Table 2

Correlation between predicted and known CRMs. The performance of six different algorithms on a common data set is compared in this table. For each sequence, the Matthews correlation coefficient is calculated by checking whether each position is a TP, TN, FP, or FN and using the equation listed in the Methods section. The sum of the correlation coefficients gives a cumulative score for each algorithm on this data set.

Gene

CRMs

HexDiff

Ahab

Cluster Buster

MSCAN

MCAST

LWF


btd

1

0.70

0.57

0.19

0.01

0.07

0.10

ems

3

0.00

0.00

-0.03

0.12

-0.01

-0.01

eve

6

0.55

0.63

0.65

0.50

0.41

0.06

fkh

1

-0.03

-0.02

-0.02

-0.04

-0.02

-0.01

ftz

5

0.40

0.28

0.28

0.07

0.16

0.08

gt

1

0.27

0.42

0.33

0.35

0.15

0.03

h

5

0.71

0.63

0.53

0.30

0.37

0.08

hb

2

0.35

0.63

0.39

0.34

0.24

0.04

hkb

1

0.51

0.00

-0.02

-0.02

-0.08

0.09

kni

3

0.55

0.55

0.39

0.37

0.23

-0.05

kr

3

0.43

0.00

0.77

0.20

0.11

-0.03

oc

2

0.70

-0.02

0.00

0.11

0.02

0.07

prd

7

0.01

-0.07

0.16

0.07

-0.04

0.05

run

6

0.27

0.16

0.08

0.08

0.02

0.07

slp1

3

-0.07

0.15

-0.04

0.00

0.07

0.01

tll

3

0.35

0.56

0.58

0.19

0.12

-0.04

Total

52

5.71

4.48

4.24

2.64

1.81

0.52


Chan and Kibler BMC Bioinformatics 2005 6:262   doi:10.1186/1471-2105-6-262

Open Data