{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:52:58Z","timestamp":1775746378880,"version":"3.50.1"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271173"],"award-info":[{"award-number":["62271173"]}],"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":["12301623"],"award-info":[{"award-number":["12301623"]}],"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":["62172122"],"award-info":[{"award-number":["62172122"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017366","name":"Key Research and Development Program of Heilongjiang","doi-asserted-by":"publisher","award":["2022ZX01A19"],"award-info":[{"award-number":["2022ZX01A19"]}],"id":[{"id":"10.13039\/100017366","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["JQ2023A003"],"award-info":[{"award-number":["JQ2023A003"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["LH2024A003"],"award-info":[{"award-number":["LH2024A003"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20233473"],"award-info":[{"award-number":["GZC20233473"]}]},{"name":"Heilongjiang Postdoctoral Foundation","award":["LBH-Z23020"],"award-info":[{"award-number":["LBH-Z23020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Multi-omics analysis of individual cells offers remarkable opportunities for exploring the dynamics and relationships of gene regulatory states across large atlas data. However, the current integration algorithms have limited performance, largely due to ignoring the impact of correlation features within the dataset on the discrepancies between omics.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this study, we propose scGT, a model based on Graph Transformer for single-cell RNA-seq and ATAC-seq data, which leverages the robust graph structures strengthened by correlation features present in each raw dataset to harmonize representations of multi-omics data, enabling the integration of multi-omics and effective label transfer. We compare scGT with other state-of-the-art methods on paired and unpaired datasets. The results show that scGT accomplishes more accurate label transfer and is capable of integrating datasets with millions of cells. Meanwhile, scGT achieves better performance for preserving biological variation during integration.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code and data used in this article can be found at https:\/\/github.com\/Jinsl-lab\/scGT.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf357","type":"journal-article","created":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T05:04:02Z","timestamp":1751173442000},"source":"Crossref","is-referenced-by-count":2,"title":["scGT:integration algorithm for single-cell RNA-seq and ATAC-seq based on graph transformer"],"prefix":"10.1093","volume":"41","author":[{"given":"Yunjing","family":"Qi","sequence":"first","affiliation":[{"name":"School of Mathematics, Harbin Institute of Technology , Harbin 150000,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9200-5161","authenticated-orcid":false,"given":"Yulong","family":"Kan","sequence":"additional","affiliation":[{"name":"School of Mathematics, Harbin Institute of Technology , Harbin 150000,","place":["China"]}]},{"given":"Jing","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Mathematics, Harbin Institute of Technology , Harbin 150000,","place":["China"]},{"name":"Zhengzhou Research Institute, Harbin Institute of Technology , Zhengzhou 450000,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2318-432X","authenticated-orcid":false,"given":"Shuilin","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Mathematics, Harbin Institute of Technology , Harbin 150000,","place":["China"]},{"name":"Zhengzhou Research Institute, Harbin Institute of Technology , Zhengzhou 450000,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"2025070713463975700_btaf357-B1","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.coisb.2017.07.004","article-title":"Single cells make big data: new challenges and opportunities in transcriptomics","volume":"4","author":"Angerer","year":"2017","journal-title":"Curr Opin Syst Biol"},{"key":"2025070713463975700_btaf357-B2","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1038\/s41587-021-00895-7","article-title":"Computational principles and challenges in single-cell data integration","volume":"39","author":"Argelaguet","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2025070713463975700_btaf357-B3","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1186\/s13059-020-02015-1","article-title":"MOFA+: a statistical framework for comprehensive integration of multi-modal single-cell data","volume":"21","author":"Argelaguet","year":"2020","journal-title":"Genome Biol"},{"key":"2025070713463975700_btaf357-B4","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/s41592-019-0466-z","article-title":"Joint analysis of heterogeneous single-cell RNA-seq dataset collections","volume":"16","author":"Barkas","year":"2019","journal-title":"Nat Methods"},{"key":"2025070713463975700_btaf357-B5","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1038\/nature05915","article-title":"The complex language of chromatin regulation during