The recent Arc Institute challenge made this painfully clear: defining evaluation metrics is hard. In some cases, trivial data transformations—and even random data—can score astonishingly high.

Great AI performance ≠ biological meaning. 6/8

Selection of the best-predicted 3D RNA structures using Rosetta and ARES. The correlation between trRosettaRNA (trRNA) and Rosetta is not surprising, but look at Alfafold3 and ARES !! #ai #RNA #structure #prediction