Application of intelligence computing to optimizing enzymatic bioprocessing in cartilage hydrolysis

This study uses the Taguchi orthogonal method and artificial neural network to optimize enzymatic bioprocessing of animal waste cartilage (chicken, mini pig and hog). Specifically, the artificial neural network is used in parallel with the Taguchi orthogonal array process for enzymatic hydrolysis of the cartilage tissue to optimize the best quality of bioactive peptides. The experiment was designed using Taguchi orthogonal array optimal level L25 physical parameters and key media components, namely temperature, pH, enzyme/substrate ratio, substrate concentration, and reaction time. The experimental results were used to train the artificial neural network (ANN) to predict the optimizing enzymatic bioprocessing in animal cartilage hydrolysis. The analysis was performed on a personal computer using NeuroSolutions 6.0 software. The experiment of an enzymatic hydrolysate of three animal cartilages followed the Taguchi orthogonal design, and we discovered that 60±1C is the most effective temperature to hydrolyze cartilage. These peptides of molecular size smaller than 10kDa (with 95% values between 10.7kDa and 2.5kDa) were capable of stimulating the porcine chondrocytes to produce glycosaminoglycan (GAG) and type II collagen in vitro. NeuroSolutions 6.0 back-propagation analysis achieved a convergence value of R2=0.9762, indicating that the enzymatic bioprocessing has good performance. Therefore, this study suggests that integrating artificial neural network and Taguchi method when constructing an optimal enzymatic bioprocessing model could significantly increase and improve the quality of final bioactive peptide products. It also suggests that integrating artificial neural network and Taguchi method in the construction of an optimal enzymatic bioprocessing in cartilage hydrolysis could be used as nutraceutical component in bone and joint health