{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T10:10:38Z","timestamp":1784110238045,"version":"3.55.0"},"reference-count":107,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100010946","name":"UC | UC San Francisco | School of Medicine, University of California, San Francisco","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010946","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Ageing Biology Foundation"},{"name":"CZI data ecosystem grant"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-025-00943-1","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T10:02:46Z","timestamp":1771236166000},"page":"123-133","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Toward informed batch correction for single-cell transcriptome integration"],"prefix":"10.1038","volume":"6","author":[{"given":"Shuang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7464-7921","authenticated-orcid":false,"given":"Malte","family":"L\u00fccken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John C.","family":"Marioni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6294-6366","authenticated-orcid":false,"given":"Sarah A.","family":"Teichmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2457-3554","authenticated-orcid":false,"given":"Peng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"943_CR1","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1038\/nprot.2017.149","volume":"13","author":"V Svensson","year":"2018","unstructured":"Svensson, V., Vento-Tormo, R. & Teichmann, S. A. Exponential scaling of single-cell RNA-seq in the past decade. Nat. Protoc. 13, 599\u2013604 (2018).","journal-title":"Nat. Protoc."},{"key":"943_CR2","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1038\/nrg2825","volume":"11","author":"JT Leek","year":"2010","unstructured":"Leek, J. T. et al. Tackling the widespread and critical impact of batch effects in high-throughput data. Nat. Rev. Genet. 11, 733\u2013739 (2010).","journal-title":"Nat. Rev. Genet."},{"key":"943_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41592-021-01336-8","volume":"19","author":"MD Luecken","year":"2022","unstructured":"Luecken, M. D. et al. Benchmarking atlas-level data integration in single-cell genomics. Nat. Methods 19, 41\u201350 (2022).","journal-title":"Nat. Methods"},{"key":"943_CR4","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s41592-023-01814-1","volume":"20","author":"C Ahlmann-Eltze","year":"2023","unstructured":"Ahlmann-Eltze, C. & Huber, W. Comparison of transformations for single-cell RNA-seq data. Nat. Methods 20, 665\u2013672 (2023).","journal-title":"Nat. Methods"},{"key":"943_CR5","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giaa151","volume":"9","author":"MD Young","year":"2020","unstructured":"Young, M. D. & Behjati, S. SoupX removes ambient RNA contamination from droplet-based single-cell RNA sequencing data. GigaScience 9, giaa151 (2020).","journal-title":"GigaScience"},{"key":"943_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1038\/s41592-025-02624-3","volume":"22","author":"L Zappia","year":"2025","unstructured":"Zappia, L. et al. Feature selection methods affect the performance of scRNA-seq data integration and querying. Nat. Methods 22, 834\u2013844 (2025).","journal-title":"Nat. Methods"},{"key":"943_CR7","doi-asserted-by":"publisher","unstructured":"Zhang, B. et al. A human embryonic limb cell atlas resolved in space and time. Nature https:\/\/doi.org\/10.1038\/s41586-023-06806-x (2023).","DOI":"10.1038\/s41586-023-06806-x"},{"key":"943_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37126-3","volume":"14","author":"HCT Nguyen","year":"2023","unstructured":"Nguyen, H. C. T., Baik, B., Yoon, S., Park, T. & Nam, D. Benchmarking integration of single-cell differential expression. Nat. Commun. 14, 1570 (2023).","journal-title":"Nat. Commun."},{"key":"943_CR9","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.cels.2020.11.008","volume":"12","author":"NM Xi","year":"2021","unstructured":"Xi, N. M. & Li, J. J. Benchmarking computational doublet-detection methods for single-cell RNA sequencing data. Cell Syst. 12, 176\u2013194.e6 (2021).","journal-title":"Cell Syst."},{"key":"943_CR10","doi-asserted-by":"publisher","first-page":"e42","DOI":"10.1093\/nar\/gkab004","volume":"49","author":"R Chazarra-Gil","year":"2021","unstructured":"Chazarra-Gil, R., van Dongen, S., Kiselev, V. Y. & Hemberg, M. Flexible comparison of batch correction methods for single-cell RNA-seq using BatchBench. Nucleic Acids Res. 49, e42 (2021).","journal-title":"Nucleic Acids Res."