scMaui: a widely applicable deep learning framework for single-cell multiomics integration in the presence of batch effects and missing data.
Autoencoders
Deep learning
Multi-omics
Single cell
Journal
BMC bioinformatics
ISSN: 1471-2105
Titre abrégé: BMC Bioinformatics
Pays: England
ID NLM: 100965194
Informations de publication
Date de publication:
06 Aug 2024
06 Aug 2024
Historique:
received:
25
08
2023
accepted:
23
07
2024
medline:
7
8
2024
pubmed:
7
8
2024
entrez:
6
8
2024
Statut:
epublish
Résumé
The recent advances in high-throughput single-cell sequencing have created an urgent demand for computational models which can address the high complexity of single-cell multiomics data. Meticulous single-cell multiomics integration models are required to avoid biases towards a specific modality and overcome sparsity. Batch effects obfuscating biological signals must also be taken into account. Here, we introduce a new single-cell multiomics integration model, Single-cell Multiomics Autoencoder Integration (scMaui) based on variational product-of-experts autoencoders and adversarial learning. scMaui calculates a joint representation of multiple marginal distributions based on a product-of-experts approach which is especially effective for missing values in the modalities. Furthermore, it overcomes limitations seen in previous VAE-based integration methods with regard to batch effect correction and restricted applicable assays. It handles multiple batch effects independently accepting both discrete and continuous values, as well as provides varied reconstruction loss functions to cover all possible assays and preprocessing pipelines. We demonstrate that scMaui achieves superior performance in many tasks compared to other methods. Further downstream analyses also demonstrate its potential in identifying relations between assays and discovering hidden subpopulations.
Identifiants
pubmed: 39107690
doi: 10.1186/s12859-024-05880-w
pii: 10.1186/s12859-024-05880-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
257Informations de copyright
© 2024. The Author(s).
Références
Macaulay IC, Ponting CP, Voet T. Single-Cell multiomics: multiple measurements from single cells. Trends Genet. 2017;33:155–68. https://doi.org/10.1016/j.tig.2016.12.003 .
doi: 10.1016/j.tig.2016.12.003
pubmed: 28089370
pmcid: 5303816
Stoeckius M, Hafemeister C, Stephenson W, Houck-Loomis B, Chattopadhyay PK, Swerdlow H, Satija R, Smibert P. Simultaneous epitope and transcriptome measurement in single cells. Nat Methods. 2017;14:865–8. https://doi.org/10.1038/nmeth.4380 .
doi: 10.1038/nmeth.4380
pubmed: 28759029
pmcid: 5669064
Clark SJ, Argelaguet R, Kapourani C-A, Stubbs TM, Lee HJ, Alda-Catalinas C, Krueger F, Sanguinetti G, Kelsey G, Marioni JC, et al. scNMT-seq enables joint profiling of chromatin accessibility DNA methylation and transcription in single cells. Nat Commun. 2018;9:781. https://doi.org/10.1038/s41467-018-03149-4 .
doi: 10.1038/s41467-018-03149-4
pubmed: 29472610
pmcid: 5823944
Priego N, Zhu L, Monteiro C, Mulders M, Wasilewski D, Bindeman W, Doglio L, Martínez L, Martínez-Saez E, et al. STAT3 labels a subpopulation of reactive astrocytes required for brain metastasis. Nat Med. 2018;24:1024–35. https://doi.org/10.1038/s41591-018-0044-4 .
doi: 10.1038/s41591-018-0044-4
pubmed: 29892069
Keshava N, Toh TS, Yuan H, Yang B, Menden MP, Wang D. Defining subpopulations of differential drug response to reveal novel target populations. NPJ Syst Biol Appl. 2019;5:36. https://doi.org/10.1038/s41540-019-0113-4 .
