{"id":"https://openalex.org/W4367183140","doi":"https://doi.org/10.1093/bib/bbad125","title":"A scalable unsupervised learning of scRNAseq data detects rare cells through integration of structure-preserving embedding, clustering and outlier detection","display_name":"A scalable unsupervised learning of scRNAseq data detects rare cells through integration of structure-preserving embedding, clustering and outlier detection","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367183140","doi":"https://doi.org/10.1093/bib/bbad125","pmid":"https://pubmed.ncbi.nlm.nih.gov/37185897"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbad125","doi":"https://doi.org/10.1093/bib/bbad125","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbad125","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","doyens","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014708185","display_name":"Koushik Mallick","orcid":"https://orcid.org/0000-0001-9399-753X","observed_orcids":["https://orcid.org/0000-0001-9399-753X"]},"institutions":[{"id":"https://openalex.org/I4405278573","display_name":"RCC Institute of Information Technology","ror":"https://ror.org/007mfn583","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405278573"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Koushik Mallick","raw_affiliation_strings":["RCC Institute of Information Technology Computer Science and Engineering, , Canal South Road, 700015, West Bengal , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RCC Institute of Information Technology Computer Science and Engineering, , Canal South Road, 700015, West Bengal , India","institution_ids":["https://openalex.org/I4405278573"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068366761","display_name":"Sikim Chakraborty","orcid":"https://orcid.org/0000-0002-3962-1782","observed_orcids":["https://orcid.org/0000-0002-3962-1782"]},"institutions":[{"id":"https://openalex.org/I2802103719","display_name":"Observer Research Foundation","ror":"https://ror.org/0228dbh09","country_code":"IN","type":"nonprofit","lineage":["https://openalex.org/I2802103719"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sikim Chakraborty","raw_affiliation_strings":["Observer Research Foundation Centre for Economy and Growth, , Rouse Avenue, New Delhi, 110002, Delhi , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Observer Research Foundation Centre for Economy and Growth, , Rouse Avenue, New Delhi, 110002, Delhi , India","institution_ids":["https://openalex.org/I2802103719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033317672","display_name":"Saurav Mallik","orcid":"https://orcid.org/0000-0003-4107-6784","observed_orcids":["https://orcid.org/0000-0003-4107-6784"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurav Mallik","raw_affiliation_strings":["Harvard T H Chan School of Public Health Department of Environmental Health, , 677 Huntington Ave, 02115, MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard T H Chan School of Public Health Department of Environmental Health, , 677 Huntington Ave, 02115, MA , USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007160886","display_name":"Sanghamitra Bandyopadhyay","orcid":"https://orcid.org/0000-0002-1490-3599","observed_orcids":["https://orcid.org/0000-0002-1490-3599","https://orcid.org/0000-0001-6370-2083"]},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sanghamitra Bandyopadhyay","raw_affiliation_strings":["Indian Statistical Institute Machine Intelligence Unit, , Barrackpore Trunk Rd., 700108, West Bengal , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute Machine Intelligence Unit, , Barrackpore Trunk Rd., 700108, West Bengal , India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007160886"],"corresponding_institution_ids":["https://openalex.org/I6498739"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":0.6044,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.56783358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"24","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/single-cell-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.9210000038146973},{"id":"https://openalex.org/keywords/rare-cell-detection","display_name":"rare cell detection","score":0.6290000081062317},{"id":"https://openalex.org/keywords/cell-type-clustering","display_name":"cell type clustering","score":0.6850000023841858},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.8429999947547913},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.9359999895095825},{"id":"https://openalex.org/keywords/isolation-forest","display_name":"Isolation Forest","score":0.8859999775886536},{"id":"https://openalex.org/keywords/one-class-svm","display_name":"one-class support vector machine","score":0.9879999756813049},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.8659999966621399},{"id":"https://openalex.org/keywords/high-dimensional-sparse-data","display_name":"high-dimensional sparse