Identification of Exon segments in DNA sequences using Modified Normalized Adaptive Algorithms
Md. Zia Ur Rahman1, Farmanulla Shaik2, SrinivasareddyPutluri3
1Md Zia Ur Rahman, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Green Fields, Vaddeswaram, Guntur-522502, Andhra Pradesh, India.
2Farmanullah Shaik, Department of Electronics and Communication Engineering, Kesanupalli, Narasaraopeta, 522601, Guntur, Andhra Pradesh, India.
3Srinivasareddy Putluri, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Green Fields, Vaddeswaram, Guntur-522502, Andhra Pradesh, India.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 747-751 | Volume-8 Issue-8, June 2019 | Retrieval Number: E3142038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A key task of genomics area is precisely tracing protein coding sections in a gene sequence. For identification of ailments and designing the drugs, analysis of these coding segments plays a crucial role. Information required for coding of proteins is present in gene fragments termed as Exons. Henceforth tracing the protein coding fragments of DNA is a key part in genomics. The elementary units in structure of DNA are Nucleotides. Three base periodicity (TBP) remains a typical property displayedthru only protein coding sections and not present withinintron segments of DNA. TBP of exon segments can be easily predicted using Signal processing techniques. Amongst several techniques, adaptive techniques are promising due to their capability to alter coefficients of weight based on deoxyribonucleic acid (DNA) sequence. From these deliberations, we propose an adaptive exon predictor (AEP) using Modified Normalized Least Mean Square (MNLMS) algorithm. To minimize computational complexity of the proposed techniques, we combined MNLMS based AEP with its sign-based variants. It was shown that AEP based on Sign Regressor MNLMS standsmucheffective in applications relation to exon identification using measures like Sensitivity, Specificity and Precision. This greatly reduces computational complexity, so that projected AEPs are attractive in nano devices. Finally, the exon locating ability of different AEPs is verified by gene sequences considered from the renowned genomic data base NCBI databank.
Keyword: Adaptive exon predictor, Ailments, Computational complexity, Deoxyribonucleic acid, Disease identification, Nucleotide, Three base periodicities.
Scope of the Article: Data Visualization using IoT.