Arc News

For years, biological research has relied on assembling natural components through trial-and-error or screening thousands of candidates until something worked. While powerful AI models for protein design, RNA engineering, and gene regulation have the potential to accelerate this process, they remain isolated in computational silos, out of reach for many experimental biologists. Today, the Laboratory of Evolutionary Design, led by Brian Hie, is releasing Proto, a framework that integrates these diverse AI tools to enable complex, multi-modal biological design.

Cells don't behave in isolation. The identity of a cell, what it does, and how it responds to perturbation is shaped by where it sits in a tissue, what signals it receives from neighbors, and what its neighbors are doing. PerturbSpace adds a single labeling step before a standard single-cell sequencing workflow, producing datasets where every cell carries its tissue location alongside its transcriptome, its CRISPR guide identity, and any other modalities your experiment includes.

Some of the most exciting AI projects I have worked on started not with graduate students or postdocs in my lab, but with undergraduates driven by raw curiosity and technical ambition. So when we launched the AIxBio Fellows Program earlier this year, I was curious who would apply and what kinds of projects we'd see proposed.

The nucleosome has long been treated as a binary regulatory switch. Nucleosome-occupied DNA is inaccessible, while nucleosome-depleted DNA is open. It's a model that has organized the chromatin field for decades and underpins the interpretation of virtually every accessibility dataset ever generated, from MNase-seq to ATAC-seq. This classical framing, however, turns out to be substantially incomplete.

The idea started during the pandemic. While learning about how viruses transferred cargo from cell to cell, Felix Horns, then a postdoc, began to wonder whether the same principle could be harnessed therapeutically. By 2023, he published a proof-of-concept study in Cell showing that cells could be engineered to package and deliver mRNA to other cells.