{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:15:29Z","timestamp":1784013329317,"version":"3.55.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013603","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T00:00:00Z","timestamp":1761782400000}}],"reference-count":62,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    A major challenge in working with single-cell RNA sequencing data is the prevalence of \u201cdropout,\u201d when some transcripts\u2019 expression values are erroneously not captured. Addressing this issue, which produces zero-inflated count data, is crucial for many downstream data analyses including the inference of gene regulatory networks (GRNs). In this paper, we introduce two novel contributions. First, we propose Dropout Augmentation (DA), a simple but effective model regularization method to improve resilience to zero inflation in single-cell data by augmenting the data with synthetic dropout events. DA offers a new perspective to solve the \u201cdropout\u201d problem beyond imputation. Second, we present DAZZLE, a stabilized and robust version of the autoencoder-based structure equation model for GRN inference using the DA concept. Benchmark experiments illustrate the improved performance and increased stability of the proposed DAZZLE model over existing approaches. The practical application of the DAZZLE model on a longitudinal mouse microglia dataset containing over 15,000 genes illustrates its ability to handle real-world single cell data with minimal gene filtration. The improved robustness and stability of DAZZLE make it a practical and valuable addition to the toolkit for GRN inference from single-cell data. Finally, we propose that Dropout Augmentation may have wider applications beyond the GRN-inference problem. Project website:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/bcb.cs.tufts.edu\/DAZZLE\" xlink:type=\"simple\">https:\/\/bcb.cs.tufts.edu\/DAZZLE<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1013603","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:54:10Z","timestamp":1761328450000},"page":"e1013603","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improved gene regulatory network inference from single cell data with dropout augmentation"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3386-6076","authenticated-orcid":true,"given":"Hao","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3357-437X","authenticated-orcid":true,"given":"Donna K.","family":"Slonim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"issue":"14","key":"pcbi.1013603.ref001","doi-asserted-by":"crossref","first-page":"4935","DOI":"10.1073\/pnas.0502024102","article-title":"Gene regulatory networks","volume":"102","author":"E Davidson","year":"2005","journal-title":"Proc Natl Acad Sci U S A."},{"issue":"10","key":"pcbi.1013603.ref002","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1038\/nrm2503","article-title":"Modelling and analysis of gene regulatory networks","volume":"9","author":"G Karlebach","year":"2008","journal-title":"Nat Rev Mol Cell Biol."},{"issue":"6","key":"pcbi.1013603.ref003","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1098\/rsfs.2011.0053","article-title":"How to infer gene networks from expression profiles, revisited","volume":"1","author":"CA Penfold","year":"2011","journal-title":"Interface Focus."},{"key":"pcbi.1013603.ref004","doi-asserted-by":"crossref","first-page":"38","DOI":"10.3389\/fcell.2014.00038","article-title":"Gene regulatory networks and their applications: understanding biological and medical problems in terms of networks","volume":"2","author":"F Emmert-Streib","year":"2014","journal-title":"Front Cell Dev Biol."},{"issue":"4","key":"pcbi.1013603.ref005","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":"V Svensson","year":"2018","journal-title":"Nat Protoc."},{"issue":"2","key":"pcbi.1013603.ref006","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1038\/s41592-019-0690-6","article-title":"Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data","volume":"17","author":"A Pratapa","year":"2020","journal-title":"Nat Methods."},{"issue":"9","key":"pcbi.1013603.ref007","article-title":"Inferring regulatory networks from expression data using tree-based methods","volume":"5","author":"VA Huynh-Thu","year":"2010","journal-title":"PLoS One."},{"issue":"12","key":"pcbi.1013603.ref008","doi-asserted-by":"crossref","first-page":"2159","DOI":"10.1093\/bioinformatics\/bty916","article-title":"GRNBoost2 and Arboreto: efficient and scalable inference of gene regulatory networks","volume":"35","author":"T Moerman","year":"2019","journal-title":"Bioinformatics."},{"issue":"5","key":"pcbi.1013603.ref009","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1093\/bioinformatics\/btw729","article-title":"LEAP: constructing gene co-expression networks for single-cell RNA-sequencing data using pseudotime ordering","volume":"33","author":"AT Specht","year":"2017","journal-title":"Bioinformatics."