Digital Signal Processing Method for Gene Identification Based on Complex Fuzzy Distance Measures

Both computational and experimental methods are used to identify and describe genes within DNA sequences. Experimental methods such as cDNA cloning, RNA-Seq, and CRISPR/Cas9 evaluate gene expression and function directly, whereas computational approaches such as ab initio prediction, homology-based methods, and machine learning predict gene locations using DNA sequence features and comparisons. By measuring sequence similarity or divergence, distance measures are essential to these procedures and support gene grouping, phylogenetic analysis, comparative genomics, and sequence alignment. This paper aims to explore some distance measures (DMs) such as Hamming distance measure, Zhang distance measure, Normalized Hamming distance measure, and Zeeshan distance measure under the environment of complex fuzzy sets (CFSs). We studied some basic properties of complex fuzzy distance measures (CFDMs). Moreover, we employed CFDMs to extract pertinent features from gene that provides uncertainty and ambiguous data. We proposed an innovative digital signal processing method for gene identification using CFDMs. We developed an algorithm utilizing CFDMs to identify a healthy gene out of several affected genes. To demonstrate the effectiveness and advancements of the proposed work, a comparison with various current methodologies was also conducted.