},{"key":"943_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1850-9","volume":"21","author":"HTN Tran","year":"2020","unstructured":"Tran, H. T. N. et al. A benchmark of batch-effect correction methods for single-cell RNA sequencing data. Genome Biol 21, 12 (2020).","journal-title":"Genome Biol"},{"key":"943_CR12","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1038\/s41591-023-02327-2","volume":"29","author":"L Sikkema","year":"2023","unstructured":"Sikkema, L. et al. An integrated cell atlas of the lung in health and disease. Nat. Med. 29, 1563\u20131577 (2023).","journal-title":"Nat. Med."},{"key":"943_CR13","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1038\/s41586-020-2922-4","volume":"587","author":"KJ Travaglini","year":"2020","unstructured":"Travaglini, K. J. et al. A molecular cell atlas of the human lung from single-cell RNA sequencing. Nature 587, 619\u2013625 (2020).","journal-title":"Nature"},{"key":"943_CR14","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1038\/s41591-019-0468-5","volume":"25","author":"FA Vieira Braga","year":"2019","unstructured":"Vieira Braga, F. A. et al. A cellular census of human lungs identifies novel cell states in health and in asthma. Nat. Med. 25, 1153\u20131163 (2019).","journal-title":"Nat. Med."},{"key":"943_CR15","doi-asserted-by":"publisher","first-page":"E1","DOI":"10.1038\/s41586-025-09247-w","volume":"643","author":"KS Smith","year":"2025","unstructured":"Smith, K. S. et al. Lack of evidence for the transitional cerebellar progenitor. Nature 643, E1\u2013E8 (2025).","journal-title":"Nature"},{"key":"943_CR16","doi-asserted-by":"publisher","unstructured":"Luo, Z. et al. Multimodal validation of the existence of transitional cerebellar progenitors in the human fetal cerebellum. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2025.06.01.657310 (2025).","DOI":"10.1101\/2025.06.01.657310"},{"key":"943_CR17","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1165\/rcmb.2020-0095MA","volume":"63","author":"JR Koenitzer","year":"2020","unstructured":"Koenitzer, J. R., Wu, H., Atkinson, J. J., Brody, S. L. & Humphreys, B. D. Single-nucleus RNA-sequencing profiling of mouse lung. reduced dissociation bias and improved rare cell-type detection compared with single-cell RNA sequencing. Am. J. Respir. Cell Mol. Biol. 63, 739\u2013747 (2020).","journal-title":"Am. J. Respir. Cell Mol. Biol."},{"key":"943_CR18","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1038\/s41592-023-01943-7","volume":"20","author":"SJ Fleming","year":"2023","unstructured":"Fleming, S. J. et al. Unsupervised removal of systematic background noise from droplet-based single-cell experiments using CellBender. Nat. Methods 20, 1323\u20131335 (2023).","journal-title":"Nat. Methods"},{"key":"943_CR19","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-023-09822-3","volume":"24","author":"M Berg","year":"2023","unstructured":"Berg, M. et al. FastCAR: fast correction for ambient RNA to facilitate differential gene expression analysis in single-cell RNA-sequencing datasets. BMC Genomics 24, 722 (2023).","journal-title":"BMC Genomics"},{"key":"943_CR20","doi-asserted-by":"publisher","unstructured":"Sheng, C. et al. Probabilistic machine learning ensures accurate ambient denoising in droplet-based single-cell omics. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2022.01.14.476312 (2022).","DOI":"10.1101\/2022.01.14.476312"},{"key":"943_CR21","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-1950-6","volume":"21","author":"S Yang","year":"2020","unstructured":"Yang, S. et al. Decontamination of ambient RNA in single-cell RNA-seq with DecontX. Genome Biol. 21, 57 (2020).","journal-title":"Genome Biol."},{"key":"943_CR22","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-024-03284-w","volume":"25","author":"W Wang","year":"2024","unstructured":"Wang, W. et al. scCDC: a computational method for gene-specific contamination detection and correction in single-cell and single-nucleus RNA-seq data. Genome Biol. 25, 136 (2024).","journal-title":"Genome Biol."},{"key":"943_CR23","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-023-02978-x","volume":"24","author":"P Janssen","year":"2023","unstructured":"Janssen, P. et al. The effect of background noise and its removal on the analysis of single-cell expression data. Genome Biol. 24, 140 (2023).","journal-title":"Genome Biol."},{"key":"943_CR24","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1093\/bioinformatics\/btp616","volume":"26","author":"MD Robinson","year":"2010","unstructured":"Robinson, M. D., McCarthy, D. J. & Smyth, G. K. edgeR: a Bioconductor package for differential expression analysis of digital gene expression data. Bioinformatics 26, 139\u2013140 (2010).","journal-title":"Bioinformatics"},{"key":"943_CR25","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv007","volume":"43","author":"ME Ritchie","year":"2015","unstructured":"Ritchie, M. E. et al. limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 43, e47 (2015).","journal-title":"Nucleic Acids Res."