Skip to content

Designed by AI.
De-risked before the clinic.

We design radiopharmaceuticals with our own models, then predict what would fail them.

Bring us a target

Who we are

Epitorix designs radiopharmaceuticals with its own models, offers the products built on them, and runs its own programs.

Epitorix is an AI company for radiopharmaceutical discovery, development and de-risking. Its own models design peptide, antibody, nanobody and mini-protein candidates, and the same models predict what would fail them — off-target binding, biodistribution, organ and cell-type risk, PK and PD — before a trial does.

What we provide

  • A 96-channel pipetting head lowered over a clear 96-well plate on an automated liquid handler, one tip per well; gloved hands defocused at the frame edges.
    96-well plate on an automated liquid handler · protein ribbon on the monitor

    Developers & researchers

    Build therapies.

    Design and rank peptides, antibodies, nanobodies and mini-proteins in one workspace.

  • A physician in a white coat, seen from behind in a daylit reading room, reads an inverted-greyscale whole-body PET maximum-intensity projection on one monitor.
    Whole-body PET maximum-intensity projection · diagnostic reading room

    Investigators

    De-risk development.

    Expose biological, clinical, patent and regulatory risk before capital is committed.

  • A crimp-capped vial in a metal shielded pig marked with a radiation trefoil, its knurled lid beside it; a gloved hand withdraws a syringe in a syringe shield.
    Shielded vials and syringe shield · radiopharmacy bench

    Investors & partners

    Back innovation.

    Four AI-designed programs now in vivo — and the models beneath them.

Xenoclea is built into EPiQ. PharmacoLaw includes PharmPhax.

Our niche

First,and best in classat off-target risk.

First and best in class for three predictions: PK/PD biodistribution, off-target organ risk and off-target cell-type risk. An agentic 3D diffusion model, built on Epitorix deep learning, makes all three before a trial does.

How we predict itOff-target binding, explained

  1. PK/PD biodistributionWhere the dose goes, organ by organ.
  2. Off-target organ riskWhich organs are exposed.
  3. Off-target cell-type riskWhich cells within them.

up to93%

accuracy detecting reported development and safety liabilities in retrospective analyses of radiopharmaceuticals with documented clinical outcomes

A 3D body assembles from separated structures, turns translucent to show a schematic tracer distribution, then marks one candidate's predicted organ risk.
Schematic of physiological FDG distribution; not patient data. Anterior view · predicted risk for one candidate, schematic.

Assessment

“EPiQ™ compresses months of complex, PhD-level research into mere hours.”

Portrait of Dr. Eliot Siegel
Dr. Eliot Siegel, MD, FACR, FSIIM, DABRCo-Founder of United Theranostics

Contact

Bring us a target.

A target to design against, a candidate to de-risk, or the pipeline data.

What are you working on?

Privacy policy

Laboratory bench · liquid handler and assay plates