Nicheformer: a foundation model for single-cell and spatial omics.

> 商业许可源文 · EUROPE_PMC · [CC-BY](https://creativecommons.org/licenses/by/)

书目信息

引用：Tejada-Lapuerta A, Schaar AC, Gutgesell R, Palla G, Halle L, Minaeva M, Vornholz L, Dony L, Drummer F, Richter T, Bahrami M, Theis FJ. (2025). Nicheformer: a foundation model for single-cell and spatial omics. Nature methods. PMID 41168487 · PMC12695652 · DOI 10.1038/s41592-025-02814-z

证据类型：PRIMARY_RESEARCH

主题：single-cell、spatial-omics

被引次数（采集时）：45

原始记录：[Europe PMC](https://europepmc.org/article/MED/41168487)

来源许可：[CC-BY](https://creativecommons.org/licenses/by/)

作者摘要（按来源许可复用）

Tissue makeup depends on the local cellular microenvironment. Spatial single-cell genomics enables scalable and unbiased interrogation of these interactions. Here we introduce Nicheformer, a transformer-based foundation model trained on both human and mouse dissociated single-cell and targeted spatial transcriptomics data. Pretrained on SpatialCorpus-110M, a curated collection of over 57 million dissociated and 53 million spatially resolved cells across 73 tissues on cellular reconstruction, Nicheformer learns cell representations that capture spatial context. It excels in linear-probing and fine-tuning scenarios for a newly designed set of downstream tasks, in particular spatial composition prediction and spatial label prediction. Critically, we show that models trained only on dissociated data fail to recover the complexity of spatial microenvironments, underscoring the need for multiscale integration. Nicheformer enables the prediction of the spatial context of dissociated cells, allowing the transfer of rich spatial information to scRNA-seq datasets. Overall, Nicheformer sets the stage for the next generation of machine-learning models in spatial single-cell analysis.

合规说明

本页保存的是来源文献书目信息及其在 CC-BY 许可下公开的作者摘要。除去除来源 HTML 标签和规范化空白外，摘要未作内容改写。本页不代表 GeniOmics 的医学建议；原文版权、署名和许可仍归原权利人，请通过原始记录核对最新版本、更正或撤稿状态。