AbstractSpatial omics technologies characterize tissue molecular properties with spatial information, but integrating and comparing spatial data across different technologies and modalities is challenging. A comparative analysis tool that can search, match and visualize both similarities and differences of molecular features in space across multiple samples is lacking.

。缺乏一种比较分析工具，可以在多个样本中搜索，匹配和可视化空间中分子特征的相似性和差异。

To address this, we introduce CAST (cross-sample alignment of spatial omics), a deep graph neural network-based method enabling spatial-to-spatial searching and matching at the single-cell level. CAST aligns tissues based on intrinsic similarities of spatial molecular features and reconstructs spatially resolved single-cell multi-omic profiles.

为了解决这个问题，我们引入了CAST（空间组学的交叉样本比对），这是一种基于深度图神经网络的方法，可以在单细胞水平上进行空间到空间的搜索和匹配。CAST基于空间分子特征的内在相似性对组织进行比对，并重建空间分辨的单细胞多组学图谱。

CAST further allows spatially resolved differential analysis (∆Analysis) to pinpoint and visualize disease-associated molecular pathways and cell–cell interactions and single-cell relative translational efficiency profiling to reveal variations in translational control across cell types and regions.

CAST进一步允许空间分辨差异分析（Δ分析）来精确定位和可视化疾病相关的分子途径和细胞间相互作用以及单细胞相对翻译效率分析，以揭示跨细胞类型和区域的翻译控制变化。

CAST serves as an integrative framework for seamless single-cell spatial data searching and matching across technologies, modalities and sample conditions..

CAST是跨技术、模式和样本条件进行无缝单细胞空间数据搜索和匹配的综合框架。。

Access through your institution

通过您的机构访问

Buy or subscribe

购买或订阅

This is a preview of subscription content, access via your institution

这是订阅内容的预览，可通过您的机构访问

Access options

访问选项

Access through your institution

通过您的机构访问

Access through your institution

通过您的机构访问

Change institution

变革机构

Buy or subscribe

购买或订阅

Access Nature and 54 other Nature Portfolio journalsGet Nature+, our best-value online-access subscription24,99 € / 30 dayscancel any timeLearn moreSubscription info for Chinese customersWe have a dedicated website for our Chinese customers. Please go to naturechina.com to subscribe to this journal.Go to naturechina.comBuy this articlePurchase on SpringerLinkInstant access to full article PDFBuy nowPrices may be subject to local taxes which are calculated during checkout.

Access Nature和54篇其他Nature Portfolio journalsGet Nature+，我们最有价值的在线订阅24,99欧元/30天，随时为中国客户获取更多订阅信息我们为中国客户提供了一个专门的网站。请访问naturechina.com订阅本期刊。访问naturechina.comBuy本文在Springerlink上购买即时访问完整文章PDFBuy now价格可能需要缴纳结帐时计算的地方税。

Additional access options:

其他访问选项：

Log in

登录

Learn about institutional subscriptions

了解机构订阅

Read our FAQs

阅读我们的常见问题

Contact customer support

联系客户支持

Fig. 1: Schematic overview of CAST.Fig. 2: CAST Stack automatically aligns tissue samples from biological replicates.Fig. 3: CAST aligns tissue samples across spatial technologies regardless of different tissue areas and gene panel sizes.Fig. 4: Delta-sample analysis detects disease-associated spatial features.Fig.

图1:CAST的示意图。图2：CAST堆栈自动对齐来自生物学重复的组织样品。图3:CAST跨空间技术对齐组织样本，而不考虑不同的组织区域和基因组大小。图4：δ样本分析检测疾病相关的空间特征。图。

5: CAST Projection enables single-cell integration of spatial omics data across multiple samples.Fig. 6: Single-cell resolved spatial–spatial integration of transcriptomics and translatomics reveals the ubiquitous heterogeneity of translation efficiency across cell types and brain regions..

