{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T19:05:37Z","timestamp":1789499137602,"version":"build-2803163510"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014773","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000}}],"reference-count":59,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation Project","award":["No.62202162"],"award-info":[{"award-number":["No.62202162"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Paired single-cell multi-omics technologies provide direct within-cell correspondence across molecular layers and offer a powerful route to dissecting cellular heterogeneity and regulatory relationships. However, effective integration requires more than modality mixing: a useful model must accurately align paired cells while preserving modality-specific topological structure and biologically meaningful variation. Existing methods often struggle with topology mismatch across modalities, underuse cross-modal complementarity within paired cells, or improve alignment at the cost of biological fidelity. To address these challenges, we present scGSI, a graph-guided self-supervised framework for paired single-cell multi-omics integration. scGSI combines heterogeneous graph encoders to preserve modality-specific neighborhood structure, a pull-in projection module to stabilize pre-alignment, and a cross-fusion mechanism with contrastive refinement to exploit complementary signals between paired modalities. Across five paired single-cell multi-omics datasets collected from four platforms, scGSI improves paired cell-state alignment while maintaining a favorable balance between modality mixing and biological variation preservation. The learned embeddings also better support downstream analyses, including cell-type discrimination and developmental trajectory inference, showing that accurate alignment need not erase biologically meaningful structure.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014773","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:58:05Z","timestamp":1788890285000},"page":"e1014773","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["scGSI: Graph-guided self-supervised integration of paired single-cell multi-omics"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4797-8837","authenticated-orcid":true,"given":"Xiang","family":"Chen","sequence":"first","affiliation":[{"name":"Hunan University of Science and Technology","place":["Xiangtan, Hunan, China"],"department":["School of Computer Science and Engineering"]},{"name":"Hunan University of Science and Technology","place":["Xiangtan, Hunan, China"],"department":["Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8421-0965","authenticated-orcid":true,"given":"Zihan","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan University of Science and Technology","place":["Xiangtan, Hunan, China"],"department":["School of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Hunan University of Science and Technology","place":["Xiangtan, Hunan, China"],"department":["School of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyi","family":"Xie","sequence":"additional","affiliation":[{"name":"Hunan University of Science and Technology","place":["Xiangtan, Hunan, China"],"department":["School of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlu","family":"Guo","sequence":"additional","affiliation":[{"name":"Hunan University of Science and Technology","place":["Xiangtan, Hunan, China"],"department":["School of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"pcbi.1014773.ref001","doi-asserted-by":"crossref","first-page":"14049","DOI":"10.1038\/ncomms14049","article-title":"Massively parallel digital transcriptional profiling of single cells","volume":"8","author":"GXY Zheng","year":"2017","journal-title":"Nat Commun"},{"issue":"9","key":"pcbi.1014773.ref002","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1038\/nmeth.4380","article-title":"Simultaneous epitope and transcriptome measurement in single cells","volume":"14","author":"M Stoeckius","year":"2017","journal-title":"Nat Methods"},{"key":"pcbi.1014773.ref003","article-title":"scCMA: A contrastive masked autoencoder framework for robust representation learning of scRNA-seq data","author":"X Chen","year":"2026","journal-title":"Interdiscip Sci Comput Life Sci"},{"issue":"4","key":"pcbi.1014773.ref004","article-title":"Chromatin potential identified by shared single-cell profiling of RNA and chromatin","volume":"183","author":"S Ma","year":"2020","journal-title":"Cell"},{"issue":"13","key":"pcbi.1014773.ref005","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Y Hao","year":"2021","journal-title":"Cell"},{"key":"pcbi.1014773.ref006","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baaa073","article-title":"A curated database reveals trends in single-cell transcriptomics","volume":"2020","author":"V Svensson","year":"2020","journal-title":"Database (Oxford)"},{"issue":"12","key":"pcbi.1014773.ref007","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1038\/s41587-019-0290-0","article-title":"High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell","volume":"37","author":"S Chen","year":"2019","journal-title":"Nat Biotechnol"},{"issue":"11","key":"pcbi.1014773.ref008","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.1014773.ref009","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":"6","key":"pcbi.1014773.ref010","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":"4","key":"pcbi.1014773.ref011","article-title":"SpaMask: dual masking graph autoencoder with contrastive learning for spatial transcriptomics","volume":"21","author":"W Min","year":"2025","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"pcbi.1014773.ref012","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1038\/s42003-025-08810-5","article-title":"SpaCross deciphers spatial structures and corrects batch effects in multi-slice spatially resolved transcriptomics","volume":"8","author":"D Fang","year":"2025","journal-title":"Commun Biol"},{"issue":"1","key":"pcbi.1014773.ref013","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s13059-021-02595-6","article-title":"A deep generative model for multi-view profiling of single-cell RNA-seq and ATAC-seq data","volume":"23","author":"G Li","year":"2022","journal-title":"Genome Biol"},{"issue":"10","key":"pcbi.1014773.ref014","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/s41580-023-00615-w","article-title":"The technological landscape and applications of single-cell multi-omics","volume":"24","author":"A Baysoy","year":"2023","journal-title":"Nat Rev Mol Cell Biol"},{"issue":"7561","key":"pcbi.1014773.ref015","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1038\/nature14590","article-title":"Single-cell chromatin accessibility reveals principles of regulatory variation","volume":"523","author":"JD Buenrostro","year":"2015","journal-title":"Nature"},{"issue":"4","key":"pcbi.1014773.ref016","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2018.07.010","article-title":"Deep profiling of mouse splenic architecture with CODEX multiplexed imaging","volume":"174","author":"Y Goltsev","year":"2018","journal-title":"Cell"},{"issue":"11","key":"pcbi.1014773.ref017","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1038\/s41581-021-00463-x","article-title":"Multi-omics integration in the age of million single-cell data","volume":"17","author":"Z Miao","year":"2021","journal-title":"Nat Rev Nephrol"},{"issue":"1","key":"pcbi.1014773.ref018","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41467-019-09982-5","article-title":"CUT&Tag for efficient epigenomic profiling of small samples and single cells","volume":"10","author":"HS Kaya-Okur","year":"2019","journal-title":"Nat Commun"},{"issue":"7","key":"pcbi.1014773.ref019","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2019.05.031","article-title":"Comprehensive integration of single-cell data","volume":"177","author":"T Stuart","year":"2019","journal-title":"Cell"},{"key":"pcbi.1014773.ref020","article-title":"Unsupervised topological alignment for single-cell multi-omics integration","volume":"36","author":"K Cao","year":"2020","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1014773.ref021","doi-asserted-by":"crossref","DOI":"10.1093\/bioadv\/vbad171","article-title":"scTopoGAN: unsupervised manifold alignment of single-cell data","volume":"3","author":"A Singh","year":"2023","journal-title":"Bioinform Adv"},{"key":"pcbi.1014773.ref022","unstructured":"Chen D, Fan B, Oliver C, Borgwardt K. Unsupervised manifold alignment with joint multidimensional scaling. The Eleventh International Conference on Learning Representations; 2023. Available from: https:\/\/openreview.net\/forum?id=lUpjsrKItz4"},{"issue":"1","key":"pcbi.1014773.ref023","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1093\/bioinformatics\/btab594","article-title":"Manifold alignment for heterogeneous single-cell multi-omics data integration using Pamona","volume":"38","author":"K Cao","year":"2021","journal-title":"Bioinformatics"},{"key":"pcbi.1014773.ref024","doi-asserted-by":"crossref","unstructured":"Singh R, Demetci P, Bonora G, Ramani V, Lee C, Fang H, et al. Unsupervised manifold alignment for single-cell multi-omics data. Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics; 2020. p. 1\u201310. https:\/\/doi.org\/10.1145\/3388440.3412410","DOI":"10.1145\/3388440.3412410"},{"issue":"1","key":"pcbi.1014773.ref025","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1089\/cmb.2021.0446","article-title":"SCOT: single-cell multi-omics alignment with optimal transport","volume":"29","author":"P Demetci","year":"2022","journal-title":"J Comput Biol"},{"issue":"1","key":"pcbi.1014773.ref026","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s12859-022-05126-7","article-title":"Single-cell multi-omics integration for unpaired data by a siamese network with graph-based contrastive loss","volume":"24","author":"C Liu","year":"2023","journal-title":"BMC Bioinform"},{"issue":"1","key":"pcbi.1014773.ref027","doi-asserted-by":"crossref","first-page":"7711","DOI":"10.1038\/s41467-023-43019-2","article-title":"Paired single-cell multi-omics data integration with Mowgli","volume":"14","author":"G-J Huizing","year":"2023","journal-title":"Nat Commun"},{"issue":"7","key":"pcbi.1014773.ref028","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btaf392","article-title":"scMGCL: accurate and efficient integration representation of single-cell multi-omics data","volume":"41","author":"Z Cheng","year":"2025","journal-title":"Bioinformatics"},{"issue":"8","key":"pcbi.1014773.ref029","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1038\/s41592-023-01909-9","article-title":"MultiVI: deep generative model for the integration of multimodal data","volume":"20","author":"T Ashuach","year":"2023","journal-title":"Nat Methods"},{"issue":"11","key":"pcbi.1014773.ref030","doi-asserted-by":"crossref","first-page":"101211","DOI":"10.1016\/j.crmeth.2025.101211","article-title":"Single-cell multiomics data integration and generation with scPairing","volume":"5","author":"J Niu","year":"2025","journal-title":"Cell Rep Methods"},{"issue":"9","key":"pcbi.1014773.ref031","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1016\/j.tibtech.2020.02.013","article-title":"Integrative methods and practical challenges for single-cell multi-omics","volume":"38","author":"A Ma","year":"2020","journal-title":"Trends Biotechnol"},{"issue":"3","key":"pcbi.1014773.ref032","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1038\/s41588-021-00790-6","article-title":"ArchR is a scalable software package for integrative single-cell chromatin accessibility analysis","volume":"53","author":"JM Granja","year":"2021","journal-title":"Nat Genet"},{"issue":"5","key":"pcbi.1014773.ref033","doi-asserted-by":"crossref","DOI":"10.1016\/j.molcel.2018.06.044","article-title":"Cicero predicts cis-regulatory DNA interactions from single-cell chromatin accessibility data","volume":"71","author":"HA Pliner","year":"2018","journal-title":"Mol Cell"},{"issue":"1","key":"pcbi.1014773.ref034","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/s13059-020-02008-0","article-title":"scATAC-pro: a comprehensive workbench for single-cell chromatin accessibility sequencing data","volume":"21","author":"W Yu","year":"2020","journal-title":"Genome Biol"},{"issue":"11","key":"pcbi.1014773.ref035","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1038\/s41592-021-01282-5","article-title":"Single-cell chromatin state analysis with Signac","volume":"18","author":"T Stuart","year":"2021","journal-title":"Nat Methods"},{"issue":"5","key":"pcbi.1014773.ref036","article-title":"stAI: a deep learning-based model for missing gene imputation and cell-type annotation of spatial transcriptomics","volume":"53","author":"G Zou","year":"2025","journal-title":"Nucleic Acids Res"},{"issue":"5","key":"pcbi.1014773.ref037","doi-asserted-by":"crossref","DOI":"10.1016\/j.immuni.2017.10.021","article-title":"Granulocyte-monocyte progenitors and monocyte-dendritic cell progenitors independently produce functionally distinct monocytes","volume":"47","author":"A Y\u00e1\u00f1ez","year":"2017","journal-title":"Immunity"},{"issue":"2","key":"pcbi.1014773.ref038","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1038\/s41590-020-00836-7","article-title":"Gut CD4+ T cell phenotypes are a continuum molded by microbes, not by TH archetypes","volume":"22","author":"E Kiner","year":"2021","journal-title":"Nat Immunol"},{"issue":"1","key":"pcbi.1014773.ref039","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1111\/cei.12149","article-title":"Transitional B cell subsets in human bone marrow","volume":"174","author":"S Agrawal","year":"2013","journal-title":"Clin Exp Immunol"},{"issue":"6","key":"pcbi.1014773.ref040","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2018.03.074","article-title":"Integrated single-cell analysis maps the continuous regulatory landscape of human hematopoietic differentiation","volume":"173","author":"JD Buenrostro","year":"2018","journal-title":"Cell"},{"issue":"1","key":"pcbi.1014773.ref041","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1186\/s13287-023-03367-8","article-title":"Immortalized erythroid cells as a novel frontier for in vitro blood production: current approaches and potential clinical application","volume":"14","author":"CF Cervellera","year":"2023","journal-title":"Stem Cell Res Ther"},{"issue":"3","key":"pcbi.1014773.ref042","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1038\/nri3795","article-title":"The generation of antibody-secreting plasma cells","volume":"15","author":"SL