Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning
Abstract Recent advances in spatial transcriptomics have enabled simultaneous preservation of high‐throughput gene expression profiles and the spatial context, enabling high‐resolution exploration of distinct regional characterization in tissue. To effectively understand the underlying biological me...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2025-01-01
|
Series: | Advanced Science |
Subjects: | |
Online Access: | https://doi.org/10.1002/advs.202410081 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832593487726379008 |
---|---|
author | Zhuohan Yu Yuning Yang Xingjian Chen Ka‐Chun Wong Zhaolei Zhang Yuming Zhao Xiangtao Li |
author_facet | Zhuohan Yu Yuning Yang Xingjian Chen Ka‐Chun Wong Zhaolei Zhang Yuming Zhao Xiangtao Li |
author_sort | Zhuohan Yu |
collection | DOAJ |
description | Abstract Recent advances in spatial transcriptomics have enabled simultaneous preservation of high‐throughput gene expression profiles and the spatial context, enabling high‐resolution exploration of distinct regional characterization in tissue. To effectively understand the underlying biological mechanisms within tissue microenvironments, there is a requisite for methods that can accurately capture external spatial heterogeneity and interpret internal gene regulation from spatial transcriptomics data. However, current methods for region identification often lack the simultaneous characterizing of spatial structure and gene regulation, thereby limiting the ability of spatial dissection and gene interpretation. Here, stDCL is developed, a dual graph contrastive learning method to identify spatial domains and interpret gene regulation in spatial transcriptomics data. stDCL adaptively incorporates gene expression data and spatial information via a graph embedding autoencoder, thereby preserving critical information within the latent embedding representations. In addition, dual graph contrastive learning is proposed to train the model, ensuring that the latent embedding representation closely resembles the actual spatial distribution and exhibits cluster similarity. Benchmarking stDCL against other state‐of‐the‐art clustering methods using complex cortex datasets demonstrates its superior accuracy and effectiveness in identifying spatial domains. Our analysis of the imputation matrices generated by stDCL reveals its capability to reconstruct spatial hierarchical structures and refine differential expression assessment. Furthermore, it is demonstrated that the versatility of stDCL in interpretability of gene regulation, spatial heterogeneity at high resolution, and embryonic developmental patterns. In addition, it is also showed that stDCL can successfully annotate disease‐associated astrocyte subtypes in Alzheimer's disease and unravel multiple relevant pathways and regulatory mechanisms. |
format | Article |
id | doaj-art-96aafcf7f135469b8b4c6fac8dfa8507 |
institution | Kabale University |
issn | 2198-3844 |
language | English |
publishDate | 2025-01-01 |
publisher | Wiley |
record_format | Article |
series | Advanced Science |
spelling | doaj-art-96aafcf7f135469b8b4c6fac8dfa85072025-01-20T13:04:19ZengWileyAdvanced Science2198-38442025-01-01123n/an/a10.1002/advs.202410081Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive LearningZhuohan Yu0Yuning Yang1Xingjian Chen2Ka‐Chun Wong3Zhaolei Zhang4Yuming Zhao5Xiangtao Li6School of Artificial Intelligence Jilin University Jilin 130012 ChinaTerrence Donnelly Centre for Cellular and Biomolecular Research University of Toronto Toronto ON M5S 3E1 CanadaCutaneous Biology Research Center, Massachusetts General Hospital Harvard Medical School Boston MA 02115 USADepartment of Computer Science City University of Hong Kong Hong Kong SAR 999077 Hong KongTerrence Donnelly Centre for Cellular and Biomolecular Research University of Toronto Toronto ON M5S 3E1 CanadaCollege of Computer and Control Engineering Northeast Forestry University Harbin 150040 ChinaSchool of Artificial Intelligence Jilin University Jilin 130012 ChinaAbstract Recent advances in spatial transcriptomics have enabled simultaneous preservation of high‐throughput gene expression profiles and the spatial context, enabling high‐resolution exploration of distinct regional characterization in tissue. To effectively understand the underlying biological mechanisms within tissue microenvironments, there is a requisite for methods that can accurately capture external spatial heterogeneity and interpret internal gene regulation from spatial transcriptomics data. However, current methods for region identification often lack the simultaneous characterizing of spatial structure and gene regulation, thereby limiting the ability of spatial dissection and gene interpretation. Here, stDCL is developed, a dual graph contrastive learning method to identify spatial domains and interpret gene regulation in spatial transcriptomics data. stDCL adaptively incorporates gene expression data and spatial information via a graph embedding autoencoder, thereby preserving critical information within the latent embedding representations. In addition, dual graph contrastive learning is proposed to train the model, ensuring that the latent embedding representation closely resembles the actual spatial distribution and exhibits cluster similarity. Benchmarking stDCL against other state‐of‐the‐art clustering methods using complex cortex datasets demonstrates its superior accuracy and effectiveness in identifying spatial domains. Our analysis of the imputation matrices generated by stDCL reveals its capability to reconstruct spatial hierarchical structures and refine differential expression assessment. Furthermore, it is demonstrated that the versatility of stDCL in interpretability of gene regulation, spatial heterogeneity at high resolution, and embryonic developmental patterns. In addition, it is also showed that stDCL can successfully annotate disease‐associated astrocyte subtypes in Alzheimer's disease and unravel multiple relevant pathways and regulatory mechanisms.https://doi.org/10.1002/advs.202410081dual graph contrastive learninggene regulationgraph contrastive learningspatial heterogeneity |
spellingShingle | Zhuohan Yu Yuning Yang Xingjian Chen Ka‐Chun Wong Zhaolei Zhang Yuming Zhao Xiangtao Li Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning Advanced Science dual graph contrastive learning gene regulation graph contrastive learning spatial heterogeneity |
title | Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning |
title_full | Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning |
title_fullStr | Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning |
title_full_unstemmed | Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning |
title_short | Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning |
title_sort | accurate spatial heterogeneity dissection and gene regulation interpretation for spatial transcriptomics using dual graph contrastive learning |
topic | dual graph contrastive learning gene regulation graph contrastive learning spatial heterogeneity |
url | https://doi.org/10.1002/advs.202410081 |
work_keys_str_mv | AT zhuohanyu accuratespatialheterogeneitydissectionandgeneregulationinterpretationforspatialtranscriptomicsusingdualgraphcontrastivelearning AT yuningyang accuratespatialheterogeneitydissectionandgeneregulationinterpretationforspatialtranscriptomicsusingdualgraphcontrastivelearning AT xingjianchen accuratespatialheterogeneitydissectionandgeneregulationinterpretationforspatialtranscriptomicsusingdualgraphcontrastivelearning AT kachunwong accuratespatialheterogeneitydissectionandgeneregulationinterpretationforspatialtranscriptomicsusingdualgraphcontrastivelearning AT zhaoleizhang accuratespatialheterogeneitydissectionandgeneregulationinterpretationforspatialtranscriptomicsusingdualgraphcontrastivelearning AT yumingzhao accuratespatialheterogeneitydissectionandgeneregulationinterpretationforspatialtranscriptomicsusingdualgraphcontrastivelearning AT xiangtaoli accuratespatialheterogeneitydissectionandgeneregulationinterpretationforspatialtranscriptomicsusingdualgraphcontrastivelearning |