Deciphering cellular microenvironments at atlas scale remains challenging because molecular identity, spatial context, and platform heterogeneity are tightly coupled. Here we present CellNiche, a scalable contrastive-learning framework that identifies and characterizes cellular microenvironments from spatial omics data using cell-centric spatial-proximity subgraphs. CellNiche combines spatial co-localization and molecular co-expression cues to learn microenvironment-aware embeddings. Across spatial omics datasets from multiple platforms (>10 million cells in total), scaling experiments show improved representations with more training data and competitive clustering and embedding-quality performance with efficient computation. In a multi-sample human non-small-cell lung cancer (NSCLC) cohort, CellNiche identifies conserved and sample-specific tumor and immune microenvironments and captures localized spatial transitions. In four independent mouse brain atlases, CellNiche integrates 293 slices into a unified virtual brain map for cross-atlas annotation transfer and spatial refinement.
Publication: NATURE COMMUNICATIONS
http://dx.doi.org/10.1038/s41467-026-71759-4
Author: Liang, Zhongming，Univ Chinese Acad Sci, Hangzhou Inst Adv Study, Sch Life Sci, Key Lab Syst Hlth Sci Zhejiang Prov, Hangzhou, Peoples R China，BGI Res, State Key Lab Genome & Multiom Technol, Hangzhou, Peoples R China, BGI Res, Key Lab Spatial Om Zhejiang Prov, Hangzhou, Peoples R China
Email：liangzhongming21@mails.ucas.ac.cnJiao, Mingqi, Univ Chinese Acad Sci, Hangzhou Inst Adv Study, Sch Life Sci, Key Lab Syst Hlth Sci Zhejiang Prov, Hangzhou, Peoples R China
Liu, Shiping(corresponding author), Univ Chinese Acad Sci, Hangzhou Inst Adv Study, Sch Life Sci, Key Lab Syst Hlth Sci Zhejiang Prov, Hangzhou, Peoples R China, BGI Res, State Key Lab Genome & Multiom Technol, Hangzhou, Peoples R China, BGI Res, Key Lab Spatial Om Zhejiang Prov, Hangzhou, Peoples R China
Email：liushiping@genomics.cnZhong, Bingxu, Shanghai Jiao Tong Univ, SJTU Yale Joint Ctr Biostat & Data Sci, Sch Life Sci & Biotechnol, Dept Bioinformat & Biostat, Shanghai, Peoples R China
Wang, Yong, Chinese Acad Sci, Acad Math & Syst Sci, State Key Lab Math Sci, Beijing, Peoples R China, Chinese Acad Sci, Univ Chinese Acad Sci, Sch Math, Beijing, Peoples R China, Univ Chinese Acad Sci, Hangzhou Inst Adv Study, Sch Life Sci, Key Lab Syst Hlth Sci Zhejiang Prov, Hangzhou, Peoples R ChinaEmail：ywang@amss.ac.cn
附件下载：