Nutt","year":"2015","journal-title":"Nat Rev Immunol"},{"issue":"1","key":"pcbi.1014773.ref043","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1038\/s41467-021-21246-9","article-title":"Inference and analysis of cell-cell communication using CellChat","volume":"12","author":"S Jin","year":"2021","journal-title":"Nat Commun"},{"issue":"6335","key":"pcbi.1014773.ref044","article-title":"Single-cell RNA-seq reveals new types of human blood dendritic cells, monocytes, and progenitors","volume":"356","author":"A-C Villani","year":"2017","journal-title":"Science"},{"issue":"2","key":"pcbi.1014773.ref045","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1038\/s41576-020-00292-x","article-title":"Deciphering cell-cell interactions and communication from gene expression","volume":"22","author":"E Armingol","year":"2021","journal-title":"Nat Rev Genet"},{"issue":"1","key":"pcbi.1014773.ref046","doi-asserted-by":"crossref","first-page":"3224","DOI":"10.1038\/s41467-022-30755-0","article-title":"Comparison of methods and resources for cell-cell communication inference from single-cell RNA-Seq data","volume":"13","author":"D Dimitrov","year":"2022","journal-title":"Nat Commun"},{"issue":"8","key":"pcbi.1014773.ref047","article-title":"Multi-task learning from multimodal single-cell omics with Matilda","volume":"51","author":"C Liu","year":"2023","journal-title":"Nucleic Acids Res"},{"issue":"43","key":"pcbi.1014773.ref048","doi-asserted-by":"crossref","first-page":"15545","DOI":"10.1073\/pnas.0506580102","article-title":"Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles","volume":"102","author":"A Subramanian","year":"2005","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"3","key":"pcbi.1014773.ref049","first-page":"100141","article-title":"clusterProfiler 4.0: A universal enrichment tool for interpreting omics data","volume":"2","author":"T Wu","year":"2021","journal-title":"Innovation"},{"issue":"6","key":"pcbi.1014773.ref050","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1002\/eji.201646837","article-title":"CD69: from activation marker to metabolic gatekeeper","volume":"47","author":"D Cibri\u00e1n","year":"2017","journal-title":"Eur J Immunol"},{"issue":"8","key":"pcbi.1014773.ref051","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1038\/s41590-018-0156-5","article-title":"Second signals rescue B cells from activation-induced mitochondrial dysfunction and death","volume":"19","author":"M Akkaya","year":"2018","journal-title":"Nat Immunol"},{"issue":"3","key":"pcbi.1014773.ref052","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1038\/nri3802","article-title":"Memory B cells","volume":"15","author":"T Kurosaki","year":"2015","journal-title":"Nat Rev Immunol"},{"issue":"3","key":"pcbi.1014773.ref053","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1038\/nri3804","article-title":"Dynamics of B cells in germinal centres","volume":"15","author":"NS De Silva","year":"2015","journal-title":"Nat Rev Immunol"},{"key":"pcbi.1014773.ref054","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1146\/annurev-immunol-020711-075032","article-title":"Germinal centers","volume":"30","author":"GD Victora","year":"2012","journal-title":"Annu Rev Immunol"},{"issue":"9","key":"pcbi.1014773.ref055","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1038\/s41590-021-00996-0","article-title":"Selenium-GPX4 axis protects follicular helper T cells from ferroptosis","volume":"22","author":"Y Yao","year":"2021","journal-title":"Nat Immunol"},{"issue":"56","key":"pcbi.1014773.ref056","article-title":"Single-cell analysis of human B cell maturation predicts how antibody class switching shapes selection dynamics","volume":"6","author":"HW King","year":"2021","journal-title":"Sci Immunol"},{"issue":"1","key":"pcbi.1014773.ref057","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.1014773.ref058","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2016.09.027","article-title":"Molecular diversity of midbrain development in mouse, human, and stem cells","volume":"167","author":"G La Manno","year":"2016","journal-title":"Cell"},{"issue":"7638","key":"pcbi.1014773.ref059","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1038\/nature21029","article-title":"Neurotoxic reactive astrocytes are induced by activated microglia","volume":"541","author":"SA Liddelow","year":"2017","journal-title":"Nature"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014773","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T18:30:51Z","timestamp":1789497051000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014773"}},"subtitle":[],"editor":[{"given":"Lihua","family":"Zhang","sequence":"first","affiliation":[{"name":"Wuhan University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":59,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014773","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]}}}