What does GeroQubit actually do?
You pick one of 21 aging-related protein targets, across two programmes: slowing ageing down, and making old cells behave young again. We design new small molecules aimed at that target and hand each one back with the chemistry needed to make it — which building blocks to buy, and which reactions to run.
21 targets · 14 tissues · 12 hallmarks
The longer answerClose
The unusual part is the order of operations. Most systems draw a molecule first and work out afterwards whether anyone can build it. Ours searches over recipes instead, so a molecule only exists in the output if a route to it already exists.
A design is specified on three axes rather than one: the target, the tissue you care about, and which kind of age-related damage you are trying to address. That combination is what makes it a geroscience tool rather than a general-purpose molecule generator.
Candidates are assembled through verified reaction templates, so the route is part of what gets designed rather than something guessed afterwards. Selection is multi-objective and deliberately ungameable: potency cannot buy back weak ADMET, because a single poor axis collapses the composite rather than being averaged away. A developability gate runs last, and a candidate whose route we cannot defend is dropped rather than scored badly.
