Comparative Analysis of Machine Learning Algorithms for Predicting Drug Mechanism of Action

Predicting the Mechanism of Action (MoA) of drugs is a crucial step in drug discovery, influencing both the efficacy and safety of therapeutic interventions. This study undertakes a comparative analysis of four machine learning algorithms-K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Trees (DT), and Random Forest (RF)-to identify the most effective method for MoA prediction. Employing Classifier Chains and Binary Relevance techniques, we explore the impact of feature selection and data balancing strategies on the performance of these algorithms. Results demonstrate that SVM and RF generally provide the best performance, especially in handling complex, feature-rich datasets. The study highlights the importance of tailored data preprocessing and balancing to optimize algorithmic predictions in pharmacological applications. Our findings offer significant insights into machine learning implementations in drug discovery, providing a foundation for further research into advanced predictive models.