5： CAST投影可以跨多个样本对空间组学数据进行单细胞整合。图6：转录组学和翻译组学的单细胞分辨空间-空间整合揭示了跨细胞类型和大脑区域翻译效率的普遍异质性。。

Data availability

数据可用性

The RIBOmap and STARmap datasets are available from (RIBOmap_mouse1, STARmap_mouse1 and RIBOmap_mouse2) https://singlecell.broadinstitute.org/single_cell/study/SCP1835 and (STARmap_mouse2) https://singlecell.broadinstitute.org/single_cell/study/SCP2203). The AD STARmap PLUS datasets (S1–S8, S64_1 and S64_2) are publicly available at https://singlecell.broadinstitute.org/single_cell/study/SCP1375/.

RIBOmap和STARmap数据集可从（RIBOmap\u mouse1、STARmap\u mouse1和RIBOmap\u mouse2）获得https://singlecell.broadinstitute.org/single_cell/study/SCP1835和（STARmap\u mouse2）https://singlecell.broadinstitute.org/single_cell/study/SCP2203)。AD STARmap PLUS数据集（S1-S8，S64\u 1和S64\u 2）可在https://singlecell.broadinstitute.org/single_cell/study/SCP1375/.

The mouse brain atlas dataset used is available at https://singlecell.broadinstitute.org/single_cell/study/SCP1830. The two Visium datasets (Mouse Brain Coronal Section 1 (FFPE) and Mouse Brain Coronal Section 2 (FFPE)) are available from https://www.10xgenomics.com/resources/datasets/mouse-brain-coronal-section-1-ffpe-2-standard and https://www.10xgenomics.com/resources/datasets/mouse-brain-coronal-section-2-ffpe-2-standard.

使用的小鼠大脑图谱数据集可在https://singlecell.broadinstitute.org/single_cell/study/SCP1830.两个Visium数据集（小鼠脑冠状切片1（FFPE）和小鼠脑冠状切片2（FFPE））可从https://www.10xgenomics.com/resources/datasets/mouse-brain-coronal-section-1-ffpe-2-standard和https://www.10xgenomics.com/resources/datasets/mouse-brain-coronal-section-2-ffpe-2-standard.

The MERFISH dataset (co1_slice37 in co1_sample13) is available from https://doi.brainimagelibrary.org/doi/10.35077/act-bag. The Slide-seq dataset (slice042) is available from https://docs.braincelldata.org/downloads/index.html. The two Stereo-seq MOSTA datasets (E16.5_E2S5 and E16.5_E2S6) are available from https://db.cngb.org/stomics/mosta/download/..

https://doi.brainimagelibrary.org/doi/10.35077/act-bag.Slide-seq数据集（slice042）可从https://docs.braincelldata.org/downloads/index.html.两个Stereo-seq MOSTA数据集（E16.5\u E2S5和E16.5\u E2S6）可从https://db.cngb.org/stomics/mosta/download/..

Code availability

代码可用性

The code and demos of CAST have been deposited to GitHub at (https://github.com/wanglab-broad/CAST) and Zenodo (https://zenodo.org/doi/10.5281/zenodo.12215314 (ref. 48)). The implementation of CAST, as well as the tutorials, are available in the demo pipeline files and CAST document page (https://cast-tutorial.readthedocs.io/en/latest/)..

CAST的代码和演示已保存到GitHub(https://github.com/wanglab-broad/CAST)和Zenodo(https://zenodo.org/doi/10.5281/zenodo.12215314（参考文献48））。演示管道文件和CAST文档页面中提供了CAST的实现以及教程(https://cast-tutorial.readthedocs.io/en/latest/)。。

ReferencesShah, S., Lubeck, E., Zhou, W. & Cai, L. In situ transcription profiling of single cells reveals spatial organization of cells in the mouse hippocampus. Neuron 92, 342–357 (2016).Article

参考Shah，S.，Lubeck，E.，Zhou，W。＆Cai，L。单细胞的原位转录谱揭示了小鼠海马中细胞的空间组织。神经元92342-357（2016）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Moffitt, J. R. et al. Molecular, spatial, and functional single-cell profiling of the hypothalamic preoptic region. Science 362, eaau5324 (2018).Article