doi: 10.1038/s41540-019-0113-4
pubmed: 31602313
pmcid: 6776548
Wu K, Lin K, Li X, Yuan X, Xu P, Ni P, Xu D. Redefining tumor-associated macrophage subpopulations and functions in the tumor microenvironment. Front Immunol. 2020;11:1731. https://doi.org/10.3389/fimmu.2020.01731 .
doi: 10.3389/fimmu.2020.01731
pubmed: 32849616
pmcid: 7417513
Lewis SM, Asselin-Labat M-L, Nguyen Q, Berthelet J, Tan X, Wimmer VC, Merino D, Rogers KL, Naik SH. Spatial omics and multiplexed imaging to explore cancer biology. Nat Methods. 2021;18:997–1012. https://doi.org/10.1038/s41592-021-01203-6 .
doi: 10.1038/s41592-021-01203-6
pubmed: 34341583
Argelaguet R, Arnol D, Bredikhin D, Deloro Y, Velten B, Marioni JC, Stegle O. MOFA+: a statistical framework for comprehensive integration of multi-modal single-cell data. Genome Biol. 2020;21:111. https://doi.org/10.1186/s13059-020-02015-1 .
doi: 10.1186/s13059-020-02015-1
pubmed: 32393329
pmcid: 7212577
Gayoso A, Steier Z, Lopez R, Regier J, Nazor KL, Streets A, Yosef N. Joint probabilistic modeling of single-cell multi-omic data with totalVI. Nat Methods. 2021;18:272–82. https://doi.org/10.1038/s41592-020-01050-x .
doi: 10.1038/s41592-020-01050-x
pubmed: 33589839
pmcid: 7954949
Stuart T, Butler A, Hoffman P, Hafemeister C, Papalexi E, Mauck WM, Hao Y, Stoeckius M, Smibert P, Satija R. Comprehensive integration of single-cell data. Cell. 2019;177:1888-1902.e21. https://doi.org/10.1016/j.cell.2019.05.031 .
doi: 10.1016/j.cell.2019.05.031
pubmed: 31178118
pmcid: 6687398
Adossa N, Khan S, Rytkönen KT, Elo LL. Computational strategies for single-cell multi-omics integration. Comput Struct Biotechnol J. 2021;19:2588–96. https://doi.org/10.1016/j.csbj.2021.04.060 .
doi: 10.1016/j.csbj.2021.04.060
pubmed: 34025945
pmcid: 8114078
Long Z, Sun C, Tang M, Wang Y, Ma J, Yu J, Wei J, Ma J, Wang B, Xie Q, et al. Single-cell multiomics analysis reveals regulatory programs in clear cell renal cell carcinoma. Cell Discov. 2022;8:68. https://doi.org/10.1038/s41421-022-00415-0 .
doi: 10.1038/s41421-022-00415-0
pubmed: 35853872
pmcid: 9296597
Fasolino M, Schwartz GW, Patil AR, Mongia A, Golson ML, Wang YJ, Morgan A, Liu C, Schug J, Liu J, et al. Single-cell multi-omics analysis of human pancreatic islets reveals novel cellular states in type 1 diabetes. Nat Metab. 2022;4:284–99. https://doi.org/10.1038/s42255-022-00531-x .
doi: 10.1038/s42255-022-00531-x
pubmed: 35228745
pmcid: 8938904
Yan R, Gu C, You D, Huang Z, Qian J, Yang Q, Cheng X, Zhang L, Wang H, Wang P, et al. Decoding dynamic epigenetic landscapes in human oocytes using single-cell multi-omics sequencing. Cell Stem Cell. 2021;28:1641-1656.e7. https://doi.org/10.1016/j.stem.2021.04.012 .
doi: 10.1016/j.stem.2021.04.012
pubmed: 33957080
Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv. https://doi.org/10.48550/arxiv.1312.6114 .
