Evaluation of the Estimation Capability of Response Surface Methodology and Artificial Neural Network for the Optimization of Bacteriocin-Like Inhibitory Substances Production by Lactococcus lactis Gh1

Bacteriocin-like inhibitory substances (BLIS) produced by Lactococcus lactis Gh1 had shown antimicrobial activity against Listeria monocytogenes ATCC 15313. Brain Heart Infusion (BHI) broth is used for the cultivation and enumeration of lactic acid bacteria, but there a need to improve current medium composition enhancement BLIS production, one approaches model optimization process identify most appropriate formulation. Response surface methodology (RSM) artificial neural network (ANN) models were employed in this study. In optimization, ANN (R2 = 0.98) provided better estimation point data fitting as compared RSM 0.79). ANN, optimal consisted 35.38 g/L soytone, 16 fructose, 3.25 sodium chloride (NaCl) 5.40 disodium phosphate (Na2HPO4). production (717.13 ± 0.76 AU/mL) was about 1.40-fold higher than that obtained nonoptimised (520.56 3.37 medium. further improved 1.18 times 2 L stirred tank bioreactor (787.40 1.30 250 mL shake flask (665.28 14.22 using optimised