Validation of protein models by a neural network approach

BMC Bioinformatics

Table 1 Pearson correlation coefficients. For each dataset belonging to the test-set the Pearson correlation coefficient between the predicted and the computed values is reported. 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	0.39	0.42	0.15	0.63	0.61	0.69	0.27	0.45
AIDE TM-score	0.39	0.32	0.38	0.48	0.89	0.70	0.43	0.51
AIDE GDT-TS	0.45	0.34	0.28	0.58	0.77	0.73	0.44	0.51
AIDE LG-score	0.52	0.31	0.22	0.29	0.77	0.48	0.38	0.42
AIDE MaxSub	0.39	0.34	0.36	0.55	0.73	0.70	0.40	0.49
ProQ LG-score	0.20	0.62	0.48	0.18	0.81	0.80	0.06	0.45
ProQ MaxSub	0.15	0.48	0.39	0.14	0.77	0.76	0.05	0.39
Victor GDT-TS	-0.29	-0.53	-0.29	-0.05	-0.78	-0.75	-0.23	-0.41

ISSN: 1471-2105