{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T02:04:21Z","timestamp":1776132261621,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2020,3,16]],"date-time":"2020-03-16T00:00:00Z","timestamp":1584316800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U19MH114830"],"award-info":[{"award-number":["U19MH114830"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["CZF2019-002454"],"award-info":[{"award-number":["CZF2019-002454"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Single-cell RNA-seq makes possible the investigation of variability in gene expression among cells, and dependence of variation on cell type. Statistical inference methods for such analyses must be scalable, and ideally interpretable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present an approach based on a modification of a recently published highly scalable variational autoencoder framework that provides interpretability without sacrificing much accuracy. We demonstrate that our approach enables identification of gene programs in massive datasets. Our strategy, namely the learning of factor models with the auto-encoding variational Bayes framework, is not domain specific and may be useful for other applications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The factor model is available in the scVI package hosted at https:\/\/github.com\/YosefLab\/scVI\/.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Contact<\/jats:title>\n                    <jats:p>v@nxn.se<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa169","type":"journal-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T16:25:08Z","timestamp":1584116708000},"page":"3418-3421","source":"Crossref","is-referenced-by-count":186,"title":["Interpretable factor models of single-cell RNA-seq via variational autoencoders"],"prefix":"10.1093","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9217-2330","authenticated-orcid":false,"given":"Valentine","family":"Svensson","sequence":"first","affiliation":[{"name":"Division of Biology and Biological Engineering , California Institute of Technology, Pasadena, CA 91125, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9537-0845","authenticated-orcid":false,"given":"Adam","family":"Gayoso","sequence":"additional","affiliation":[{"name":"Center for Computational Biology"}]},{"given":"Nir","family":"Yosef","sequence":"additional","affiliation":[{"name":"Center for Computational Biology"},{"name":"Department of Electrical Engineering and Computer Sciences , University of California, Berkeley, CA 91125, USA"},{"name":"Chan Zuckerberg Biohub , San Francisco, CA 94158, USA"}]},{"given":"Lior","family":"Pachter","sequence":"additional","affiliation":[{"name":"Division of Biology and Biological Engineering , California Institute of Technology, Pasadena, CA 91125, USA"},{"name":"Department of Computing and Mathematical Sciences , California Institute of Technology, Pasadena, CA 91125, USA"}]}],"member":"286","published-online":{"date-parts":[[2020,3,16]]},"reference":[{"key":"2023062312020300900_btaa169-B1","first-page":"119","author":"Ainsworth","year":"2018"},{"key":"2023062312020300900_btaa169-B2","first-page":"114","author":"Andrews","year":"2017"},{"key":"2023062312020300900_btaa169-B3","doi-asserted-by":"crossref","first-page":"2586","DOI":"10.1128\/MCB.22.8.2586-2597.2002","article-title":"Cripto-1 activates Nodal- and ALK4-dependent and -independent signaling pathways in mammary epithelial cells","volume":"22","author":"Bianco","year":"2002","journal-title":"Mol. Cell. Biol"},{"key":"2023062312020300900_btaa169-B4","doi-asserted-by":"crossref","first-page":"4164","DOI":"10.1073\/pnas.0308531101","article-title":"Metagenes and molecular pattern discovery using matrix factorization","volume":"101","author":"Brunet","year":"2004","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023062312020300900_btaa169-B5","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1186\/s13059-017-1334-8","article-title":"F-scLVM: scalable and versatile factor analysis for single-cell RNA-Seq","volume":"18","author":"Buettner","year":"2017","journal-title":"Genome Biol"},{"key":"2023062312020300900_btaa169-B6","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1038\/s41586-019-0969-x","article-title":"The single-cell transcriptional landscape of mammalian organogenesis","volume":"566","author":"Cao","year":"2019","journal-title":"Nature"},{"key":"2023062312020300900_btaa169-B7","doi-asserted-by":"crossref","first-page":"4011","DOI":"10.1093\/bioinformatics\/btz177","article-title":"Probabilistic count matrix factorization for single cell expression data analysis","volume":"35","author":"Durif","year":"2019","journal-title":"Bioinformatics"},{"key":"2023062312020300900_btaa169-B8","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1038\/s41467-018-07931-2","article-title":"Single-cell RNA-Seq denoising using a deep count autoencoder","volume":"10","author":"Eraslan","year":"2019","journal-title":"Nat. Commun"},{"key":"2023062312020300900_btaa169-B9","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.devcel.2010.02.012","article-title":"Resolution of cell fate decisions revealed by single-cell gene expression analysis from Zygote to blastocyst","volume":"18","author":"Guo","year":"2010","journal-title":"Dev. Cell"},{"key":"2023062312020300900_btaa169-B10","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1093\/biostatistics\/kxx053","article-title":"Missing data and technical variability in single-cell RNA-sequencing experiments","volume":"19","author":"Hicks","year":"2018","journal-title":"Biostatistics"},{"key":"2023062312020300900_btaa169-B11","first-page":"3","volume-title":"Advances in Neural Information Processing Systems 6","author":"Hinton","year":"1993"},{"key":"2023062312020300900_btaa169-B12","first-page":"448","author":"Ioffe","year":"2015"},{"key":"2023062312020300900_btaa169-B13","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1101\/gr.110882.110","article-title":"Characterization of the single-cell transcriptional landscape by highly multiplex RNA-seq","volume":"21","author":"Islam","year":"2011","journal-title":"Genome