Skip to main content

Table 9 Number and percentage of valid and invalid co-occurrences identified by PL-PPF in the GO and SDG datasets

From: Predicting protein functions by applying predicate logic to biomedical literature

Dataset

Number and percentage of proteins

Biological Process

Molecular Function

GO

dataset

Number of valid co-occurrences identified

39,928

9614

Number of invalid co-occurrences identified

22,458

6962

Percentage of valid co-occurrences identified

64%

58%

SGD

dataset

Number of valid co-occurrences identified

2152

858

Number of invalid co-occurrences identified

1986

1090

Percentage of valid co-occurrences identified

52%

44%