Evolve the enzymology…
We should almost be sophisticated enough to solve that computationally at this point.
Evolve the enzymology…
We should almost be sophisticated enough to solve that computationally at this point.
Turns out we are right on the cusp of being able to solve this sort of problem computationally…
Bad. No.
Ovchinnikov points out that AI-designed proteins often differ from naturally occurring proteins.
Synthetic proteins designed by a language model?
Why bad?
Why not a “language” model!?
20amino acids. “Words” that are hundreds or even thousands of characters long.
Much easier for an AI to grok.
Simple chemistry/physics at its heart.
Design a specific catalyst for any reaction scheme you can imagine…
It makes sense how you describe it, but I just wish I were smart enough to understand its implications.
What does the paper say?
I’m interested in the paper
Which paper?
Why not READ it?
If you don’t KNOW which paper, how are folks supposed to help?
Maybe this will be easier to digest?