus, advanced model-based methods that can reduce the can ensure accelerated development of robust processes with minimal experiments are necessary. Though mechanistic models for chromatography are quite popular, their success is limited by the need to have accurate knowledge of adsorption isotherms and mass transfer kinetics. As an alternative, in this work, a hybrid modeling approach is proposed. Thereby, the chromatographic unit behavior is learned by a combination of neural network and mechanistic model while fitting suitable experimental breakthrough curves. Since this approach does not require identifying suitable mechanistic assumptions for all the phenomena, it can be developed with lower effort. Thus, allowing the scientists to concentrate their focus on process development. The performance of the hybrid model is compared with the mechanistic Lumped kinetic Model for in-silico data and experiments conducted on a system of industrial relevance. The flexibility of the hybrid modeling approach results in about three times higher accuracies compared to Lumped Kinetic Model. This is validated for five different isotherm models used to simulate data, with the hybrid model showing about two to three times lower prediction errors in all the cases. Not only in prediction, but we could also show that the hybrid model is more robust in extrapolating across process conditions with about three times lower error than the LKM. Additionally, it could be demonstrated that an appropriately tailored formulation of the hybrid model can be used to generate representations for the underlying principles such as adsorption equilibria and mass transfer kinetics.
publishDate 2021
dc.date.none.fl_str_mv 2021-08
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/154013
Narayanan, Harini; Seidler, Tobias; Luna, Martín Francisco; Sokolov, Michael; Morbidelli, Massimo; et al.; Hybrid Models for the simulation and prediction of chromatographic processes for protein capture; Elsevier Science; Journal of Chromatography - A; 1650; 8-2021; 1-12
0021-9673
1873-3778
CONICET Digital
CONICET
url http://hdl.handle.net/11336/154013
identifier_str_mv Narayanan, Harini; Seidler, Tobias; Luna, Martín Francisco; Sokolov, Michael; Morbidelli, Massimo; et al.; Hybrid Models for the simulation and prediction of chromatographic processes for protein capture; Elsevier Science; Journal of Chromatography - A; 1650; 8-2021; 1-12
0021-9673
1873-3778
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1016/j.chroma.2021.462248
info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S0021967321003721
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier Science
publisher.none.fl_str_mv Elsevier Science
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613986217099264
score 13.070432