{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:14:22Z","timestamp":1787008462202,"version":"build-2736575974"},"reference-count":61,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2023,8,12]],"date-time":"2023-08-12T00:00:00Z","timestamp":1691798400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Foundation","doi-asserted-by":"publisher","award":["NNF20OC0062606"],"award-info":[{"award-number":["NNF20OC0062606"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Foundation","doi-asserted-by":"publisher","award":["NNF20OC0059939"],"award-info":[{"award-number":["NNF20OC0059939"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Foundation","doi-asserted-by":"publisher","award":["NNF20OC0063268"],"award-info":[{"award-number":["NNF20OC0063268"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Learning low-dimensional representations of single-cell transcriptomics has become instrumental to its downstream analysis. The state of the art is currently represented by neural network models, such as variational autoencoders, which use a variational approximation of the likelihood for inference.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We here present the Deep Generative Decoder (DGD), a simple generative model that computes model parameters and representations directly via maximum a posteriori estimation. The DGD handles complex parameterized latent distributions naturally unlike variational autoencoders, which typically use a fixed Gaussian distribution, because of the complexity of adding other types. We first show its general functionality on a commonly used benchmark set, Fashion-MNIST. Secondly, we apply the model to multiple single-cell datasets. Here, the DGD learns low-dimensional, meaningful, and well-structured latent representations with sub-clustering beyond the provided labels. The advantages of this approach are its simplicity and its capability to provide representations of much smaller dimensionality than a comparable variational autoencoder.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>scDGD is available as a python package at https:\/\/github.com\/Center-for-Health-Data-Science\/scDGD. The remaining code is made available here: https:\/\/github.com\/Center-for-Health-Data-Science\/dgd.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad497","type":"journal-article","created":{"date-parts":[[2023,8,12]],"date-time":"2023-08-12T11:44:16Z","timestamp":1691840656000},"source":"Crossref","is-referenced-by-count":8,"title":["The Deep Generative Decoder: MAP estimation of representations improves modelling of single-cell RNA data"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6016-8337","authenticated-orcid":false,"given":"Viktoria","family":"Schuster","sequence":"first","affiliation":[{"name":"Center for Health Data Science, University of Copenhagen , 2200 Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5147-6282","authenticated-orcid":false,"given":"Anders","family":"Krogh","sequence":"additional","affiliation":[{"name":"Center for Health Data Science, University of Copenhagen , 2200 Copenhagen, Denmark"},{"name":"Department of Computer Science, University of Copenhagen , 2100 Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,8,12]]},"reference":[{"key":"2023090705532123700_btad497-B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450963","article-title":"A survey of unsupervised generative models for exploratory data analysis and representation learning","volume":"54","author":"Abukmeil","year":"2021","journal-title":"ACM Comput Surv"},{"key":"2023090705532123700_btad497-B2","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1093\/bioinformatics\/bty533","article-title":"GrandPrix: scaling up the Bayesian GPLVM for single-cell