期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：9
出版社：Journal of Theoretical and Applied
摘要：True prediction of protein coding regions in a deoxyribonucleic acid (DNA) is a major task in the field of Bioinformatics. Study of regions which code for proteins is a key aspect of disease identification and designing drugs. The sections of DNA that include protein coding information are known as exons. Mainly exon regions in the genes show three base periodicity (TBP), which serves as a base for all exon locating methods. For locating the exon regions many techniques have been applied successfully, but development is still needed in this area. Using signal processing methods, TBP can be easily determined. Adaptive signal processing techniques found to be apt due to their diverse ability to alter filter co-efficients depending on the genomic sequence. In this paper, we propose efficient an adaptive exon predictor (AEP) based on these deliberations for DNA sequence analysis and computing. In order to increase the exon locating capability, we develop various AEPs using normalized least mean forth algorithm (NLMF) and its variants. These proposed AEPs notably reduces computational complexity and provides better performance in terms of performance measures like sensitivity, specificity, and precision. It was shown that variable normalized least mean forth (VXENLMF) based AEP is found to be superior than NLMS in exon identification applications based on performance measures with Specificity 0.7468, Sensitivity 0.7562, and Precision 0.7523 at a threshold of 0.8 for a genomic sequence with accession AF009962. Also, this algorithm performs better with respect to convergence by normalization of step size. Finally the exon locating capability of various AEPs is tested using several real DNA sequences obtained from National Center for Biotechnology Information (NCBI) database and compared with existing LMS method. It was shown that proposed AEPs are more efficient for locating exon regions in a DNA sequence.
关键词：Adaptive Exon Predictor; Computational Complexity; Deoxyribonucleic Acid; Disease Identification; Exons; Three Base Periodicity