Zuo C, Dai H, Chen L. Deep cross-omics cycle attention model for joint analysis of single-cell multi-omics data. Bioinformatics. 2021. https://doi.org/10.1093/bioinformatics/btab403 .
doi: 10.1093/bioinformatics/btab403
pubmed: 34629071
pmcid: 8504052
Zuo C, Chen L. Deep-joint-learning analysis model of single cell transcriptome and open chromatin accessibility data. Brief Bioinform. 2021. https://doi.org/10.1093/bib/bbaa287 .
doi: 10.1093/bib/bbaa287
pubmed: 34347021
Minoura K, Abe K, Nam H, Nishikawa H, Shimamura T. A mixture-of-experts deep generative model for integrated analysis of single-cell multiomics data. Cell Rep Methods. 2021;1: 100071. https://doi.org/10.1016/j.crmeth.2021.100071 .
doi: 10.1016/j.crmeth.2021.100071
pubmed: 35474667
pmcid: 9017195
Gong B, Zhou Y, Purdom E. Cobolt: integrative analysis of multimodal single-cell sequencing data. Genome Biol. 2021;22:351. https://doi.org/10.1186/s13059-021-02556-z .
doi: 10.1186/s13059-021-02556-z
pubmed: 34963480
pmcid: 8715620
Lee C, van der Schaar M (2021) A variational information bottleneck approach to multi-omics data integration. arXiv. https://doi.org/10.48550/arxiv.2102.03014
Lotfollahi M, Litinetskaya A, Theis FJ. Multigrate: single-cell multi-omic data integration. BioRxiv. 2022. https://doi.org/10.1101/2022.03.16.484643 .
doi: 10.1101/2022.03.16.484643
Brombacher E, Hackenberg M, Kreutz C, Binder H, Treppner M. The performance of deep generative models for learning joint embeddings of single-cell multi-omics data. Front Mol Biosci. 2022;9: 962644. https://doi.org/10.3389/fmolb.2022.962644 .
doi: 10.3389/fmolb.2022.962644
pubmed: 36387277
pmcid: 9643784
Cao Z-J, Gao G. Multi-omics single-cell data integration and regulatory inference with graph-linked embedding. Nat Biotechnol. 2022;40:1458–66. https://doi.org/10.1038/s41587-022-01284-4 .
doi: 10.1038/s41587-022-01284-4
pubmed: 35501393
pmcid: 9546775
Kopp W, Akalin A, Ohler U. Simultaneous dimensionality reduction and integration for single-cell ATAC-seq data using deep learning. Nat Mach Intell. 2022;4:162–8. https://doi.org/10.1038/s42256-022-00443-1 .
doi: 10.1038/s42256-022-00443-1
Luecken MD, Burkhardt DB, Cannoodt R, Lance C, Agrawal A, Aliee H, Chen AT, Deconinck L, Detweiler AM, Granados AA, et al. (2021) A sandbox for prediction and integration of dna, rna, and proteins in single cells. In: Thirty-fifth conference on neural information processing systems datasets and benchmarks track (Round 2)
Ma S, Zhang B, LaFave LM, Earl AS, Chiang Z, Hu Y, Ding J, Brack A, Kartha VK, Tay T, et al. Chromatin potential identified by shared single-cell profiling of RNA and chromatin. Cell. 2020;183:1103-1116.e20. https://doi.org/10.1016/j.cell.2020.09.056 .
doi: 10.1016/j.cell.2020.09.056
pubmed: 33098772
pmcid: 7669735
Robinette ML, Colonna M. Immune modules shared by innate lymphoid cells and T cells. J Allergy Clin Immunol. 2016;138:1243–51. https://doi.org/10.1016/j.jaci.2016.09.006 .
doi: 10.1016/j.jaci.2016.09.006
pubmed: 27817796
pmcid: 5111630
Vivier E, Artis D, Colonna M, Diefenbach A, Di Santo JP, Eberl G, Koyasu S, Locksley RM, McKenzie ANJ, Mebius RE, et al. Innate lymphoid cells: 10 years on. Cell. 2018;174:1054–66. https://doi.org/10.1016/j.cell.2018.07.017 .
