An Approach for the Estimation of Concentrations of Soluble Compounds in E. coli Bioprocesses.

Accurate estimations of the concentrations of soluble compounds are crucial for optimizing bioprocesses involving Escherichia coli (E. coli). This study proposes a hybrid model structure that leverages off-gas analysis data and physiological parameters, including the average biomass age and specific growth rate, to estimate soluble compounds such as acetate and glutamate in fed-batch cultivations We used a hybrid recurrent neural network to establish the relationships between these parameters. To enhance the precision of the estimates, the model incorporates ensemble averaging and information gain. Ensemble averaging combines varying model inputs, leading to more robust representations of the underlying dynamics in E. coli bioprocesses. Our hybrid model estimates acetates with 1% and 8% system precision using data from the first site and the second site at GSK plc, respectively. Using the data from the second site, the precision of the approach for other solutes was as fallows: isoleucine -8%, lactate and glutamate -9%, and a 13% error for glutamine., These results, demonstrate its practical potential.

Bridging Offline Functional Model Carrying Aging-Specific Growth Rate Information and Recombinant Protein Expression: Entropic Extension of Akaike Information Criterion.

This study presents a mathematical model of recombinant protein expression, including its development, selection, and fitting results based on seventy fed-batch cultivation experiments from two independent biopharmaceutical sites. To resolve the overfitting feature of the Akaike information criterion, we proposed an entropic extension, which behaves asymptotically like the classical criteria. Estimation of recombinant protein concentration was performed with pseudo-global optimization processes while processing offline recombinant protein concentration samples. We show that functional models including the average age of the cells and the specific growth at induction or the start of product biosynthesis are the best descriptors for datasets. We also proposed introducing a tuning coefficient that would force the modified Akaike information criterion to avoid overfitting when the designer requires fewer model parameters. We expect that a lower number of coefficients would allow the efficient maximization of target microbial products in the upstream section of contract development and manufacturing organization services in the future. Experimental model fitting was accomplished simultaneously for 46 experiments at the first site and 24 fed-batch experiments at the second site. Both locations contained 196 and 131 protein samples, thus giving a total of 327 target product concentration samples derived from the bioreactor medium.