Artificial Neural Network (ANN) was used to build a predictive model of the combined effects of independent variables (pH, temperature, hydrolysis time, enzyme/substrate ratio and the concentration of substrate) for antioxidant peptides production. Optimum operating conditions for the maximum antioxidant capability were reported as: 1)the hydrolysate which could scavenge the radical DPPH· most effectively were hydrolyzed for 4.8h with Alcalase at pH?7.5 and 60?℃, muscle∶water=1∶1.9, enzyme/substrate =0.2%; 2)the hydrolysate which could scavenge the radical OH· most effectively were hydrolyzed for 6?h with Alcalase at pH?7.5 and 60?℃，muscle∶water=1∶1.4, enzyme/substrate =0.16%; 3)the hydrolysate which could scavenge the radical O2·- most effectively were hydrolysis for 4.3?h at pH?7.5 and 60?℃, muscle∶water=1∶1, enzyme/substrate =0.2%. The results showed that ANN is very helpful tool for the bioactive peptides production.
