{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T02:51:53Z","timestamp":1777690313685,"version":"3.51.4"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T00:00:00Z","timestamp":1711670400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Cell-type clustering is a crucial first step for single-cell RNA-seq data analysis. However, existing clustering methods often provide different results on cluster assignments with respect to their own data pre-processing, choice of distance metrics, and strategies of feature extraction, thereby limiting their practical applications.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose Cross-Tabulation Ensemble Clustering (CTEC) method that formulates two re-clustering strategies (distribution- and outlier-based) via cross-tabulation. Benchmarking experiments on five scRNA-Seq datasets illustrate that the proposed CTEC method offers significant improvements over the individual clustering methods. Moreover, CTEC-DB outperforms the state-of-the-art ensemble methods for single-cell data clustering, with 45.4% and 17.1% improvement over the single-cell aggregated from ensemble clustering method (SAFE) and the single-cell aggregated clustering via Mixture model ensemble method (SAME), respectively, on the two-method ensemble test.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code of the benchmark in this work is available at the GitHub repository https:\/\/github.com\/LWCHN\/CTEC.git.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae130","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T18:51:24Z","timestamp":1711565484000},"source":"Crossref","is-referenced-by-count":7,"title":["CTEC: a cross-tabulation ensemble clustering approach for single-cell RNA sequencing data analysis"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6981-557X","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"first","affiliation":[{"name":"AI Lab , Shenzhen 518054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong , Hong Kong, 999077, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8031-9086","authenticated-orcid":false,"given":"Jiangning","family":"Song","sequence":"additional","affiliation":[{"name":"Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University , Clayton, VIC 3800, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Yao","sequence":"additional","affiliation":[{"name":"AI Lab , Shenzhen 518054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,3,29]]},"reference":[{"key":"2024040210053371500_btae130-B1","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1145\/253417.253350","article-title":"Cross-tabulation algorithms","volume":"26","author":"Barghoorn","year":"1996","journal-title":"SIGAPL APL Quote Quad"},{"key":"2024040210053371500_btae130-B2","doi-asserted-by":"crossref","first-page":"P10008","DOI":"10.1088\/1742-5468\/2008\/10\/P10008","article-title":"Fast unfolding of communities in large networks","volume":"2008","author":"Blondel","year":"2008","journal-title":"J Stat Mech"},{"key":"2024040210053371500_btae130-B3","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1038\/nbt.4096","article-title":"Integrating single-cell transcriptomic data across different conditions, technologies, and species","volume":"36","author":"Butler","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2024040210053371500_btae130-B4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/03610927408827101","article-title":"A dendrite method for cluster analysis","volume":"3","author":"Calinski","year":"1974","journal-title":"Comm Stats Theory Methods"},{"key":"2024040210053371500_btae130-B5","doi-asserted-by":"crossref","first-page":"4616","DOI":"10.1038\/s41467-022-32097-3","article-title":"Scarf enables a highly memory-efficient analysis of large-scale single-cell genomics data","volume":"13","author":"Dhapola","year":"2022","journal-title":"Nat Commun"},{"key":"2024040210053371500_btae130-B6","first-page":"1","article-title":"The impact of random models on clustering similarity","volume":"18","author":"Gates","year":"2017","journal-title":"J Mach Learn Res"},{"key":"2024040210053371500_btae130-B7","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1038\/nature14966","article-title":"Single-cell messenger RNA sequencing reveals rare intestinal cell types","volume":"525","author":"Gr\u00fcn","year":"2015","journal-title":"Nature"},{"key":"2024040210053371500_btae130-B8","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1093\/nar\/gkz959","article-title":"Same-clustering: single-cell aggregated clustering via mixture model ensemble","volume":"48","author":"Huh","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2024040210053371500_btae130-B9","doi-asserted-by":"crossref","first-page":"10978","DOI":"10.1093\/nar\/gkx754","article-title":"Accounting for technical noise in differential expression analysis of single-cell RNA sequencing data","volume":"45","author":"Jia","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2024040210053371500_btae130-B10","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1038\/nmeth.4236","article-title":"SC3: consensus clustering of single-cell RNA-seq data","volume":"14","author":"Kiselev","year":"2017","journal-title":"Nat Methods"},{"key":"2024040210053371500_btae130-B11","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1101\/gr.271874.120","article-title":"A joint deep learning model enables simultaneous batch effect correction, denoising and clustering in single-cell transcriptomics","volume":"31","author":"Lakkis","year":"2021","journal-title":"Genome