Radical Numerics
An AI lab building general biological intelligence: foundation models trained on DNA and other biological data, released to partners as APIs and tuned models.
Money and evidence
Latest round, Seed, 2026-06-15: the record then held 1 research entry, highest level 2. The first research entry is dated 2026-06-15; the highest level so far is 4 (Tested in the physical world).
Rounds and research, on one timeline
- 2026-10-20Research
Level 2 · Computed
With Lawrence Livermore, Radical Numerics reports its biology model predicting which rare earth metal a protein prefers better than the other methods tested
Telling these metals apart is a refining problem: China refined 91% of the world's supply in 2024 on the International Energy Agency's count, and the elements differ so little in size, 0.013 angstroms between neighbours, that the standard route needs harsh acids and a lot of energy. Proteins can distinguish them, and the question is whether a model can say which protein will, before anyone makes it. This model had no rare earth binding data in its training, and the lab is now testing the candidates the model generated and ranked.
- 2026-10-20Research
Level 4 · Tested in the physical world
Radical Numerics and Aptamino run three rounds of lab-measured antibody design with Omnii-1, and two designs bind tighter than the test can read
This is a loop where the model's own ranking decides what gets made, and each round's measurements go back into it. Antibody sequences were not a domain of this genome model's original pretraining; they came in afterwards, as public repertoires and the partner's own measured designs. What is being tested is whether a general biological model can be turned to one partner's narrow design problem. Ranked on the same 327 measured designs, what the model has learned predicts expression and potency a little better than protein-specific models, with a plain one-hot encoding of the sequence close behind on potency.
- 2026-10-20Research
Level 3 · Checked against existing evidence
Radical Numerics reports its Omnii-1 model scoring above AlphaGenome and Borzoi at telling which changes in non-coding DNA actually do something
Most DNA changes tied to disease sit outside the stretches that code for proteins, and working out which of them does anything is the bottleneck. The earlier models read DNA alone. This one also reads lab measurements of how the DNA is packaged and used in a given tissue, and can take those measurements as an input rather than only predict them. Its lead over Borzoi grows the further the change sits from the gene, from 0.05 within 500 bases to 0.19 beyond 50,000.
- 2026-10-20Research
Level 4 · Tested in the physical world
Radical Numerics reports that phage variants its Omnii-1 model designed were given to one patient with a drug-resistant infection, under compassionate use
A model's design has gone into a person's treatment, not only into a dish: the company says this is the first clinical use of AI-generated phages, under an authorised, physician-led compassionate-use pathway. What the model wrote is one region of a known T7 genome, not a genome. It also ranks which designs to test against a given bacterial strain (on the hardest of three library strains, 24% of its top 100 picks beat the activity threshold against 4.5% of the library), and that ranking is the step a therapy matched to one patient has to get right.
- 2026-06-15Research
Level 2 · Computed
Radical Numerics previews Omnii, a genome language model that scores noncoding variants above CADD and Evo 2 on the company's own benchmark runs
Base genome models have trailed hand-built scores like CADD on variant interpretation, which is the applied task geneticists care about. This is the first report from Evo's authors that a post-trained genome model passes those scores on noncoding variants, where most disease-linked variation sits.
- 2026-06-15SeedRound
$50M
For: scale the next generation of models, grow the research team, and build compute and data infrastructure
Models and platformHiring
Amount and lead are from the company's post. The participant list and the use of funds are as JustAINews reports them; that article also puts Patrick Collison among the pre-seed backers, which is why he is listed apart from this round.
Lead · Emergence CapitalObvious VenturesTriatomic CapitalFactoryFirst Spark Ventures
On the deal: Gordon Ritter (Founder and General Partner; spoke for the firm in the announcement, Emergence Capital)
By this date the record held 1 research entry, highest level 2
Announced by the company · radicalnumerics.ai ↗On the timeline →
Research entries are the timeline's graded entries that name this company. A level grades one claim, not the company, and a blank can mean the record has not caught up rather than that nothing was published.
Other backers, round not stated
Named as backers in investor databases, reports or the investors' own posts; no source read places them in a round on the record.
Patrick Collison
Its investors also backed
Other companies on this page whose rounds name the same investor.