Hyperbox Mixture Regression for process performance prediction in antibody production

This paper addresses the challenges of predicting bioprocess performance, particularly in monoclonal antibody (mAb) production, where conventional statistical methods often fall short due to time-series data’s complexity and high dimensionality. We propose a novel Hyperbox Mixture Regression (HMR) m...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Nik-Khorasani, Thanh Tung Khuat, Bogdan Gabrys
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Digital Chemical Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772508125000055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850192707948904448
author Ali Nik-Khorasani
Thanh Tung Khuat
Bogdan Gabrys
author_facet Ali Nik-Khorasani
Thanh Tung Khuat
Bogdan Gabrys
author_sort Ali Nik-Khorasani
collection DOAJ
description This paper addresses the challenges of predicting bioprocess performance, particularly in monoclonal antibody (mAb) production, where conventional statistical methods often fall short due to time-series data’s complexity and high dimensionality. We propose a novel Hyperbox Mixture Regression (HMR) model that employs hyperbox-based input space partitioning to enhance predictive accuracy while managing uncertainty inherent in bioprocess data. The HMR model is designed to dynamically generate hyperboxes for input samples in a single-pass process, thereby improving learning speed and reducing computational complexity. Our experimental study utilizes a dataset that contains 106 bioreactors. This study evaluates the model’s performance in predicting critical quality attributes in monoclonal antibody manufacturing over a 15-day cultivation period. The results demonstrate that the HMR model outperforms comparable approximators in accuracy and learning speed and maintains interpretability and robustness under uncertain conditions. These findings underscore the potential of HMR as a powerful tool for enhancing predictive analytics in bioprocessing applications.
format Article
id doaj-art-dedabece25684501a71520e1f21f42df
institution OA Journals
issn 2772-5081
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Digital Chemical Engineering
spelling doaj-art-dedabece25684501a71520e1f21f42df2025-08-20T02:14:28ZengElsevierDigital Chemical Engineering2772-50812025-03-011410022110.1016/j.dche.2025.100221Hyperbox Mixture Regression for process performance prediction in antibody productionAli Nik-Khorasani0Thanh Tung Khuat1Bogdan Gabrys2Department of Electrical Engineering, Ferdowsi University of Mashhad, Mashhad, IranComplex Adaptive Systems Laboratory, Data Science Institute, University of Technology Sydney, Sydney, Australia; Corresponding author.Complex Adaptive Systems Laboratory, Data Science Institute, University of Technology Sydney, Sydney, AustraliaThis paper addresses the challenges of predicting bioprocess performance, particularly in monoclonal antibody (mAb) production, where conventional statistical methods often fall short due to time-series data’s complexity and high dimensionality. We propose a novel Hyperbox Mixture Regression (HMR) model that employs hyperbox-based input space partitioning to enhance predictive accuracy while managing uncertainty inherent in bioprocess data. The HMR model is designed to dynamically generate hyperboxes for input samples in a single-pass process, thereby improving learning speed and reducing computational complexity. Our experimental study utilizes a dataset that contains 106 bioreactors. This study evaluates the model’s performance in predicting critical quality attributes in monoclonal antibody manufacturing over a 15-day cultivation period. The results demonstrate that the HMR model outperforms comparable approximators in accuracy and learning speed and maintains interpretability and robustness under uncertain conditions. These findings underscore the potential of HMR as a powerful tool for enhancing predictive analytics in bioprocessing applications.http://www.sciencedirect.com/science/article/pii/S2772508125000055Bioprocess performance predictionNeuro-Fuzzy systemHyperboxRegressionMonoclonal antibodies
spellingShingle Ali Nik-Khorasani
Thanh Tung Khuat
Bogdan Gabrys
Hyperbox Mixture Regression for process performance prediction in antibody production
Digital Chemical Engineering
Bioprocess performance prediction
Neuro-Fuzzy system
Hyperbox
Regression
Monoclonal antibodies
title Hyperbox Mixture Regression for process performance prediction in antibody production
title_full Hyperbox Mixture Regression for process performance prediction in antibody production
title_fullStr Hyperbox Mixture Regression for process performance prediction in antibody production
title_full_unstemmed Hyperbox Mixture Regression for process performance prediction in antibody production
title_short Hyperbox Mixture Regression for process performance prediction in antibody production
title_sort hyperbox mixture regression for process performance prediction in antibody production
topic Bioprocess performance prediction
Neuro-Fuzzy system
Hyperbox
Regression
Monoclonal antibodies
url http://www.sciencedirect.com/science/article/pii/S2772508125000055
work_keys_str_mv AT alinikkhorasani hyperboxmixtureregressionforprocessperformancepredictioninantibodyproduction
AT thanhtungkhuat hyperboxmixtureregressionforprocessperformancepredictioninantibodyproduction
AT bogdangabrys hyperboxmixtureregressionforprocessperformancepredictioninantibodyproduction