{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T03:43:22Z","timestamp":1792813402685,"version":"4.5.0"},"reference-count":55,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:00:00Z","timestamp":1743638400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62262069"],"award-info":[{"award-number":["62262069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12101026"],"award-info":[{"award-number":["12101026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan Fundamental Research Project","award":["202301AT070230"],"award-info":[{"award-number":["202301AT070230"]}]},{"name":"Young Talent Program of Yunnan Province","award":["C619300A067"],"award-info":[{"award-number":["C619300A067"]}]},{"name":"Scientific Research Fund Project of Yunnan Education Department","award":["2025Y0011"],"award-info":[{"award-number":["2025Y0011"]}]},{"name":"Graduate Research and Innovation Fund Project of Yunnan University","award":["KC-24249547"],"award-info":[{"award-number":["KC-24249547"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Understanding the spatial locations of cell within tissues is crucial for unraveling the organization of cellular diversity. Recent advancements in spatial resolved transcriptomics (SRT) have enabled the analysis of gene expression while preserving the spatial context within tissues. Spatial domain characterization is a critical first step in SRT data analysis, providing the foundation for subsequent analyses and insights into biological implications. Graph neural networks (GNNs) have emerged as a common tool for addressing this challenge due to the structural nature of SRT data. However, current graph-based deep learning approaches often overlook the instability caused by the high sparsity of SRT data. Masking mechanisms, as an effective self-supervised learning strategy, can enhance the robustness of these models. To this end, we propose SpaMask, dual masking graph autoencoder with contrastive learning for SRT analysis. Unlike previous GNNs, SpaMask masks a portion of spot nodes and spot-to-spot edges to enhance its performance and robustness. SpaMask combines Masked Graph Autoencoders (MGAE) and Masked Graph Contrastive Learning (MGCL) modules, with MGAE using node masking to leverage spatial neighbors for improved clustering accuracy, while MGCL applies edge masking to create a contrastive loss framework that tightens embeddings of adjacent nodes based on spatial proximity and feature similarity. We conducted a comprehensive evaluation of SpaMask on eight datasets from five different platforms. Compared to existing methods, SpaMask achieves superior clustering accuracy and effective batch correction.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012881","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T20:01:58Z","timestamp":1743710518000},"page":"e1012881","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":55,"title":["SpaMask: Dual masking graph autoencoder with contrastive learning for spatial transcriptomics"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2558-2911","authenticated-orcid":true,"given":"Wenwen","family":"Min","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghai","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"issue":"10","key":"pcbi.1012881.ref001","doi-asserted-by":"crossref","first-page":"1706","DOI":"10.1101\/gr.275224.121","article-title":"Advances in spatial transcriptomic data analysis","volume":"31","author":"R Dries","year":"2021","journal-title":"Genome Res"},{"issue":"6","key":"pcbi.1012881.ref002","doi-asserted-by":"crossref","first-page":"bbae571","DOI":"10.1093\/bib\/bbae571","article-title":"SpaDiT: diffusion transformer for spatial gene expression prediction using scRNA-seq","volume":"25","author":"X Li","year":"2024","journal-title":"Brief Bioinform"},{"issue":"20","key":"pcbi.1012881.ref003","doi-asserted-by":"crossref","first-page":"e103","DOI":"10.1093\/nar\/gkad801","article-title":"STAMarker: determining spatial domain-specific variable genes with saliency maps in deep learning","volume":"51","author":"C Zhang","year":"2023","journal-title":"Nucleic Acids Res"},{"issue":"2","key":"pcbi.1012881.ref004","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.cell.2020.05.039","article-title":"Multimodal analysis of composition and spatial architecture in human squamous cell carcinoma","volume":"182","author":"AL Ji","year":"2020","journal-title":"Cell"},{"issue":"10","key":"pcbi.1012881.ref005","doi-asserted-by":"crossref","first-page":"1777","DOI":"10.1016\/j.cell.2022.04.003","article-title":"Spatiotemporal transcriptomic atlas of mouse organogenesis using DNA nanoball-patterned arrays","volume":"185","author":"A Chen","year":"2022","journal-title":"Cell"},{"issue":"1","key":"pcbi.1012881.ref006","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1038\/s41467-022-29439-6","article-title":"Deciphering