Skip to main content
EURASIP Journal on Bioinformatics and Systems Biology

Table 3 Performance results

From: Reverse Engineering of Gene Regulatory Networks: A Comparative Study

Name

Type

sen

spe

pre

AUC

DBN

D

0.030(0.084)

0.953(0.117)

0.041(0.119)

0.971(0.067)

—

 

U

0.050(0.119)

0.924(0.173)

0.064(0.138)

0.953(0.083)

—

 

B

0.084(0.196)

0.924(0.173)

0.099(0.193)

0.919(0.116)

—

NN

D

0.276(0.197)

0.660(0.216)

0.091(0.073)

0.800(0.131)

0.324

 

U

0.334(0.204)

0.617(0.278)

0.208(0.162)

0.768(0.157)

0.350

 

B

0.539(0.255)

0.574(0.278)

0.281(0.164)

0.628(0.147)

0.557

SSM

D

0.027(0.073)

0.973(0.053)

0.052(0.139)

0.973(0.068)

—

 

U

0.030(0.075)

0.975(0.048)

0.094(0.224)

0.970(0.071)

—

 

B

0.049(0.114)

0.975(0.048)

0.153(0.297)

0.951(0.110)

—

GGM

D

—

—

—

—

—

 

U

0.238(0.198)

0.585(0.290)

0.116(0.157)

0.868(0.145)

0.266

 

B

0.442(0.326)

0.585(0.290)

0.225(0.212)

0.695(0.185)

0.526

MI

D

—

—

—

—

—

 

U

0.196(0.129)

0.745(0.146)

0.163(0.124)

0.843(0.130)

—

 

B

0.287(0.177)

0.745(0.146)

0.239(0.170)

0.757(0.162)

—

PC0

D

—

—

—

—

—

 

U

0.177(0.154)

0.659(0.234)

0.106(0.153)

0.891(0.116)

0.253

 

B

0.513(0.228)

0.492(0.223)

0.220(0.174)

0.703(0.132)

0.506

PC1

D

—

—

—

—

—

 

U

0.228(0.161)

0.541(0.226)

0.105(0.131)

0.898(0.126)

0.249

 

B

0.545(0.225)

0.461(0.214)

0.219(0.168)

0.705(0.135)

0.502

PC2

D

—

—

—

—

—

 

U

0.186(0.136)

0.635(0.154)

0.108(0.125)

0.892(0.125)

0.249

 

B

0.493(0.186)

0.515(0.151)

0.217(0.157)

0.702(0.140)

0.504

PC3

D

—

—

—

—

—

 

U

0.221(0.154)

0.573(0.179)

0.108(0.102)

0.888(0.135)

0.250

 

B

0.526(0.223)

0.484(0.190)

0.217(0.142)

0.701(0.130)

0.506

SC0

D

—

—

—

—

—

 

U

0.285(0.195)

0.555(0.217)

0.129(0.135)

0.842(0.141)

0.298

 

B

0.491(0.247)

0.555(0.217)

0.230(0.175)

0.676(0.139)

0.528

SC1

D

—

—

—

—

—

 

U

0.272(0.186)

0.563(0.215)

0.127(0.135)

0.849(0.137)

0.291

 

B

0.518(0.233)

0.518(0.209)

0.231(0.173)

0.682(0.135)

0.521

SC2

D

—

—

—

—

—

 

U

0.256(0.165)

0.588(0.143)

0.125(0.117)

0.851(0.137)

0.290

 

B

0.500(0.188)

0.542(0.145)

0.229(0.155)

0.678(0.129)

0.523

  1. Results of each application applied on all 600 datasets. DBN: Dynamic Bayesian network; NN: Neural network; MI: ARACNE; PC: Partial correlation with Pearson correlation of given order; SC: Partial correlation with Spearman correlation of given order; SSM: State space model; GGM: Graphical Gaussian model. Type is the performance measure type, that can be D for directed graph, U for undirected graph, B for binary and undirected graph. sen, spe, pre, and d are defined in (10), (11), (12), and (7), respectively. AUC is the area under the ROC curve. The averaged values are given with standard deviation in parenthesis. The top value of each type and column is highlighted in boldface.
Back to article page