Skip to main content

Table 2 Training and test sets and number of protein pairs respectively used in each experiment

From: Evolving knowledge graph similarity for supervised learning in complex biomedical domains

Training set

No. of pairs

Test set

No. of pairs

S

6912

D+Gub+Gb

47307

D

2739

S+Gub+Gb

51480

Gb

31349

D+S+Gub

22870

Gub

31320

D+S+Gb

22899

S+Gb+Gub

69581

D

2115

D+Gb+Gub

65408

S

5037

S+D

9651

Gb+Gub

44929

Gb+Gub

62669

S+D

7239

S+Gb

38261

D+Gub

17746

D+Gub

34059

S+Gb

20697

S+Gub

38232

D+Gb

17771

D+Gb

34088

S+Gub

20668

  1. The names of the datasets STRING-HS, DIP-HS, GRID/HPRD-unbal-HS, and GRID/HPRD-bal-HS are abbreviated to “S”, “D”, “Gub” and “Gb”, respectively