{"id":"https://openalex.org/W3010772070","doi":"https://doi.org/10.1089/cmb.2019.0299","title":"De Novo Clustering of Long-Read Transcriptome Data Using a Greedy, Quality Value-Based Algorithm","display_name":"De Novo Clustering of Long-Read Transcriptome Data Using a Greedy, Quality Value-Based Algorithm","publication_year":2020,"publication_date":"2020-03-17","ids":{"openalex":"https://openalex.org/W3010772070","doi":"https://doi.org/10.1089/cmb.2019.0299","mag":"3010772070","pmid":"https://pubmed.ncbi.nlm.nih.gov/32181688","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/8884114"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2019.0299","doi":"https://doi.org/10.1089/cmb.2019.0299","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2019.0299","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2018/11/06/463463.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082939519","display_name":"Kristoffer Sahlin","orcid":"https://orcid.org/0000-0001-7378-2320","observed_orcids":["https://orcid.org/0000-0001-7378-2320"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kristoffer Sahlin","raw_affiliation_strings":["Department of Computer Science and Engineering and Pennsylvania State University, University Park, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X","observed_orcids":["https://orcid.org/0000-0003-3143-594X"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Center for Computational Biology and Bioinformatics, Pennsylvania State University, University Park, Pennsylvania","Department of Biochemistry and Molecular Biology, Pennsylvania State University, University Park, Pennsylvania","Department of Computer Science and Engineering and Pennsylvania State University, University Park, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology and Bioinformatics, Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082939519"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":4.0853,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.95879594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"27","issue":"4","first_page":"472","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965999722480774,"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":0.9965999722480774,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.001500000013038516,"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/T10604","display_name":"RNA Research and Splicing","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"}}],"keywords":[{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"greedy algorithm","score":0.6100000143051147},{"id":"https://openalex.org/keywords/quality-value","display_name":"quality value","score":0.6980000138282776},{"id":"https://openalex.org/keywords/error-rate","display_name":"error rate","score":0.4959999918937683},{"id":"https://openalex.org/keywords/pacbio-iso-seq","display_name":"PacBio Iso-Seq","score":0.9150000214576721},{"id":"https://openalex.org/keywords/oxford-nanopore","display_name":"Oxford Nanopore","score":0.9100000262260437},{"id":"https://openalex.org/keywords/protein-isoforms","display_name":"protein isoforms","score":0.6899999976158142},{"id":"https://openalex.org/keywords/gene-family-clustering","display_name":"gene family clustering","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7638964653015137},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7215936183929443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6916617155075073},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.68194979429245},{"id":"https://openalex.org/C126513998","wikidata":"https://www.wikidata.org/wiki/Q8973627","display_name":"Nanopore sequencing","level":4,"score":0.5436467528343201},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5057973861694336},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5036174654960632},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4963412880897522},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.22979167103767395},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22529089450836182},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2093939185142517},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11113622784614563},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10281634330749512},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09757637977600098},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1089/cmb.2019.0299","doi":"https://doi.org/10.1089/cmb.2019.0299","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2019.0299","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"doi:10.1101/463463","doi":"https://doi.org/10.1101/463463","is_oa":true,"landing_page_url":"https://doi.org/10.1101/463463","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2018/11/06/463463.full.