{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T22:37:16Z","timestamp":1775255836372,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1007794","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T00:00:00Z","timestamp":1589241600000}}],"reference-count":70,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2020,4,27]],"date-time":"2020-04-27T00:00:00Z","timestamp":1587945600000},"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"],"DOI":"10.1371\/journal.pcbi.1007794","type":"journal-article","created":{"date-parts":[[2020,4,27]],"date-time":"2020-04-27T14:47:44Z","timestamp":1587998864000},"page":"e1007794","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":17,"title":["Scedar: A scalable Python package for single-cell RNA-seq exploratory data analysis"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9663-5841","authenticated-orcid":true,"given":"Yuanchao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1507-9829","authenticated-orcid":true,"given":"Man S.","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1334-1694","authenticated-orcid":true,"given":"Erin R.","family":"Reichenberger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2972-0354","authenticated-orcid":true,"given":"Ben","family":"Stear","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3302-4610","authenticated-orcid":true,"given":"Deanne M.","family":"Taylor","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2020,4,27]]},"reference":[{"key":"pcbi.1007794.ref001","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"},{"key":"pcbi.1007794.ref002","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1126\/science.aao4750","article-title":"Developmental and oncogenic programs in H3K27M gliomas dissected by single-cell RNA-seq","volume":"360","author":"MG Filbin","year":"2018","journal-title":"Science"},{"key":"pcbi.1007794.ref003","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1126\/science.aam8940","article-title":"Comprehensive single-cell transcriptional profiling of a multicellular organism","volume":"357","author":"J Cao","year":"2017","journal-title":"Science"},{"key":"pcbi.1007794.ref004","volume":"6","author":"A Regev","year":"2017","journal-title":"The Human Cell Atlas. Elife"},{"key":"pcbi.1007794.ref005","article-title":"Challenges in unsupervised clustering of single-cell RNA-seq data","author":"VY Kiselev","year":"2019","journal-title":"Nat Rev Genet"},{"key":"pcbi.1007794.ref006","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1186\/s12864-016-3300-3","article-title":"Assessing characteristics of RNA amplification methods for single cell RNA sequencing","volume":"17","author":"HR Dueck","year":"2016","journal-title":"BMC Genomics"},{"key":"pcbi.1007794.ref007","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1016\/j.molcel.2017.01.023","article-title":"Comparative Analysis of Single-Cell RNA Sequencing Methods","volume":"65","author":"C Ziegenhain","year":"2017","journal-title":"Mol Cell"},{"key":"pcbi.1007794.ref008","article-title":"Integrating single-cell transcriptomic data across different conditions, technologies, and species","author":"A Butler","year":"2018","journal-title":"Nat Biotechnol"},{"key":"pcbi.1007794.ref009","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13059-017-1382-0","article-title":"SCANPY: large-scale single-cell gene expression data analysis","volume":"19","author":"FA Wolf","year":"2018","journal-title":"Genome Biol"},{"key":"pcbi.1007794.ref010","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2934664","article-title":"Apache Spark: A Unified Engine for Big Data Processing","volume":"59","author":"M Zaharia","year":"2016","journal-title":"Commun ACM"},{"key":"pcbi.1007794.ref011","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","article-title":"MapReduce: simplified data processing on large clusters","volume":"51","author":"J Dean","year":"2008","journal-title":"Commun ACM"},{"key":"pcbi.1007794.ref012","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. Tensorflow: A system for large-scale machine learning. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). usenix.org; 2016. pp. 265\u2013283."