Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning

Autores
Luna, Martín Francisco; Mione, Federico Martin; Martínez, Ernesto Carlos; Cruz Bournazou, M. Nicolas
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
For efficiency and reproducibility, modern biotech laboratories increasingly rely on robotic platforms to perform complex, dynamic experiments to generate informative data for bioprocess development and knowledge discovery. Furthering the goal of self-driving biolabs imposes the need of automating cognitive demanding tasks such as redesigning online an experiment to maximize information gain in the face of different sources of uncertainty including microorganism behavior, hardware failure, and noisy measurements. In this work, a reinforcement learning (RL) based formulation of the online experimental redesign problem for dynamic experiments is proposed. Simulation-based learning of a redesign policy for parallel cultivations in a high-throughput platform is discussed to provide implementation details regarding the RL agent design (perceptions and actions) and the reward function used. The simulated environment and a training workflow for sequential information control are integrated with the Proximal Policy Optimization (PPO) algorithm to learn how to modify ’on the fly’ an offline design based solely on previous observations and actions in a given experiment. Results obtained demonstrate the feasibility of using deep RL to guarantee the quality of the generated data and increase the level of automation that can be used on high-throughput platforms.
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
Fil: Mione, Federico Martin. 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
Fil: Martínez, Ernesto Carlos. 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. Technishe Universitat Berlin. Institut Fur Biotechnologie. Kunstliche Intelligenz Fur Wissensbasierte Integriete Biolabore; Alemania
Fil: Cruz Bournazou, M. Nicolas. Kunstliche Intelligenz Fur Wissensbasierte Integriete Biolabore ; Institut Fur Biotechnologie ; Technishe Universitat Berlin;
Materia
HIGH-THROUGHPUT CULTIVATION
DEEP LEARNING
DYNAMIC EXPERIMENT
ONLINE REDESIGN
REINFORCEMENT LEARNING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/281858
Acceder
id CONICETDig_59a1a19fbf62d46a794efa59d2c162c4
oai_identifier_str oai:ri.conicet.gov.ar:11336/281858
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learningLuna, Martín FranciscoMione, Federico MartinMartínez, Ernesto CarlosCruz Bournazou, M. NicolasHIGH-THROUGHPUT CULTIVATIONDEEP LEARNINGDYNAMIC EXPERIMENTONLINE REDESIGNREINFORCEMENT LEARNINGhttps://purl.org/becyt/ford/2.4https://purl.org/becyt/ford/2For efficiency and reproducibility, modern biotech laboratories increasingly rely on robotic platforms to perform complex, dynamic experiments to generate informative data for bioprocess development and knowledge discovery. Furthering the goal of self-driving biolabs imposes the need of automating cognitive demanding tasks such as redesigning online an experiment to maximize information gain in the face of different sources of uncertainty including microorganism behavior, hardware failure, and noisy measurements. In this work, a reinforcement learning (RL) based formulation of the online experimental redesign problem for dynamic experiments is proposed. Simulation-based learning of a redesign policy for parallel cultivations in a high-throughput platform is discussed to provide implementation details regarding the RL agent design (perceptions and actions) and the reward function used. The simulated environment and a training workflow for sequential information control are integrated with the Proximal Policy Optimization (PPO) algorithm to learn how to modify ’on the fly’ an offline design based solely on previous observations and actions in a given experiment. Results obtained demonstrate the feasibility of using deep RL to guarantee the quality of the generated data and increase the level of automation that can be used on high-throughput platforms.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; ArgentinaFil: Mione, Federico Martin. 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; ArgentinaFil: Martínez, Ernesto Carlos. 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. Technishe Universitat Berlin. Institut Fur Biotechnologie. Kunstliche Intelligenz Fur Wissensbasierte Integriete Biolabore; AlemaniaFil: Cruz Bournazou, M. Nicolas. Kunstliche Intelligenz Fur Wissensbasierte Integriete Biolabore ; Institut Fur Biotechnologie ; Technishe Universitat Berlin;Pergamon-Elsevier Science Ltd2025-11info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/281858Luna, Martín Francisco; Mione, Federico Martin; Martínez, Ernesto Carlos; Cruz Bournazou, M. Nicolas; Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning; Pergamon-Elsevier Science Ltd; Computers and Chemical Engineering; 206; 11-2025; 1-150098-1354CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S0098135425005034info:eu-repo/semantics/altIdentifier/doi/10.1016/j.compchemeng.2025.109500info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-03-31T14:58:25Zoai:ri.conicet.gov.ar:11336/281858instacron: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:34982026-03-31 14:58:26.12CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
title Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
spellingShingle Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
Luna, Martín Francisco
HIGH-THROUGHPUT CULTIVATION
DEEP LEARNING
DYNAMIC EXPERIMENT
