基于遗传算法进化的人工神经网络,以葡萄糖为原料,对出芽短梗霉产普鲁兰多糖的发酵培养条件进行优化。首先通过单因素试验和Plackett-Burman实验筛选显著因素,再进行Box-Behnken实验建立数据样本,最后利用Matlab建立神经网络模型寻找最优解。结果表明,葡萄糖和酵母抽提物对普鲁兰多糖的合成具有显著的正效应,K2HPO4对普鲁兰多糖的合成具有显著的负效应。遗传算法-人工神经网络的决定系数与相对误差分别为0.998 8与1.72%。最终优化获得普鲁兰多糖发酵的最佳培养基组分为葡萄糖150 g/L,酵母抽提物7.1 g/L,MgSO4·7H2O 1.4 g/L,K2HPO4 7 g/L,NaCl 7 g/L,自然pH。在此条件下,普鲁兰多糖的产量为83.25 g/L,较优化前提高了79.73%。经济分析表示优化后的培养基成本较优化前降低了约70 %。该研究结果为普鲁兰多糖的工业化生产提供了数据支撑,有助于提升普鲁兰多糖在行业中的竞争力。
Using glucose as raw material, the fermentation conditions of pullulan polysaccharide produced by Aureobasidium pullulans were optimized by artificial neural network based on genetic algorithm (GA-ANN). Firstly, single factor test and Plackett-Burman (PB) experiment were used to screen significant factors, then Box-Behnken (BBD) experiment was conducted to establish data samples, and finally Matlab was used to establish model optimization to find the optimal solution. Results showed that glucose and yeast extracts had a significant positive effect on the synthesis of pullulan polysaccharide, while K2HPO4 had a significant negative effect on the synthesis of pullulan polysaccharide. The coefficient and relative error of GA-ANN were 0.998 8 and 1.67% respectively. Finally, the optimal fermentation conditions of pullulan polysaccharide were 150 g/L of glucose, 7.1 g/L of yeast extract, 1.4 g/L of MgSO4·7H2O, 7 g/L of K2HPO4, 7 g/L of NaCl, and natural pH. Under these conditions, the yield of pullulan polysaccharide was 83.25 g/L, 79.73 % higher than that before optimization. The cost of optimized medium was reduced by about 70% compared with that before optimization. The results provide data support for the industrial production of pullulan polysaccharide and help to improve the competitiveness of pullulan polysaccharide in the industry.
[1] SINGH R S, SAINI G K, KENNEDY J F.Pullulan:Microbial sources, production and applications[J].Carbohydrate Polymers, 2008, 73(4):515-531.
[2] HONG T T, MA Y, YUAN Y R, et al.Understanding the influence of pullulan on the quality changes, water mobility, structural properties and thermal properties of frozen cooked noodles[J].Food Chemistry, 2021, 365:130512.
[3] DING Y Y, JIANG F, CHEN L, et al.An alternative hard capsule prepared with the high molecular weight pullulan and gellan:Processing, characterization, and in vitro drug release[J].Carbohydrate Polymers, 2020, 237:116172.
[4] SINGH R S, KAUR N, HASSAN M, et al.Pullulan in biomedical research and development-A review[J].International Journal of Biological Macromolecules, 2021, 166:694-706.
[5] PRIYADARSHI R, KIM S M, RHIM J W.Pectin/pullulan blend films for food packaging:Effect of blending ratio[J].Food Chemistry, 2021, 347:129022.
[6] MEHTA A, PRASAD G S, CHOUDHURY A R.Cost effective production of pullulan from agri-industrial residues using response surface methodology[J].International Journal of Biological Macromolecules, 2014, 64:252-256.
[7] SINGH R S, KAUR N, KENNEDY J F.Pullulan production from agro-industrial waste and its applications in food industry:A review[J].Carbohydrate Polymers, 2019, 217:46-57.
[8] CHENG K C, DEMIRCI A, CATCHMARK J M.Evaluation of medium composition and fermentation parameters on pullulan production by Aureobasidium pullulans[J].Food Science and Technology International, 2011, 17(2):99-109.
[9] HE C Y, ZHANG Z, ZHANG Y D, et al.Efficient pullulan production by Aureobasidium pullulans using cost-effective substrates[J].International Journal of Biological Macromolecules, 2021, 186:544-553.
