转录组基础模型跨越15亿年进化揭示细胞组织通用原理

James D. Pearce1, Sara E. Simmonds1, Gita Mahmoudabadi1, Lakshmi Krishnan1, Giovanni Palla1, Ana-Maria Istrate1, Alexander Tarashansky1, Benjamin Nelson1, Omar Valenzuela1, Donghui Li1, Stephen R. Quake1,2,3*, Theofanis Karaletsos4†* Single-cell transcriptomics is revolutionizing our understanding of cellular diversity, yet comparing transcriptional programs across the tree of life remains challenging. We developed TranscriptFormer, a family of generative foundation models trained on up to 112 million cells spanning 1.53 billion years of evolution across 12 species. We demonstrate state-of-the-art performance on cell type classification, even for species separated by over 685 million years of evolution, and zero-shot disease state identification in human cells. Developmental trajectories, phylogenetic relationships, and cellular hierarchies emerge naturally in TranscriptFormer’s representations without any explicit training on these annotations. …