DNA序列映射方法对蛋白质编码区预测准确率的影响

目的]探讨当前主要的DNA序列映射方法对蛋白质编码区的预测准确率的影响,寻找有效的映射方法。方法]以AC（Approximate Correlation）为碱基层的预测准确率的测度,采用FIR（Finite Impulse Response）窄通带滤波器预测算法研究各种映射方法对预测准确率的影响。结果]在ALLSEQ和HMR195 2个DNA序列集上,Voss法和Z-curve方法是较PN（Paired Numeric）法、EIIP（Electron-Io Interaction Potential）法和复数法更为有效的映射方法。结论]该研究结果为用预测结果的AC值来验证新映射方法的有效性奠定了基础,对利用生物信息学方法正确揭示DNA序列的结构具有重要意义。

Effects of Mapping Methods on Accuracy of Protein Coding Regions Prediction

Objective] To discuss the effects of major mapping methods for DNA sequence on the accuracy of protein coding regions prediction,and to find out the effective mapping methods.Method] By taking Approximate Correlation(AC) as the full measure of the prediction accuracy at nucleotide level,the windowed narrow pass-band filter(WNPBF) based prediction algorithm was applied to study the effects of different mapping methods on prediction accuracy.Result] In DNA data sets ALLSEQ and HMR195,the Voss and Z-Curve methods are proved to be more effective mapping methods than paired numeric(PN),Electron-ion Interaction Potential(EIIP) and complex number methods.Conclusion] This study lays the foundation to verify the effectiveness of new mapping methods by using the predicted AC value,and it is meaningful to reveal DNA structure by using bioinformatics methods.