},{"key":"943_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-017-02554-5","volume":"9","author":"D Risso","year":"2018","unstructured":"Risso, D., Perraudeau, F., Gribkova, S., Dudoit, S. & Vert, J.-P. A general and flexible method for signal extraction from single-cell RNA-seq data. Nat. Commun. 9, 284 (2018).","journal-title":"Nat. Commun."},{"key":"943_CR27","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-022-02601-5","volume":"23","author":"R Jiang","year":"2022","unstructured":"Jiang, R., Sun, T., Song, D. & Li, J. J. Statistics or biology: the zero-inflation controversy about scRNA-seq data. Genome Biol. 23, 31 (2022).","journal-title":"Genome Biol."},{"key":"943_CR28","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-02096-y","volume":"21","author":"TH Kim","year":"2020","unstructured":"Kim, T. H., Zhou, X. & Chen, M. Demystifying \u201cdrop-outs\u201d in single-cell UMI data. Genome Biol. 21, 196 (2020).","journal-title":"Genome Biol."},{"key":"943_CR29","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1038\/s41588-021-00873-4","volume":"53","author":"A Sarkar","year":"2021","unstructured":"Sarkar, A. & Stephens, M. Separating measurement and expression models clarifies confusion in single-cell RNA sequencing analysis. Nat. Genet. 53, 770\u2013777 (2021).","journal-title":"Nat. Genet."},{"key":"943_CR30","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1038\/s41587-019-0379-5","volume":"38","author":"V Svensson","year":"2020","unstructured":"Svensson, V. Droplet scRNA-seq is not zero-inflated. Nat. Biotechnol. 38, 147\u2013150 (2020).","journal-title":"Nat. Biotechnol."},{"key":"943_CR31","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-016-0947-7","volume":"17","author":"ATL Lun","year":"2016","unstructured":"Lun, A. T. L., Bach, K. & Marioni, J. C. Pooling across cells to normalize single-cell RNA sequencing data with many zero counts. Genome Biol. 17, 75 (2016).","journal-title":"Genome Biol."},{"key":"943_CR32","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1874-1","volume":"20","author":"C Hafemeister","year":"2019","unstructured":"Hafemeister, C. & Satija, R. Normalization and variance stabilization of single-cell RNA-seq data using regularized negative binomial regression. Genome Biol. 20, 296 (2019).","journal-title":"Genome Biol."},{"key":"943_CR33","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1038\/s41576-023-00586-w","volume":"24","author":"L Heumos","year":"2023","unstructured":"Heumos, L. et al. Best practices for single-cell analysis across modalities. Nat. Rev. Genet. 24, 550\u2013572 (2023).","journal-title":"Nat. Rev. Genet."},{"key":"943_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12266-7","volume":"10","author":"B Vieth","year":"2019","unstructured":"Vieth, B., Parekh, S., Ziegenhain, C., Enard, W. & Hellmann, I. A systematic evaluation of single cell RNA-seq analysis pipelines. Nat. Commun. 10, 4667 (2019).","journal-title":"Nat. Commun."},{"key":"943_CR35","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.cels.2019.03.010","volume":"8","author":"MB Cole","year":"2019","unstructured":"Cole, M. B. et al. Performance assessment and selection of normalization procedures for single-cell RNA-seq. Cell Syst. 8, 315\u2013328.e8 (2019).","journal-title":"Cell Syst."},{"key":"943_CR36","doi-asserted-by":"publisher","first-page":"2223","DOI":"10.1093\/bioinformatics\/btab085","volume":"37","author":"AS Booeshaghi","year":"2021","unstructured":"Booeshaghi, A. S. & Pachter, L. Normalization of single-cell RNA-seq counts by log(x + 1) or log(1 + x). Bioinformatics 37, 2223\u20132224 (2021).","journal-title":"Bioinformatics"},{"key":"943_CR37","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1038\/nmeth.2645","volume":"10","author":"P Brennecke","year":"2013","unstructured":"Brennecke, P. et al. Accounting for technical noise in single-cell RNA-seq experiments. Nat. Methods 10, 1093\u20131095 (2013).","journal-title":"Nat. Methods"},{"key":"943_CR38","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-016-1010-4","volume":"17","author":"L Jiang","year":"2016","unstructured":"Jiang, L., Chen, H., Pinello, L. & Yuan, G.-C. GiniClust: detecting rare cell types from single-cell gene expression data with Gini index. Genome Biol. 17, 144 (2016).","journal-title":"Genome Biol."