FunFOLD: an improved automated method for the prediction of ligand binding residues using 3D models of proteins

Roche, Daniel B; Tetchner, Stuart J; McGuffin, Liam J

doi:10.1186/1471-2105-12-160

BMC Bioinformatics

Table 6 The mean MCC and BDT raw scores and Z-scores obtained by FunFOLD are compared with those obtained by the top CASP9 function prediction groups for the partial binding sites analysis.

From: FunFOLD: an improved automated method for the prediction of ligand binding residues using 3D models of proteins

Group ID	N	Mean score for group		Mean score for FunFOLD		Difference in mean score		Mean Z-score for group		Mean Z-score for FunFOLD		P-value (raw score)		P-value (Z-score)		1 - p-value (raw score)		1 - p-value (Z-score)
		MCC	BDT	MCC	BDT	MCC	BDT	MCC	BDT	MCC	BDT	MCC	BDT	MCC	BDT	MCC	BDT	MCC	BDT
FN096	24	0.626	0.520	0.508	0.439	-0.188	-0.018	0.526	0.413	0.052	0.108	0.954	0.879	0.938	0.853	0.004	0.049	0.062	0.049
FN035	20	0.636	0.545	0.531	0.467	-0.105	-0.078	0.512	0.593	0.095	0.144	0.897	0.951	0.904	0.951	0.103	0.131	0.096	0.241
FN339	24	0.597	0.492	0.508	0.439	-0.089	-0.053	0.458	0.333	0.052	0.108	0.932	0.772	0.897	0.815	0.068	0.121	0.103	0.147
FN242	23	0.591	0.505	0.504	0.439	-0.087	-0.066	0.457	0.404	0.023	0.101	0.948	0.767	0.952	0.817	0.052	0.233	0.048	0.183
FN104	22	0.619	0.538	0.513	0.447	-0.106	-0.091	0.366	0.350	0.004	0.043	0.973	0.962	0.968	0.912	0.027	0.038	0.032	0.088
FN315	21	0.620	0.459	0.538	0.439	-0.081	-0.020	0.332	0.152	0.085	0.108	0.784	0.698	0.671	0.637	0.216	0.228	0.329	0.185
FN110	22	0.594	0.548	0.546	0.470	-0.048	-0.078	0.233	0.430	0.133	0.161	0.487	0.869	0.375	0.759	0.513	0.277	0.625	0.364
FN094	23	0.552	0.482	0.531	0.458	-0.021	-0.024	0.171	0.177	0.129	0.168	0.596	0.723	0.537	0.636	0.404	0.302	0.463	0.363
FN114	23	0.548	0.479	0.499	0.436	-0.049	-0.044	0.063	0.014	0.005	0.055	0.745	0.723	0.555	0.458	0.255	0.277	0.445	0.542
FN452	22	0.543	0.448	0.518	0.451	-0.025	0.003	0.011	-0.082	0.023	0.091	0.588	0.334	0.524	0.257	0.412	0.666	0.476	0.743
FN236	24	0.486	0.418	0.508	0.439	0.022	0.021	-0.049	-0.147	0.052	0.108	0.440	0.361	0.404	0.269	0.596	0.639	0.596	0.731
FN425	23	0.409	0.346	0.507	0.439	0.097	0.093	-0.323	-0.349	0.035	0.111	0.111	0.031	0.111	0.054	0.886	0.969	0.889	0.946
FN017	23	0.403	0.376	0.531	0.458	0.128	0.094	-0.501	-0.397	0.129	0.168	0.019	0.016	0.013	0.011	0.981	0.941	0.987	0.951
FN057	23	0.424	0.364	0.531	0.458	0.107	0.082	-0.534	-0.373	0.129	0.168	0.026	0.059	0.013	0.049	0.974	0.984	0.987	0.989
FN113	22	0.477	0.381	0.523	0.456	0.046	0.075	-0.548	-0.594	0.082	0.114	0.126	0.049	0.044	0.035	0.874	0.972	0.956	0.984
FN072	23	0.418	0.366	0.531	0.458	0.113	0.092	-0.551	-0.446	0.129	0.168	0.019	0.028	0.012	0.016	0.981	0.991	0.988	0.996
FN415	23	0.388	0.353	0.531	0.458	0.142	0.105	-0.619	-0.542	0.129	0.168	0.007	0.009	0.006	0.004	0.993	0.951	0.994	0.975

The analysis is based on common subsets of all CASP9 targets, with a minimum of 10 predictions in common. N, size of the common subset used in the comparison; MCC, Matthews Correlation Coefficient; BDT, the Binding Site Distance Test Score [36].P-value, the p-value for the paired Wilcoxon signed rank sum test using the raw scores; P-value (Z-score), the p-value for the paired Wilcoxon signed rank sum test using the Z-scores; 1 - p-value, 1 minus the p-value for the paired Wilcoxon signed rank sum test using the raw scores; 1-p-value (Z-score), 1 minus the p-value for the paired Wilcoxon signed rank sum test using the Z-scores. The table is sorted by the Mean MCC Z-score for groups with the best CASP9 groups at the top. The highest mean scores, mean Z-scores, significant p-values and significant 1-p-values are indicated in bold. Server groups are underlined.

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com