Development and rigorous validation of antimalarial predictive models using machine learning approaches

The large collection of known and experimentally verified compounds from the ChEMBL database was used to build different classification models for predicting the antimalarial activity against Plasmodium falciparum. Four different machine learning methods, namely the support vector machine (SVM), random forest (RF), k-nearest neighbour (kNN) and XGBoost have been used for the development of models using the diverse antimalarial dataset from ChEMBL. A well-established feature selection framework was used to select the best subset from a larger pool of descriptors. Performance of the models was rigorously evaluated by evaluation of the applicability domain, Y-scrambling and AUC-ROC curve. Additionally, the predictive power of the models was also assessed using probability calibration and predictiveness curves. SVM and XGBoost showed the best performances, yielding an accuracy of ~85% on the independent test set. In term of probability prediction, SVM and XGBoost were well calibrated. Total gain (TG) from the predictiveness curve was more related to SVM (TG = 0.67) and XGBoost (TG = 0.75). These models also predict the high-affinity compounds from PubChem antimalarial bioassay (as external validation) with a high probability score. Our findings suggest that the selected models are robust and can be potentially useful for facilitating the discovery of antimalarial agents.