DNA Classification For Finding E.coli

This study presents an innovative approach to classify DNA sequences for the accurate detection of Escherichia coli (E.coli) bacteria using machine learning. E.coli is a common pathogen in various environments, including food and water, making its rapid identification crucial for public health and safety. Traditional methods for E.coli detection are often time-consuming and labor-intensive. Our project leverages state-of-the-art machine learning techniques to automate the classification of DNA sequences as either E.coli or non-E.coli. We utilize a comprehensive dataset of DNA sequences, that includes Escherichia coli and Non Escherichia coli samples, to train and evaluate our classification model. The key steps of our approach involve data preprocessing, feature extraction from DNA sequences, and the development of a robust classification model. We explore different machine learning models and algorithms which also include deep learning algorithms and models, to identify the best-performing model for this specific task. We have selected SVM model and MLP model. Our outcomes shows how effictively we move forward and accurately classify DNA sequences as E.coli or non-E.coli. This project contribute in the field of microbial observations which provide a faster and more efficient method for E.coli identification, with potential applications in food safety, environmental monitoring, and healthcare. We are evaluating our model by confusion matrix and accuracy. The f1-score for SVM model is 0.96. The f1-score for MLP model is 0.93.