{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T04:16:35Z","timestamp":1778127395099,"version":"3.51.4"},"reference-count":55,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42374174"],"award-info":[{"award-number":["42374174"]}],"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":["42274172"],"award-info":[{"award-number":["42274172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Quant. Biol."],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Single\u2010cell multi\u2010omics sequencing technology provides a powerful tool for studying cellular heterogeneity. However, beyond the challenges of sparsity, heterogeneity, and dimensionality differences, a critical challenge in multi\u2010omics data integration lies in preserving the true regulatory relationships among molecular features. To address these limitations, we propose single\u2010cell multi\u2010omics graph neural networks (scMOG), a framework that leverages heterogeneous graphs to preserve regulatory relationships in single\u2010cell multi\u2010omics data. scMOG leverages encoders to extract low\u2010dimensional embeddings of both cells and features while reconstructing the input data using zero\u2010inflated negative binomial decoders, effectively handling high sparsity and noise. In addition, scMOG introduces a contrastive learning module and an omics alignment module to preserve differences in expression patterns across distinct omics while extracting consistent information. Experimental results on eight single\u2010cell multi\u2010omics datasets demonstrate that scMOG outperforms existing methods, producing embeddings that capture meaningful biological signals. scMOG provides an effective solution for integrating single\u2010cell multi\u2010omics data, offering a scalable framework that preserves regulatory signals.<\/jats:p>","DOI":"10.1002\/qub2.70041","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T03:45:07Z","timestamp":1778125507000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["scMOG: A graph neural network method for regulatory relationship\u2010preserving single\u2010cell multi\u2010omics integration"],"prefix":"10.1002","volume":"14","author":[{"given":"Yucheng","family":"Lu","sequence":"first","affiliation":[{"name":"School of Mathematics and Physics China University of Geosciences  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Physics China University of Geosciences  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mathematics and Physics China University of Geosciences  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"issue":"1","key":"e_1_2_10_2_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-024-54569-4","article-title":"Human single cell RNA\u2010sequencing reveals a targetable CD8+ exhausted T cell population that maintains mouse low\u2010grade glioma growth","volume":"15","author":"Barakat R","year":"2024","journal-title":"Nat Commun"},{"issue":"1","key":"e_1_2_10_3_1","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-024-54202-4","article-title":"Dyna\u2010vivo\u2010seq unveils cellular RNA dynamics during acute kidney injury via in vivo metabolic RNA labeling\u2010based scRNA\u2010seq","volume":"15","author":"Yin K","year":"2024","journal-title":"Nat Commun"},{"issue":"12","key":"e_1_2_10_4_1","doi-asserted-by":"crossref","first-page":"2512","DOI":"10.1038\/s41593-024-01768-3","article-title":"Single\u2010cell m6A profiling in the mouse brain uncovers cell type\u2010specific RNA methylomes and age\u2010dependent differential methylation","volume":"27","author":"Tegowski M","year":"2024","journal-title":"Nat Neurosci"},{"issue":"1","key":"e_1_2_10_5_1","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1186\/s40364-024-00643-4","article-title":"Single\u2010cell sequencing to multi\u2010omics: technologies and applications","volume":"12","author":"Wu X","year":"2024","journal-title":"Biomark Res"},{"issue":"1","key":"e_1_2_10_6_1","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1038\/s41467-018-08205-7","article-title":"Deconvolution of single\u2010cell multi\u2010omics layers reveals regulatory heterogeneity","volume":"10","author":"Liu L","year":"2019","journal-title":"Nat Commun"},{"issue":"10","key":"e_1_2_10_7_1","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/s41580-023-00615-w","article-title":"The technological landscape and applications of single\u2010cell multi\u2010omics","volume":"24","author":"Baysoy A","year":"2023","journal-title":"Nat Rev Mol Cell Biol"},{"issue":"1","key":"e_1_2_10_8_1","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1038\/s41467-018-07931-2","article-title":"Single\u2010cell RNA\u2010seq denoising using a deep count autoencoder","volume":"10","author":"Eraslan G","year":"2019","journal-title":"Nat