Table 6 Long range accuracy evaluation 2. Average long range accuracy values at δ = 1 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) | 63.86% | 62.60% | 58.92% |
RaptorX-Contact (94) | 52.13% | 47.50% | 45.58% |
rf_full (78) | 45.64% | 43.45% | 40.88% |
MLiD (94) | 42.77% | 39.65% | 37.26% |
rf_select (78) | 42.18% | 39.99% | 36.88% |
svm (78) | 42.05% | 36.87% | 34.20% |
DCA (88) | 39.76% | 36.20% | 33.73% |
sda_Ensemble (78) | 32.82% | 31.02% | 29.85% |
IASL-COPE (91) | 32.07% | 28.93% | 27.30% |
sda_unbalanced (78) | 29.17% | 27.67% | 26.52% |
MULTICOM-NOVEL (94) | 25.73% | 25.21% | 25.11% |
sda_balanced (78) | 21.60% | 20.91% | 21.60% |
raghavagps-paaint (76) | 17.63% | 18.13% | 18.41% |
PLCT (91) | 15.67% | 16.61% | 16.46% |
Pcons-net (87) | 15.29% | 15.85% | 16.27% |
FoDTcm (32) | 8.55% | 8.89% | 8.73% |