Moffitt，J.R.等人。下丘脑视前区的分子，空间和功能单细胞分析。科学362，eaau5324（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Stickels, R. R. et al. Highly sensitive spatial transcriptomics at near-cellular resolution with Slide-seqV2. Nat. Biotechnol. 39, 313–319 (2021).Article

Stickels，R.R.等人。使用Slide-seqV2在近细胞分辨率下进行高度敏感的空间转录组学。美国国家生物技术公司。39313-319（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Chen, A. et al. Spatiotemporal transcriptomic atlas of mouse organogenesis using DNA nanoball-patterned arrays. Cell 185, 1777–1792.e21 (2022).Article

Chen，A。等人。使用DNA纳米球图案阵列的小鼠器官发生的时空转录组图谱。细胞1851777-1792.e21（2022）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Zeng, H. et al. Integrative in situ mapping of single-cell transcriptional states and tissue histopathology in a mouse model of Alzheimer’s disease. Nat. Neurosci. 26, 430–446 (2023).CAS

Zeng，H.等人。阿尔茨海默病小鼠模型中单细胞转录状态和组织组织病理学的整合原位定位。自然神经科学。26430-446（2023）。中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lu, T., Ang, C. E. & Zhuang, X. Spatially resolved epigenomic profiling of single cells in complex tissues. Cell 185, 4448–4464.e17 (2022).Article

Lu，T.，Ang，C.E。＆Zhuang，X。复杂组织中单细胞的空间分辨表观基因组分析。细胞1854448–4464.e17（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zeng, H. et al. Spatially resolved single-cell translatomics at molecular resolution. Science 380, eadd3067 (2023).Article

Zeng，H。等人。分子分辨率的空间分辨单细胞翻译组学。科学380，eadd3067（2023）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Goltsev, Y. et al. Deep profiling of mouse splenic architecture with CODEX multiplexed imaging. Cell 174, 968–981.e15 (2018).Article

Goltsev，Y。等人。用CODEX多重成像对小鼠脾脏结构进行深度分析。细胞174968-981.e15（2018）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zeira, R., Land, M., Strzalkowski, A. & Raphael, B. J. Alignment and integration of spatial transcriptomics data. Nat. Methods 19, 567–575 (2022).Article

Zeira，R.，Land，M.，Strzalkowski，A。＆Raphael，B.J。空间转录组学数据的比对和整合。自然方法19567-575（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Yuan, Y. & Bar-Joseph, Z. GCNG: graph convolutional networks for inferring gene interaction from spatial transcriptomics data. Genome Biol. 21, 300 (2020).Article

Yuan，Y。＆Bar Joseph，Z。GCNG：用于从空间转录组学数据推断基因相互作用的图卷积网络。基因组生物学。21300（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Hu, J. et al. SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network. Nat. Methods 18, 1342–1351 (2021).Article

Hu，J.等人，《SpaGCN：整合基因表达、空间位置和组织学，通过图卷积网络识别空间域和空间可变基因》。Nat。方法181342-1351（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Dong, K. & Zhang, S. Deciphering spatial domains from spatially resolved transcriptomics with an adaptive graph attention auto-encoder. Nat. Commun. 13, 1739 (2022).Article

Dong，K。＆Zhang，S。使用自适应图形注意自动编码器从空间分辨的转录组学中破译空间域。国家公社。131739（2022年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Fischer, D. S., Schaar, A. C. & Theis, F. J. Modeling intercellular communication in tissues using spatial graphs of cells. Nat. Biotechnol. 41, 332–336 (2023).Article

Fischer，D.S.，Schaar，A.C。＆Theis，F.J。使用细胞空间图模拟组织中的细胞间通讯。美国国家生物技术公司。41332-336（2023）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Palla, G., Fischer, D. S., Regev, A. & Theis, F. J. Spatial components of molecular tissue biology. Nat. Biotechnol. 40, 308–318 (2022).Article

