Skip to main content
. 2013 Jul 6;7:57. doi: 10.1186/1752-0509-7-57

Figure 4.

Figure 4

Network reconstruction from incomplete perturbation data.X-axis represents the number of perturbations and Y-axis represents AUROC in panel (a) and AUPR in panel(b). The error-bars indicate the standard deviations of the corresponding AUROCs in panel (a) and AUPRs in panel (b). The results suggest that the networks reconstructed by BVSA is significantly more accurate than both LMML and random guesses even when only half of the MAPK modules were perturbed and no repetitions of the experiments were available.