},{"key":"pcbi.1007794.ref013","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1186\/s13059-017-1305-0","article-title":"Splatter: simulation of single-cell RNA sequencing data","volume":"18","author":"L Zappia","year":"2017","journal-title":"Genome Biol"},{"key":"pcbi.1007794.ref014","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/nbt.2967","article-title":"Low-coverage single-cell mRNA sequencing reveals cellular heterogeneity and activated signaling pathways in developing cerebral cortex","volume":"32","author":"AA Pollen","year":"2014","journal-title":"Nat Biotechnol"},{"key":"pcbi.1007794.ref015","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1016\/j.cell.2015.05.002","article-title":"Highly Parallel Genome-wide Expression Profiling of Individual Cells Using Nanoliter Droplets","volume":"161","author":"EZ Macosko","year":"2015","journal-title":"Cell"},{"key":"pcbi.1007794.ref016","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"},{"key":"pcbi.1007794.ref017","doi-asserted-by":"crossref","first-page":"e1006245","DOI":"10.1371\/journal.pcbi.1006245","article-title":"Exploring the single-cell RNA-seq analysis landscape with the scRNA-tools database","volume":"14","author":"L Zappia","year":"2018","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1007794.ref018","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining\u2014KDD \u201816. New York, New York, USA: ACM Press; 2016. pp. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"pcbi.1007794.ref019","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"L van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"pcbi.1007794.ref020","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv [stat.ML]. 2018. Available: http:\/\/arxiv.org\/abs\/1802.03426","DOI":"10.21105\/joss.00861"},{"key":"pcbi.1007794.ref021","doi-asserted-by":"crossref","first-page":"e98679","DOI":"10.1371\/journal.pone.0098679","article-title":"ForceAtlas2, a continuous graph layout algorithm for handy network visualization designed for the Gephi software","volume":"9","author":"M Jacomy","year":"2014","journal-title":"PLoS One"},{"key":"pcbi.1007794.ref022","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1186\/s13059-015-0679-0","article-title":"quantro: a data-driven approach to guide the choice of an appropriate normalization method","volume":"16","author":"SC Hicks","year":"2015","journal-title":"Genome Biol"},{"key":"pcbi.1007794.ref023","unstructured":"M\u00fcllner D. Modern hierarchical, agglomerative clustering algorithms. arXiv [stat.ML]. 2011. Available: http:\/\/arxiv.org\/abs\/1109.2378"},{"issue":"Suppl 1","key":"pcbi.1007794.ref024","doi-asserted-by":"crossref","first-page":"S22","DOI":"10.1093\/bioinformatics\/17.suppl_1.S22","article-title":"Fast optimal leaf ordering for hierarchical clustering","volume":"17","author":"Z Bar-Joseph","year":"2001","journal-title":"Bioinformatics"},{"key":"pcbi.1007794.ref025","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1198\/016214501753168398","article-title":"Model Selection and the Principle of Minimum Description Length","volume":"96","author":"MH Hansen","year":"2001","journal-title":"J Am Stat Assoc"},{"key":"pcbi.1007794.ref026","doi-asserted-by":"crossref","DOI":"10.1201\/b10576","volume-title":"generatingfunctionology","author":"HS Wilf","year":"2005"},{"key":"pcbi.1007794.ref027","first-page":"439","article-title":"Restricted combinations and compositions","volume":"14","author":"M Abramson","year":"1976","journal-title":"Fibonacci Quart"},{"key":"pcbi.1007794.ref028","doi-asserted-by":"crossref","unstructured":"Aydin K, Bateni M, Mirrokni V. Distributed Balanced Partitioning via Linear Embedding. Proceedings of the Ninth ACM International Conference on Web Search and Data Mining. New York, NY, USA: ACM; 2016. pp. 387\u2013396.","DOI":"10.1145\/2835776.2835829"},{"key":"pcbi.1007794.ref029","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":"VA Traag","year":"2019","journal-title":"Sci Rep"},{"key":"pcbi.1007794.ref030","unstructured":"Malkov YA, Yashunin DA. Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs. arXiv [cs.DS]. 2016. Available: http:\/\/arxiv.org\/abs\/1603.09320"},{"key":"pcbi.1007794.ref031","doi-asserted-by":"crossref","first-page":"e1004333","DOI":"10.1371\/journal.pcbi.1004333","article-title":"BASiCS: Bayesian Analysis of Single-Cell Sequencing Data","volume":"11","author":"CA Vallejos","year":"2015","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1007794.ref032","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1038\/nmeth.2967","article-title":"Bayesian approach to single-cell differential expression analysis","volume":"11","author":"PV Kharchenko","year":"2014","journal-title":"Nat Methods"},{"key":"pcbi.1007794.ref033","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1038\/nmeth.4150","article-title":"Single-cell mRNA quantification and differential analysis with Census","volume":"14","author":"X Qiu","year":"2017","journal-title":"Nat Methods"},{"key":"pcbi.1007794.ref034","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1038\/nmeth.4612","article-title":"Bias, robustness and scalability in single-cell differential expression analysis","volume":"15","author":"C Soneson","year":"2018","journal-title":"Nat