Skip to main content

Table 3 Occurrence of gold standard relations in the same sentence

From: Ranking relations between diseases, drugs and genes for a curation task

PharmGKB data set

 

In Same Sentence

In Diff. Sentences

 

Relation

Absolute

Relative

 

Relative

Total

Dr-Dr

111

86.7

17

13.3

128

Ge-Ge

113

80.1

28

19.9

141

Dr-Ge

2 895

75.0

963

25.0

3 858

Di-Ge

2 009

64.8

1 093

35.2

3 102

Di-Dr

816

63.8

463

36.2

1 279

Di-Di

13

59.1

9

40.9

22

All

5 957

69.8

2 573

30.2

8 530

CTD data set

 

In Same Sentence

In Diff. Sentences

 

Relation

Absolute

Relative

 

Relative

Total

Di-Ge

3 457

75.6

1 118

24.4

4 575

Dr-Ge

23 123

67.0

11 365

33.0

34 488

Dr-Di

3 948

66.6

1 982

33.4

5 930

All

30 528

67.9

14 465

32.1

44 993

  1. Distribution of all gold standard relations where both entities could be identified by our term recognizer. An occurrence of a relation is categorized as "In Same Sentence" if there exists at least one sentence in a given abstract where both entities co-occur. An occurrence of a relation is categorized as "In Different Sentences" if both entities can be found in a given abstract but never co-occur together in the same sentence. For these tables metadata such as MeSH terms and chemical substance lists were not included.