Skip to main content

Table 3 The sensitivity of 18 methods on the Lindahl's dataset.

From: Improving protein fold recognition by random forest

Method Family Superfamily Fold
Top1 Top5 Top1 Top5 Top1 Top5
PSI-Blast 71.2 72.3 27.4 27.9 4 4.7
HMMER 67.7 73.5 20.7 31.3 4.4 14.6
SAM-T98 70.1 75.4 28.3 38.9 3.4 18.7
BLASTLINK 74.6 78.9 29.3 40.6 6.9 16.5
SSERCH 68.6 75.5 20.7 32.5 5.6 15.6
SSHMM 63.1 71.7 18.4 31.6 6.9 24
THREADER 49.2 58.9 10.8 24.7 14.6 37.7
Fugue 82.2 85.8 41.9 53.2 12.5 26.8
SPARKS 81.6 88.1 52.5 69.1 28.7 47.7
SP3 81.6 86.8 55.3 67.7 30.8 47.4
HHpred 82.9 87.1 58 70 25.2 39.4
SP4 80.9 86.3 57.8 57.8 30.8 53.6
SP5 82.4 87.6 59.8 70 37.9 58.7
RAPTOR 86.6 89.3 56.3 69 38.2 58.7
SPARKS-X 84.1 90.3 59.0 76.3 45.2 67.0
BoostThreader 86.5 90.5 66.1 76.4 42.6 57.4
FOLDpro 85 89.9 55 70 26.5 48.3
RF-fold 84.5 91.5 63.4 79.3 40.8 58.3
  1. The bold font denotes the highest sensitivity in their respective categories of prediction. The results of other methods are taken from [5, 28, 29]