{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T02:29:18Z","timestamp":1770776958141,"version":"3.50.0"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T00:00:00Z","timestamp":1764892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Gulf Coast Consortia","award":["5T15LM007093-31"],"award-info":[{"award-number":["5T15LM007093-31"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1U24MH130988-01"],"award-info":[{"award-number":["1U24MH130988-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1UL1TR003167"],"award-info":[{"award-number":["1UL1TR003167"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1UM1TR004906-01"],"award-info":[{"award-number":["1UM1TR004906-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1R01AG066749"],"award-info":[{"award-number":["1R01AG066749"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["5R56AG069880-02"],"award-info":[{"award-number":["5R56AG069880-02"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000005","name":"Department of Defense","doi-asserted-by":"publisher","award":["W81XWH-22-1-0164"],"award-info":[{"award-number":["W81XWH-22-1-0164"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004917","name":"Cancer Prevention and Research Institute of Texas","doi-asserted-by":"publisher","award":["RP170668"],"award-info":[{"award-number":["RP170668"]}],"id":[{"id":"10.13039\/100004917","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Single-cell RNA sequencing (scRNA-Seq) technology enables detailed exploration of gene expression at the individual cell level, crucial for annotating cell types and understanding cellular diversity. Traditional methods for cell type annotation often rely on marker genes and manual labeling, posing challenges due to low data quality and incomplete reference datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We developed CeLLTra, a novel contrastive learning framework that leverages a Transformer-based model integrating biological pathway information to group genes into super tokens, effectively capturing comprehensive gene expression from scRNA-Seq data. By combining this pathway-informed Transformer with a pretrained domain-specific language model, CeLLTra accurately aligns cell-type annotations with gene expression profiles. Evaluations on a large-scale human scRNA-Seq dataset showed that CeLLTra significantly outperformed state-of-the-art methods in supervised and zero-shot cell-type prediction. Additionally, CeLLTra generalized well to external datasets, improving clustering performance and enabling better characterization of cancerous cell states in tumor-infiltrating myeloid cells from non-small cell lung cancer patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>CeLLTra is freely available on GitHub (https:\/\/github.com\/WJZheng-group\/CeLLTra) and Zenodo (https:\/\/doi.org\/10.5281\/zenodo.17666735). The datasets underlying this article are the following: GSE201333 and GSE127465. All these datasets are publicly available and can be freely accessed on the Gene Expression Omnibus repository.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf655","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T13:10:24Z","timestamp":1764853824000},"source":"Crossref","is-referenced-by-count":0,"title":["CeLLTra: aligning cell names with gene expression via a pathway-informed transformer"],"prefix":"10.1093","volume":"42","author":[{"given":"Zhao","family":"Li","sequence":"first","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston Department of Bioinformatics & Systems Medicine, , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0685-0057","authenticated-orcid":false,"given":"Zaiyi","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Virginia Department of Electrical and Computer Engineering, , Charlottesville, VA 22903,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongbin","family":"Li","sequence":"additional","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston Department of Bioinformatics & Systems Medicine, , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Chen","sequence":"additional","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston Department of Bioinformatics & Systems Medicine, , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuntao","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Texas MD Anderson Cancer Center Department of Genomic Medicine, , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meer A","family":"Ali","sequence":"additional","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston Department of Bioinformatics & Systems Medicine, , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jundong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Virginia Department of Electrical and Computer Engineering, , Charlottesville, VA 22903,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7411-6047","authenticated-orcid":false,"given":"W Jim","family":"Zheng","sequence":"additional","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston Department of Bioinformatics & Systems Medicine, , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"key":"2026020704020115300_btaf655-B1","doi-asserted-by":"crossref","first-page":"205","DOI":"10.3233\/AO-2008-0057","article-title":"BioTop: an upper domain ontology for the life sciences","volume":"3","author":"Beisswanger","year":"2008","journal-title":"Appl Ontol"},{"key":"2026020704020115300_btaf655-B2","doi-asserted-by":"publisher","first-page":"17700","DOI":"10.1609\/aaai.v38i16.29722","article-title":"Beyond attention: Breaking the limits of transformer context length with recurrent memory","author":"Bulatov","year":"2024","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"2026020704020115300_btaf655-B3","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1093\/bioinformatics\/bty498","article-title":"A descriptive marker gene approach to single-cell pseudotime inference","volume":"35","author":"Campbell","year":"2019","journal-title":"Bioinformatics"},{"key":"2026020704020115300_btaf655-B4","doi-asserted-by":"crossref","first-page":"317","DOI":"10.3389\/fgene.2019.00317","article-title":"Single-cell RNA-seq technologies and related computational data analysis","volume":"10","author":"Chen","year":"2019","journal-title":"Front Genet"},{"key":"2026020704020115300_btaf655-B5","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1038\/s41592-024-02201-0","article-title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI","volume":"21","author":"Cui","year":"2024","journal-title":"Nat Methods"},{"key":"2026020704020115300_btaf655-B6","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1186\/gm468","article-title":"Understanding cellular function and disease with comparative pathway analysis","volume":"5","author":"Davis","year":"2013","journal-title":"Genome Med"},{"key":"2026020704020115300_btaf655-B7","author":"Devlin J, Chang MW, Lee K"},{"key":"2026020704020115300_btaf655-B8","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s13326-016-0088-7","article-title":"The cell ontology 2016: enhanced content, modularization, and ontology interoperability","volume":"7","author":"Diehl","year":"2016","journal-title":"J Biomed Semant"},{"key":"2026020704020115300_btaf655-B9","author":"Dosovitskiy","year":"2020"},{"key":"2026020704020115300_btaf655-B10","first-page":"6611","article-title":"khin. et al sctab: scaling cross-tissue single-cell annotation models","volume":"4","author":"Fischer","journal-title":"Nat Commun"},{"key":"2026020704020115300_btaf655-B11","doi-asserted-by":"crossref","first-page":"2366","DOI":"10.1038\/s41593-024-01774-5","article-title":"Integrated multimodal cell atlas of alzheimer\u2019s disease","volume":"27","author":"Gabitto","year":"2024","journal-title":"Nat Neurosci"},{"key":"2026020704020115300_btaf655-B12","first-page":"633","author":"Godec","year":"2022"},{"key":"2026020704020115300_btaf655-B13","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1093\/biostatistics\/kxac021","article-title":"A probabilistic gene expression barcode for annotation of cell types from single-cell RNA-seq data","volume":"23","author":"Grabski","year":"2022","journal-title":"Biostatistics"},{"key":"2026020704020115300_btaf655-B14","first-page":"1","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Transact Comput Healthcare (HEALTH)"},{"key":"2026020704020115300_btaf655-B15","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1186\/s13059-021-02281-7","article-title":"scSorter: assigning cells to known cell types according to marker genes","volume":"22","author":"Guo","year":"2021","journal-title":"Genome Biol"},{"key":"2026020704020115300_btaf655-B16","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1038\/s41592-024-02305-7","article-title":"Large-scale foundation model on single-cell transcriptomics","volume":"21","author":"Hao","year":"2024","journal-title":"Nat Methods"},{"key":"2026020704020115300_btaf655-B17","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1038\/s41592-024-02235-4","article-title":"Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis","volume":"21","author":"Hou","year":"2024","journal-title":"Nat Methods"},{"key":"2026020704020115300_btaf655-B18","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1146\/annurev.genom.2.1.343","article-title":"A new approach to decoding life: systems biology","volume":"2","author":"Ideker","year":"2001","journal-title":"Annu Rev Genomics Hum Genet"},{"key":"2026020704020115300_btaf655-B19","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1038\/s41596-024-01045-4","article-title":"CellChat for systematic analysis of cell\u2013cell communication from single-cell transcriptomics","volume":"20","author":"Jin","year":"2025","journal-title":"Nat Protoc"},{"key":"2026020704020115300_btaf655-B20","first-page":"91","author":"Kanehisa","year":"2002"},{"key":"2026020704020115300_btaf655-B21","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1038\/s41576-018-0088-9","article-title":"Challenges in unsupervised clustering of single-cell RNA-seq data","volume":"20","author":"Kiselev","year":"2019","journal-title":"Nat Rev Genet"},{"key":"2026020704020115300_btaf655-B22","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1126\/science.1069492","article-title":"Systems biology: a brief