{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:31:29Z","timestamp":1781537489651,"version":"3.54.5"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T00:00:00Z","timestamp":1709596800000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Flanders AI Research Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Automatic cell type annotation methods assign cell type labels to new datasets by extracting relationships from a reference RNA-seq dataset. However, due to the limited resolution of gene expression features, there is always uncertainty present in the label assignment. To enhance the reliability and robustness of annotation, most machine learning methods address this uncertainty by providing a full reject option, i.e. when the predicted confidence score of a cell type label falls below a user-defined threshold, no label is assigned and no prediction is made. As a better alternative, some methods deploy hierarchical models and consider a so-called partial rejection by returning internal nodes of the hierarchy as label assignment. However, because a detailed experimental analysis of various rejection approaches is missing in the literature, there is currently no consensus on best practices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We evaluate three annotation approaches (i) full rejection, (ii) partial rejection, and (iii) no rejection for both flat and hierarchical probabilistic classifiers. Our findings indicate that hierarchical classifiers are superior when rejection is applied, with partial rejection being the preferred rejection approach, as it preserves a significant amount of label information. For optimal rejection implementation, the rejection threshold should be determined through careful examination of a method\u2019s rejection behavior. Without rejection, flat and hierarchical annotation perform equally well, as long as the cell type hierarchy accurately captures transcriptomic relationships.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Code is freely available at https:\/\/github.com\/Latheuni\/Hierarchical_reject and https:\/\/doi.org\/10.5281\/zenodo.10697468.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae128","type":"journal-article","created":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T11:40:23Z","timestamp":1709638823000},"source":"Crossref","is-referenced-by-count":5,"title":["Uncertainty-aware single-cell annotation with a hierarchical reject option"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1883-2310","authenticated-orcid":false,"given":"Lauren","family":"Theunissen","sequence":"first","affiliation":[{"name":"Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent, Belgium"},{"name":"Data Mining and Modelling for Biomedicine, VIB Center for Inflammation Research , Ghent, Belgium"},{"name":"Department of Applied Mathematics, Computer Science and Statistics, Ghent University , Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Mortier","sequence":"additional","affiliation":[{"name":"Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0415-1506","authenticated-orcid":false,"given":"Yvan","family":"Saeys","sequence":"additional","affiliation":[{"name":"Data Mining and Modelling for Biomedicine, VIB Center for Inflammation Research , Ghent, Belgium"},{"name":"Department of Applied Mathematics, Computer Science and Statistics, Ghent University , Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5950-3003","authenticated-orcid":false,"given":"Willem","family":"Waegeman","sequence":"additional","affiliation":[{"name":"Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,3,5]]},"reference":[{"key":"2024032203514118300_btae128-B1","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1186\/s13059-019-1795-z","article-title":"A comparison of automatic cell identification methods for single-cell RNA sequencing data","volume":"20","author":"Abdelaal","year":"2019","journal-title":"Genome Biol"},{"key":"2024032203514118300_btae128-B2","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1186\/s13059-019-1862-5","article-title":"scPred: accurate supervised method for cell-type classification from single-cell RNA-seq data","volume":"20","author":"Alquicira-Hernandez","year":"2019","journal-title":"Genome Biol"},{"key":"2024032203514118300_btae128-B3","doi-asserted-by":"crossref","first-page":"101913","DOI":"10.1016\/j.isci.2020.101913","article-title":"CellO: comprehensive and hierarchical cell type classification of human cells with the cell ontology","volume":"24","author":"Bernstein","year":"2021","journal-title":"iScience"},{"key":"2024032203514118300_btae128-B4","first-page":"51","author":"Beygelzimer","year":"2009"},{"key":"2024032203514118300_btae128-B5","doi-asserted-by":"crossref","first-page":"2907","DOI":"10.1109\/TKDE.2015.2441707","article-title":"Bayes-optimal hierarchical multilabel classification","volume":"27","author":"Bi","year":"2015","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2024032203514118300_btae128-B6","doi-asserted-by":"crossref","first-page":"3458","DOI":"10.1038\/s41467-020-17281-7","article-title":"Searching large-scale scRNA-seq databases via unbiased cell embedding with cell BLAST","volume":"11","author":"Cao","year":"2020","journal-title":"Nat