CAPRI (Critical Assessment of Predicted Interactions) experiment is a community-wide effort dedicated to evaluating the current state of methods for prediction of protein complex structure.
The evaluation of results for the last 7 rounds comprising a total of 20 prediction targets, was recently presented in Tel Aviv at the sixth CAPRI Evaluation Meeting. More then 6000 models submitted by 68 predictor groups and 14 automated servers were processed.
Automated protein docking server ClusPro developed by our own Applied BioComputation group in collaboration with Structural BioInformatics lab at Boston University was ranked first in the server category. The summary of the results is shown below. For each predictor group, the table shows the number of acceptable or better predictions, and among those the number of high quality models, indicated by three stars, as well as the number of medium quality solutions, indicated by two stars.
|PatchDock-FiberDock, DOCK/PIERR, MegaDock, GRAMM-X||1|
Interestingly, the server’s performance was comparable to that of the best human predictor groups, although the latter had access to all information available in the literature. The results for the 10 best-performing groups are provided below for comparison.
|Human predictor rankings|