通过将空间转录组学与组织学相结合来推断超分辨率组织结构。
Inferring super-resolution tissue architecture by integrating spatial transcriptomics with histology.
机构信息
Statistical Center for Single-Cell and Spatial Genomics, Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
Department of Human Genetics, School of Medicine, Emory University, Atlanta, GA, USA.
出版信息
Nat Biotechnol. 2024 Sep;42(9):1372-1377. doi: 10.1038/s41587-023-02019-9. Epub 2024 Jan 2.
Abstract
Spatial transcriptomics (ST) has demonstrated enormous potential for generating intricate molecular maps of cells within tissues. Here we present iStar, a method based on hierarchical image feature extraction that integrates ST data and high-resolution histology images to predict spatial gene expression with super-resolution. Our method enhances gene expression resolution to near-single-cell levels in ST and enables gene expression prediction in tissue sections where only histology images are available.
摘要
空间转录组学（ST）在生成组织内细胞的复杂分子图谱方面显示出巨大的潜力。在这里，我们提出了一种基于分层图像特征提取的方法 iStar，它将 ST 数据和高分辨率组织学图像集成在一起，以超分辨率预测空间基因表达。我们的方法将 ST 中的基因表达分辨率提高到接近单细胞水平，并能够在仅提供组织学图像的组织切片中预测基因表达。
相似文献
1
Inferring super-resolution tissue architecture by integrating spatial transcriptomics with histology.
Nat Biotechnol. 2024 Sep;42(9):1372-1377. doi: 10.1038/s41587-023-02019-9. Epub 2024 Jan 2.
2
stGRL: spatial domain identification, denoising, and imputation algorithm for spatial transcriptome data based on multi-task graph contrastive representation learning.
BMC Biol. 2025 Jul 1;23(1):177. doi: 10.1186/s12915-025-02290-z.
3
SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors.
Cancer Res. 2025 Jan 2;85(1):171-182. doi: 10.1158/0008-5472.CAN-24-1472.
4
Linking transcriptome and morphology in bone cells at cellular resolution with generative AI.
J Bone Miner Res. 2024 Dec 31;40(1):20-26. doi: 10.1093/jbmr/zjae151.
5
Gene Spatial Integration: enhancing spatial transcriptomics analysis via deep learning and batch effect mitigation.
Bioinformatics. 2025 Jun 13;41(6). doi: 10.1093/bioinformatics/btaf350.
6
Integrated analysis of single-cell RNA-seq and spatial transcriptomics to identify the lactylation-related protein TUBB2A as a potential biomarker for glioblastoma in cancer cells by machine learning.
Front Immunol. 2025 Jun 26;16:1601533. doi: 10.3389/fimmu.2025.1601533. eCollection 2025.
7
A visual-omics foundation model to bridge histopathology with spatial transcriptomics.
Nat Methods. 2025 May 29. doi: 10.1038/s41592-025-02707-1.
8
Deciphering normal and cancer stem cell niches by spatial transcriptomics: opportunities and challenges.
Genes Dev. 2025 Jan 7;39(1-2):64-85. doi: 10.1101/gad.351956.124.
9
A comprehensive review of spatial transcriptomics data alignment and integration.
Nucleic Acids Res. 2025 Jun 20;53(12). doi: 10.1093/nar/gkaf536.
10
Inferring single-cell resolution spatial gene expression via fusing spot-based spatial transcriptomics, location, and histology using GCN.
Brief Bioinform. 2024 Nov 22;26(1). doi: 10.1093/bib/bbae630.
引用本文的文献
1
SpaVGN: A hybrid deep learning framework for high-resolution spatial transcriptomics data reconstruction and spatial domain identification.
PLoS One. 2025 Aug 14;20(8):e0329122. doi: 10.1371/journal.pone.0329122. eCollection 2025.
2
Integrated in vivo combinatorial functional genomics and spatial transcriptomics of tumours to decode genotype-to-phenotype relationships.
