[1]辛月振,孙贝贝,夏盛瑜.数据挖掘方法在生物实验数据上的应用[J].计算机技术与发展,2018,28(09):143-146.[doi:10.3969/ j. issn.1673-629X.2018.09.029]
 XIN Yue-zhen,SUN Bei-bei,XIA Sheng-yu.Application of Data Mining Method in Biological Experiment Data[J].,2018,28(09):143-146.[doi:10.3969/ j. issn.1673-629X.2018.09.029]
点击复制

数据挖掘方法在生物实验数据上的应用()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年09期
页码:
143-146
栏目:
应用开发研究
出版日期:
2018-09-10

文章信息/Info

Title:
Application of Data Mining Method in Biological Experiment Data
文章编号:
1673-629X(2018)09-0143-04
作者:
辛月振孙贝贝夏盛瑜
中国石油大学(华东) 计算机与通信工程学院,山东 青岛 266580
Author(s):
XIN Yue-zhenSUN Bei-beiXIA Sheng-yu
School of Computer &Communication Engineering,China University of Petroleum,Qingdao 266580,China
关键词:
生物信息学培养条件优化数据分类BP 神经网络遗传算法
Keywords:
bioinformaticsoptimization of culture conditionsdata classificationBP neural networkgenetic algorithm
分类号:
TP39
DOI:
10.3969/ j. issn.1673-629X.2018.09.029
文献标志码:
A
摘要:
桑黄是一种具有很大药用价值的真菌,其产物黄酮具有抗癌作用。 现阶段对桑黄黄酮的研究主要集中在多糖的药用机理、组成等方面。 鉴于桑黄很少存在于野生环境,桑黄黄酮类化合物大多是从实验室培养提取,因此桑黄的实验室培养成为一个非常有前景的研究方向。 为了解决生物实验试验周期长、实验数据难以利用的问题,利用桑黄生物实验所得到的数据,包括接种量、PH 值、初始液量、温度、种龄、发酵时间和转速等参数,利用数据挖掘的方法,建立高产、低产的分类模型对数据进行分类。 随后建立了基于高产数据集的 BP 神经网络预测模型。 最后用遗传算法寻找最佳培养条件。结果表明,预测准确率达 90%以上,且预测产量略高于实际产量。
Abstract:
Phellinus is a kind of fungus with great medicinal value,which is known as one of the elemental components in drugs avoiding cancers. The research on Phellinus focuses on polysaccharides,proteoglycans medicinal mechanism,composition and other aspects. Since Phellinus rarely exists in the wild environment,Phellinus flavonoids are mostly extracted from laboratory cultures. Cultivating Phellinus in the lab becomes a promising research branch. In order to solve the problem of long biological experiment period and difficult use of the experimental data,we use the data obtained by Phellinus experiment including inoculum size,PH value,initial liquid volume,temperature,seed age,fermentation time and speed and other parameters with data mining method to establish a high yield and low yield classification model. Then a BP neural network prediction model based on high yield dataset is established. Finally,the best culture condition is found by genetic algorithm. The result shows that forecasting accuracy rate is more than 90% and the yield we forecast is a slight increase than the real yield.

相似文献/References:

[1]孙秋凤.microRNA计算识别中的模式识别技术[J].计算机技术与发展,2010,(06):97.
 SUN Qiu-feng.Pattern Recognition Technology for MicroRNA Identification[J].,2010,(09):97.
[2]黄凯峰 何洁月.基于生物医学文献的知识发现研究[J].计算机技术与发展,2008,(02):62.
 HUANG Kai-feng,HE Jie-yue.Survey of Biomedicine Literature - Based Discovery[J].,2008,(09):62.

更新日期/Last Update: 2018-09-10