Palla，G.，Fischer，D.S.，Regev，A。＆Theis，F.J。分子组织生物学的空间成分。美国国家生物技术公司。40308-318（2022）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Long, Y. et al. Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST. Nat. Commun. 14, 1155 (2023).Article

Long，Y.等人。空间转录组学与GraphST的空间信息聚类，整合和去卷积。国家公社。141155（2023）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Chen, M., Wei, Z., Huang, Z., Ding, B. & Li, Y. Simple and deep graph convolutional networks. in Proceedings of the 37th International Conference on Machine Learning 1725–1735 (PMLR, 2020).Lein, E. S. et al. Genome-wide atlas of gene expression in the adult mouse brain. Nature 445, 168–176 (2007).Article .

Chen，M.，Wei，Z.，Huang，Z.，Ding，B。＆Li，Y。简单和深度图卷积网络。在第37届国际机器学习会议论文集1725-1735（PMLR，2020）中。Lein，E.S.等人，《成年小鼠大脑中全基因组基因表达图谱》。《自然》445168-176（2007）。文章。

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Wang, Q. et al. The Allen Mouse Brain Common Coordinate Framework: a 3D reference atlas. Cell 181, 936–953.e20 (2020).Article

Wang，Q。等人。艾伦小鼠大脑共同坐标框架：3D参考地图集。细胞181936-953.e20（2020）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zhang, M. et al. Molecularly defined and spatially resolved cell atlas of the whole mouse brain. Nature 624, 343–354 (2023).Article

Zhang，M.等人。整个小鼠大脑的分子定义和空间分辨细胞图谱。自然624343-354（2023）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Langlieb, J. et al. The molecular cytoarchitecture of the adult mouse brain. Nature 624, 333–342 (2023).Article

Langlieb，J。等人。成年小鼠大脑的分子细胞结构。自然624333-342（2023）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Shi, H. et al. Spatial atlas of the mouse central nervous system at molecular resolution. Nature 622, 552–561 (2023).Article

Shi，H.等人。分子分辨率的小鼠中枢神经系统空间图谱。自然622552-561（2023）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Rood, J. E. et al. Toward a common coordinate framework for the human body. Cell 179, 1455–1467 (2019).Article

Rood，J.E.等人致力于人体的共同坐标框架。细胞1791455-1467（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Armingol, E., Officer, A., Harismendy, O. & Lewis, N. E. Deciphering cell–cell interactions and communication from gene expression. Nat. Rev. Genet. 22, 71–88 (2021).Article

Armingol，E.，Officer，A.，Harismendy，O。＆Lewis，N.E。从基因表达中解读细胞间相互作用和通讯。Genet自然Rev。22，71-88（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Yeh, F. L., Wang, Y., Tom, I., Gonzalez, L. C. & Sheng, M. TREM2 binds to apolipoproteins, including APOE and CLU/APOJ, and thereby facilitates uptake of amyloid-β by microglia. Neuron 91, 328–340 (2016).Krasemann, S. et al. The TREM2–APOE pathway drives the transcriptional phenotype of dysfunctional microglia in neurodegenerative diseases.

Yeh，F.L.，Wang，Y.，Tom，I.，Gonzalez，L.C。＆Sheng，M。TREM2与载脂蛋白结合，包括APOE和CLU/APOJ，从而促进小胶质细胞摄取淀粉样蛋白-β。神经元91328-340（2016）。。

Immunity 47, 566–581.e9 (2017).Article .