},{"issue":"15","key":"pcbi.1013603.ref010","doi-asserted-by":"crossref","first-page":"2314","DOI":"10.1093\/bioinformatics\/btx194","article-title":"SCODE: an efficient regulatory network inference algorithm from single-cell RNA-Seq during differentiation","volume":"33","author":"H Matsumoto","year":"2017","journal-title":"Bioinformatics."},{"issue":"6","key":"pcbi.1013603.ref011","doi-asserted-by":"crossref","first-page":"110333","DOI":"10.1016\/j.celrep.2022.110333","article-title":"Network inference with Granger causality ensembles on single-cell transcriptomics","volume":"38","author":"A Deshpande","year":"2022","journal-title":"Cell Rep."},{"issue":"3","key":"pcbi.1013603.ref012","article-title":"Gene regulatory network inference from single-cell data using multivariate information measures","volume":"5","author":"TE Chan","year":"2017","journal-title":"Cell Syst."},{"issue":"11","key":"pcbi.1013603.ref013","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1038\/nmeth.4463","article-title":"SCENIC: single-cell regulatory network inference and clustering","volume":"14","author":"S Aibar","year":"2017","journal-title":"Nat Methods."},{"issue":"1","key":"pcbi.1013603.ref014","doi-asserted-by":"crossref","first-page":"3064","DOI":"10.1038\/s41467-023-38637-9","article-title":"Inference of cell type-specific gene regulatory networks on cell lineages from single cell omic datasets","volume":"14","author":"S Zhang","year":"2023","journal-title":"Nat Commun."},{"issue":"1","key":"pcbi.1013603.ref015","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1089\/cmb.2021.0437","article-title":"GRNUlar: a deep learning framework for recovering single-cell gene regulatory networks","volume":"29","author":"H Shrivastava","year":"2022","journal-title":"J Comput Biol."},{"issue":"1","key":"pcbi.1013603.ref016","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.1038\/s42003-022-04226-7","article-title":"NetREX-CF integrates incomplete transcription factor data with gene expression to reconstruct gene regulatory networks","volume":"5","author":"Y Wang","year":"2022","journal-title":"Commun Biol."},{"issue":"5","key":"pcbi.1013603.ref017","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0064832","article-title":"Passing messages between biological networks to refine predicted interactions","volume":"8","author":"K Glass","year":"2013","journal-title":"PLoS One."},{"issue":"7","key":"pcbi.1013603.ref018","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1038\/s43588-021-00099-8","article-title":"Modeling gene regulatory networks using neural network architectures","volume":"1","author":"H Shu","year":"2021","journal-title":"Nat Comput Sci."},{"key":"pcbi.1013603.ref019","unstructured":"Kingma DP, Welling M. Auto-encoding variational bayes. arXiv preprint 2013. https:\/\/arxiv.org\/abs\/1312.6114"},{"key":"pcbi.1013603.ref020","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1186\/s12918-016-0370-4","article-title":"Integrated single cell data analysis reveals cell specific networks and novel coactivation markers","volume":"10","author":"S Ghazanfar","year":"2016","journal-title":"BMC Syst Biol."},{"issue":"5","key":"pcbi.1013603.ref021","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1016\/j.cell.2015.04.044","article-title":"Droplet barcoding for single-cell transcriptomics applied to embryonic stem cells","volume":"161","author":"AM Klein","year":"2015","journal-title":"Cell."},{"key":"pcbi.1013603.ref022","doi-asserted-by":"crossref","first-page":"14049","DOI":"10.1038\/ncomms14049","article-title":"Massively parallel digital transcriptional profiling of single cells","volume":"8","author":"GXY Zheng","year":"2017","journal-title":"Nat Commun."},{"issue":"5","key":"pcbi.1013603.ref023","doi-asserted-by":"crossref","first-page":"102393","DOI":"10.1016\/j.isci.2021.102393","article-title":"Imputing single-cell RNA-seq data by combining graph convolution and autoencoder neural networks","volume":"24","author":"J Rao","year":"2021","journal-title":"iScience."},{"issue":"3","key":"pcbi.1013603.ref024","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae148","article-title":"scINRB: single-cell gene expression imputation with network regularization and bulk RNA-seq data","volume":"25","author":"Y Kang","year":"2024","journal-title":"Brief Bioinform."},{"issue":"1","key":"pcbi.1013603.ref025","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1038\/s41467-018-03405-7","article-title":"An accurate and robust imputation method scImpute for single-cell RNA-seq data","volume":"9","author":"WV Li","year":"2018","journal-title":"Nat Commun."},{"issue":"1","key":"pcbi.1013603.ref026","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1186\/s13059-019-1837-6","article-title":"DeepImpute: an accurate, fast, and scalable deep neural network method to impute single-cell RNA-seq data","volume":"20","author":"C Arisdakessian","year":"2019","journal-title":"Genome Biol."},{"key":"pcbi.1013603.ref027","article-title":"Imputation method for single-cell RNA-seq data using neural topic model","volume":"12","author":"Y Qi","year":"2022","journal-title":"Gigascience."