Image guided construction of a common coordinate framework for spatial transcriptome data

Abstract Spatial transcriptomics is a powerful technology for high-resolution mapping of gene expression in tissue samples, enabling a molecular level understanding of tissue architecture. The acquisition entails dissecting and profiling micron-thick tissue slices, with multiple slices often needed...

Full description

Saved in:
Bibliographic Details
Main Authors: Peter Lais, Shawn Mishra, Kun Xiong, Huanan Shi, Gurinder Singh Atwal, Yu Bai
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-01862-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850125428622098432
author Peter Lais
Shawn Mishra
Kun Xiong
Huanan Shi
Gurinder Singh Atwal
Yu Bai
author_facet Peter Lais
Shawn Mishra
Kun Xiong
Huanan Shi
Gurinder Singh Atwal
Yu Bai
author_sort Peter Lais
collection DOAJ
description Abstract Spatial transcriptomics is a powerful technology for high-resolution mapping of gene expression in tissue samples, enabling a molecular level understanding of tissue architecture. The acquisition entails dissecting and profiling micron-thick tissue slices, with multiple slices often needed for a comprehensive study. However, the lack of a common coordinate framework (CCF) among slices, due to slicing and displacement variations, can hinder data analysis, making data comparison and integration challenging, and potentially compromising analysis accuracy. Here we present a deep learning algorithm STaCker that unifies the coordinates of transcriptomic slices via an image registration process. STaCker derives a composite image representation by integrating tissue image and gene expression that are transformed to be resilient to noise and batch effects. STaCker overcomes the training data scarcity by training exclusively on diverse synthetic data. Its performance on various benchmarking datasets shows a significant increase in spatial concordance in aligned slices, surpassing existing methods. STaCker also successfully harmonizes multiple real spatial transcriptome datasets acquired from various platforms. These results indicate that STaCker is a valuable computational tool for constructing a CCF with spatial transcriptome data.
format Article
id doaj-art-ffa3cb514f3e4a96854afe424954dba1
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ffa3cb514f3e4a96854afe424954dba12025-08-20T02:34:07ZengNature PortfolioScientific Reports2045-23222025-05-0115112010.1038/s41598-025-01862-xImage guided construction of a common coordinate framework for spatial transcriptome dataPeter Lais0Shawn Mishra1Kun Xiong2Huanan Shi3Gurinder Singh Atwal4Yu Bai5New York University Grossman School of MedicineRegeneron Pharmaceuticals, Inc.Regeneron Pharmaceuticals, Inc.Regeneron Pharmaceuticals, Inc.Flagship PioneeringRegeneron Pharmaceuticals, Inc.Abstract Spatial transcriptomics is a powerful technology for high-resolution mapping of gene expression in tissue samples, enabling a molecular level understanding of tissue architecture. The acquisition entails dissecting and profiling micron-thick tissue slices, with multiple slices often needed for a comprehensive study. However, the lack of a common coordinate framework (CCF) among slices, due to slicing and displacement variations, can hinder data analysis, making data comparison and integration challenging, and potentially compromising analysis accuracy. Here we present a deep learning algorithm STaCker that unifies the coordinates of transcriptomic slices via an image registration process. STaCker derives a composite image representation by integrating tissue image and gene expression that are transformed to be resilient to noise and batch effects. STaCker overcomes the training data scarcity by training exclusively on diverse synthetic data. Its performance on various benchmarking datasets shows a significant increase in spatial concordance in aligned slices, surpassing existing methods. STaCker also successfully harmonizes multiple real spatial transcriptome datasets acquired from various platforms. These results indicate that STaCker is a valuable computational tool for constructing a CCF with spatial transcriptome data.https://doi.org/10.1038/s41598-025-01862-x
spellingShingle Peter Lais
Shawn Mishra
Kun Xiong
Huanan Shi
Gurinder Singh Atwal
Yu Bai
Image guided construction of a common coordinate framework for spatial transcriptome data
Scientific Reports
title Image guided construction of a common coordinate framework for spatial transcriptome data
title_full Image guided construction of a common coordinate framework for spatial transcriptome data
title_fullStr Image guided construction of a common coordinate framework for spatial transcriptome data
title_full_unstemmed Image guided construction of a common coordinate framework for spatial transcriptome data
title_short Image guided construction of a common coordinate framework for spatial transcriptome data
title_sort image guided construction of a common coordinate framework for spatial transcriptome data
url https://doi.org/10.1038/s41598-025-01862-x
work_keys_str_mv AT peterlais imageguidedconstructionofacommoncoordinateframeworkforspatialtranscriptomedata
AT shawnmishra imageguidedconstructionofacommoncoordinateframeworkforspatialtranscriptomedata
AT kunxiong imageguidedconstructionofacommoncoordinateframeworkforspatialtranscriptomedata
AT huananshi imageguidedconstructionofacommoncoordinateframeworkforspatialtranscriptomedata
AT gurindersinghatwal imageguidedconstructionofacommoncoordinateframeworkforspatialtranscriptomedata
AT yubai imageguidedconstructionofacommoncoordinateframeworkforspatialtranscriptomedata