Enhanced production of mycelium biomass and exopolysaccharides of Pleurotus ostreatus by integrating response surface methodology and artificial neural network

Abstract

This study aimed to enhance the production of mycelium biomass and exopolysaccharides (EPS) of Pleurotus ostreatus in submerged fermentation. Response Surface Methodology (RSM)sought to optimize culture conditions, whereas Artificial Neural Network (ANN)aimed to predict the mycelium biomass and EPS. After optimization of RSM model conditions, the maximum biomass (36.45 g/L) and EPS (6.72 g/L) were obtained at the optimum temperature of 22.9 °C, pH 5.6, and agitation of 138.9 rpm. Further, the Genetic Algorithm (GA) was employed to optimize the cultivation conditions in order to maximize the mycelium biomass and EPS production. The ANN model with an optimized network structure gave the coefficient of determination (R²) value of 0.99 and the least mean squared error of 1.9 for the validation set. In the end, a graphical user interface was developed to predict mycelium biomass and EPS production.

Keywords: Bioactive compounds; Edible fungi; Genetic algorithm; Graphical user interface; Machine learning.