Comparison of In Silico Tools for Splice-Altering Variant Prediction Using Established Spliceogenic Variants: An End-User’s Point of View

Table 1

Summary of evaluation measures for 7 in silico tools for all splice sites.

In silico tools	AUC (95% CI)	Cutoff	TP	FP	TN	FN	Sensitivity	Specificity
SpliceAI	0.991 (0.980–1.002)	0.02	148	2	62	2	0.987	0.969
SpliceRover	0.944 (0.912–0.977)	0.010746	149	8	56	9	0.943	0.875
SPiCE	0.916 (0.879–0.954)	0.04424	92	3	61	18	0.836	0.953
MES	0.912 (0.878–0.946)	0.063125	126	2	60	26	0.829	0.968
NNSplice	0.895 (0.857–0.934)	0	126	12	50	22	0.851	0.806
SSF	0.889 (0.854–0.924)	0	121	4	60	31	0.796	0.937
HSF	0.782 (0.740–0.824)	0	75	0	64	58	0.564	1

Abbreviations: AUC, area under the curve; TP, true positives; FP, false positives; TN, true negatives; FN, false negatives.