{"id":"https://openalex.org/W7167817196","doi":"https://doi.org/10.1093/bioinformatics/btag506","title":"Cross-dataset annotation harmonization for cell-type hierarchy construction","display_name":"Cross-dataset annotation harmonization for cell-type hierarchy construction","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7167817196","doi":"https://doi.org/10.1093/bioinformatics/btag506","pmid":"https://pubmed.ncbi.nlm.nih.gov/42423286"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag506","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag506","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag506","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027561311","display_name":"Tianhong Zhou","orcid":"https://orcid.org/0000-0002-9537-8465"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhong Zhou","raw_affiliation_strings":["MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140347444","display_name":"Yixin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Chen","raw_affiliation_strings":["College of Biomedical Engineering, Fudan University , Shanghai 200438,"],"raw_orcid":"https://orcid.org/0000-0002-2946-5122","affiliations":[{"raw_affiliation_string":"College of Biomedical Engineering, Fudan University , Shanghai 200438,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103655091","display_name":"Zhu Y","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingtao Zhu","raw_affiliation_strings":["School of Medicine, Tsinghua Medicine, Tsinghua University , Beijing 100084,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Medicine, Tsinghua Medicine, Tsinghua University , Beijing 100084,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033877009","display_name":"Jinmeng Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinmeng Jia","raw_affiliation_strings":["MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I4210160507","display_name":"Center for Life Sciences","ror":"https://ror.org/05kje8j93","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570","https://openalex.org/I4210160507","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuegong Zhang","raw_affiliation_strings":["Center for Synthetic and Systems Biology, School of Life Sciences and School of Medicine, Tsinghua University , Beijing 100084,","MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,"],"raw_orcid":"https://orcid.org/0000-0002-9684-5643","affiliations":[{"raw_affiliation_string":"Center for Synthetic and Systems Biology, School of Life Sciences and School of Medicine, Tsinghua University , Beijing 100084,","institution_ids":["https://openalex.org/I4210160507","https://openalex.org/I99065089"]},{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140307296","display_name":"Lei Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wei","raw_affiliation_strings":["MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,"],"raw_orcid":"https://orcid.org/0000-0002-1546-6458","affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084,","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74262588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"7","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":0.9889000058174133,"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":0.9889000058174133,"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":0.007899999618530273,"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/T10885","display_name":"Gene expression and cancer classification","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8274000287055969},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7784000039100647},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.7343999743461609},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7311000227928162},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6080999970436096},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5521000027656555}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8274000287055969},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7784000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754999995231628},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.7343999743461609},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7311000227928162},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6080999970436096},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5521000027656555},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49900001287460327},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2863999903202057}],"mesh":[{"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":"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":"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","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":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag506","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag506","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42423286","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42423286","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13401821","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13401821/","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag506","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag506","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G367058354","display_name":null,"funder_award_id":"62\u00a0433\u00a0001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5881847713","display_name":null,"funder_award_id":"92470105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6074738754","display_name":null,"funder_award_id":"2024YFF0729203","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6722913013","display_name":null,"funder_award_id":"62373210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1976373002","https://openalex.org/W2089890078","https://openalex.org/W2462007197","https://openalex.org/W2612519453","https://openalex.org/W2739492614","https://openalex.org/W2766959028","https://openalex.org/W2794480084","https://openalex.org/W2796170779","https://openalex.org/W2800392236","https://openalex.org/W2800808913","https://openalex.org/W2895456557","https://openalex.org/W2922020904","https://openalex.org/W2931036699","https://openalex.org/W2949177718","https://openalex.org/W2949693884","https://openalex.org/W2950891712","https://openalex.org/W2951271761","https://openalex.org/W2951914955","https://openalex.org/W3025989739","https://openalex.org/W3040876684","https://openalex.org/W3110514822","https://openalex.org/W3121168830","https://openalex.org/W3163661434","https://openalex.org/W3173802674","https://openalex.org/W3196650609","https://openalex.org/W3212552860","https://openalex.org/W4282937885","https://openalex.org/W4297243391","https://openalex.org/W4307432965","https://openalex.org/W4320717228","https://openalex.org/W4327575912","https://openalex.org/W4379879135","https://openalex.org/W4384023988","https://openalex.org/W4385290032","https://openalex.org/W4390064086","https://openalex.org/W4392168151","https://openalex.org/W4399387478","https://openalex.org/W4401815196","https://openalex.org/W4402313775"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Single-cell":[1],"transcriptomic":[2],"datasets":[3,43,181],"annotate":[4],"cell":[5,39,49,75,160],"types":[6,76],"with":[7],"diverse":[8],"schemes":[9],"and":[10,22,44,60,70,77,95,104,147,156,179,195],"varying":[11],"resolution.":[12],"This":[13],"poses":[14],"challenges":[15],"in":[16,119,128,152,182],"building":[17],"unified":[18],"hierarchical":[19,157],"cell-type":[20,102,145,169],"structures":[21],"hinders":[23],"integration":[24],"of":[25,48],"large-scale":[26],"datasets.":[27,173],"To":[28,79],"address":[29],"this,":[30],"several":[31],"computational":[32],"methods":[33,65,116],"have":[34,124],"been":[35],"developed":[36,134],"to":[37],"harmonize":[38],"type":[40],"annotations":[41],"across":[42,66,74,172],"build":[45],"data-driven":[46],"hierarchies":[47,103],"types.":[50],"RESULTS:":[51],"Here,":[52],"we":[53,83,113,133],"benchmarked":[54],"three":[55,85],"state-of-the-art":[56],"methods:":[57],"scHPL,":[58],"treeArches,":[59],"CellHint.":[61],"We":[62],"evaluated":[63],"these":[64],"five":[67,71],"simulated":[68,120,178],"scenarios":[69,73,121],"real-world":[72,130,180],"organs.":[78],"assess":[80],"harmonization":[81,146],"results,":[82,112],"designed":[84],"metrics,":[86],"Annotation":[87],"Harmonization":[88],"F1-score":[89],"(AH-F1),":[90],"Tree":[91],"Edit":[92],"Distance":[93],"Similarity":[94],"Parent-Children":[96],"Branches":[97],"Similarity,":[98],"comparing":[99],"the":[100,105,110,168,183,193],"constructed":[101],"knowledge-based":[106],"ones.":[107],"Based":[108],"on":[109,139,187,200],"benchmarking":[111],"found":[114],"that":[115],"performed":[117],"well":[118],"but":[122],"still":[123],"room":[125],"for":[126,144,167,192],"improvement":[127],"complex":[129],"data.":[131],"Thus,":[132],"OTHarmonizer,":[135],"a":[136,163],"tool":[137],"based":[138],"partial":[140],"optimal":[141],"transport":[142],"(OT)":[143],"hierarchy":[148,170],"construction.":[149],"OTHarmonizer":[150,196],"excels":[151],"accurately":[153],"capturing":[154],"equivalent":[155],"relationships":[158],"between":[159],"types,":[161],"offering":[162],"more":[164],"effective":[165],"approach":[166],"construction":[171],"AVAILABILITY":[174],"AND":[175],"IMPLEMENTATION:":[176],"The":[177,189],"benchmark":[184,194],"are":[185,197],"available":[186,198],"https://figshare.com/articles/dataset/OTHarmonizer/28243205.":[188],"source":[190],"codes":[191],"online":[199],"GitHub":[201],"at":[202],"https://github.com/Duck-Boss/OTHarmonizer.":[203]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-07-10T00:00:00"}
