Classification performance with three benchmark datasets.

a Total of 249,500 domain pairs selected randomly from SCOPe_NR10. b Total of 249,500 domain pairs selected randomly from SCOPe_FAMILY. c Total of 99,792 protein pairs selected randomly from PDB30. d–f SCOPe classification. g Area under the ROC curve. h Area under the PRC. i Number of alignments calculated from the alignment program. The best performances among the four structure alignment methods are indicated in bold. AUC, area under the ROC curve; AUPRC, area under the PRC; CAB-align, contact area-based alignment; PDB, protein data bank; PRC, precision-recall curve; ROC, receiver-operating characteristic. Classification performance with three benchmark datasets.