Department of Biotechnology, National Institute of Technology Raipur, Raipur, India.
Prep Biochem Biotechnol. 2020;50(10):1031-1041. doi: 10.1080/10826068.2020.1780612. Epub 2020 Jul 25.
Chitinase is responsible for the breaking down of chitin to N-acetyl-glucosamine units linked through (1-4)-glycosidic bond. The chitinases find several applications in waste management and pest control. The high yield with characteristics thermal stability of chitinase is the key to their industrial application. Therefore, the present work focuses on parameter optimization for chitinase production using fungus MTCC 9331. Three different optimization approaches, namely, response surface methodology (RSM), artificial neural network (ANN) and genetic algorithm (GA) were used. The parameters under study were incubation time, pH and inoculum size. The central composite design with RSM was used for the optimization of the process parameters. Further, results were validated with GA and ANN. A multilayer feed-forward algorithm was performed for ANN, i.e., Levenberg-Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient. The ANN predicted values gave higher chitinase activity, i.e., 102.24 U/L as compared to RSM-predicted values, i.e., 88.38 U/L. The predicted chitinase activity was also closer to the observed data at these levels. The validation study suggested that the highest activity of chitinase as predicted by ANN is in line with experimental analysis. The comparison of three different statistical approaches suggested that ANN gives better optimization results compared to the GA and RSM study.
几丁质酶负责将几丁质分解成通过（1-4）-糖苷键连接的 N-乙酰葡萄糖胺单位。几丁质酶在废物管理和害虫防治中有多种应用。几丁质酶的高产量和热稳定性是其工业应用的关键。因此，本工作侧重于使用真菌 MTCC 9331 生产几丁质酶的参数优化。使用了三种不同的优化方法，即响应面法（RSM）、人工神经网络（ANN）和遗传算法（GA）。研究的参数为培养时间、pH 和接种量。用 RSM 进行中心复合设计以优化工艺参数。进一步，用 GA 和 ANN 验证结果。对 ANN 进行了多层前馈算法，即 Levenberg-Marquardt、贝叶斯正则化和比例共轭梯度。ANN 预测值给出了更高的几丁质酶活性，即 102.24 U/L，而 RSM 预测值为 88.38 U/L。在这些水平下，预测的几丁质酶活性也更接近观察数据。验证研究表明，ANN 预测的几丁质酶最高活性与实验分析一致。三种不同统计方法的比较表明，ANN 比 GA 和 RSM 研究提供了更好的优化结果。
