Chuck Schumer’s entire political philosophy could fit on a bumper sticker: “Eventually, they’ll forget.”

Chuck Schumer’s entire political philosophy could fit on a bumper sticker: “Eventually, they’ll forget.”

AlphaFold is pretty legit! I would say amino acid/nucleotide sequences are some of the best use cases. But in general the AI hype is dumb. If you don't tell me*how* you use AI in the pitch I'm assuming you shoehorned it in unnecessarily.

True. Which is why we’re building.

Once you use AlphaFold to invent a new drug, it still has to be brought to market using pharma company infrastructure, not a server farm.

What’s striking here is the potential coupling of AI-based torsional prediction with traditional force field corrections. If AlphaFold can reconcile glycosidic linkage ambiguity with context-aware energetic constraints, it could unify
protein–glycan modeling under a single predictive framework.

This reminded me of what Dame Janet Thornton said about AlphaFold. It's a help to protein research, but not a substitute for protein researchers.
youtu.be/lxgaILSZEbU?...

Let's differentiate between GenAI and machine learning (ML).

Alphafold is ML. I'm personally familiar with several applications of ML that are transformational for biochemistry, drug development, and healthcare. ML is great at mining huge datasets for patterns.

I don't know anything about GenAI.