基于拟比对CNN方法的人类p53癌症基因二级数据库构建及分析

Construction and Analysis of Secondary Database of Human Cancer Gene p53 Based on Quasi Alignment Cellular Neural Network

DOI：10.3969/j.issn.1673-1689.2019.04.003

中文关键词: 二级数据库 癌症 p53基因序列 细胞神经网络 序列比对

英文关键词: secondary database,cancer,p53 gene sequence,cellular neural network,sequence alignment

基金项目:

摘要点击次数: 110

全文下载次数: 143

中文摘要:

以NCBI维护的一级数据库为数据源建立人类癌症p53核苷酸序列二级数据库，该数据库设计主要包括4个方面：癌症信息、p53序列信息、样本信息和参考文献信息。以XML格式为中间格式保存一级数据库数据，并通过解析提交到二级数据库，初步实现数据的检索、链接和统计分析等功能。本文提出一种拟比对CNN方法对p53癌症基因序列进行比对分析，通过改善传统CNN相似度评估公式，增强两序列全局比对相似度的敏感性和可靠性。结果表明，将改进的序列比对算法应用于乳腺癌和非小细胞肺癌p53外显子基因序列比对，发现外显子5突变后序列比对结果存在较大差异，可以作为区别这两种癌症的参考。此外，通过将一级数据库以XML形式转化成二级数据库，实现了网络数据与本地数据的动态交换。

英文摘要:

Using the biological primary databases at the National Center for Biotechnology Information（NCBI），We construct a secondary database of human cancer-related nucleotides p53. The database design mainly includes four aspects：cancer information，p53 sequence information，sample information and reference information. We store the data from NCBI in XML file，then by parsing the files to secondary database and initially realize the data of searching，linking ，statistical analysis and other functions. p53 cancer gene sequences are compared by quasi alignment one dimensional cellular neural network method，and the sensitivity and reliability of the global alignment of the two sequences are enhanced by improving the similarity evaluation formula. We applied the improved sequence alignment algorithm in non small cell lung cancer and breast cancer p53 gene sequence alignment , the result shows that there are great differences in mutant p53 Exon 5 of two cancer sequences which can be used to discriminate these two cancers. In addition, by transforming the primary database into the secondary database in the form of XML, the dynamic exchange of network data and local data is redized, which provides an excellent platform for the study of cancer and p53 gene.

查看全文 查看/发表评论 下载PDF阅读器