data","score":0.8130000233650208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041422963142395},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7278734445571899},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.653584361076355},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5617959499359131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5561451315879822},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5356900691986084},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5304661989212036},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5081393718719482},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.487255722284317},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47685396671295166},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.45221275091171265},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4495568871498108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44398579001426697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40701940655708313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3999876379966736},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10374903678894043},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbad125","doi":"https://doi.org/10.1093/bib/bbad125","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbad125","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","doyens","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37185897","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37185897","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in bioinformatics","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W374166679","https://openalex.org/W1566352582","https://openalex.org/W1673310716","https://openalex.org/W1813068103","https://openalex.org/W1844800652","https://openalex.org/W1988592429","https://openalex.org/W2023887100","https://openalex.org/W2033403400","https://openalex.org/W2051658465","https://openalex.org/W2087242711","https://openalex.org/W2102212449","https://openalex.org/W2107686700","https://openalex.org/W2109890799","https://openalex.org/W2120205807","https://openalex.org/W2193667971","https://openalex.org/W2296719434","https://openalex.org/W2307567449","https://openalex.org/W2473258837","https://openalex.org/W2492794003","https://openalex.org/W2496323672","https://openalex.org/W2572662684","https://openalex.org/W2598326928","https://openalex.org/W2607274990","https://openalex.org/W2612758576","https://openalex.org/W2618735189","https://openalex.org/W2735067671","https://openalex.org/W2739329039","https://openalex.org/W2755506253","https://openalex.org/W2786672974","https://openalex.org/W2796170779","https://openalex.org/W2889571716","https://openalex.org/W2902652978","https://openalex.org/W2907783748","https://openalex.org/W2912393903","https://openalex.org/W2942678593","https://openalex.org/W2950548777","https://openalex.org/W2951506174","https://openalex.org/W2954165312","https://openalex.org/W3044109215","https://openalex.org/W3108941787","https://openalex.org/W3111307227","https://openalex.org/W4210554489","https://openalex.org/W4225116051","https://openalex.org/W4235169531"],"related_works":["https://openalex.org/W4362672096","https://openalex.org/W4389799054","https://openalex.org/W3180192281","https://openalex.org/W4385294687","https://openalex.org/W3148355078","https://openalex.org/W3017924613","https://openalex.org/W4392344407","https://openalex.org/W7138887410","https://openalex.org/W4387125037","https://openalex.org/W4402029625"],"abstract_inverted_index":{"Single-cell":[0],"RNA-seq":[1],"analysis":[2],"has":[3,18],"become":[4],"a":[5,40,71,95,122],"powerful":[6],"tool":[7],"to":[8,32,86,142,159,210],"analyse":[9],"the":[10,20,33,46,106,129,132,136,166,172,189,193],"transcriptomes":[11],"of":[12,22,25,135,165,179,214],"individual":[13],"cells.":[14],"In":[15,90],"turn,":[16],"it":[17],"fostered":[19],"possibility":[21],"screening":[23],"thousands":[24],"single":[26],"cells":[27],"in":[28,51,74],"parallel.":[29],"Thus,":[30],"contrary":[31],"traditional":[34],"bulk":[35],"measurements":[36,44],"that":[37,126,204],"only":[38],"paint":[39],"macroscopic":[41],"picture,":[42],"gene":[43],"at":[45,57,222],"cell":[47,180,202],"level":[48],"aid":[49],"researchers":[50],"studying":[52],"different":[53],"tissues":[54],"and":[55,70,81,103,131,138,153,182],"organs":[56],"various":[58],"stages.":[59],"However,":[60],"accurate":[61],"clustering":[62,99],"methods":[63,80],"for":[64,98],"such":[65,111],"high-dimensional":[66,113],"data":[67,102,137],"remain":[68],"exiguous":[69],"persistent":[72],"challenge":[73],"this":[75,88,91],"domain.":[76],"Of":[77],"late,":[78],"several":[79,186],"techniques":[82],"have":[83],"been":[84],"promulgated":[85],"address":[87],"issue.":[89],"article,":[92],"we":[93,115,147],"propose":[94],"novel":[96],"framework":[97],"large-scale":[100],"single-cell":[101,144],"subsequently":[104],"identifying":[105],"rare-cell":[107,161,183],"sub-populations.":[108,162,184],"To":[109],"handle":[110],"sparse,":[112],"data,":[114],"leverage":[116],"PaCMAP":[117],"(Pairwise":[118],"Controlled":[119],"Manifold":[120],"Approximation),":[121],"feature":[123],"extraction":[124],"algorithm":[125],"preserves":[127],"both":[128],"local":[130],"global":[133],"structures":[134],"Gaussian":[139],"Mixture":[140],"Model":[141],"cluster":[143],"data.":[145],"Subsequently,":[146],"exploit":[148],"Edited":[149],"Nearest":[150],"Neighbours":[151],"sampling":[152],"Isolation":[154],"Forest/One-class":[155],"Support":[156],"Vector":[157],"Machine":[158],"identify":[160],"The":[163,197,217],"performance":[164],"proposed":[167,190,198],"method":[168,191,199],"is":[169,220],"validated":[170],"using":[171],"publicly":[173],"available":[174,221],"datasets":[175],"with":[176,212],"varying":[177],"degrees":[178],"types":[181,203],"On":[185],"benchmark":[187],"datasets,":[188],"outperforms":[192],"existing":[194],"state-of-the-art":[195],"methods.":[196],"successfully":[200],"identifies":[201],"constitute":[205],"populations":[206],"ranging":[207],"from":[208],"0.1":[209],"8%":[211],"F1-scores":[213],"0.91":[215],"0.09.":[216],"source":[218],"code":[219],"https://github.com/scrab017/RarPG.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2023-04-28T00:00:00"}