data","volume":"35","author":"Ahmed","year":"2019","journal-title":"Bioinformatics"},{"key":"2023090705532123700_btad497-B3","first-page":"1383","author":"Bai","year":"2022"},{"key":"2023090705532123700_btad497-B4","author":"Balestriero","year":"2021"},{"key":"2023090705532123700_btad497-B5","author":"Biewald","year":"2020"},{"key":"2023090705532123700_btad497-B6","first-page":"600","author":"Bojanowski","year":"2018"},{"key":"2023090705532123700_btad497-B7","author":"B\u00f6hm","year":"2022"},{"key":"2023090705532123700_btad497-B8","first-page":"7327","author":"Bond-Taylor","year":"2022"},{"key":"2023090705532123700_btad497-B9","author":"Bond-Taylor","year":"2021"},{"key":"2023090705532123700_btad497-B10","first-page":"617","author":"Collins","year":"2001"},{"key":"2023090705532123700_btad497-B11","first-page":"1078","author":"Cremer","year":"2018"},{"key":"2023090705532123700_btad497-B13","author":"Dilokthanakul","year":"2017"},{"key":"2023090705532123700_btad497-B14","doi-asserted-by":"crossref","first-page":"eabl5197","DOI":"10.1126\/science.abl5197","article-title":"Cross-tissue immune cell analysis reveals tissue-specific features in humans","volume":"376","author":"Dom\u00ednguez Conde","year":"2022","journal-title":"Science"},{"key":"2023090705532123700_btad497-B15","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1038\/s41587-021-01206-w","article-title":"A Python library for probabilistic analysis of single-cell omics data","volume":"40","author":"Gayoso","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2023090705532123700_btad497-B16","first-page":"2672","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow","year":"2014"},{"key":"2023090705532123700_btad497-B17","doi-asserted-by":"crossref","first-page":"4415","DOI":"10.1093\/bioinformatics\/btaa293","article-title":"scVAE: variational auto-encoders for single-cell gene expression data","volume":"36","author":"Gr\u00f8nbech","year":"2020","journal-title":"Bioinformatics"},{"key":"2023090705532123700_btad497-B18","doi-asserted-by":"crossref","first-page":"43992","DOI":"10.1109\/ACCESS.2020.2977671","article-title":"Variational autoencoder with optimizing Gaussian mixture model priors","volume":"8","author":"Guo","year":"2020","journal-title":"IEEE Access"},{"key":"2023090705532123700_btad497-B19","doi-asserted-by":"crossref","first-page":"11","DOI":"10.25080\/TCWV9851","volume-title":"Proceedings of the 7th Python in Science Conference","author":"Hagberg","year":"2008"},{"key":"2023090705532123700_btad497-B20","first-page":"1976","author":"Han","year":"2017"},{"key":"2023090705532123700_btad497-B21","first-page":"770","author":"He","year":"2016"},{"key":"2023090705532123700_btad497-B22","first-page":"6629","author":"Heusel","year":"2017"},{"key":"2023090705532123700_btad497-B23","first-page":"6840","author":"Ho","year":"2020"},{"key":"2023090705532123700_btad497-B24","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF01908075","article-title":"Comparing partitions","volume":"2","author":"Hubert","year":"1985","journal-title":"J Classif"},{"key":"2023090705532123700_btad497-B25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3527850","article-title":"Generative adversarial networks for face generation: a survey","volume":"55","author":"Kammoun","year":"2022","journal-title":"ACM Comput Surv"},{"key":"2023090705532123700_btad497-B26","author":"Kingma","year":"2013"},{"key":"2023090705532123700_btad497-B27","first-page":"46","author":"Lalchand","year":"2022"},{"key":"2023090705532123700_btad497-B28","first-page":"329","author":"Lawrence","year":"2003"},{"key":"2023090705532123700_btad497-B29","volume-title":"A Tutorial on Energy-Based Learning","author":"Lecun","year":"2006"},{"key":"2023090705532123700_btad497-B30","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans Inform Theory"},{"key":"2023090705532123700_btad497-B31","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"Lopez","year":"2018","journal-title":"Nat Methods"},{"key":"2023090705532123700_btad497-B32","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":"2023090705532123700_btad497-B33","first-page":"1089","author":"Mohamed","year":"2008"},{"key":"2023090705532123700_btad497-B34","first-page":"120","volume-title":"Percolate: An Exponential Family JIVE Model to Design DNA-Based Predictors of Drug Response","author":"Mourragui","year":"2023"},{"key":"2023090705532123700_btad497-B35","first-page":"8024","author":"Paszke","year":"2019"},{"key":"2023090705532123700_btad497-B36","author":"Radford","year":"2016"},{"key":"2023090705532123700_btad497-B37","author":"Radosavovic","year":"2020"},{"key":"2023090705532123700_btad497-B38","first-page":"1530","author":"Rezende","year":"2015"},{"key":"2023090705532123700_btad497-B39","author":"Schuster","year":"2021"},{"key":"2023090705532123700_btad497-B40","author":"Schuster","year":"2021"},{"key":"2023090705532123700_btad497-B41","author":"Seitzer","year":"2020"},{"key":"2023090705532123700_btad497-B42","doi-asserted-by":"crossref","first-page":"5684","DOI":"10.1038\/s41467-021-26017-0","article-title":"VEGA