Study on the extraction process of total protein from Euphorbiae Semen based on Box-Behnken response surface methodology and back propaga-tion neural network
Objective To optimize the extraction process of total protein from Euphorbiae Semen based on Box-Behnken response surface methodology and back propagation(BP)neural network.Methods With the total protein extraction rate and purity as the index,the extraction method of total protein from Euphorbiae Semen was determined by comparing the method of alkali extraction and acid precipitation method,ammonium sulfate salting-out method,and ultrasonic extraction method.The Box-Behnken response surface methodology combined with BP neural network was used to optimize the extraction process of total protein and verify it.The total protein from Euphorbiae Semen was precipitated by ammonium sulfate salting-out method to determine the effect of different ammonium sulfate saturation salting-out on total protein content.Results The effect of ammonium sulfate salting-out method on the extraction of total protein from Euphorbiae Semen was better.The total protein extraction rate optimized by Box-Behnken response surface methodology and BP neural network was higher,and the optimal extraction process was as follows:the ratio of solid to liquid was 1:23(g/ml),the extraction time was 3.2 h,and the phosphate buffer solution concentration was 0.02 mol/L,and the extraction rate of total protein was 19.87％,RSD value was 0.30％.When the saturation of ammonium sulfate for salting-out was 90％,the total protein was basically precipitated completely.Conclusion The optimized process based on Box-Behnken response surface methodology and BP neural network is stable and feasible,and the model prediction effect is good,which can provide reference for the extraction process of Euphorbiae Semen.
NETL
NSTL
万方数据