Commun"},{"issue":"1","key":"e_1_2_10_9_1","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1186\/s13059-022-02649-3","article-title":"scINSIGHT for interpreting single\u2010cell gene expression from biologically heterogeneous data","volume":"23","author":"Qian K","year":"2022","journal-title":"Genome Biol"},{"issue":"9","key":"e_1_2_10_10_1","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad546","article-title":"scAce: an adaptive embedding and clustering method for single\u2010cell gene expression data","volume":"39","author":"He X","year":"2023","journal-title":"Bioinformatics"},{"issue":"2","key":"e_1_2_10_11_1","doi-asserted-by":"crossref","first-page":"e85","DOI":"10.1002\/qub2.85","article-title":"scSCC: a swapped contrastive learning\u2010based clustering method for single\u2010cell gene expression data","volume":"13","author":"Wang X","year":"2025","journal-title":"Quant Biol"},{"issue":"4","key":"e_1_2_10_12_1","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad133","article-title":"scMCs: a framework for single\u2010cell multi\u2010omics data integration and multiple clusterings","volume":"39","author":"Ren L","year":"2023","journal-title":"Bioinformatics"},{"issue":"3","key":"e_1_2_10_13_1","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.1109\/JBHI.2025.3595904","article-title":"MomicPred: a cell cycle prediction framework based on dual\u2010branch multi\u2010modal feature fusion for single\u2010cell multi\u2010omics data","volume":"30","author":"Shi Z","year":"2026","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"e_1_2_10_14_1","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1186\/s13059-024-03338-z","article-title":"scCross: a deep generative model for unifying single\u2010cell multi\u2010omics with seamless integration, cross\u2010modal generation, and in silico exploration","volume":"25","author":"Yang X","year":"2024","journal-title":"Genome Biol"},{"issue":"4","key":"e_1_2_10_15_1","doi-asserted-by":"crossref","DOI":"10.1093\/nargab\/lqae135","article-title":"scATAcat: cell\u2010type annotation for scATAC\u2010seq data","volume":"6","author":"Altay A","year":"2024","journal-title":"NAR Genom. Bioinform"},{"issue":"9","key":"e_1_2_10_16_1","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1038\/s41592-022-01595-z","article-title":"MIRA: joint regulatory modeling of multimodal expression and chromatin accessibility in single cells","volume":"19","author":"Lynch AW","year":"2022","journal-title":"Nat Methods"},{"issue":"6","key":"e_1_2_10_17_1","doi-asserted-by":"crossref","DOI":"10.15252\/msb.20178124","article-title":"Multi\u2010omics factor analysis\u2014a framework for unsupervised integration of multi\u2010omics data sets","volume":"14","author":"Argelaguet R","year":"2018","journal-title":"Mol Syst Biol"},{"issue":"30","key":"e_1_2_10_18_1","doi-asserted-by":"crossref","first-page":"7723","DOI":"10.1073\/pnas.1805681115","article-title":"Integrative analysis of single\u2010cell genomics data by coupled nonnegative matrix factorizations","volume":"115","author":"Duren Z","year":"2018","journal-title":"Proc Natl Acad Sci"},{"issue":"1","key":"e_1_2_10_19_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-017-1269-0","article-title":"MATCHER: manifold alignment reveals correspondence between single cell transcriptome and epigenome dynamics","volume":"18","author":"Welch JD","year":"2017","journal-title":"Genome Biol"},{"issue":"1","key":"e_1_2_10_20_1","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaf009","article-title":"scHiClassifier: a deep learning framework for cell type prediction by fusing multiple feature sets from single\u2010cell Hi\u2010C data","volume":"26","author":"Zhou X","year":"2024","journal-title":"Briefings Bioinf"},{"issue":"1","key":"e_1_2_10_21_1","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1038\/s42003-024-06626-3","article-title":"scHiCyclePred: a deep learning framework for predicting cell cycle phases from single\u2010cell Hi\u2010C data using multi\u2010scale interaction information","volume":"7","author":"Wu Y","year":"2024","journal-title":"Commun Biol"},{"issue":"3","key":"e_1_2_10_22_1","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaf289","article-title":"A novel deep learning framework with dynamic tokenization for identifying chromatin interactions along with motif importance investigation","volume":"26","author":"Li L","year":"2025","journal-title":"Briefings Bioinf"},{"key":"e_1_2_10_23_1","article-title":"Auto\u2010encoding variational bayes","author":"Kingma DP","year":"2013","journal-title":"arXiv"},{"issue":"1","key":"e_1_2_10_24_1","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1186\/s12859-024-05706-9","article-title":"Integration of scRNA\u2010seq data by disentangled representation learning with condition domain