Optimization of actinomycin V production by Streptomyces triostinicus using artificial neural network and genetic algorithm

Abstract

Artificial neural network (ANN) and genetic algorithm (GA) were applied to optimize the medium components for the production of actinomycinV from a newly isolated strain of Streptomyces triostinicus which is not reported to produce this class of antibiotics. Experiments were conducted using the central composite design (CCD), and the data generated was used to build an artificial neural network model. The concentrations of five medium components (MgSO4, NaCl, glucose, soybean meal and CaCO3) served as inputs to the neural network model, and the antibiotic yield served as outputs of the model. Using the genetic algorithm, the input space of the neural network model was optimized to find out the optimum values for maximum antibiotic yield. Maximum antibiotic yield of 452.0 mg l−1 was obtained at the GA-optimized concentrations of medium components (MgSO4 3.657; NaCl 1.9012; glucose 8.836; soybean meal 20.1976 and CaCO3 13.0842 gl−1). The antibiotic yield obtained by the ANN/GA was 36.7% higher than the yield obtained with the response surface methodology (RSM).