Evaluation metrics were used to verify the robustness of PCB against a series of variations in the data using multiplicative exponential noise (with CVs ranging from 0% to 30%).

(A) and (B) The root mean square error (RMSE) and Spearman correlation coefficients were employed to evaluate the accuracy of the temporal progression inference. (C),(D),(E) and (F) The AUC, accuracy, positive predictive value (PPV) and Matthews correlation coefficient (MCC) were employed to evaluate the robustness of the reconstructed regulatory relationships between alternative splicing events and RNA-binding proteins.