New AI model deciphers the code in proteins that tells them where to go

Welcome to Inflection, where we capture moments of breakthrough at Whitehead Institute. Here, you’ll get an insider’s view of groundbreaking foundational research, hear directly from the scientists behind these discoveries, and explore why their insights matter for our understanding of health and disease.

This is a condensed version of Inflection. Sign up here to get the full edition in your inbox every other Thursday.

An AI model that predicts where proteins will reside within a cell

Proteins are the workhorses that keep our cells running. Researchers have long known that the structure of a protein determines what it can do but, more recently, they are coming to appreciate that a protein’s localization is also critical for its function.

What they’ve learned:?Whitehead Institute Member Richard Young ,?Young lab postdoc Henry Kilgore , Regina Barzilay at MIT’s CSAIL,?and colleagues have created a machine learning model that can predict in which cellular compartments a protein will reside. This AI model will help generate proteins to reside in a desired compartment, and detect disease mutations that alter cellular compartments.?

Why it matters:?Being able to generate functional proteins in this way could improve researchers’ ability to develop more effective therapies, and help them learn more about the roles of localization in protein function and mis-localization in disease.

Find the full edition of Inflection here.