},{"issue":"1","key":"pcbi.1013603.ref028","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1162\/neco.1995.7.1.108","article-title":"Training with noise is equivalent to tikhonov regularization","volume":"7","author":"CM Bishop","year":"1995","journal-title":"Neural Computation."},{"key":"pcbi.1013603.ref029","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint 2012. https:\/\/arxiv.org\/abs\/1207.0580"},{"key":"pcbi.1013603.ref030","unstructured":"Yu Y, Chen J, Gao T, Yu M. DAG-GNN: DAG structure learning with graph neural networks. arXiv preprint 2019. p. 7154\u201363."},{"issue":"11","key":"pcbi.1013603.ref031","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1089\/cmb.2024.0607","article-title":"From noise to knowledge: diffusion probabilistic model-based neural inference of gene regulatory networks","volume":"31","author":"H Zhu","year":"2024","journal-title":"J Comput Biol."},{"key":"pcbi.1013603.ref032","doi-asserted-by":"crossref","first-page":"617282","DOI":"10.3389\/fgene.2021.617282","article-title":"Evaluating the reproducibility of single-cell gene regulatory network inference algorithms","volume":"12","author":"Y Kang","year":"2021","journal-title":"Front Genet."},{"issue":"6","key":"pcbi.1013603.ref033","first-page":"665","article-title":"ppcor: an R package for a fast calculation to semi-partial correlation coefficients","volume":"22","author":"S Kim","year":"2015","journal-title":"Commun Stat Appl Methods."},{"issue":"2","key":"pcbi.1013603.ref034","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1093\/bioinformatics\/btx575","article-title":"SINCERITIES: inferring gene regulatory networks from time-stamped single cell transcriptional expression profiles","volume":"34","author":"N Papili Gao","year":"2018","journal-title":"Bioinformatics."},{"issue":"1","key":"pcbi.1013603.ref035","doi-asserted-by":"crossref","DOI":"10.1016\/j.immuni.2018.11.004","article-title":"Single-Cell RNA sequencing of microglia throughout the mouse lifespan and in the injured brain reveals complex cell-state changes","volume":"50","author":"TR Hammond","year":"2019","journal-title":"Immunity."},{"issue":"12","key":"pcbi.1013603.ref036","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.1525528113","article-title":"New tools for studying microglia in the mouse and human CNS","volume":"113","author":"ML Bennett","year":"2016","journal-title":"Proc Natl Acad Sci U S A."},{"issue":"7","key":"pcbi.1013603.ref037","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1038\/s41590-020-0707-4","article-title":"Novel Hexb-based tools for studying microglia in the CNS","volume":"21","author":"T Masuda","year":"2020","journal-title":"Nat Immunol."},{"key":"pcbi.1013603.ref038","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s40478-015-0203-5","article-title":"Induction of a common microglia gene expression signature by aging and neurodegenerative conditions: a co-expression meta-analysis","volume":"3","author":"IR Holtman","year":"2015","journal-title":"Acta Neuropathol Commun."},{"issue":"2","key":"pcbi.1013603.ref039","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1002\/alz.12389","article-title":"Diversity of transcriptomic microglial phenotypes in aging and Alzheimer\u2019s disease","volume":"18","author":"D Boche","year":"2022","journal-title":"Alzheimers Dement."},{"issue":"6","key":"pcbi.1013603.ref040","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1007\/s00401-021-02370-8","article-title":"Analyzing microglial phenotypes across neuropathologies: a practical guide","volume":"142","author":"M Schwabenland","year":"2021","journal-title":"Acta Neuropathol."},{"issue":"15","key":"pcbi.1013603.ref041","doi-asserted-by":"crossref","first-page":"2383","DOI":"10.3390\/cells11152383","article-title":"Profiling microglia through single-cell RNA sequencing over the course of development, aging, and disease","volume":"11","author":"S Pettas","year":"2022","journal-title":"Cells."},{"issue":"10","key":"pcbi.1013603.ref042","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1038\/s41419-020-03084-7","article-title":"CSF1R signaling is a regulator of pathogenesis in progressive MS","volume":"11","author":"N Hagan","year":"2020","journal-title":"Cell Death Dis."},{"key":"pcbi.1013603.ref043","doi-asserted-by":"crossref","first-page":"101865","DOI":"10.1016\/j.redox.2021.101865","article-title":"Apolipoprotein E deficiency induces a progressive increase in tissue iron contents with age in mice","volume":"40","author":"J Ma","year":"2021","journal-title":"Redox Biol."},{"issue":"1","key":"pcbi.1013603.ref044","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40478-021-01126-5","article-title":"Iron loading is a prominent feature of activated microglia in Alzheimer\u2019s disease patients","volume":"9","author":"B Kenkhuis","year":"2021","journal-title":"Acta Neuropathol Commun."},{"issue":"1","key":"pcbi.1013603.ref045","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s13045-018-0606-4","article-title":"MALAT1: a druggable long non-coding RNA for targeted anti-cancer approaches","volume":"11","author":"N Amodio","year":"2018","journal-title":"J Hematol Oncol."