Google AI Releases C2S-Scale 27B Model that Translate Complex Single-Cell Gene Expression Data into cell sentences that LLMs can Understand

Google Research, DeepMind, and Yale have developed C2S-Scale 27B, a 27-billion-parameter foundation model designed for single-cell RNA sequencing (scRNA-seq) analysis, which formalizes gene expression profiles as 'cell sentences'ordered lists of gene symbolsenabling large language models (LLMs) to interpret cellular states natively. This innovative approach transforms high-dimensional gene expression data into a text-like format, facilitating tasks such as cell-type prediction, tissue classification, and biological question answering through standard LLM prompt and completion paradigms. Built on the Gemma