{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:33:44Z","timestamp":1772138024281,"version":"3.50.1"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T00:00:00Z","timestamp":1738195200000},"content-version":"vor","delay-in-days":69,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0905400"],"award-info":[{"award-number":["2023YFF0905400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2341229"],"award-info":[{"award-number":["U2341229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Imaging-based spatial transcriptomics (iST), such as MERFISH, CosMx SMI, and Xenium, quantify gene expression level across cells in space, but more importantly, they directly reveal the subcellular distribution of RNA transcripts at the single-molecule resolution. The subcellular localization of RNA molecules plays a crucial role in the compartmentalization-dependent regulation of genes within individual cells. Understanding the intracellular spatial distribution of RNA for a particular cell type thus not only improves the characterization of cell identity but also is of paramount importance in elucidating unique subcellular regulatory mechanisms specific to the cell type. However, current cell type annotation approaches of iST primarily utilize gene expression information while neglecting the spatial distribution of RNAs within cells. In this work, we introduce a semi-supervised graph contrastive learning method called Focus, the first method, to the best of our knowledge, that explicitly models RNA\u2019s subcellular distribution and community to improve cell type annotation. Focus demonstrates significant improvements over state-of-the-art algorithms across a range of spatial transcriptomics platforms, achieving improvements up to 27.8% in terms of accuracy and 51.9% in terms of F1-score for cell type annotation. Furthermore, Focus enjoys the advantages of intricate cell type-specific subcellular spatial gene patterns and providing interpretable subcellular gene analysis, such as defining the gene importance score. Importantly, with the importance score, Focus identifies genes harboring strong relevance to cell type-specific pathways, indicating its potential in uncovering novel regulatory programs across numerous biological systems.<\/jats:p>","DOI":"10.1093\/bib\/bbaf020","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T23:20:02Z","timestamp":1736464802000},"source":"Crossref","is-referenced-by-count":2,"title":["Graph contrastive learning of subcellular-resolution spatial transcriptomics improves cell type annotation and reveals critical molecular pathways"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2147-3498","authenticated-orcid":false,"given":"Qiaolin","family":"Lu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University , Qianjin Street 2699, 130010 Changchun ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayuan","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Michigan State University , 220 Trowbridge Rd, East Lansing, MI 48824 ,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingxiao","family":"Li","sequence":"additional","affiliation":[{"name":"Department, Boston University , Commonwealth Ave, Boston, MA 02215 ,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University , Qianjin Street 2699, 130010 Changchun ,","place":["China"]},{"name":"International Center of Future Science, Jilin University , Qianjin Street 2699, 130010 Changchun ,","place":["China"]},{"name":"Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University , Qianjin Street 2699, 130010 Changchun ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,1,30]]},"reference":[{"key":"2025013015140707500_ref1","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/s41586-021-03634-9","article-title":"Exploring tissue architecture using spatial transcriptomics","volume":"596","author":"Rao","year":"2021","journal-title":"Nature"},{"key":"2025013015140707500_ref2","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1038\/s41587-022-01448-2","article-title":"The expanding vistas of spatial transcriptomics","volume":"41","author":"Tian","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2025013015140707500_ref3","doi-asserted-by":"publisher","first-page":"1794","DOI":"10.1038\/s41587-022-01483-z","article-title":"High-plex imaging of RNA and proteins at subcellular resolution in fixed tissue by spatial molecular imaging","volume":"40","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2025013015140707500_ref4","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1038\/s41586-021-03705-x","article-title":"Spatially resolved cell atlas of the mouse primary motor cortex by