Skip to main content

Table 1 Summary of expert curated abstracts used in this study. The abstracts are partitioned into four categories based on the pathogen from which the epitopes are derived. Other refers to the pathogens that are not in the first three categories

From: Automating document classification for the Immune Epitope Database

Category

Number of abstracts

Relevant abstracts

Irrelevant abstracts

Category A-C pathogens

7577

1942

5635

Allergen

4992

1080

3912

Emerging and Re-emerging infectious diseases

2911

845

2066

Other

5430

1845

3585