Use of uniform designs in combination with neural networks for viral infection process development

Abstract

This work aimed to compare the predictive capacity of empirical models, based on the uniform design utilization combined to artificial neural networks with respect to classical factorial designs in bioprocess, using as example the rabies virus replication in BHK-21 cells. The viral infection process parameters under study were temperature (34°C, 37°C), multiplicity of infection (0.04, 0.07, 0.1), times of infection, and harvest (24, 48, 72 hours) and the monitored output parameter was viral production. A multilevel factorial experimental design was performed for the study of this system. Fractions of this experimental approach (18, 24, 30, 36 and 42 runs), defined according uniform designs, were used as alternative for modelling through artificial neural network and thereafter an output variable optimization was carried out by means of genetic algorithm methodology. Model prediction capacities for all uniform design approaches under study were better than that found for classical factorial design approach. It was demonstrated that uniform design in combination with artificial neural network could be an efficient experimental approach for modelling complex bioprocess like viral production. For the present study case, 67% of experimental resources were saved when compared to a classical factorial design approach. In the near future, this strategy could replace the established factorial designs used in the bioprocess development activities performed within biopharmaceutical organizations because of the improvements gained in the economics of experimentation that do not sacrifice the quality of decisions.

Interaction of virus populations with their hosts

“…A virus will endure a fitness cost as a result of having confronted a selective constraint successfully (as illustrated with specific examples in Chapters 5 and 8), and a universal optimization is highly unlikely. Application of the "no free lunch" theorem to complexity theory is currently under investigation regarding its applicability to biological processes, such as genetic optimization algorithms (Whitley and Watson, 2005;Manning et al, 2013;Buenno et al, 2015;Popovici, 2018). Data of viral RNA and protein functions suggest that due to the extremely compact biological information imprinted into a physically small genome, each nucleotide is exploited for multiple functions, even those nucleotides that do not belong to overlapping genes (alternative open-reading frames with two different proteins encoded in part by the same nucleotide sequence).…”

Optimization of artificial neural network by genetic algorithm for describing viral production from uniform design data

“…The experimental matrixes for the five fractions were defined as U n (6 4 ), where n, 6, and 4 represent the number of experimental runs, level number, number of variables, respectively. This step has been previously described [17].…”

“…GAs are used for defining ANN topology, selection of training methods, and weights and biases. In addition they have been widely used for searching an optimal bioprocess critical parameter in order to maximize product quality and process efficiency indexes [17,18], which is sometimes referred to as GA-optimized neural network system (GONNS) [19].…”

Interaction of Virus Populations with Their Hosts

“…A virus will endure a fitness cost as a result of having successfully confronted a selective constraint, as illustrated with specific examples in Chapters 5 and 8, but a universal optimization is impossible. Application of the "no free lunch" theorem to complexity theory is currently under investigation regarding its applicability to biological processes such as genetic optimization algorithms (Whitley and Watson, 2005;Manning et al, 2013;Buenno et al, 2015). Data for virus evolution suggest that due to the extremely compact information packed into a physically small genome, each nucleotide is exploited for multiple functions, even those nucleotides that do not belong to overlapping genes (alternative open-reading frames with two different proteins encoded by the same nucleotide sequence).…”