Skip to main content

Table 7 Performance of physicochemical descriptor classifier on an independent test data.

From: LacSubPred: predicting subtypes of Laccases, an important lignin metabolism-related enzyme class, using in silico approaches

Cluster #

ACC

ERR

MCC

PER

SEN

SPE

FN

FP

TP

TN

cluster-0

100

0

1

100

100

100

0

0

3

30

cluster-1

97

0.03

0.851

100

75

100

1

0

3

29

cluster-2

100

0

1

100

100

100

0

0

3

30

cluster-3

97

0.03

0

0

0

100

1

0

0

32

cluster-4

100

0

1

100

100

100

0

0

2

31

cluster-5

97

0.03

0.909

100

86

100

1

0

6

26

cluster-6

100

0

1

100

100

100

0

0

3

30

cluster-7

100

0

1

100

100

100

0

0

3

30

cluster-8

97

0.03

0.851

100

75

100

1

0

3

29

cluster-9

100

0

1

100

100

100

0

0

1

32

cluster-10

97

3.03

0.696

50

100

97

0

1

1

31

cluster-11

97

3.03

0.696

50

100

97

0

1

1

31

Overall

97.98

1.02

0.8678

87.88

87.88

98.90

-

-

-

-

  1. ACC: accuracy, ERR: error, MCC: Matthews Correlation Coefficient, PER: Precision, SEN: Sensitivity, SPE: Specificity, FN: False Negatives, FP: False Positives, TP: True Positives, TN: True Negatives.