},{"key":"943_CR39","doi-asserted-by":"publisher","first-page":"2865","DOI":"10.1093\/bioinformatics\/bty1044","volume":"35","author":"TS Andrews","year":"2019","unstructured":"Andrews, T. S. & Hemberg, M. M3Drop: dropout-based feature selection for scRNASeq. Bioinformatics 35, 2865\u20132867 (2019).","journal-title":"Bioinformatics"},{"key":"943_CR40","doi-asserted-by":"publisher","first-page":"4841","DOI":"10.1016\/j.cell.2022.11.005","volume":"185","author":"P He","year":"2022","unstructured":"He, P. et al. A human fetal lung cell atlas uncovers proximal-distal gradients of differentiation and key regulators of epithelial fates. Cell 185, 4841\u20134860.e25 (2022).","journal-title":"Cell"},{"key":"943_CR41","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26085-2","volume":"12","author":"B Ranjan","year":"2021","unstructured":"Ranjan, B. et al. DUBStepR is a scalable correlation-based feature selection method for accurately clustering single-cell data. Nat. Commun. 12, 5849 (2021).","journal-title":"Nat. Commun."},{"key":"943_CR42","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/j.neuron.2017.09.026","volume":"96","author":"YE Wu","year":"2017","unstructured":"Wu, Y. E., Pan, L., Zuo, Y., Li, X. & Hong, W. Detecting activated cell populations using single-cell RNA-seq. Neuron 96, 313\u2013329.e6 (2017).","journal-title":"Neuron"},{"key":"943_CR43","doi-asserted-by":"publisher","DOI":"10.15252\/msb.202211147","volume":"19","author":"A Neuschulz","year":"2023","unstructured":"Neuschulz, A. et al. A single-cell RNA labeling strategy for measuring stress response upon tissue dissociation. Mol. Syst. Biol. 19, e11147 (2023).","journal-title":"Mol. Syst. Biol."},{"key":"943_CR44","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1126\/science.aad0501","volume":"352","author":"I Tirosh","year":"2016","unstructured":"Tirosh, I. et al. Dissecting the multicellular ecosystem of metastatic melanoma by single-cell RNA-seq. Science 352, 189\u2013196 (2016).","journal-title":"Science"},{"key":"943_CR45","doi-asserted-by":"publisher","first-page":"eaay3224","DOI":"10.1126\/science.aay3224","volume":"367","author":"J-E Park","year":"2020","unstructured":"Park, J.-E. et al. A cell atlas of human thymic development defines T cell repertoire formation. Science 367, eaay3224 (2020).","journal-title":"Science"},{"key":"943_CR46","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1038\/nbt.3102","volume":"33","author":"F Buettner","year":"2015","unstructured":"Buettner, F. et al. Computational analysis of cell-to-cell heterogeneity in single-cell RNA-sequencing data reveals hidden subpopulations of cells. Nat. Biotechnol. 33, 155\u2013160 (2015).","journal-title":"Nat. Biotechnol."},{"key":"943_CR47","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.ymeth.2015.06.021","volume":"85","author":"A Scialdone","year":"2015","unstructured":"Scialdone, A. et al. Computational assignment of cell-cycle stage from single-cell transcriptome data. Methods 85, 54\u201361 (2015).","journal-title":"Methods"},{"key":"943_CR48","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1038\/s41588-023-01421-y","volume":"55","author":"N Kumasaka","year":"2023","unstructured":"Kumasaka, N. et al. Mapping interindividual dynamics of innate immune response at single-cell resolution. Nat. Genet. 55, 1066\u20131075 (2023).","journal-title":"Nat. Genet."},{"key":"943_CR49","doi-asserted-by":"publisher","first-page":"e8746","DOI":"10.15252\/msb.20188746","volume":"15","author":"MD Luecken","year":"2019","unstructured":"Luecken, M. D. & Theis, F. J. Current best practices in single-cell RNA-seq analysis: a tutorial. Mol. Syst. Biol. 15, e8746 (2019).","journal-title":"Mol. Syst. Biol."},{"key":"943_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Sheng, Q., Wang, G., Xu, L. & Jin, S. Quantifying batch effects for individual genes in single-cell data. Nat. Comput. Sci. 5, 612\u2013620 (2025).","DOI":"10.1038\/s43588-025-00824-7"},{"key":"943_CR51","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1093\/bioinformatics\/btz625","volume":"36","author":"K Pola\u0144ski","year":"2020","unstructured":"Pola\u0144ski, K. et al. BBKNN: fast batch alignment of single cell transcriptomes. Bioinformatics 36, 964\u2013965 (2020).","journal-title":"Bioinformatics"},{"key":"943_CR52","doi-asserted-by":"publisher","unstructured":"Zhu, Q. et al. Revealing a coherent cell-state landscape across single-cell datasets with CONCORD. Nat. Biotechnol. https:\/\/doi.org\/10.1038\/s41587-025-02950-z (2026).","DOI":"10.1038\/s41587-025-02950-z"},{"key":"943_CR53","doi-asserted-by":"publisher","first-page":"i573","DOI":"10.1093\/bioinformatics\/btaa796","volume":"36","author":"AB Dincer","year":"2020","unstructured":"Dincer, A. B., Janizek, J. D. & Lee, S.