[10] YANG J, HUANG Y, XU H Y, et al.Optimization of fungi co-fermentation for improving anthraquinone contents and antioxidant activity using artificial neural networks[J].Food Chemistry, 2020, 313:126138.
[11] SEBAYANG A H, MASJUKI H H, ONG H C, et al.Optimization of bioethanol production from sorghum grains using artificial neural networks integrated with ant colony[J].Industrial Crops and Products, 2017, 97:146-155.
[12] HOSU A, CRISTEA V M, CIMPOIU C.Analysis of total phenolic, flavonoids, anthocyanins and tannins content in Romanian red wines:Prediction of antioxidant activities and classification of wines using artificial neural networks[J].Food Chemistry, 2014, 150:113-118.
[13] ZADOR A M.A critique of pure learning and what artificial neural networks can learn from animal brains[J].Nature Communications, 2019, 10(1):1-7.
[14] 迟雷, 王静雨, 侯俊超, 等.基于人工神经网络和遗传算法的普鲁兰酶重组大肠杆菌高密度发酵工艺优化[J].食品科学, 2021, 42(10):73-78.
CHI L, WANG J Y, HOU J C, et al.Artificial neural network-genetic algorithm-based optimization of high cell density cultivation of recombinant Escherichia coli for producing pullulanase[J].Food Science, 2021, 42(10):73-78.
[15] IYYAPPAN J, BHARATHIRAJA B, BASKAR G, et al.Process optimization and kinetic analysis of malic acid production from crude glycerol using Aspergillus niger[J].Bioresource Technology, 2019, 281:18-25.
[16] 王云龙, 刘松, 堵国成, 等.基于人工神经网络的L-天冬酰胺酶发酵培养基优化[J].食品与发酵工业, 2018, 44(8):27-33.
WANG Y L, LIU S, DU G C, et al.Optimization of L-asparaginase fermentation medium based on artificial neural network[J].Food and Fermentation Industries, 2018, 44(8):27-33.
[17] PENCHEVA T, ANGELOVA M, SOTIROVA E, et al.How to assess different algorithms using intuitionistic fuzzy logic[J].Mathematics, 2021, 9(18):2189.
[18] ZHENG Z Y, GUO X N, ZHU K X, et al.Artificial neural network-Genetic algorithm to optimize wheat germ fermentation condition:Application to the production of two anti-tumor benzoquinones[J].Food Chemistry, 2017, 227:264-270.
[19] 陈世伟, 唐淑贤, 王舸楠, 等. 基于蛋白质组学分析尿嘧啶对出芽短梗霉产普鲁兰多糖的影响[J]. 食品工业科技, 2022, 43(16):18-25.
CHEN S W, TANG S X, WANG G N, et al. Proteomics analysis of the effect of uracil on pullulan polysaccharide production by Aureobasidium pullulans[J]. Science and Technology of Food Industry, 2022, 43(16):18-25.
[20] 张伊凡, 陈世伟, 郭利飞, 等.维生素B5对出芽短梗霉产普鲁兰多糖的影响[J].食品与发酵工业, 2022, 48(11):16-23.
ZHANG Y F, CHEN S W, GUO L F, et al.Effect of vitamin B5 on production of pullulan by Aureobasidium pullulans[J].Food and Fermentation Industries, 2022, 48(11):16-23.
[21] SHENG L, ZHU G L, TONG Q L.Effect of uracil on pullulan production by Aureobasidium pullulans CGMCC1234[J].Carbohydrate Polymers, 2014, 101:435-437.
[22] ZHANG S Z, YUAN Y K, LIU C Z, et al.Modeling and optimization of porous aerogel adsorbent for removal of cadmium from crab viscera homogenate using response surface method and artificial neural network[J].LWT, 2021, 150:111990.
[23] AYDINLI B, CAGLAR A, PEKOL S, et al.The prediction of potential energy and matter production from biomass pyrolysis with artificial neural network[J].Energy Exploration & Exploitation, 2017, 35(6):698-712.
[24] 朱灿灿, 陈晨, 王大慧, 等.普鲁兰生物合成中底物的作用及其生理机制[J].食品科学, 2019, 40(14):63-68.
ZHU C C, CHEN C, WANG D H, et al.Physiological mechanism underlying the effect of substrates on pullulan biosynthesis[J].Food Science, 2019, 40(14):63-68.
