Despite extraordinary progress in automation, robotics and high-throughput lab techniques, biology remains largely post hoc.
Biological systems are perturbed, their responses measured, mechanisms inferred after the fact, and experimental outcomes treated as proxies for causality.
This paradigm has generated unprecedented volumes of data, but data alone does not reveal how biological systems form, change between healthy and disease states, or respond to intervention.
A new architecture is needed for mechanistic understanding.

In 2024, we designed a bioreactor to produce biological consumables for deep-space missions such as the NASA Artemis Program. To do this, we needed to model how electromagnetic fields, microgravity, and quantum-scale forces influence protein folding.
Those insights became JupitR - a new mathematical framework to compute causality.

We are using JupitR to build micro world models.
Rather than making statistical inferences from training data, micro world models simulate the physical conditions in which biological phenomena happen.
These models allow the first glimpses into the layer of biology invisible to conventional methods.