-I. Adversarial deconfounding autoencoder for learning robust gene expression embeddings. Bioinformatics 36, i573\u2013i582 (2020).","journal-title":"Bioinformatics"},{"key":"943_CR54","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1089\/cmb.2020.0439","volume":"28","author":"S Ge","year":"2021","unstructured":"Ge, S., Wang, H., Alavi, A., Xing, E. & Bar-Joseph, Z. Supervised adversarial alignment of single-cell RNA-seq data. J. Comput. Biol. 28, 501\u2013513 (2021).","journal-title":"J. Comput. Biol."},{"key":"943_CR55","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1038\/nbt.4091","volume":"36","author":"L Haghverdi","year":"2018","unstructured":"Haghverdi, L., Lun, A. T. L., Morgan, M. D. & Marioni, J. C. Batch effects in single-cell RNA-sequencing data are corrected by matching mutual nearest neighbors. Nat. Biotechnol. 36, 421\u2013427 (2018).","journal-title":"Nat. Biotechnol."},{"key":"943_CR56","unstructured":"Lun, A. fastMNN description. GitHub https:\/\/marionilab.github.io\/FurtherMNN2018\/theory\/description.html (2019)."},{"key":"943_CR57","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1038\/s41587-019-0113-3","volume":"37","author":"B Hie","year":"2019","unstructured":"Hie, B., Bryson, B. & Berger, B. Efficient integration of heterogeneous single-cell transcriptomes using Scanorama. Nat. Biotechnol. 37, 685\u2013691 (2019).","journal-title":"Nat. Biotechnol."},{"key":"943_CR58","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.1016\/j.cell.2019.05.031","volume":"177","author":"T Stuart","year":"2019","unstructured":"Stuart, T. et al. Comprehensive integration of single-cell data. Cell 177, 1888\u20131902.e21 (2019).","journal-title":"Cell"},{"key":"943_CR59","doi-asserted-by":"publisher","first-page":"9775","DOI":"10.1073\/pnas.1820006116","volume":"116","author":"Y Lin","year":"2019","unstructured":"Lin, Y. et al. scMerge leverages factor analysis, stable expression, and pseudoreplication to merge multiple single-cell RNA-seq datasets. Proc. Natl Acad. Sci. USA 116, 9775\u20139784 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"943_CR60","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1093\/bioinformatics\/btab821","volume":"38","author":"X Wang","year":"2022","unstructured":"Wang, X., Wang, J., Zhang, H., Huang, S. & Yin, Y. HDMC: a novel deep learning-based framework for removing batch effects in single-cell RNA-seq data. Bioinformatics 38, 1295\u20131303 (2022).","journal-title":"Bioinformatics"},{"key":"943_CR61","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1764-6","volume":"20","author":"T Wang","year":"2019","unstructured":"Wang, T. et al. BERMUDA: a novel deep transfer learning method for single-cell RNA sequencing batch correction reveals hidden high-resolution cellular subtypes. Genome Biol. 20, 165 (2019).","journal-title":"Genome Biol."},{"key":"943_CR62","doi-asserted-by":"publisher","first-page":"1873","DOI":"10.1016\/j.cell.2019.05.006","volume":"177","author":"JD Welch","year":"2019","unstructured":"Welch, J. D. et al. Single-cell multi-omic integration compares and contrasts features of brain cell identity. Cell 177, 1873\u20131887.e17 (2019).","journal-title":"Cell"},{"key":"943_CR63","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15851-3","volume":"11","author":"X Li","year":"2020","unstructured":"Li, X. et al. Deep learning enables accurate clustering with batch effect removal in single-cell RNA-seq analysis. Nat. Commun. 11, 2338 (2020).","journal-title":"Nat. Commun."},{"key":"943_CR64","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.1101\/gr.271874.120","volume":"31","author":"J Lakkis","year":"2021","unstructured":"Lakkis, J. et al. A joint deep learning model enables simultaneous batch effect correction, denoising, and clustering in single-cell transcriptomics. Genome Res. 31, 1753\u20131766 (2021).","journal-title":"Genome Res."},{"key":"943_CR65","doi-asserted-by":"publisher","unstructured":"Moinfar, A. A. & Theis, F. J. Unsupervised deep disentangled representation of single-cell omics. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2024.11.06.622266 (2024).","DOI":"10.1101\/2024.11.06.622266"},{"key":"943_CR66","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1038\/s41592-019-0576-7","volume":"16","author":"M Amodio","year":"2019","unstructured":"Amodio, M. et al. Exploring single-cell data with deep multitasking neural networks. Nat. Methods 16, 1139\u20131145 (2019).","journal-title":"Nat. Methods"},{"key":"943_CR67","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/s42256-024-00934-3","volume":"7","author":"T Richter","year":"2024","unstructured":"Richter, T., Bahrami, M., Xia, Y., Fischer, D. S. & Theis, F. J. Delineating the effective use of self-supervised learning in single-cell genomics. Nat. Mach. Intell. 