Dynamic probabilistic threshold networks to infer signaling pathways from time-course perturbation data

BMC Bioinformatics

Table 1 Performance comparison of D-PBTN, PBTN, DEPN and BDAGL on simulated data

Shown are achieved values of the area under the ROC curve (AUC_ROC) and the area under the PR curve (AUC_PR). Values shown are median values over 100 iterations. Inference was performed on the SN1 data, with data with different levels of noise and missing values, on the SN2 data including a negative feedback loop, and on the SN3 (KEGG) data set. Note that BDAGL cannot handle missing values. The upper part of the table shows the area under the ROC curve, while the lower part of the table shows the area under the PR curve.

ISSN: 1471-2105