{"id":"https://openalex.org/W4308364494","doi":"https://doi.org/10.1093/bioinformatics/btac720","title":"Vaeda computationally annotates doublets in single-cell RNA sequencing data","display_name":"Vaeda computationally annotates doublets in single-cell RNA sequencing data","publication_year":2022,"publication_date":"2022-11-05","ids":{"openalex":"https://openalex.org/W4308364494","doi":"https://doi.org/10.1093/bioinformatics/btac720","pmid":"https://pubmed.ncbi.nlm.nih.gov/36342203"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac720","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac720","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac720/48448959/btac720.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac720/48448959/btac720.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081411555","display_name":"Hannah Schriever","orcid":"https://orcid.org/0000-0002-9459-5548"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannah Schriever","raw_affiliation_strings":["Canegie Mellon\u2014University of Pittsburgh Joint PhD Program, University of Pittsburgh , Pittsburgh, PA 15201, USA","Department of Developmental Biology, University of Pittsburgh , Pittsburgh, PA 15201, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canegie Mellon\u2014University of Pittsburgh Joint PhD Program, University of Pittsburgh , Pittsburgh, PA 15201, USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"Department of Developmental Biology, University of Pittsburgh , Pittsburgh, PA 15201, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010346419","display_name":"Dennis Kostka","orcid":"https://orcid.org/0000-0002-1460-5487"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dennis Kostka","raw_affiliation_strings":["Department of Computational & Systems Biology and Center for Evolutionary Biology and Medicine, University of Pittsburgh , Pittsburgh, PA 15201, USA","Department of Developmental Biology, University of Pittsburgh , Pittsburgh, PA 15201, USA"],"raw_orcid":"https://orcid.org/0000-0002-1460-5487","affiliations":[{"raw_affiliation_string":"Department of Computational & Systems Biology and Center for Evolutionary Biology and Medicine, University of Pittsburgh , Pittsburgh, PA 15201, USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"Department of Developmental Biology, University of Pittsburgh , Pittsburgh, PA 15201, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010346419"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.5197,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.62324948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"39","issue":"1","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":0.9983999729156494,"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":0.9983999729156494,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.00019999999494757503,"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":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7914196252822876},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7781320810317993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7266181111335754},{"id":"https://openalex.org/keywords/barcode","display_name":"Barcode","score":0.6674864292144775},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5567097663879395},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45245134830474854},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4217376410961151},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.4136272668838501},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3675786256790161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3639378249645233},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3363184928894043},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2456410825252533},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16139081120491028},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14458626508712769}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7914196252822876},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7781320810317993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266181111335754},{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.6674864292144775},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5567097663879395},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45245134830474854},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4217376410961151},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.4136272668838501},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3675786256790161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3639378249645233},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3363184928894043},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2456410825252533},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16139081120491028},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14458626508712769},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"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":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","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":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","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":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac720","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac720","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac720/48448959/btac720.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"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:36342203","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36342203","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:9805559","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9805559","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac720","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac720","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac720/48448959/btac720.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"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/G3629156057","display_name":null,"funder_award_id":"5T32EB009403","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"}],"funders":[{"id":"https://openalex.org/F4320310174","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308364494.pdf","grobid_xml":"https://content.openalex.org/works/W4308364494.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2050871273","https://openalex.org/W2774307122","https://openalex.org/W2785085486","https://openalex.org/W2800392236","https://openalex.org/W2817838603","https://openalex.org/W2897249806","https://openalex.org/W2951068818","https://openalex.org/W2951506174","https://openalex.org/W2953151710","https://openalex.org/W2972480532","https://openalex.org/W3037482866","https://openalex.org/W3106188259","https://openalex.org/W3113268000","https://openalex.org/W3123418868","https://openalex.org/W3183469109","https://openalex.org/W3183815066","https://openalex.org/W3203240306","https://openalex.org/W3208540095"],"related_works":["https://openalex.org/W2256570403","https://openalex.org/W2074156223","https://openalex.org/W2103246366","https://openalex.org/W2901653204","https://openalex.org/W2102526470","https://openalex.org/W4378447789","https://openalex.org/W2613659923","https://openalex.org/W3207557903","https://openalex.org/W2803056468","https://openalex.org/W1980504858"],"abstract_inverted_index":{"MOTIVATION:":[0],"Single-cell":[1],"RNA":[2],"sequencing":[3],"(scRNA-seq)":[4],"continues":[5],"to":[6,85,123,141],"expand":[7],"our":[8],"knowledge":[9],"by":[10,54],"facilitating":[11],"the":[12,18,55,187,201,205],"study":[13],"of":[14,20,43,110,153,183,189],"transcriptional":[15,70],"heterogeneity":[16],"at":[17,198,212,221],"level":[19],"single":[21,64],"cells.":[22],"Despite":[23],"this":[24,67,81],"technology's":[25],"utility":[26],"and":[27,58,75,87,120,127,145,156,173,180,200],"success":[28],"in":[29,36,112,151,186],"biomedical":[30],"research,":[31],"technical":[32],"artifacts":[33],"are":[34,40,52,93,219],"present":[35,208],"scRNA-seq":[37,91,113,177],"data.":[38,114],"Doublets/multiplets":[39],"a":[41,63,104,117,171],"type":[42],"artifact":[44],"that":[45,147],"occurs":[46],"when":[47],"two":[48],"or":[49],"more":[50],"cells":[51],"tagged":[53],"same":[56],"barcode,":[57],"therefore":[59],"they":[60],"appear":[61],"as":[62],"cell.":[65],"Because":[66],"introduces":[68],"non-existent":[69],"profiles,":[71],"doublets":[72,89,111],"can":[73],"bias":[74],"mislead":[76],"downstream":[77],"analysis.":[78],"To":[79],"address":[80],"limitation,":[82],"computational":[83,108],"methods":[84,164],"annotate":[86],"remove":[88],"form":[90],"datasets":[92,144],"needed.":[94],"RESULTS:":[95],"We":[96,131],"introduce":[97],"vaeda":[98,148,160,169],"(Variational":[99],"Auto-Encoder":[100],"for":[101,107,165,176,204],"Doublet":[102],"Annotation),":[103],"new":[105],"approach":[106],"annotation":[109,139,179],"Vaeda":[115,195],"integrates":[116],"variational":[118],"auto-encoder":[119],"Positive-Unlabeled":[121],"learning":[122],"produce":[124],"doublet":[125,129,138,154,157,166,178],"scores":[126,155],"binary":[128],"calls.":[130,158],"apply":[132],"vaeda,":[133],"along":[134],"with":[135],"seven":[136],"existing":[137],"methods,":[140],"16":[142],"benchmark":[143],"find":[146],"performs":[149],"competitively":[150],"terms":[152],"Notably,":[159],"outperforms":[161],"other":[162],"python-based":[163,190],"annotation.":[167],"Altogether,":[168],"is":[170,196,210],"robust":[172],"competitive":[174],"method":[175],"may":[181],"be":[182],"particular":[184],"interest":[185],"context":[188],"workflows.":[191],"AVAILABILITY":[192],"AND":[193],"IMPLEMENTATION:":[194],"available":[197,220],"https://github.com/kostkalab/vaeda,":[199],"version":[202],"used":[203],"results":[206],"we":[207],"here":[209],"archived":[211],"zenodo":[213],"(https://doi.org/10.5281/zenodo.7199783).":[214],"SUPPLEMENTARY":[215],"INFORMATION:":[216],"Supplementary":[217],"data":[218],"Bioinformatics":[222],"online.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