Res"},{"key":"2023062312020300900_btaa169-B14","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.20487","article-title":"Dynamics of embryonic stem cell differentiation inferred from single-cell transcriptomics show a series of transitions through discrete cell states","volume":"6","author":"Jang","year":"2017","journal-title":"eLife"},{"key":"2023062312020300900_btaa169-B15","author":"Kingma","year":"2013"},{"key":"2023062312020300900_btaa169-B16","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1002\/art.40398","article-title":"Transcriptional regulation of CD 4+ T cell differentiation in experimentally induced arthritis and rheumatoid arthritis","volume":"70","author":"Kondo","year":"2018","journal-title":"Arthrit. Rheumatol"},{"key":"2023062312020300900_btaa169-B17","doi-asserted-by":"crossref","first-page":"e1004224","DOI":"10.1371\/journal.pcbi.1004224","article-title":"Geometry of the gene expression space of individual cells","volume":"11","author":"Korem","year":"2015","journal-title":"PLoS Comput. Biol"},{"key":"2023062312020300900_btaa169-B18","doi-asserted-by":"crossref","first-page":"e8557","DOI":"10.15252\/msb.20188557","article-title":"De Novo gene signature identification from single-cell RNA-seq with hierarchical Poisson factorization","volume":"15","author":"Levitin","year":"2019","journal-title":"Mol. Syst. Biol"},{"key":"2023062312020300900_btaa169-B19","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1016\/j.celrep.2017.07.043","article-title":"Cell-type-specific gene programs of the normal human nephron define kidney cancer subtypes","volume":"20","author":"Lindgren","year":"2017","journal-title":"Cell Rep"},{"key":"2023062312020300900_btaa169-B20","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":"2023062312020300900_btaa169-B21","first-page":"3403","author":"Marino","year":"2018"},{"key":"2023062312020300900_btaa169-B22","first-page":"566","article-title":"Principal components analysis","volume":"6","author":"Pearson","year":"1901","journal-title":"London Edinburgh Dublin Philos. Mag. J"},{"key":"2023062312020300900_btaa169-B23","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1186\/s13059-015-0805-z","article-title":"ZIFA: dimensionality reduction for zero-inflated single-cell gene expression analysis","volume":"16","author":"Pierson","year":"2015","journal-title":"Genome Biol"},{"key":"2023062312020300900_btaa169-B24","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1038\/s41586-019-0933-9","article-title":"A single-cell molecular map of mouse gastrulation and early organogenesis","volume":"566","author":"Pijuan-Sala","year":"2019","journal-title":"Nature"},{"key":"2023062312020300900_btaa169-B25","author":"Plaut","year":"2018"},{"key":"2023062312020300900_btaa169-B26","first-page":"455","author":"Raychaudhuri","year":"2000"},{"key":"2023062312020300900_btaa169-B27","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1038\/s41467-017-02554-5","article-title":"A general and flexible method for signal extraction from single-cell RNA-Seq data","volume":"9","author":"Risso","year":"2018","journal-title":"Nat. Commun"},{"key":"2023062312020300900_btaa169-B28","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1038\/nrg3229","article-title":"Comparative studies of gene expression and the evolution of gene regulation","volume":"13","author":"Romero","year":"2012","journal-title":"Nat. Rev. Genet"},{"key":"2023062312020300900_btaa169-B29","author":"Rostom","year":"2017"},{"key":"2023062312020300900_btaa169-B30","author":"Srivastava","year":"2017"},{"key":"2023062312020300900_btaa169-B31","first-page":"249","author":"Stuart","year":"2003"},{"key":"2023062312020300900_btaa169-B32","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1038\/s41587-019-0379-5","article-title":"Droplet scRNA-Seq is not zero-inflated","volume":"38","author":"Svensson","year":"2020","journal-title":"Nat. Biotechnol"},{"key":"2023062312020300900_btaa169-B33","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1038\/nprot.2017.149","article-title":"Exponential scaling of single-cell RNA-Seq in the past decade","volume":"13","author":"Svensson","year":"2018","journal-title":"Nat. Protoc"},{"key":"2023062312020300900_btaa169-B34","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1146\/annurev-cellbio-100913-012908","article-title":"Comparative analysis of gene regulatory networks: from network reconstruction to evolution","volume":"31","author":"Thompson","year":"2015","journal-title":"Annu. Rev. Cell Dev. Biol"},{"key":"2023062312020300900_btaa169-B35","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1111\/1467-9868.00196","article-title":"Probabilistic principal component analysis","volume":"61","author":"Tipping","year":"1999","journal-title":"J. R. Soc. Ser. B Statist. Methodol"},{"key":"2023062312020300900_btaa169-B36","author":"Townes","year":"2019"},{"key":"2023062312020300900_btaa169-B37","first-page":"7","article-title":"Role of Oct4 in the early embryo development","volume":"3","author":"Wu","year":"2014","journal-title":"Cell Regen. (Lond.)"},{"key":"2023062312020300900_btaa169-B38","doi-asserted-by":"crossref","first-page":"e2888","DOI":"10.7717\/peerj.2888","article-title":"Detecting heterogeneity in single-cell RNA-Seq data by non-negative matrix factorization","volume":"5","author":"Zhu","year":"2017","journal-title":"PeerJ"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa169\/33040778\/btaa169.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/11\/3418\/50670669\/bioinformatics_36_11_3418.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/11\/3418\/50670669\/bioinformatics_36_11_3418.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T17:22:03Z","timestamp":1687627323000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/11\/3418\/5807606"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,3,16]]},"references-count":38,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2020,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa169","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/737601","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,6]]},"published":{"date-parts":[[2020,3,16]]}}}