Skip to main content

Table 3 Corpus statistics for mutation impact extraction tasks

From: Benchmarking infrastructure for mutation text mining

 

Number of documents

Impact mutations∗

Impacts∗(mutation, protein property, impact direction)

Impact sentences

Impact sentences grounded to mutations

OMM Impact

40

223

-

2045

1997

EnzyMiner

38

172

282

440

440

DHLA

13

52∗∗

73

-

-

  1. (∗) - Unique per document.
  2. (∗∗) - The OMM Impact and Enzyminer corpora contain single point mutations as well as combined mutations. There are only single point mutations in the DHLA corpus.
Back to article page

Journal of Biomedical Semantics

ISSN: 2041-1480