{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T06:18:58Z","timestamp":1773555538260,"version":"3.50.1"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2020,1,23]],"date-time":"2020-01-23T00:00:00Z","timestamp":1579737600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Research Grants Council"},{"name":"Hong Kong Special Administrative Region of China","award":["HKU 17259316"],"award-info":[{"award-number":["HKU 17259316"]}]},{"name":"Collaborative Research Fund","award":["C7047-16G"],"award-info":[{"award-number":["C7047-16G"]}]},{"name":"General Research Fund","award":["17208918"],"award-info":[{"award-number":["17208918"]}]},{"name":"General Research Fund","award":["17209017"],"award-info":[{"award-number":["17209017"]}]},{"name":"General Research Fund","award":["201611159293"],"award-info":[{"award-number":["201611159293"]}]},{"name":"Innovation and Technology Support Programme","award":["ITS\/204\/18"],"award-info":[{"award-number":["ITS\/204\/18"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>New single-cell technologies continue to fuel the explosive growth in the scale of heterogeneous single-cell data. However, existing computational methods are inadequately scalable to large datasets and therefore cannot uncover the complex cellular heterogeneity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We introduce a highly scalable graph-based clustering algorithm PARC\u2014Phenotyping by Accelerated Refined Community-partitioning\u2014for large-scale, high-dimensional single-cell data (&amp;gt;1 million cells). Using large single-cell flow and mass cytometry, RNA-seq and imaging-based biophysical data, we demonstrate that PARC consistently outperforms state-of-the-art clustering algorithms without subsampling of cells, including Phenograph, FlowSOM and Flock, in terms of both speed and ability to robustly detect rare cell populations. For example, PARC can cluster a single-cell dataset of 1.1 million cells within 13\u2009min, compared with &amp;gt;2\u2009h for the next fastest graph-clustering algorithm. Our work presents a scalable algorithm to cope with increasingly large-scale single-cell analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>https:\/\/github.com\/ShobiStassen\/PARC.<\/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\/btaa042","type":"journal-article","created":{"date-parts":[[2020,1,16]],"date-time":"2020-01-16T15:10:24Z","timestamp":1579187424000},"page":"2778-2786","source":"Crossref","is-referenced-by-count":108,"title":["PARC: ultrafast and accurate clustering of phenotypic data of millions of single cells"],"prefix":"10.1093","volume":"36","author":[{"given":"Shobana V","family":"Stassen","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering"}]},{"given":"Dickson M D","family":"Siu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering"}]},{"given":"Kelvin C M","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering"}]},{"given":"Joshua W K","family":"Ho","sequence":"additional","affiliation":[{"name":"School of Biomedical Sciences , Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong SAR, China"}]},{"given":"Hayden K H","family":"So","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering"}]},{"given":"Kevin K","family":"Tsia","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering"}]}],"member":"286","published-online":{"date-parts":[[2020,1,23]]},"reference":[{"key":"2023013110295068400_btaa042-B1","year":"2017"},{"key":"2023013110295068400_btaa042-B2","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1002\/cyto.a.21007","article-title":"Rapid cell population identification in flow cytometry data","volume":"79","author":"Aghaeepour","year":"2011","journal-title":"Cytometry A"},{"key":"2023013110295068400_btaa042-B5","first-page":"E6372","article-title":"Nanoscale dynamics of higher-order chromatin","volume":"113","author":"Almassalha","year":"2016","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023013110295068400_btaa042-B7","doi-asserted-by":"crossref","first-page":"14108","DOI":"10.1073\/pnas.0804650106","article-title":"Changing numbers of neuronal and non-neuronal cells underlie postnatal brain growth in the rat","volume":"106","author":"Bandeira","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023013110295068400_btaa042-B8","author":"Barabasi","year":"2019"},{"key":"2023013110295068400_btaa042-B9","year":"2016"},{"key":"2023013110295068400_btaa042-B10","doi-asserted-by":"crossref","first-page":"10256","DOI":"10.1038\/ncomms10256","article-title":"Label-free cell cycle analysis for high-throughput imaging flow cytometry","volume":"7","author":"Blasi","year":"2016","journal-title":"Nat. Commun"},{"key":"2023013110295068400_btaa042-B11","first-page":"6","article-title":"Fast unfolding of communities in large networks","volume":"10008","author":"Blondel","year":"2008","journal-title":"J. Stat. Mech. Theory Exp"},{"key":"2023013110295068400_btaa042-B13","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.1016\/j.bpj.2014.02.023","article-title":"Sandrine L\u00e9v\u00eaque-Fort, fast label-free cytoskeletal network imaging in living mammalian cells","volume":"106","author":"Bon","year":"2014","journal-title":"Biophys. J"},{"key":"2023013110295068400_btaa042-B14","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1038\/nmeth.4397","article-title":"Data-analysis strategies for image-based cell