Skip to main content

Table 2 Assessment on the GENIA and RLIMS-P corpora

From: Application of text-mining for updating protein post-translational modification annotation in UniProtKB

 

Acetylation

Glycosylation

Methylation

Phosphorylation

# events/documents

68

93

70

110

False negative

7

31

26

15

False positive

2

0

0

12

Recall

90%

66%

63%

86%

Precision

97%

100%

100%

89%

  1. #events is the number of acetylation, glycosylation or methylation events with site information on in the GENIA corpus, #documents is the number of abstracts positive for phosphorylation information in the RLIMP-P corpus.