Title :
The improved AMDF gene exon prediction
Author :
Xueying Zhang ; Qiang Li ; Xin Guan
Author_Institution :
Sch. of Electron. & Inf. Eng., Tianjin Univ., Tianjin, China
Abstract :
In order to improve the predictive accuracy and save the computation time, the improved average magnitude difference function (AMDF) is proposed in the paper. The AMDF was widely used to detect the gene exon as a time domain algorithm. In the paper the improved average magnitude difference function (AMDF) method-the sum of magnitude difference square function (SMDSF), which was proposed in the music signal processing, are firstly utilized in the gene detection. The predictive accuracy of the coding regions has increased 10% and 2% respectively for two different sequences and 5% as the statistical result for the GENESCAN database at a 10% false positive rate. SMDSF not only increases significantly in all kinds of performance index but also shorten the running time.
Keywords :
DNA; biology computing; genomics; signal processing; time-domain analysis; AMDF gene exon prediction; GENESCAN database; average magnitude difference function method; gene exon detection; sum of magnitude difference square function; time domain algorithm; Accuracy; Bioinformatics; DNA; Discrete Fourier transforms; Encoding; Feature extraction; Genomics; AMDF; CAMDF; DFT; DNA sequence; SMDSF; period-3 behavior;
Conference_Titel :
Natural Computation (ICNC), 2011 Seventh International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9950-2
DOI :
10.1109/ICNC.2011.6022375