Paper Info
Title
New Exon Prediction Techniques Using Adaptive Signal Processing Algorithms for Genomic Analysis.
Abstract
Substantial research and monetary aids to healthcare establishments are provided by cloud computing. A benign position to store and handle vast genome data is offered by cloud services. Labs for gene sequencing send out raw and contingent data over the Internet to multiple sequence collections under conservative flow of gene information. The use of cloud services also reduces the storage costs of deoxyribonucleic acid (DNA) sequencing. Here, an efficient and new bio-informatics genomic system is proposed by the use of cloud services from Amazon to access the stored gene data and process it. A key task in bio-informatics is to locate protein-coding sections in a gene sequence based on three base periodicity (TBP) is for disease diagnosis and design drugs. Here, a novel cloud-based adaptive exon predictor (AEP) using Amazon cloud services is proposed to improve the accuracy in exon finding ability as well as aimed at superior convergence. Noise in the input gene sequence given to the proposed AEPs is pre-processed using normalized LMS filtering. Computational complexity can be reduced using proposed data normalized form of least logarithmic absolute difference (NLLAD) algorithm and its error normalized variants. It was shown that sign regressor NLLAD (SRNLLAD) dependent AEP is efficient in exon forecast applications using different metrics for a performance like sensitivity 0.8037, precision 0.8052 along with specificity 0.8146 by different gene sequences considered from the National Center for Biotechnology Information (NCBI) databank. The proposed AEPs have shown upright performance than typical LMS and other AEPs in terms of exon prediction accuracy, convergence, and computational complexity. Their less computational complexity will be found attractive, and they are suitable to use in bio-informatics nano devices.
Year
DOI
Venue
2019
10.1109/ACCESS.2019.2923253
IEEE ACCESS
Keywords
Field
DocType
Amazon cloud services,bio-informatics,convergence,deoxyribonucleic acid,National Center for Biotechnology Information,base three periodicity
Convergence (routing),Normalization (statistics),Computer science,Algorithm,Filter (signal processing),Adaptive filter,Computational complexity theory,Absolute difference,The Internet,Cloud computing
Journal
Volume
ISSN
Citations 
7
2169-3536
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Srinivasareddy Putluri100.68
Md. Zia Ur Rahman211.71
Chandra Sekhar Amara300.34
Nagireddy Putluri400.34