Table 7 Short range accuracy evaluation 3. Average short range accuracy values at δ = 0 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 |
|---|---|---|---|
CONSIP2 (94) | 76.18% | 66.18% | 55.85% |
MULTICOM-NOVEL (94) | 60.58% | 53.84% | 50.71% |
PLCT (91) | 54.94% | 57.13% | 57.47% |
RaptorX-Contact (94) | 54.89% | 50.02% | 43.04% |
rf_full (78) | 52.18% | 42.91% | 35.28% |
rf_select (78) | 46.41% | 38.68% | 31.11% |
sda_unbalanced (78) | 39.77% | 38.67% | 38.80% |
sda_Ensemble (78) | 39.49% | 33.57% | 28.57% |
Pcons-net (87) | 37.32% | 34.20% | 33.66% |
sda_balanced (78) | 35.38% | 30.67% | 25.13% |
IASL-COPE (91) | 33.01% | 30.40% | 30.36% |
svm (78) | 30.90% | 28.40% | 24.64% |
DCA_cpp (88) | 18.78% | 14.74% | 12.85% |
raghavagps-paaint (76) | 15.92% | 15.46% | 15.14% |
FoDTcm (32) | 5.00% | 7.29% | 8.05% |
MLiD (94) | N/A | N/A | N/A |