免疫力47566-581.e9（2017）。文章。

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Parhizkar, S. et al. Loss of TREM2 function increases amyloid seeding but reduces plaque-associated ApoE. Nat. Neurosci. 22, 191–204 (2019).Article

Parhizkar，S。等人。TREM2功能的丧失增加了淀粉样蛋白的接种，但减少了斑块相关的ApoE。自然神经科学。22191-204（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wolfe, C. M., Fitz, N. F., Nam, K. N., Lefterov, I. & Koldamova, R. The role of APOE and TREM2 in Alzheimer's disease-current understanding and perspectives. Int. J. Mol. Sci. 20, 81 (2019).Article

Wolfe，C.M.，Fitz，N.F.，Nam，K.N.，Lefterov，I。＆Koldamova，R。APOE和TREM2在阿尔茨海默病当前理解和观点中的作用。Int.J.Mol.Sci。20,81（2019）。文章

Google Scholar

谷歌学者

Nandrot, E. F. et al. Essential role for MFG-E8 as ligand for αvβ5 integrin in diurnal retinal phagocytosis. Proc. Natl Acad. Sci. USA 104, 12005–12010 (2007).Article

Nandrot，E.F.等人。MFG-E8作为αvβ5整合素配体在昼夜视网膜吞噬作用中的重要作用。程序。国家科学院。科学。美国10412005–12010（2007）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wei, X. et al. Single-cell Stereo-seq reveals induced progenitor cells involved in axolotl brain regeneration. Science 377, eabp9444 (2022).Johnson, W. E., Li, C. & Rabinovic, A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8, 118–127 (2007).Article .

Wei，X。等人。单细胞Stereo-seq揭示了参与轴突脑再生的诱导祖细胞。科学377，eabp9444（2022）。Johnson，W.E.，Li，C。＆Rabinovic，A。使用经验贝叶斯方法调整微阵列表达数据中的批次效应。生物统计学8118-127（2007）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Korsunsky, I. et al. Fast, sensitive and accurate integration of single-cell data with Harmony. Nat. Methods 16, 1289–1296 (2019).Article

Korsunsky，I。等人。单细胞数据与和谐的快速，灵敏和准确整合。自然方法161289-1296（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Spitzer, M. H. et al. An interactive reference framework for modeling a dynamic immune system. Science 349, 1259425 (2015).Baron, M. et al. A single-cell transcriptomic map of the human and mouse pancreas reveals inter- and intra-cell population structure. Cell Syst. 3, 346–360.e4 (2016).Article .

Spitzer，M.H.等人。用于建模动态免疫系统的交互式参考框架。科学3491259425（2015）。Baron，M。等人。人和小鼠胰腺的单细胞转录组图谱揭示了细胞间和细胞内的种群结构。细胞系统。3346-360.e4（2016）。文章。

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Haghverdi, L., Lun, A. T. L., Morgan, M. D. & Marioni, J. C. Batch effects in single-cell RNA-sequencing data are corrected by matching mutual nearest neighbors. Nat. Biotechnol. 36, 421–427 (2018).Article

Haghverdi，L.，Lun，A.T.L.，Morgan，M.D。和Marioni，J.C。通过匹配相互最近的邻居来校正单细胞RNA测序数据中的批次效应。美国国家生物技术公司。36421-427（2018）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Biancalani, T. et al. Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram. Nat. Methods 18, 1352–1362 (2021).Article

Biancalani，T。等人。空间分辨单细胞转录组与七巧板的深度学习和比对。自然方法181352-1362（2021）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kleshchevnikov, V. et al. Cell2location maps fine-grained cell types in spatial transcriptomics. Nat. Biotechnol. 40, 661–671 (2022).Article

Kleshchevnikov，V。等人Cell2location绘制了空间转录组学中的细粒细胞类型。美国国家生物技术公司。40661-671（2022）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Stuart, T. et al. Comprehensive integration of single-cell data. Cell 177, 1888–1902.e21 (2019).Article

Stuart，T。等人。单细胞数据的综合集成。细胞1771888-1902.e21（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Welch, J. D. et al. Single-cell multi-omic integration compares and contrasts features of brain cell identity. Cell 177, 1873–1887.e17 (2019).Article

Welch，J.D.等人，《单细胞多组学整合》比较和对比了脑细胞同一性的特征。细胞1771873-1887.e17（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Virshup, I., Rybakov, S., Theis, F. J., Angerer, P. & Alexander Wolf, F. anndata: annotated data. Preprint at bioRxiv https://doi.org/10.1101/2021.12.16.473007 (2021).Wang, M. et al. Deep Graph Library: a graph-centric, highly-performant package for graph neural networks. Preprint at https://arxiv.org/abs/1909.01315 (2019).Zhang, H., Wu, Q., Yan, J., Wipf, D.

