Validation of protein models by a neural network approach

BMC Bioinformatics

Table 2 10%-fraction enrichment. The 10%-fraction enrichment is shown for each dataset belonging to the test-set. The performance of AIDE is compared to that of ProQ and Victor/FRST validation softwares.

	lmds	4state_reduced	CASP5	fisa	MD	hg_structal	ROSETTA	average
AIDE RMSD	15.20	42.58	37.10	25.00	48.19	43.67	20.80	33.22
AIDE TM-score	1.84	31.18	34.84	19.50	72.29	44.82	26.49	32.99
AIDE GDT-TS	2.07	32.68	29.86	11.50	72.28	50.57	25.29	32.03
AIDE LG-score	25.80	34.40	31.67	17.52	67.47	42.53	29.96	35.62
AIDE MaxSub	3.22	33.54	35.29	10.00	73.49	44.82	24.12	32.06
ProQ LG-score	18.30	54.78	39.59	12.50	72.45	74.71	13.30	40.80
ProQ MaxSub	1.95	52.84	45.24	12.00	65.86	67.84	43.69	41.34
Victor GDT-TS	14.40	42.57	28.50	4.0	63.85	54.02	11.61	31.27

ISSN: 1471-2105