Classification of DNA Sequence Using Soft Computing Techniques: A Survey

Abstract

Objectives: This survey detects which methodology of soft computing are used frequently together to solve the problems of Deoxyribonucleic acid (DNA) sequencing and provides an overview of underlying concepts commonly used for DNA classification using soft computing technique. Methods/Analysis: DNA sequence classification is a significant problem in computational biology. The DNA sequence is used to identify differences and similarities between organisms within a species. The selection of attributes is primary criteria in DNA classification. DNA sequence classification techniques involve for origin of particular characteristics from the progressions. Different species have distinct genetic structure. Findings: The distinctive asset of soft computing is that helps to learn from empirical procedure that helps for DNA classification. The major components of Soft Computing are Fuzzy Sets (FS), Artificial Neural Networks (ANN), Genetic algorithms (GAs), Evolutionary Strategies (ES), Support Vector Machines (SVM), Rough Sets (RS), Simulated Annealing (SA), biological inspired Swarm Optimization (SO), Ant Colony Optimization (ACO) and Tabu Search (TS). Soft Computing techniques are recognized as gorgeous options to the standard, conventional hard computing methods. Novelty /Improvement: This paper presents to identify the DNA sequences using the different classification approaches have been proposed by various researchers.