7, 68\u201378 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"943_CR68","doi-asserted-by":"publisher","first-page":"5876","DOI":"10.1016\/j.cell.2023.11.026","volume":"186","author":"C Xu","year":"2023","unstructured":"Xu, C. et al. Automatic cell-type harmonization and integration across Human Cell Atlas datasets. Cell 186, 5876\u20135891.e20 (2023).","journal-title":"Cell"},{"key":"943_CR69","doi-asserted-by":"publisher","DOI":"10.15252\/msb.20209620","volume":"17","author":"C Xu","year":"2021","unstructured":"Xu, C. et al. Probabilistic harmonization and annotation of single-cell transcriptomics data with deep generative models. Mol. Syst. Biol. 17, e9620 (2021).","journal-title":"Mol. Syst. Biol."},{"key":"943_CR70","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1038\/s41592-023-02035-2","volume":"20","author":"C De Donno","year":"2023","unstructured":"De Donno, C. et al. Population-level integration of single-cell datasets enables multi-scale analysis across samples. Nat. Methods 20, 1683\u20131692 (2023).","journal-title":"Nat. Methods"},{"key":"943_CR71","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1038\/s41592-025-02808-x","volume":"22","author":"P Boyeau","year":"2025","unstructured":"Boyeau, P. et al. Deep generative modeling of sample-level heterogeneity in single-cell genomics. Nat. Methods 22, 2264\u20132274 (2025).","journal-title":"Nat. Methods"},{"key":"943_CR72","doi-asserted-by":"publisher","unstructured":"Aliee, H. et al. inVAE: Conditionally invariant representation learning for generating multivariate single-cell reference maps. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2024.12.06.627196 (2024).","DOI":"10.1101\/2024.12.06.627196"},{"key":"943_CR73","doi-asserted-by":"publisher","unstructured":"Megas, S. et al. Integrating multi-covariate disentanglement with counterfactual analysis on synthetic data enables cell type discovery and counterfactual predictions. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2025.06.03.657578 (2025).","DOI":"10.1101\/2025.06.03.657578"},{"key":"943_CR74","doi-asserted-by":"publisher","unstructured":"Piran, Z., Cohen, N., Hoshen, Y. & Nitzan, M. Disentanglement of single-cell data with biolord. Nat. Biotechnol. https:\/\/doi.org\/10.1038\/s41587-023-02079-x (2024).","DOI":"10.1038\/s41587-023-02079-x"},{"key":"943_CR75","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45227-w","volume":"15","author":"Z Zhang","year":"2024","unstructured":"Zhang, Z., Zhao, X., Bindra, M., Qiu, P. & Zhang, X. scDisInFact: disentangled learning for integration and prediction of multi-batch multi-condition single-cell RNA-sequencing data. Nat. Commun. 15, 912 (2024).","journal-title":"Nat. Commun."},{"key":"943_CR76","doi-asserted-by":"publisher","first-page":"1998","DOI":"10.1038\/s41588-023-01523-7","volume":"55","author":"E Dann","year":"2023","unstructured":"Dann, E. et al. Precise identification of cell states altered in disease using healthy single-cell references. Nat. Genet. 55, 1998\u20132008 (2023).","journal-title":"Nat. Genet."},{"key":"943_CR77","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1038\/s41590-018-0276-y","volume":"20","author":"D Aran","year":"2019","unstructured":"Aran, D. et al. Reference-based analysis of lung single-cell sequencing reveals a transitional profibrotic macrophage. Nat. Immunol. 20, 163\u2013172 (2019).","journal-title":"Nat. Immunol."},{"key":"943_CR78","doi-asserted-by":"publisher","DOI":"10.1126\/science.abl5197","volume":"376","author":"C Dom\u00ednguez Conde","year":"2022","unstructured":"Dom\u00ednguez Conde, C. et al. Cross-tissue immune cell analysis reveals tissue-specific features in humans. Science 376, eabl5197 (2022).","journal-title":"Science"},{"key":"943_CR79","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1038\/s41587-021-01001-7","volume":"40","author":"M Lotfollahi","year":"2022","unstructured":"Lotfollahi, M. et al. Mapping single-cell data to reference atlases by transfer learning. Nat. Biotechnol. 40, 121\u2013130 (2022).","journal-title":"Nat. Biotechnol."},{"key":"943_CR80","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","volume":"618","author":"CV Theodoris","year":"2023","unstructured":"Theodoris, C. V. et al. Transfer learning enables predictions in network biology. Nature 618, 616\u2013624 (2023).","journal-title":"Nature"},{"key":"943_CR81","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1038\/s41592-024-02305-7","volume":"21","author":"M Hao","year":"2024","unstructured":"Hao, M. et al. Large-scale foundation model on single-cell transcriptomics. Nat. Methods 21, 1481\u20131491 (2024).","journal-title":"Nat. Methods"},{"key":"943_CR82","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1038\/s42256-022-00534-z","volume":"4","author":"F Yang","year":"2022","unstructured":"Yang, F. et al. scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data. Nat. Mach. Intell. 