人工神经原网络处理PCR数据在细菌鉴定中的应用  

Artificial neural network aided bacterial identification

作　　者：刘毅[1] 徐维家[1] 李妍[1] 

机构地区：[1]大连市中心医院检验科,辽宁大连116033

出　　处：《中国微生态学杂志》2009年第5期468-470,473,共4页Chinese Journal of Microecology

摘　　要：目的16S rRNA和16S-23S rRNA间区片段是常用细菌分类鉴定靶点,本研究探讨人工神经原网络(ANN)对上述位点PCR扩增产物数据分析在细菌快速鉴定方面的价值。方法2对16S rRNA基因荧光引物和1对16S-23S rRNA区间基因引物用于扩增血液标本中分离出的317株细菌。相关毛细管电泳(CE)限制性片段长度多态性(RFLP)和单链构象多态性(SSCP)数据进行人工神经原网络分析。结果16S-23S rRNA基因的RFLP数据对未知菌鉴定的准确率高于16S rRNA基因的SSCP数据,分别为98.0%和79.6%。结论实验证明了人工神经原网络作为一种模式识别方法对于简化细菌鉴定十分有价值。Objective The 16S ribosomal ribonucleic acid （rRNA） and 16S-23S rRNA spacer region genes were commonly used as taxonomic and phylogenetic tools. In this study, artificial neural network （ANN） analysis was discussed in view of bacterial identification. Method Two pairs of fluorescent-labeled primers for 16S rRNA genes and one pair of primers for 16S-23S rRNA spacer region genes were selected to amplify target sequences of 317 isolates from positive blood cultures. The polymerase chain reaction （PCR） products of both were then subjected to restriction fragment length polymorphism （RFLP） analysis by capillary electrophoresis. For products of 16S rRNA genes, single-strand conformation polymor- phism （SSCP） analysis was also performed directly. Result When the data were processed by ANN, the accuracy of prediction based on 16S-23S rRNA spacer region gene RFLP data was much higher than that of prediction based on 16S rRNA gene SSCP analysis data （98.0% vs. 79.6% ）. Conclusion This study proved that the utilization of ANN as a pattern recognition method was a valuable strategy to simplify bacterial identification.

关 键 词：毛细管电泳 人工神经原网络 单链构象多态性 限制性片段长度多态性 

分 类 号：O212.1[理学—概率论与数理统计]