overview","volume":"295","author":"Kitano","year":"2002","journal-title":"Science"},{"key":"2026020704020115300_btaf655-B23","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1093\/bioinformatics\/btr260","article-title":"Molecular signatures database (MSigDB) 3.0","volume":"27","author":"Liberzon","year":"2011","journal-title":"Bioinformatics"},{"key":"2026020704020115300_btaf655-B24","doi-asserted-by":"crossref","first-page":"btae316","DOI":"10.1093\/bioinformatics\/btae316","article-title":"Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data","volume":"40","author":"Liu","year":"2024","journal-title":"Bioinformatics"},{"key":"2026020704020115300_btaf655-B25","doi-asserted-by":"crossref","first-page":"e8746","DOI":"10.15252\/msb.20188746","article-title":"Current best practices in single\u2013cell RNA\u2013seq analysis: a tutorial","volume":"15","author":"Luecken","year":"2019","journal-title":"Mol Syst Biol"},{"key":"2026020704020115300_btaf655-B26","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2026020704020115300_btaf655-B27","doi-asserted-by":"crossref","first-page":"eabf1970","DOI":"10.1126\/science.abf1970","article-title":"Single-cell RNA-seq reveals cell type\u2013specific molecular and genetic associations to lupus","volume":"376","author":"Perez","year":"2022","journal-title":"Science"},{"key":"2026020704020115300_btaf655-B28","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1038\/s41592-019-0535-3","article-title":"Supervised classification enables rapid annotation of cell atlases","volume":"16","author":"Pliner","year":"2019","journal-title":"Nat Methods"},{"key":"2026020704020115300_btaf655-B29","first-page":"8748","author":"Radford","year":"2021"},{"key":"2026020704020115300_btaf655-B30","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1038\/nprot.2017.149","article-title":"Exponential scaling of single-cell RNA-seq in the past decade","volume":"13","author":"Svensson","year":"2018","journal-title":"Nat Protoc"},{"key":"2026020704020115300_btaf655-B31","first-page":"367","volume":"562","author":"Schaum N, Karkanias J, Neff NF"},{"key":"2026020704020115300_btaf655-B32","doi-asserted-by":"crossref","first-page":"eabl4896","DOI":"10.1126\/science.abl4896","article-title":"The tabula sapiens: A multiple-organ, single-cell transcriptomic atlas of humans","volume":"376","author":"Jones","year":"2022","journal-title":"Science"},{"key":"2026020704020115300_btaf655-B33","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","article-title":"Transfer learning enables predictions in network biology","volume":"618","author":"Theodoris","year":"2023","journal-title":"Nature"},{"key":"2026020704020115300_btaf655-B34","doi-asserted-by":"crossref","first-page":"5233","DOI":"10.1038\/s41598-019-41695-z","article-title":"From louvain to leiden: guaranteeing well-connected communities","volume":"9","author":"Traag","year":"2019","journal-title":"Sci Rep"},{"key":"2026020704020115300_btaf655-B35","doi-asserted-by":"crossref","first-page":"5556","DOI":"10.1038\/s41467-021-25725-x","article-title":"Leveraging the cell ontology to classify unseen cell types","volume":"12","author":"Wang","year":"2021","journal-title":"Nat Commun"},{"key":"2026020704020115300_btaf655-B36","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":"2026020704020115300_btaf655-B37","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":"2026020704020115300_btaf655-B38","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41586-023-06812-z","article-title":"A high-resolution transcriptomic and spatial atlas of cell types in the whole mouse brain","volume":"624","author":"Yao","year":"2023","journal-title":"Nature"},{"key":"2026020704020115300_btaf655-B39","volume-title":"PLoS Comput Biol","author":"Yixuan","year":"2023"},{"key":"2026020704020115300_btaf655-B40","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1126\/science.aaa1934","article-title":"Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq","volume":"347","author":"Zeisel","year":"2015","journal-title":"Science"},{"key":"2026020704020115300_btaf655-B41","doi-asserted-by":"crossref","first-page":"531","DOI":"10.3390\/genes10070531","article-title":"SCINA: a semi-supervised subtyping algorithm of single cells and bulk samples","volume":"10","author":"Zhang","year":"2019","journal-title":"Genes (Basel)"},{"key":"2026020704020115300_btaf655-B42","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1016\/j.immuni.2019.03.009","article-title":"Single-cell transcriptomics of human and mouse lung cancers reveals conserved myeloid populations across individuals and species","volume":"50","author":"Zilionis","year":"2019","journal-title":"Immunity"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/2\/btaf655\/65779726\/btaf655.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/2\/btaf655\/65779726\/btaf655.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T09:02:17Z","timestamp":1770454937000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf655\/8371888"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,12,5]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf655","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,2]]},"published":{"date-parts":[[2025,12,5]]},"article-number":"btaf655"}}