{"id":"https://openalex.org/W3129725981","doi":"https://doi.org/10.1093/bib/bbab034","title":"Accurate feature selection improves single-cell RNA-seq cell clustering","display_name":"Accurate feature selection improves single-cell RNA-seq cell clustering","publication_year":2021,"publication_date":"2021-01-25","ids":{"openalex":"https://openalex.org/W3129725981","doi":"https://doi.org/10.1093/bib/bbab034","mag":"3129725981","pmid":"https://pubmed.ncbi.nlm.nih.gov/33611426"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbab034","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab034","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8644062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060121625","display_name":"Kenong Su","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenong Su","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA 30322, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA 30322, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016835023","display_name":"Tianwei Yu","orcid":"https://orcid.org/0000-0003-2502-1628"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianwei Yu","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083170497","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0003-1269-7354"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Department of Biostatistics and Bioinformatics, Emory University, 201 Dowman Dr, Atlanta, GA 30322, USA"],"raw_orcid":"https://orcid.org/0000-0003-1269-7354","affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Bioinformatics, Emory University, 201 Dowman Dr, Atlanta, GA 30322, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083170497"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":4.7384,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.96486261,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"22","issue":"5","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":0.9726999998092651,"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/T10773","display_name":"Extracellular vesicles in disease","score":0.9574000239372253,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8948120474815369},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6722812652587891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6628631353378296},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.589067816734314},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5817484259605408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5507088303565979},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5057733058929443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5036467909812927},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49333325028419495},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4800640046596527},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.4463026523590088},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.34198498725891113}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8948120474815369},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6722812652587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628631353378296},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.589067816734314},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5817484259605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507088303565979},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5057733058929443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5036467909812927},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49333325028419495},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4800640046596527},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.4463026523590088},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.34198498725891113},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"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":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","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":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","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":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},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbab034","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab034","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33611426","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33611426","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8644062","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8644062","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8644062","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8644062","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2973095053","display_name":null,"funder_award_id":"R01GM124061","funder_id":"https://openalex.org/F4320334944","funder_display_name":"Shenzhen Graduate School, Peking University"},{"id":"https://openalex.org/G4978443175","display_name":null,"funder_award_id":"R01 GM122083","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G5092685581","display_name":null,"funder_award_id":"P50 AG025688","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G6188594240","display_name":null,"funder_award_id":"P50AG025688","funder_id":"https://openalex.org/F4320334944","funder_display_name":"Shenzhen Graduate School, Peking University"},{"id":"https://openalex.org/G6207237116","display_name":null,"funder_award_id":"R01GM122083","funder_id":"https://openalex.org/F4320334944","funder_display_name":"Shenzhen Graduate School, Peking University"},{"id":"https://openalex.org/G7211878532","display_name":null,"funder_award_id":"R01 GM124061","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334944","display_name":"Shenzhen Graduate School, Peking University","ror":"https://ror.org/02v51f717"},{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1580018887","https://openalex.org/W1685464609","https://openalex.org/W1975900269","https://openalex.org/W1984883254","https://openalex.org/W1987971958","https://openalex.org/W2019552331","https://openalex.org/W2030644393","https://openalex.org/W2069089843","https://openalex.org/W2086320398","https://openalex.org/W2102212449","https://openalex.org/W2118258530","https://openalex.org/W2135937351","https://openalex.org/W2193667971","https://openalex.org/W2295278941","https://openalex.org/W2343956310","https://openalex.org/W2373831850","https://openalex.org/W2561508962","https://openalex.org/W2598326928","https://openalex.org/W2605611918","https://openalex.org/W2620676965","https://openalex.org/W2763879419","https://openalex.org/W2774644977","https://openalex.org/W2796170779","https://openalex.org/W2800392236","https://openalex.org/W2806122497","https://openalex.org/W2884197618","https://openalex.org/W2888562574","https://openalex.org/W2900387735","https://openalex.org/W2901677030","https://openalex.org/W2910366648","https://openalex.org/W2916020270","https://openalex.org/W2949236943","https://openalex.org/W2951444558","https://openalex.org/W2951506174","https://openalex.org/W2951914955","https://openalex.org/W2952027905","https://openalex.org/W2953251392","https://openalex.org/W2954610188","https://openalex.org/W2970227992","https://openalex.org/W2984644935","https://openalex.org/W2989716250","https://openalex.org/W2990138404","https://openalex.org/W2996274328","https://openalex.org/W2997280954","https://openalex.org/W2998065416","https://openalex.org/W3003444384","https://openalex.org/W3009302866","https://openalex.org/W3016020856","https://openalex.org/W3111977710","https://openalex.org/W4213009331","https://openalex.org/W4233637541","https://openalex.org/W4235169531","https://openalex.org/W4285719527","https://openalex.org/W6637461618","https://openalex.org/W6774097251"],"related_works":["https://openalex.org/W1574003721","https://openalex.org/W2311450085","https://openalex.org/W2804957450","https://openalex.org/W2163488696","https://openalex.org/W3197105638","https://openalex.org/W4232587025","https://openalex.org/W3168918549","https://openalex.org/W2060220440","https://openalex.org/W2309230723","https://openalex.org/W2804498673"],"abstract_inverted_index":{"Cell":[0],"clustering":[1,24,73,78,116,154,159],"is":[2,25],"one":[3],"of":[4,30,49,63,99,111],"the":[5,53,61,72,96,109,137,158],"most":[6],"important":[7,20],"and":[8,60,144],"commonly":[9],"performed":[10],"tasks":[11],"in":[12,22],"single-cell":[13],"RNA":[14],"sequencing":[15],"(scRNA-seq)":[16],"data":[17],"analysis.":[18],"An":[19],"step":[21,84],"cell":[23,58,115],"to":[26,33],"select":[27],"a":[28,68,81,122],"subset":[29],"genes":[31],"(referred":[32],"as":[34],"'features'),":[35],"whose":[36],"expression":[37,101],"patterns":[38],"will":[39],"then":[40],"be":[41],"used":[42],"for":[43],"downstream":[44],"clustering.":[45],"A":[46],"good":[47],"set":[48,65],"features":[50,148],"should":[51],"include":[52,80],"ones":[54],"that":[55,146],"distinguish":[56],"different":[57],"types,":[59],"quality":[62],"such":[64],"could":[66],"have":[67],"significant":[69],"impact":[70,110],"on":[71,86,95,114,139],"accuracy.":[74,117,160],"All":[75],"existing":[76,153],"scRNA-seq":[77,142],"tools":[79,155],"feature":[82,90,112,123],"selection":[83,91,113,124],"relying":[85],"some":[87],"simple":[88],"unsupervised":[89],"methods,":[92],"mostly":[93],"based":[94],"statistical":[97],"moments":[98],"gene-wise":[100],"distributions.":[102],"In":[103,118],"this":[104],"work,":[105],"we":[106,120],"carefully":[107],"evaluate":[108],"addition,":[119],"develop":[121],"algorithm":[125],"named":[126],"FEAture":[127],"SelecTion":[128],"(FEAST),":[129],"which":[130],"provides":[131],"more":[132],"representative":[133],"features.":[134],"We":[135],"apply":[136],"method":[138],"12":[140],"public":[141],"datasets":[143],"demonstrate":[145],"using":[147],"selected":[149],"by":[150],"FEAST":[151],"with":[152],"significantly":[156],"improve":[157]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}