Limits...
A fast algorithm for exonic regions prediction in DNA sequences.

Saberkari H, Shamsi M, Heravi H, Sedaaghi MH - J Med Signals Sens (2013)

Bottom Line: First, the symbolic DNA sequences were converted to digital signal using the electron ion interaction potential method.Then, to reduce the effect of background noise in the period-3 spectrum, we used the discrete wavelet transform at three levels and applied it on the input digital signal.Simulation results confirmed that the proposed method can be used as a promising tool for exon prediction in DNA sequences.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering, Sahand University of Technology, Tabriz, Iran.

ABSTRACT
The main purpose of this paper is to introduce a fast method for gene prediction in DNA sequences based on the period-3 property in exons. First, the symbolic DNA sequences were converted to digital signal using the electron ion interaction potential method. Then, to reduce the effect of background noise in the period-3 spectrum, we used the discrete wavelet transform at three levels and applied it on the input digital signal. Finally, the Goertzel algorithm was used to extract period-3 components in the filtered DNA sequence. The proposed algorithm leads to decrease the computational complexity and hence, increases the speed of the process. Detection of small size exons in DNA sequences, exactly, is another advantage of the algorithm. The proposed algorithm ability in exon prediction was compared with several existing methods at the nucleotide level using: (i) specificity - sensitivity values; (ii) receiver operating curves (ROC); and (iii) area under ROC curve. Simulation results confirmed that the proposed method can be used as a promising tool for exon prediction in DNA sequences.

No MeSH data available.


Results of the algorithms for identification of the exonic regions on the gene sequence AJ223321.1: (a) DFT, (b) MS-filter, and (c) Proposed algorithm
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3959004&req=5

Figure 11: Results of the algorithms for identification of the exonic regions on the gene sequence AJ223321.1: (a) DFT, (b) MS-filter, and (c) Proposed algorithm

Mentions: In this paper, to evaluate the performance of the proposed algorithm, DFT[8] and Multi-Stage filter (MS)[33] methods are implemented. Figures 8-11a and b show results of implementation of these methods and the proposed algorithm in identifying protein coding regions in four gene sequences explained above. As can be seen, the accuracy of the DFT method for protein coding regions estimation is not high due to the noise associated with the original signal. However, the MS filter resulted a good spectral component compared to DFT and reduced the computational complexity. Also, the non-coding regions are relatively suppressed in it, but this method cannot recognize the small size exonic regions. As shown in Figures 8-11c, the large amount of noise is removed in the proposed method due to applying the DWT, and small size of exons (For example, first exon in F56F11.4 gene sequence) can be identified because of using the Goertzel algorithm.


A fast algorithm for exonic regions prediction in DNA sequences.

Saberkari H, Shamsi M, Heravi H, Sedaaghi MH - J Med Signals Sens (2013)

Results of the algorithms for identification of the exonic regions on the gene sequence AJ223321.1: (a) DFT, (b) MS-filter, and (c) Proposed algorithm
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3959004&req=5

Figure 11: Results of the algorithms for identification of the exonic regions on the gene sequence AJ223321.1: (a) DFT, (b) MS-filter, and (c) Proposed algorithm
Mentions: In this paper, to evaluate the performance of the proposed algorithm, DFT[8] and Multi-Stage filter (MS)[33] methods are implemented. Figures 8-11a and b show results of implementation of these methods and the proposed algorithm in identifying protein coding regions in four gene sequences explained above. As can be seen, the accuracy of the DFT method for protein coding regions estimation is not high due to the noise associated with the original signal. However, the MS filter resulted a good spectral component compared to DFT and reduced the computational complexity. Also, the non-coding regions are relatively suppressed in it, but this method cannot recognize the small size exonic regions. As shown in Figures 8-11c, the large amount of noise is removed in the proposed method due to applying the DWT, and small size of exons (For example, first exon in F56F11.4 gene sequence) can be identified because of using the Goertzel algorithm.

Bottom Line: First, the symbolic DNA sequences were converted to digital signal using the electron ion interaction potential method.Then, to reduce the effect of background noise in the period-3 spectrum, we used the discrete wavelet transform at three levels and applied it on the input digital signal.Simulation results confirmed that the proposed method can be used as a promising tool for exon prediction in DNA sequences.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering, Sahand University of Technology, Tabriz, Iran.

ABSTRACT
The main purpose of this paper is to introduce a fast method for gene prediction in DNA sequences based on the period-3 property in exons. First, the symbolic DNA sequences were converted to digital signal using the electron ion interaction potential method. Then, to reduce the effect of background noise in the period-3 spectrum, we used the discrete wavelet transform at three levels and applied it on the input digital signal. Finally, the Goertzel algorithm was used to extract period-3 components in the filtered DNA sequence. The proposed algorithm leads to decrease the computational complexity and hence, increases the speed of the process. Detection of small size exons in DNA sequences, exactly, is another advantage of the algorithm. The proposed algorithm ability in exon prediction was compared with several existing methods at the nucleotide level using: (i) specificity - sensitivity values; (ii) receiver operating curves (ROC); and (iii) area under ROC curve. Simulation results confirmed that the proposed method can be used as a promising tool for exon prediction in DNA sequences.

No MeSH data available.