Google’s Gemma AI model helps discover new potential cancer therapy pathway

We’re launching a new 27 billion parameter foundation model for single-cell analysis built on the Gemma family of open models. Google DeepMind and Yale created C2S-Scale a new model built on the Gemma family of open models. This model identified a drug combination that may make tumors more visible to the immune system, offering a new cancer therapy approach. Researchers can now access the model and resources to build on this work. Today, as part of our research collaboration with Yale University, we’re releasing Cell2Sentence-Scale 27B (C2S-Scale), a new 27 billion parameter foundation model designed to understand the language of individual cells. Built on the Gemma family of open models, C2S-Scale represents a new frontier in single-cell analysis. This announcement marks a milestone for AI in science. C2S-Scale generated a novel hypothesis about cancer cellular behavior and we have since confirmed its prediction with experimental validation in living cells. This discovery reveals a pr

How a Gemma model helped discover a new potential cancer therapy pathway Oct 15, 2025 | x.com Facebook LinkedIn Mail Copy link We’re launching a new 27 billion parameter foundation model for single-cell analysis built on the Gemma family of open models. Shekoofeh Azizi Staff Research Scientist, Research Lead, Google DeepMind Bryan Perozzi Senior Staff Research Scientist, Graph Mining, Google Research Share x.com Facebook LinkedIn Mail Copy link Read AI-generated summary Google DeepMind and Yale created C2S-Scale a new model built on the Gemma family of open models. This model identified a drug

related reading

• Google’s Gemma AI model helps discover new potential cancer therapy pathwayblog.google
• Gap Mapgap-map.org
• Arc Institute’s first virtual cell model: <span style="font-variant: small-caps">S<span style="font-weight: bolder">tate</span></span> | Arc Institutearcinstitute.org
• Going Founder Mode On Cancer - by Elliot Hershbergcenturyofbio.com
• Data driven model discovery and interpretation for CAR T-cell killing using sparse identification and latent variablespmc.ncbi.nlm.nih.gov
• OCTO - Noetiknoetik.ai
• Medicine's Endgamenotboring.co
• scGen predicts single-cell perturbation responsesnature.com
• scGPT: toward building a foundation model for single-cell multi-omics using generative AI | Nature Methodsnature.com
• Using Interpretability to Identify a Novel Class of Alzheimer's Biomarkersgoodfire.ai
• PREDICTING SINGLE-CELL PERTURBATION RESPONSES FOR UNSEEN DRUGSarxiv.org
• Models of Lifepress.asimov.com