DescFold: A web server for protein fold recognition

BMC Bioinformatics

Table 3 The ROCn scores and the corresponding sensitivity values of DescFold using different descriptors.^a

Descriptors included	ROC16,744 (Sn)^{b, c}	ROC83,720 (Sn)^{b, c}	ROC167,440 (Sn)^{b, c}	AUC
SSEA + Psi-blast + Rps-blast	0.0029 (34.70%)	0.0209 (52.76%)	0.0506 (64.56%)	0.8768
SSEA + Psi-blast + Rps-blast + motif	0.0032 (37.73%)	0.0223 (55.25%)	0.0529 (66.49%)	0.8831
SSEA + Psi-blast + Rps-blast + motif + PPA	0.0041 (46.94%)	0.0256 (60.06%)	0.0584 (70.21%)	0.8962
SSEA + Psi-blast + Rps-blast + motif + PPA + PSPA	0.0050 (70.21%)	0.0305 (68.51%)	0.0668 (75.93%)	0.9143

^aThese measurements reflect the performance of remote homology identification for all protein pairs within the SCOP_1.73_1835 dataset.
^bROC16,744, ROC83,720, and ROC167,440 stand for the ROCn scores at 1%, 5%, and 10% false positive rates, respectively.
^cThe value inside the parentheses denotes the corresponding sensitivity.

ISSN: 1471-2105