Commun"},{"key":"2024032203514118300_btae128-B7","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/s10844-006-0003-2","article-title":"Classifying web documents in a hierarchy of categories: a comprehensive study","volume":"28","author":"Ceci","year":"2007","journal-title":"J Intell Inf Syst"},{"key":"2024032203514118300_btae128-B8","author":"Chan Zuckerberg Initiative Single-Cell COVID-19 Consortia"},{"key":"2024032203514118300_btae128-B9","doi-asserted-by":"crossref","first-page":"2749","DOI":"10.1038\/s41596-021-00534-0","article-title":"Tutorial: guidelines for annotating single-cell transcriptomic maps using automated and manual methods","volume":"16","author":"Clarke","year":"2021","journal-title":"Nat Protoc"},{"key":"2024032203514118300_btae128-B10","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/2041-1480-4-32","article-title":"The Drosophila anatomy ontology","volume":"4","author":"Costa","year":"2013","journal-title":"J Biomed Seman"},{"key":"2024032203514118300_btae128-B11","doi-asserted-by":"crossref","first-page":"e95","DOI":"10.1093\/nar\/gkz543","article-title":"CHETAH: a selective, hierarchical cell type identification method for single-cell RNA sequencing","volume":"47","author":"de Kanter","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2024032203514118300_btae128-B12","author":"Dembczy\u0144ski","year":"2012"},{"key":"2024032203514118300_btae128-B13","first-page":"511","volume-title":"Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2016. Lecture Notes in Computer Science","author":"Dembczy\u0144ski","year":"2016"},{"key":"2024032203514118300_btae128-B14","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/s41576-022-00449-w","article-title":"Single-cell atlases: shared and tissue-specific cell types across human organs","volume":"23","author":"Elmentaite","year":"2022","journal-title":"Nat Rev Genet"},{"key":"2024032203514118300_btae128-B15","first-page":"39","author":"Frank","year":"2004"},{"key":"2024032203514118300_btae128-B16","doi-asserted-by":"crossref","first-page":"5271","DOI":"10.1038\/s41467-022-33045-x","article-title":"devCellPy is a machine learning-enabled pipeline for automated annotation of complex multilayered single-cell transcriptomic data","volume":"13","author":"Galdos","year":"2022","journal-title":"Nat Commun"},{"key":"2024032203514118300_btae128-B17","author":"Ghadar","year":"2022"},{"key":"2024032203514118300_btae128-B18","doi-asserted-by":"crossref","first-page":"iyac035","DOI":"10.1093\/genetics\/iyac035","article-title":"FlyBase: a guided tour of highlighted features","volume":"220","author":"Gramates","year":"2022","journal-title":"Genetics"},{"key":"2024032203514118300_btae128-B19","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":"2024032203514118300_btae128-B20","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","article-title":"Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods","volume":"110","author":"H\u00fcllermeier","year":"2021","journal-title":"Mach Learn"},{"key":"2024032203514118300_btae128-B21","doi-asserted-by":"crossref","first-page":"D870","DOI":"10.1093\/nar\/gkac947","article-title":"CellMarker 2.0: an updated database of manually curated cell markers in human\/mouse and web tools based on scRNA-seq data","volume":"51","author":"Hu","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2024032203514118300_btae128-B22","doi-asserted-by":"crossref","first-page":"bbab035","DOI":"10.1093\/bib\/bbab035","article-title":"Evaluation of machine learning approaches for cell-type identification from single-cell transcriptomics data","volume":"22","author":"Huang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024032203514118300_btae128-B23","doi-asserted-by":"crossref","first-page":"4431","DOI":"10.1093\/bioinformatics\/btab499","article-title":"HieRFIT: a hierarchical cell type classification tool for projections from complex single-cell atlas datasets","volume":"37","author":"Kaymaz","year":"2021","journal-title":"Bioinformatics"},{"key":"2024032203514118300_btae128-B24","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1038\/nmeth.4644","article-title":"Scmap: projection of single-cell RNA-seq data across data sets","volume":"15","author":"Kiselev","year":"2018","journal-title":"Nat Methods"},{"key":"2024032203514118300_btae128-B25","doi-asserted-by":"crossref","first-page":"eabk2432","DOI":"10.1126\/science.abk2432","article-title":"Fly cell atlas: a single-nucleus transcriptomic atlas of the adult fruit fly","volume":"375","author":"Li","year":"2022","journal-title":"Science (New York, N.Y.)"