Machine learning in bioprocess development: from promise to practice

Kim

Biotech & Bioengineering

et al. 2023

Recently, the advancement in process analytical technology and artificial intelligence (AI) has enabled the generation of enormous culture data sets from biomanufacturing processes that produce various recombinant therapeutic proteins (RTPs), such as monoclonal antibodies (mAbs). Thus, now it is very important to exploit them for the enhanced reliability, efficiency, and consistency of the RTP‐producing culture processes and for the reduced incipient or abrupt faults. It is achievable by AI‐based data‐driven models (DDMs), which allow us to correlate biological and process conditions and cell culture states. In this work, we provide practical guidelines for choosing the best combination of model elements to design and implement successful DDMs for given hypothetical in‐line data sets during mAb‐producing Chinese hamster ovary cell culture, as such enabling us to forecast dynamic behaviors of culture performance such as viable cell density, mAb titer as well as glucose, lactate and ammonia concentrations. To do so, we created DDMs that balance computational load with model accuracy and reliability by identifying the best combination of multistep ahead forecasting strategies, input features, and AI algorithms, which is potentially applicable to implementation of interactive DDM within bioprocess digital twins. We believe this systematic study can help bioprocess engineers start developing predictive DDMs with their own data sets and learn how their cell cultures behave in near future, thereby rendering proactive decision possible.

Section: Resultsmentioning

confidence: 99%

“…Additionally, ensemble models can help mitigate the impact of model bias or overfitting, which can be particularly important in real-time applications where data are continually being generated and models need to be updated on a regular basis (Helleckes et al, 2022).…”

Section: Real-time Application Of Stepwise Evaluationmentioning

confidence: 99%

Data‐driven prediction models for forecasting multistep ahead profiles of mammalian cell culture toward bioprocess digital twins

Kim

Biotech & Bioengineering

et al. 2023

“…108,109 Advantages of hybrid models over traditional mechanistic approaches include higher adaptability to process variations and data heterogeneity, higher capability to be transferred to similar processes and an overall reduction in necessary process understanding. 101,110 Hybrid models demonstrated excellent performance in rapid evaluation and optimization of complex downstream processes. 29 A hybrid modeling approach has demonstrated superior accuracy and robustness compared to a Lumped kinetics mechanistic model to predict breakthrough curves.…”

Section: Mathematical Models For Process Design Control and Monitoringmentioning

confidence: 99%

“…Hybrid models attempt to augment a mechanistic (fully parametric) with data‐driven approaches (statistical and machine learning), to enable capturing of phenomena that are highly‐nonlinear or not well understood (e.g., the impact of variability in raw material on product CQAs) 108,109 . Advantages of hybrid models over traditional mechanistic approaches include higher adaptability to process variations and data heterogeneity, higher capability to be transferred to similar processes and an overall reduction in necessary process understanding 101,110 . Hybrid models demonstrated excellent performance in rapid evaluation and optimization of complex downstream processes 29 .…”

Section: Quality Control and Process Monitoringmentioning

confidence: 99%

Current challenges and recent advances on the path towards continuous biomanufacturing

Drobnjakovic

Hart²,

Kulvatunyou

et al. 2023

Biotechnology Progress

Continuous biopharmaceutical manufacturing is currently a field of intense research due to its potential to make the entire production process more optimal for the modern, ever‐evolving biopharmaceutical market. Compared to traditional batch manufacturing, continuous bioprocessing is more efficient, adjustable, and sustainable and has reduced capital costs. However, despite its clear advantages, continuous bioprocessing is yet to be widely adopted in commercial manufacturing. This article provides an overview of the technological roadblocks for extensive adoptions and points out the recent advances that could help overcome them. In total, three key areas for improvement are identified: Quality by Design (QbD) implementation, integration of upstream and downstream technologies, and data and knowledge management. First, the challenges to QbD implementation are explored. Specifically, process control, process analytical technology (PAT), critical process parameter (CPP) identification, and mathematical models for bioprocess control and design are recognized as crucial for successful QbD realizations. Next, the difficulties of end‐to‐end process integration are examined, with a particular emphasis on downstream processing. Finally, the problem of data and knowledge management and its potential solutions are outlined where ontologies and data standards are pointed out as key drivers of progress.

Biotech & Bioengineering

“…Ever since then, fluorescence online monitoring has widely been established as an effective tool for bioprocess development. Due to the growing interest in generating process insights and the call to implement process analytical technologies (FDA, 2004), the application of appropriate machine learning evaluation algorithms for data exploitation is regularly reviewed (Claßen et al, 2017; Faassen & Hitzmann, 2015; Helleckes et al, 2023; Lourenço et al, 2012; Mowbray et al, 2021; Rathore et al, 2011; Reyes et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Advancing 2D fluorescence online monitoring in microtiter plates by separating scattered light and fluorescence measurement, using a tunable emission monochromator

Berg,

Busch,

Alawiyah

et al. 2023

Online fluorescence monitoring has become a key technology in modern bioprocess development, as it provides in‐depth process knowledge at comparably low costs. In particular, the technology is widely established for high‐throughput microbioreactor cultivation systems, due to its noninvasive character. For microtiter plates, previously also multi‐wavelength 2D fluorescence monitoring was developed. To overcome an observed limitation of fluorescence sensitivity, this study presents a modified spectroscopic setup, including a tunable emission monochromator. The new optical component enables the separation of the scattered and fluorescent light measurements, which allows for the adjustment of integration times of the charge‐coupled device detector. The resulting increased fluorescence sensitivity positively affected the performance of principal component analysis for spectral data of Escherichia coli batch cultivation experiments with varying sorbitol concentration supplementation. In direct comparison with spectral data recorded at short integration times, more biologically consistent signal dynamics were calculated. Furthermore, during partial least square regression for E. coli cultivation experiments with varying glucose concentrations, improved modeling performance was observed. Especially, for the growth‐uncoupled acetate concentration, a considerable improvement of the root‐mean‐square error from 0.25 to 0.17 g/L was achieved. In conclusion, the modified setup represents another important step in advancing 2D fluorescence monitoring in microtiter plates.