Methods"},{"key":"pcbi.1007794.ref035","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1186\/s13059-016-1077-y","article-title":"A statistical approach for identifying differential distributions in single-cell RNA-seq experiments","volume":"17","author":"KD Korthauer","year":"2016","journal-title":"Genome Biol"},{"key":"pcbi.1007794.ref036","doi-asserted-by":"crossref","first-page":"R40","DOI":"10.1093\/hmg\/ddy100","article-title":"Cell type discovery using single-cell transcriptomics: implications for ontological representation","volume":"27","author":"BD Aevermann","year":"2018","journal-title":"Hum Mol Genet"},{"key":"pcbi.1007794.ref037","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"pcbi.1007794.ref038","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pcbi.1007794.ref039","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest Neighbor Pattern Classification","volume":"13","author":"T Cover","year":"2006","journal-title":"IEEE Trans Inf Theory"},{"key":"pcbi.1007794.ref040","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/0165-0114(86)90004-7","article-title":"Generalized k-nearest neighbor rules","volume":"18","author":"JC Bezdek","year":"1986","journal-title":"Fuzzy Sets and Systems"},{"key":"pcbi.1007794.ref041","unstructured":"Bellet A, Habrard A, Sebban M. A Survey on Metric Learning for Feature Vectors and Structured Data. arXiv [cs.LG]. 2013. Available: http:\/\/arxiv.org\/abs\/1306.6709"},{"key":"pcbi.1007794.ref042","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":"D Risso","year":"2018","journal-title":"Nat Commun"},{"key":"pcbi.1007794.ref043","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1186\/s13059-015-0805-z","article-title":"ZIFA: Dimensionality reduction for zero-inflated single-cell gene expression analysis","volume":"16","author":"E Pierson","year":"2015","journal-title":"Genome Biol"},{"key":"pcbi.1007794.ref044","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1126\/science.1198817","article-title":"Mammalian genes are transcribed with widely different bursting kinetics","volume":"332","author":"DM Suter","year":"2011","journal-title":"Science"},{"key":"pcbi.1007794.ref045","doi-asserted-by":"crossref","first-page":"12248","DOI":"10.1038\/ncomms12248","article-title":"A single-molecule view of transcription reveals convoys of RNA polymerases and multi-scale bursting","volume":"7","author":"K Tantale","year":"2016","journal-title":"Nat Commun"},{"key":"pcbi.1007794.ref046","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1038\/nmeth.4236","article-title":"SC3: consensus clustering of single-cell RNA-seq data","volume":"14","author":"VY Kiselev","year":"2017","journal-title":"Nat Methods"},{"key":"pcbi.1007794.ref047","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"M Ester","year":"1996","journal-title":"Kdd"},{"key":"pcbi.1007794.ref048","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1007\/3-540-44503-X_27","volume-title":"Database Theory\u2014ICDT 2001","author":"CC Aggarwal","year":"2001"},{"key":"pcbi.1007794.ref049","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1137\/18M1216134","article-title":"Clustering with t-SNE, Provably","volume":"1","author":"GC Linderman","year":"2019","journal-title":"SIAM Journal on Mathematics of Data Science"},{"key":"pcbi.1007794.ref050","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF01908075","article-title":"Comparing partitions","volume":"2","author":"L Hubert","year":"1985","journal-title":"J Classification"},{"key":"pcbi.1007794.ref051","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1126\/science.1245316","article-title":"Single-cell RNA-seq reveals dynamic, random monoallelic gene expression in mammalian cells","volume":"343","author":"Q Deng","year":"2014","journal-title":"Science"},{"key":"pcbi.1007794.ref052","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/j.stem.2015.09.011","article-title":"Single Cell RNA-Sequencing of Pluripotent States Unlocks Modular Transcriptional Variation","volume":"17","author":"AA Kolodziejczyk","year":"2015","journal-title":"Cell Stem Cell"},{"key":"pcbi.1007794.ref053","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1126\/science.aaa1934","article-title":"Brain structure. Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq","volume":"347","author":"A Zeisel","year":"2015","journal-title":"Science"},{"key":"pcbi.1007794.ref054","article-title":"SAVER: gene expression recovery for single-cell RNA sequencing","volume":"1","author":"M Huang","year":"2018","journal-title":"Nat Methods"},{"key":"pcbi.1007794.ref055","article-title":"Recovering Gene Interactions from Single-Cell Data Using Data Diffusion","author":"D van Dijk","year":"2018","journal-title":"Cell"},{"key":"pcbi.1007794.ref056","first-page":"141598","article-title":"scImpute: Accurate And Robust Imputation For Single Cell RNA-Seq Data","author":"WV Li","year":"2017","journal-title":"bioRxiv"},{"key":"pcbi.1007794.ref057","doi-asserted-by":"crossref","unstructured":"Xianyi Z, Qian W, Yunquan Z. Model-driven Level 3 BLAS Performance Optimization on Loongson 3A Processor. 