香港大学黄渊华团队取得一项新突破。他们研究出TemporalVAE：胚胎发育过程中时间序列单细胞转录组的图谱辅助时间映射。这一研究成果发表在2025年10月28日出版的国际学术期刊《自然—细胞生物学》上。

在这里，课题组人员介绍了TemporalVAE，这是一种双目标设置下的深度生成模型，即使在零样本环境下，也可以从压缩的潜在空间推断每个细胞的生物时间。通过小鼠发育图谱，课题组研究人员证明了它在数百万细胞中的可扩展性，基于图谱的跨平台细胞分期的准确性，以及通过识别具有硅微扰的时间敏感基因的可解释性。TemporalVAE在体内和体外条件下都能有效地在人类胚胎植入期间对细胞进行分期，并支持人类、猕猴和狨猴胚胎的跨灵长类动物比较，突出了其广泛的生物医学应用潜力。

研究人员表示，国际上的努力已经产生了广泛的单细胞时间序列图谱数据集，例如关于单主题胚胎发生的数据集，为绘制生物医学研究中的疾病模型提供了参考。然而，由于细胞状态的复杂性以及时间戳和实验批次之间的紧密耦合，有效地为单个数据集的时间分析对这些数据进行主题化是具有挑战性的。

附：英文原文

Title: TemporalVAE: atlas-assisted temporal mapping of time-series single-cell transcriptomes during embryogenesis

Author: Liu, Yijun, Cai, Fangxin, Barile, Melania, Chang, Yi, Cao, Dandan, Huang, Yuanhua

Issue&Volume: 2025-10-28

Abstract: International efforts have yielded extensive single-cell time-series atlas datasets, such as those on mouse embryogenesis, providing a reference for mapping disease models across biomedical research. However, effectively using such data for temporal analysis of individual datasets is challenging due to the intricate nature of cell states and the tight coupling between time stamps and experimental batches. Here we introduce TemporalVAE, a deep generative model in a dual-objective setting that infers the biological time of each cell from a compressed latent space, even in a zero-shot setting. With a mouse development atlas, we demonstrated its scalability with millions of cells, accuracy in atlas-based cell staging across platforms and interpretability by identifying temporally sensitive genes with in silico perturbation. TemporalVAE effectively stages cells during human peri-implantation under both in vivo and in vitro conditions, and supports cross-primate comparisons among human, cynomolgus and marmoset embryos, highlighting its potential for broad biomedical applications.

DOI: 10.1038/s41556-025-01787-7

Source: https://www.nature.com/articles/s41556-025-01787-7