{"id":"https://openalex.org/W7225749206","doi":"https://doi.org/10.64898/2026.11.08.764985","title":"ProClust provides reliable statistical significance of clusters for single-cell transcriptomic data","display_name":"ProClust provides reliable statistical significance of clusters for single-cell transcriptomic data","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225749206","doi":"https://doi.org/10.64898/2026.11.08.764985"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.08.764985","doi":"https://doi.org/10.64898/2026.11.08.764985","is_oa":false,"landing_page_url":"https://doi.org/10.64898/2026.11.08.764985","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"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/A5161372112","display_name":"Haina Qian","orcid":"https://orcid.org/0009-0005-6251-2583","observed_orcids":["https://orcid.org/0009-0005-6251-2583"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haina Qian","raw_affiliation_strings":["University of Michigan;"],"raw_orcid":"https://orcid.org/0009-0005-6251-2583","affiliations":[{"raw_affiliation_string":"University of Michigan;","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161418359","display_name":"Haoze Wu","orcid":"https://orcid.org/0009-0006-4112-5151","observed_orcids":["https://orcid.org/0009-0006-4112-5151"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoze Wu","raw_affiliation_strings":["University of Michigan;"],"raw_orcid":"https://orcid.org/0009-0006-4112-5151","affiliations":[{"raw_affiliation_string":"University of Michigan;","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035129631","display_name":"Yifan Dai","orcid":"https://orcid.org/0000-0001-7897-5228","observed_orcids":["https://orcid.org/0000-0001-7897-5228"]},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Dai","raw_affiliation_strings":["University of North Carolina at Chapel Hill;"],"raw_orcid":"https://orcid.org/0000-0001-7897-5228","affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill;","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058221612","display_name":"Guanao Yan","orcid":"https://orcid.org/0000-0002-6861-1882","observed_orcids":["https://orcid.org/0000-0002-6861-1882"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanao Yan","raw_affiliation_strings":["Michigan State University"],"raw_orcid":"https://orcid.org/0000-0002-6861-1882","affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100376614","display_name":"Yufeng Liu","orcid":"https://orcid.org/0000-0002-1686-0545","observed_orcids":["https://orcid.org/0000-0002-1686-0545"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufeng Liu","raw_affiliation_strings":["University of Michigan;"],"raw_orcid":"https://orcid.org/0000-0002-1686-0545","affiliations":[{"raw_affiliation_string":"University of Michigan;","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7835999727249146},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6636999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5601000189781189},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5547999739646912},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C63085389","wikidata":"https://www.wikidata.org/wiki/Q4287912","display_name":"Medoid","level":3,"score":0.4627000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.33169999718666077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C120639","wikidata":"https://www.wikidata.org/wiki/Q7068958","display_name":"Null distribution","level":4,"score":0.32030001282691956},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.3012000024318695},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.28769999742507935},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2732999920845032},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25119999051094055},{"id":"https://openalex.org/C120577422","wikidata":"https://www.wikidata.org/wiki/Q843558","display_name":"Alternative hypothesis","level":3,"score":0.25040000677108765},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.08.764985","doi":"https://doi.org/10.64898/2026.11.08.764985","is_oa":false,"landing_page_url":"https://doi.org/10.64898/2026.11.08.764985","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clustering":[0],"of":[1,30,37,113,139],"single-cell":[2],"RNA":[3],"sequencing":[4],"(scRNA-seq)":[5],"data":[6],"is":[7,39,95,206],"widely":[8],"used":[9],"to":[10,27,42,73,98],"identify":[11],"cell":[12,20,31],"populations.":[13,141],"However,":[14],"overclustering":[15,107,196],"can":[16,81],"partition":[17],"a":[18,50,61,65,70,186],"single":[19,62],"population":[21,134],"into":[22],"multiple":[23],"clusters,":[24],"potentially":[25],"leading":[26],"spurious":[28],"identification":[29],"subpopulations.":[32],"Assessing":[33],"the":[34,100,110,132,147],"statistical":[35,51],"significance":[36,55],"clusters":[38,92],"therefore":[40],"needed":[41],"support":[43],"their":[44],"biological":[45],"interpretation.":[46],"We":[47],"propose":[48],"ProClust,":[49],"test":[52],"for":[53,87,177,192],"clustering":[54,75,158],"in":[56],"scRNA-seq":[57,144],"data.":[58],"ProClust":[59,90,121,156,184,203],"defines":[60],"cluster":[63],"as":[64],"log-concave":[66],"distribution":[67],"and":[68,117,154,171,189,197],"adopts":[69],"projection-based":[71],"approach":[72],"quantify":[74],"uncertainty":[76],"through":[77],"p-values.":[78],"These":[79],"projections":[80],"also":[82],"provide":[83],"interpretable":[84,190],"visual":[85],"evidence":[86,97,176],"individual":[88],"clusterings.":[89],"merges":[91],"when":[93],"there":[94],"insufficient":[96,175],"reject":[99],"single-cluster":[101],"null":[102,127],"hypothesis,":[103],"refining":[104,193],"an":[105,194],"initial":[106,195],"without":[108],"prespecifying":[109],"final":[111],"number":[112],"clusters.":[114],"Across":[115],"parametric":[116],"PBMC-based":[118],"semi-synthetic":[119],"simulations,":[120],"avoided":[122],"false":[123],"subdivisions":[124],"under":[125],"single-population":[126],"settings":[128],"while":[129,167],"consistently":[130],"recovering":[131],"underlying":[133],"structure":[135],"across":[136],"different":[137],"numbers":[138],"true":[140],"In":[142],"real":[143],"datasets":[145],"from":[146],"Human":[148],"Lung":[149],"Cell":[150],"Atlas,":[151],"Tabula":[152],"Muris,":[153],"Hydra,":[155],"produced":[157],"solutions":[159],"that":[160,183],"showed":[161],"overall":[162],"agreement":[163],"with":[164,174],"reference":[165],"annotations":[166],"retaining":[168],"supported":[169,199],"substructure":[170],"merging":[172],"groups":[173],"separation.":[178],"Together,":[179],"these":[180],"results":[181],"demonstrate":[182],"provides":[185],"statistically":[187],"principled":[188],"framework":[191],"distinguishing":[198],"cellular":[200],"heterogeneity.":[201],"The":[202],"R":[204],"package":[205],"available":[207],"at":[208],"https://github.com/Anonym027/ProClust.":[209]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}