Premium
Hybrid Modeling and Intensified DoE: An Approach to Accelerate Upstream Process Characterization
Author(s) -
Bayer Benjamin,
Striedner Gerald,
Duerkop Mark
Publication year - 2020
Publication title -
biotechnology journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.144
H-Index - 84
eISSN - 1860-7314
pISSN - 1860-6768
DOI - 10.1002/biot.202000121
Subject(s) - fractional factorial design , design of experiments , bioprocess , factorial experiment , computer science , biological system , biochemical engineering , central composite design , process (computing) , factorial , plackett–burman design , process engineering , mathematics , response surface methodology , machine learning , engineering , statistics , biology , chemical engineering , operating system , mathematical analysis
Abstract Process characterization is necessary in the biopharmaceutical industry, leading to concepts such as design of experiments (DoE) in combination with process modeling. However, these methods still have shortcomings, including large numbers of required experiments. The concept of intensified design of experiments (iDoE) is proposed, that is, intra‐experimental shifts of critical process parameters (CPP) that combine with hybrid modeling to more rapidly screen a particular design space. To demonstrate these advantages, a comprehensive experimental design of Escherichia coli (E. coli) fed‐batch cultivations (20 L) producing recombinant human superoxide dismutase is presented. The accuracy of hybrid models trained on iDoE and on a fractional‐factorial design is evaluated, without intra‐experimental shifts, to simultaneously predict the biomass concentration and product titer of the full‐factorial design. The hybrid model trained on data from the iDoE describes the biomass and product at each time point for the full‐factorial design with high and adequate accuracy. The fractional‐factorial hybrid model demonstrates inferior accuracy and precision compared to the intensified approach. Moreover, the intensified hybrid model only required one‐third of the data for model training compared to the full‐factorial description, resulting in a reduced experimental effort of >66%. Thus, this combinatorial approach has the potential to accelerate bioprocess characterization.