Fig. 1. Schematic illustration of the analytic workflow for constructing antioxidant compound prediction models employing five ML algorithms.
ML, machine learning; ABTS, 2,2’-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid); DPPH, 2,2-diphenyl-1-picrylhydrazyl; SMILES, Simplified Molecular Input Line Entry System; ECFP-4, Extended-Connectivity Fingerprints with a radius of 4; RF, Random Forest; SVM, Support Vector Machine; XGB, XGBoost; LR, Logistic Regression; DNN, Deep Neural Network.
© Korean J Physiol Pharmacol
