Skip to main content

Table 9 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 extended 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
FN035 20 0.714 0.637 0.577 0.508 -0.137 -0.129 0.684 0.647 0.078 0.080 0.866 0.955 0.890 0.947 0.134 0.045 0.110 0.053
FN096 24 0.678 0.596 0.546 0.473 -0.132 -0.123 0.590 0.547 0.038 0.054 0.957 0.948 0.948 0.941 0.043 0.052 0.052 0.059
FN339 24 0.648 0.576 0.546 0.473 -0.102 -0.103 0.468 0.487 0.038 0.054 0.941 0.926 0.885 0.934 0.059 0.034 0.115 0.105
FN242 23 0.649 0.557 0.545 0.475 -0.104 -0.082 0.456 0.333 0.008 0.044 0.975 0.851 0.975 0.851 0.025 0.074 0.025 0.066
FN315 21 0.681 0.512 0.582 0.473 -0.099 -0.039 0.403 0.077 0.068 0.054 0.831 0.450 0.763 0.450 0.169 0.149 0.237 0.149
FN104 22 0.666 0.573 0.555 0.484 -0.112 -0.089 0.275 0.186 -0.012 -0.016 0.912 0.778 0.808 0.778 0.088 0.141 0.192 0.222
FN110 22 0.657 0.618 0.588 0.508 -0.070 -0.111 0.274 0.488 0.117 0.102 0.684 0.895 0.500 0.895 0.316 0.384 0.500 0.550
FN094 23 0.575 0.473 0.571 0.494 -0.004 0.021 -0.013 -0.104 0.113 0.112 0.301 0.112 0.233 0.112 0.699 0.375 0.767 0.500
FN114 23 0.576 0.478 0.539 0.472 -0.037 -0.006 -0.076 -0.198 -0.010 -0.002 0.662 0.277 0.404 0.277 0.388 0.835 0.596 0.888
FN113 22 0.575 0.516 0.565 0.493 -0.010 -0.023 -0.109 -0.027 0.067 0.056 0.377 0.500 0.266 0.500 0.623 0.419 0.734 0.581
FN236 24 0.535 0.444 0.546 0.473 -0.011 0.029 -0.121 -0.265 0.038 0.054 0.463 0.152 0.320 0.152 0.537 0.610 0.680 0.723
FN452 22 0.589 0.508 0.560 0.488 -0.028 -0.020 -0.166 -0.135 0.007 0.032 0.639 0.419 0.448 0.419 0.361 0.755 0.552 0.848
FN017 23 0.471 0.430 0.571 0.494 0.100 0.063 -0.442 -0.285 0.113 0.112 0.040 0.037 0.024 0.037 0.960 0.960 0.976 0.963
FN425 23 0.429 0.345 0.545 0.471 0.116 0.126 -0.523 -0.599 -0.011 0.011 0.049 0.012 0.049 0.012 0.951 0.984 0.951 0.941
FN072 23 0.474 0.423 0.571 0.494 0.097 0.071 -0.528 -0.376 0.113 0.112 0.024 0.059 0.019 0.059 0.976 0.957 0.981 0.970
FN057 23 0.475 0.419 0.571 0.494 0.096 0.075 -0.540 -0.386 0.113 0.112 0.022 0.030 0.012 0.030 0.978 0.978 0.988 0.990
FN415 23 0.457 0.416 0.571 0.494 0.114 0.078 -0.556 -0.426 0.113 0.112 0.022 0.022 0.012 0.010 0.978 0.992 0.988 0.988
  1. 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.