From: Motif kernel generated by genetic programming improves remote homology and fold detection
Average ROC and ROC-50 scores | ||||
---|---|---|---|---|
Superfamily level | Fold level | |||
ROC | ROC-50 | ROC | ROC-50 | |
GPkernel | 0.902 | 0.591 | 0.844 | 0.514 |
GPextended | 0.869 | 0.542 | 0.753 | 0.371 |
GPboost | 0.797 | 0.375 | 0.688 | 0.298 |
SVM-Pairwise | 0.849 | 0.555 | 0.724 | 0.359 |
Mismatch | 0.878 | 0.543 | 0.814 | 0.467 |
eMOTIF | 0.857 | 0.551 | 0.698 | 0.308 |
LA-kernel | 0.919 | 0.686 | 0.834 | 0.504 |
PSI-BLAST | 0.575 | 0.175 | 0.501 | 0.010 |