Designer Proteins

the baker lab / rosetta are still going strong, with complementary ML approaches:

The hope is that the next time there’s an outbreak, within 2 days, we’ll have models of candidates

2023-07-13: Protein design is getting real.

10–20% of RFdiffusion’s designs bind to their intended target strongly enough to be useful, compared with less than 1% for earlier, pre-AI methods.Biochemist Matthias Gloegl has been hitting success rates approaching 50%, which means it can take just a week or 2 to come up with working designs, as opposed to months. “It’s really insane”. The latest protein-design tools have proved to be extremely powerful at creating proteins that can do a particular task — so long as that function can be described in terms of a shape, such as the surface of a protein to bind to. Tools such as RFdiffusion aren’t yet able to handle other kinds of specifications, such as making a protein that can carry out a particular reaction regardless of its shape — when “you know what you want but you don’t know what the geometry is”.

Leave a comment