Fig. 5.

Training an XAI model to distinguish between housekeeping and developmental enhancers. A The developmental and housekeeping enhancers used in the training step and their overlap with predicted super enhancers. B Confusion matrices statistics from individual bin predictions. Accuracy, precision, and recall were computed and plotted for the XAI model (see Fig. 1). C ROC curve for developmental vs housekeeping trained model. C, D Rules involved in predicting bins as belonging to developmental enhancers (C) and housekeeping enhancers (D); see Fig. 4A, B