Prediction of Drug-Target Interaction Using Random Forest in Coronavirus Disease 2019 Case

Abstract

Coronavirus disease 2019 is an infectious disease that causes severe respiratory, digestive, and systemic infections that caused a pandemic in 2019. One of the focuses of the drug development process to fight the coronavirus disease 2019 is by carrying out drug repurposing. This study uses random forest with a feature-based chemogenomics approach on the drug-target interaction data of coronavirus disease 2019. The feature extraction process is carried out on compounds and protein using PubChem fingerprint and amino acid composition respectively. Feature selection using XGBoost is done to reduce the data dimension. The random undersampling process was also carried out to solve the problem of imbalanced data in the dataset. Using the cross-validation process, the random forest model produced an average accuracy value of 0.98, recall value of 0.92, precision value of 0.95, AUROC value of 0.95, and F1 score of 0.93. The random forest model also produced an accuracy value of 0.99, recall value of 0.93, the precision value of 0.94, AUROC value of 0.99, and F-measure of 0.94 when used to predict the original dataset (dataset without random undersampling process).