iiinova — where your digital self keeps evolving

Karl Krauth

@kkt.bsky.social

Postdoc at Stanford. Previously PhD student at Berkeley AI research. Trying to understand proteins with microfluidics and machine learning. www.karlk.net

Posts Replies Media

Reposted by Karl Krauth

Ben Neely @benneely.com · 24/11/2024

I took biochem in 2001, and for nearly 20 years read amino acid sequences daily… and I never knew Dayhoff named them or even the logic behind things like Q until last Friday (h/t Mike Janech). Also, this is another big Dayhoff moment for me. She was incredible! #proteomics #bioinformatics

biology.arizona.edu

Dr. Margaret Oakley Dayhoff

1419979

Karl Krauth @kkt.bsky.social · 20/11/2024

Always so impressed by how good this intro to graph neural nets is. They did such a good job of broadly covering the field without diving into a million papers. I love that they build intuition for how designing GNN architectures is tricky, wish more ML posts did that.

distill.pub

A Gentle Introduction to Graph Neural Networks

What components are needed for building learning algorithms that leverage the structure and properties of graphs?

0150

Karl Krauth @kkt.bsky.social · 19/11/2024

Has a machine learning model ever successfully designed an enzyme that's 5x faster than the sequences in its training set? Specifically looking for an experimentally verified example where the model is the decision maker rather than a human assistant.

220