Table 5.

Mean performance characteristics of the taxonomy- and phenotype-based UC classifiers over 10 classification iterations.

Strategy: dataset	Taxonomy-based classifier			Phenotype-based classifier
	Mean sensitivity	Mean specificity	Mean AUC	Mean sensitivity	Mean specificity	Mean AUC
Single:CHN	0.7909	0.9048	0.9277	0.8091	0.8857	0.9281
Single:ESP	0.3000	0.8667	0.6583	0.3250	0.7741	0.5815
Single:NLD	0.6300	0.9376	0.9240	0.5500	0.8678	0.8232
L1O:CHN	0.6324	0.5955	0.6791	0.4189	0.8791	0.6832
L1O:ESP	0.3051	0.8626	0.6607	0.3308	0.7714	0.5751
L1O:NLD	0.7354	0.4972	0.6944	0.8364	0.1022	0.4341
Mixed: all datasets	0.5970	0.8590	0.8153	0.5667	0.7836	0.7240
Mean across all variants	0.5701	0.7891	0.7656	0.5481	0.7234	0.6785

In the L1O strategy description, the name of the dataset corresponds to the test set (for example, the “L1O:CHN” description means that the classifier was trained on the ESP and NLD datasets and tested on the CHN dataset). Cell color reflects the characteristics' values (greater values correspond to darker colors).