Virshup，I.，Rybakov，S.，Theis，F.J.，Angerer，P。和Alexander Wolf，F。anndata：注释数据。bioRxiv预印本https://doi.org/10.1101/2021.12.16.473007（2021年）。。预印于https://arxiv.org/abs/1909.01315（2019年）。张，吴，严，J，维普，D。

& Yu, P. S. From canonical correlation analysis to self-supervised graph neural networks. in Advances in Neural Information Processing Systems 34, 76–89 (Curran Associates, 2021).Rueckert, D. et al. Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med.

&Yu，P.S。从典型相关分析到自监督图神经网络。《神经信息处理系统进展》34,76-89（Curran Associates，2021）。Rueckert，D。等人。使用自由形式变形的非刚性配准：应用于乳房MR图像。。医学。

Imaging 18, 712–721 (1999).Article .

成像18712-721（1999）。文章。

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Jones, A., Townes, F. W., Li, D. & Engelhardt, B. E. Alignment of spatial genomics data using deep Gaussian processes. Nat. Methods 20, 1379–1387 (2023).Article

Jones，A.，Townes，F.W.，Li，D。＆Engelhardt，B.E。使用深高斯过程对齐空间基因组学数据。自然方法201379-1387（2023）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Efremova, M., Vento-Tormo, M., Teichmann, S. A. & Vento-Tormo, R. CellPhoneDB: inferring cell–cell communication from combined expression of multi-subunit ligand–receptor complexes. Nat. Protoc. 15, 1484–1506 (2020).Article

Efremova，M.，Vento-Tormo，M.，Teichmann，S.A。和Vento-Tormo，R.CellPhoneDB：从多亚基配体-受体复合物的组合表达推断细胞间通讯。自然协议。151484-1506（2020）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Palla, G. et al. Squidpy: a scalable framework for spatial omics analysis. Nat. Methods 19, 171–178 (2022).Article

Palla，G.等人，《Squidpy：空间组学分析的可扩展框架》。自然方法19171-178（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wolf, F. A., Angerer, P. & Theis, F. J. SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 19, 15 (2018).Article

Wolf，F.A.，Angerer，P。＆Theis，F.J。SCANPY：大规模单细胞基因表达数据分析。基因组生物学。19,15（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Yu, G., Wang, L.-G., Han, Y. & He, Q.-Y. clusterProfiler: an R package for comparing biological themes among gene clusters. OMICS 16, 284–287 (2012).Article

Yu，G.，Wang，L.-G.，Han，Y.＆He，Q.-Y.clusterProfiler：用于比较基因簇之间生物学主题的R包。组学16284-287（2012）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Tang, Z. et al. Search and match across spatial omics samples at single-cell resolution. Zenodo https://zenodo.org/doi/10.5281/zenodo.12215314 (2024).Download referencesAcknowledgementsWe thank H. Shi and Y. Zhou for their help with the brain region identification, J. N. Pan for the help with tutorials, documentation of the CAST software package and paper revision, H.

Tang，Z.等人。在单细胞分辨率下搜索和匹配空间组学样本。泽诺多https://zenodo.org/doi/10.5281/zenodo.12215314（2024年）。下载参考文献致谢我们感谢H.Shi和Y.Zhou在大脑区域识别方面的帮助，J.N.Pan在教程，CAST软件包文档和论文修订方面的帮助，H。

