This study underlines the biotechnical valorization of the accumulated and unusable remains of agro-industrial orange fruit peel waste to produce α-amylase under submerged conditions by Streptomyces sp. KP314280 (20r). The response surface methodology based on central composite design (RSM-CCD) and artificial neural network coupled with a genetic algorithm (ANN-GA) were used to model and optimize the conditions for the α-amylase production. Four independent variables were evaluated for α-amylase activity including substrate concentration, inoculum size, sodium chloride powder (NaCl), and pH. A ten-fold cross-validation indicated that the ANN has a greater ability than the RSM to predict the α-amylase activity (R2ANN = 0.884 and R2RSM = 0.725). The analysis of variance indicated that the aforementioned four factors significantly affected the α-amylase activity. Additionally, the α-amylase production experiments were conducted according to the optimal conditions generated by the GA. The results indicated that the amylase yield increased by 4-fold. Moreover, the α-amylase production (12.19 U/mL) in the optimized medium was compatible with the predicted conditions outlined by the ANN-GA model (12.62 U/mL). As such, the ANN and GA combination is optimizable for α-amylase production and exhibits an accurate prediction which provides an alternative to other biological applications.
Keywords: Artificial neural network; Genetic algorithm; Orange waste; Response surface methodology; Streptomyces sp. (20r); α-amylase.
Copyright © 2021 Elsevier Inc. All rights reserved.