2012 IEEE 18th International Conference on Parallel and Distributed Systems. 2012. pp. 684\u2013691.","DOI":"10.1109\/ICPADS.2012.97"},{"key":"pcbi.1007794.ref058","doi-asserted-by":"crossref","unstructured":"Wang Q, Zhang X, Zhang Y, Yi Q. AUGEM: Automatically generate high performance Dense Linear Algebra kernels on x86 CPUs. SC \u201813: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. 2013. pp. 1\u201312.","DOI":"10.1145\/2503210.2503219"},{"key":"pcbi.1007794.ref059","article-title":"The single-cell transcriptional landscape of mammalian organogenesis","volume":"1","author":"J Cao","year":"2019","journal-title":"Nature"},{"key":"pcbi.1007794.ref060","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1002\/glia.22524","article-title":"Unique transcriptome signature of mouse microglia","volume":"61","author":"C Beutner","year":"2013","journal-title":"Glia"},{"key":"pcbi.1007794.ref061","doi-asserted-by":"crossref","first-page":"eaah4573","DOI":"10.1126\/science.aah4573","article-title":"Single-cell RNA-seq reveals new types of human blood dendritic cells, monocytes, and progenitors","volume":"356","author":"A-C Villani","year":"2017","journal-title":"Science"},{"key":"pcbi.1007794.ref062","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1038\/nrc.2017.58","article-title":"Unravelling biology and shifting paradigms in cancer with single-cell sequencing","volume":"17","author":"T Baslan","year":"2017","journal-title":"Nat Rev Cancer"},{"key":"pcbi.1007794.ref063","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1038\/nbt.3854","article-title":"Single-cell topological RNA-seq analysis reveals insights into cellular differentiation and development","volume":"35","author":"AH Rizvi","year":"2017","journal-title":"Nat Biotechnol"},{"key":"pcbi.1007794.ref064","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1016\/j.cell.2019.02.026","article-title":"Optimal-Transport Analysis of Single-Cell Gene Expression Identifies Developmental Trajectories in Reprogramming","volume":"176","author":"G Schiebinger","year":"2019","journal-title":"Cell"},{"key":"pcbi.1007794.ref065","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1038\/nbt.4038","article-title":"Integrative single-cell analysis of transcriptional and epigenetic states in the human adult brain","volume":"36","author":"BB Lake","year":"2018","journal-title":"Nat Biotechnol"},{"key":"pcbi.1007794.ref066","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1038\/nature24489","article-title":"A single-cell survey of the small intestinal epithelium","volume":"551","author":"AL Haber","year":"2017","journal-title":"Nature"},{"key":"pcbi.1007794.ref067","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1038\/550451a","article-title":"The Human Cell Atlas: from vision to reality","volume":"550","author":"O Rozenblatt-Rosen","year":"2017","journal-title":"Nature"},{"key":"pcbi.1007794.ref068","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1038\/nmeth.3734","article-title":"Characterizing transcriptional heterogeneity through pathway and gene set overdispersion analysis","volume":"13","author":"J Fan","year":"2016","journal-title":"Nat Methods"},{"key":"pcbi.1007794.ref069","article-title":"BIRCH: an efficient data clustering method for very large databases","author":"T Zhang","year":"1996","journal-title":"ACM Sigmod Record"},{"key":"pcbi.1007794.ref070","doi-asserted-by":"crossref","first-page":"D457","DOI":"10.1093\/nar\/gkv1070","article-title":"KEGG as a reference resource for gene and protein annotation","volume":"44","author":"M Kanehisa","year":"2016","journal-title":"Nucleic Acids Res"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1007794","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T00:00:00Z","timestamp":1589241600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1007794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T13:46:18Z","timestamp":1589291178000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1007794"}},"subtitle":[],"editor":[{"given":"Mihaela","family":"Pertea","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,4,27]]},"references-count":70,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,4,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1007794","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/375196","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,27]]}}}