Brilliantly wrong

Recently, a pivotal moment in protein design happened: binding affinities and success rates have improved rapidly.

Last year Pascal Notin wrote a great post summarizing important observation about AI + proteins: Have we hit the scaling wall for protein language models?.

Who needs fast autograd?

This month brought two preprints describing optical pooled CRISPR screens.

Einops is soon-to-turn 5 years.

A great achievement of the past decade in programming is a shift in paradigm from transition-focused to state-focused.

Summary I argue for wider usage of delimiter-first in the code three friends [tic, tac, toe] becomes three friends ・tic ・tac ・toe.

If you want to learn some culprits of microscopy … you’d better watch this video by microbehunter, because rest of the post is view of ML person on things you should (not) expect from lab microscopy during experiment design.

(a friendly reminder that reading post before commenting is a great idea.

Abstract: Frequently comparing deep learning models?