transcription","volume":"447","author":"Berger","year":"2007","journal-title":"Nature"},{"key":"2025070713463975700_btaf357-B6","doi-asserted-by":"crossref","first-page":"eaba7721","DOI":"10.1126\/science.aba7721","article-title":"A human cell atlas of fetal gene expression","volume":"370","author":"Cao","year":"2020","journal-title":"Science"},{"key":"2025070713463975700_btaf357-B7","doi-asserted-by":"crossref","first-page":"1380","DOI":"10.1126\/science.aau0730","article-title":"Joint profiling of chromatin accessibility and gene expression in thousands of single cells","volume":"361","author":"Cao","year":"2018","journal-title":"Science"},{"key":"2025070713463975700_btaf357-B8","doi-asserted-by":"crossref","first-page":"1458","DOI":"10.1038\/s41587-022-01284-4","article-title":"Multi-omics single-cell data integration and regulatory inference with graph-linked embedding","volume":"40","author":"Cao","year":"2022","journal-title":"Nat. Biotechnol"},{"key":"2025070713463975700_btaf357-B9","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":"Chen","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2025070713463975700_btaf357-B10","doi-asserted-by":"crossref","first-page":"2441","DOI":"10.1093\/bioinformatics\/bty148","article-title":"Network-based integration of multi-omics data for prioritizing cancer genes","volume":"34","author":"Dimitrakopoulos","year":"2018","journal-title":"Bioinformatics"},{"key":"2025070713463975700_btaf357-B11","doi-asserted-by":"crossref","first-page":"eaba7612","DOI":"10.1126\/science.aba7612","article-title":"A human cell atlas of fetal chromatin accessibility","volume":"370","author":"Domcke","year":"2020","journal-title":"Science"},{"key":"2025070713463975700_btaf357-B12","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1038\/nbt.4091","article-title":"Batch effects in single-cell RNA-sequencing data are corrected by matching mutual nearest neighbors","volume":"36","author":"Haghverdi","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2025070713463975700_btaf357-B13","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1037\/h0071325","article-title":"Analysis of a complex of statistical variables into principal components","volume":"24","author":"Hotelling","year":"1933","journal-title":"J. Educ. Psychol"},{"key":"2025070713463975700_btaf357-B14","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s13059-020-1932-8","article-title":"scAI: an unsupervised approach for the integrative analysis of parallel single-cell transcriptomic and epigenomic profiles","volume":"21","author":"Jin","year":"2020","journal-title":"Genome Biol"},{"key":"2025070713463975700_btaf357-B15","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1093\/bfgp\/elx019","article-title":"A brief review of single-cell transcriptomic technologies","volume":"17","author":"Kalisky","year":"2018","journal-title":"Brief Funct Genomics"},{"key":"2025070713463975700_btaf357-B16","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1038\/s41576-018-0089-8","article-title":"Chromatin accessibility and the regulatory epigenome","volume":"20","author":"Klemm","year":"2019","journal-title":"Nat Rev Genet"},{"key":"2025070713463975700_btaf357-B17","author":"Krzysztof","year":"2021"},{"key":"2025070713463975700_btaf357-B18","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1038\/s41586-022-05060-x","article-title":"Spatial multi-omic map of human myocardial infarction","volume":"608","author":"Kuppe","year":"2022","journal-title":"Nature"},{"key":"2025070713463975700_btaf357-B19","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1186\/s13059-023-03073-x","article-title":"Benchmarking algorithms for joint integration of unpaired and paired single-cell RNA-seq and ATAC-seq data","volume":"24","author":"Lee","year":"2023","journal-title":"Genome Biol"},{"key":"2025070713463975700_btaf357-B20","doi-asserted-by":"crossref","first-page":"6045","DOI":"10.1038\/s41467-023-41795-5","article-title":"scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration","volume":"14","author":"Li","year":"2023","journal-title":"Nat Commun"},{"key":"2025070713463975700_btaf357-B21","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1038\/s41587-021-01161-6","article-title":"scJoint integrates atlas-scale single-cell RNA-seq and ATAC-seq data with transfer learning","volume":"40","author":"Lin","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2025070713463975700_btaf357-B22","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41592-021-01336-8","article-title":"Benchmarking atlas-level data integration in single-cell genomics","volume":"19","author":"Luecken","year":"2022","journal-title":"Nat Methods"},{"key":"2025070713463975700_btaf357-B23","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":"Ma","year":"2020","journal-title":"Trends Biotechnol"},{"key":"2025070713463975700_btaf357-B24","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1016\/j.cell.2020.09.056","article-title":"Chromatin potential identified by shared Single-Cell profiling of RNA and chromatin","volume":"183","author":"Ma","year":"2020","journal-title":"Cell"},{"key":"2025070713463975700_btaf357-B25","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1038\/s41587-021-00927-2","article-title":"Scalable, multimodal