},{"issue":"2","key":"pcbi.1013603.ref046","doi-asserted-by":"crossref","DOI":"10.1002\/edm2.10","article-title":"MALAT1: a regulator of inflammatory cytokines in diabetic complications","volume":"1","author":"AD Gordon","year":"2018","journal-title":"Endocrinol Diabetes Metab."},{"issue":"1","key":"pcbi.1013603.ref047","article-title":"Long noncoding RNA MALAT1 contributes to inflammatory response of microglia following spinal cord injury via the modulation of a miR-199b\/IKK\u03b2\/NF-\u03baB signaling pathway","volume":"315","author":"H-J Zhou","year":"2018","journal-title":"Am J Physiol Cell Physiol."},{"issue":"1","key":"pcbi.1013603.ref048","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1186\/s13041-020-00656-8","article-title":"LncRNA MALAT1 facilitates inflammasome activation via epigenetic suppression of Nrf2 in Parkinson\u2019s disease","volume":"13","author":"L-J Cai","year":"2020","journal-title":"Mol Brain."},{"key":"pcbi.1013603.ref049","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gky1131","article-title":"STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets","volume":"47","author":"D Szklarczyk","year":"2019","journal-title":"Nucleic Acids Res."},{"issue":"8","key":"pcbi.1013603.ref050","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1101\/gr.240663.118","article-title":"Benchmark and integration of resources for the estimation of human transcription factor activities","volume":"29","author":"L Garcia-Alonso","year":"2019","journal-title":"Genome Res."},{"key":"pcbi.1013603.ref051","article-title":"RegNetwork: an integrated database of transcriptional and post-transcriptional regulatory networks in human and mouse","volume":"2015","author":"Z-P Liu","year":"2015","journal-title":"Database (Oxford)."},{"key":"pcbi.1013603.ref052","article-title":"TRRUST v2: an expanded reference database of human and mouse transcriptional regulatory interactions","volume":"46","author":"H Han","year":"2018","journal-title":"Nucleic Acids Res."},{"issue":"7414","key":"pcbi.1013603.ref053","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"Consortium ENCODE Project","year":"2012","journal-title":"Nature."},{"key":"pcbi.1013603.ref054","article-title":"ChIP-Atlas 2021 update: a data-mining suite for exploring epigenomic landscapes by fully integrating chip-seq, ATAC-seq and Bisulfite-seq data","volume":"50","author":"Z Zou","year":"2022","journal-title":"Nucleic acids research."},{"key":"pcbi.1013603.ref055","article-title":"ESCAPE: database for integrating high-content published data collected from human and mouse embryonic stem cells","volume":"2013","author":"H Xu","year":"2013","journal-title":"Database (Oxford)."},{"issue":"1","key":"pcbi.1013603.ref056","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1093\/nar\/30.1.207","article-title":"Gene expression omnibus: NCBI gene expression and hybridization array data repository","volume":"30","author":"R Edgar","year":"2002","journal-title":"Nucleic Acids Res."},{"issue":"7","key":"pcbi.1013603.ref057","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1038\/s41593-022-01091-9","article-title":"The embryonic zebrafish brain is seeded by a lymphatic-dependent population of mrc1+ microglia precursors","volume":"25","author":"LA Green","year":"2022","journal-title":"Nat Neurosci."},{"issue":"3","key":"pcbi.1013603.ref058","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"T Saito","year":"2015","journal-title":"PLoS One."},{"key":"pcbi.1013603.ref059","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008"},{"issue":"7","key":"pcbi.1013603.ref060","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1038\/s41596-020-0336-2","article-title":"A scalable SCENIC workflow for single-cell gene regulatory network analysis","volume":"15","author":"B Van de Sande","year":"2020","journal-title":"Nat Protoc."},{"issue":"9","key":"pcbi.1013603.ref061","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.1038\/s41592-023-01938-4","article-title":"SCENIC+: single-cell multiomic inference of enhancers and gene regulatory networks","volume":"20","author":"C Bravo Gonz\u00e1lez-Blas","year":"2023","journal-title":"Nat Methods."},{"issue":"15","key":"pcbi.1013603.ref062","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gks543","article-title":"i-cisTarget: an integrative genomics method for the prediction of regulatory features and cis-regulatory modules","volume":"40","author":"C Herrmann","year":"2012","journal-title":"Nucleic Acids Res."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013603","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T00:00:00Z","timestamp":1761782400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:53:14Z","timestamp":1761846794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013603"}},"subtitle":[],"editor":[{"given":"Saurabh","family":"Sinha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"references-count":62,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013603","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,24]]}}}