Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis

Abstract Recent progress in multiplexed tissue imaging is deepening our understanding of tumor microenvironments related to treatment response and disease progression. However, analyzing whole-slide images with millions of cells remains computationally challenging, and few methods provide a principl...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiyu Peng, James W. Smithy, Mohammad Yosofvand, Caroline E. Kostrzewa, MaryLena Bleile, Fiona D. Ehrich, Jasme Lee, Michael A. Postow, Margaret K. Callahan, Katherine S. Panageas, Ronglai Shen
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-61821-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342207583059968
author Xiyu Peng
James W. Smithy
Mohammad Yosofvand
Caroline E. Kostrzewa
MaryLena Bleile
Fiona D. Ehrich
Jasme Lee
Michael A. Postow
Margaret K. Callahan
Katherine S. Panageas
Ronglai Shen
author_facet Xiyu Peng
James W. Smithy
Mohammad Yosofvand
Caroline E. Kostrzewa
MaryLena Bleile
Fiona D. Ehrich
Jasme Lee
Michael A. Postow
Margaret K. Callahan
Katherine S. Panageas
Ronglai Shen
author_sort Xiyu Peng
collection DOAJ
description Abstract Recent progress in multiplexed tissue imaging is deepening our understanding of tumor microenvironments related to treatment response and disease progression. However, analyzing whole-slide images with millions of cells remains computationally challenging, and few methods provide a principled approach for integrative analysis across images. Here, we introduce SpatialTopic, a spatial topic model designed to decode high-level spatial tissue architecture from multiplexed images. By integrating both cell type and spatial information, SpatialTopic identifies recurrent spatial patterns, or “topics,” that reflect biologically meaningful tissue structures. We benchmarked SpatialTopic across diverse single-cell spatial transcriptomic and proteomic imaging platforms spanning multiple tissue types. We show that SpatialTopic is highly scalable to large-scale images, along with high precision and interpretability. It consistently identifies biologically and clinically significant spatial topics, such as tertiary lymphoid structures, and tracks spatial changes over disease progression. Its computational efficiency and broad applicability will enhance the analysis of large-scale imaging datasets.
format Article
id doaj-art-2ba9fa616ce64d018a804c2adda770fa
institution Kabale University
issn 2041-1723
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-2ba9fa616ce64d018a804c2adda770fa2025-08-20T03:43:27ZengNature PortfolioNature Communications2041-17232025-07-0116111510.1038/s41467-025-61821-yScalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysisXiyu Peng0James W. Smithy1Mohammad Yosofvand2Caroline E. Kostrzewa3MaryLena Bleile4Fiona D. Ehrich5Jasme Lee6Michael A. Postow7Margaret K. Callahan8Katherine S. Panageas9Ronglai Shen10Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterDepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterDepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterDepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterDepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterDepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterNeag Comprehensive Cancer Center, UConn HealthDepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterDepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer CenterAbstract Recent progress in multiplexed tissue imaging is deepening our understanding of tumor microenvironments related to treatment response and disease progression. However, analyzing whole-slide images with millions of cells remains computationally challenging, and few methods provide a principled approach for integrative analysis across images. Here, we introduce SpatialTopic, a spatial topic model designed to decode high-level spatial tissue architecture from multiplexed images. By integrating both cell type and spatial information, SpatialTopic identifies recurrent spatial patterns, or “topics,” that reflect biologically meaningful tissue structures. We benchmarked SpatialTopic across diverse single-cell spatial transcriptomic and proteomic imaging platforms spanning multiple tissue types. We show that SpatialTopic is highly scalable to large-scale images, along with high precision and interpretability. It consistently identifies biologically and clinically significant spatial topics, such as tertiary lymphoid structures, and tracks spatial changes over disease progression. Its computational efficiency and broad applicability will enhance the analysis of large-scale imaging datasets.https://doi.org/10.1038/s41467-025-61821-y
spellingShingle Xiyu Peng
James W. Smithy
Mohammad Yosofvand
Caroline E. Kostrzewa
MaryLena Bleile
Fiona D. Ehrich
Jasme Lee
Michael A. Postow
Margaret K. Callahan
Katherine S. Panageas
Ronglai Shen
Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis
Nature Communications
title Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis
title_full Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis
title_fullStr Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis
title_full_unstemmed Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis
title_short Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis
title_sort scalable topic modelling decodes spatial tissue architecture for large scale multiplexed imaging analysis
url https://doi.org/10.1038/s41467-025-61821-y
work_keys_str_mv AT xiyupeng scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT jameswsmithy scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT mohammadyosofvand scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT carolineekostrzewa scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT marylenableile scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT fionadehrich scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT jasmelee scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT michaelapostow scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT margaretkcallahan scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT katherinespanageas scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis
AT ronglaishen scalabletopicmodellingdecodesspatialtissuearchitectureforlargescalemultiplexedimaginganalysis