This work focuses almost entirely on a single category of proteins: fold-switchers. That is, proteins that can adopt two distinct conformations depending on the state of the system. Sort of like a flip-flop.
Anyway, its conclusions are a bit grandiose, we already would have expected AF2 and 3 to do poorly on predicting both structures of a fold-switcher. And nobody really thinks that AF "learns the protein's energy function"- AF3 does nothing of the sort.
Most of AF3's abilities are memorization, but that's not a bad thing. It's already been shown to generalize out of class but also work poorly where there is poor data density (either coevolutionary data, or structural data).
Agreed, that this is a limited scope for what AF does. Nevertheless, it seems interesting to confirm that its primary strengths are memorization, which is not surprising.
Anyway, its conclusions are a bit grandiose, we already would have expected AF2 and 3 to do poorly on predicting both structures of a fold-switcher. And nobody really thinks that AF "learns the protein's energy function"- AF3 does nothing of the sort.
Most of AF3's abilities are memorization, but that's not a bad thing. It's already been shown to generalize out of class but also work poorly where there is poor data density (either coevolutionary data, or structural data).