Table 8 Medium range accuracy evaluation 3. Average medium 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) | 70.76% | 63.23% | 54.96% |
RaptorX-Contact (94) | 51.91% | 46.01% | 39.47% |
Pcons-net (87) | 43.51% | 40.64% | 39.66% |
MLiD (94) | 41.01% | 37.69% | 32.81% |
PLCT (91) | 39.02% | 40.10% | 40.85% |
MULTICOM-NOVEL (94) | 38.75% | 36.89% | 34.79% |
rf_full (78) | 33.08% | 29.68% | 26.09% |
IASL-COPE (91) | 32.14% | 29.43% | 29.02% |
rf_select (78) | 31.28% | 26.68% | 22.65% |
DCA_cpp (88) | 30.98% | 25.07% | 19.91% |
sda_Ensemble (78) | 23.72% | 23.01% | 19.64% |
svm (78) | 18.33% | 17.03% | 16.64% |
sda_unbalanced (78) | 16.99% | 15.51% | 14.25% |
sda_balanced (78) | 15.90% | 16.90% | 16.05% |
raghavagps-paaint (76) | 13.42% | 13.16% | 13.69% |
FoDTcm (32) | 1.56% | 4.18% | 5.22% |