Data-Driven Yield Improvement in Upstream Bioprocessing of Monoclonal Antibodies: A Machine Learning Case Study

Αποθηκεύτηκε σε:
Λεπτομέρειες βιβλιογραφικής εγγραφής
Εκδόθηκε σε:Processes vol. 13, no. 11 (2025), p. 3394-3412
Κύριος συγγραφέας: Strüssmann, Breno Renato
Άλλοι συγγραφείς: de Queiroz Anderson Rodrigo, Hvam Lars
Έκδοση:
MDPI AG
Θέματα:
Διαθέσιμο Online:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Ετικέτες: Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!

MARC

LEADER 00000nab a2200000uu 4500
001 3275549596
003 UK-CbPIL
022 |a 2227-9717 
024 7 |a 10.3390/pr13113394  |2 doi 
035 |a 3275549596 
045 2 |b d20250101  |b d20251231 
084 |a 231553  |2 nlm 
100 1 |a Strüssmann, Breno Renato  |u Department of Civil and Mechanical Engineering, Technical University of Denmark, 2800 Copenhagen, Denmark; lahv@dtu.dk 
245 1 |a Data-Driven Yield Improvement in Upstream Bioprocessing of Monoclonal Antibodies: A Machine Learning Case Study 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a The increasing demand for monoclonal antibody (mAb) therapeutics has intensified the need for more efficient and consistent biomanufacturing processes. We present a data-driven, machine-learning (ML) approach to exploring and predicting upstream yield behavior. Drawing on industrial-scale batch records for a single mAb product from a contract development and manufacturing organization, we applied regression models to identify key process parameters and estimate production outcomes. Random forest regression, gradient boosting machine, and support vector regression (SVR) were evaluated to predict three yield indicators: bioreactor final weight (BFW), harvest titer (HT), and packed cell volume (PCV). SVR outperformed other models for BFW prediction (R2 = 0.978), while HT and PCV were difficult to model accurately with the available data. Exploratory analysis using sequential least-squares programming suggested parameter combinations associated with improved yield estimates relative to historical data. Sensitivity analysis highlighted the most influential process parameters. While the findings demonstrate the potential of ML for predictive, data-driven yield improvement, the results should be interpreted as an exploratory proof of concept rather than a fully validated optimization framework. This study highlights the need to incorporate process constraints and control logic, along with interpretable or hybrid modeling frameworks, to enable practical deployment in regulated biomanufacturing environments. 
653 |a Monoclonal antibodies 
653 |a Datasets 
653 |a Bioprocessing 
653 |a Sensitivity analysis 
653 |a Parameter sensitivity 
653 |a Regression analysis 
653 |a Regression models 
653 |a Data analysis 
653 |a Machine learning 
653 |a Manufacturing 
653 |a Cell culture 
653 |a Learning algorithms 
653 |a Biotechnology 
653 |a Good Manufacturing Practice 
653 |a Parameter identification 
653 |a Parameter estimation 
653 |a Support vector machines 
653 |a Process controls 
653 |a Bioreactors 
653 |a Cell size 
653 |a Process parameters 
700 1 |a de Queiroz Anderson Rodrigo  |u CCEE Department, NC State University, Raleigh, NC 27606, USA; ardequei@ncsu.edu 
700 1 |a Hvam Lars  |u Department of Civil and Mechanical Engineering, Technical University of Denmark, 2800 Copenhagen, Denmark; lahv@dtu.dk 
773 0 |t Processes  |g vol. 13, no. 11 (2025), p. 3394-3412 
786 0 |d ProQuest  |t Materials Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3275549596/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3275549596/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3275549596/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch