Table 14. Division of positive and unlabelled kinases by type.

	Serine/Threonine	Tyrosine	Atypical	Unknown
Entire Dataset	390 (59%)	90 (14%)	27 (4%)	154 (23%)
Unlabelled Proteins	355 (63%)	50 (9%)	26 (5%)	136 (24%)
Unlabelled Proteins With Positive Similarity >0.5	56 (52%)	33 (31%)	1 (1%)	17 (16%)
Unlabelled Proteins With Positive Similarity ≥0.75	16 (33%)	26 (53%)	0 (0%)	7 (14%)
Positive Proteins	35 (37%)	40 (43%)	1 (1%)	18 (19%)

The distribution of proteins in the entire Kinase dataset, all unlabelled proteins, misclassified unlabelled proteins and all positive proteins by kinase type. Unknown kinases are ones where it is not known whether they are Serine/Threonine, Tyrosine or atypical kinases.