Blind selection ability of all-atom models generated by at iterations and .
Datasets usually provide raw data for analysis. This raw data often comes in spreadsheet form, but can be any collection of data, on which analysis can be performed.
The first prediction is the model with the lowest energy. The best prediction is the best model out of the five lowest energies. All results are shown as CαRMSD to native structure. Models produced at iteration alone and iteration alone are compared. For comparison, the columns Rosetta show the same data obtained from a sample of Rosetta models randomly picked from Rosetta's prediction results.