profiling","volume":"14","author":"Caicedo","year":"2017","journal-title":"Nat. Methods"},{"key":"2023013110295068400_btaa042-B16","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1146\/annurev-genom-091416-035324","article-title":"Single-cell (multi)omics technologies","volume":"19","author":"Chappell","year":"2018","journal-title":"Annu. Rev. Genomics Hum. Genet"},{"key":"2023013110295068400_btaa042-B20","article-title":"Scalable analysis of cell-type composition from single-cell transcriptomics using deep recurrent learning","author":"Deng","year":"2019","journal-title":"Nat. Methods Brief. Commun"},{"key":"2023013110295068400_btaa042-B22","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.12688\/f1000research.15666.2","article-title":"A systematic performance evaluation of clustering methods for single-cell RNA-seq data","volume":"7","author":"Du\u00f2","year":"2018","journal-title":"F1000Research"},{"key":"2023013110295068400_btaa042-B26","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1002\/cyto.a.22625","article-title":"FlowSOM: using self-organizing maps for visualization and interpretation of cytometry data","volume":"87","author":"Gassen","year":"2015","journal-title":"Cytometry A"},{"key":"2023013110295068400_btaa042-B27","doi-asserted-by":"crossref","first-page":"2052","DOI":"10.1093\/bioinformatics\/bts300","article-title":"flowPeaks: a fast unsupervised clustering for flow cytometry data via K-means and density peak finding","volume":"28","author":"Ge","year":"2012","journal-title":"Bioinformatics"},{"key":"2023013110295068400_btaa042-B29","doi-asserted-by":"crossref","first-page":"994","DOI":"10.3324\/haematol.2008.005421","article-title":"Morphological evaluation of monocytes and their precursors","volume":"94","author":"Goasguen","year":"2009","journal-title":"Haematologica"},{"key":"2023013110295068400_btaa042-B31","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1038\/nbt.4091","article-title":"Batch effects in single-cell RNA-sequencing data are corrected by matching mutual nearest neighbors","volume":"36","author":"Haghverdi","year":"2018","journal-title":"Nat. Biotechnol"},{"key":"2023013110295068400_btaa042-B32","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1186\/s13059-017-1215-1","article-title":"Multi-omics approaches to disease","volume":"18","author":"Hasin","year":"2017","journal-title":"Genome Biol"},{"key":"2023013110295068400_btaa042-B8570467","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.biocel.2017.01.004","article-title":"Characterising live cell behaviour: Traditional label-free and quantitative phase imaging approaches","volume":"84","author":"Kasprowicz","year":"2017","journal-title":"Int. J. Biochem. Cell Biol."},{"key":"2023013110295068400_btaa042-B38","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.imlet.2011.02.003","article-title":"CD160: a unique activating NK cell receptor","volume":"138","author":"Le Bouteiller","year":"2011","journal-title":"Immunol. Lett"},{"key":"2023013110295068400_btaa042-B40","article-title":"Multi-ATOM: ultrahigh-throughput single-cell quantitative phase imaging with subcellular resolution","volume":"12, e201800479.","author":"Lee","year":"2019","journal-title":"J. Biophotonics"},{"key":"2023013110295068400_btaa042-B41","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1002\/cyto.a.23765","article-title":"Quantitative phase imaging flow cytometry for ultra-large-scale single-cell biophysical phenotyping","volume":"95","author":"Lee","year":"2019","journal-title":"Cytometry A"},{"key":"2023013110295068400_btaa042-B42","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.cell.2015.05.047","article-title":"Data-driven phenotypic dissection of AML reveals progenitor-like cells that correlate with prognosis","volume":"162","author":"Levine","year":"2015","journal-title":"Cell"},{"key":"2023013110295068400_btaa042-B46","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/s41592-018-0308-4","article-title":"Fast interpolation-based t-SNE for improved visualization of single-cell RNA-seq data","volume":"16","author":"Linderman","year":"2019","journal-title":"Nat. Methods"},{"key":"2023013110295068400_btaa042-B47","doi-asserted-by":"publisher","author":"Malkov","year":"2016","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"2023013110295068400_btaa042-B48","author":"McInnes","year":"2018"},{"key":"2023013110295068400_btaa042-B49","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1002\/cyto.a.22445","article-title":"SWIFT\u2014Scalable clustering for automated identification of rare cell populations in large, high-dimensional flow cytometry datasets, part 2: biological evaluation","volume":"85A","author":"Mosmann","year":"2014","journal-title":"Cytometry"},{"key":"2023013110295068400_btaa042-B50","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1002\/cyto.a.22324","article-title":"Frequency determination of rare populations by flow cytometry: a hematopoietic stem cell perspective","volume":"83A","author":"Nilsson","year":"2013","journal-title":"Cytometry A"},{"key":"2023013110295068400_btaa042-B51","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1038\/s41419-018-0327-1","article-title":"The pro-inflammatory phenotype of the human non-classical monocyte subset is attributed to senescence","volume":"9","author":"Ong","year":"2018","journal-title":"Cell Death Dis"},{"key":"2023013110295068400_btaa042-B2444974","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1038\/nmeth.3281","article-title":"Real-time