profiling of chromatin accessibility, gene expression and protein levels in single cells","volume":"39","author":"Mimitou","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2025070713463975700_btaf357-B26","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1038\/nmeth.2639","article-title":"Smart-seq2 for sensitive full-length transcriptome profiling in single cells","volume":"10","author":"Picelli","year":"2013","journal-title":"Nat Methods"},{"key":"2025070713463975700_btaf357-B27","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.cell.2015.09.004","article-title":"Molecular identity of human outer radial glia during cortical development","volume":"163","author":"Pollen","year":"2015","journal-title":"Cell"},{"key":"2025070713463975700_btaf357-B28","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1186\/s13059-015-0737-7","article-title":"Single-cell ATAC-seq: strength in numbers","volume":"16","author":"Pott","year":"2015","journal-title":"Genome Biol"},{"key":"2025070713463975700_btaf357-B29","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J Comput Appl Math"},{"key":"2025070713463975700_btaf357-B30","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1146\/annurev.immunol.22.012703.104702","article-title":"Central memory and effector memory T cell subsets: function, generation, and maintenance","volume":"22","author":"Sallusto","year":"2004","journal-title":"Annu Rev Immunol"},{"key":"2025070713463975700_btaf357-B31","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1038\/44385","article-title":"Two subsets of memory T lymphocytes with distinct homing potentials and effector functions","volume":"401","author":"Sallusto","year":"1999","journal-title":"Nature"},{"key":"2025070713463975700_btaf357-B32","doi-asserted-by":"crossref","first-page":"3826","DOI":"10.1038\/s41467-021-24172-y","article-title":"scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics","volume":"12","author":"Song","year":"2021","journal-title":"Nat Commun"},{"key":"2025070713463975700_btaf357-B33","doi-asserted-by":"crossref","first-page":"1888","DOI":"10.1016\/j.cell.2019.05.031","article-title":"Comprehensive integration of single-cell data","volume":"177","author":"Stuart","year":"2019","journal-title":"Cell"},{"key":"2025070713463975700_btaf357-B34","first-page":"baaa073","article-title":"A curated database reveals trends in single-cell transcriptomics","volume":"2020","author":"Svensson","year":"2020","journal-title":"Database J Biol Databases Curation"},{"key":"2025070713463975700_btaf357-B35","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1038\/s41586-018-0590-4","article-title":"Single-cell transcriptomics of 20 mouse organs creates a tabula muris","volume":"562","author":"Tabula Muris Consortium","year":"2018","journal-title":"Nature"},{"key":"2025070713463975700_btaf357-B36","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1038\/nmeth.3629","article-title":"Fixed single-cell transcriptomic characterization of human radial glial diversity","volume":"13","author":"Thomsen","year":"2016","journal-title":"Nat Methods"},{"key":"2025070713463975700_btaf357-B37","first-page":"27387","volume-title":"Advances in Neural Information Processing Systems","author":"Wu","year":"2022"},{"key":"2025070713463975700_btaf357-B38","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1038\/s42256-022-00534-z","article-title":"scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data","volume":"4","author":"Yang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025070713463975700_btaf357-B39","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s12264-021-00759-9","article-title":"Developmental origins of human cortical oligodendrocytes and astrocytes","volume":"38","author":"Yang","year":"2022","journal-title":"Neurosci Bull"},{"key":"2025070713463975700_btaf357-B40","doi-asserted-by":"crossref","first-page":"4374","DOI":"10.1109\/JBHI.2025.3540712","article-title":"Fast virtual stenting for thoracic endovascular aortic repair of aortic dissection using graph deep learning","volume":"29","author":"Zhang","year":"2025","journal-title":"IEEE J Biomed Health Inform"},{"key":"2025070713463975700_btaf357-B41","doi-asserted-by":"crossref","first-page":"14049","DOI":"10.1038\/ncomms14049","article-title":"Massively parallel digital transcriptional profiling of single cells","volume":"8","author":"Zheng","year":"2017","journal-title":"Nat Commun"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf357\/63568422\/btaf357.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/7\/btaf357\/63568422\/btaf357.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/7\/btaf357\/63568422\/btaf357.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T17:46:58Z","timestamp":1751910418000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf357\/8172517"}},"subtitle":[],"editor":[{"given":"Laura","family":"Cantini","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,6,24]]},"references-count":41,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf357","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,6,24]]},"article-number":"btaf357"}}