Skip to main content

Table 20 Percentage of predicted non-existent class IDs out of the total number of predicted mismatch class IDs for the core + extensions set for the training, validation and evaluation sets

From: Concept recognition as a machine translation problem

Ontology

% Non-existent class IDs in training (%)

% Non-existent class IDs in validation (%)

% Non-existent class IDs in evaluation (%)

ChEBI_EXT

8

8

17

CL_EXT

1

1

9

GO_BP_EXT

2

2

3

GO_CC_EXT

4

4

21

GO_MF_EXT

2

2

4

MOP_EXT

0

6

0

NCBITaxon_EXT

9

9

25

PR_EXT

7

7

5

SO_EXT

1

1

2

UBERON_EXT

1

1

1