Fig. 3

SCOUR performance on synthetic (a Smaller Synthetic Model and b Bigger Synthetic Model) and biological models (c S. cerevisiae and d E. coli) using noiseless training and test data. Bar graphs for accuracy, sensitivity, specificity, and PPV for each step of SCOUR in each tested model. Error bars represent the standard error of the mean (n = 30 from independent autogenerated training replicates)