基于神经网络预测的SNP信息的剪接点识别算法研究

J4 ›› 2016, Vol. 38 ›› Issue (05): 885-890.

基于神经网络预测的SNP信息的剪接点识别算法研究

赵婧1，魏彬2，陈明淑1，张晓娟1

（1.西京学院控制工程学院，陕西西安 710123；2.武警工程大学，陕西西安 710086）

收稿日期:2015-04-16 修回日期:2015-07-10 出版日期:2016-05-25 发布日期:2016-05-25
基金资助:
西京学院科研基金（XJ140115）；武警工程大学基础研究基金（WJY201518）

A splice site prediction algorithm
based on SNP and neural network

ZHAO Jing1,WEI Bin2,CHEN Mingshu1,ZHANG Xiaojuan1

(1.School of Control Engineering,Xijing University,Xi’an 710123;2.Armed Police Engineering University,Xi’an 710086,China)

Received:2015-04-16 Revised:2015-07-10 Online:2016-05-25 Published:2016-05-25

摘要/Abstract

摘要：

随着基因组计划的完成，人们需要尽快从这些海量数据中了解基因组的结构，揭示生命的奥秘，剪接位点识别是其中的一个重要环节，然而到目前为止该问题仍未能得到很好的解决。在分析此问题时引入了第三代遗传标记单核苷酸多态性(SNP)，以期探索变异对剪接机制的影响；其次，对DNA序列的数字化进行了探讨。通过实验表明，单核苷酸多态性的引入对于剪接位点识别算法的性能有着一定的影响，此外文中提出的编码方法对预测精度的提升亦有正面作用，整体效果比目前常用方法有了大幅提升。

关键词: SNP, 剪接位点预测, 人工神经网络, 符号序列分析

Abstract:

Along with the progress of Human Genome Plan, people need to find out the genome structure from gained information. Recognition of splice sites is an essential part of this task. However, it is also a complicated problem, and satisfied results still cannot be reached. We design a splice site prediction algorithm based on BP network and SNP data to discover the influence of SNP on splice. In addition, a new encoding method is used to convert the DNA character sequences into decimal strings. Experimental results show the effectiveness of the SNP data and the new encoding method.

Key words: SNP;splice site prediction;artificial neural network;symbolic series analysis

赵婧1，魏彬2，陈明淑1，张晓娟1. 基于神经网络预测的SNP信息的剪接点识别算法研究[J]. J4, 2016, 38(05): 885-890.

ZHAO Jing1,WEI Bin2,CHEN Mingshu1,ZHANG Xiaojuan1 . A splice site prediction algorithm
based on SNP and neural network [J]. J4, 2016, 38(05): 885-890.

