基于全相位频谱分析的基因识别算法研究  

Gene Prediction Based on All-Phase Spectrum Analysis

作　　者：王飞宇[1] 郑紫微[1] 杨任尔[1] 

机构地区：[1]宁波大学信息科学与工程学院,浙江宁波315211

出　　处：《宁波大学学报（理工版）》2016年第2期37-42,共6页Journal of Ningbo University：Natural Science and Engineering Edition

基　　金：国家自然科学基金(60972063);浙江省杰出青年科学基金(R111041);宁波市科技创新团队(2011B81002);教育部高等学校博士学科点专项科研基金(20113305110002)

摘　　要：为对未知基因序列的编码区进行预测,利用基因编码区存在的频谱3-周期性质,在传统的固定窗口长度滑动窗算法的基础上,提出了一种改进型的基因识别算法.新算法将全相位谱分析技术与多采样率数字信号处理技术相结合,有效地降低了传统滑动窗算法中存在的截断效应,减少了计算量并且可实现流水线操作.最后通过计算机仿真将该算法所得结果与其他识别算法所得结果相比较,结果表明该算法在核苷酸水平上有较高的预测准确性.The 3-base periodicity, which exists in the coding regions, is adopted to predict the location of coding regions in an unknown DNA sequence. Based on the fixed-length sliding window approach, an improved algorithm for gene prediction is proposed, which combines all-phase FFT spectrum analysis and multi-rate digital signal processing. The method possesses some merits including reducing the truncation effect, improving the operation efficiency and providing a scheme for pipeline operation. Computer simulation results are given to compare the presented approach with other method for gene prediction, indicating that the proposed method achieves a satisfactory prediction accuracy at the nucleotide level.

关 键 词：基因识别 3-周期性 全相位FFT谱分析 截断效应 

分 类 号：TN911.6[电子电信—通信与信息系统]