RAPTOR
Comparison of RAPTOR and
PSI-BLAST in recent CASPs
CASP (Critical Assessment of Techniques for Protein Structure Prediction) is a community wide experiment which is held every two years by NIH. All participatory 3D protein structure prediction servers will be assessed in the experiment. RAPTOR has been an active participant since CASP5 in 2002.
The targets used in CASP have been classified into two groups: Homology Modeling (for easy targets) and Fold Recognition (for hard targets). Servers are evaluated for each group.
The sum of the MaxSub scores for targets are listed below, measuring the accuracy of a server. The number of correctly recognized targets is also compared in the following tables.
| Homology Modeling Targets | ||
| Server | MaxSub Score (Z Score) | Correctly Predicted Targets (Z Score) |
| RAPTOR | 94.31 (77.6) | 104.43 (72.7) |
| PSI-BLAST | 88.03 (37.8) | 99.26 (40.0) |
| Fold Recognition Targets | ||
| Server | MaxSub Score (Z Score) | Correctly Predicted Targets (Z Score) |
| RAPTOR | 10.35 (24.9) | 12.59 (21.9) |
| PSI-BLAST | 8.65 (10.6) | 11.31 (13.0) |
Essentially, if you are performing tasks that require fold recognition, use RAPTOR. It provides superior protein structure prediction. Blast results generally fail, as they provide less than 25% accuracy, in situations where a structure is predicted.
