近日，美国斯坦福大学Jure Leskovec及其小组的研究认为通用细胞嵌入为细胞生物学提供基础模型。2026年7月8日出版的《自然》杂志发表了这项成果。

本文提出了通用细胞嵌入（UCE）的基础模型。UCE在以自我监督为主题的大量细胞数据上进行训练，创建了一个统一的生物潜伏空间，可以代表不同组织和物种的细胞。尽管存在实验噪声，但这个潜在空间捕获了重要的生物变异。UCE的通用性意味着新的细胞可以嵌入而不需要数据标记、模型训练或微调。小组以UCE为主题创建了集成的超大规模地图集，嵌入了36数以百计的实验，数十个组织和8个物种的上百万个细胞，超过1000个独特命名的细胞类型。该课题组人员可以深入了解空间中细胞类型和组织的组织结构。UCE的嵌入空间展示了突现行为，识别它从未训练过的生物学，例如识别发育谱系和嵌入未包含在训练集中的物种数据。总的来说，通过为每个细胞状态和类型提供通用表示，UCE是对单细胞数据进行分析、注释和假设生成的有价值的工具。

据了解，为细胞开发一个通用的表征空间，包括跨物种细胞类型的巨大分子多样性，将是细胞生物学的变革。最近的工作主题是单细胞转录组学方法，以细胞图谱的形式创建细胞类型的分子定义，为这种努力提供了必要的数据。

附：英文原文

Title: Universal cell embedding provides a foundation model for cell biology

Author: Rosen, Yanay, Roohani, Yusuf, Agrawal, Ayush, Samotoran, Leon, Quake, Stephen R., Leskovec, Jure

Issue&Volume: 2026-07-08

Abstract: Developing a universal representation space for cells that encompasses the tremendous molecular diversity of cell types across species would be transformative for cell biology. Recent work using single-cell transcriptomic approaches to create molecular definitions of cell types in the form of cell atlases has provided the necessary data for such an endeavour1,2,3. Here we present the universal cell embedding (UCE) foundation model. UCE was trained on a large corpus of cell data using self-supervision, creating a unified biological latent space that can represent cells across diverse tissues and species. This latent space captures important biological variation despite the presence of experimental noise. UCE’s universality means that new cells can be embedded with no data labelling, model training or fine-tuning. We used UCE to create the Integrated Mega-scale Atlas, embedding 36million cells, with more than 1,000 uniquely named cell types, from hundreds of experiments, dozens of tissues and eight species. We gain insights into the organization of cell types and tissues within the space. UCE’s embedding space exhibits emergent behaviour, identifying biology that it was never trained for, such as identifying developmental lineages and embedding data from species that were not included in the training set. Overall, by enabling a universal representation for every cell state and type, UCE is a valuable tool for analysis, annotation and hypothesis generation over single-cell data.

DOI: 10.1038/s41586-026-10689-z

Source: https://www.nature.com/articles/s41586-026-10689-z