Skip to main content
. 2010 Jun 15;26(16):1975–1982. doi: 10.1093/bioinformatics/btq319

Table 1.

Performance comparison between the three methods of catalytic residue prediction when evaluation was carried out per chain, family, superfamily and fold

FEATURE
GBT
Structure Kernel
AUC sn AUC sn AUC sn
Fold 76.4 0.20 80.4 0.34 86.1 0.40
Superfamily 76.5 0.20 80.8 0.34 86.1 0.40
Family 76.7 0.21 80.7 0.34 86.8 0.42
Chain 76.7 0.21 81.1 0.34 87.3 0.45

Methods were evaluated on the same dataset using 10-fold cross-validation. The sensitivity sn is shown for sp = 0.95.