Res"},{"key":"2024040210053371500_btae130-B12","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1038\/s41592-020-0905-x","article-title":"Cumulus provides cloud-based data analysis for large-scale single-cell and single-nucleus RNA-seq","volume":"17","author":"Li","year":"2020","journal-title":"Nat Methods"},{"key":"2024040210053371500_btae130-B13","doi-asserted-by":"crossref","first-page":"2338","DOI":"10.1038\/s41467-020-15851-3","article-title":"Deep learning enables accurate clustering with batch effect removal in single-cell RNA-seq analysis","volume":"11","author":"Li","year":"2020","journal-title":"Nat Commun"},{"key":"2024040210053371500_btae130-B14","first-page":"1118","author":"Li","year":"2020"},{"key":"2024040210053371500_btae130-B15","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1186\/s13059-017-1188-0","article-title":"CIDR: ultrafast and accurate clustering through imputation for single-cell RNA-seq data","volume":"18","author":"Lin","year":"2017","journal-title":"Genome Biol"},{"key":"2024040210053371500_btae130-B16","doi-asserted-by":"crossref","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: uniform manifold approximation and projection","volume":"3","author":"McInnes","year":"2018","journal-title":"JOSS"},{"key":"2024040210053371500_btae130-B17","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1186\/s12859-022-05085-z","article-title":"Sc3s: efficient scaling of single cell consensus clustering to millions of cells","volume":"23","author":"Quah","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2024040210053371500_btae130-B18","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1016\/j.cell.2021.01.053","article-title":"Covid-19 immune features revealed by a large-scale single-cell transcriptome atlas","volume":"184","author":"Ren","year":"2021","journal-title":"Cell"},{"key":"2024040210053371500_btae130-B19","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":"2024040210053371500_btae130-B20","doi-asserted-by":"crossref","first-page":"100002","DOI":"10.1074\/mcp.RA120.002275","article-title":"On the robustness of Graph-Based clustering to random network alterations","volume":"20","author":"Stacey","year":"2021","journal-title":"Mol Cell Proteomics"},{"key":"2024040210053371500_btae130-B21","first-page":"583","article-title":"Cluster ensembles\u2014a knowledge reuse framework for combining multiple partitions","volume":"3","author":"Strehl","year":"2003","journal-title":"J Mach Learn Res"},{"key":"2024040210053371500_btae130-B22","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1093\/bioinformatics\/btx490","article-title":"DIMM-SC: a Dirichlet mixture model for clustering droplet-based single cell transcriptomic data","volume":"34","author":"Sun","year":"2018","journal-title":"Bioinformatics"},{"key":"2024040210053371500_btae130-B23","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":"2024040210053371500_btae130-B24","first-page":"2597","article-title":"Visualizing data using T-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2024040210053371500_btae130-B25","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1038\/nmeth.4207","article-title":"Visualization and analysis of single-cell RNA-seq data by kernel-based similarity learning","volume":"14","author":"Wang","year":"2017","journal-title":"Nat Methods"},{"key":"2024040210053371500_btae130-B26","doi-asserted-by":"crossref","first-page":"91855","DOI":"10.1109\/ACCESS.2020.2994380","article-title":"Three-Way ensemble clustering for incomplete data","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"2024040210053371500_btae130-B27","doi-asserted-by":"crossref","first-page":"e1010753","DOI":"10.1371\/journal.pcbi.1010753","article-title":"Secuer: ultrafast, scalable and accurate clustering of single-cell RNA-seq data","volume":"18","author":"Wei","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"2024040210053371500_btae130-B28","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":"2024040210053371500_btae130-B29","first-page":"740","author":"Xie","year":"2016"},{"key":"2024040210053371500_btae130-B30","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1093\/bioinformatics\/bty793","article-title":"SAFE-clustering: single-cell aggregated (from ensemble) clustering for single-cell RNA-seq data","volume":"35","author":"Yang","year":"2019","journal-title":"Bioinformatics"},{"key":"2024040210053371500_btae130-B31","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1186\/s12859-018-2092-7","article-title":"An interpretable framework for clustering single-cell RNA-Seq datasets","volume":"19","author":"Zhang","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"2024040210053371500_btae130-B32","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1214\/17-AOAS1110","article-title":"A unified statistical framework for single cell and bulk rna sequencing data","volume":"12","author":"Zhu","year":"2018","journal-title":"Ann Appl Stat"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae130\/57122325\/btae130.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae130\/57137064\/btae130.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae130\/57137064\/btae130.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T13:43:59Z","timestamp":1712065439000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae130\/7637679"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,29]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae130","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,4,1]]},"published":{"date-parts":[[2024,3,29]]},"article-number":"btae130"}}