{"id":"https://openalex.org/W4205428105","doi":"https://doi.org/10.1093/bib/bbab567","title":"A comprehensive comparison of supervised and unsupervised methods for cell type identification in single-cell RNA-seq","display_name":"A comprehensive comparison of supervised and unsupervised methods for cell type identification in single-cell RNA-seq","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4205428105","doi":"https://doi.org/10.1093/bib/bbab567","pmid":"https://pubmed.ncbi.nlm.nih.gov/35021202"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbab567","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab567","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,"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"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8921620","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065527238","display_name":"Xiaobo Sun","orcid":"https://orcid.org/0000-0001-9876-5666"},"institutions":[{"id":"https://openalex.org/I158934434","display_name":"Zhongnan University of Economics and Law","ror":"https://ror.org/04yqxxq63","country_code":"CN","type":"education","lineage":["https://openalex.org/I158934434"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Sun","raw_affiliation_strings":["Department of Statistics, School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I158934434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077926203","display_name":"Xiaochu Lin","orcid":"https://orcid.org/0000-0001-7938-6185"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaochu Lin","raw_affiliation_strings":["Department of Biostatistics and Bioinformatics, Rollins School of Public Health, Emory University, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Bioinformatics, Rollins School of Public Health, Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389131","display_name":"Ziyi Li","orcid":"https://orcid.org/0000-0001-8359-0533"},"institutions":[{"id":"https://openalex.org/I1343551460","display_name":"The University of Texas MD Anderson Cancer Center","ror":"https://ror.org/04twxam07","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1343551460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyi Li","raw_affiliation_strings":["Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas, U.S"],"raw_orcid":"https://orcid.org/0000-0001-8359-0533","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas, U.S","institution_ids":["https://openalex.org/I1343551460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083170497","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0003-1269-7354"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Department of Biostatistics and Bioinformatics, Rollins School of Public Health, Emory University, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1269-7354","affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Bioinformatics, Rollins School of Public Health, Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083170497"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":2.9607,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.92805926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"23","issue":"2","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/T10773","display_name":"Extracellular vesicles in disease","score":0.9941999912261963,"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/T11313","display_name":"Immune cells in cancer","score":0.9613999724388123,"subfield":{"id":"https://openalex.org/subfields/2403","display_name":"Immunology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7134220600128174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.617231011390686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5613932609558105},{"id":"https://openalex.org/keywords/rna-seq","display_name":"RNA-Seq","score":0.5098006129264832},{"id":"https://openalex.org/keywords/cell","display_name":"Cell","score":0.46303853392601013},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4588833749294281},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38646697998046875},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18221184611320496},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.09647849202156067},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.09384781122207642},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0837956964969635},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0796433687210083}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7134220600128174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.617231011390686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5613932609558105},{"id":"https://openalex.org/C107397762","wikidata":"https://www.wikidata.org/wiki/Q2542347","display_name":"RNA-Seq","level":5,"score":0.5098006129264832},{"id":"https://openalex.org/C1491633281","wikidata":"https://www.wikidata.org/wiki/Q7868","display_name":"Cell","level":2,"score":0.46303853392601013},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4588833749294281},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38646697998046875},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18221184611320496},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.09647849202156067},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.09384781122207642},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0837956964969635},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0796433687210083},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D016000","descriptor_name":"Cluster