Analysis of Machine Learning Approaches for DNA Sequencing and Classification: An optimized Approach

Abstract

DNA sequencing is essential to contemporary research. It facilitates the advancement of many fields, including phylogenetics, genetics, and meta-genetics. DNA strands must be extracted and read in order to perform DNA sequencing. In order to improve prediction for DNA research and obtain the most accurate results, this research paper compares DNA sequencing using machine learning algorithms. It also aims to efficiently classify DNA sequences according to their features, improving the efficiency and accuracy of DNA sequence classification. The efficiency of various methods is evaluated and contrasted in the study using important metrics like as F1-score, accuracy, precision, and recall. The results indicated that for the human DNA sequence, the Random Forest approach provided the best accuracy of 0.9292 and F1-score of 0.930, while the Genetic algorithm produced higher accuracy of 0.91 and F1-score of 0.913. The potential advancement of genomics research, customized medicine, and various scientific applications that rely on precise classification of DNA sequences is presented by the combination of machine learning and DNA sequencing.