spatial domains from spatially resolved transcriptomics with an adaptive graph attention auto-encoder","volume":"13","author":"K Dong","year":"2022","journal-title":"Nat Commun"},{"issue":"4","key":"pcbi.1012881.ref007","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1038\/s41592-024-02215-8","article-title":"Benchmarking spatial clustering methods with spatially resolved transcriptomics data","volume":"21","author":"Z Yuan","year":"2024","journal-title":"Nat Methods"},{"issue":"1","key":"pcbi.1012881.ref008","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1186\/s13073-022-01075-1","article-title":"An introduction to spatial transcriptomics for biomedical research","volume":"14","author":"CG Williams","year":"2022","journal-title":"Genome Med"},{"issue":"11","key":"pcbi.1012881.ref009","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41592-021-01255-8","article-title":"SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network","volume":"18","author":"J Hu","year":"2021","journal-title":"Nat Methods"},{"issue":"1","key":"pcbi.1012881.ref010","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1186\/s13059-024-03361-0","article-title":"Benchmarking clustering, alignment, and integration methods for spatial transcriptomics","volume":"25","author":"Y Hu","year":"2024","journal-title":"Genome Biol"},{"issue":"10","key":"pcbi.1012881.ref011","doi-asserted-by":"crossref","first-page":"P10008","DOI":"10.1088\/1742-5468\/2008\/10\/P10008","article-title":"Fast unfolding of communities in large networks","author":"VD Blondel","year":"2008","journal-title":"J Statist Mech: Theory Exp"},{"issue":"11","key":"pcbi.1012881.ref012","doi-asserted-by":"crossref","first-page":"1375","DOI":"10.1038\/s41587-021-00935-2","article-title":"Spatial transcriptomics at subspot resolution with BayesSpace","volume":"39","author":"E Zhao","year":"2021","journal-title":"Nat Biotechnol"},{"issue":"1","key":"pcbi.1012881.ref013","first-page":"106","article-title":"A comprehensive overview of graph neural network-based approaches to clustering for spatial transcriptomics","volume":"23","author":"T Liu","year":"2023","journal-title":"Comput Struct Biotechnol J."},{"issue":"1","key":"pcbi.1012881.ref014","doi-asserted-by":"crossref","first-page":"bbae630","DOI":"10.1093\/bib\/bbae630","article-title":"Inferring single-cell resolution spatial gene expression via fusing spot-based spatial transcriptomics, location, and histology using GCN","volume":"26","author":"S Xue","year":"2024","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1012881.ref015","first-page":"857","article-title":"Self-supervised learning: generative or contrastive","volume":"35","author":"X Liu","year":"2021","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"pcbi.1012881.ref016","article-title":"Semi-supervised classification with graph convolutional networks","author":"T Kipf"},{"issue":"45","key":"pcbi.1012881.ref017","doi-asserted-by":"crossref","first-page":"e2403572","DOI":"10.1002\/advs.202403572","article-title":"Spatially informed graph structure learning extracts insights from spatial transcriptomics","volume":"11","author":"W Nie","year":"2024","journal-title":"Adv Sci (Weinh)"},{"issue":"6","key":"pcbi.1012881.ref018","doi-asserted-by":"crossref","first-page":"bbae551","DOI":"10.1093\/bib\/bbae551","article-title":"Multimodal contrastive learning for spatial gene expression prediction using histology images","volume":"25","author":"W Min","year":"2024","journal-title":"Brief Bioinform"},{"issue":"7","key":"pcbi.1012881.ref019","doi-asserted-by":"crossref","first-page":"btae451","DOI":"10.1093\/bioinformatics\/btae451","article-title":"Unraveling spatial domain characterization in spatially resolved transcriptomics with robust graph contrastive clustering","volume":"40","author":"Y Zhang","year":"2024","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1012881.ref020","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s13073-024-01283-x","article-title":"Unsupervised spatially embedded deep representation of spatial transcriptomics","volume":"16","author":"H Xu","year":"2024","journal-title":"Genome Med"},{"key":"pcbi.1012881.ref021","article-title":"Deep graph infomax","author":"P Velickovic"},{"issue":"6","key":"pcbi.1012881.ref022","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1038\/s43588-022-00266-5","article-title":"Cell clustering for spatial transcriptomics data with graph neural networks","volume":"2","author":"J Li","year":"2022","journal-title":"Nat Comput Sci"},{"issue":"1","key":"pcbi.1012881.ref023","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1038\/s41467-023-36796-3","article-title":"Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST","volume":"14","author":"Y