merfish","volume":"598","author":"Zhang","year":"2021","journal-title":"Nature"},{"key":"2025013015140707500_ref5","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1038\/s41586-019-1049-y","article-title":"Transcriptome-scale super-resolved imaging in tissues by RNA seqFISH+","volume":"568","author":"Eng","year":"2019","journal-title":"Nature"},{"key":"2025013015140707500_ref6","doi-asserted-by":"crossref","first-page":"eaax2656","DOI":"10.1126\/science.aax2656","article-title":"Expansion sequencing: spatially precise in situ transcriptomics in intact biological systems","volume":"371","author":"Alon","year":"2021","journal-title":"Science"},{"key":"2025013015140707500_ref7","doi-asserted-by":"publisher","first-page":"aaa6090","DOI":"10.1126\/science.aaa6090","article-title":"Spatially resolved, highly multiplexed RNA profiling in single cells","volume":"348","year":"2015","journal-title":"Science"},{"key":"2025013015140707500_ref8","doi-asserted-by":"publisher","first-page":"8353","DOI":"10.1038\/s41467-023-43458-x","article-title":"High resolution mapping of the tumor microenvironment using integrated single-cell, spatial and in situ analysis","volume":"14","year":"2023","journal-title":"Nat Commun"},{"key":"2025013015140707500_ref9","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.26599\/BDMA.2024.9020034","article-title":"Transformer-based single-cell language model: a survey","volume":"7","author":"Lan","year":"2024","journal-title":"Big Data Min Anal"},{"key":"2025013015140707500_ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641284","article-title":"Deep learning in single-cell analysis","volume-title":"ACM Transactions on Intelligent Systems and Technology","year":"2024"},{"key":"2025013015140707500_ref11","doi-asserted-by":"publisher","DOI":"10.1126\/science.abl5197","article-title":"Cross-tissue immune cell analysis reveals tissue-specific features in humans","volume":"376","year":"2022","journal-title":"Science"},{"key":"2025013015140707500_ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-35923-4","article-title":"Transformer for one stop interpretable cell type annotation","volume":"14","year":"2023","journal-title":"Nat Commun"},{"key":"2025013015140707500_ref13","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1093\/bioinformatics\/btz592","article-title":"ACTINN: automated identification of cell types in single cell RNA sequencing","volume":"36","author":"Ma","year":"2020","journal-title":"Bioinformatics"},{"key":"2025013015140707500_ref14","doi-asserted-by":"publisher","first-page":"e122","DOI":"10.1093\/nar\/gkab775","article-title":"scDeepSort: a pre-trained cell-type annotation method for single-cell transcriptomics using deep learning with a weighted graph neural network","volume":"49","author":"Shao","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2025013015140707500_ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04278-2","article-title":"Single-cell classification using graph convolutional networks","volume":"22","author":"Wang","year":"2021","journal-title":"BMC Bioinform"},{"key":"2025013015140707500_ref16","doi-asserted-by":"publisher","first-page":"7640","DOI":"10.1038\/s41467-022-35288-0","article-title":"Spatial-ID: a cell typing method for spatially resolved transcriptomics via transfer learning and spatial embedding","volume":"13","author":"Shen","year":"2022","journal-title":"Nat Commun"},{"key":"2025013015140707500_ref17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCBB.2024.3387911","article-title":"Deep imputation bi-stochastic graph regularized matrix factorization for clustering single-cell RNA-sequencing data","author":"Lan","year":"2024","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025013015140707500_ref18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ymeth.2023.11.019","article-title":"JLONMFSC: clustering scRNA-seq data based on joint learning of non-negative matrix factorization and subspace clustering","volume":"222","author":"Lan","year":"2024","journal-title":"Methods"},{"key":"2025013015140707500_ref19","doi-asserted-by":"crossref","first-page":"bbae072","DOI":"10.1093\/bib\/bbae072","article-title":"scDOT: enhancing single-cell RNA-seq data annotation and uncovering novel cell types through multi-reference integration","volume":"25","author":"Xiong","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025013015140707500_ref20","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"5th International Conference on Learning Representations 2017","author":"Kipf","year":"2016"},{"key":"2025013015140707500_ref21","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"2025013015140707500_ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-023-01657-3","article-title":"TACCO