Statistical versus neural network-embedded swarm intelligence optimization of a metallo-neutral-protease production: activity kinetics and food industry applications.

An integrated approach involving response surface methodology (RSM) and artificial neural network-ant-colony hybrid optimization (ANN-ACO) was adopted to develop a bioprocess medium to increase the yield of neutral protease under submerged fermentation conditions. The ANN-ACO model was comparatively superior (predicted = 98.5%, mean squared error [MSE] = 0.0353) to RSM model (predicted = 86.4%, MSE = 23.85) in predictive capability arising from its low performance error. The hybrid model recommended a medium containing (gL) molasses 45.00, urea 9.81, casein 25.45, Ca 1.23, Zn 0.021, Mn 0.020, and 4.45% (vv) inoculum, for a 6.75-fold increase in protease activity from a baseline of 76.63 UmL. Yield was further increased in a 5-L bioreactor to a final volumetric productivity of 3.472 mg(Lh). The 10.0-fold purified 46.6-kDa-enzyme had maximum activity at pH 6.5, 45-55 °C, with K of 6.92 mM, V of 769.23 µmolmL min, k of 28.49 s, and k/K of 4.117 × 103 M s, at 45 °C, pH 6.5. The enzyme was stabilized by Ca, activated by Zn but inhibited by EDTA suggesting that it was a metallo-protease. The biomolecule significantly clarified orange and pineapple juices indicating its food industry application.