ProCKSI: a decision support system for Protein (Structure) Comparison, Knowledge, Similarity and Information

BMC Bioinformatics

Table 5 ROC Analysis for the Rost and Sander Dataset. Analysis of the performance of different similarity measures in terms of AUC values for each SCOP classification level using the Rost and Sander dataset. The Consensus measures are composed of ^aCE/Z, DaliLite/Z, FAST/Align, MaxCMO/Overlap, TM-align/TM, and USM/USM for the Class and Species level, and CE/Z, DaliLite/Z, FAST/SN, MaxCMO/Overlap, TM-align/TM, and USM/USM for all remaining levels, ^bFAST/Align, FAST/SN, and DaliLite/Z for the Class level, and CE/Z, Dali/Z, and Dali/Align for all remaining levels, and ^cFAST/Align and FAST/SN for the Class level, and CE/Z and Dali/Z for all remaining levels.

Method	Measure	AUC Values for SCOP Classification Level
		Class	Fold	Superfamily	Family	Protein	Species
CE	RMSD	0.574	0.776	0.754	0.718	0.625	0.626
	Align	0.694	0.704	0.660	0.643	0.503	0.486
	Z	0.712	0.848	0.838	0.826	0.769	0.759
DaliLite	RMSD	0.677	0.807	0.794	0.786	0.746	0.751
	Align	0.693	0.827	0.807	0.792	0.755	0.759
	Z	0.696	0.846	0.830	0.817	0.792	0.797
FAST	RMSD	0.454	0.530	0.514	0.490	0.322	0.303
	Align	0.770	0.800	0.773	0.757	0.684	0.672
	SN	0.747	0.802	0.779	0.761	0.684	0.671
MaxCMO	Align	0.665	0.685	0.687	0.730	0.672	0.667
	Overlap	0.682	0.751	0.743	0.769	0.706	0.693
TM-align	RMSD	0.475	0.624	0.602	0.550	0.354	0.336
	Align	0.695	0.747	0.733	0.741	0.656	0.645
	TM	0.705	0.773	0.756	0.751	0.673	0.666
USM	USM	0.678	0.686	0.680	0.683	0.578	0.566
Consensus	All	0.764	0.816	0.797	0.793	0.724	0.712
	BestOfEach^a	0.759	0.818	0.804	0.803	0.746	0.740
	Best3^b	0.780	0.865	0.854	0.847	0.710	0.806
	Best2^c	0.725	0.863	0.855	0.845	0.799	0.791

ISSN: 1471-2105