加窗窄通带滤波器蛋白质编码区预测算法  

Prediction Algorithm for Protein Coding Regions Based on Windowed Narrow Pass-Band Filter

作　　者：马玉韬[1,2] 车进[1,2] 关欣[1] 滕建辅[1] 

机构地区：[1]天津大学电子信息工程学院,天津300072 [2]宁夏大学物理电气信息学院,银川750021

出　　处：《数据采集与处理》2013年第2期129-135,共7页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61162020)资助项目;宁夏自然科学基金(NZ1024)资助项目;宁夏高校科学研究项目(2011263)资助项目

摘　　要：改进Gabor小波变换(Modified Gabor wavelet transform,MGWT)蛋白质编码区预测算法给出的预测结果在当前所有的独立预测算法中准确率最高。本文提出了有限脉冲响应(Finite impulse response,FIR)加窗窄通带滤波器蛋白质编码区预测(Windowed narrow pass-band filter,WNPBF)算法。算法的主要部分包括:以F56F11.4序列为例给出了WNPBF阶数选择的依据,并据此设计WNPBF;为消除滤波器群延迟对预测结果产生的不良影响,对信号用边界对称延拓法进行预处理并对窄带滤波器滤波输出信号进行截取;为改善预测结果,设计滑动平均滤波器平滑功率谱密度曲线。在ALLSEQ和HMR195两个DNA序列集上获得预测准确率分别接近或达到独立预测算法的最高水平。通过比较后发现,所提出的WNPBF算法较MGWT算法效率更高,使用该算法可以直观和客观地比较不同滤波器的预测结果。The modified Gabor wavelet transform （MGWT） algorithm provides the best predic-tion results among the independent protein coding regions prediction algorithms. To be com-pared, a finite impulse response （FIR） windowed narrow pass-band filter （WNPBF）-based protein coding regions prediction algorithm is proposed. The algorithm is mainly consisted of the following parts： designing a WNPBF with appropriate length, which taking the DNA se-quence F56F11. 4 as an example; extending the DNA sequences using the boundary symmetric padding method and cutting off the beginning part of WNPBF outputs to eliminate the side effects of the group delay of the filter on prediction results; designing a moving average filter to smooth the power spectral density curve to get better prediction results. Experiments per-formed on DNA data sets ALLSEQ and HMR195 respectively give the prediction results which are close or equal to the best ones. The proposed algorithm is much more efficient than MGWT algorithm and can be used to compare the prediction results of different filters directly and ob-jectively.

关 键 词：蛋白质编码区预测 窄通带滤波器 FIR滤波器 窗函数法 群延迟 

分 类 号：TN713[电子电信—电路与系统] Q751[生物学—分子生物学]