adaptation","volume":"25","author":"Liu R","year":"2024","journal-title":"BMC Bioinf"},{"issue":"3","key":"e_1_2_10_25_1","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1038\/s41592-020-01050-x","article-title":"Joint probabilistic modeling of single\u2010cell multi\u2010omic data with totalVI","volume":"18","author":"Gayoso A","year":"2021","journal-title":"Nat Methods"},{"issue":"1","key":"e_1_2_10_26_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-021-02556-z","article-title":"Cobolt: integrative analysis of multimodal single\u2010cell sequencing data","volume":"22","author":"Gong B","year":"2021","journal-title":"Genome Biol"},{"issue":"22","key":"e_1_2_10_27_1","doi-asserted-by":"crossref","first-page":"4091","DOI":"10.1093\/bioinformatics\/btab403","article-title":"Deep cross\u2010omics cycle attention model for joint analysis of single\u2010cell multi\u2010omics data","volume":"37","author":"Zuo C","year":"2021","journal-title":"Bioinformatics"},{"issue":"12","key":"e_1_2_10_28_1","doi-asserted-by":"crossref","first-page":"6121","DOI":"10.1109\/JBHI.2023.3317272","article-title":"scMIC: a deep multi\u2010level information fusion framework for clustering single\u2010cell multi\u2010omics data","volume":"27","author":"Zhan Y","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"issue":"2","key":"e_1_2_10_29_1","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae102","article-title":"Effective multi\u2010modal clustering method via skip aggregation network for parallel scRNA\u2010seq and scATAC\u2010seq data","volume":"25","author":"Hu D","year":"2024","journal-title":"Briefings Bioinf"},{"issue":"10","key":"e_1_2_10_30_1","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae599","article-title":"scDRMAE: integrating masked autoencoder with residual attention networks to leverage omics feature dependencies for accurate cell clustering","volume":"40","author":"Zhang T","year":"2024","journal-title":"Bioinformatics"},{"key":"e_1_2_10_31_1","first-page":"770","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"He K","year":"2016"},{"issue":"6","key":"e_1_2_10_32_1","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1038\/s41592-023-01899-8","article-title":"SIMBA: single\u2010cell embedding along with features","volume":"21","author":"Chen H","year":"2024","journal-title":"Nat Methods"},{"issue":"1","key":"e_1_2_10_33_1","doi-asserted-by":"crossref","DOI":"10.1093\/nargab\/lqae004","article-title":"scBiG for representation learning of single\u2010cell gene expression data based on bipartite graph embedding","volume":"6","author":"Li T","year":"2024","journal-title":"NAR Genom Bioinform"},{"issue":"6","key":"e_1_2_10_34_1","doi-asserted-by":"crossref","first-page":"bbae538","DOI":"10.1093\/bib\/bbae538","article-title":"Structure\u2010preserved integration of scRNA\u2010seq data using heterogeneous graph neural network","volume":"25","author":"Zhang X","year":"2024","journal-title":"Briefings Bioinf"},{"issue":"5","key":"e_1_2_10_35_1","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1016\/j.jmva.2006.11.013","article-title":"Comparing clusterings\u2014An information based distance","volume":"98","author":"Meil\u0103 M","year":"2007","journal-title":"J Multivariate Anal"},{"issue":"3","key":"e_1_2_10_36_1","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/j.media.2005.03.009","article-title":"Normalized mutual information based registration using k\u2010means clustering and shading correction","volume":"10","author":"Knops ZF","year":"2006","journal-title":"Med Image Anal"},{"issue":"12","key":"e_1_2_10_37_1","doi-asserted-by":"crossref","first-page":"1624","DOI":"10.1109\/TKDE.2005.198","article-title":"Document clustering using locality preserving indexing","volume":"17","author":"Cai D","year":"2005","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"e_1_2_10_38_1","article-title":"UMAP: uniform manifold approximation and projection for dimension reduction","author":"McInnes L","year":"2018","journal-title":"arXiv"},{"key":"e_1_2_10_39_1","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1145\/3397271.3401063","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"He X","year":"2020"},{"issue":"5","key":"e_1_2_10_40_1","doi-asserted-by":"crossref","first-page":"4532","DOI":"10.1109\/JIOT.2019.2956827","article-title":"Context\u2010aware QoS prediction with neural collaborative filtering for internet\u2010of\u2010things services","volume":"7","author":"Gao H","year":"2019","journal-title":"IEEE Internet Things J"},{"key":"e_1_2_10_41_1","first-page":"1","article-title":"SCANPY: large\u2010scale single\u2010cell gene expression data analysis","volume":"19","author":"Wolf FA","year":"2018","journal-title":"Genome Biol"},{"issue":"1","key":"e_1_2_10_42_1","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-022-35031-9","article-title":"Clustering