},{"key":"2024032203514118300_btae128-B26","doi-asserted-by":"crossref","first-page":"e9389","DOI":"10.15252\/msb.20199389","article-title":"scClassify: sample size estimation and multiscale classification of cells using single and multiple reference","volume":"16","author":"Lin","year":"2020","journal-title":"Mol Syst Biol"},{"key":"2024032203514118300_btae128-B27","author":"Liu","year":"2023"},{"key":"2024032203514118300_btae128-B28","doi-asserted-by":"crossref","first-page":"e8746","DOI":"10.15252\/msb.20188746","article-title":"Current best practices in single-cell RNA-seq analysis: a tutorial","volume":"15","author":"Luecken","year":"2019","journal-title":"Mol Syst Biol"},{"key":"2024032203514118300_btae128-B29","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1007\/s10994-018-5733-1","article-title":"On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis","volume":"107","author":"Melnikov","year":"2018","journal-title":"Mach Learn"},{"key":"2024032203514118300_btae128-B30","doi-asserted-by":"crossref","first-page":"2799","DOI":"10.1038\/s41467-021-23196-8","article-title":"Hierarchical progressive learning of cell identities in single-cell data","volume":"12","author":"Michielsen","year":"2021","journal-title":"Nat Commun"},{"key":"2024032203514118300_btae128-B31","doi-asserted-by":"crossref","first-page":"6157","DOI":"10.1016\/j.csbj.2021.11.004","article-title":"Bacterial species identification using MALDI-TOF mass spectrometry and machine learning techniques: a large-scale benchmarking study","volume":"19","author":"Mortier","year":"2021","journal-title":"Comput Struct Biotechnol J"},{"key":"2024032203514118300_btae128-B32","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1007\/s10618-021-00751-x","article-title":"Efficient set-valued prediction in multi-class classification","volume":"35","author":"Mortier","year":"2021","journal-title":"Data Min Knowl Disc"},{"key":"2024032203514118300_btae128-B33","first-page":"65","article-title":"Accuracy-rejection curves (ARCS) for comparing classification methods with a reject option","volume":"8","author":"Nadeem","year":"2010","journal-title":"J Mach Learn Res Proc Track"},{"key":"2024032203514118300_btae128-B34","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1016\/j.csbj.2021.01.015","article-title":"Automated methods for cell type annotation on scRNA-seq data","volume":"19","author":"Pasquini","year":"2021","journal-title":"Comput Struct Biotechnol J"},{"key":"2024032203514118300_btae128-B35","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2024032203514118300_btae128-B36","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"1999","journal-title":"Adv Large Margin Classif"},{"key":"2024032203514118300_btae128-B37","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":"2024032203514118300_btae128-B38","doi-asserted-by":"crossref","first-page":"lqad058","DOI":"10.1093\/nargab\/lqad058","article-title":"scROSHI \u2013 robust supervised hierarchical identification of single cells","volume":"5","author":"Prummer","year":"2022","journal-title":"NAR Genomics Bioinf"},{"key":"2024032203514118300_btae128-B39","first-page":"333","volume-title":"Mach Learn","author":"Read","year":"2011"},{"key":"2024032203514118300_btae128-B40","author":"Salehi","year":"2022"},{"key":"2024032203514118300_btae128-B41","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1038\/nbt.3192","article-title":"Spatial reconstruction of single-cell gene expression data","volume":"33","author":"Satija","year":"2015","journal-title":"Nat Biotechnol"},{"key":"2024032203514118300_btae128-B42","first-page":"3183","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Sensoy","year":"2018"},{"key":"2024032203514118300_btae128-B43","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s10618-010-0175-9","article-title":"A survey of hierarchical classification across different application domains","volume":"22","author":"Silla","year":"2011","journal-title":"Data Min Knowl Disc"},{"key":"2024032203514118300_btae128-B44","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":"2024032203514118300_btae128-B45","first-page":"521","author":"Sun","year":"2001"},{"key":"2024032203514118300_btae128-B46","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/s41586-018-0654-5","article-title":"Shared and distinct transcriptomic cell types across neocortical areas","volume":"563","author":"Tasic","year":"2018","journal-title":"Nature"},{"key":"2024032203514118300_btae128-B47","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":"2024032203514118300_btae128-B48","first-page":"3281","author":"Wang","year":"2009"},{"key":"2024032203514118300_btae128-B49","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1186\/s13059-020-02027-x","article-title":"Accounting for cell type hierarchy in evaluating single cell RNA-seq clustering","volume":"21","author":"Wu","year":"2020","journal-title":"Genome Biol"},{"key":"2024032203514118300_btae128-B50","doi-asserted-by":"crossref","first-page":"2739","DOI":"10.1016\/j.cell.2022.06.031","article-title":"What is a cell type and how to define it?","volume":"185","author":"Zeng","year":"2022","journal-title":"Cell"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae128\/56838629\/btae128.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/3\/btae128\/57056303\/btae128.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/3\/btae128\/57056303\/btae128.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T23:52:26Z","timestamp":1711065146000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae128\/7619283"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,1]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae128","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.09.25.559294","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,3,1]]},"published":{"date-parts":[[2024,3,1]]},"article-number":"btae128"}}