Table 4. Average performance measures for different network computed using correlation reconstructions for thresholds 0 (REL), 0.4 and 0.8 with standard deviations in parentheses.

Measures
AUPR	0.26(0.06)	0.19(0.07)	0.05(0.02)	0.24(0.06)	0.20(0.06)	0.06(0.01)
AUROC	0.74(0.02)	0.61(0.04)	0.51(0.01)	0.70(0.04)	0.61(0.03)	0.51(0.00)
Pr1Rec	0.73(0.30)	0.73(0.30)	0.38(0.43)	0.84(0.36)	0.84(0.36)	0.84(0.36)
Pr10Rec	0.67(0.18)	0.67(0.17)	0.05(0.01)	0.73(0.15)	0.73(0.15)	0.05(0.01)
Pr50Rec	0.16(0.04)	0.06(0.01)	0.04(0.01)	0.11(0.03)	0.06(0.01)	0.04(0.01)
Pr80Rec	0.06(0.00)	0.04(0.01)	0.04(0.01)	0.05(0.01)	0.04(0.01)	0.04(0.01)
AUPR score	45.53	30.75	2.30	39.12	32.02	3.24
AUROC score	17.75	5.63	0.45	13.48	5.84	0.52
Overall score	31.64	18.19	1.38	26.30	18.93	1.88

Pr1Rec, Pr10Rec, Pr50Rec, Pr80Rec represent precision at 1%, 10%, 50%, and 80% recall when all (₁₀₀) and only half of the perturbations (₅₀) are considered.