Long","year":"2023","journal-title":"Nat Commun"},{"issue":"11","key":"pcbi.1012881.ref024","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1038\/s42256-023-00734-1","article-title":"Construction of a 3D whole organism spatial atlas by joint modelling of multiple slices with deep neural networks","volume":"5","author":"G Wang","year":"2023","journal-title":"Nat Mach Intell"},{"issue":"1","key":"pcbi.1012881.ref025","doi-asserted-by":"crossref","first-page":"7603","DOI":"10.1038\/s41467-023-43220-3","article-title":"SPACEL: deep learning-based characterization of spatial transcriptome architectures","volume":"14","author":"H Xu","year":"2023","journal-title":"Nat Commun"},{"issue":"10","key":"pcbi.1012881.ref026","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1038\/s43588-023-00528-w","article-title":"Integrating spatial transcriptomics data across different conditions, technologies and developmental stages","volume":"3","author":"X Zhou","year":"2023","journal-title":"Nat Comput Sci"},{"key":"pcbi.1012881.ref027","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1145\/3534678.3539321","article-title":"GraphMAE: self-supervised masked graph autoencoders","author":"Z Hou","year":"2022","journal-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"},{"key":"pcbi.1012881.ref028","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1145\/3543507.3583379","article-title":"GraphMAE2: a decoding-enhanced masked self-supervised graph learner","author":"Z Hou","year":"2023","journal-title":"Proceedings of the ACM Web Conference 2023"},{"key":"pcbi.1012881.ref029","first-page":"1268","article-title":"What\u2019s behind the mask: understanding masked graph modeling for graph autoencoders","author":"J Li","year":"2023","journal-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"},{"key":"pcbi.1012881.ref030","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1145\/3539597.3570404","article-title":"S2GAE: self-supervised graph autoencoders are generalizable learners with graph masking","author":"Q Tan","year":"2023","journal-title":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining"},{"issue":"3","key":"pcbi.1012881.ref031","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1038\/s41593-020-00787-0","article-title":"Transcriptome-scale spatial gene expression in the human dorsolateral prefrontal cortex","volume":"24","author":"KR Maynard","year":"2021","journal-title":"Nat Neurosci"},{"issue":"26","key":"pcbi.1012881.ref032","doi-asserted-by":"crossref","first-page":"eabb3446","DOI":"10.1126\/sciadv.abb3446","article-title":"Molecular atlas of the adult mouse brain","volume":"6","author":"C Ortiz","year":"2020","journal-title":"Sci Adv"},{"issue":"20","key":"pcbi.1012881.ref033","doi-asserted-by":"crossref","first-page":"5970","DOI":"10.1158\/0008-5472.CAN-18-0747","article-title":"Spatially resolved transcriptomics enables dissection of genetic heterogeneity in stage III cutaneous malignant melanoma","volume":"78","author":"K Thrane","year":"2018","journal-title":"Cancer Res"},{"issue":"6400","key":"pcbi.1012881.ref034","doi-asserted-by":"crossref","first-page":"eaat5691","DOI":"10.1126\/science.aat5691","article-title":"Three-dimensional intact-tissue sequencing of single-cell transcriptional states","volume":"361","author":"X Wang","year":"2018","journal-title":"Science"},{"issue":"11","key":"pcbi.1012881.ref035","doi-asserted-by":"crossref","first-page":"932","DOI":"10.1038\/s41592-018-0175-z","article-title":"Spatial organization of the somatosensory cortex revealed by osmFISH","volume":"15","author":"S Codeluppi","year":"2018","journal-title":"Nat Methods"},{"issue":"6416","key":"pcbi.1012881.ref036","doi-asserted-by":"crossref","first-page":"eaau5324","DOI":"10.1126\/science.aau5324","article-title":"Molecular, spatial, and functional single-cell profiling of the hypothalamic preoptic region","volume":"362","author":"JR Moffitt","year":"2018","journal-title":"Science"},{"issue":"4","key":"pcbi.1012881.ref037","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","volume":"2","author":"H Abdi","year":"2010","journal-title":"Wiley Interdiscip Rev: Comput Statist"},{"key":"pcbi.1012881.ref038","first-page":"2259","article-title":"GiGaMAE: generalizable graph masked autoencoder via collaborative latent space reconstruction","author":"Y Shi","year":"2023","journal-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management"},{"key":"pcbi.1012881.ref039","first-page":"297","article-title":"Noise-contrastive estimation: a new estimation principle for unnormalized statistical models","author":"M Gutmann","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"issue":"5","key":"pcbi.1012881.ref040","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1109\/TPAMI.1987.4767965","article-title":"Least-squares fitting of