deformability cytometry: on-the-fly cell mechanical phenotyping","volume":"12","author":"Otto","year":"2015","journal-title":"Nat. Methods"},{"key":"2023013110295068400_btaa042-B54","doi-asserted-by":"crossref","first-page":"S69","DOI":"10.1002\/cyto.b.20554","article-title":"Elucidation of seventeen human peripheral blood B-cell subsets and quantification of the tetanus response using a density-based method for the automated identification of cell populations in multidimensional flow cytometry data","volume":"78B (Suppl 1","author":"Qian","year":"2010","journal-title":"Cytometry B Clin. Cytometry"},{"key":"2023013110295068400_btaa042-B55","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1038\/nbt.1991","article-title":"Extracting a cellular hierarchy from high-dimensional cytometry data with SPADE","volume":"29","author":"Qiu","year":"2011","journal-title":"Nat. Biotechnol"},{"key":"2023013110295068400_btaa042-B56","doi-asserted-by":"crossref","first-page":"e27041","DOI":"10.7554\/eLife.27041","article-title":"The human cell Atlas","volume":"6","author":"Regev","year":"2017","journal-title":"eLife"},{"key":"2023013110295068400_btaa042-B8936543","year":"2017"},{"key":"2023013110295068400_btaa042-B59","doi-asserted-by":"crossref","first-page":"4755","DOI":"10.1523\/JNEUROSCI.6412-11.2012","article-title":"The fraction of cortical GABAergic neurons is constant from near the start of cortical neurogenesis to adulthood","volume":"32","author":"Sahara","year":"2012","journal-title":"J. Neurosci"},{"key":"2023013110295068400_btaa042-B62","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/nmeth.3863","article-title":"Automated mapping of phenotype space with single-cell data","volume":"13","author":"Samusik","year":"2016","journal-title":"Nat. Methods"},{"key":"2023013110295068400_btaa042-B66","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1016\/j.cell.2016.04.019","article-title":"Mass cytometry: single cells, many features","volume":"165","author":"Spitzer","year":"2016","journal-title":"Cell"},{"key":"2023013110295068400_btaa042-B68","author":"Stuart","year":"2018"},{"key":"2023013110295068400_btaa042-B8529460","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/s41586-018-0654-5","article-title":"Shared and distinct transcriptomic cell types across neocortical areas","volume":"563","author":"Tasic","year":"2018","journal-title":"Nature"},{"key":"2023013110295068400_btaa042-B69","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1038\/nn.4216","article-title":"Adult mouse cortical cell taxonomy by single cell transcriptomics","volume":"19","author":"Tasic","year":"2016","journal-title":"Nat. Neurosci"},{"key":"2023013110295068400_btaa042-B71","doi-asserted-by":"crossref","first-page":"016114","DOI":"10.1103\/PhysRevE.84.016114","article-title":"Narrow scope for resolution-limit-free community detection","volume":"84","author":"Traag","year":"2011","journal-title":"Phys. Rev. E"},{"key":"2023013110295068400_btaa042-B72","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":"2023013110295068400_btaa042-B43406995","doi-asserted-by":"publisher","first-page":"212ra163","DOI":"10.1126\/scitranslmed.3006559","article-title":"Quantitative diagnosis of malignant pleural effusions by single-cell mechanophenotyping","volume":"5","author":"Tse","year":"2013","journal-title":"Sci. Transl. Med."},{"key":"2023013110295068400_btaa042-B74","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1002\/cyto.a.23030","article-title":"Comparison of clustering methods for high-dimensional single-cell flow and mass cytometry data","volume":"89","author":"Weber","year":"2016","journal-title":"Cytometry A"},{"key":"2023013110295068400_btaa042-B75","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":"Wolf","year":"2018","journal-title":"Genome Biol"},{"key":"2023013110295068400_btaa042-B77","doi-asserted-by":"crossref","first-page":"e201700178","DOI":"10.1002\/jbio.201700178","article-title":"A high-throughput all-optical laser-scanning imaging flow cytometer with biomolecular specificity and subcellular resolution","volume":"11","author":"Yan","year":"2018","journal-title":"J. Biophotonics"},{"key":"2023013110295068400_btaa042-B79","doi-asserted-by":"crossref","first-page":"1988","DOI":"10.1073\/pnas.1610630114","article-title":"A distinct subset of plasmacytoid dendritic cells induces activation and differentiation of B and T lymphocytes","volume":"114","author":"Zhang","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023013110295068400_btaa042-B80","doi-asserted-by":"crossref","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":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa042\/33047501\/btaa042.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/9\/2778\/48984889\/bioinformatics_36_9_2778.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/9\/2778\/48984889\/bioinformatics_36_9_2778.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T15:40:25Z","timestamp":1675179625000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/9\/2778\/5714737"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,1,23]]},"references-count":48,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa042","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/765628","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":[[2020,5,1]]},"published":{"date-parts":[[2020,1,23]]}}}