doi: 10.1016/j.cell.2018.07.017
pubmed: 30142344
Vandereyken K, Sifrim A, Thienpont B, Voet T. Methods and applications for single-cell and spatial multi-omics. Nat Rev Genet. 2023;24:494–515. https://doi.org/10.1038/s41576-023-00580-2 .
doi: 10.1038/s41576-023-00580-2
pubmed: 36864178
Ashuach T, Gabitto MI, Koodli RV, Saldi G-A, Jordan MI, Yosef N. MultiVI: deep generative model for the integration of multimodal data. Nat Methods. 2023;20:1222–31. https://doi.org/10.1038/s41592-023-01909-9 .
doi: 10.1038/s41592-023-01909-9
pubmed: 37386189
pmcid: 10406609
Hao Y, Hao S, Andersen-Nissen E, Mauck WM, Zheng S, Butler A, Lee MJ, Wilk AJ, Darby C, Zager M, et al. Integrated analysis of multimodal single-cell data. Cell. 2021;184:3573–87. https://doi.org/10.1016/j.cell.2021.04.048 .
doi: 10.1016/j.cell.2021.04.048
pubmed: 34062119
pmcid: 8238499
Hao Y, Stuart T, Kowalski MH, Choudhary S, Hoffman P, Hartman A, Srivastava A, Molla G, Madad S, Fernandez-Granda C, et al. Dictionary learning for integrative, multimodal and scalable single-cell analysis. Nat Biotechnol. 2024;42:293–304. https://doi.org/10.1038/s41587-023-01767-y .
doi: 10.1038/s41587-023-01767-y
pubmed: 37231261
Sun Z, Tang Y, Zhang Y, Fang Y, Jia J, Zeng W, Fang D. Joint single-cell multiomic analysis in Wnt3a induced asymmetric stem cell division. Nat Commun. 2021;12:5941. https://doi.org/10.1038/s41467-021-26203-0 .
doi: 10.1038/s41467-021-26203-0
pubmed: 34642323
pmcid: 8511096
Chen C, Yu W, Alikarami F, Qiu Q, Chen C-H, Flournoy J, Gao P, Uzun Y, Fang L, Davenport JW, et al. Single-cell multiomics reveals increased plasticity, resistant populations, and stem-cell-like blasts in KMT2A-rearranged leukemia. Blood. 2022;139:2198–211. https://doi.org/10.1182/blood.2021013442 .
doi: 10.1182/blood.2021013442
pubmed: 34864916
pmcid: 8990373
Hu X, Hu Y, Wu F, Leung RWT, Qin J. Integration of single-cell multi-omics for gene regulatory network inference. Comput Struct Biotechnol J. 2020;18:1925–38. https://doi.org/10.1016/j.csbj.2020.06.033 .
doi: 10.1016/j.csbj.2020.06.033
pubmed: 32774787
pmcid: 7385034
Andreatta M, Corria-Osorio J, Müller S, Cubas R, Coukos G, Carmona SJ. Interpretation of T cell states from single-cell transcriptomics data using reference atlases. Nat Commun. 2021;12:2965. https://doi.org/10.1038/s41467-021-23324-4 .
doi: 10.1038/s41467-021-23324-4
pubmed: 34017005
pmcid: 8137700
Moris N, Pina C, Arias AM. Transition states and cell fate decisions in epigenetic landscapes. Nat Rev Genet. 2016;17:693–703. https://doi.org/10.1038/nrg.2016.98 .
doi: 10.1038/nrg.2016.98
pubmed: 27616569
Haghverdi L, Büttner M, Wolf FA, Buettner F, Theis FJ. Diffusion pseudotime robustly reconstructs lineage branching. Nat Methods. 2016;13:845–8. https://doi.org/10.1038/nmeth.3971 .
