Imagine being able to ask a cell how it’s feeling, what it’s doing or how it might respond to a drug — and receiving an answer back in plain English. Today, in partnership with Yale University, we’re introducing Cell2Sentence-Scale (C2S-Scale), a family of open-source large language models trained to interpret and understand biology at the single-cell level.

C2S-Scale bridges biology and artificial intelligence, converting complex cellular data into simple, readable “cell sentences.” Researchers can then ask questions about specific cells, like “Is this cell cancerous?” or “How will this cell respond to Drug X?” and receive clear, biologically-informed answers in natural language.

C2S-Scale has the potential to:

• Speed drug development and discovery
• Personalize medicine and improve outcomes
• Democratize science through open-source availability
• Help researchers better understand, treat and prevent disease

Learn more about how C2S-Scale is advancing medical science, and how to try it yourself, with Google Research.