{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T02:16:31Z","timestamp":1793499391454,"version":"4.5.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T00:00:00Z","timestamp":1637280000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T00:00:00Z","timestamp":1637280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012688","name":"Universit\u00e4t Rostock","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012688","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>The research landscape of single-cell and single-nuclei RNA-sequencing is evolving rapidly. In particular, the area for the detection of rare cells was highly facilitated by this technology. However, an automated, unbiased, and accurate annotation of rare subpopulations is challenging. Once rare cells are identified in one dataset, it is usually necessary to generate further specific datasets to enrich the analysis (e.g., with samples from other tissues). From a machine learning perspective, the challenge arises from the fact that rare-cell subpopulations constitute an imbalanced classification problem.\u00a0We here introduce a Machine Learning (ML)-based oversampling method that uses gene expression counts of already identified rare cells as an input to generate synthetic cells to then identify similar (rare) cells in other publicly available experiments. We utilize single-cell synthetic oversampling (sc-SynO), which is based on the Localized Random Affine Shadowsampling (LoRAS) algorithm. The algorithm corrects for the overall imbalance ratio of the minority and majority class.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>We demonstrate the effectiveness of our method for three independent use cases, each consisting of already published datasets. The first use case identifies cardiac glial cells in snRNA-Seq data (17 nuclei out of 8635). This use case was designed to take a larger imbalance ratio (~1 to 500) into account and only uses single-nuclei data. The second use case was designed to jointly use snRNA-Seq data and scRNA-Seq on a lower imbalance ratio (~1 to 26) for the training step to likewise investigate the potential of the algorithm to consider both single-cell capture procedures and the impact of \u201cless\u201d rare-cell types. The third dataset refers to the murine data of the Allen Brain Atlas, including more than 1 million cells. For validation purposes only, all datasets have also been analyzed traditionally using common data analysis approaches, such as the Seurat workflow.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>In comparison to baseline testing without oversampling, our approach identifies rare-cells with a robust precision-recall balance, including a high accuracy and low false positive detection rate. A practical benefit of our algorithm is that it can be readily implemented in other and existing workflows. The code basis in R and Python is publicly available at FairdomHub, as well as GitHub, and can easily be transferred to identify other rare-cell types.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-021-04469-x","type":"journal-article","created":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T11:02:49Z","timestamp":1637319769000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Automated annotation of rare-cell types from single-cell RNA-sequencing data through synthetic oversampling"],"prefix":"10.1186","volume":"22","author":[{"given":"Saptarshi","family":"Bej","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne-Marie","family":"Galow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"David","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Wolfien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olaf","family":"Wolkenhauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,11,19]]},"reference":[{"key":"4469_CR1","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s13059-020-1926-6","volume":"21","author":"D L\u00e4hnemann","year":"2020","unstructured":"L\u00e4hnemann D, K\u00f6ster J, Szczurek E, et al. Eleven grand challenges in single-cell data science. Genome Biol. 2020;21:31. https:\/\/doi.org\/10.1186\/s13059-020-1926-6.","journal-title":"Genome Biol"},{"key":"4469_CR2","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.1038\/s12276-020-0420-2","volume":"52","author":"J Lee","year":"2020","unstructured":"Lee J, Hyeon D, Hwang D. Single-cell multiomics: technologies and data analysis methods. Exp Mol Med. 2020;52:1428\u201342.","journal-title":"Exp Mol Med"},{"key":"4469_CR3","doi-asserted-by":"crossref","unstructured":"Du\u00f3 A, Robinson M, Soneson C. A systematic performance evaluation of clustering methods for single-cell rna-seq data [version 2; peer review: 2 approved]. F1000Research 2018;7:1141.","DOI":"10.12688\/f1000research.15666.1"},{"key":"4469_CR4","doi-asserted-by":"crossref","unstructured":"Freytag S, Tian L, L\u00f6nnstedt I, Ng M, Bahlo M. Comparison of clustering tools in r for medium-sized 10x genomics single-cell rna-sequencing data [version 2; peer review: 3 approved]. F1000Research, 2018;7, 1297.","DOI":"10.12688\/f1000research.15809.1"},{"key":"4469_CR5","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1038\/s41576-018-0088-9","volume":"20","author":"VY Kiselev","year":"2019","unstructured":"Kiselev VY, Andrews TS, Hemberg M. Challenges in unsupervised clustering of single-cell rna-seq data. Nat Rev Genet. 