Zhou, K. Maher, J. Tian, W. Wang and P. Tan for discussion. Z.T. thanks X. Jin for his guidance in formulating the algorithms and Y. Zhou for technical assistance. S.L. thanks W. Mo for the discussions on GNNs. X.W. gratefully acknowledges support from the Thomas D. and Virginia W. Cabot Professorship, Edward Scolnick Professorship, Ono Pharma Breakthrough Science Initiative Award, Merkin Institute Fellowship, NIH DP2 New Innovator Award (1DP2GM146245) and National Institutes of Health BRAIN CONNECTS (UM1 NS132173).Author informationAuthor notesThese authors contributed equally: Zefang Tang, Shuchen Luo.Authors and AffiliationsBroad Institute of MIT and Harvard, Cambridge, MA, USAZefang Tang, Shuchen Luo, Hu Zeng, Jiahao Huang, Xin Sui, Morgan Wu & Xiao WangDepartment of Chemistry, Massachusetts Institute of Technology, Cambridge, MA, USAZefang Tang, Shuchen Luo, Hu Zeng, Jiahao Huang, Xin Sui & Xiao WangAuthorsZefang TangView author publicationsYou can also search for this author in.

Zhou，K。Maher，J。Tian，W。Wang和P。Tan进行讨论。Z、 T.感谢X.Jin在制定算法方面的指导，以及Y.Zhou的技术援助。S、 L.感谢W.Mo就GNNs进行的讨论。十、 W.非常感谢Thomas D.和Virginia W.Cabot教授、Edward Scolnick教授、Ono Pharma突破性科学倡议奖、Merkin研究所奖学金、NIH DP2新创新者奖（1DP2GM146245）和National Institutes of Health BRAIN CONNECTS（UM1 NS132173）的支持。作者信息作者注意到这些作者做出了同样的贡献：唐泽芳，罗淑晨。作者和附属机构麻省理工学院和哈佛大学路学院，剑桥，马萨诸塞州，USAZefang Tang，罗书臣，胡增，黄家豪，辛穗，Morgan Wu＆Xiao Wang麻省理工学院化学系，剑桥，马萨诸塞州，USAZefang Tang，罗书臣，胡增，黄家豪，辛穗＆Xiao Wang作者唐泽芳观点作者出版物您也可以在中搜索这位作者。

PubMed Google ScholarShuchen LuoView author publicationsYou can also search for this author in

PubMed Google ScholarShuchen LuoView作者出版物您也可以在

PubMed Google ScholarHu ZengView author publicationsYou can also search for this author in

PubMed Google ScholarHu ZengView作者出版物您也可以在

PubMed Google ScholarJiahao HuangView author publicationsYou can also search for this author in

PubMed Google ScholarJiahao HuangView作者出版物您也可以在

PubMed Google ScholarXin SuiView author publicationsYou can also search for this author in

PubMed Google ScholarXin SuiView作者出版物您也可以在

PubMed Google ScholarMorgan WuView author publicationsYou can also search for this author in

PubMed Google Scholarmargan WuView作者出版物您也可以在

PubMed Google ScholarXiao WangView author publicationsYou can also search for this author in

PubMed Google ScholarXiao WangView作者出版物您也可以在

PubMed Google ScholarContributionsX.W., Z.T. and S.L. conceived the study. Z.T. and S.L. formulated, developed and implemented the CAST algorithm. H.Z. and X.S. collected RIBOmap and STARmap half-brain data. Z.T. and J.H. performed data preprocessing of the RIBOmap and STARmap half-brain data.

PubMed谷歌学术贡献x。W、 ，Z.T.和S.L.构思了这项研究。Z、 T.和S.L.制定，开发和实施了CAST算法。H、 Z.和X.S.收集了RIBOmap和STARmap半脑数据。Z、 T.和J.H.对RIBOmap和STARmap半脑数据进行了数据预处理。

J.H. reproduced CAST code. Z.T. and S.L. performed data analysis under the supervision of X.W. The manuscript was written by Z.T., S.L., M.W. and X.W. All authors read and approved the manuscript.Corresponding authorCorrespondence to.

