An efficient way of identification of protein coding regions of eukaryotic genes using digital FIR filter governed by Ramanujan's Sum

Abstract

Finding protein coding regions, i.e., exons in a gene is a complex problem due to its diverse nature. In this paper, a novel FIR filtering governed by Ramanujan's Sum is proposed for identification of protein coding regions in gene. The efficacy of the designed algorithms is tested on Caenorhabditis Elegans cosmid F56F11.4a, various benchmark datasets like GENSCAN, HMR195, ASP67, and, BG570, and compared to well-established algorithms based on Antinotch, Butterworth, and Comb filters. The numerical conversion of the biological sequence here is an integer sequence and Ramanujan's Sum always generates a periodic sequence of integer numbers. This results in reduced quantisation error and simple hardware implementation. The evaluation of the designed Ramanujan's Sum governed filtering is done at the exonic level, nucleotide level, and through ROC plots. The results obtained on gene F56F11.4 attain specificity of 82%, sensitivity 97%, and precision of 85% while the AUC value of ROC curve was calculated as 0.96 square units. These evaluation parameters reveal that the proposed method gives enhanced results while comparing it to other existing exon-finding techniques.