STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration
Abstract Spatial transcriptomics is an essential application for investigating cellular structures and interactions and requires multimodal information to precisely study spatial domains. Here, we propose STAIG, a deep-learning model that integrates gene expression, spatial coordinates, and histolog...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-56276-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571497664741376 |
|---|---|
| author | Yitao Yang Yang Cui Xin Zeng Yubo Zhang Martin Loza Sung-Joon Park Kenta Nakai |
| author_facet | Yitao Yang Yang Cui Xin Zeng Yubo Zhang Martin Loza Sung-Joon Park Kenta Nakai |
| author_sort | Yitao Yang |
| collection | DOAJ |
| description | Abstract Spatial transcriptomics is an essential application for investigating cellular structures and interactions and requires multimodal information to precisely study spatial domains. Here, we propose STAIG, a deep-learning model that integrates gene expression, spatial coordinates, and histological images using graph-contrastive learning coupled with high-performance feature extraction. STAIG can integrate tissue slices without prealignment and remove batch effects. Moreover, it is designed to accept data acquired from various platforms, with or without histological images. By performing extensive benchmarks, we demonstrate the capability of STAIG to recognize spatial regions with high precision and uncover new insights into tumor microenvironments, highlighting its promising potential in deciphering spatial biological intricates. |
| format | Article |
| id | doaj-art-1b4f7570d6484c0c8527da90c9f45192 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-1b4f7570d6484c0c8527da90c9f451922025-02-02T12:31:47ZengNature PortfolioNature Communications2041-17232025-01-0116111510.1038/s41467-025-56276-0STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integrationYitao Yang0Yang Cui1Xin Zeng2Yubo Zhang3Martin Loza4Sung-Joon Park5Kenta Nakai6Department of Computational Biology and Medical Science, Graduate School of Frontier Sciences, the University of TokyoDepartment of Computational Biology and Medical Science, Graduate School of Frontier Sciences, the University of TokyoDepartment of Computational Biology and Medical Science, Graduate School of Frontier Sciences, the University of TokyoDepartment of Computational Biology and Medical Science, Graduate School of Frontier Sciences, the University of TokyoHuman Genome Center, the Institute of Medical Science, the University of TokyoHuman Genome Center, the Institute of Medical Science, the University of TokyoDepartment of Computational Biology and Medical Science, Graduate School of Frontier Sciences, the University of TokyoAbstract Spatial transcriptomics is an essential application for investigating cellular structures and interactions and requires multimodal information to precisely study spatial domains. Here, we propose STAIG, a deep-learning model that integrates gene expression, spatial coordinates, and histological images using graph-contrastive learning coupled with high-performance feature extraction. STAIG can integrate tissue slices without prealignment and remove batch effects. Moreover, it is designed to accept data acquired from various platforms, with or without histological images. By performing extensive benchmarks, we demonstrate the capability of STAIG to recognize spatial regions with high precision and uncover new insights into tumor microenvironments, highlighting its promising potential in deciphering spatial biological intricates.https://doi.org/10.1038/s41467-025-56276-0 |
| spellingShingle | Yitao Yang Yang Cui Xin Zeng Yubo Zhang Martin Loza Sung-Joon Park Kenta Nakai STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration Nature Communications |
| title | STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration |
| title_full | STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration |
| title_fullStr | STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration |
| title_full_unstemmed | STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration |
| title_short | STAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration |
| title_sort | staig spatial transcriptomics analysis via image aided graph contrastive learning for domain exploration and alignment free integration |
| url | https://doi.org/10.1038/s41467-025-56276-0 |
| work_keys_str_mv | AT yitaoyang staigspatialtranscriptomicsanalysisviaimageaidedgraphcontrastivelearningfordomainexplorationandalignmentfreeintegration AT yangcui staigspatialtranscriptomicsanalysisviaimageaidedgraphcontrastivelearningfordomainexplorationandalignmentfreeintegration AT xinzeng staigspatialtranscriptomicsanalysisviaimageaidedgraphcontrastivelearningfordomainexplorationandalignmentfreeintegration AT yubozhang staigspatialtranscriptomicsanalysisviaimageaidedgraphcontrastivelearningfordomainexplorationandalignmentfreeintegration AT martinloza staigspatialtranscriptomicsanalysisviaimageaidedgraphcontrastivelearningfordomainexplorationandalignmentfreeintegration AT sungjoonpark staigspatialtranscriptomicsanalysisviaimageaidedgraphcontrastivelearningfordomainexplorationandalignmentfreeintegration AT kentanakai staigspatialtranscriptomicsanalysisviaimageaidedgraphcontrastivelearningfordomainexplorationandalignmentfreeintegration |