unifies annotation transfer and decomposition of cell identities for single-cell and spatial omics","volume":"41","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2025013015140707500_ref23","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning conference","author":"Chen","year":"2020"},{"key":"2025013015140707500_ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539213","article-title":"Graph neural networks for multimodal single-cell data integration","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","year":"2022"},{"key":"2025013015140707500_ref25","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1145\/1963405.1963487","article-title":"Efficient k-nearest neighbor graph construction for generic similarity measures","volume-title":"Proceedings of the 20th international conference on World wide web","author":"Dong","year":"2011"},{"key":"2025013015140707500_ref26","doi-asserted-by":"publisher","first-page":"100476","DOI":"10.1016\/j.crmeth.2023.100476","article-title":"Subcellular spatially resolved gene neighborhood networks in single cells","volume":"3","author":"Fang","year":"2023","journal-title":"Cell Rep Methods"},{"key":"2025013015140707500_ref27","doi-asserted-by":"publisher","DOI":"10.1109\/isda.2011.6121636","article-title":"Generalized Louvain method for community detection in large networks","volume-title":"2011 11th International Conference on Intelligent Systems Design and Applications","year":"2011"},{"key":"2025013015140707500_ref28","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025013015140707500_ref29","first-page":"12121","article-title":"Graph contrastive learning automated","volume-title":"International Conference on Machine Learning","author":"You","year":"2021"},{"key":"2025013015140707500_ref30","doi-asserted-by":"publisher","first-page":"11382","DOI":"10.1109\/TNNLS.2023.3260258","article-title":"Multiview subspace clustering via low-rank symmetric affinity graph","volume":"35","author":"Lan","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2025013015140707500_ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3698192","article-title":"Contrastive clustering learning for multi-behavior recommendation","volume":"43","author":"Lan","year":"2024","journal-title":"ACM Trans Inf Syst"},{"key":"2025013015140707500_ref32","first-page":"36839","article-title":"Boosting graph contrastive learning via graph contrastive saliency","volume-title":"International Conference on Machine Learning","author":"Chunyu","year":"2023"},{"key":"2025013015140707500_ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467186","article-title":"MoCL: data-driven molecular fingerprint via knowledge-aware contrastive learning from molecular graph","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","year":"2021"},{"key":"2025013015140707500_ref34","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025013015140707500_ref35","first-page":"2921","article-title":"Multi-view graph contrastive representation learning for drug-drug interaction prediction","volume":"2021","author":"Wang","year":"2021","journal-title":"Proc Web Conf"},{"key":"2025013015140707500_ref36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1012409","article-title":"MVST: Identifying spatial domains of spatial transcriptomes from multiple views using multi-view graph convolutional networks","volume":"20","year":"2024","journal-title":"PLoS Comput Biol"},{"key":"2025013015140707500_ref37","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"5th International Conference on Learning Representations 2017","author":"Jang","year":"2016"},{"key":"2025013015140707500_ref38","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0925-2312(91)90023-5","article-title":"Multilayer perceptrons for classification and regression","volume":"2","author":"Murtagh","year":"1991","journal-title":"Neurocomputing"},{"key":"2025013015140707500_ref39","article-title":"Graph Feature Networks","author":"Chen","year":"2019"},{"key":"2025013015140707500_ref40","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume":"33","author":"Tian","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025013015140707500_ref41","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1073\/pnas.1310653110","article-title":"Differentiated kidney epithelial cells repair injured proximal tubule","volume":"111","author":"Kusaba","year":"2014","journal-title":"Proc Natl Acad Sci"},{"key":"2025013015140707500_ref42","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1002\/path.4125","article-title":"Proximal tubular cells contain a phenotypically distinct, scattered cell population involved in tubular