Table 2 Medium range accuracy evaluation 1. Average medium range accuracy values at δ = 2 resolution for the top 10, top L/10, and top L/5 contact predictions from various predictors (with our methods listed in bold font) evaluated on CASP11 targets and sorted by Top 10 accuracy scores
From: Predicting protein residue-residue contacts using random forests and deep networks
Method | Top 10 | L/10 | L/5 |
|---|---|---|---|
RaptorX-Contact (94) | 84.68% | 80.57% | 77.90% |
CONSIP2 (94) | 84.50% | 82.18% | 79.28% |
MLiD (94) | 77.34% | 74.82% | 70.92% |
rf_full (78) | 74.49% | 73.48% | 69.91% |
rf_select (78) | 65.51% | 63.28% | 61.47% |
svm (78) | 62.18% | 60.60% | 58.76% |
sda_Ensemble (78) | 60.26% | 59.59% | 57.15% |
MULTICOM-NOVEL (94) | 58.41% | 57.59% | 57.22% |
IASL-COPE (91) | 55.97% | 52.63% | 52.54% |
sda_balanced (78) | 54.87% | 53.76% | 51.96% |
PLCT (91) | 54.82% | 55.65% | 55.91% |
Pcons-net (87) | 53.22% | 52.18% | 51.85% |
DCA_cpp (88) | 50.85% | 44.89% | 40.65% |
sda_unbalanced (78) | 44.93% | 46.50% | 46.69% |
raghavagps-paaint (76) | 43.29% | 44.04% | 43.84% |
FoDTcm (32) | 25.00% | 30.79% | 30.60% |