Makingphysiologycomputable.

We're building the first foundation model that understands how the human body actually works over time.

Scroll to explore
0%
of drug candidates fail to reach patients after entering clinical trials
FDA, Tufts CSDD
$0.0B
average cost to bring a single drug to market
Tufts Center for Drug Development
0.0M
patients annually affected by adverse drug reactions in the US
JAMA Internal Medicine
The Problem

Drug development is broken at the biology layer.


Nine out of ten drugs that enter clinical trials never reach patients. The reason usually isn't commercial, it's biological. A compound that looks fine at the target level can turn toxic once it hits the whole system.

Today's models test compounds against isolated targets, but the body doesn't work that way. Your liver talks to your heart. Your kidney talks to your liver. Something that looks clean in isolation can trigger a cascade no single-organ model will catch. Physiology is continuous; medicine records it as sparse snapshots.

We're building a physiological foundation model that treats the body as one connected system and learns its state from continuous data, not snapshots. We're not building another risk score. We're making physiology computable.

Live signal modeling

PhysioFM reads the body
as a continuous signal.

Cardiac — ECG trace
Hepatic — enzyme flux
Renal — filtration rate
CNS — neural oscillation
PhysioFM

How we model
human physiology.

01
Continuous-time modeling
We train on continuous physiological signals across every organ system, not snapshots. The full picture of a living body, moment to moment.
02
Multi-organ simulation
We model how organs affect each other: liver, kidney, heart, brain. So a toxic cascade shows up before it ever reaches a patient.
03
Drug compound inference
Give us a compound and we model its full-body toxicity and pharmacokinetic profile, before anyone is exposed.
Our mission
“We don't lack data. What we've been missing is a model that can read it at the level of the whole organism. That's what we're building.”
The Team

Built by people who understand the problem.

We come from Harvard, Princeton, Stanford, and UC Berkeley, with backgrounds in computational biology, machine learning, drug development, and clinical care.

Blogs

Coming Soon

We're working on sharing our research and insights. Check back soon for updates on our work in computational physiology.

Join Us

We're building the team.

We are a small team working on a hard problem. If you have a background in ML systems, computational biology, pharmacokinetics, or clinical data, we want to hear from you.

Contact

Let's talk.

Whether you're an investor, a potential collaborator, a pharma partner, or someone who wants to work on this problem — reach out directly.