On-prem biological LLMs that simulate human biology, learn from your data, and outperform general-purpose AI on drug development tasks. YC W26.
New York
Joined February 2026
- Tweets87
- Following6
- Followers1.9K
- Likes61
CellType retweeted
Which patients will respond to immunotherapy?
Across 5 cohorts, 43% responded. In CT-Translate’s top-ranked third: 61%.
451 patients. Every prediction made by a model that never saw that patient.
Retrospective results:
celltype.com/blog/post/ct-tr…
Predicting patient outcomes from lab data is a long-sought goal in drug development.
Introducing CT-Translate, a preclinical-to-clinical foundation model built to do it.
In its top-ranked third of immunotherapy patients, 61% responded vs 43% overall.
celltype.com/blog/post/ct-tr…
One model, 69 clinical questions. In: a tumor profile, clinical details and a plain-English question. Out: a probability per patient, so patients can be ranked.
Built on CT1, our foundation model. Trained on drug screens and more than 13,000 patients across 20 studies.
It runs on-prem, frozen and versioned on a single GPU, no external calls. Your fine-tuned weights stay on your premises and run on the licensed CellType foundation model.
Built with a top-10 pharma translational team. Test it on patients you hold out:
celltype.com/blog/post/ct-tr…
One model, 69 clinical questions. In: a tumor profile, clinical details and a plain-English question. Out: a probability per patient, so patients can be ranked.
Built on CT1, our foundation model. Trained on drug screens and more than 13,000 patients across 20 studies.
It runs on-prem, frozen and versioned on a single GPU, no external calls. Your fine-tuned weights stay on your premises and run on the licensed CellType foundation model.
Built with a top-10 pharma translational team. Test it on patients you hold out:
celltype.com/blog/post/ct-tr…
CellType retweeted
Really impressive work from Anthropic. 17 lab-confirmed binders. The next question is biological: does binding actually protect a cell? As AI gets better at designing molecules, predicting what they do in a cellular context becomes even more valuable.
New on our Science Blog: designing protein binders against scorpion neurotoxins.
Scorpions sting about 1.2m people every year, and antivenoms are often costly or in short supply. Claude has made an early step toward finding new treatments.
anthropic.com/research/claud…
