{"id":"https://openalex.org/W7134897903","doi":"https://doi.org/10.1093/bioinformatics/btag117","title":"Souporcell3: robust demultiplexing for high-donor single-cell RNA-seq datasets","display_name":"Souporcell3: robust demultiplexing for high-donor single-cell RNA-seq datasets","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7134897903","doi":"https://doi.org/10.1093/bioinformatics/btag117","pmid":"https://pubmed.ncbi.nlm.nih.gov/41808435"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag117","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag117","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/btag117","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076204928","display_name":"Minindu Weerakoon","orcid":"https://orcid.org/0009-0007-0237-2376"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minindu Weerakoon","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,"],"raw_orcid":"https://orcid.org/0009-0007-0237-2376","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hai Vu","orcid":"https://orcid.org/0009-0002-2876-6190"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hai Vu","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,"],"raw_orcid":"https://orcid.org/0009-0002-2876-6190","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051266995","display_name":"Reza Behboudi","orcid":"https://orcid.org/0009-0009-2604-3854"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reza Behboudi","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060528195","display_name":"Haynes Heaton","orcid":"https://orcid.org/0000-0002-9649-525X"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haynes Heaton","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,"],"raw_orcid":"https://orcid.org/0000-0002-9649-525X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University , Auburn, AL 36849,","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060528195"],"corresponding_institution_ids":["https://openalex.org/I82497590"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.253758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","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":0.9990000128746033,"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":0.9990000128746033,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.0003000000142492354,"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"}},{"id":"https://openalex.org/T11297","display_name":"Ferroptosis and cancer prognosis","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.4740999937057495},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44130000472068787},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33329999446868896},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.301800012588501},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.24959999322891235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343999743461609},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47200000286102295},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36629998683929443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.24959999322891235},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.24220000207424164}],"mesh":[{"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":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098430","descriptor_name":"Clustering Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098430","descriptor_name":"Clustering 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":"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":"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":"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":"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":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":"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}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag117","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag117","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:41808435","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41808435","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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13012599","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13012599/","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/btag117","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag117","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":[{"display_name":"Zero hunger","score":0.43991124629974365,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1965650377","https://openalex.org/W2033403400","https://openalex.org/W2086959852","https://openalex.org/W2160039585","https://openalex.org/W2995043840","https://openalex.org/W2997393200","https://openalex.org/W3023290106","https://openalex.org/W3114078084","https://openalex.org/W3134873297","https://openalex.org/W4235169531","https://openalex.org/W4414553388"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Accurate":[1],"demultiplexing":[2,52,82],"of":[3,78,81,104,109],"pooled":[4],"single-cell":[5],"RNA-seq":[6],"(scRNA-seq)":[7],"data":[8,62],"is":[9,150],"critical":[10],"for":[11,92,96],"large-scale":[12],"studies.":[13],"However,":[14],"existing":[15],"methods":[16,55],"like":[17],"vireo,":[18,114,116],"while":[19],"effective":[20],"up":[21,83],"to":[22,31,59,84,113],"\u223c16":[23],"donors,":[24],"often":[25],"struggle":[26],"with":[27,102],"poor":[28],"clustering":[29],"due":[30],"local":[32],"optima":[33],"as":[34,68],"donor":[35],"numbers":[36],"rise.":[37],"In":[38],"high-donor":[39],"scenarios,":[40],"overlapping":[41],"genotypes,":[42],"a":[43],"dense":[44],"genotype":[45],"space,":[46],"and":[47,63,99,107,117,128,144],"increased":[48],"doublet":[49,139],"formation":[50],"make":[51],"challenging,":[53],"requiring":[54],"that":[56],"are":[57],"robust":[58,97],"sparse,":[60],"high-dimensional":[61],"maintain":[64],"reliable":[65],"accuracy":[66,143],"even":[67],"sample":[69],"complexity":[70],"grows.":[71],"RESULTS:":[72],"We":[73],"present":[74],"an":[75],"enhanced":[76],"version":[77],"souporcell":[79],"capable":[80],"64":[85],"donors.":[86],"The":[87],"method":[88],"uses":[89],"10\u00d7":[90],"merge":[91],"initialization,":[93],"K-Harmonic":[94],"Means":[95],"clustering,":[98],"iterative":[100],"refinement":[101],"reinitialization":[103],"low-quality":[105],"clusters":[106,127],"locking":[108],"high-quality":[110],"ones.":[111],"Compared":[112],"overclustered":[115],"the":[118,154],"original":[119],"souporcell,":[120],"our":[121],"approach":[122],"completely":[123],"eliminates":[124],"incorrectly":[125],"merged":[126],"achieves":[129],"consistently":[130],"high":[131],"Adjusted":[132],"Rand":[133],"Index":[134],"(ARI)":[135],"scores":[136],"across":[137],"various":[138],"rates,":[140],"demonstrating":[141],"improved":[142],"scalability.":[145],"AVAILABILITY":[146],"AND":[147],"IMPLEMENTATION:":[148],"Souporcell3":[149],"freely":[151],"available":[152],"under":[153],"MIT":[155],"open-source":[156],"license":[157],"at":[158],"https://github.com/wheaton5/souporcell.":[159]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-03-12T00:00:00"}
