{"id":"https://openalex.org/W7136763942","doi":"https://doi.org/10.1371/journal.pcbi.1014008","title":"A benchmark of semi-supervised scRNA-seq integration methods in real-world scenarios","display_name":"A benchmark of semi-supervised scRNA-seq integration methods in real-world scenarios","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7136763942","doi":"https://doi.org/10.1371/journal.pcbi.1014008","pmid":"https://pubmed.ncbi.nlm.nih.gov/41838767"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1014008","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1014008","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1014008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129403827","display_name":"Xiaoyu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Shen","raw_affiliation_strings":["Department of Statistics and Data Science, Yale University, New Haven, Connecticut, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Yale University, New Haven, Connecticut, United States of America","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129449608","display_name":"Chuan He","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuan He","raw_affiliation_strings":["Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6412-450X","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, United States of America","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129632107","display_name":"Leying Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leying Guan","raw_affiliation_strings":["Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, United States of America","Program in Computational Biology and Bioinformatics, Yale University, New Haven, Connecticut, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, United States of America","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Program in Computational Biology and Bioinformatics, Yale University, New Haven, Connecticut, United States of America","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":5.1191,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93641652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"3","first_page":"e1014008","last_page":"e1014008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9973000288009644,"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":0.9973000288009644,"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":0.0008999999845400453,"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"}},{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/robustness","display_name":"Robustness (evolution)","score":0.8585000038146973},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7175999879837036},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6018000245094299},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.3885999917984009},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.3231000006198883}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8585000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773000001907349},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7175999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6428999900817871},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5049999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.26660001277923584}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","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":"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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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},{"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":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1371/journal.pcbi.1014008","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1014008","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:41838767","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41838767","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13020996","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13020996/","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1014008","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1014008","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2612519453","https://openalex.org/W2769379242","https://openalex.org/W2773586544","https://openalex.org/W2794521141","https://openalex.org/W2794891507","https://openalex.org/W2887779955","https://openalex.org/W2901677030","https://openalex.org/W2905317377","https://openalex.org/W2907514116","https://openalex.org/W2922020904","https://openalex.org/W2942880491","https://openalex.org/W2949177718","https://openalex.org/W2949237386","https://openalex.org/W2950891712","https://openalex.org/W2965552103","https://openalex.org/W2971653850","https://openalex.org/W2973034691","https://openalex.org/W2984472267","https://openalex.org/W3002417351","https://openalex.org/W3092295864","https://openalex.org/W3124814274","https://openalex.org/W3132357920","https://openalex.org/W3134181354","https://openalex.org/W3164692211","https://openalex.org/W3165190053","https://openalex.org/W3174072032","https://openalex.org/W3196650609","https://openalex.org/W4214932646","https://openalex.org/W4220985590","https://openalex.org/W4225598893","https://openalex.org/W4235169531","https://openalex.org/W4283728503","https://openalex.org/W4295531497","https://openalex.org/W4321452463","https://openalex.org/W4377023457","https://openalex.org/W4378212544","https://openalex.org/W4379879135","https://openalex.org/W4385421874","https://openalex.org/W4389058627","https://openalex.org/W4391311741","https://openalex.org/W4403756780"],"related_works":[],"abstract_inverted_index":{"Semi-supervised":[0],"methods":[1,50,95],"for":[2],"single-cell":[3],"RNA-seq":[4],"integration":[5],"promise":[6],"improved":[7],"batch":[8],"correction":[9],"and":[10,22,80,83,112,123],"preservation":[11],"of":[12,24],"biological":[13],"signal":[14],"by":[15],"leveraging":[16],"cell-type":[17],"labels.":[18],"However,":[19],"reported":[20],"benefits":[21,98],"robustness":[23,103],"them":[25],"towards":[26],"imperfect":[27],"cell":[28],"type":[29],"labels":[30,79],"often":[31,104],"come":[32],"from":[33],"overly":[34],"idealized":[35],"settings.":[36],"Here":[37],"we":[38,69],"present,":[39],"to":[40],"our":[41],"knowledge,":[42],"the":[43,127],"first":[44],"systematic":[45],"benchmark":[46],"comparing":[47],"leading":[48],"semi-supervised":[49,94,136],"with":[51],"widely":[52],"used":[53],"unsupervised":[54,121,129],"approaches":[55],"across":[56],"six":[57],"diverse":[58],"datasets":[59],"under":[60,99,107],"realistic":[61,108],"conditions.":[62],"Beyond":[63],"randomly":[64],"missing":[65],"or":[66],"erroneous":[67],"labels,":[68,75],"examine":[70],"four":[71],"additional":[72],"scenarios":[73],"(boundary-mixed":[74],"batch-specific":[76],"annotations,":[77,101],"auto-generated":[78],"varied-granularity":[81],"labels)":[82],"evaluate":[84],"performance":[85],"using":[86],"nine":[87],"established":[88],"metrics.":[89],"We":[90],"find":[91],"that":[92,134],"although":[93],"can":[96],"provide":[97],"perfect":[100],"their":[102,120],"degrades":[105],"substantially":[106],"imperfections.":[109],"Only":[110],"scANVI":[111],"ssSTACAS":[113],"maintain":[114],"stable":[115],"but":[116],"modest":[117,146],"improvements":[118],"over":[119],"counterparts,":[122],"none":[124],"consistently":[125],"outperform":[126],"strongest":[128],"approach.":[130],"These":[131],"results":[132],"indicate":[133],"current":[135],"strategies":[137],"offer":[138],"limited":[139],"practical":[140],"advantage":[141],"when":[142],"label":[143],"quality":[144],"is":[145],"uncertain.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-17T00:00:00"}