Table 5.

Fold recognition performances with predicted distances/structures

Method	Benchmark set	Top-1 hit			Top-5 hits			Top-10 hits			Top-20 hits
		T	H	X	T	H	X	T	H	X	T	H	X
CE	CASP12	0.29	0.37	0.35	0.43	0.53	0.56	0.43	0.53	0.56	0.46	0.53	0.56
CE + rc		0.36	0.40	0.35	0.43	0.47	0.50	0.54	0.57	0.56	0.54	0.57	0.56
TM-align		0.21	0.33	0.35	0.39	0.43	0.53	0.54	0.57	0.59	0.61	0.60	0.62
TM-align + rc		0.36	0.40	0.35	0.43	0.50	0.47	0.50	0.53	0.53	0.54	0.60	0.59
CE	CASP13	0.33	0.40	0.43	0.39	0.50	0.57	0.44	0.55	0.65	0.50	0.55	0.65
CE + rc		0.39	0.45	0.48	0.56	0.60	0.61	0.61	0.65	0.70	0.61	0.65	0.74
TM-align		0.50	0.55	0.61	0.50	0.60	0.70	0.56	0.65	0.74	0.56	0.65	0.74
TM-align + rc		0.39	0.45	0.48	0.56	0.60	0.61	0.56	0.60	0.65	0.61	0.65	0.70

Note: TPR fold recognition performances on CASP12 and CASP13 benchmark sets. Comparison of TPR performance achieved by CE and TM-align with their own scoring system against those obtained by using statistically significant congruence coefficient, CE + r_c and TM-align + r_c, respectively. The TPR performances are assessed with respect to the top-1, top-5, top-10 and top-20 ranked hits. ECOD hierarchy: (T) Topology Level (28 targets in CASP12, 18 targets in CASP13), (H) Homology Level (30 targets in CASP12, 20 targets in CASP13), (X) Possible Homology Level (34 targets in CASP12, 23 targets in CASP13). Best TPR performances per column on CASP12 and CASP13 benchmark sets are highlighted in bold.