J、 H.复制的铸造代码。Z、 T.和S.L.在X.W.的监督下进行了数据分析。手稿由Z.T.，S.L.，M.W.和X.W.撰写。所有作者均阅读并批准了手稿。对应作者对应。

Xiao Wang.Ethics declarations

小王。道德宣言

Competing interests

相互竞争的利益

X.W. is a scientific co-founder of Stellaromics. X.W. and H.Z. are inventors on pending patent applications related to STARmap PLUS and RIBOmap. The other authors declare no competing interests.

十、 W.是Stellaromics的科学联合创始人。十、 W.和H.Z.是与STARmap PLUS和RIBOmap相关的未决专利申请的发明人。其他作者声明没有利益冲突。

Peer review

同行评审

Peer review information

同行评审信息

Nature Methods thanks Qing Nie and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Peer reviewer reports are available.

。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Extended dataExtended Data Fig. 1 CAST Mark identifies the common spatial features between the simulated and real samples.a, The schematic workflow of the self-supervised learning framework used in CAST Mark.

Additional informationPublisher的注释Springer Nature在已发布的地图和机构隶属关系中的管辖权主张方面保持中立。扩展数据扩展数据图1 CAST标记识别了模拟样本和真实样本之间的共同空间特征。a，CAST标记中使用的自监督学习框架的示意工作流程。

b, The simulation strategy to generate the simulated dataset S1’ from the real sample S1 (8 month, control) in STARmap PLUS dataset (Methods). c, The k-means (k = 20) clustering results of the graph embedding generated by CAST Mark. Different colors in the cells indicate different clusters of the graph embedding.

b、 从STARmap PLUS数据集（方法）中的真实样本S1（8个月，对照）生成模拟数据集S1'的模拟策略。c、 由CAST Mark生成的图嵌入的k均值（k = 20）聚类结果。单元格中的不同颜色表示图嵌入的不同聚类。

d, The t-SNE visualization of the spatial embedding labeled with samples (left) and k-means clusters (k = 20, right). e, The clustering performance adjusted Rand index (ARI) and the percentage of the consistent cells in different numbers of the clusters (k). Each box contains 10 technical replicates using different random seeds.

d、 用样本（左）和k均值聚类（k=20，右）标记的空间嵌入的t-SNE可视化。e、 。每个盒子包含10个使用不同随机种子的技术复制品。

f, The k-means (k = 100) clustering results of the spatial embedding generated by CAST Mark. g, The distance distribution of the cells in different k-clusters and non-distribution groups (sample size = 8,789 for each group). The distance indicates each cell in the simulated sample S1’ to the closest one with the same cluster in the S1 sample.

f、 由CAST标记产生的空间嵌入的k均值（k = 100）聚类结果，不同k簇和非分布组中细胞的距离分布（每组样本量=8789）。该距离表示模拟样品S1'中的每个细胞与S1样品中具有相同簇的最接近的细胞。

In the boxplots of e and g, the middle line indicates the median; the first and third quartiles are shown by the lower and upper lines, respectively; the upper and lower whiskers extend to values not exceeding 1.5 times the IQR. h, Enabled by a deep GNN and a self-supervised CCA objective, CAST Mark outperforms existing GNN-based methods (SpaGCN, STAGATE, GraphST) in tissue segmentation tasks at a ~ 9,800-cell scale.

在e和g的箱线图中，中线表示中位数；第一和第三四分位数分别由下线和上线显示；上下晶须的延伸值不超过IQR的1.5倍。h、 通过深度GNN和自我监督的CCA目标，CAST-Mark在9800个细胞规模的组织分割任务中优于现有的基于GNN的方法（SpaGCN，STAGATE，GraphST）。

Segmentation results w.

分割结果w。

Nat Methods (2024). https://doi.org/10.1038/s41592-024-02410-7Download citationReceived: 23 May 2023Accepted: 12 August 2024Published: 18 September 2024DOI: https://doi.org/10.1038/s41592-024-02410-7Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

Nat方法（2024）。https://doi.org/10.1038/s41592-024-02410-7Download引文接收日期：2023年5月23日接收日期：2024年8月12日发布日期：2024年9月18日OI：https://doi.org/10.1038/s41592-024-02410-7Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供