{"id":"https://openalex.org/W3090608751","doi":"https://doi.org/10.1101/2020.09.28.317594","title":"I-CONVEX: Fast and Accurate de Novo Transcriptome Recovery from Long Reads","display_name":"I-CONVEX: Fast and Accurate de Novo Transcriptome Recovery from Long Reads","publication_year":2020,"publication_date":"2020-10-01","ids":{"openalex":"https://openalex.org/W3090608751","doi":"https://doi.org/10.1101/2020.09.28.317594","mag":"3090608751"},"language":"en","primary_location":{"id":"doi:10.1101/2020.09.28.317594","doi":"https://doi.org/10.1101/2020.09.28.317594","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.09.28.317594","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/10/01/2020.09.28.317594.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2020/10/01/2020.09.28.317594.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080703858","display_name":"Sina Baharlouei","orcid":"https://orcid.org/0000-0003-1894-4483","observed_orcids":["https://orcid.org/0000-0003-1894-4483"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sina Baharlouei","raw_affiliation_strings":["Department of Industrial and Systems Engineering, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041237539","display_name":"Meisam Razaviyayn","orcid":"https://orcid.org/0000-0003-4342-6661","observed_orcids":["https://orcid.org/0000-0003-4342-6661"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meisam Razaviyayn","raw_affiliation_strings":["Department of Industrial and Systems Engineering, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055161576","display_name":"Elizabeth Tseng","orcid":"https://orcid.org/0000-0002-1074-5095","observed_orcids":["https://orcid.org/0000-0002-1074-5095"]},"institutions":[{"id":"https://openalex.org/I68554272","display_name":"Pacific Biosciences (United States)","ror":"https://ror.org/00fcszb13","country_code":"US","type":"company","lineage":["https://openalex.org/I68554272"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Tseng","raw_affiliation_strings":["Pacific Biosciences, Menlo Park, California, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Biosciences, Menlo Park, California, United States of America","institution_ids":["https://openalex.org/I68554272"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024072566","display_name":"David N. C. Tse","orcid":"https://orcid.org/0000-0003-1460-5900","observed_orcids":["https://orcid.org/0000-0003-1460-5900"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Tse","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080703858"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.0003000000142492354,"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/de-novo-transcriptome-assembly","display_name":"de novo transcriptome assembly","score":0.8960000276565552},{"id":"https://openalex.org/keywords/long-read-sequencing","display_name":"long-read sequencing","score":0.9049999713897705},{"id":"https://openalex.org/keywords/error-correction","display_name":"error correction","score":0.7350000143051147},{"id":"https://openalex.org/keywords/transcript-isoforms","display_name":"mRNA isoforms","score":0.6880000233650208}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6615234613418579},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6007322072982788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5880246758460999},{"id":"https://openalex.org/C53345823","wikidata":"https://www.wikidata.org/wiki/Q5531554","display_name":"Gene isoform","level":3,"score":0.542884111404419},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5345413088798523},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5036150813102722},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43230748176574707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4029022753238678},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27443835139274597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2730955481529236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21685433387756348},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1442294418811798},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12848088145256042},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2020.09.28.317594","doi":"https://doi.org/10.1101/2020.09.28.317594","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.09.28.317594","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/10/01/2020.09.28.317594.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2020.09.28.317594","doi":"https://doi.org/10.1101/2020.09.28.317594","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.09.28.317594","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/10/01/2020.09.28.317594.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3090608751.pdf","grobid_xml":"https://content.openalex.org/works/W3090608751.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W438799900","https://openalex.org/W958219903","https://openalex.org/W1502916507","https://openalex.org/W1579534339","https://openalex.org/W1944880632","https://openalex.org/W1981509058","https://openalex.org/W1990293955","https://openalex.org/W2047940964","https://openalex.org/W2109911015","https://openalex.org/W2117688129","https://openalex.org/W2132069633","https://openalex.org/W2141458291","https://openalex.org/W2154431984","https://openalex.org/W2233603983","https://openalex.org/W2312323279","https://openalex.org/W2337011385","https://openalex.org/W2463761386","https://openalex.org/W2886347923","https://openalex.org/W2899345312","https://openalex.org/W2950150251","https://openalex.org/W2952666313"],"related_works":["https://openalex.org/W3010772070","https://openalex.org/W4378234256","https://openalex.org/W4313454274","https://openalex.org/W3086120018","https://openalex.org/W4409696082","https://openalex.org/W4317553434","https://openalex.org/W3043509961","https://openalex.org/W2893222042","https://openalex.org/W7213942876","https://openalex.org/W2739626056"],"abstract_inverted_index":{"Long-read":[0],"sequencing":[1],"technologies":[2],"demonstrate":[3],"high":[4,15],"potential":[5],"for":[6],"de":[7],"novo":[8],"discovery":[9],"of":[10],"complex":[11],"transcript":[12],"isoforms,":[13],"but":[14],"error":[16,23],"rates":[17],"pose":[18],"a":[19,41],"significant":[20],"challenge.":[21],"Existing":[22],"correction":[24],"methods":[25],"rely":[26],"on":[27,31,62],"clustering":[28,50],"reads":[29],"based":[30],"isoform-level":[32],"alignment":[33],"and":[34,56,65],"cannot":[35],"be":[36],"efficiently":[37],"scaled.":[38],"We":[39],"propose":[40],"new":[42],"method,":[43],"I-CONVEX,":[44],"that":[45],"performs":[46],"fast,":[47],"alignment-free":[48],"isoform":[49],"with":[51],"almost":[52],"linear":[53],"computational":[54],"complexity,":[55],"leads":[57],"to":[58],"better":[59],"consensus":[60],"accuracy":[61],"simulated,":[63],"synthetic,":[64],"real":[66],"datasets.":[67]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2020-10-08T00:00:00"}