4, 852\u2013866 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"943_CR83","doi-asserted-by":"publisher","unstructured":"Cui, H. et al. scGPT: toward building a foundation model for single-cell multi-omics using generative AI. Nat. Methods https:\/\/doi.org\/10.1038\/s41592-024-02201-0 (2024).","DOI":"10.1038\/s41592-024-02201-0"},{"key":"943_CR84","doi-asserted-by":"publisher","unstructured":"Rosen, Y. et al. Universal cell embeddings: a foundation model for cell biology. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.11.28.568918 (2023).","DOI":"10.1101\/2023.11.28.568918"},{"key":"943_CR85","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1038\/s41422-024-01034-y","volume":"34","author":"X Yang","year":"2024","unstructured":"Yang, X. et al. GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model. Cell Res. 34, 830\u2013845 (2024).","journal-title":"Cell Res."},{"key":"943_CR86","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-58699-1","volume":"16","author":"J Kalfon","year":"2025","unstructured":"Kalfon, J., Samaran, J., Peyr\u00e9, G. & Cantini, L. scPRINT: pre-training on 50 million cells allows robust gene network predictions. Nat. Commun. 16, 3607 (2025).","journal-title":"Nat. Commun."},{"key":"943_CR87","doi-asserted-by":"publisher","unstructured":"Ding, J. et al. Toward a privacy-preserving predictive foundation model of single-cell transcriptomics with federated learning and tabular modeling. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2025.01.06.631427 (2025).","DOI":"10.1101\/2025.01.06.631427"},{"key":"943_CR88","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1038\/s41586-024-08411-y","volume":"638","author":"G Heimberg","year":"2025","unstructured":"Heimberg, G. et al. A cell atlas foundation model for scalable search of similar human cells. Nature 638, 1085\u20131094 (2025).","journal-title":"Nature"},{"key":"943_CR89","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-025-03574-x","volume":"26","author":"KZ Kedzierska","year":"2025","unstructured":"Kedzierska, K. Z., Crawford, L., Amini, A. P. & Lu, A. X. Zero-shot evaluation reveals limitations of single-cell foundation models. Genome Biol. 26, 101 (2025).","journal-title":"Genome Biol."},{"key":"943_CR90","doi-asserted-by":"publisher","unstructured":"Liu, T., Li, K., Wang, Y., Li, H. & Zhao, H. Evaluating the utilities of foundation models in single-cell data analysis. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.09.08.555192 (2024).","DOI":"10.1101\/2023.09.08.555192"},{"key":"943_CR91","doi-asserted-by":"publisher","first-page":"2343","DOI":"10.1016\/j.cell.2024.03.009","volume":"187","author":"M Lotfollahi","year":"2024","unstructured":"Lotfollahi, M., Yuhan Hao, Theis, F. J. & Satija, R. The future of rapid and automated single-cell data analysis using reference mapping. Cell 187, 2343\u20132358 (2024).","journal-title":"Cell"},{"key":"943_CR92","doi-asserted-by":"publisher","unstructured":"Hsu, J. et al. Comparing 10x Genomics single-cell 3\u2032 and 5\u2032 assay in short-and long-read sequencing. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2022.10.27.514084 (2022).","DOI":"10.1101\/2022.10.27.514084"},{"key":"943_CR93","doi-asserted-by":"publisher","first-page":"108189","DOI":"10.1016\/j.celrep.2020.108189","volume":"32","author":"N Thrupp","year":"2020","unstructured":"Thrupp, N. et al. Single-nucleus RNA-seq is not suitable for detection of microglial activation genes in humans. Cell Rep. 32, 108189 (2020).","journal-title":"Cell Rep."},{"key":"943_CR94","doi-asserted-by":"publisher","unstructured":"Huang, Y.-N. et al. The systematic assessment of completeness of public metadata accompanying omics studies. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2021.11.22.469640 (2022).","DOI":"10.1101\/2021.11.22.469640"},{"key":"943_CR95","doi-asserted-by":"publisher","unstructured":"Wang, H., Leskovec, J. & Regev, A. Limitations of cell embedding metrics assessed using drifting islands. Nat. Biotechnol. https:\/\/doi.org\/10.1038\/s41587-025-02702-z (2025).","DOI":"10.1038\/s41587-025-02702-z"},{"key":"943_CR96","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1038\/s41587-021-01033-z","volume":"40","author":"E Dann","year":"2022","unstructured":"Dann, E., Henderson, N. C., Teichmann, S. A., Morgan, M. D. & Marioni, J. C. Differential abundance testing on single-cell data using k-nearest neighbor graphs. Nat. Biotechnol. 