Skip to main content
. 2016 Jul 8;113(30):8430–8435. doi: 10.1073/pnas.1523335113

Fig. 4.

Fig. 4.

Calculations vs. experiment across all NN parameters. Comparisons are based on (A) RECCES–Rosetta weight sets trained on canonical and dangling-end data (same values as in Fig. 3) and (B) “best-case” weight sets fitted post hoc over all available NN parameters, including D–U stacked pairs measured for blind predictions.