An organism’s genetic information is contained in its genome. A clinician can learn about a patient’s genetic composition that is, the genetic information carried out in the human body by sequencing thousands or even millions of DNA molecules in that individual. This technique is essential for identifying the variants and mutations that exist inside a particular genetic illness. This data is used by medical professionals and researchers to better understand the patient’s present state of health and assist in developing treatment and surgical plans. DNA sequencing is used to detect epidemics, discover a person’s past medical history, and develop more effective treatments for serious illnesses like cancer and rheumatoid arthritis. Drug manufacturers may be able to target groupings of people who are related genetically by understanding each patient’s distinct genetic profile. This may lead to more precise and customised information, such as the medicine type and dosage amount. Therefore, DNA sequencing is essential to the process of biological research. To sequence the DNA on a human dataset effectively, this paper proposed a machine learning model to do this task. The proposed model divided into important steps, that are: data preprocessing including encoding the DNA sequence with K-mer counts, frequency extraction, vectorization to convert data into numerical and balancing the data with SMOTE. The data split into training and testing and then loaded to machine learning classifiers like Navie baye, Random Forest and Support Vector Machine. The results conduct that Navie Baye achieves a high accuracy with 93.37% when compared with other algorithms. This study analysis will help us determine which algorithm performs better and can provide satisfying accuracy.