Program · BIO·03
We train models on the behaviour of living systems, cells, proteins, and the molecular machinery between them, learning the rules of biology to accelerate medicine and molecular design. Biology is the richest dataset we have, and we treat it as one.
What we work on
A program is a small set of hard, coupled problems. These are the ones this group is working on now.
A cell is a computer we did not design. By training on millions of live-cell trajectories, we build models that predict how a cell will respond to a perturbation before it happens, turning the wet lab from a place of discovery into a place of confirmation.
Structure prediction told us what proteins look like. The next question is what they do, in context, in a pathway, under stress. We model the behaviour, not just the shape, connecting molecular events to cellular outcomes.
The space of possible molecules is vastly larger than any lab can test. Models that have learned biology's rules let us search that space in silico, surfacing the few candidates worth the bench.
Signals from the program
Selected writing from this program
Collaborate
We hire researchers and engineers who want to push one of these programs forward, and partners who want to put the results to work.
