Computational biology for decarbonization
We turn unknown genomes into a to-do list of lab tests.
No reference data, no model organism, no problem. Stoma tells you which genes to test first — then builds what they point to.
Novel methods in our pipeline
- AlphaFold
- ESM-2
- Foldseek
- InterPro
- SignalP
Approach
Decarbonization is a biology problem, not an energy problem.
The bottleneck is biology, not engineering.
The organisms that already do this work in nature have no reference genome and no known function for most of their genes.
Drug-discovery tools weren't built for this.
They assume dense reference data. Non-model biology has none — so we built for data scarcity from the start.
Faster breakthroughs → Faster adoption.
The goal is to optimize research so science reaches practical use faster — and at greater scale.
Platform
A ranked list of what's worth testing next.
One pipeline, one ranked output — instead of five disconnected tools a biologist has to run and reconcile by hand.
- Function class
- Structural homology
- Interaction partners
- Transit peptides
- Regulatory signals
Ranked hypotheses — run #0412
unannotated genome → pipeline
scaffold_0412_g7
Oxidoreductase
scaffold_0188_g2
Transporter, putative
scaffold_0312_g14
Structural homolog: Foldseek hit
scaffold_0091_g3
Regulatory signal detected
What the output actually is
A ranked hypothesis with a confidence score — not a verified function. It tells you where to look first. The wet lab still does the proving.
Get in touch
Three reasons to write in.
Co-founder conversation
Senior computational biologist, structural biology or protein engineering background.
Scientific collaboration
Working on non-model systems, host-symbiont biology, or related genomics.
Investor interest
Noted, and appreciated — let's keep in touch as things develop.