Hyperparameter Tuning on Graph Neural Network for the Classification of SARS-CoV-2 Inhibitors

Abstract

COVID-19 is caused by the SARS-CoV-2 virus, which results in a range of symptoms, from mild to severe, and can lead to fatalities. As of October 2023, WHO has recorded 771 cases of COVID-19 globally. Various efforts have been made to control the spread of the virus, including vaccination, isolation measures, and intensive medical care. The emergence of new SARS-CoV-2 variants has led to the ongoing evolution of virus transmission. Continued research is essential to understand this virus and develop strategies to address the pandemic. Inhibitors of SARS-CoV-2 play a crucial role in the vaccine development process. Inhibitors can impede the virus's development, helping reduce disease severity and control the pandemic. The classification of inhibitors is expected to serve as a foundation for selecting compounds that can be developed into vaccines. This research develops a Graph Neural Network model for inhibitor classification and uses the random search method for hyperparameter tuning. Graph Neural Networks are chosen due to their excellent performance in modelling graph data. This study demonstrates the success of hyperparameter tuning in improving the performance of the Graph Neural Network for accurate classification of SARS-CoV-2 inhibitors.