of single\u2010cell multi\u2010omics data with a multimodal deep learning method","volume":"13","author":"Lin X","year":"2022","journal-title":"Nat Commun"},{"issue":"1","key":"e_1_2_10_43_1","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-021-99003-7","article-title":"A topology\u2010preserving dimensionality reduction method for single\u2010cell RNA\u2010seq data using graph autoencoder","volume":"11","author":"Luo Z","year":"2021","journal-title":"Sci Rep"},{"issue":"1","key":"e_1_2_10_44_1","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1038\/s41467-025-55900-3","article-title":"Genetic coupling of enhancer activity and connectivity in gene expression control","volume":"16","author":"Ray\u2010Jones H","year":"2025","journal-title":"Nat Commun"},{"issue":"1","key":"e_1_2_10_45_1","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13072-020-0327-0","article-title":"Integrative prediction of gene expression with chromatin accessibility and conformation data","volume":"13","author":"Schmidt F","year":"2020","journal-title":"Epigenetics Chromatin"},{"issue":"3","key":"e_1_2_10_46_1","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1038\/s41592-024-02179-9","article-title":"Tapioca: a platform for predicting de novo protein\u2013protein interactions in dynamic contexts","volume":"21","author":"Reed TJ","year":"2024","journal-title":"Nat Methods"},{"issue":"1","key":"e_1_2_10_47_1","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-023-36736-1","article-title":"Hierarchical graph learning for protein\u2013protein interaction","volume":"14","author":"Gao Z","year":"2023","journal-title":"Nat Commun"},{"issue":"1","key":"e_1_2_10_48_1","doi-asserted-by":"crossref","first-page":"D721","DOI":"10.1093\/nar\/gky900","article-title":"CellMarker: a manually curated resource of cell markers in human and mouse","volume":"47","author":"Zhang X","year":"2019","journal-title":"Nucleic Acids Res"},{"issue":"6237","key":"e_1_2_10_49_1","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1126\/science.aab1601","article-title":"Multiplex single\u2010cell profiling of chromatin accessibility by combinatorial cellular indexing","volume":"348","author":"Cusanovich DA","year":"2015","journal-title":"Science"},{"key":"e_1_2_10_50_1","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1145\/312624.312649","volume-title":"Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Hofmann T","year":"1999"},{"key":"e_1_2_10_51_1","first-page":"2825","article-title":"Scikit\u2010learn: machine learning in python","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"J Mach Learn Res"},{"key":"e_1_2_10_52_1","article-title":"Adam: a method for stochastic optimization","author":"Kingma DP","year":"2014","journal-title":"arXiv"},{"issue":"10","key":"e_1_2_10_53_1","doi-asserted-by":"crossref","DOI":"10.1088\/1742-5468\/2008\/10\/P10008","article-title":"Fast unfolding of communities in large networks","volume":"2008","author":"Blondel VD","year":"2008","journal-title":"J. Stat Mech"},{"issue":"4","key":"e_1_2_10_54_1","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1016\/j.cell.2020.09.056","article-title":"Chromatin potential identified by shared single\u2010cell profiling of RNA and chromatin","volume":"183","author":"Ma S","year":"2020","journal-title":"Cell"},{"issue":"11","key":"e_1_2_10_55_1","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.1038\/s41592-024-02429-w","article-title":"Benchmarking algorithms for single\u2010cell multi\u2010omics prediction and integration","volume":"21","author":"Hu Y","year":"2024","journal-title":"Nat Methods"},{"issue":"12","key":"e_1_2_10_56_1","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1038\/s41587-019-0290-0","article-title":"High\u2010throughput sequencing of the transcriptome and chromatin accessibility in the same cell","volume":"37","author":"Chen S","year":"2019","journal-title":"Nat Biotechnol"}],"container-title":["Quantitative Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qub2.70041","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/qub2.70041","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qub2.70041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T03:45:15Z","timestamp":1778125515000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/qub2.70041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":55,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/qub2.70041"],"URL":"https:\/\/doi.org\/10.1002\/qub2.70041","archive":["Portico"],"relation":{},"ISSN":["2095-4689","2095-4697"],"issn-type":[{"value":"2095-4689","type":"print"},{"value":"2095-4697","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"2025-11-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70041"}}