Skip to main content

Table 1 The LogicNet performance in predicting the GRNs and the logic functions, for 100 logic function simulations. The performance is evaluated at three levels, i.e., for undirected/directed networks and for directed logical networks in which the integrative detection of the directed edges and logic functions is evaluated

From: LogicNet: probabilistic continuous logics in reconstructing gene regulatory networks

 

Sample size

GRN

TPR

FPR

PPV

ACC

MCC

F-measure

PC-LogicNet

10

Undirected

0.48

0.05

0.82

0.79

0.51

0.61

Directed

0.42

0.08

0.51

0.84

0.37

0.46

Directed Logical

0.42

–

0.52

–

–

0.46

50

Undirected

0.50

0.05

0.84

0.80

0.53

0.63

Directed

0.44

0.08

0.53

0.84

0.39

0.48

Directed Logical

0.43

–

0.53

–

–

0.47

Fuzzy-LogicNet

10

Undirected

0.43

0.05

0.81

0.77

0.46

0.56

Directed

0.36

0.05

0.57

0.85

0.37

0.44

Directed Logical

0.09

–

0.13

–

–

0.10

50

Undirected

0.50

0.10

0.72

0.77

0.45

0.59

Directed

0.43

0.07

0.55

0.85

0.40

0.48

Directed Logical

0.08

–

0.10

–

–

0.09