Analysis","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":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","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":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbab567","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab567","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,"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:35021202","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35021202","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,"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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8921620","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8921620","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8921620","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8921620","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2748096557","display_name":null,"funder_award_id":"R01GM122083","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4363365247","display_name":null,"funder_award_id":"61773401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4614546149","display_name":null,"funder_award_id":"R03 CA270725","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G4978443175","display_name":null,"funder_award_id":"R01 GM122083","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1985987855","https://openalex.org/W2072240081","https://openalex.org/W2144351558","https://openalex.org/W2154431984","https://openalex.org/W2180374961","https://openalex.org/W2306630387","https://openalex.org/W2373831850","https://openalex.org/W2523369352","https://openalex.org/W2523419694","https://openalex.org/W2526262591","https://openalex.org/W2528543174","https://openalex.org/W2598326928","https://openalex.org/W2767394894","https://openalex.org/W2774307122","https://openalex.org/W2794521141","https://openalex.org/W2794891507","https://openalex.org/W2796170779","https://openalex.org/W2804847416","https://openalex.org/W2884197618","https://openalex.org/W2895456557","https://openalex.org/W2907514116","https://openalex.org/W2915857439","https://openalex.org/W2916020270","https://openalex.org/W2917919349","https://openalex.org/W2942678593","https://openalex.org/W2946016273","https://openalex.org/W2948469692","https://openalex.org/W2949177718","https://openalex.org/W2949787092","https://openalex.org/W2949829455","https://openalex.org/W2951158909","https://openalex.org/W2951506174","https://openalex.org/W2951638683","https://openalex.org/W2951914955","https://openalex.org/W2952303649","https://openalex.org/W2952598125","https://openalex.org/W2955621471","https://openalex.org/W2966569571","https://openalex.org/W2971398276","https://openalex.org/W2971653850","https://openalex.org/W2973034691","https://openalex.org/W2984472267","https://openalex.org/W2984629040","https://openalex.org/W2997470228","https://openalex.org/W3003444384","https://openalex.org/W3013151148","https://openalex.org/W3037558964","https://openalex.org/W3088521497","https://openalex.org/W3117771127","https://openalex.org/W3205198892","https://openalex.org/W4233637541","https://openalex.org/W4256385088","https://openalex.org/W6745691576"],"related_works":["https://openalex.org/W4394426846","https://openalex.org/W4200033037","https://openalex.org/W4394543623","https://openalex.org/W3213655218","https://openalex.org/W4394560977","https://openalex.org/W4394488504","https://openalex.org/W4394163355","https://openalex.org/W3147425560","https://openalex.org/W2233436997","https://openalex.org/W2898732673"],"abstract_inverted_index":{"The":[0],"cell":[1,45,77,85,89,135,202],"type":[2,46],"identification":[3,47,132],"is":[4,138,233],"among":[5],"the":[6,37,63,108,122,126,131,142,159,201,217,223,249],"most":[7,120],"important":[8],"tasks":[9],"in":[10,16,119,174],"single-cell":[11],"RNA-sequencing":[12],"(scRNA-seq)":[13],"analysis.":[14],"Many":[15],"silico":[17],"methods":[18,48,124,144,189],"have":[19],"been":[20],"developed":[21],"and":[22,42,59,91,94,113,155,181,226],"can":[23],"be":[24,166,191],"roughly":[25],"categorized":[26],"as":[27,235],"either":[28],"supervised":[29,41,112,123,143,194],"or":[30],"unsupervised.":[31],"In":[32,185],"this":[33,175],"study,":[34,176],"we":[35,102],"investigated":[36,62,173],"performances":[38],"of":[39,54,65,68,73,76,97,111,133,219,244],"8":[40],"10":[43],"unsupervised":[44,114,127,188],"using":[49],"14":[50],"public":[51],"scRNA-seq":[52],"datasets":[53],"different":[55,207],"tissues,":[56],"sequencing":[57,79],"protocols":[58],"species.":[60],"We":[61,116],"impacts":[64,106],"a":[66,146,213,236],"number":[67,75],"factors,":[69],"including":[70],"total":[71],"amount":[72],"cells,":[74],"types,":[78],"depth,":[80],"batch":[81],"effects,":[82],"reference":[83,147,183],"bias,":[84],"population":[86],"imbalance,":[87],"unknown/novel":[88],"type,":[90],"computational":[92],"efficiency":[93],"scalability.":[95],"Instead":[96],"merely":[98],"comparing":[99],"individual":[100],"methods,":[101,128],"focused":[103],"on":[104,107],"factors'":[105],"general":[109,214],"category":[110],"methods.":[115,195,246],"found":[117],"that":[118,240],"scenarios,":[121,187],"outperformed":[125],"except":[129],"for":[130,216],"unknown":[134],"types.":[136],"This":[137],"particularly":[139],"true":[140],"when":[141],"use":[145],"dataset":[148,171,227],"with":[149],"high":[150,156],"informational":[151],"sufficiency,":[152],"low":[153],"complexity":[154],"similarity":[157],"to":[158,179,193,222],"query":[160],"dataset.":[161],"However,":[162],"such":[163],"outperformance":[164],"could":[165,190],"undermined":[167],"by":[168],"some":[169],"undesired":[170],"properties":[172],"which":[177],"lead":[178],"uninformative":[180],"biased":[182],"datasets.":[184],"these":[186],"comparable":[192],"Our":[196],"study":[197],"not":[198],"only":[199],"explained":[200],"typing":[203],"methods'":[204],"behaviors":[205],"under":[206],"experimental":[208],"settings":[209],"but":[210],"also":[211],"provided":[212],"guideline":[215],"choice":[218],"method":[220],"according":[221],"scientific":[224],"goal":[225],"properties.":[228],"Finally,":[229],"our":[230],"evaluation":[231,243],"workflow":[232],"implemented":[234],"modularized":[237],"R":[238],"pipeline":[239],"allows":[241],"future":[242],"new":[245],"Availability:":[247],"All":[248],"source":[250],"codes":[251],"are":[252],"available":[253],"at":[254],"https://github.com/xsun28/scRNAIdent.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}