Improvement of L-asparaginase, an Anticancer Agent of Aspergillus arenarioides EAN603 in Submerged Fermentation Using a Radial Basis Function Neural Network with a Specific Genetic Algorithm (RBFNN-GA)

The present study aimed to optimize the production of L-asparaginase from Aspergillus arenarioides EAN603 in submerged fermentation using a radial basis function neural network with specific genetic algorithm (RBFNN-GA) and response surface methodology (RSM). Independent factors used included temperature (x1), pH (x2), incubation time (x3), soybean concentration (x4). coefficient predicted model Box–Behnken design (BBD) was R2 = 0.9079 (p < 0.05); however, lack fit significant indicating that independent are not fitted quadratic model. These results were confirmed during optimization process, which revealed standard error (SE) 11.65 while 0.9799, at 145.35 124.54 IU mL?1 actual enzyme recorded 34 °C, 8.5, after 7 days 10 g L?1 organic powder concentrations. Compared RBFNN-GA, investigated had benefits effects on L-asparaginase, correlation R 0.935484, can classify 91.666667% test data samples better degree precision; values higher than for data.