two 3-d point sets","volume":"9","author":"KS Arun","year":"1987","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pcbi.1012881.ref041","first-page":"2023","article-title":"stGCL: A versatile cross-modality fusion method based on multi-modal graph contrastive learning for spatial transcriptomics","author":"N Yu","year":"2023","journal-title":"bioRxiv"},{"issue":"22","key":"pcbi.1012881.ref042","doi-asserted-by":"crossref","first-page":"e131","DOI":"10.1093\/nar\/gkac901","article-title":"DeepST: identifying spatial domains in spatial transcriptomics by deep learning","volume":"50","author":"C Xu","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1012881.ref043","article-title":"DiffusionST: a diffusion model-based framework for enhancing spatial transcriptomics data quality and identifying spatial domains","author":"Y Cui","year":"2024"},{"issue":"1","key":"pcbi.1012881.ref044","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1186\/s13059-023-03078-6","article-title":"SPIRAL: integrating and aligning spatially resolved transcriptomics data across different experiments, conditions, and technologies","volume":"24","author":"T Guo","year":"2023","journal-title":"Genome Biol"},{"issue":"336","key":"pcbi.1012881.ref045","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","article-title":"Objective criteria for the evaluation of clustering methods","volume":"66","author":"WM Rand","year":"1971","journal-title":"J Am Statist Assoc"},{"issue":"1","key":"pcbi.1012881.ref046","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s13059-019-1850-9","article-title":"A benchmark of batch-effect correction methods for single-cell RNA sequencing data","volume":"21","author":"HTN Tran","year":"2020","journal-title":"Genome Biol"},{"issue":"29","key":"pcbi.1012881.ref047","doi-asserted-by":"crossref","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: uniform manifold approximation and projection","volume":"3","author":"L McInnes","year":"2018","journal-title":"JOSS"},{"issue":"1","key":"pcbi.1012881.ref048","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1186\/s13059-019-1663-x","article-title":"PAGA: graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells","volume":"20","author":"FA Wolf","year":"2019","journal-title":"Genome Biol"},{"issue":"2","key":"pcbi.1012881.ref049","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1038\/s41592-019-0701-7","article-title":"Statistical analysis of spatial expression patterns for spatially resolved transcriptomic studies","volume":"17","author":"S Sun","year":"2020","journal-title":"Nat Methods"},{"issue":"5","key":"pcbi.1012881.ref050","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1038\/nmeth.4636","article-title":"SpatialDE: identification of spatially variable genes","volume":"15","author":"V Svensson","year":"2018","journal-title":"Nat Methods"},{"issue":"2","key":"pcbi.1012881.ref051","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/j.cell.2012.02.052","article-title":"Large-scale cellular-resolution gene profiling in human neocortex reveals species-specific molecular signatures","volume":"149","author":"H Zeng","year":"2012","journal-title":"Cell"},{"key":"pcbi.1012881.ref052","doi-asserted-by":"crossref","first-page":"D996","DOI":"10.1093\/nar\/gks1042","article-title":"Allen Brain Atlas: an integrated spatio-temporal portal for exploring the central nervous system","volume":"41","author":"SM Sunkin","year":"2013","journal-title":"Nucleic Acids Res."},{"issue":"6","key":"pcbi.1012881.ref053","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1080\/15384101.2022.2147141","article-title":"High expression of IGHG1 promotes breast cancer malignant development by activating the AKT pathway","volume":"22","author":"Y Jin","year":"2023","journal-title":"Cell Cycle"},{"issue":"W1","key":"pcbi.1012881.ref054","doi-asserted-by":"crossref","first-page":"W191","DOI":"10.1093\/nar\/gkz369","article-title":"g:Profiler: a web server for functional enrichment analysis and conversions of gene lists (2019 update)","volume":"47","author":"U Raudvere","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1012881.ref055","doi-asserted-by":"crossref","first-page":"D835","DOI":"10.1093\/nar\/gkt1155","article-title":"EMAGE mouse embryo spatial gene expression database: 2014 update","volume":"42","author":"L Richardson","year":"2014","journal-title":"Nucleic Acids Res"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T20:04:37Z","timestamp":1743710677000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012881"}},"subtitle":[],"editor":[{"given":"Hatice Ulku","family":"Osmanbeyoglu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,3]]},"references-count":55,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012881","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,3]]}}}