doi: 10.1038/nmeth.3971
pubmed: 27571553
Commons W (2022) File: hematopoiesis (human) diagram en.svg — Wikimedia Commons, the free media repository
Wolf FA, Hamey FK, Plass M, Solana J, Dahlin JS, Göttgens B, Rajewsky N, Simon L, Theis FJ. PAGA: graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells. Genome Biol. 2019;20:59. https://doi.org/10.1186/s13059-019-1663-x .
doi: 10.1186/s13059-019-1663-x
pubmed: 30890159
pmcid: 6425583
Lin DS, Tian L, Tomei S, Amann-Zalcenstein D, Baldwin TM, Weber TS, Schreuder J, Stonehouse OJ, Rautela J, Huntington ND, et al. Single-cell analyses reveal the clonal and molecular aetiology of Flt3L-induced emergency dendritic cell development. Nat Cell Biol. 2021;23:219–31. https://doi.org/10.1038/s41556-021-00636-7 .
doi: 10.1038/s41556-021-00636-7
pubmed: 33649477
Schlitzer A, Sivakamasundari V, Chen J, Sumatoh HRB, Schreuder J, Lum J, Malleret B, Zhang S, Larbi A, Zolezzi F, et al. Identification of cDC1- and cDC2-committed DC progenitors reveals early lineage priming at the common DC progenitor stage in the bone marrow. Nat Immunol. 2015;16:718–28. https://doi.org/10.1038/ni.3200 .
doi: 10.1038/ni.3200
pubmed: 26054720
Messerschmidt DM, Knowles BB, Solter D. DNA methylation dynamics during epigenetic reprogramming in the germline and preimplantation embryos. Genes Dev. 2014;28:812–28. https://doi.org/10.1101/gad.234294.113 .
doi: 10.1101/gad.234294.113
pubmed: 24736841
pmcid: 4003274
Jeong Y, de Andrade E, Sousa LB, Thalmeier D, Toth R, Ganslmeier M, Breuer K, Plass C, Lutsik P. Systematic evaluation of cell-type deconvolution pipelines for sequencing-based bulk DNA methylomes. Brief Bioinform. 2022. https://doi.org/10.1093/bib/bbac248 .
doi: 10.1093/bib/bbac248
pubmed: 35794707
pmcid: 9294431
Argelaguet R, Clark SJ, Mohammed H, Stapel LC, Krueger C, Kapourani C-A, Imaz-Rosshandler I, Lohoff T, Xiang Y, Hanna CW, et al. Multi-omics profiling of mouse gastrulation at single-cell resolution. Nature. 2019;576:487–91. https://doi.org/10.1038/s41586-019-1825-8 .
doi: 10.1038/s41586-019-1825-8
pubmed: 31827285
pmcid: 6924995
Bassalert C, Valverde-Estrella L, Chazaud C. Primitive endoderm differentiation: from specification to epithelialization. Curr Top Dev Biol. 2018;128:81–104. https://doi.org/10.1016/bs.ctdb.2017.12.001 .
doi: 10.1016/bs.ctdb.2017.12.001
pubmed: 29477172
Carlson BM, Carlson BM. Formation of germ layers and early derivatives. Human Embryol Devel Biol. 2014. https://doi.org/10.1016/B978-1-4557-2794-0.00005-X .
doi: 10.1016/B978-1-4557-2794-0.00005-X
Campbell KR, Steif A, Laks E, Zahn H, Lai D, McPherson A, Farahani H, Kabeer F, O’Flanagan C, Biele J, et al. clonealign: statistical integration of independent single-cell RNA and DNA sequencing data from human cancers. Genome Biol. 2019;20:54. https://doi.org/10.1186/s13059-019-1645-z .
doi: 10.1186/s13059-019-1645-z
pubmed: 30866997
pmcid: 6417140
Amodio M, Krishnaswamy S (2018) MAGAN: aligning biological manifolds. arXiv. https://doi.org/10.48550/arxiv.1803.00385 .
