{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T12:52:04Z","timestamp":1790427124677,"version":"4.1.0"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01HL169347"],"award-info":[{"award-number":["R01HL169347"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["K99\/R00HG011468"],"award-info":[{"award-number":["K99\/R00HG011468"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R35GM154865"],"award-info":[{"award-number":["R35GM154865"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Dimensionality reduction for single-cell RNA-sequencing (scRNA-seq) data involving multiple biological samples presents a significant analytical challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We introduce MUlti-Sample Trajectory-Assisted Reduction of Dimensions (MUSTARD), an innovative trajectory-guided dimensionality reduction method specifically designed for multi-sample, multi-condition scRNA-seq data. By integrating pseudotemporal information, MUSTARD provides a comprehensive unsupervised approach that simultaneously captures major gene expression variation patterns along pseudotime trajectories and across multiple samples, facilitating the discovery of biologically meaningful sample heterogeneity, endotypes, and associated gene markers and modules. In data-driven simulations, MUSTARD outperformed existing methods in distinguishing sample groups, achieving superior out-of-sample prediction accuracy. In two COVID-19 datasets and a tuberculosis dataset, MUSTARD identified components linked to symptom severity, batch effect, and other known biological variations, with notable overlap in immune response genes across the two independent COVID-19 datasets. These results underscore MUSTARD\u2019s flexibility and power in identifying biologically relevant sample heterogeneity across diverse datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The R package MUSTARD with a detailed user manual is publicly available at https:\/\/github.com\/haotian-zhuang\/MUSTARD and Zenodo (DOI: 10.5281\/zenodo.18293392). The source code to reproduce the results in this paper is available at https:\/\/github.com\/haotian-zhuang\/MUSTARD_Paper and Zenodo (DOI: 10.5281\/zenodo.18293392).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag192","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T11:26:47Z","timestamp":1776770807000},"source":"Crossref","is-referenced-by-count":1,"title":["Trajectory-guided dimensionality reduction for multi-sample single-cell RNA-seq data reveals biologically relevant sample-level heterogeneity"],"prefix":"10.1093","volume":"42","author":[{"given":"Haotian","family":"Zhuang","sequence":"first","affiliation":[{"name":"Duke University Department of Biostatistics & Bioinformatics, , Durham, NC, 27710 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9306-3796","authenticated-orcid":false,"given":"Xin","family":"Gai","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Vanderbilt University , Nashville, TN, 37232 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8721-5252","authenticated-orcid":false,"given":"Anru R","family":"Zhang","sequence":"additional","affiliation":[{"name":"Duke University Department of Biostatistics & Bioinformatics, , Durham, NC, 27710 ,","place":["United States"]},{"name":"Duke University Department of Computer Science, , Durham, NC, 27708 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenpin","family":"Hou","sequence":"additional","affiliation":[{"name":"Duke University Department of Biostatistics & Bioinformatics, , Durham, NC, 27710 ,","place":["United States"]},{"name":"Columbia University Department of Biostatistics, , New York, NY, 10032 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9457-4704","authenticated-orcid":false,"given":"Zhicheng","family":"Ji","sequence":"additional","affiliation":[{"name":"Duke University Department of Biostatistics & Bioinformatics, , Durham, NC, 27710 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2455-2622","authenticated-orcid":false,"given":"Pixu","family":"Shi","sequence":"additional","affiliation":[{"name":"Duke University Department of Biostatistics & Bioinformatics, , Durham, NC, 27710 ,","place":["United States"]},{"name":"Duke Microbiome Center, Duke University School of Medicine, Durham, NC 27710, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,4,22]]},"reference":[{"key":"2026052023572896800_btag192-B1","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":"2026052023572896800_btag192-B2","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1038\/nbt.4314","article-title":"Dimensionality reduction for visualizing