regeneration","volume":"229","author":"Smeets","year":"2013","journal-title":"J Pathol"},{"key":"2025013015140707500_ref43","doi-asserted-by":"crossref","first-page":"btac757","DOI":"10.1093\/bioinformatics\/btac757","article-title":"GSEApy: a comprehensive package for performing gene set enrichment analysis in python","volume":"39","author":"Fang","year":"2023","journal-title":"Bioinformatics"},{"key":"2025013015140707500_ref44","doi-asserted-by":"publisher","first-page":"D353","DOI":"10.1093\/nar\/gkw1092","article-title":"KEGG: new perspectives on genomes, pathways, diseases and drugs","volume":"45","author":"Kanehisa","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2025013015140707500_ref45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-021-02264-8","article-title":"Genewalk identifies relevant gene functions for a biological context using network representation learning","volume":"22","author":"Ietswaart","year":"2021","journal-title":"Genome Biol"},{"key":"2025013015140707500_ref46","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1038\/s41596-018-0103-9","article-title":"Pathway enrichment analysis and visualization of omics data using g:Profiler, GSEA, Cytoscape and EnrichmentMap","volume":"14","author":"Reimand","year":"2019","journal-title":"Nat Protoc"},{"key":"2025013015140707500_ref47","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1111\/pace.13310","article-title":"Dofetilide for suppression of atrial fibrillation in hypertrophic cardiomyopathy: a case series and literature review","volume":"41","author":"Moore","year":"2018","journal-title":"Pacing Clin Electrophysiol"},{"key":"2025013015140707500_ref48","first-page":"147","article-title":"Primary lung cancer associated with dilated phase of hypertrophic cardiomyopathy; report of a case","volume":"70","author":"Sakai","year":"2017","journal-title":"Kyobu geka"},{"key":"2025013015140707500_ref49","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1111\/j.1399-3038.2011.01236.x","article-title":"Modern management of primary b-cell immunodeficiencies","volume":"22","author":"Hoernes","year":"2011","journal-title":"Pediatr Allergy Immunol"},{"key":"2025013015140707500_ref50","doi-asserted-by":"publisher","first-page":"2210","DOI":"10.1111\/cas.14900","article-title":"MZT2A promotes nsclc viability and invasion by increasing AKT phosphorylation via the MOZART2 domain","volume":"112","author":"Wang","year":"2021","journal-title":"Cancer Sci"},{"key":"2025013015140707500_ref51","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.cca.2017.11.010","article-title":"A review of S100 protein family in lung cancer","volume":"476","author":"Wang","year":"2018","journal-title":"Clin Chim Acta"},{"key":"2025013015140707500_ref52","first-page":"9815806","article-title":"Prognostic roles of mRNA expression of S100 in non-small-cell lung cancer","volume":"2018","author":"Liu","year":"2018","journal-title":"Biomed Res Int"},{"key":"2025013015140707500_ref53","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1038\/sj.onc.1206845","article-title":"Dual-specificity phosphatase 5 (DUSP5) as a direct transcriptional target of tumor suppressor P53","volume":"22","author":"Ueda","year":"2003","journal-title":"Oncogene"},{"key":"2025013015140707500_ref54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0184861","article-title":"DUSP5 and DUSP6, two ERK specific phosphatases, are markers of a higher MAPK signaling activation in BRAF mutated thyroid cancers","volume":"12","year":"2017","journal-title":"PLoS One"},{"key":"2025013015140707500_ref55","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14235739","article-title":"NDRG1 in Cancer: A Suppressor, Promoter, or Both?","volume":"14","year":"2022","journal-title":"Cancers"},{"key":"2025013015140707500_ref56","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1021\/bi00354a033","article-title":"Human type III collagen gene expression is coordinately modulated with the type I collagen genes during fibroblast growth","volume":"25","author":"Miskulin","year":"1986","journal-title":"Biochemistry"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/1\/bbaf020\/61700774\/bbaf020.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/1\/bbaf020\/61700774\/bbaf020.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T10:14:28Z","timestamp":1738232068000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf020\/7990577"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,11,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf020","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.03.08.584192","asserted-by":"object"}]},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,11,22]]},"article-number":"bbaf020"}}