ONLINE REDESIGN
REINFORCEMENT LEARNING
title_short Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
title_full Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
title_fullStr Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
title_full_unstemmed Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
title_sort Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning
dc.creator.none.fl_str_mv Luna, Martín Francisco
Mione, Federico Martin
Martínez, Ernesto Carlos
Cruz Bournazou, M. Nicolas
author Luna, Martín Francisco
author_facet Luna, Martín Francisco
Mione, Federico Martin
Martínez, Ernesto Carlos
Cruz Bournazou, M. Nicolas
author_role author
author2 Mione, Federico Martin
Martínez, Ernesto Carlos
Cruz Bournazou, M. Nicolas
author2_role author
author
author
dc.subject.none.fl_str_mv HIGH-THROUGHPUT CULTIVATION
DEEP LEARNING
DYNAMIC EXPERIMENT
ONLINE REDESIGN
REINFORCEMENT LEARNING
topic HIGH-THROUGHPUT CULTIVATION
DEEP LEARNING
DYNAMIC EXPERIMENT
ONLINE REDESIGN
REINFORCEMENT LEARNING
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.4
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv For efficiency and reproducibility, modern biotech laboratories increasingly rely on robotic platforms to perform complex, dynamic experiments to generate informative data for bioprocess development and knowledge discovery. Furthering the goal of self-driving biolabs imposes the need of automating cognitive demanding tasks such as redesigning online an experiment to maximize information gain in the face of different sources of uncertainty including microorganism behavior, hardware failure, and noisy measurements. In this work, a reinforcement learning (RL) based formulation of the online experimental redesign problem for dynamic experiments is proposed. Simulation-based learning of a redesign policy for parallel cultivations in a high-throughput platform is discussed to provide implementation details regarding the RL agent design (perceptions and actions) and the reward function used. The simulated environment and a training workflow for sequential information control are integrated with the Proximal Policy Optimization (PPO) algorithm to learn how to modify ’on the fly’ an offline design based solely on previous observations and actions in a given experiment. Results obtained demonstrate the feasibility of using deep RL to guarantee the quality of the generated data and increase the level of automation that can be used on high-throughput platforms.
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
Fil: Mione, Federico Martin. 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
Fil: Martínez, Ernesto Carlos. 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. Technishe Universitat Berlin. Institut Fur Biotechnologie. Kunstliche Intelligenz Fur Wissensbasierte Integriete Biolabore; Alemania
Fil: Cruz Bournazou, M. Nicolas. Kunstliche Intelligenz Fur Wissensbasierte Integriete Biolabore ; Institut Fur Biotechnologie ; Technishe Universitat Berlin;
description For efficiency and reproducibility, modern biotech laboratories increasingly rely on robotic platforms to perform complex, dynamic experiments to generate informative data for bioprocess development and knowledge discovery. Furthering the goal of self-driving biolabs imposes the need of automating cognitive demanding tasks such as redesigning online an experiment to maximize information gain in the face of different sources of uncertainty including microorganism behavior, hardware failure, and noisy measurements. In this work, a reinforcement learning (RL) based formulation of the online experimental redesign problem for dynamic experiments is proposed. Simulation-based learning of a redesign policy for parallel cultivations in a high-throughput platform is discussed to provide implementation details regarding the RL agent design (perceptions and actions) and the reward function used. The simulated environment and a training workflow for sequential information control are integrated with the Proximal Policy Optimization (PPO) algorithm to learn how to modify ’on the fly’ an offline design based solely on previous observations and actions in a given experiment. Results obtained demonstrate the feasibility of using deep RL to guarantee the quality of the generated data and increase the level of automation that can be used on high-throughput platforms.
publishDate 2025
dc.date.none.fl_str_mv 2025-11
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/11336/281858
Luna, Martín Francisco; Mione, Federico Martin; Martínez, Ernesto Carlos; Cruz Bournazou, M. Nicolas; Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning; Pergamon-Elsevier Science Ltd; Computers and Chemical Engineering; 206; 11-2025; 1-15
0098-1354
CONICET Digital
CONICET
url http://hdl.handle.net/11336/281858
identifier_str_mv Luna, Martín Francisco; Mione, Federico Martin; Martínez, Ernesto Carlos; Cruz Bournazou, M. Nicolas; Online redesign of dynamic experiments for high-throughput bioprocess development using deep reinforcement learning; Pergamon-Elsevier Science Ltd; Computers and Chemical Engineering; 206; 11-2025; 1-15
0098-1354
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S0098135425005034
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.compchemeng.2025.109500
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Pergamon-Elsevier Science Ltd
publisher.none.fl_str_mv Pergamon-Elsevier Science Ltd
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_ 1861214025038168064
score 12.822162

Publicaciones similares