single-cell data using umap","volume":"37","author":"Becht","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2026052023572896800_btag192-B3","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1038\/s41586-021-03752-4","article-title":"Transcriptional programs of neoantigen-specific til in anti-pd-1-treated lung cancers","volume":"596","author":"Caushi","year":"2021","journal-title":"Nature"},{"key":"2026052023572896800_btag192-B4","doi-asserted-by":"crossref","first-page":"6077","DOI":"10.1038\/s41467-020-19894-4","article-title":"Muscat detects subpopulation-specific state transitions from multi-sample multi-condition single-cell transcriptomics data","volume":"11","author":"Crowell","year":"2020","journal-title":"Nat Commun"},{"key":"2026052023572896800_btag192-B5","doi-asserted-by":"crossref","first-page":"eadg1487","DOI":"10.1126\/sciimmunol.adg1487","article-title":"Lung tumor\u2013infiltrating treg have divergent transcriptional profiles and function linked to checkpoint blockade response","volume":"8","author":"Dykema","year":"2023","journal-title":"Sci Immunol"},{"key":"2026052023572896800_btag192-B6","doi-asserted-by":"crossref","first-page":"e93161","DOI":"10.7554\/eLife.93161","article-title":"Multicellular factor analysis of single-cell data for a tissue-centric understanding of disease","volume":"12","author":"Flores","year":"2023","journal-title":"Elife"},{"key":"2026052023572896800_btag192-B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/21-AOS2061","article-title":"An optimal statistical and computational framework for generalized tensor estimation","volume":"50","author":"Han","year":"2022","journal-title":"Ann Statist"},{"key":"2026052023572896800_btag192-B8","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1080\/01621459.2022.2153689","article-title":"Guaranteed functional tensor singular value decomposition","volume":"119","author":"Han","year":"2024","journal-title":"J Am Stat Assoc"},{"key":"2026052023572896800_btag192-B9","doi-asserted-by":"crossref","first-page":"3573","DOI":"10.1016\/j.cell.2021.04.048","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Hao","year":"2021","journal-title":"Cell"},{"key":"2026052023572896800_btag192-B10","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1038\/s41576-023-00586-w","article-title":"Best practices for single-cell analysis across modalities","volume":"24","author":"Heumos","year":"2023","journal-title":"Nat Rev Genet"},{"key":"2026052023572896800_btag192-B11","doi-asserted-by":"crossref","first-page":"7286","DOI":"10.1038\/s41467-023-42841-y","article-title":"A statistical framework for differential pseudotime analysis with multiple single-cell rna-seq samples","volume":"14","author":"Hou","year":"2023","journal-title":"Nat Commun"},{"key":"2026052023572896800_btag192-B12","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1038\/s41592-018-0033-z","article-title":"Saver: gene expression recovery for single-cell rna sequencing","volume":"15","author":"Huang","year":"2018","journal-title":"Nat Methods"},{"key":"2026052023572896800_btag192-B13","doi-asserted-by":"crossref","first-page":"e117\u2013e117","DOI":"10.1093\/nar\/gkw430","article-title":"Tscan: pseudo-time reconstruction and evaluation in single-cell RNA-seq analysis","volume":"44","author":"Ji","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2026052023572896800_btag192-B14","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","article-title":"Fast, sensitive and accurate integration of single-cell data with harmony","volume":"16","author":"Korsunsky","year":"2019","journal-title":"Nat Methods"},{"key":"2026052023572896800_btag192-B15","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1186\/1471-2105-9-559","article-title":"Wgcna: an r package for weighted correlation network analysis","volume":"9","author":"Langfelder","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2026052023572896800_btag192-B16","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"Lopez","year":"2018","journal-title":"Nat Methods"},{"key":"2026052023572896800_btag192-B17","first-page":"eabc8511","article-title":"Deep immune profiling of covid-19 patients reveals distinct immunotypes with therapeutic implications","volume":"369","author":"Mathew","year":"2020","journal-title":"Science (1979)"},{"key":"2026052023572896800_btag192-B18","doi-asserted-by":"crossref","first-page":"100498","DOI":"10.1016\/j.crmeth.2023.100498","article-title":"Hdwgcna identifies co-expression networks in high-dimensional transcriptomics data","volume":"3","author":"Morabito","year":"2023","journal-title":"Cell Rep