参考文献［11］

［1］	Moghimi F,Shalmani M T M,Sedigh A K,et al. Two new methods for DNA splice site prediction based on neurofuzzy network and clustering［J］. Neural Computing & Applications,2013,23(S1):407414.
［2］	Zhou Xiong. Splice sites identification based on multiscale component features and adjacent positions relationship features［J］. Computer Engineering and Application,2014,50(10):120123.(in Chinese)
［3］	Li Qin, Zhang Jin, Pian Cong, et al. Predicting the splice site based on position correlation weight matrix and incremental diversity of sequence component［J］. Acta Biophysica Sinica,2014,30(5):391400.(in Chinese)
［4］	Sun Bo, Li Xiaoxia, Li Chengguo. Recognition of splice sites based on fuzzy support vector machine［J］. Journal of Computer Applications,2011,31(4):11171120.(in Chinese)
［5］	Zuo Y,Zhang P,Liu L,et al. Sequencespecific flexibility organization of splicing flanking sequence and prediction of splice sites in the human genome［J］. Chromosome Research,2014,22(3):321334.
［6］	Zhang Q W,Peng Q K,Zhang Q,et al. Splice sites prediction of human genome using lengthvariable Markov model and feature selection［J］. Expert Systems with Applications,2010, 37(4):27712782.
［7］	Maji S,Garg D. Hybrid approach using SVM and MM2 in splice site junction identification［J］. Current Bioinformatics,2014,9(1):7685.
［8］	Bari A T M G,Reaz M R,Jeong BS. Effective DNA encoding for splice site prediction using SVM［J］. MatchCommunications in Mathematical and in Computer Chemistry,2014,71(1):241258.
［9］	Guo Shuo, Zhu Yisheng, Wang Qinghui. Predicting splice site by improved Bayesian classifier［J］. Journal of System Simulation,2011,23(7):14291432.(in Chinese)
［10］	Li Shaoyan,Deng Wei. Identification of splice sites based on probability statistical feature［J］. Computer Engineering and Applications,2011,47(31):182184.(in Chinesse)
［11］	Lü Jia, Peng Qinke. The extraction of splice features based on fast Fourier transform［J］. Transactions of Beijing Institute of Technology,2014,34(2):207210.(in Chinesse)
［12］	Roshyara N R,Kirsten H,Horn K,et al. Impact of preimputation SNPfiltering on genotype imputation results［J］. BMC Genetics,20140812.doi:10.1186/612863014.00885.
［13］	SegoviaJuarez J L, Colombano S, Kirschner D. Identifying DNA splice sites using hypernetworks with artificial molecular evolution［J］. Biosystems,2007,87(23):117124.
［14］	Talluri R,Wang J,Shete S. Calculation of exact pvalues when SNPs are tested using multiple genetic models［J］. BMC Genetics,20140320.doi:10.1186/47121561575.
［15］	Ning S W,Zhao Z X L,Ye J R,et al. LincSNP:A database of linking diseaseassociated SNPs to human large intergenic noncoding RNAs［J］. BMC Bioinformatics,20140520.doi:10.1186/1471210515152.
［16］	NNSplice:Splice site prediction by neural network, berkeley drosophila genome project［EB/OL］.［20131213］.http://www.fruitfly.org/seq_tools/splice.html.
［17］	GENIO/splice:Splice Site and Exon Prediction in Human Genomic DNA［EB/OL］.［20131213］.http://www.biogenio.com/splice/splice.cgi.
［18］	FSPLICE:FSPLICE 1.0,Prediction of potential splice sites in Homo_sapiens genomic DNA［EB/OL］.［20131213］.http://sun1.softberry.com/berry.phtml?topic=fsplice&group=programs&%20subgroup=gfind.
	附中文参考文献:
［2］	周雄.多尺度组分特征和位点关联特征相融合的剪接位点识别［J］.计算机工程与应用，2014,50(10):120123.
［3］	李琴，张瑾，姘聪,等.基于位置关联权重矩阵及序列组分的多样性增量识别剪接位点［J］.生物物理学报，2014,30(5):391400.
［4］	孙波，李小霞，李铖果.基于模糊支技向量机的剪接位点识别［J］.计算机应用，2011,31(4):11171120.
［9］	郭烁，朱义胜，王庆辉.一种改进的贝叶斯的分类器剪接位点预测［J］.系统仿真学报，2011,23(7):14291432.
［10］	李绍燕，邓伟.一种基于概率统计特征的剪接位点识别方法［J］.计算机工程与应用，2011,47(31):182184.
［11］	吕佳，彭勤科.基于快速傅里叶变换的剪接特征提取［J］.北京理工大学学报，2014,34(2):207210.

[1]	甘秋云. ED算法和SNP-index算法计算SNP位点的比较分析——以拟南芥为例[J]. 计算机工程与科学, 2022, 44(04): 707-712.
[2]	蔡钊，马林华，宋博，唐红. 基于ARIMA-ANN预测模型的能量感知路由算法[J]. J4, 2015, 37(06): 1064-1070.
[3]	张彦成段禅伦. 基于自组织特征映射神经网络的土壤分类[J]. J4, 2008, 30(10): 113-115.
[4]	黄同城[1,2] 丁友东[1]. 手写体数字识别与认证的小波特征提取[J]. J4, 2006, 28(10): 47-49.
[5]	夏阳陆余良孙乐昌. 多传感器网络信息数据融合技术研究[J]. J4, 2005, 27(2): 25-27.
[6]	王鹏白建军卢泽新. 卫星网络协议的仿真与模拟技术研究[J]. J4, 2004, 26(5): 4-6.
[7]	何小娟曾建潮徐玉斌. 基于思维进化算法的神经网络权值与结构优化[J]. J4, 2004, 26(5): 38-42.
[8]	王珑[1] 谭明峰[2]. 基于ART1人工神经网络的数据聚类[J]. J4, 2002, 24(2): 92-95.
[9]	王志坚蔡自兴. 一种新的Petri网推理方法[J]. J4, 2002, 24(2): 102-104.