Genomic Insights Revealed: Multiclass DNA Sequence Classification Using Optimized Naive Bayes Modeling

In this studies paper, we explore the use of Naive Bayes modeling to categorise multiclass DNA sequences, in particular that specialize in human, chimpanzee, and canine genomes. With the substantial quantity of genomic facts available, it’s miles vital to have accurate techniques for species identification in both natural research and other fields. Our observe makes use of a complete technique that includes k-mer extraction and vectorization the usage of CountVectorizer, along with a rigorous hyperparameter tuning method for the Naive Bayes model. We inspect the suitability of Naive Bayes in studying genomic statistics and its capacity to find the pattern of DNA sequences. To set the basis for our assessment, we very well take a look at the dataset, which include preprocessing steps and function extraction. With the massive amount of genomic data to be had, it’s far crucial to have accurate techniques for species identification in every natural studies and different fields. The fine-tuned Naive Bayes model achieve exceptional accuracy of 99% in classifying multiclass DNA sequences. Therefore, in this research paper, we find out the usage of Naive Bayes modeling to categorise multiclass DNA sequences, particularly focusing on human, chimpanzee, and dog genomes.