[1]张光亚,方柏山.木聚糖酶氨基酸组成与最适温度的模型[J].华侨大学学报(自然科学版),2005,26(2):191-194.[doi:10.3969/j.issn.1000-5013.2005.02.021]
 Zhang Guangya,Fang Baishan.A Model for Amino Acid Composition and Optimum Temperature in F/10 Xylanase[J].Journal of Huaqiao University(Natural Science),2005,26(2):191-194.[doi:10.3969/j.issn.1000-5013.2005.02.021]
点击复制

木聚糖酶氨基酸组成与最适温度的模型()
分享到:

《华侨大学学报(自然科学版)》[ISSN:1000-5013/CN:35-1079/N]

卷:
第26卷
期数:
2005年第2期
页码:
191-194
栏目:
出版日期:
2005-04-20

文章信息/Info

Title:
A Model for Amino Acid Composition and Optimum Temperature in F/10 Xylanase
文章编号:
1000-5013(2005)02-0191-04
作者:
张光亚方柏山
华侨大学材料科学与工程学院; 华侨大学材料科学与工程学院 福建泉州362021; 福建泉州362021
Author(s):
Zhang Guangya Fang Baishan
College of Material Science and Engineering, Huaqiao University, 362021, Quanzhou, China
关键词:
均匀设计 BP神经网络 木聚糖酶 氨基酸组成 最适温度
Keywords:
uniform design BP neural network xylanase amino acid composition optimum temperature
分类号:
O629.8
DOI:
10.3969/j.issn.1000-5013.2005.02.021
文献标志码:
A
摘要:
运用基于均匀设计(UD)的神经网络(NNs)构造法,构建F/10家族木聚糖酶氨基酸组成和最适温度的数学模型.当学习速率为0.1、动态参数为0.6、Sigmoid参数为0.9,隐含层结点数为7时,该模型对最适温度的拟合和预测的平均绝对百分比误差分别为6.61%和1.78%,均方根误差分别为5.43℃和2.00℃,平均绝对误差分别为4.13℃和1.46℃.
Abstract:
By using uniform design and neural network construction, the authors established a mathematical model for amino acid composition and optimal temperature of xylanases in F/10 family. As compared with the method of stepwise regression adopted by previous literature, the present model showed better results in fitting and prediction of optinal temperature. Under the conditions including learning rate of 0.1 and dynamic parameter of 0.6 and sigmoid parameter of 0.9 and knot number in the hidden layer of 7, the results of the present model in fitting and prediction of optimal temperatare can be shown respectively by mean absolute percent error of 6.6% and 1.78%, mean square error of 5.43 ℃ and 2.00 ℃, and mean absolute error of 4.13 ℃ and 1.46 ℃.

参考文献/References:

[1] Xue Yiming, Mao Guizhong, Shao Weilan. Expression of xlyanase B gene of Thermotoga maritime in Escherichia coli [J]. Food and Fermentation Industries, 2003, (11):20-25.doi:10.3321/j.issn:0253-990X.2003.11.005.
[2] Badhan A K, Chadha B S. Functionally diverse multiple xylanases of thermophilic fungus Myceliophthora sp.IMI 38709 [J]. Enzyme and Microbial Technology, 2004(5):460-466.doi:10.1016/j.enzmictec.2004.07.002.
[3] Kulkarni N, Shendye A. Molecular and biotechnological aspects of xylanases [J]. FEMS Microbiology Reviews, 1999.411-456.
[4] Fang Baishan, Chen Hongwen, Xie Xiaolan. The medium optimization of xylitol fermentation based on neural networks and genetic algorithms [J]. Chinese Journal of Biotechnology, 2000(5):648-650.doi:10.3321/j.issn:1000-3061.2000.05.025.
[5] Vladimir B, George R, Margo H. Prediction of MHC class Ⅱ binding peptides using an evolutionary algorithm and artificial neural network [J]. Bioinformatics, 1998(2):121-130.
[6] Zhao Ziqiang, Huang Dashan, Sun Binyi. Human face recognition based on multi-features using neural networks committee [J]. Pattern Recognition Letters, 2004, (12):1351-1358.
[7] Vieille C, Zeikus G J. Hyperthermophilic enzymes: Sources, uses, and molecular mechanisms for thermostability [J]. Microbiology and Molecular Biology Reviews, 2001(1):1-43.
[8] Liu Lianwei, Wang Mingli, Shao Weilan. A novel model to determine the dipeptides responsible for optimum temperature in F/10 xylanase [J]. Process Biochemistry, 2005(3):1389-1394.
[9] 方柏山. 生物技术过程模型优化与控制 [M]. 广州:暨南大学出版社, 1997.185-212.
[10] 方开泰. 均匀设计与均匀设计表 [M]. 北京:科学出版社, 1994.21-85.
[11] Ossi T, Kirsikka E. A combination of weakly stabilizing mutations with a disulfide bridge in the helix region of Trichoderma reesei endo-1, 4-xylanase Ⅱ increases the thermal stability through synergism [J]. Journal of Biotechnology, 2001(1):37-46.doi:10.1016/S0168-1656(01)00253-X.
[12] Voigt C A, Mayo S L, Arnold F H. Computational method to reduce the search space for directed protein evolution [J]. Proceedings of the National Academy of Sciences of the United States of America, 2001.3778-3783.

