by ProfluentUS
Write new proteins to order instead of borrowing them from nature, starting with gene editors that are smaller, more precise or able to insert whole genes, so more genetic diseases become fixable.
Partnered with Lilly (up to $2.25B) and BioMarin; designs still preclinical.
Updated 28 Apr 2026Checked 11 Oct0 updates this week
The model reads billions of natural protein sequences and learns which strings of amino acids fold and work.
Asked for a family like CRISPR editors, it writes new members hundreds of mutations from anything in nature.
Designs are built and tested; results steer the model toward traits like stability, binding or editing precision.
Profluent does not run its own drug pipeline; partners like Lilly develop the editors into treatments.
| Spec | ProGen3 & OpenCRISPR |
|---|---|
| Largest model trained on | About 3.4 billion protein sequencesR (reported) |
| Protein Atlas size | 115+ billion unique proteinsR (reported) |
| OpenCRISPR-1 distance from SpCas9 | About 400 mutationsR (reported) |
| CRISPR operons mined for training | 1 million+R (reported) |
R reported by the company
Profluent
Protein language models, AI-designed gene editors
Profluent trains large language models on protein sequences to design new proteins, starting with gene editors. Its OpenCRISPR-1 was the first AI-designed CRISPR editor to edit human DNA.