Wu M, Goodman N (2018) Multimodal generative models for scalable weakly-supervised learning. arXiv. https://doi.org/10.48550/arxiv.1802.05335
Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International conference on machine learning, p. 1180
Leek JT, Johnson WE, Parker HS, Fertig EJ, Jaffe AE, Zhang Y, Storey JD, Torres LC (2017) sva: surrogate variable analysis. Bioconductor R package, 3.50.0. https://doi.org/10.18129/b9.bioc.sva .
Lin Y, Ghazanfar S, Wang KYX, Gagnon-Bartsch JA, Lo KK, Su X, Han Z-G, Ormerod JT, Speed TP, Yang P, et al. scMerge leverages factor analysis, stable expression, and pseudoreplication to merge multiple single-cell RNA-seq datasets. Proc Natl Acad Sci USA. 2019;116:9775–84. https://doi.org/10.1073/pnas.1820006116 .
doi: 10.1073/pnas.1820006116
pubmed: 31028141
pmcid: 6525515
Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114
Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2013) Intriguing properties of neural networks. arXiv. https://doi.org/10.48550/arxiv.1312.6199 .
Lun ATL, McCarthy DJ, Marioni JC. A step-by-step workflow for low-level analysis of single-cell RNA-seq data with Bioconductor [version 2; peer review: 3 approved 2 approved with reservations]. FRes. 2016;5:2122. https://doi.org/10.12688/f1000research.9501.2 .
doi: 10.12688/f1000research.9501.2
Wolf FA, Angerer P, Theis FJ. SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 2018;19:15. https://doi.org/10.1186/s13059-017-1382-0 .
doi: 10.1186/s13059-017-1382-0
pubmed: 29409532
pmcid: 5802054
Dalby M, Rennie S, Andersson R. Fantom5 transcribed enhancers in Mm10. 2018. Zenodo. https://doi.org/10.5281/zenodo.1411211 .
Stuart T, Srivastava A, Madad S, Lareau CA, Satija R. Single-cell chromatin state analysis with Signac. Nat Methods. 2021;18:1333–41. https://doi.org/10.1038/s41592-021-01282-5 .
doi: 10.1038/s41592-021-01282-5
pubmed: 34725479
pmcid: 9255697
Lakkis J, Schroeder A, Su K, Lee MYY, Bashore AC, Reilly MP, Li M. A multi-use deep learning method for CITE-seq and single-cell RNA-seq data integration with cell surface protein prediction and imputation. Nat Mach Intell. 2022;4:940–52. https://doi.org/10.1038/s42256-022-00545-w .
doi: 10.1038/s42256-022-00545-w
pubmed: 36873621
pmcid: 9979929
Huizing G-J, Deutschmann IM, Peyré G, Cantini L. Paired single-cell multi-omics data integration with Mowgli. Nat Commun. 2023;14:7711. https://doi.org/10.1038/s41467-023-43019-2 .
doi: 10.1038/s41467-023-43019-2
pubmed: 38001063
pmcid: 10673889
Blondel VD, Guillaume J-L, Lambiotte R, Lefebvre E. Fast unfolding of communities in large networks. J Stat Mech. 2008;2008:P10008. https://doi.org/10.1088/1742-5468/2008/10/P10008 .
doi: 10.1088/1742-5468/2008/10/P10008
Levine JH, Simonds EF, Bendall SC, Davis KL, Amir ED, Tadmor MD, Litvin O, Fienberg HG, Jager A, Zunder ER, et al. Data-driven phenotypic dissection of AML reveals progenitor-like cells that correlate with prognosis. Cell. 2015;162:184–97. https://doi.org/10.1016/j.cell.2015.05.047 .
doi: 10.1016/j.cell.2015.05.047
pubmed: 26095251
pmcid: 4508757