Methods"},{"key":"2026052023572896800_btag192-B19","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1038\/s41590-021-00933-1","article-title":"Multimodally profiling memory t cells from a tuberculosis cohort identifies cell state associations with demographics, environment and disease","volume":"22","author":"Nathan","year":"2021","journal-title":"Nat Immunol"},{"key":"2026052023572896800_btag192-B20","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1038\/nmeth.4402","article-title":"Reversed graph embedding resolves complex single-cell trajectories","volume":"14","author":"Qiu","year":"2017","journal-title":"Nat Methods"},{"key":"2026052023572896800_btag192-B21","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41587-019-0071-9","article-title":"A comparison of single-cell trajectory inference methods","volume":"37","author":"Saelens","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2026052023572896800_btag192-B22","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1186\/s13059-024-03453-x","article-title":"Tempted: time-informed dimensionality reduction for longitudinal microbiome studies","volume":"25","author":"Shi","year":"2024","journal-title":"Genome Biol"},{"key":"2026052023572896800_btag192-B23","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1038\/s41591-021-01329-2","article-title":"Single-cell multi-omics analysis of the immune response in covid-19","volume":"27","author":"Stephenson","year":"2021","journal-title":"Nat Med"},{"key":"2026052023572896800_btag192-B24","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1186\/s12864-018-4772-0","article-title":"Slingshot: cell lineage and pseudotime inference for single-cell transcriptomics","volume":"19","author":"Street","year":"2018","journal-title":"BMC Genomics"},{"key":"2026052023572896800_btag192-B25","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":"2026052023572896800_btag192-B26","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1016\/j.cell.2020.10.037","article-title":"Multi-omics resolves a sharp disease-state shift between mild and moderate covid-19","volume":"183","author":"Su","year":"2020","journal-title":"Cell"},{"key":"2026052023572896800_btag192-B27","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1186\/s13059-019-1898-6","article-title":"Accuracy, robustness and scalability of dimensionality reduction methods for single-cell RNA-seq analysis","volume":"20","author":"Sun","year":"2019","journal-title":"Genome Biol"},{"key":"2026052023572896800_btag192-B28","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1038\/s41587-021-01131-y","article-title":"Single-cell immunology of sars-cov-2 infection","volume":"40","author":"Tian","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2026052023572896800_btag192-B29","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1038\/nbt.2859","article-title":"The dynamics and regulators of cell fate decisions are revealed by pseudotemporal ordering of single cells","volume":"32","author":"Trapnell","year":"2014","journal-title":"Nat Biotechnol"},{"key":"2026052023572896800_btag192-B30","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2026052023572896800_btag192-B31","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1038\/s41592-021-01343-9","article-title":"Identifying temporal and spatial patterns of variation from multimodal data using mefisto","volume":"19","author":"Velten","year":"2022","journal-title":"Nat Methods"},{"key":"2026052023572896800_btag192-B32","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13059-017-1382-0","article-title":"Scanpy: large-scale single-cell gene expression data analysis","volume":"19","author":"Wolf","year":"2018","journal-title":"Genome Biol"},{"key":"2026052023572896800_btag192-B33","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13059-022-02605-1","article-title":"Ideas: individual level differential expression analysis for single-cell rna-seq data","volume":"23","author":"Zhang","year":"2022","journal-title":"Genome Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag192\/68143755\/btag192.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/5\/btag192\/68143755\/btag192.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/5\/btag192\/68143755\/btag192.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:57:59Z","timestamp":1779335879000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag192\/8661458"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,22]]},"references-count":33,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag192","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,4,22]]},"article-number":"btag192"}}