StackTTCA: a stacking ensemble learning-based framework for accurate and high-throughput identification of tumor T cell antigens

Table 3 Cross-validation and independent test results for ET classifiers trained with three different features

Evaluation strategy	Feature	Number of feature	ACC	Sn	Sp	MCC	AUC
Cross-validation	APF	156	0.867	0.884	0.850	0.737	0.933
Cross-validation	BPF	10	0.879	0.896	0.861	0.760	0.935
Independent test	APF	156	0.899	0.907	0.891	0.798	0.958
Independent test	BPF	10	0.932	0.958	0.908	0.866	0.962

ISSN: 1471-2105