Skip to main content

Table 4 Evaluation results obtained with the CESSM evaluation tool.

From: IntelliGO: a new vector-based semantic similarity measure including annotation origin

Metrics

Method

  

SimGIC

SimUI

RA

RM

RB

LA

LM

LB

JA

JM

JB

IntelliGO

 

ECC

0.62

0.63

0.39

0.45

0.60

0.42

0.45

0.64

0.34

0.36

0.56

0.65

 

Pfam

0.63

0.61

0.44

0.18

0.57

0.44

0.18

0.56

0.33

0.12

0.49

0.48

All EC

SeqSim

0.71

0.59

0.50

0.12

0.66

0.46

0.12

0.60

0.29

0.10

0.54

0.40

 

ECC

0.58

0.57

0.37

0.47

0.48

0.38

0.51

0.51

0.37

0.46

0.51

0.48

 

Pfam

0.58

0.55

0.43

0.44

0.52

0.42

0.42

0.51

0.33

0.34

0.45

0.43

Non-IEA EC

SeqSim

0.66

0.59

0.46

0.48

0.65

0.41

0.40

0.59

0.31

0.36

0.52

0.43

  1. Table 4: Pearson linear correlation coefficients are displayed for the ECC (Enzyme Classification Comparison), Pfam, and sequence similarity metrics (SeqSim). The Molecular Function GO annotation is used including (first three rows) or excluding (last three rows) annotation terms with IEA evidence codes. The column headings are listed as: SimUI: Union Intersection similarity; RA: Resnick Average; RM: Resnick Max; RB: Resnick Best match; LA: Lord Average; LM: Lord Max; LB: Lord Best match; JA: Jaccard Average; JM: Jaccard Max; JB: Jaccard Best match.