CellType

Excited for YC Demo Day!

Great finally meeting Taylor Hsu from Senhwa Biosciences in person in San Francisco. Their drug CX-4945 was identified in our screen out of 4,000 compounds. Now CellType and Senhwa are partnering to further develop it together — exciting things in the pipeline! senhwabio.com/en/news/202603…

This is the thesis behind @CellTypeInc. You can't just prompt an LLM to design a drug. You need a simulator that can evaluate whether a design actually works—and then use that feedback to train models that get better at the hard direction. Paper: arxiv.org/abs/2603.12724

The elegant part is that the same asymmetry that makes inverse design hard also suggests the fix. Scientists have already built forward simulators for many of these problems. Those simulators can be repurposed as RL environments: propose a design, evaluate it, learn from the reward. In our case studies, training on simulator feedback lets a small 8B model outperform much larger frontier models on selected scientific design tasks.

LLMs can ace science exams and explain complex mechanisms. But can they actually do science—design a molecule, a dosing regimen, or a gene circuit that works? We built SciDesignBench, a benchmark for testing frontier LLMs on scientific design tasks grounded in real simulators. The core finding is that models that can talk fluently about science still struggle when asked to produce designs that actually satisfy quantitative targets. We also propose a simulator-feedback RL recipe that improves performance on these tasks. Paper: arxiv.org/abs/2603.12724 🧵

Our first clinical-stage pharma partnership. CellType models working on a real drug, in real patients. This is what we built for.

We are thrilled to announce CellType's strategic partnership with Senhwa Biosciences! We're using our models to accelerate their clinical oncology drug, CX-4945, unlocking novel mechanisms to make tumors more visible to the immune system. senhwabio.com/en/news/202603…

Keep working in your local environment while CellType Agent Pro offloads heavy GPU jobs to CellType Cloud. Run protein folding, molecular simulations, single-cell models, and other GPU-heavy bio workflows without managing your own GPU stack. Try it at celltype.com/agent

People kept telling us they wanted to run the CellType Agent but didn't have the compute. So we built CellType Agent Pro — GPU compute, plus an on-prem option for teams with sensitive data. celltype.com/agent

This team of Yale CS Professor + postdoc is building a next-gen drug company. It's been great working with them this batch. Congrats on the launch!

@Jan_Haris_ Live now! pip install celltype-cli (requires Python 3.10 and above) then run ct, it'll walk you through setup.

@celltypeinc is it live?

We teach models to reason about biology. Today we're open-sourcing the tool we built to run that science. Think Claude Code, but for drug discovery. pip install celltype-cli

@dagarfield This is fixed now, we pushed to PyPI shortly after launch. Run pip install celltype-cli (requires Python 3.10+)

@celltypeinc ERROR: Could not find a version that satisfies the requirement celltype-cli (from versions: none) ERROR: No matching distribution found for celltype-cli :(

@jboysen0 pip install celltype-cli now pulls in all deps correctly. Thanks for flagging this early.

@celltypeinc Not on PyPI yet, and deps also need work eg claude_agent_sdk needs to be added

100+ domain tools. CLI-native. Fully extensible. celltype.com/cli github.com/celltype/cli

We benchmarked celltype-cli against other agentic systems on computational biology tasks.

.@celltypeinc is building the agentic drug company. AI agents + foundation models that simulate human biology. They've already discovered and validated a novel cancer treatment signal and work with Top 10 pharma. Congrats on the launch @david_van_dijk and @vrkici! ycombinator.com/launches/PSn-c…

First cell division. We're live. Time to make drugs that actually work. ycombinator.com/launches/PSn-c…