Nat Biomed Eng. 2025 Jul 28. doi: 10.1038/s41551-025-01437-1.
3
STHD: probabilistic cell typing of single spots in whole transcriptome spatial data with high definition.
Genome Biol. 2025 Jul 18;26(1):213. doi: 10.1186/s13059-025-03608-4.
4
Predicting fine-grained cell types from histology images through cross-modal learning in spatial transcriptomics.
Bioinformatics. 2025 Jul 1;41(Supplement_1):i115-i124. doi: 10.1093/bioinformatics/btaf201.
5
PIVOT: an open-source tool for multi-omic spatial data registration.
bioRxiv. 2025 Jun 8:2025.06.08.658506. doi: 10.1101/2025.06.08.658506.
6
Informatics at the Frontier of Cancer Research.
Cancer Res. 2025 Aug 15;85(16):2967-2986. doi: 10.1158/0008-5472.CAN-24-2829.
7
Bridging cell morphological behaviors and molecular dynamics in multi-modal spatial omics with MorphLink.
Nat Commun. 2025 Jul 1;16(1):5878. doi: 10.1038/s41467-025-61142-0.
8
AI-Driven Transcriptome Prediction in Human Pathology: From Molecular Insights to Clinical Applications.
Biology (Basel). 2025 Jun 4;14(6):651. doi: 10.3390/biology14060651.
9
Spatially Resolved Panoramic in vivo CRISPR Screen via Perturb-DBiT.
Res Sq. 2025 May 8:rs.3.rs-6481967. doi: 10.21203/rs.3.rs-6481967/v1.
10
Cell-type deconvolution methods for spatial transcriptomics.
Nat Rev Genet. 2025 May 14. doi: 10.1038/s41576-025-00845-y.
本文引用的文献
1
Next-Generation Morphometry for pathomics-data mining in histopathology.
Nat Commun. 2023 Jan 28;14(1):470. doi: 10.1038/s41467-023-36173-0.
2
Multiplexed 3D atlas of state transitions and immune interaction in colorectal cancer.
Cell. 2023 Jan 19;186(2):363-381.e19. doi: 10.1016/j.cell.2022.12.028.
3
Spatiotemporal transcriptomic atlas of mouse organogenesis using DNA nanoball-patterned arrays.
Cell. 2022 May 12;185(10):1777-1792.e21. doi: 10.1016/j.cell.2022.04.003. Epub 2022 May 4.
4
Spatially informed cell-type deconvolution for spatial transcriptomics.
Nat Biotechnol. 2022 Sep;40(9):1349-1359. doi: 10.1038/s41587-022-01273-7. Epub 2022 May 2.
5
B cells and tertiary lymphoid structures as determinants of tumour immune contexture and clinical outcome.
Nat Rev Clin Oncol. 2022 Jul;19(7):441-457. doi: 10.1038/s41571-022-00619-z. Epub 2022 Apr 1.
6
Super-resolved spatial transcriptomics by deep data fusion.
Nat Biotechnol. 2022 Apr;40(4):476-479. doi: 10.1038/s41587-021-01075-3. Epub 2021 Nov 29.
7
SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network.
Nat Methods. 2021 Nov;18(11):1342-1351. doi: 10.1038/s41592-021-01255-8. Epub 2021 Oct 28.
8
Spatial deconvolution of HER2-positive breast cancer delineates tumor-associated cell type interactions.
Nat Commun. 2021 Oct 14;12(1):6012. doi: 10.1038/s41467-021-26271-2.
9
A single-cell and spatially resolved atlas of human breast cancers.
Nat Genet. 2021 Sep;53(9):1334-1347. doi: 10.1038/s41588-021-00911-1. Epub 2021 Sep 6.
10
SpaceM reveals metabolic states of single cells.
Nat Methods. 2021 Jul;18(7):799-805. doi: 10.1038/s41592-021-01198-0. Epub 2021 Jul 5.
Zotero 插件