Identifying Antibiotic Resistance in Pathogenic Bacteria through SVM and Neural Network Predictive Models

The development and widespread implementation of technologies for detecting antibiotic resistance in pathogenic bacteria are both urgent and instrumental for advancements in biology and medicine. This paper presents a study where DNA base sequences are utilized as sample data, categorized into susceptible and resistant groups. A predictive model based on Support Vector Machine (SVM) is employed to accurately distinguish between these groups by identifying specific DNA sequence loci. Additionally, a comparative analysis with neural network models is conducted to refine the classification and prediction methods for pathogenic bacteria. The findings indicate that the SVM model is effective in classifying and predicting the base sequence loci that are significantly associated with genetic mutations leading to antibiotic resistance in bacteria.