40, 245\u2013253 (2022).","journal-title":"Nat. Biotechnol."},{"key":"943_CR97","doi-asserted-by":"publisher","unstructured":"Alsabbagh, A. R. et al. Foundation models meet imbalanced single-cell data when learning cell type annotations. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.10.24.563625 (2023).","DOI":"10.1101\/2023.10.24.563625"},{"key":"943_CR98","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1038\/s41587-023-02097-9","volume":"42","author":"H Maan","year":"2024","unstructured":"Maan, H. et al. Characterizing the impacts of dataset imbalance on single-cell data integration. Nat. Biotechnol. 42, 1899\u20131908 (2024).","journal-title":"Nat. Biotechnol."},{"key":"943_CR99","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TVCG.2022.3209408","volume":"29","author":"F Cheng","year":"2023","unstructured":"Cheng, F., Keller, M. S., Qu, H., Gehlenborg, N. & Wang, Q. Polyphony: an interactive transfer learning framework for single-cell data analysis. IEEE Trans. Vis. Comput. Graph. 29, 591\u2013601 (2023).","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"943_CR100","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1038\/s41556-021-00787-7","volume":"23","author":"D Osumi-Sutherland","year":"2021","unstructured":"Osumi-Sutherland, D. et al. Cell type ontologies of the Human Cell Atlas. Nat. Cell Biol. 23, 1129\u20131135 (2021).","journal-title":"Nat. Cell Biol."},{"key":"943_CR101","unstructured":"Metadata. Human Cell Atlas Data Portal https:\/\/data.humancellatlas.org\/metadata (2025)."},{"key":"943_CR102","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1093\/biostatistics\/kxj037","volume":"8","author":"WE Johnson","year":"2007","unstructured":"Johnson, W. E., Li, C. & Rabinovic, A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8, 118\u2013127 (2007).","journal-title":"Biostatistics"},{"key":"943_CR103","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","volume":"16","author":"I Korsunsky","year":"2019","unstructured":"Korsunsky, I. et al. Fast, sensitive and accurate integration of single-cell data with Harmony. Nat. Methods 16, 1289\u20131296 (2019).","journal-title":"Nat. Methods"},{"key":"943_CR104","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1038\/s41592-019-0494-8","volume":"16","author":"M Lotfollahi","year":"2019","unstructured":"Lotfollahi, M., Wolf, F. A. & Theis, F. J. scGen predicts single-cell perturbation responses. Nat. Methods 16, 715\u2013721 (2019).","journal-title":"Nat. Methods"},{"key":"943_CR105","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","volume":"15","author":"R Lopez","year":"2018","unstructured":"Lopez, R., Regier, J., Cole, M. B., Jordan, M. I. & Yosef, N. Deep generative modeling for single-cell transcriptomics. Nat. Methods 15, 1053\u20131058 (2018).","journal-title":"Nat. Methods"},{"key":"943_CR106","doi-asserted-by":"publisher","first-page":"i610","DOI":"10.1093\/bioinformatics\/btaa800","volume":"36","author":"M Lotfollahi","year":"2020","unstructured":"Lotfollahi, M., Naghipourfar, M., Theis, F. J. & Wolf, F. A. Conditional out-of-distribution generation for unpaired data using transfer VAE. Bioinformatics 36, i610\u2013i617 (2020).","journal-title":"Bioinformatics"},{"key":"943_CR107","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-59926-5","volume":"16","author":"Y Zeng","year":"2025","unstructured":"Zeng, Y. et al. CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells. Nat. Commun. 16, 4679 (2025).","journal-title":"Nat. Commun."}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00943-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00943-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00943-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T23:02:18Z","timestamp":1772060538000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00943-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":107,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["943"],"URL":"https:\/\/doi.org\/10.1038\/s43588-025-00943-1","relation":{},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]},"assertion":[{"value":"31 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"J.C.M. has been an employee of Genentech, Inc. since September 2022. S.A.T. is a scientific advisory board member of Bioptimus, ForeSite Labs, Xaira Therapeutics, Board observer and equity holder of TransitionBio, a co-founder, consultant and Board Director of Ensocell Therapeutics, a non-executive director of 10x Genomics and a part-time employee of GlaxoSmithKline.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}