stMixer for Scalable Mosaic Integration and Label Transfer in Spatial Histology and Multi-Omics.

Overview

1. College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China
2. State Key Laboratory of Biocontrol, Innovation Center for Evolutionary Synthetic Biology, School of Life Sciences, Sun Yat‐sen University, Guangzhou, China
3. School of Mathematical Sciences and School of AI, Shanghai Jiao Tong University, Shanghai, China
4. Key Laboratory of Systems Health Science of Zhejiang Province, School of Life Science, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Hangzhou, China
5. Tianfu Jincheng Laboratory, Chengdu, China

Abstract

Integrating spatial histology with multi‐slide, multi‐omics data is essential for deciphering tissue architecture and cellular dynamics at high resolution. However, incomplete modality overlap across sections hinders coherent integration and cross‐condition analysis. Here, we present stMixer, an unsupervised framework that (i) employs self‐looped cross‐attention to jointly encode histological, molecular, and spatial features; (ii) implements a multi‐modal metric learning module to achieve biologically coherent integration across sections; and (iii) uses a graph‐guided, cluster‐level voting algorithm to enable anatomically faithful label propagation. Benchmarking across six spatial modalities demonstrates that stMixer achieves superior scalability and accuracy in dimensionality reduction, batch correction, and label transfer. The framework accommodates large, heterogeneous datasets across tissues, species, and technologies. We further showcase its versatility in mosaic integration, pseudo‐time inference, and cross‐tissue knowledge transfer. Notably, stMixer uncovers transient thymic states overlooked by competing methods, resolves fine‐grained cortical microstructures, and corrects anatomical mis‐annotations through integration with single‐cell reference. stMixer is available at https://github.com/YQX‐code/stMixer/.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• geo:GSE205055 — at NCBI GEO; found in “Data Availability Statement”
• sra:SRP135960 — at NCBI SRA; found in “Data Availability Statement”

Data Availability Statement

stMixer was applied to both synthetic benchmarks and nine real‐world spatial datasets generated by five different technologies, covering lymph node, thymus, brain, spleen, and breast cancer.The human lymph node dataset was profiled using the 10x Genomics platform and is available from SpatialGlue (Long et al. 2024).The mouse thymus dataset was generated using Stereo‐CITE‐seq (Liao et al. 2023, unpublished), and can be downloaded from the Spatial Transcript Omics DataBase(https://db.cngb.org/stomics/project/STT0000094). Three mouse brain datasets were profiled using the spatial ATAC‐RNA‐seq platform (Zhang et al. 2023), and have been deposited in the Gene Expression Omnibus under accession code GSE205055 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE205055) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE205055). Two mouse spleen datasets were generated using the SPOTS platform (Ben‐Chetrit et al. 2023), and have been deposited in the Gene Expression Omnibus under accession number GSE198353 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE198353) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE198353). Two human breast cancer datasets are available on the 10x Genomics website (https://www.10xgenomics.com/datasets/). The mouse brain single‐cell dataset (Zeisel et al. 2018) is deposited in the sequence read archive under accession code SRP135960 (https://www.ncbi.nlm.nih.gov/sra/SRP135960).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 4 keywords, 5 MeSH terms, 7 funders, 49 references.

Cite

This paper

Yang, Q., Wang, Y., Chen, L., & Zuo, C. (2026). stMixer for Scalable Mosaic Integration and Label Transfer in Spatial Histology and Multi-Omics. Advanced science (Weinheim, Baden-Wurttemberg, Germany), 13(48), e75905. https://doi.org/10.1002/advs.75905

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s42003-026-10462-y [code]

SpaDC enables sequence-based integrative analysis and regulatory inference of spatial chromatin accessibility data.

Journal: Communications biology

In common: genetics / omics, 6 references

[2] doi:10.1002/advs.75969 [code]

Accurately Deciphering Tissue Heterogeneity From Spatial Multi-Modal and Multi-Omics With STransformer.

Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)

In common: genetics / omics, 5 references

[3] doi:10.1093/bib/bbag331 [code]

SPOmiAlign: a modality-agnostic computational framework for multimodal spatial omics alignment enabled by a feature matching foundation model.

Journal: Briefings in bioinformatics

In common: methods / tools, genetics / omics, 4 references

[4] doi:10.1093/bioinformatics/btag220 [code]

Riemannian metric learning for alignment of spatial multiomics.

Journal: Bioinformatics (Oxford, England)

In common: methods / tools, genetics / omics, 4 references

[5] doi:10.1073/pnas.2527896123

Spatially tunable multiomic sequencing using light-driven combinatorial barcoding of molecules in tissues.

Journal: Proceedings of the National Academy of Sciences of the United States of America

In common: genetics / omics, 4 references

[6] doi:10.1038/s41592-026-03194-8 [code]

Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering.

Journal: Nature methods

In common: methods / tools, genetics / omics, 3 references

[7] doi:10.1093/bioinformatics/btag652 [code]

mmVelo: a deep generative model for estimating cell state-dependent dynamics across multiple modalities.

Journal: Bioinformatics (Oxford, England)

In common: genetics / omics, 3 references

[8] doi:10.1016/j.celrep.2026.117500 [code]

Spatio-molecular gene expression reflects dorsal anterior cingulate cortex structure and function in the human brain.

Journal: Cell reports

In common: histology / microscopy, genetics / omics, 3 references

[9] doi:10.1002/advs.77003 [code]

SemanticST: A Scalable Multi-Contextual Graph Learning Framework for Uncovering Spatial Niches and Robust Multi-Sample Integration in Spatial Transcriptomics.

Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)

In common: methods / tools, genetics / omics, 3 references

[10] doi:10.1093/bioinformatics/btag430 [code]

SPIDER: spatially integrated denoising via embedding regularization with single cell supervision.

Journal: Bioinformatics (Oxford, England)

In common: genetics / omics, 3 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.