2019;20:273\u201382.","journal-title":"Nat Rev Genet"},{"key":"4469_CR6","doi-asserted-by":"crossref","unstructured":"Jindal A, Gupta P, Jayadeva, Sengupta D. Discovery of rare cells from voluminous single cell expression data. Nat Commun. 2018;9:12.","DOI":"10.1038\/s41467-018-07234-6"},{"key":"4469_CR7","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1038\/s41586-018-0581-5","volume":"562","author":"F Zhang","year":"2018","unstructured":"Zhang F, Lehallier B, Schaum N, Li TQ. Single-cell transcriptomics of 20 mouse organs creates a tabula muris. Nature. 2018;562:367\u201372.","journal-title":"Nature"},{"key":"4469_CR8","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/s10994-020-05913-4","volume":"110","author":"S Bej","year":"2021","unstructured":"Bej S, Davtyan N, Wolfien M, Nassar M, Wolkenhauer O. Loras: An oversampling approach for imbalanced datasets. Mach Learn. 2021;110:279\u2013301. https:\/\/doi.org\/10.1007\/s10994-020-05913-4.","journal-title":"Mach Learn"},{"key":"4469_CR9","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1038\/nature14966","volume":"525","author":"D Gr\u00fcn","year":"2015","unstructured":"Gr\u00fcn D, Lyubimova A, Kester L, Wiebrands K, Basak O, Sasaki N, Clevers H, Oudenaarden AV. Single-cell messenger RNA sequencing reveals rare intestinal cell types. Nature. 2015;525:251\u20135.","journal-title":"Nature"},{"key":"4469_CR10","doi-asserted-by":"crossref","unstructured":"Jiang L, Chen H, Pinello L, Yuan G. GiniClust: detecting rare cell types from single-cell gene expression data with Gini index. Genome Biol. 2016;17.","DOI":"10.1186\/s13059-016-1010-4"},{"key":"4469_CR11","doi-asserted-by":"publisher","first-page":"012","DOI":"10.1088\/1755-1315\/58\/1\/012031","volume":"58","author":"B Santoso","year":"2017","unstructured":"Santoso B, Wijayanto H, Notodiputro KA, Sartono B. Synthetic over sampling methods for handling class imbalanced problems: a review. IOP Conf Ser Earth Environ Sci. 2017;58:012\u201331. https:\/\/doi.org\/10.1088\/1755-1315\/58\/1\/012031.","journal-title":"IOP Conf Ser Earth Environ Sci"},{"key":"4469_CR12","unstructured":"Weiss G, McCarthy K, Zabar B. Cost-sensitive learning vs. sampling: Which is best for handling unbalanced classes with unequal error costs? In: DMIN, 2007;pp.\u00a035\u201341."},{"key":"4469_CR13","doi-asserted-by":"publisher","first-page":"05","DOI":"10.1038\/nbt.4096","volume":"36","author":"A Butler","year":"2018","unstructured":"Butler A, Hoffman P, Smibert P, Papalexi E, Satija R. Integrating single-cell transcriptomic data across different conditions, technologies, and species. Nat Biotechnol. 2018;36:05.","journal-title":"Nat Biotechnol"},{"issue":"2","key":"4469_CR14","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3390\/cells9020318","volume":"9","author":"M Wolfien","year":"2020","unstructured":"Wolfien M, Galow A-M, M\u00fcller P, Bartsch M, Brunner RM, Goldammer T, Wolkenhauer O, Hoeflich A, David R. Single-nucleus sequencing of an entire mammalian heart: cell type composition and velocity. Cells. 2020;9(2):43\u201348.","journal-title":"Cells"},{"key":"4469_CR15","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1093\/cvr\/cvaa054","volume":"116","author":"M Wolfien","year":"2020","unstructured":"Wolfien M, Galow A-M, M\u00fcller P, Bartsch M, Brunner RM, Goldammer T, Wolkenhauer O, Hoeflich A, David R. Single nuclei sequencing of entire mammalian hearts: strain-dependent cell-type composition and velocity. Cardiovasc Res. 2020;116:1249\u201351.","journal-title":"Cardiovasc Res"},{"key":"4469_CR16","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1172\/jci.insight.131092","volume":"4","author":"R Vidal","year":"2019","unstructured":"Vidal R, Wagner JUG, Braeuning C, Fischer C, Patrick R, Tombor L, Muhly-Reinholz M, John D, Kliem M, Conrad T, Guimar\u00e3es-Camboa N, Harvey R, Dimmeler S, Sauer S. Transcriptional heterogeneity of fibroblasts is a hallmark of the aging heart. JCI Insight. 2019;4:11.","journal-title":"JCI Insight"},{"key":"4469_CR17","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.3390\/cells9051144","volume":"9","author":"A-M Galow","year":"2020","unstructured":"Galow A-M, Wolfien M, M\u00fcller P, Bartsch M, Brunner R, Hoeflich A, Wolkenhauer O, David R, Goldammer T. Integrative cluster analysis of whole hearts reveals proliferative cardiomyocytes in adult mice. Cells. 2020;9:1144.","journal-title":"Cells"},{"issue":"1","key":"4469_CR18","doi-asserted-by":"publisher","first-page":"2889","DOI":"10.1038\/s41467-019-10709-9","volume":"10","author":"N Linscheid","year":"2019","unstructured":"Linscheid N, Logantha SJRJ, Poulsen PC, Zhang S, Schr\u00f6lkamp M, Egerod KL, Thompson JJ, Kitmitto A, Galli G, Humphries MJ, Zhang H, Pers TH, Olsen JV, Boyett M, Lundby A. Quantitative proteomics and single-nucleus transcriptomics of the sinus node elucidates the foundation of cardiac pacemaking. Nat Commun. 