基于MiRfilter系统的毛果杨miRNA预测

上海大学学报(自然科学版) ›› 2010, Vol. 16 ›› Issue (4): 397-403.

基于MiRfilter系统的毛果杨miRNA预测

赵洁苑，龚云路，王翼飞

（上海大学理学院，上海 200444）

收稿日期:2009-02-20 出版日期:2010-08-30 发布日期:2010-08-30
通讯作者: 王翼飞(1948～)，男，教授，博士生导师,研究方向为计算分子生物学. E-mail:yifei_wang@staff.shu.edu.cn
基金资助:
国家自然科学基金资助项目（30871341）；上海市重点学科建设资助项目（S30104）；上海市教委重点学科建设资助项目（J50101）

Prediction of Populus trichocarpa miRNAs with Improved MiRfilter System

ZHAO Jie-yuan,GONG Yun-lu,WANG Yi-fei

(College of Sciences, Shanghai University, Shanghai 200444, China)

Received:2009-02-20 Online:2010-08-30 Published:2010-08-30

摘要/Abstract

摘要：

从参数训练、参数范围训练、候选成熟体打分等方面改进miRNA预测系统MiRfilter，使其适应拥有更长前体的植物miRNA的预测.预测毛果杨基因组上的miRNA，并对系统进行精度检验.利用MiRfilter系统共预测出3 860条候选miRNA；在110个正样本中，正确识别91条前体和80条成熟体，前体预测精度为82.73%，成熟体预测精度为72.73%；在毛果杨第4号染色体（LG_Ⅳ）上得到的1 968个负样本中，有12个数据可认为是miRNA，假阳性率为0.61%.

关键词: 植物miRNA；MiRfilter；毛果杨基因组；一类分类法；K最近邻分类器（KNN）

Abstract:

This paper improves the MiRfilter system by parameter, range of parameter and score in mature miRNAs in order to predict miRNAs in plants. We predict miRNAs in Populus trichocarpa genome and use its positive and negative samples to examine the accuracy of MiRfilter’s prediction. MiRfilter predicts 3 860 Populus trichocarpa miRNA candidates in all. It correctly identifies 91 precursors and 80 matures in 110 positive samples. Accuracies of the precursor and mature prediction reach 82.73% and 72.73%, respectively. We find 12 false positive miRNAs from 1 968 negative samples in LG_Ⅳ chromosome, and the false positive rate reaches 0.61%.

Key words: plant miRNA; MiRfilter; Populus trichocarpa genome; oneclass methods; K nearest neighbor (KNN)

中图分类号:

O 224

赵洁苑，龚云路，王翼飞. 基于MiRfilter系统的毛果杨miRNA预测[J]. 上海大学学报(自然科学版), 2010, 16(4): 397-403.

ZHAO Jie-yuan,GONG Yun-lu,WANG Yi-fei. Prediction of Populus trichocarpa miRNAs with Improved MiRfilter System[J]. Journal of Shanghai University（Natural Science Edition）, 2010, 16(4): 397-403.