相似文献/References:

[1]杨冠鲁,李元杰.神经网络SNC无刷柴油发电机励磁控制器[J].华侨大学学报(自然科学版),2001,22(3):317.[doi:10.3969/j.issn.1000-5013.2001.03.021]
 Yang Guanlu,Li Yuanjie.Exciting Controller of Brushless Diesel Generator Based on BP Neural Network[J].Journal of Huaqiao University(Natural Science),2001,22(2):317.[doi:10.3969/j.issn.1000-5013.2001.03.021]
[2]张光亚,葛慧华,方柏山.一种预测木聚糖酶最适温度的PCANN模型[J].华侨大学学报(自然科学版),2007,28(1):55.[doi:10.3969/j.issn.1000-5013.2007.01.015]
 ZHANG Guang-ya,GE Hui-hua,FANG Bai-shan.A Principal Component-Artificial Neural Network Model for Predicting Optimum Temperature in F/10 Xylanases[J].Journal of Huaqiao University(Natural Science),2007,28(2):55.[doi:10.3969/j.issn.1000-5013.2007.01.015]
[3]涂帆,常方强.BP神经网络预测水泥搅拌桩单桩承载力[J].华侨大学学报(自然科学版),2007,28(1):68.[doi:10.3969/j.issn.1000-5013.2007.01.018]
 TU Fan,CHANG Fang-qiang.The Method of BP Neural Network Predicting the Bearing Capacity of Single Cement Mixing Pile[J].Journal of Huaqiao University(Natural Science),2007,28(2):68.[doi:10.3969/j.issn.1000-5013.2007.01.018]
[4]许建文,刘斌.注塑件体积收缩率变化的数值模拟优化与预报[J].华侨大学学报(自然科学版),2010,31(3):241.[doi:10.11830/ISSN.1000-5013.2010.03.0241]
 XU Jian-wen,LIU Bin.Optimization and Forecast of Numerical Simulation of Volumetric Shrinkage Variation for Injection Molding Products[J].Journal of Huaqiao University(Natural Science),2010,31(2):241.[doi:10.11830/ISSN.1000-5013.2010.03.0241]
[5]黄凯宗,张光亚.使用伪氨基酸组成和BP神经网络预测类弹性蛋白多肽的相变温度[J].华侨大学学报(自然科学版),2011,32(2):194.[doi:10.11830/ISSN.1000-5013.2011.02.0194]
 HUANG Kai-zong,ZHANG Guang-ya.Using Pseudo-Amino Acid Composition and BP Neural Network to Predict the Transition Temperature of Elastin-Like Peptides[J].Journal of Huaqiao University(Natural Science),2011,32(2):194.[doi:10.11830/ISSN.1000-5013.2011.02.0194]
[6]李平,周博.双容水箱的神经PID控制[J].华侨大学学报(自然科学版),2012,33(6):608.[doi:10.11830/ISSN.1000-5013.2012.06.0608]
 LI Ping,ZHOU Bo.PID Control Based on Neural Networks in Double-Tank System[J].Journal of Huaqiao University(Natural Science),2012,33(2):608.[doi:10.11830/ISSN.1000-5013.2012.06.0608]
[7]付宝英,王启志.自适应粒子群优化BP神经网络的变压器故障诊断[J].华侨大学学报(自然科学版),2013,34(3):262.[doi:10.11830/ISSN.1000-5013.2013.03.0262]
 FU Bao-ying,WANG Qi-zhi.Transformer Fault Diagnosis of Adaptive Particle SwarmOptimization BP Neural Network[J].Journal of Huaqiao University(Natural Science),2013,34(2):262.[doi:10.11830/ISSN.1000-5013.2013.03.0262]
[8]杨洋,李钟慎,范伟.高精度数据采集系统定时器的仿真分析[J].华侨大学学报(自然科学版),2013,34(6):610.[doi:10.11830/ISSN.1000-5013.2013.06.0610]
 YANG Yang,LI Zhong-shen,FAN Wei.Simulation Analysis of High-Precision Data Acquisition System with Timers[J].Journal of Huaqiao University(Natural Science),2013,34(2):610.[doi:10.11830/ISSN.1000-5013.2013.06.0610]
[9]林源清,张光亚.G/11木聚糖酶最适pH值的预测及其与氨基酸位置的关系[J].华侨大学学报(自然科学版),2014,35(3):316.[doi:10.11830/ISSN.1000-5013.2014.03.0316]
 LIN Yuan-qing,ZHANG Guang-ya.Prediction of Optimum pH of G/11 Xylanases and the Relationship between the Location of Amino Acid and Optimum pH Value[J].Journal of Huaqiao University(Natural Science),2014,35(2):316.[doi:10.11830/ISSN.1000-5013.2014.03.0316]
[10]余路.电信客户流失的组合预测模型[J].华侨大学学报(自然科学版),2016,37(5):637.[doi:10.11830/ISSN.1000-5013.201605022]
 YU Lu.Combination Forecasting Model of Customer Churns in Telecom Industry[J].Journal of Huaqiao University(Natural Science),2016,37(2):637.[doi:10.11830/ISSN.1000-5013.201605022]

备注/Memo

备注/Memo:
华侨大学科研基金资助项目(03HZR7)
更新日期/Last Update: 2014-03-23