{"id":"https://openalex.org/W3178303611","doi":"https://doi.org/10.1093/bioinformatics/btab315","title":"Practical selection of representative sets of RNA-seq samples using a hierarchical approach","display_name":"Practical selection of representative sets of RNA-seq samples using a hierarchical approach","publication_year":2021,"publication_date":"2021-04-30","ids":{"openalex":"https://openalex.org/W3178303611","doi":"https://doi.org/10.1093/bioinformatics/btab315","mag":"3178303611","pmid":"https://pubmed.ncbi.nlm.nih.gov/34252927"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab315","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab315","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i334/39620219/btab315.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/37/Supplement_1/i334/39620219/btab315.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003422267","display_name":"Laura H. Tung","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura H Tung","raw_affiliation_strings":["Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113653378","display_name":"Carl Kingsford","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113653378"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0793,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.42266515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"37","issue":"Supplement_1","first_page":"i334","last_page":"i341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.854200005531311,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.854200005531311,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.03180000185966492,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.01510000042617321,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.643007755279541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6332908868789673},{"id":"https://openalex.org/keywords/rna-seq","display_name":"RNA-Seq","score":0.47804123163223267},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4251924157142639},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.32770025730133057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30212539434432983},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15309354662895203},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10170480608940125},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.06394967436790466},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.053741395473480225}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.643007755279541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6332908868789673},{"id":"https://openalex.org/C107397762","wikidata":"https://www.wikidata.org/wiki/Q2542347","display_name":"RNA-Seq","level":5,"score":0.47804123163223267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4251924157142639},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32770025730133057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30212539434432983},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15309354662895203},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10170480608940125},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.06394967436790466},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.053741395473480225},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081246","descriptor_name":"RNA-Seq","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":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":"D000465","descriptor_name":"Algorithms","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab315","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab315","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i334/39620219/btab315.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:34252927","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34252927","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:8275344","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8275344","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/btab315","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab315","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i334/39620219/btab315.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/G2917921242","display_name":null,"funder_award_id":"DGE1745016","funder_id":"https://openalex.org/F4562087700","funder_display_name":"National Science Foundation Graduate Research Fellowship Program"},{"id":"https://openalex.org/G3023850491","display_name":null,"funder_award_id":"R01GM122935","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5836720286","display_name":null,"funder_award_id":"R01 GM122935","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6667550415","display_name":"IIBR:Informatics:Toward an Automated RNA-seq Bioinformatician","funder_award_id":"1937540","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4562087700","display_name":"National Science Foundation Graduate Research Fellowship Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3178303611.pdf","grobid_xml":"https://content.openalex.org/works/W3178303611.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1590776313","https://openalex.org/W1966872876","https://openalex.org/W1974834807","https://openalex.org/W2036288429","https://openalex.org/W2092927559","https://openalex.org/W2096128575","https://openalex.org/W2116041602","https://openalex.org/W2138002832","https://openalex.org/W2151537585","https://openalex.org/W2160754664","https://openalex.org/W2165232124","https://openalex.org/W2168561568","https://openalex.org/W2907815526","https://openalex.org/W2948852427","https://openalex.org/W2949681238","https://openalex.org/W3086834003","https://openalex.org/W6642027795","https://openalex.org/W6680496891","https://openalex.org/W6763169275"],"related_works":["https://openalex.org/W4200033037","https://openalex.org/W3213655218","https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W3147425560","https://openalex.org/W2233436997","https://openalex.org/W3018517591","https://openalex.org/W4254856796","https://openalex.org/W2265065644","https://openalex.org/W1971332228"],"abstract_inverted_index":{"MOTIVATION:":[0],"Despite":[1],"numerous":[2],"RNA-seq":[3,10,20,36,67,76,96,235],"samples":[4,37,77,97,156,207],"available":[5,35,75,258,268],"at":[6,259,269],"large":[7,72,100,247],"databases,":[8],"most":[9],"analysis":[11],"tools":[12],"are":[13,267],"evaluated":[14],"on":[15,63,229,246],"a":[16,24,30,54,60,99,124,142,239],"limited":[17,118],"number":[18],"of":[19,43,70,74,79,95,174,186,234],"samples.":[21],"This":[22],"drives":[23],"need":[25],"for":[26,49,91,201],"methods":[27],"to":[28,38,133,172,193,242],"select":[29],"representative":[31,50,113,130,138,147,155,164,176,222,243],"subset":[32,61,216],"from":[33],"all":[34],"facilitate":[39],"comprehensive,":[40],"unbiased":[41],"evaluation":[42],"bioinformatics":[44],"tools.":[45],"In":[46],"sequence-based":[47],"approaches":[48],"set":[51,94,114,131,139,148,165,177,223,233,244],"selection":[52,115,140,149,166,224,245],"(e.g.":[53,102],"k-mer":[55,64],"counting":[56],"approach":[57],"that":[58,145,162,173,209,220],"selects":[59,154],"based":[62],"similarities":[65],"between":[66],"samples),":[68],"because":[69],"the":[71,85,92,103,188,230,250],"numbers":[73],"and":[78,107,152,183,197,204,261],"k-mers/sequences":[80,90],"in":[81,98],"each":[82],"sample,":[83],"computing":[84,119,187],"full":[86,189],"similarity":[87,190],"matrix":[88,191],"using":[89],"entire":[93,231],"database":[101],"SRA)":[104],"has":[105],"memory":[106,184,199],"runtime":[108,182,195],"challenges;":[109],"this":[110,135],"makes":[111],"direct":[112,175,215],"infeasible":[116],"with":[117,214],"resources.":[120],"RESULTS:":[121],"We":[122,160,218],"developed":[123],"novel":[125],"computational":[126],"method":[127],"called":[128],"'hierarchical":[129],"selection'":[132],"handle":[134],"challenge.":[136],"Hierarchical":[137],"is":[141,257],"divide-and-conquer-like":[143],"algorithm":[144],"breaks":[146],"into":[150],"sub-selections":[151],"hierarchically":[153],"through":[157],"multiple":[158],"levels.":[159],"demonstrate":[161],"hierarchical":[163,221],"can":[167],"achieve":[168],"summarization":[169],"quality":[170],"close":[171],"selection,":[178],"while":[179],"largely":[180],"reducing":[181],"requirements":[185],"(up":[192],"8.4\u00d7":[194],"reduction":[196,200],"5.35\u00d7":[198],"10":[202],"000":[203,206],"12":[205],"respectively":[208],"could":[210],"be":[211],"practically":[212],"run":[213],"selection).":[217],"show":[219],"substantially":[225],"outperforms":[226],"random":[227],"sampling":[228],"SRA":[232],"samples,":[236],"making":[237],"it":[238],"practical":[240],"solution":[241],"databases":[248],"like":[249],"SRA.":[251],"AVAILABILITY":[252],"AND":[253],"IMPLEMENTATION:":[254],"The":[255],"code":[256],"https://github.com/Kingsford-Group/hierrepsetselection":[260],"https://github.com/Kingsford-Group/jellyfishsim.":[262],"SUPPLEMENTARY":[263],"INFORMATION:":[264],"Supplementary":[265],"data":[266],"Bioinformatics":[270],"online.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}