Fig. 3From: Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets Model performance on DUD-E, Human and C. elegans (classification). Three-fold cross-validation and random-guess ROC curves plotted in different colors. a DUD-E, mean AUC = 0.959; b Human, mean AUC = 0.948; c C. elegans, mean AUC = 0.960Back to article page