TranscriptFormer: A generative cell atlas across 1.5 billion years of evolution

• 成果类型: Article
• 署名作者: Pearce, James D.; Simmonds, Sara E.; Mahmoudabadi, Gita; Krishnan, Lakshmi; Palla, Giovanni; Istrate, Ana-Maria; Tarashansky, Alexander; Nelson, Benjamin; Valenzuela, Omar; Li, Donghui; Quake, Stephen R.; Karaletsos, Theofanis
• 署名单位: Stanford University; Stanford University; Chan Zuckerberg Initiative (CZI)
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-8075; 1095-9203
• DOI: 10.1126/science.aec8514
• 发表日期: 2026-07-02
• 页码: aec8514
• 关键词: RNA-SEQ ANALYSIS; gene; origin

摘要

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. This work establishes a powerful framework for quantitative single-cell analysis and comparative cellular biology, thus demonstrating that universal principles of cellular organization can be learned and predicted across the tree of life.