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:8884114","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8884114","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,"listed_in":[],"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":"J Comput Biol","raw_type":"Text"},{"id":"pmid:32181688","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32181688","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,"listed_in":[],"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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1101/463463","doi":"https://doi.org/10.1101/463463","is_oa":true,"landing_page_url":"https://doi.org/10.1101/463463","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2018/11/06/463463.full.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1106789989","display_name":"Y Chromosome Evolution","funder_award_id":"R01GM130691","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2039187732","display_name":"ABI Innovation: A Novel Framework for Detecting Genomic Structural Variation","funder_award_id":"1356529","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3426846984","display_name":"III: Small: Reconstructing viral population without using a reference genome","funder_award_id":"1421908","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4106800444","display_name":"CAREER: De Novo Assembly of Large Genomic Data","funder_award_id":"1453527","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/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3010772070.pdf","grobid_xml":"https://content.openalex.org/works/W3010772070.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W958219903","https://openalex.org/W1987820419","https://openalex.org/W2024072609","https://openalex.org/W2041126213","https://openalex.org/W2070455968","https://openalex.org/W2105765411","https://openalex.org/W2110734043","https://openalex.org/W2116699248","https://openalex.org/W2116913753","https://openalex.org/W2120096459","https://openalex.org/W2124351063","https://openalex.org/W2138615112","https://openalex.org/W2142167651","https://openalex.org/W2144560237","https://openalex.org/W2145853890","https://openalex.org/W2149616469","https://openalex.org/W2150483253","https://openalex.org/W2156125289","https://openalex.org/W2164883482","https://openalex.org/W2170747616","https://openalex.org/W2260037449","https://openalex.org/W2415697913","https://openalex.org/W2597262405","https://openalex.org/W2602978558","https://openalex.org/W2608509736","https://openalex.org/W2617273082","https://openalex.org/W2688344404","https://openalex.org/W2739626056","https://openalex.org/W2747802896","https://openalex.org/W2751702521","https://openalex.org/W2751810028","https://openalex.org/W2789843538","https://openalex.org/W2802684988","https://openalex.org/W2805146307","https://openalex.org/W2893222042","https://openalex.org/W2898449026","https://openalex.org/W2899345312","https://openalex.org/W2950150251","https://openalex.org/W2950214184","https://openalex.org/W2950589160","https://openalex.org/W2950954328","https://openalex.org/W2952080813","https://openalex.org/W2953008890","https://openalex.org/W2953020124","https://openalex.org/W4235169531"],"related_works":["https://openalex.org/W4409696082","https://openalex.org/W7008986173","https://openalex.org/W2739626056","https://openalex.org/W2893222042","https://openalex.org/W4391517794","https://openalex.org/W2795256898","https://openalex.org/W4318465612","https://openalex.org/W4414379595","https://openalex.org/W4382631187","https://openalex.org/W4313454274"],"abstract_inverted_index":{"Abstract":[0],"Long-read":[1],"sequencing":[2],"of":[3,20,42,52,66,88,111,132],"transcripts":[4],"with":[5],"PacBio":[6],"Iso-Seq":[7],"and":[8,54,85,104,114],"Oxford":[9],"Nanopore":[10],"Technologies":[11],"has":[12],"proven":[13],"to":[14,17,62,83,93,137],"be":[15],"central":[16],"the":[18,40,50],"study":[19],"complex":[21],"isoform":[22],"landscapes":[23],"in":[24,130],"many":[25],"organisms.":[26],"However,":[27],"current":[28],"de":[29],"novo":[30],"transcript":[31],"reconstruction":[32],"algorithms":[33,56],"from":[34],"long-read":[35],"data":[36],"are":[37],"limited,":[38],"leaving":[39],"potential":[41],"these":[43],"technologies":[44],"unfulfilled.":[45],"A":[46],"common":[47],"bottleneck":[48],"is":[49,79,122,142],"dearth":[51],"scalable":[53],"accurate":[55],"for":[57],"clustering":[58,76],"long":[59],"reads":[60],"according":[61],"their":[63],"gene":[64],"family":[65],"origin.":[67],"To":[68],"address":[69],"this":[70],"challenge,":[71],"we":[72],"develop":[73],"isONclust,":[74],"a":[75,109,123],"algorithm":[77],"that":[78,120],"greedy":[80],"(in":[81,91],"order":[82,92],"scale)":[84],"makes":[86],"use":[87],"quality":[89],"values":[90],"handle":[94],"variable":[95],"error":[96],"rates).":[97],"We":[98],"test":[99],"isONclust":[100,121],"on":[101],"three":[102],"simulated":[103],"five":[105],"biological":[106],"datasets,":[107],"across":[108],"breadth":[110],"organisms,":[112],"technologies,":[113],"read":[115],"depths.":[116],"Our":[117,140],"results":[118],"demonstrate":[119],"substantial":[124],"improvement":[125],"over":[126],"previous":[127],"approaches,":[128],"both":[129],"terms":[131],"overall":[133],"accuracy":[134],"and/or":[135],"scalability":[136],"large":[138],"datasets.":[139],"tool":[141],"available":[143],"at":[144],"https://github.com/ksahlin/isONclust":[145],".":[146]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-03-23T00:00:00"}