SVEA: an accurate model for structural variation detection using multi-channel image encoding and enhanced AlexNet architecture

Table 2 Performance of SVEA and W/O MHSA, MSC on Different Datasets

Data	Model	DEL			DUP			INS			INV			Overall
		P	R	F1	P	R	F1	P	R	F1	P	R	F1	A(%)
	SVEA	0.97	0.97	0.97	0.95	0.94	0.95	0.98	0.98	0.98	0.80	0.65	0.72	97.2
HG00514	w/o SA	0.97	0.97	0.97	0.96	0.92	0.94	0.97	0.98	0.97	0.93	0.62	0.74	96.5
	w/o C	0.96	0.97	0.96	0.95	0.96	0.95	0.98	0.97	0.98	0.00	0.00	0.00	97.1
	SVEA	0.96	0.98	0.95	0.97	0.95	0.96	0.98	0.96	0.97	0.70	0.72	0.77	97.5
HG00733	w/o SA	0.96	0.97	0.97	0.97	0.95	0.96	0.98	0.98	0.98	0.91	0.87	0.89	97.5
	w/o C	0.95	0.98	0.96	0.93	0.95	0.94	0.98	0.97	0.98	1.00	0.07	0.13	96.8
	SVEA	0.98	0.96	0.97	0.93	0.97	0.95	0.98	0.99	0.98	0.80	0.67	0.74	97.2
NA19240	w/o SA	0.96	0.97	0.97	0.96	0.94	0.95	0.98	0.98	0.98	0.92	0.64	0.76	97.1
	w/o C	0.94	0.95	0.95	0.96	0.90	0.93	0.97	0.97	0.97	1.00	0.02	0.04	95.8

P: Precision, R: Recall, F1: F1 score, A: Accuracy. SVEA: Structural Variation detection with Enhanced AlexNet architecture. w/o SA: Without Multi-Head Self-Attention. w/o C: Without Multi-Head Self-Attention and Multi-Scale Convolution.

ISSN: 1479-5876