Advanced protein coding region prediction applying robust SVD algorithm

摘要

Prediction of protein coding region has been one of the challenging issues in the context of Genomic Signal Processing and bioinformatics. This paper presents a variation of the Singular Value Decomposition (SVD) algorithm based on the pseudo EIIP mapping for exon location detection. The spectral peaks at 1/3 frequency component position of DNA sequence are utilized to identify the exons location. In addition to this three distinct threshold formulations have been used to investigate the performance of the algorithm in terms of various parameters like accuracy, sensitivity, specificity, geometric-mean and execution time. Moreover several other standard numerical mapping schemes and algorithms have been modeled and tested for comparison purpose which proves the efficiency of the algorithm.