is an interpretable generative model for inferring biological network activity in single-cell transcriptomics","volume":"12","author":"Seninge","year":"2021","journal-title":"Nat Commun"},{"key":"2023090705532123700_btad497-B43","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1186\/s13059-019-1861-6","article-title":"Feature selection and dimension reduction for single-cell RNA-Seq based on a multinomial model","volume":"20","author":"Townes","year":"2019","journal-title":"Genome Biol"},{"key":"2023090705532123700_btad497-B44","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":"2023090705532123700_btad497-B45","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1038\/nature25741","article-title":"Population snapshots predict early haematopoietic and erythroid hierarchies","volume":"555","author":"Tusi","year":"2018","journal-title":"Nature"},{"key":"2023090705532123700_btad497-B46","first-page":"19667","author":"Vahdat","year":"2020"},{"key":"2023090705532123700_btad497-B47","first-page":"11287","author":"Vahdat","year":"2021"},{"key":"2023090705532123700_btad497-B48","first-page":"1747","volume-title":"Proceedings of the 33rd International Conference on Machine Learning, Vol. 48 of Proceedings of Machine Learning Research","author":"van den Oord","year":"2016"},{"key":"2023090705532123700_btad497-B49","first-page":"6309","author":"van den Oord","year":"2017"},{"key":"2023090705532123700_btad497-B50","first-page":"2579","article-title":"Visualizing high-dimensional data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2023090705532123700_btad497-B51","author":"Vaswani","year":"2017"},{"key":"2023090705532123700_btad497-B52","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1186\/s12859-020-03625-z","article-title":"A robust nonlinear low-dimensional manifold for single cell RNA-seq data","volume":"21","author":"Verma","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2023090705532123700_btad497-B53","author":"Virshup","year":"2021"},{"key":"2023090705532123700_btad497-B54","doi-asserted-by":"crossref","first-page":"101308","DOI":"10.1016\/j.csl.2021.101308","article-title":"Generative adversarial networks for speech processing: a review","volume":"72","author":"Wali","year":"2022","journal-title":"Comput Speech Lang"},{"key":"2023090705532123700_btad497-B55","first-page":"290","author":"Wei","year":"2022"},{"key":"2023090705532123700_btad497-B56","author":"Xiao","year":"2017"},{"key":"2023090705532123700_btad497-B57","author":"Xiao","year":"2019"},{"key":"2023090705532123700_btad497-B58","author":"Xu","year":"2023"},{"key":"2023090705532123700_btad497-B59","first-page":"1","author":"Yacoby"},{"key":"2023090705532123700_btad497-B61","author":"Zadeh","year":"2021"},{"key":"2023090705532123700_btad497-B62","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1126\/science.aaa1934","article-title":"Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq","volume":"347","author":"Zeisel","year":"2015","journal-title":"Science"},{"key":"2023090705532123700_btad497-B63","doi-asserted-by":"publisher","first-page":"14049","DOI":"10.1038\/ncomms14049","article-title":"Massively parallel digital transcriptional profiling of single cells","volume":"8","author":"Zheng","year":"2017","journal-title":"Nat Commun"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad497\/51102639\/btad497.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/9\/btad497\/51405404\/btad497.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/9\/btad497\/51405404\/btad497.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T20:56:33Z","timestamp":1729889793000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad497\/7241685"}},"subtitle":[],"editor":[{"given":"Valentina","family":"Boeva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,8,12]]},"references-count":61,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,9,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad497","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,9,1]]},"published":{"date-parts":[[2023,8,12]]},"article-number":"btad497"}}