2019;10(1):2889.","journal-title":"Nat Commun"},{"key":"4469_CR19","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/1471-2105-14-106","volume":"14","author":"R Blagus","year":"2013","unstructured":"Blagus R, Lusa L. Smote for high-dimensional class-imbalanced data. BMC Bioinform. 2013;14:106. https:\/\/doi.org\/10.1186\/1471-2105-14-106.","journal-title":"BMC Bioinform"},{"key":"4469_CR20","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1038\/s41467-019-14018-z","volume":"11","author":"M Marouf","year":"2018","unstructured":"Marouf M, Machart P, Magruder S, Bansal V, Kilian C, Krebs C, Bonn S. Realistic in silico generation and augmentation of single cell rna-seq data using generative adversarial neural networks. Nat Commun. 2018;11:166.","journal-title":"Nat Commun"},{"key":"4469_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15252\/msb.20209620","volume":"17","author":"C Xu","year":"2021","unstructured":"Xu C, Lopez R, Mehlman E, Regier J, Jordan M, Yosef N. Probabilistic harmonization and annotation of single-cell transcriptomics data with deep generative models. Mol Syst Biol. 2021;17:1.","journal-title":"Mol Syst Biol"},{"key":"4469_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41592-020-00979-3","volume":"17","author":"M Brbi\u0107","year":"2020","unstructured":"Brbi\u0107 M, Zitnik M, Wang S, Pisco A, Altman R, Darmanis S, Leskovec J. Mars: discovering novel cell types across heterogeneous single-cell experiments. Nat Methods. 2020;17:1\u20137.","journal-title":"Nat Methods"},{"key":"4469_CR23","doi-asserted-by":"publisher","first-page":"3585","DOI":"10.1093\/bioinformatics\/btaa137","volume":"36","author":"L Wang","year":"2020","unstructured":"Wang L, Catalan F, Shamardani K, Babikir H, Diaz A. Ensemble learning for classifying single-cell data and projection across reference atlases. Bioinformatics. 2020;36:3585\u20137.","journal-title":"Bioinformatics"},{"key":"4469_CR24","doi-asserted-by":"publisher","first-page":"19","DOI":"10.36255\/exonpublications.bioinformatics.2021","volume":"1","author":"M Wolfien","year":"2021","unstructured":"Wolfien M, David R, Galow A-M. Single-Cell RNA sequencing procedures and data analysis. Bioinformatics. 2021;1:19\u201335. https:\/\/doi.org\/10.36255\/exonpublications.bioinformatics.2021.","journal-title":"Bioinformatics"},{"key":"4469_CR25","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. Smote: Synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321\u201335. https:\/\/doi.org\/10.1613\/jair.953.","journal-title":"J Artif Intell Res."},{"key":"4469_CR26","doi-asserted-by":"publisher","unstructured":"Han H, Wang W-Y, Mao B-H. Borderline-smote: a new over-sampling method in imbalanced data sets learning. In: Advances in Intelligent Computing. ICIC, 2005;vol. 3644, pp.\u00a0878\u2013887. Springer, Berlin. https:\/\/doi.org\/10.1007\/1153805_91.","DOI":"10.1007\/1153805_91"},{"key":"4469_CR27","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1504\/IJKESDP.2011.039875","volume":"3","author":"HM Nguyen","year":"2011","unstructured":"Nguyen HM, Cooper E, Kamei K. Borderline over-sampling for imbalanced data classification. Int J Knowl Eng Soft Data Paradigms. 2011;3:4\u201321.","journal-title":"Int J Knowl Eng Soft Data Paradigms"},{"key":"4469_CR28","doi-asserted-by":"publisher","unstructured":"Haibo H, Yang B, Garcia E, Shutao L. Adasyn: Adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE international joint conference on neural networks, 2008. https:\/\/doi.org\/10.1109\/IJCNN.2008.4633969","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"4469_CR29","doi-asserted-by":"crossref","unstructured":"Puntumapon K, Waiyamai K. A pruning-based approach for searching precise and generalized region for synthetic minority over-sampling. In: Advances in knowledge discovery and data mining (Berlin, Heidelberg), 2012;7302, 371\u2013382. Springer, Berlin.","DOI":"10.1007\/978-3-642-30220-6_31"},{"key":"4469_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0118432","volume":"10","author":"T Saito","year":"2015","unstructured":"Saito T, Rehmsmeier M. The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE. 2015;10:1\u201321. https:\/\/doi.org\/10.1371\/journal.pone.0118432.","journal-title":"PLoS ONE"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04469-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-021-04469-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04469-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T11:04:08Z","timestamp":1637319848000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-021-04469-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,19]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["4469"],"URL":"https:\/\/doi.org\/10.1186\/s12859-021-04469-x","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,19]]},"assertion":[{"value":"9 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare that they have no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"557"}}