Skip to main content
. 2012 Sep 7;3:7. doi: 10.1186/2041-1480-3-7

Table 4.

Measures for seven generalization queries

(A) Lipids GO:0044242 GO:0008299 GO:0008654          
Tool
GPM
G2P
GPM
G2P
GPM
G2P
 
 
(a) Number of results
4
26
9
16
25
27
 
 
(b) Relevant among (a)
3
20
1
2
5
11
 
 
(c) Total relevant
22
3
12
 
 
     
(d) Common results
1
2
5
 
 
     
(e) Relevant among (d)
1
0
4
 
 
     
Precision
0.750
0.769
0.111
0.125
0.200
0.407
 
 
Relative Recall
0.136
0.864
0.333
0.667
0.417
0.917
 
 
F-score
0.231
0.814
0.167
0.211
0.270
0.564
 
 
(B) Other
GO:0050658
GO:0033013
GO:0006805
GO:0048284
       
Tool
GPM
G2P
GPM
G2P
GPM
G2P
GPM
G2P
(a) Number of results
25
10
15
19
30
23
24
17
(b) Relevant among (a)
7
2
3
3
17
14
10
9
(c) Total relevant
9
6
26
16
       
(d) Common results
3
6
7
8
       
(e) Relevant among (d)
1
2
4
4
       
Precision
0.280
0.200
0.200
0.158
0.567
0.609
0.417
0.529
Relative Recall
0.875
0.250
0.600
0.600
0.680
0.560
0.625
0.563
F-score 0.424 0.222 0.300 0.250 0.618 0.583 0.500 0.545

Results’ sets sizes and values of precision, relative recall and F-score using GoPubMed and GO2PUB search tools for seven random queries: three lipid-related queries (part A) and four queries about other topics (part B). Values of precision, relative recall and F-score are calculated from (a), (b) and (c) lines. (d) and (e) lines provide GO2PUB and GoPubMed common results’ sets sizes and the number of common relevant results.